[{"id":"doi:10.1016/j.apmt.2025.102916","name":"Analysis of resistive switching properties in TiO2-based RRAM device for neuromorphic computing applications","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.apmt.2025.102916","authors":["Usman Isyaku Bature","Haider Abbas","Ali Alzahrani","Arshid Nisar","Faisal Bashir","Furqan Zahoor"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-23T07:33:08Z","doi":"10.1016/j.apmt.2025.102916","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1063/5.0257074","name":"Inversion-sensing SiO2-based MOS capacitive synapse for neuromorphic computing","source":"crossref","abstract":"In this work, an inversion-sensing SiO2-based capacitive synapse device was introduced by using the lateral coupling effect in a concentric metal–oxide–semiconductor structure. The device achieved a CHCS/CLCS ratio of 24 with a low programming voltage of VPGM = −2.5 V. Technology Computer Aided Design (TCAD) simulations confirmed the device's high sensitivity to changes in external charges. For oxide with an effective positive charge density (Neff) exceeding 2.8×1011 cm−2, a small variation of 5×109 cm−2 could influence a lot in the capacitance value of the device in the inversion region. This sensitivity enabled multi-state capacitance modulation by adjusting the number of pulses and operating voltages. Additionally, the scalability of the device was validated through simulations. The on/off ratio could be further improved by substituting the gate dielectric material. Overall, the lateral coupling effect not only enhances the performance of charge-trapping-based devices but also provides a viable strategy for expanding memory windows across various types of capacitive memory technologies.","url":"https://doi.org/10.1063/5.0257074","authors":["Chi-Yi Kao","Jenn-Gwo Hwu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T12:43:52Z","doi":"10.1063/5.0257074","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1016/j.mssp.2025.109950","name":"Sputtered HfYOx buffer layer with reduced nonlinearity for neuromorphic computing applications","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.mssp.2025.109950","authors":["Kuan-Lin Yeh","Po-An Shih","Wei-Chueh Cheng","Kai-Ling Hsu","Sheng-Yuan Chu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-09T12:50:32Z","doi":"10.1016/j.mssp.2025.109950","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1007/978-981-92-1599-7_26","name":"Observer-Based Dynamic Event-Triggered Tracking Control for Nonlinear MASs with Unknown Time-Varying Sensor Sensitivity","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-92-1599-7_26","authors":["Hongxuan Song","Guangliang Liu","Yingnan Pan","Wen Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-14T18:18:30Z","doi":"10.1007/978-981-92-1599-7_26","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1002/sstr.202570004","name":"Modulating Alkyl Groups in Copolymer to Control Ion Transport in Electrolyte‐Gated Organic Transistors for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1002/sstr.202570004","authors":["Junho Sung","Minji Kim","Sein Chung","Yongchan Jang","Soyoung Kim","Min‐Seok Kang","Hee‐Young Lee","Joonhee Kang","Donghwa Lee","Wonho Lee","Eunho Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-10T17:53:22Z","doi":"10.1002/sstr.202570004","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1109/mind67540.2025.11351933","name":"BKD-BSNN: Blurred Knowledge Distillation-Enhanced Binarized Spiking Neural Network for Efficient Neuromorphic Vision","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mind67540.2025.11351933","authors":["Jianming Zhu","Ping He","Zhiyuan Hu","Rong Xiao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-27T04:49:35Z","doi":"10.1109/mind67540.2025.11351933","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1117/12.2543781","name":"Neuromorphic computing through photonic integrated circuits","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.2543781","authors":["George Mourgias-Alexandris","Angelina Totovic","Nikolaos Passalis","George Dabos","Anastasios Tefas","Nikos Pleros"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-02-26T20:46:36Z","doi":"10.1117/12.2543781","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1109/ted.2022.3212262","name":"Call for Papers: Materials, processing and integration for neuromorphic devices and in-memory computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ted.2022.3212262","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-03T22:11:24Z","doi":"10.1109/ted.2022.3212262","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1109/icnc52316.2021.9608039","name":"Time Series of Landslide Displacement Prediction based on VMD-LSTM","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc52316.2021.9608039","authors":["Mengfei Xu","Jiejie Chen","Honggang Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-29T20:59:32Z","doi":"10.1109/icnc52316.2021.9608039","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1109/imw.2019.8739698","name":"Synaptic Devices Based on 3-D AND Flash Memory Architecture for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/imw.2019.8739698","authors":["Yoohyun Noh","Yungtak Seo","Byunggook Park","Jong-Ho Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-06-21T02:37:16Z","doi":"10.1109/imw.2019.8739698","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1038/s44287-025-00235-w","name":"Neuromorphic devices in action","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s44287-025-00235-w","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-11T13:02:32Z","doi":"10.1038/s44287-025-00235-w","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1109/icnc64304.2024.10987653","name":"Saturated Impulsive Distributed Filtering for Target Estimation Over Sensor Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987653","authors":["Yuan Tian","Zhenyu Ao","Qi Han","Qiao Yuan","Wenlong Fu","Ruonan Cui"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987653","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.2139/ssrn.6402373","name":"Inverted C-Pocket TFET Based LIF Neuron for Energy-Efficient Neuromorphic Computing with Adaptive Threshold Logic and Image Classification","source":"crossref","abstract":"n this work, we propose a novel Leaky Integrate and Fire (LIF) neuron based on an adjustable band-to-band tunneling mechanism, which significantly improves integration density and energy consumption. Neural activity has been simulated using the forward transfer characteristics of an In0.47Ga0.53As based inverted C-Pocket TFET with a steep sub-threshold swing and lower threshold voltage. In addition to providing adjustable characteristics, the calibrated simulations conducted with Silvaco TCAD 2D simulator, it verifies that inverted C-pocket TFET can successfully mimic the neural activity of neuron, without use of external circuit. The proposed LIF neuron requires only 60 aJ per spike with spiking frequency in the range of MHz This energy use is at least 105 times lesser to the 1T MOSFET-type neuron and 1,000 times lesser to the TFET-type neuron previously described in literature. This significant enhancement is due to tunneling and structural engineering approaches. This neuron has been well used to perform the application of threshold logic gates. It offers an approach for designing extremely scalable and low-power threshold logic circuits for emerging neuromorphic computing systems. Finally, a multilayer SNN is used to confirm the proposed neuron&amp;apos;s image classification capacity with an accuracy of 95.81%.","url":"https://doi.org/10.2139/ssrn.6402373","authors":["Mohd Faizan","Ehraz Ashraf","ABDULLAH Alshahrani","Neelofer Afzal","Sajad  A. Loan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-12T17:40:35Z","doi":"10.2139/ssrn.6402373","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.29363/nanoge.matnec.2022.018","name":"Brain-like avalanche behavior in filamentary networks of memristive Ag-hBN system","source":"crossref","abstract":"","url":"https://doi.org/10.29363/nanoge.matnec.2022.018","authors":["Ankit Rao","Sooraj Sanjay","Srinivasan Raghavan","Pavan Nukala"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-30T08:35:25Z","doi":"10.29363/nanoge.matnec.2022.018","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1149/ma2024-01572999mtgabs","name":"(Invited) Engineering the Switching Kinetics of Valence Change-Based Memristive Devices for Neuromorphic Computing","source":"crossref","abstract":"Memristive devices based on the valence mechanism are highly interesting candidates for the use as hardware representation of synapses in neuromorphic computing. The memristive model system SrTiO 3 exhibit gradual switching and can be tuned between short-term and long-term plasticity. We will discuss the impact of the switching kinetics on the gradual switching mode and provide general guidelines for the design of gradual switching systems. Moreover, we present an approach to accelerate the switching kinetics of SrTiO 3 by up to 10 3 times, or reduce the operating voltage by ≈ 30% to maintain the switching speed. Our approach is to introduce a low thermal conductivity layer inside the active electrode of the active electrode of the devices, which blocks the heat dissipation caused by Joule heating during switching. Our method leaves the switching layer and its interfaces with the electrodes intact, while the use of HfO 2 and TaO x as the heat blocking layers ensures ease of fabrication and CMOS compatibility. We will demonstrate that this approach is transferable to other more common material systems.","url":"https://doi.org/10.1149/ma2024-01572999mtgabs","authors":["Alexandros Sarantopoulos","Regina Dittmann"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-19T15:53:55Z","doi":"10.1149/ma2024-01572999mtgabs","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1109/iitc51362.2021.9537346","name":"Enabling Ferroelectric Memories in BEoL - towards advanced neuromorphic computing architectures","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iitc51362.2021.9537346","authors":["David Lehninger","Maximilian Lederer","Tarek Ali","Thomas Kampfe","Konstantin Mertens","Konrad Seidel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-20T21:22:55Z","doi":"10.1109/iitc51362.2021.9537346","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1007/978-981-92-1599-7_2","name":"Collision-free Cluster Formation Control of Autonomous Surface Vehicle Based on Artificial Potential Function","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-92-1599-7_2","authors":["Huijuan Li","Nan Gu","Zhouhua Peng","Lu Liu","Haoliang Wang","Anqing Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-14T18:17:12Z","doi":"10.1007/978-981-92-1599-7_2","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1007/978-981-92-1599-7_12","name":"Neural Network Structure-Based Adaptive SMC for Pneumatic Artificial Muscle Systems with State Constraints and Input Dead Zones","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-92-1599-7_12","authors":["Jiaxi Pei","Ming Li","Menghua Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-14T18:20:13Z","doi":"10.1007/978-981-92-1599-7_12","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1021/acsanm.5c00007","name":"Battery-Free Neuromorphic Computing Based on PMMA/SiO<sub>2</sub> Nanoparticle Memristor and Near-Field Communication","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acsanm.5c00007","authors":["Lin Liu","Jingyu Wang","Yong Yan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-17T19:02:06Z","doi":"10.1021/acsanm.5c00007","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1002/smtd.202500089","name":"Coupling Light into Memristors: Advances in Halide Perovskite Resistive Switching and Neuromorphic Computing","source":"europepmc","abstract":"Abstract Resistive switching memristor is an emerging nonvolatile memory technology designed to overcome the physical limitations of conventional systems and the performance bottleneck of the von Neumann architecture. Notably, halide perovskite (HP)‐based memristors have gained significant attention in recent years due to their unique ionic migration behavior and exceptional photoelectric properties. This review highlights HP‐based resistive switching, focusing on its recent developments in coupling light into memristors and discussing its implications for neuromorphic computing. The mechanisms of resistive switching are explored alongside the role of HP photoelectric properties in enhancing switching dynamics. The advantages and applications of light‐coupled resistive switching, including reduced switching voltage, enhanced operation reliability, multilevel switching capability, and the development of light‐integrated artificial synapses are discussed comprehensively. By fully harnessing the exceptional optoelectronic properties of HPs, this emerging field may pave the way for innovative approaches to memory technologies and light‐responsive neuromorphic systems.","url":"https://doi.org/10.1002/smtd.202500089","authors":["Zijian Feng","Jintao Wang","Fandi Chen","Beining Dong","Xinyu Ma","Tingting Mei","Ni Yang","Xinwei Guan","Long Hu","Chun‐Ho Lin","Zhi Li","Tom Wu"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/smtd.202500089","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1016/j.memori.2023.100088","name":"Bio-inspired artificial synapses: Neuromorphic computing chip engineering with soft biomaterials","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.memori.2023.100088","authors":["Tanvir Ahmed"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-18T04:14:06Z","doi":"10.1016/j.memori.2023.100088","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1002/widm.70014","name":"Neuromorphic Computing and Applications: A Topical Review","source":"crossref","abstract":"ABSTRACT Neuromorphic computers achieve energy efficiency by emulating brain structure and event‐driven processing that reduces energy consumption significantly. An increasing interest in this technology started in the initial years of this millennium, sparked by the awareness and concern on the ever‐increasing power demands of modern‐day computing. In current times, there are several neuromorphic computers and sensors that continue to be developed in both industry and academic research. The focus of this survey is on the neuromorphic computing applications of these devices that include brain‐inspired neural networks, brain‐inspired artificial neural networks, and Hybrid circuits comprising both artificial and brain‐inspired units of computation. Many of these applications use neuromorphic sensors as input devices. We have surveyed three specific neuromorphic computers viz. SpiNNaker, TrueNorth, Loihi, and one neuromorphic sensor viz. Dynamic vision sensor (DVS)‐based electronic retina; the demonstration of neuromorphic computing and applications using these devices far outnumbers those on the others that are currently available, which forms the basis of our choice. The applications include low‐power cognitive machine intelligence as well as neuropathological understanding and knowledge discovery. Overall, our survey identifies the potential for neuromorphic computing to provide low power, low cost, and dynamic solutions for societal and scientific problems in the not‐too‐distant future.","url":"https://doi.org/10.1002/widm.70014","authors":["Pavan Kumar Enuganti","Basabdatta Sen Bhattacharya","Teresa Serrano Gotarredona","Oliver Rhodes"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-29T05:40:43Z","doi":"10.1002/widm.70014","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1117/3.100022.ch6","name":"2D neuromorphic photonics","source":"crossref","abstract":"","url":"https://doi.org/10.1117/3.100022.ch6","authors":["Wen Zhou","James Tan","Johannes Feldmann","Harish Bhaskaran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-02T21:15:00Z","doi":"10.1117/3.100022.ch6","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.21203/rs.3.rs-2789677/v1","name":"On-chip phonon-magnon reservoir for neuromorphic computing","source":"preprints","abstract":"Abstract Reservoir computing is a concept in which signals to process are mapped onto a high-dimensional phase space of a fixed dynamical system called “reservoir” for subsequent recognition by an artificial neural network. Implementations of reservoirs are possible using different hardware and, accordingly, exploit different carriers and mechanisms of signal transformation. Despite the growing number of neuromorphic prototypes of reservoirs, demands for miniaturization, efficiency, and robustness all require implementation of the reservoir on a chip, and remain among the key challenges. Here we propose a nanodevice, in which a sandwich of a semiconductor phonon waveguide and a patterned ferromagnetic layer enables efficient reservoir computing. The optical input signal is coded by a pulsed write-laser and converted into a propagating multimode phonon wave packet, which interacts with a bunch of magnon modes. The output signal read by a second laser represents a phase-sensitive superposition of all the phonon and magnon modes, which possesses ultimate sensitivity to the relative positions of the write- and read-laser spots. The reservoir efficiently separates the visual shapes drawn by the write-laser beam on the nanodevice surface in an area with size comparable to a single pixel of a modern digital camera. Thus, our finding suggests the phonon-magnon interaction as a promising hardware basis for realization of rapid on-chip reservoir computing for future neuromorphic architectures.","url":"https://doi.org/10.21203/rs.3.rs-2789677/v1","authors":["Alexey Scherbakov","Dmytro Yaremkevich","Luke De Clerk","Serhii Kukhtaruk","Richard Campion","Andrew Rushforth","Sergey Savel’ev","Alexander Balanov","Manfred Bayer","Achim Nadzeyka"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-2789677/v1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1109/igsc51522.2020.9291228","name":"Low Size, Weight, and Power Neuromorphic Computing to Improve Combustion Engine Efficiency","source":"crossref","abstract":"","url":"https://doi.org/10.1109/igsc51522.2020.9291228","authors":["Catherine D. Schuman","Steven R. Young","J. Parker Mitchell","J. Travis Johnston","Derek Rose","Bryan P. Maldonado","Brian C. Kaul"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-04-14T01:42:20Z","doi":"10.1109/igsc51522.2020.9291228","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1016/j.asoc.2026.114984","name":"Homeostatically-regulated liquid state machines for robust and efficient arrhythmia classification: A neuromorphic approach","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2026.114984","authors":["Xiang Guo","Shule Xu","Jun Jiao","Xinxiang Zhao","Yang Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-11T23:54:28Z","doi":"10.1016/j.asoc.2026.114984","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.3389/fncom.2025.1737839","name":"Bridging neuromorphic computing and deep learning for next-generation neural data interpretation","source":"europepmc","abstract":"The rapid advancement of electrophysiological techniques, brain imaging, and brain-machine interfaces (BMIs) has ushered neuroscience into an era of data explosion. Confronted with neural data that are high-dimensional, highly nonlinear, and exhibit complex temporal dependencies, conventional statistical and signal processing methods-often reliant on linear assumptions or low-dimensional projections-struggle to reveal the true mechanisms of brain activity [1]. In response to this challenge, deep learning (DL) and neuromorphic computing (NC) have emerged as two promising yet conceptually distinct computational paradigms. Deep learning has demonstrated remarkable capabilities in data-driven modeling, achieving significant breakthroughs in neural signal decoding and cognitive state identification. However, its inherent limitations-high energy consumption, limited interpretability, and low biological plausibility-restrict its deeper application in computational neuroscience. In contrast, neuromorphic computing, inspired by the event-driven and local plasticity properties of biological neural systems, offers unique advantages in low-power adaptive processing. Nonetheless, it still faces challenges in training algorithms and scalability [2,3]. To address these complementary shortcomings, this article proposes a hybrid framework that integrates neuromorphic computing with deep learning, aiming to harmonize biological plausibility with high computational performance, thereby opening new pathways for developing next-generation models and tools for neural data interpretation [4].Neuromorphic computing seeks to emulate the structural and functional organization of the brain, enabling computational systems to operate in ways that resemble biological neural processing. Its central idea is to incorporate event-driven and asynchronous communication, allowing computation to occur only when an event is triggered rather than at fixed time intervals [5]. This mechanism markedly reduces redundant operations and energy consumption, mirroring the physiological principle by which neurons fire only when their membrane potential surpasses a threshold.At the heart of neuromorphic computing lies the Spiking Neural Network (SNN), which represents information through discrete electrical impulses, or spikes, that are temporally encoded to convey meaning [6] [7]. Learning in SNNs is commonly governed by Spike-Timing-Dependent Plasticity (STDP)-a local rule that adjusts synaptic strength based on the precise timing of pre-and postsynaptic spikes. This biologically grounded mechanism enables SNNs to capture causal relationships in neural activity, making them more faithful to real neural dynamics than conventional Artificial Neural Networks (ANNs). Consequently, SNNs excel in handling temporal sequences, sparse representations, and real-time responses.In recent years, hardware implementations such as Intel Loihi, IBM TrueNorth, and BrainScaleS have demonstrated the promise of neuromorphic architectures for low-power, massively parallel computation [5][7]. For example, the Loihi chip integrates on-chip plasticity circuits that support localized learning, achieving power efficiency several orders of magnitude better than traditional GPUs. Simultaneously, rapid advances in memristor technology have introduced new opportunities for neuromorphic hardware [6][8] [9]. Memristors-devices that exhibit non-volatility, tunable conductance, and synapse-like behavior-enable in-memory computing, merging data storage and processing to emulate synaptic functionality directly on the chip. Despite these advances, several challenges remain. The discrete nature of spikes makes training difficult, as standard backpropagation cannot be directly applied. Scalability also remains a concern: current systems struggle to maintain learning efficiency and robustness in large-scale data environments. Furthermore, the ecosystem of algorithms and software frameworks is still immature, lacking standardized interfaces for widespread adoption [3]. A recent Nature report highlights key breakthroughs in inter-chip communication, scalable architecture, and event-driven scheduling, signaling an important step toward large-scale, next-generation brain-inspired computing systems [10].As the dominant paradigm in contemporary artificial intelligence, deep learning (DL) has achieved remarkable success in the analysis of neural data owing to its hierarchical feature extraction and nonlinear approximation capabilities [1] [11]. Architectures such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Transformers have been widely applied to the decoding of electroencephalography (EEG), local field potentials (LFP), and functional magnetic resonance imaging (fMRI) signals. These models can automatically extract multilayer representations, enabling the discovery of hidden relationships between neural activity and cognitive states.In practical applications, CNNs have demonstrated high accuracy and robustness in EEG-based emotion recognition and brain-machine interface (BMI) command classification tasks [12]. RNNs and Long Short-Term Memory (LSTM) networks have exhibited outstanding capabilities in modeling the temporal dynamics of neural signals and predicting brain activity patterns [13]. Moreover, Transformer-based architectures have shown a superior ability to capture global dependencies across multimodal neural datasets, significantly improving the interpretability and scalability of neural decoding frameworks [14]. Collectively, these advances indicate that deep learning not only facilitates complex pattern recognition in brain data but also provides statistical insights into the structure of neural processes.However, the advantages of deep learning are accompanied by several intrinsic limitations. First, artificial neural networks rely on continuous activation functions and global backpropagation, which diverge from the local learning and synaptic plasticity observed in biological neural systems, resulting in limited biological plausibility. Second, the computational process of deep networks depends on large-scale matrix multiplications and parallel processing, leading to extremely high power consumption-orders of magnitude greater than that of biological brains. Third, deep models often suffer from poor interpretability; although their predictive performance is high, the internal representations rarely align with specific neurophysiological structures or mechanisms. In addition, conventional deep learning models lack temporal precision, making it difficult to accurately capture spike-based neural dynamics with millisecond resolution [15] [16].Therefore, while deep learning has proven powerful in feature extraction and cognitive modeling of neural data, achieving a genuine transition from \"prediction\" to \"understanding\" requires the incorporation of computational paradigms that align more closely with neurophysiological mechanisms. Neuromorphic computing offers a biologically inspired and energy-efficient complement to deep learning, paving the way toward a more interpretable and power-efficient framework for neural data modeling.To reconcile the strong representational capacity of deep learning with the biological plausibility of neuromorphic computing, this work proposes a Hybrid Neuromorphic-Deep Learning Framework [4] [17]. The framework integrates event-driven spiking computation with end-to-end deep feature learning, forming a multilayer neural data-processing system that is interpretable, energy-efficient, and aligned with neurophysiological dynamics.At the architectural level, the framework consists of three major components: a neuromorphic front-end, a hybrid learning layer, and a deep interpretation back-end. The neuromorphic front-end extracts event-driven signals-such as spike trains-from multimodal neural recordings while performing noise suppression and initial temporal encoding [18]. Through the use of spiking neural networks (SNNs) or memristor-based neuromorphic circuits, this stage enables low-power, real-time preprocessing at the hardware level [8] [18]. Recent progress in two-dimensional-material neuromorphic chips has further enhanced efficiency, sensitivity, and scalability, offering robust hardware support for hybrid neural architectures [19].The hybrid learning layer serves as the interface between the neuromorphic and deep-learning modules. Its role is to map sparse spike-based events into higher-level feature vectors. This can be achieved using surrogate-gradient optimization or biologically inspired local plasticity rules [11] [14], integrating local learning mechanisms with global gradient-based adaptation for improved interpretability and flexibility.To operationalize the event-to-vector transformation within this layer, several established spike-to-vector conversion and differentiable training strategies can be adopted. For example, Meng et al. (2022) [20] introduced a differentiable spike-representation learning method that maps temporal spike sequences into continuous vector spaces, enabling cross-domain transformation from event-based signals to feature embeddings. Similarly, Zhang et al. (2023) [21]demonstrated that surrogate-gradient-based direct training in hybrid SNN-ANN networks can effectively extract and vectorize event-driven features. Furthermore, hybrid neural frameworks such as the Hybrid Neural Network (HNN) proposed by Zhao et al. (2022) [17] have verified that constructing learnable interaction layers between ANNs and SNNs enables efficient cross-domain feature projection, providing a feasible technical route for implementing the hybrid module in our framework. In addition, the analysis by Liu et al. (2024) [4]on the mechanisms and information flow in hybrid neural systems offers further theoretical support for the mapping strategy adopted here.The deep interpretation back-end applies advanced neural models-such as Transformers, graph convolutional networks (GCNs), or recurrent neural networks (RNNs)-for pattern recognition, brain-state decoding, and cognitive representation learning. This stage further benefits from pre-training and knowledge-transfer mechanisms, improving generalization and abstraction quality [4] [17]. Information flows from event-driven spike streams at the neuromorphic front-end, through the hybrid mapping layer, to high-level cognitive inference in the deep model. With a closed-loop design, feedback from the deep model can dynamically regulate neuromorphic parameters, enabling online learning and forming an adaptive, self-optimizing neural system.Compared with the HNN framework introduced by Zhao et al. (2022) [17], which primarily targets efficient heterogeneous ANN-SNN co-inference, the proposed framework extends beyond coupling mechanisms to incorporate a neuromorphic sensory front-end and a deep interpretive back-end. This results in a cross-scale architecture spanning event encoding, hybrid feature learning, and neurodynamics-aligned interpretation. Consequently, the present framework emphasizes event-driven representation, biological interpretability, and alignment with neurophysiological mechanisms, offering broader conceptual scope and greater relevance for neural data analysis. This hybrid framework offers several notable advantages. Event-driven computation reduces redundant operations and energy consumption. Spike-based representations correspond directly to neuronal firing patterns, improving interpretability. Deep neural models provide scalable abstraction for high-dimensional neural datasets. Finally, the integration of local plasticity with online adaptation imparts robustness and flexibility, forming a promising foundation for next-generation self-adaptive brain-machine systems. The integration of neuromorphic computing and deep learning represents not only a technological complementarity but also a profound paradigm shift in computational neuroscience [4][20]. This cross-level integration provides a systematic pathway for neural information processing that bridges biological inspiration and high-dimensional modeling, allowing models to simultaneously capture neurodynamic plausibility and the abstract representational power of deep networks. Through this hybrid framework, computational neuroscience is gradually transitioning from mere signal fitting toward functional interpretation of neural mechanisms.In the domain of neural encoding and decoding, hybrid models can more accurately characterize the dynamic firing patterns of neuronal populations, enabling precise recognition of complex neural processes such as motor intention, perceptual representation, and cognitive load [1]. By combining the temporal precision of spike-based events with the hierarchical representations of deep networks, researchers can achieve a multi-scale description of neural information, uncovering the diversity and plasticity inherent in neural coding.For brain connectivity modeling, integrating spike-driven event models with Graph Neural Networks (GNNs) offers a promising approach to uncover causal interactions and functional topologies among neural circuits [17]. Such frameworks not only facilitate the reconstruction of dynamic brain networks but also provide computational insights for the early diagnosis and intervention of neurological disorders such as epilepsy and Alzheimer's disease.In brain-machine interfaces (BMIs) and neural rehabilitation, the hybrid architecture enables real-time signal decoding on low-power neuromorphic hardware, supporting adaptive and online-learning-based neural communication systems [8][22]. By combining the efficient temporal processing of spiking neural networks with the high-level pattern recognition capability of deep learning, these systems can dynamically adjust decoding strategies while maintaining energy efficiency-thereby enhancing self-learning capabilities for intelligent neuroprosthetic control and rehabilitation.From a hardware-intelligence co-design perspective, the rapid progress of memristor technology and three-dimensional integrated circuits is driving a deep convergence between neuromorphic chips and AI accelerators [9][18]. This cross-layer collaboration enables brain-inspired learning and adaptive cognition in edge-computing environments, making it feasible to achieve efficient, real-time neural computation directly on localized devices.Looking forward, the core objective of computational neuroscience will revolve around achieving a balanced trade-off between energy efficiency, interpretability, and scalability. By combining the biological realism of neuromorphic computing with the abstraction capabilities of deep learning, a new generation of neural intelligent systems may emerge-systems that not only elucidate the computational principles and information flow of the brain but also drive the advancement of adaptive intelligent chips, brain-inspired computing platforms, and next-generation brain-machine interface technologies.Despite the significant potential of the hybrid neuromorphic-deep learning framework, several limitations remain that must be addressed in future research. First, event-driven encoding is inherently sensitive to noise and may not be suitable for neural recording modalities with low temporal resolution or high measurement noise-such as calcium imaging or fMRI-which restricts its applicability across modalities. Second, training hybrid ANN-SNN systems often incurs substantial computational overhead. Cross-domain gradient propagation can introduce instability, and the field still lacks a unified strategy for multimodal fusion across spike-based and continuous representations. Third, current neuromorphic hardware faces practical challenges, including variability and limited reproducibility in memristive devices, as well as bandwidth constraints in inter-chip communication. These factors hinder large-scale deployment and stable on-chip training. Finally, although the deep interpretation module enables powerful high-dimensional feature abstraction, its biological interpretability remains imperfect and cannot yet fully align with real neurophysiological mechanisms. Therefore, applying this framework to real neural data analysis and brain-machine interface systems will require careful balancing among algorithmic design, hardware implementation, and neuroscientific validation.We argue that the fusion of neuromorphic computing and deep learning constitutes a paradigm shiftfor computational neuroscience, moving the field beyond isolated algorithms toward a holistic paradigm that embraces cross-level abstraction, biological plausibility, and stringent energy constraints [4]. The synergistic integrationof event-driven processing with deep hierarchical learning is pivotal, enabling not only a more profound interpretation of neural dynamics but also the co-design of intelligent and energy-efficient hardware. This hybrid framework establishes a new foundation for future research, poised to significantly advance our capabilities in decoding neural computation, diagnosing neurological disorders, and engineering adaptive, brain-inspired intelligence [17,22].","url":"https://doi.org/10.3389/fncom.2025.1737839","authors":["Manyun Zhang","Tianlei Wang","Zhiyuan Zhu"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fncom.2025.1737839","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.53941/ldm.2026.100002","name":"Spatio-Temporal Confinement in Two-Dimensional Channels for Neuromorphic Computing","source":"crossref","abstract":"Graphene oxide (GO), with its unique two-dimensional structure, adjustable functional groups, and tunable nanofluidic channels, has emerged as a promising platform for bio-inspired neuromorphic computing. This perspective explores the structural and functional analogies between GO membranes and biological ion channels, emphasizing GO’s ability to support selective ion transport, stimuli-responsive behavior, and synaptic plasticity. Recent advances in material engineering and device integration have enabled GO-based artificial synapses, including memristors and ion-gated transistors, to emulate key neuronal features such as excitatory postsynaptic currents, paired-pulse facilitation, and spike-timing-dependent plasticity with sub-millisecond response times and picojoule-level energy consumption. Moreover, the incorporation of GO with polymers, quantum dots, and semiconductors has facilitated multimodal control via electric, optical, and chemical inputs. Together, these developments position GO as a powerful material system for future neuromorphic devices that operate in aqueous and dynamic biological environments, paving the way toward brain-inspired hardware, neuroprosthetics, and intelligent biointerfaces.","url":"https://doi.org/10.53941/ldm.2026.100002","authors":["Hongwei Zhu","Honglin Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-16T02:54:46Z","doi":"10.53941/ldm.2026.100002","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1109/icnc64304.2024.10987859","name":"OSA-Net: A Deep Learning Approach for Obstructive Sleep Apnea Classification Using ECG Scalograms","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987859","authors":["Xielan Tang","Yamei Li","Qingqing Yang","Lu Luo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987859","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.2174/9789815305364124010004","name":"Neuromorphic Computing: Forging a Link between Artificial Intelligence and Neurological Models","source":"crossref","abstract":"By emulating the design and operation of the human brain, neuromorphic computing promises to close the gap between artificial intelligence and brain-inspired technologies. Researchers create specialized hardware and software to mimic the brain's processing speed, capacity for learning, and energy economy. This chapter examines the drivers, difficulties, and prospective uses of neuromorphic computing, with a focus on robotics, sensory processing, and pattern recognition. The entire potential of brain-inspired systems will be unlocked by ongoing research, revolutionizing the field of AI and paving the way for the creation of cutting-edge, intelligent machines that follow the principles of the brain.","url":"https://doi.org/10.2174/9789815305364124010004","authors":["Madhvan Bajaj","Priyanshu Rawat","Vikrant Sharma","Satvik Vats"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-23T03:51:36Z","doi":"10.2174/9789815305364124010004","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.2139/ssrn.4385387","name":"A Novel Low-Power Memristor for Neuromorphic Computing Using Carbon Conductive Filament","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4385387","authors":["Tianqi Yu","Yong Fang","Xinyue Chen","Min Liu","Dong Wang","Wei Lei","Helong Jiang","Likun Pan","Zhiwei Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-22T20:05:13Z","doi":"10.2139/ssrn.4385387","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1002/9781118927601.ch6","name":"Learning in Neuromorphic Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9781118927601.ch6","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-12-27T02:59:29Z","doi":"10.1002/9781118927601.ch6","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.3389/fncom.2021.665662","name":"Editorial: Understanding and Bridging the Gap Between Neuromorphic Computing and Machine Learning","source":"crossref","abstract":"","url":"https://doi.org/10.3389/fncom.2021.665662","authors":["Lei Deng","Huajin Tang","Kaushik Roy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-17T05:04:00Z","doi":"10.3389/fncom.2021.665662","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/icrc57508.2022.00017","name":"Virtual Neuron: A Neuromorphic Approach for Encoding Numbers","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icrc57508.2022.00017","authors":["Prasanna Date","Shruti Kulkarni","Aaron Young","Catherine Schuman","Thomas Potok","Jeffrey S. Vetter"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-17T17:18:24Z","doi":"10.1109/icrc57508.2022.00017","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/icnc59488.2023.10462831","name":"Meta-PolyArc:A Face Recognition Algorithm for Truck Drivers at Unmanned Gates Aiming at Few-shot Problem","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462831","authors":["Runxing Cao","Qing Liu","Liwei Peng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462831","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/icnc59488.2023.10462898","name":"Privacy Preserving Discretized Spiking Neural Network with TFHE","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462898","authors":["Pengbo Li","Ting Gao","Huifang Huang","Jiani Cheng","Shuhong Gao","Zhigang Zeng","Jinqiao Duan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462898","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.21203/rs.3.rs-1791364/v1","name":"Realization of Tunable Plasticity in Porous Synaptic Memristors for Neuromorphic Computing","source":"preprints","abstract":"Abstract Brain-inspired neuromorphic computing is a promising way to implement artificial intelligence to overcome the issues of independent information processing and storage. An artificial synaptic device with tunable plasticity can perform learning and memorization by adjusting the weight of the synapse. In this work, a synaptic memristor composed of porous silicon oxide (PSiO x ) incorporated with MoS 2 quantum dots (QDs) is fabricated and excitatory paired-pulse facilitation (PPF), post-tetanic potentiation (PTP), learning-forgetting behavior, and spike-timing-dependent plasticity (STDP) are demonstrated. The short/long-term plasticity (SLTP) in biological synapses reveal the possibility of tunable synaptic plasticity with self-regulating functions under a series of excitation frequency between 200 μs and 10 ms. An artificial neural network (ANN) is designed theoretically according to the SLTP characteristic curves of the synapses and the recognition rate is observed to increase from 54.2% to 91.8% by simply adjusting the input frequency. The image recognition accuracy is improved by 6% in the presence of 20% noise at an input frequency of 1 ms. The excellent results and novel strategy reveal an important step for image recognition in next-generation neuromorphic computing systems.","url":"https://doi.org/10.21203/rs.3.rs-1791364/v1","authors":["Anping Huang","Qin Gao","Jiangshun Huang","Yuhang Ji","Juan Gao","Mei Wang","Zhisong Xiao","Ying Zhu","Paul Chu"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.21203/rs.3.rs-1791364/v1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.62441/nano-ntp.vi.2974","name":"Neuromorphic Computing: Advancing Energy-Efficient AI Systems through Brain-Inspired Architectures","source":"crossref","abstract":"Neuromorphic computing represents a transformative approach to artificial intelligence, leveraging brain-inspired architectures to enhance energy efficiency and computational performance. This paper explores the principles and innovations underlying neuromorphic systems, which mimic the neural structures and processes of biological brains. We discuss the advantages of these architectures in processing information more efficiently than traditional von Neumann models, particularly in tasks involving pattern recognition, sensory processing, and adaptive learning. By integrating concepts from neuroscience with cutting-edge hardware developments, such as spiking neural networks and memristors, neuromorphic computing addresses the critical challenges of power consumption and scalability in AI applications. This review highlights recent advancements, ongoing research efforts, and potential future directions, illustrating how neuromorphic computing can redefine the landscape of AI by enabling systems that are not only faster and more efficient but also capable of real-time learning and decision-making in dynamic environments.","url":"https://doi.org/10.62441/nano-ntp.vi.2974","authors":["Rajesh Kumar Malviya","Ramanakar Reddy Danda","Kiran Kumar Maguluri","Battapothu Vinod Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-05T02:21:21Z","doi":"10.62441/nano-ntp.vi.2974","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.29363/nanoge.neuronics.2025.003","name":"ELECTRONICS and NEUROMORPHIC TECHNOLOGY ENHANCEMENT THROUGH IONIC NANOARICHITECTONICS","source":"crossref","abstract":"","url":"https://doi.org/10.29363/nanoge.neuronics.2025.003","authors":["Kazuya Terabe","Daiki Nishioka","Wataru Namiki","Tohru Tsuruoka","Takashi Tsuchiya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-23T11:35:32Z","doi":"10.29363/nanoge.neuronics.2025.003","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1201/9781003338918-5","name":"Neuromorphic Building Blocks with Memristors","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003338918-5","authors":["Idongesit Ebong","Pinaki Mazumder"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-21T19:26:45Z","doi":"10.1201/9781003338918-5","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1088/2634-4386/ad3be7","name":"Scaling neural simulations in STACS","source":"crossref","abstract":"Abstract As modern neuroscience tools acquire more details about the brain, the need to move towards biological-scale neural simulations continues to grow. However, effective simulations at scale remain a challenge. Beyond just the tooling required to enable parallel execution, there is also the unique structure of the synaptic interconnectivity, which is globally sparse but has relatively high connection density and non-local interactions per neuron. There are also various practicalities to consider in high performance computing applications, such as the need for serializing neural networks to support potentially long-running simulations that require checkpoint-restart. Although acceleration on neuromorphic hardware is also a possibility, development in this space can be difficult as hardware support tends to vary between platforms and software support for larger scale models also tends to be limited. In this paper, we focus our attention on Simulation Tool for Asynchronous Cortical Streams (STACS), a spiking neural network simulator that leverages the Charm++ parallel programming framework, with the goal of supporting biological-scale simulations as well as interoperability between platforms. Central to these goals is the implementation of scalable data structures suitable for efficiently distributing a network across parallel partitions. Here, we discuss a straightforward extension of a parallel data format with a history of use in graph partitioners, which also serves as a portable intermediate representation for different neuromorphic backends. We perform scaling studies on the Summit supercomputer, examining the capabilities of STACS in terms of network build and storage, partitioning, and execution. We highlight how a suitably partitioned, spatially dependent synaptic structure introduces a communication workload well-suited to the multicast communication supported by Charm++. We evaluate the strong and weak scaling behavior for networks on the order of millions of neurons and billions of synapses, and show that STACS achieves competitive levels of parallel efficiency.","url":"https://doi.org/10.1088/2634-4386/ad3be7","authors":["Felix Wang","Shruti Kulkarni","Bradley Theilman","Fredrick Rothganger","Catherine Schuman","Seung-Hwan Lim","James B Aimone"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-08T22:27:35Z","doi":"10.1088/2634-4386/ad3be7","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1117/3.100022.ch8","name":"Large-scale neuromorphic systems enabled by integrated photonics","source":"crossref","abstract":"","url":"https://doi.org/10.1117/3.100022.ch8","authors":["Qiming Zhang","Weihong Shen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-02T21:15:11Z","doi":"10.1117/3.100022.ch8","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1016/j.measurement.2025.116960","name":"Correlation between linear conductance variability and accuracy in neuromorphic computing using AuNP-DNA/HfO2 bilayer memristor devices","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.measurement.2025.116960","authors":["Myoungsu Chae","Doowon Lee","Hyunbin Lee","Yuseong Jang","Taegi Kim","Youngeun Kim","Hee-Dong Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-06T19:39:59Z","doi":"10.1016/j.measurement.2025.116960","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1007/978-981-92-1599-7_20","name":"Neural-Based Adaptive Event-Triggered Tracking Control for Series Elastic Actuator with Input Dead Zones","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-92-1599-7_20","authors":["Lingzhe Zhu","Jing Zhao","Naiqi Wu","Yibin Li","Menghua Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-14T18:17:48Z","doi":"10.1007/978-981-92-1599-7_20","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1364/cleo_si.2017.sth1n.3","name":"Superconducting optoelectronic platform for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1364/cleo_si.2017.sth1n.3","authors":["S. M. Buckley","A. N. McCaughan","J. Chiles","R. P. Mirin","S. W. Nam","J. M. Shainline"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-05-08T12:15:09Z","doi":"10.1364/cleo_si.2017.sth1n.3","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/icm66518.2025.11322475","name":"A $\\Delta \\mathrm{T}$-Triggered Spiking Temperature Sensor for Neuromorphic and Edge Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icm66518.2025.11322475","authors":["Moustafa Nawito"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-12T18:21:00Z","doi":"10.1109/icm66518.2025.11322475","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1002/9781118927601.ch10","name":"Programmable and Configurable Analog Neuromorphic ICs","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9781118927601.ch10","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-12-27T02:59:29Z","doi":"10.1002/9781118927601.ch10","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/edtm58488.2024.10511458","name":"Spintronics-Based Neuromorphic and Ising Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/edtm58488.2024.10511458","authors":["Debanjan Bhowmik","Ram Singh Yadav","Neha Garg","Amod Holla","Pranaba K. Muduli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-07T17:23:10Z","doi":"10.1109/edtm58488.2024.10511458","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/metroxraine58569.2023.10405839","name":"Aging Aware Retraining with a Sparse Update for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/metroxraine58569.2023.10405839","authors":["Aswani Radhakrishnan","Alex James"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-01T13:26:36Z","doi":"10.1109/metroxraine58569.2023.10405839","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/ccwc54503.2022.9720737","name":"Benchmarking Conventional Vision Models on Neuromorphic Fall Detection and Action Recognition Dataset","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ccwc54503.2022.9720737","authors":["Karthik Sivarama Krishnan","Koushik Sivarama Krishnan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-04T15:27:19Z","doi":"10.1109/ccwc54503.2022.9720737","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1201/9781003328957-15","name":"Spike-Based Neuromorphic Computing for Next-Generation Computer Vision","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003328957-15","authors":["Md Sakib Hasan","Catherine D. Schuman","Zhongyang Zhang","Tauhidur Rahman","Garrett S. Rose"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-29T19:28:44Z","doi":"10.1201/9781003328957-15","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1038/s41563-025-02230-w","name":"A neuromorphic mechanosensory skin","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s41563-025-02230-w","authors":["Qianbo Yu","Jiaqi Liu","Wentao Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-28T09:03:33Z","doi":"10.1038/s41563-025-02230-w","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1109/edtm58488.2024.10511578","name":"Magnetic Soliton MTJ Devices for Neuromorphic Computing Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/edtm58488.2024.10511578","authors":["Aijaz H. Lone","Daniel N. Rahimi","Hossein Fariborzi","Gianluca Setti"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-07T17:23:10Z","doi":"10.1109/edtm58488.2024.10511578","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1002/pssr.202500341","name":"Low‐Voltage Flexible Copper Iodide Synaptic Transistors for Neuromorphic Computing","source":"crossref","abstract":"A flexible copper iodide (CuI) thin‐film transistor integrated with a chitosan gate dielectric is demonstrated in this article, which is fabricated on a polyethylene terephthalate (PET) substrate via a low‐temperature solution process. The device operation is enabled by the electric double layer effect induced by proton migration in chitosan, achieving low‐voltage driving at 2 V. Additionally, the device is tested under various mechanical bending conditions, demonstrating its flexibility and mechanical reliability. A transition from short‐term memory to long‐term memory is realized by modulating the pulse amplitude. Furthermore, the synaptic plasticity is shown to be tunable by pulse parameters (duration, frequency, number), which is quantitatively correlated with the proton diffusion kinetics in chitosan. These behaviors, resembling biological spike‐timing‐dependent plasticity, are systematically analyzed to establish a framework for neuromorphic computing. The results highlight the potential of the CuI/chitosan platform for flexible neuromorphic electronics, offering insights into adaptive learning rules and biohybrid systems.","url":"https://doi.org/10.1002/pssr.202500341","authors":["Xiaodong Xu","Wei Dou","Pengfei Chen","Jiangyun Lei","Yuling Peng","Dongsheng Tang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-09T03:54:05Z","doi":"10.1002/pssr.202500341","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.2172/2281801","name":"Real-Time Neuromorphic Processing of Spatiotemporal Data for Scientific Discovery","source":"crossref","abstract":"","url":"https://doi.org/10.2172/2281801","authors":["Peng Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-04T22:16:40Z","doi":"10.2172/2281801","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1021/acsaelm.4c02278","name":"P3OT-Based Organic Polymer Memristors for Artificial Synaptic Behavior and Neuromorphic Computing Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acsaelm.4c02278","authors":["Hongguang Zhang","Linkai Li","Aiqian Guo","Jianda Li","Yong-Tao Li","Wen Li","Mingdong Yi","Liang Xie"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-26T15:36:01Z","doi":"10.1021/acsaelm.4c02278","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1002/aelm.202500440","name":"Organic Thin‐Film Transistors for Neuromorphic Computing","source":"crossref","abstract":"ABSTRACT Organic Thin‐Film Transistors (OTFTs), including Organic Field‐Effect Transistors (OFETs) and Organic Electro‐Chemical Transistors (OECTs), offer clear advantages over traditional silicon‐based devices, particularly in power efficiency and biocompatibility. When combined with neuromorphic computing, which mimics the brain's event‐driven processing to improve computational efficiency, OTFTs become a powerful platform for next‐generation electronics. These devices have demonstrated strong potential as artificial synapses and neurons, showing key spike‐based performance metrics such as Excitatory Post‐Synaptic Current (EPSC), Paired‐Pulse Facilitation (PPF), and Long‐Term Potentiation (LTP). This review captures recent progress in OTFT‐based synaptic and neuronal devices, alongside an in‐depth analysis of how fabrication parameters influence neuromorphic performance. Such insights are critical for designing and optimizing organic neuromorphic systems. We examine the transition from single‐transistor synapses to multi‐transistor neuron models, including emerging organic Single Transistor Latch (STL) neurons that mimic Leaky Integrate and Fire (LIF) and related dynamics. This review also explores the development of OTFT‐based neural networks, their performance relative to Metal‐Oxide‐Semiconductor Field‐Effect Transistor (MOSFET)‐based systems, and their potential shift toward fully neuromorphic Spiking Neural Networks (SNNs). Beyond surveying device demonstrations, this review introduces a standardized characterization protocol for OTFT synapses, and maps the physical mechanisms of OTFT architectures onto appropriate learning rules and network models. By linking materials, device physics, and neuromorphic algorithms, we highlight the opportunities for co‐designing flexible, bio‐integrated OTFT‐based neuromorphic systems.","url":"https://doi.org/10.1002/aelm.202500440","authors":["Luke McCarthy","Mohan V. Jacob","Mostafa Rahimi Azghadi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-18T16:06:06Z","doi":"10.1002/aelm.202500440","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1149/ma2020-02312049mtgabs","name":"Memristive Organic Bismuth Iodides for Neuromorphic Computing with High Performance","source":"crossref","abstract":"We report here synthesis of memristive organic bismuth iodide and its application to neuromorphic computing. A x Bi y I x+3y (A = organic monovalent cation) thin films are prepared by spin coating, where structural dimensionality and electrical properties are found to depend on composition. The solid solution synthesized by mixing 2 dimensional (2D) composition with 0 dimensional (0D) one exhibits bipolar switching behavior, where electrical conductivity is significantly lowered as compared to the individual 2D and 0D phase. In addition, activation energy for resistive switching is also substantially lowered by mixing the dimensionality. Memristor is coupled with transistor (1t-1r system), which results in the resistance of 60 MΩ for writing and the operating voltage of 0.6 V alongside linear and symmetric weight update and selectivity. This indicates that the organic bismuth iodide is highly promising for large scale neural network. Furthermore, a crossbar array prepared based on the synthesized organic bismuth iodide shows linear and symmetric weight update. Simulation using MNIST (Modified National Institute of Standards and Technology) data set based on single-layer perceptron model confirms that average of accuracy rate of the synthesized organic bismuth iodide in the crossbar array is close to ideal rate accuracy.","url":"https://doi.org/10.1149/ma2020-02312049mtgabs","authors":["June-Mo Yang","So-Yeon Kim","Nam-Gyu Park"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-22T18:59:08Z","doi":"10.1149/ma2020-02312049mtgabs","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/icnc59488.2023.10462762","name":"3DNesT: A Hierarchical Local Self-Attention Model for Alzheimer’s Disease Diagnosis","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462762","authors":["Xiaopeng Kang","Yong Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462762","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.55092/esp20260003","name":"Magnetic tunnel junctions for neuromorphic computing: from device physics to network architectures","source":"crossref","abstract":"","url":"https://doi.org/10.55092/esp20260003","authors":["Liyuan Yang","Mengchun Pan","Peisen Li","Miaosen Liu","Minhui Ji"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-12T11:38:34Z","doi":"10.55092/esp20260003","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.20517/energymater.2025.185","name":"Triboelectric-memristive coupling for self-powered neuromorphic computing: mechanisms, devices, and systems","source":"crossref","abstract":"Coupling triboelectric nanogenerators (TENGs) with memristors offers a direct route to integrating energy harvesting and adaptive learning within a single physical substrate, thereby enabling self-powered neuromorphic systems driven by ubiquitous mechanical stimuli. Unlike conventional electronics that rely on external power rails, triboelectric-memristive hybrids transduce mechanical excitations into programmable resistive states, supporting synaptic functions such as short-term plasticity, long-term plasticity, and spike-timing-dependent plasticity. This review synthesizes the physical mechanisms of triboelectric-memristive coupling and clarifies how charge transfer, interfacial electron-ion interactions, and device-level state dynamics collectively enable energy-to-information transduction for signal processing and learning. In contrast to previous surveys that focus on TENGs or memristors in isolation, we establish a unified transduction framework that links mechanical stimulus statistics to TENG waveform characteristics and further to memristive state-variable evolution, which serves as the organizing principle throughout the paper. We then present (ⅰ) a mechanism-guided taxonomy of representative device architectures and their achievable plasticity modes; and (ⅱ) a system-level perspective on the integration of self - powered sensing, in-memory learning, and multimodal data fusion. Finally, we summarize key challenges - including charge stability, humidity tolerance, device variability, and scalable integration - and discuss emerging directions such as large-area triboelectric materials for improved array uniformity, multiphysics co-learning for enhanced in-sensor intelligence, and physics-informed compact models to support device-circuit-algorithm co-design under stochastic energy inputs.","url":"https://doi.org/10.20517/energymater.2025.185","authors":["Haiyang Qin","Qinrao Li","Dongzhu Lu","Jianxin Lin","Wenke Gao","Huachuan Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-21T05:46:47Z","doi":"10.20517/energymater.2025.185","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1109/iccr67387.2025.11291668","name":"Neuromorphic Cryptography: Brain-Inspired Secure Encoding for Embedded Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccr67387.2025.11291668","authors":["Nida Nasir","Hussam Al Hamadi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-19T18:56:15Z","doi":"10.1109/iccr67387.2025.11291668","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.4018/979-8-3373-9785-6.ch004","name":"Quantum-Inspired or Neuromorphic Discrete-Event Computing Paradigms for Future Ubiquitous Systems","source":"crossref","abstract":"Foundations of quantum-inspired discrete-event architectures constitute an emerging and transformative paradigm in the modelling, simulation, and design of complex, dynamic, and stochastic systems, particularly in the context of large-scale distributed networks, Internet of Things (IoT) ecosystems, cyber-physical systems, cloud and edge computing, service-oriented architectures, and high-performance computing environments, where traditional discrete-event simulation (DES) approaches face challenges related to scalability, uncertainty, combinatorial complexity, and real-time decision-making; quantum-inspired methodologies draw conceptual and algorithmic insights from quantum mechanics, quantum computing principles, and quantum information theory, including superposition, entanglement, probabilistic amplitudes, and parallelism, to enhance the capability of DES frameworks to represent, process, and optimize highly complex event-driven interactions across heterogeneous devices, services, and computing layers.","url":"https://doi.org/10.4018/979-8-3373-9785-6.ch004","authors":["Shrishail Math","H. D. Madhuri","Vijaykumar Yadhav","Mallanagouda Patil","P. Selvakumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-05T16:35:20Z","doi":"10.4018/979-8-3373-9785-6.ch004","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1587/nolta.12.625","name":"Special section on nonlinear dynamical aspects of edge computing and neuromorphic hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1587/nolta.12.625","authors":["Hideyuki Suzuki","Shigeo Sato"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-30T22:39:03Z","doi":"10.1587/nolta.12.625","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1007/978-3-032-32260-9_9","name":"Two-Dimensional Material-Based Bio-Inspired Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-32260-9_9","authors":["Heemyoung Hong","Chang Yun Heo","Heejun Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-13T06:32:28Z","doi":"10.1007/978-3-032-32260-9_9","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.2139/ssrn.4860557","name":"Controlling Long-Term Plasticity in Neuromorphic Computing Through Modulation of Ferroelectric Polarization","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4860557","authors":["Donghwa Lee","Junho Sung","Minhui Kim","Na-Hyun Kim","Seonggyu Lee","Hee-Young Lee","Dongyeong Jeong","Eunho Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-11T01:21:11Z","doi":"10.2139/ssrn.4860557","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.3390/photonics13050431","name":"Memristors for the Post-Von Neumann Era: Hardware Paradigms, Neuromorphic Perception, and Computing Systems","source":"crossref","abstract":"Memristors, as transformative electronic devices designed to transcend the von Neumann architecture, enable the physical unification of information storage and computation, thereby offering a foundational hardware pathway toward energy-efficient, brain-inspired computing. Their intrinsic analog resistive switching, non-volatility, and history-dependent learning capabilities allow them to natively implement in-memory computing and emulate synaptic plasticity, addressing the critical bottlenecks of energy and speed in conventional systems. Notably, the evolution from electrically controlled memristors to optoelectronic memristors marks a paradigm shift from pure computing to integrated sensing-processing, opening new dimensions for high-speed, parallel, and adaptive signal processing. In recent years, significant progress has been made in the development of memristor-based neuromorphic vision and tactile systems, on-chip signal processors, and dynamic trajectory trackers, demonstrating their potential in edge intelligence, adaptive robotics, and real-time perceptual tasks. This review systematically summarizes the latest advances in memristor technology, providing a comprehensive analysis of their operating mechanisms, material and structural innovations, and cutting-edge applications in neuromorphic perception and computing. Furthermore, it discusses the key challenges and future directions for the development and integration of memristor-based systems in the post-von Neumann era.","url":"https://doi.org/10.3390/photonics13050431","authors":["Kerui Fu","Tianling Qin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-28T13:26:41Z","doi":"10.3390/photonics13050431","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.62802/tfme0736","name":"Advancing Artificial Intelligence: The Potential of Brain-Inspired Architectures and Neuromorphic Computing for Adaptive, Efficient Systems","source":"crossref","abstract":"Brain-inspired AI architecture, also known as neuromorphic computing, seeks to emulate the structure and functionality of the human brain to create more efficient, adaptive, and intelligent systems. Unlike traditional AI models that rely on conventional computing frameworks, brain-inspired architectures leverage neural networks and synapse-like connections to perform computations more similarly to biological brains. This approach offers significant advantages, including lower power consumption, improved learning capabilities, and enhanced problem-solving efficiency, particularly in tasks that require complex pattern recognition and cognitive processes. This paper explores the key components of brain-inspired AI architectures, such as spiking neural networks (SNNs) and neuromorphic hardware, and reviews the latest advancements in this field. We examine their applications across diverse domains, including robotics, autonomous systems, and medical diagnostics, where brain-like adaptability and real-time learning are critical. Additionally, we analyze the challenges associated with scaling these architectures, including hardware constraints and the complexity of accurately mimicking human brain functionality. The potential for combining brain-inspired AI with current machine learning models is also discussed, highlighting future directions for achieving more advanced, efficient, and human-like artificial intelligence systems. This research contributes to the growing body of knowledge on neuromorphic computing and its promise in shaping the future of AI technologies.Moreover, brain-inspired AI architectures have the potential to surpass traditional AI systems in terms of real-time decision-making and learning efficiency, particularly in environments that require adaptive behavior. The use of spiking neural networks (SNNs) in these architectures allows for more biologically plausible models of neuron activity, which can lead to advancements in sensory processing and autonomous decision-making. As neuromorphic hardware continues to evolve, integrating it with existing AI frameworks could enhance both performance and scalability. However, replicating the brain's full complexity remains a significant challenge, particularly in terms of creating energy-efficient hardware capable of supporting large-scale neural networks. Despite these challenges, the development of brain-inspired AI promises to bridge the gap between artificial and human intelligence, offering transformative possibilities for various industries.","url":"https://doi.org/10.62802/tfme0736","authors":["Alp Dulundu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-29T12:11:46Z","doi":"10.62802/tfme0736","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/aipe58786.2023.00015","name":"The need for neuromorphic computing in industrial robotics","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aipe58786.2023.00015","authors":["Tapanta Bhanja","Jonathan Nußbaum","Khalil Abuibaid","Tatjana Legler","Achim Wagner","Martin Ruskowski"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-25T19:06:22Z","doi":"10.1109/aipe58786.2023.00015","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.20944/preprints202511.1462.v1","name":"The Neuromorphic Conductor: A Speculative Framework for Brain-Chip Interfaces to Restore Bodily Function","source":"europepmc","abstract":"This report is a deep dive into the complex world of using neuromorphic chips to help people with severe brain damage regain control of their bodies. We’ll look at the fundamental science behind neuromorphic computing, explore the current landscape of brain-computer interfaces (BCIs), and confront the biological and ethical challenges of making such a technology a reality. The main idea is to create a kind of “digital nervous system” that could bypass damaged parts of the brain to restore basic functions like movement and breathing. This isn't just a technical paper; it’s a detailed exploration of the immense hurdles and profound questions that must be answered before we can truly build a bridge between mind and machine. This document is a starting point for anyone looking to understand this fascinating and difficult field.","url":"https://doi.org/10.20944/preprints202511.1462.v1","authors":["Anand Rawat","Anamika Yadav"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202511.1462.v1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1002/9781118927601.ch16","name":"Towards Large‐Scale Neuromorphic Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9781118927601.ch16","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-12-27T02:59:29Z","doi":"10.1002/9781118927601.ch16","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1109/icons62911.2024.00001","name":"2024 International Conference on Neuromorphic Systems ICONS 2024","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024.00001","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T18:37:03Z","doi":"10.1109/icons62911.2024.00001","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1088/2634-4386/ada8d4/v4/response1","name":"Author response for \"Maximizing information in neuron populations for neuromorphic spike encoding\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2634-4386/ada8d4/v4/response1","authors":["Ahmad El Ferdaoussi","Éric Plourde","Jean Rouat"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-11T16:33:42Z","doi":"10.1088/2634-4386/ada8d4/v4/response1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.31219/osf.io/gtv6q","name":"Extremely high bandwidth optical neuromorphic processing, microwave photonics and data transmission with Kerr microcombs","source":"crossref","abstract":"We report ultrahigh bandwidth applications of Kerr microcombs to optical neural networks and to optical data transmission, at data rates from 44 Terabits/s (Tb/s) to approaching 100 Tb/s. Convolutional neural networks (CNNs) are a powerful category of artificial neural networks that can extract the hierarchical features of raw data to greatly reduce the network complexity and enhance the accuracy for machine learning tasks such as computer vision, speech recognition, playing board games and medical diagnosis [1-7]. Optical neural networks can dramatically accelerate the computing speed to overcome the inherent bandwidth bottleneck of electronics. We use a new and powerful class of micro-comb called soliton crystals that exhibit robust operation and stable generation as well as a high intrinsic efficiency with an extremely low spacing of 48.9 GHz. We demonstrate a universal optical vector convolutional accelerator operating at 11 Tera-OPS/s (TOPS) on 250,000 pixel images for 10 kernels simultaneously — enough for facial image recognition. We use the same hardware to sequentially form a deep optical CNN with ten output neurons, achieving successful recognition of full 10 digits with 900 pixel handwritten digit images. We also report world record high data transmission over standard optical fiber from a single optical source, at 44.2 Terabits/s over the C-band, with a spectral efficiency of 10.4 bits/s/Hz, with a coherent data modulation format of 64 QAM. We achieve error free transmission across 75 km of standard optical fiber in the lab and over a field trial with a metropolitan optical fiber network. Our work demonstrates the ability of optical soliton crystal micro-combs to exceed other approaches in performance for the most demanding practical optical communications applications.","url":"https://doi.org/10.31219/osf.io/gtv6q","authors":["David Moss"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-21T19:32:22Z","doi":"10.31219/osf.io/gtv6q","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1007/s12668-025-02078-z","name":"Neuromorphic Elements as a First Step Towards Sociomorphic Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s12668-025-02078-z","authors":["Victor Erokhin","Irina S. Karabulatova"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-08T01:28:34Z","doi":"10.1007/s12668-025-02078-z","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1109/ecoc.2018.8535535","name":"Photonics for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ecoc.2018.8535535","authors":["Paul R. Prucnal","Alexander N. Tait","Mitchell A. Nahmias","Thomas Ferreira De Lima","Hsuan-Tung Peng","Bhavin J. Shastri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-12-03T19:58:27Z","doi":"10.1109/ecoc.2018.8535535","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/async58294.2023.10239638","name":"An Efficient Data Structure for Sparse Bit-Vectors with Applications in Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/async58294.2023.10239638","authors":["Prafull Purohit","Johannes Leugering","Rajit Manohar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-06T17:24:13Z","doi":"10.1109/async58294.2023.10239638","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/icnc64304.2024.10987713","name":"Trigonometric Expansion based Random Fourier Feature Algorithm for Nonlinear Adaptive Filtering","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987713","authors":["Qiangqiang Zhang","Shunran Xiang","Wei Zhang","Shiyuan Wang","Dongyuan Lin","Hongjuan Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987713","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1002/admt.71158","name":"Defect‐Controlled Ti‐Doped Perovskite Memristors for High Accuracy Neuromorphic Computing","source":"crossref","abstract":"ABSTRACT Neuromorphic computing requires electronic devices capable of stable analogue switching, low energy operation, and reliable synaptic behaviour. In this study, Zinc zirconate (ZZO) and Ti‐doped ZnZrO 3 (TZZO) perovskite thin films were developed to realise high‐performance memristors, and their switching behaviour is correlated with defect chemistry and electronic structure. Resistive switching devices with Ag/ZZO/FTO and Ag/TZZO/FTO configurations exhibit consistent bipolar switching, governed by ohmic, space‐charge‐limited conduction (SCLC), and high‐field‐assisted transport mechanisms associated with Schottky and Poole–Frenkel conduction. The switching behaviour in Ag/TZZO/FTO is primarily attributed to an oxygen‐vacancy‐mediated valence change memory (VCM) mechanism, with possible minor contributions from field‐assisted Ag‐ion migration. These devices showed strong performance, with endurance reaching 10 4 cycles and retention of 10 4 s. Density functional theory (DFT) studies revealed that Ti doping improves electrical conductivity via defect‐driven transport pathways. The neuromorphic computing potential of these devices was validated by integrating their long‐term potentiation and depression (LTP and LTD) behaviours into a convolutional neural network (CNN) trained on the MNIST dataset, achieving digit recognition accuracies of 94.35% for ZZO and 98.35% for TZZO. These results establish the Ti‐doped ZZO as a promising candidate for next‐generation non‐volatile memory and neuromorphic applications.","url":"https://doi.org/10.1002/admt.71158","authors":["Narender Malishetty","Vaishali Chandmare","Narendar Vadthiya","Hitesh Borkar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-10T04:41:16Z","doi":"10.1002/admt.71158","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1109/icnc52316.2021.9608128","name":"Event-triggered Pinning Synchronization of Multi-weighted Coupled Neural Networks without and with Time Delays","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc52316.2021.9608128","authors":["Xin Xiao","Yanli Huang","Jinliang Wang","Yihao Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-29T15:59:32Z","doi":"10.1109/icnc52316.2021.9608128","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1007/978-981-97-4445-9_6","name":"Design of Spiking Neural Networks (SNN) with Domain-Wall Devices","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-4445-9_6","authors":["Debanjan Bhowmik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-15T14:02:06Z","doi":"10.1007/978-981-97-4445-9_6","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/atigb59969.2023.10364403","name":"Statistical Study on Data Dependency of Memristor Crossbar Architectures for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/atigb59969.2023.10364403","authors":["Minh Le","Son Ngoc Truong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-25T19:40:28Z","doi":"10.1109/atigb59969.2023.10364403","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/edtm55494.2023.10103091","name":"IGZO Photonic-Synaptic Transistors with Outstanding Linearity by Controlling Oxygen Vacancy for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/edtm55494.2023.10103091","authors":["Taewon Seo","Juyoung Yun","Yoonyoung Chung"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-26T17:55:20Z","doi":"10.1109/edtm55494.2023.10103091","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/mdat.2021.3051399","name":"Embracing Stochasticity to Enable Neuromorphic Computing at the Edge","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mdat.2021.3051399","authors":["Amogh Agrawal","Deboleena Roy","Utkarsh Saxena","Kaushik Roy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-02-09T05:08:43Z","doi":"10.1109/mdat.2021.3051399","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/icnc64304.2024.10987761","name":"Preassigned-Time Stabilization of Memristive Chaotic Circuit via Switching Control","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987761","authors":["Qiming Wang","Leimin Wang","Wenzhao Qin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987761","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1007/978-3-540-73007-1_53","name":"A Programmable Time Event Coded Circuit Block for Reconfigurable Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-540-73007-1_53","authors":["Thomas Jacob Koickal","Luiz C. P. Gouveia","Alister Hamilton"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-09-20T13:34:35Z","doi":"10.1007/978-3-540-73007-1_53","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/icccis48478.2019.8974525","name":"Binary-Weighted Synaptic Circuit for Neuromorphic Learning System Using Stochastic Memristor SPICE Model","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icccis48478.2019.8974525","authors":["M. Nigus","Rashmi Priyadarshini","R.M. Mehra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-30T23:42:47Z","doi":"10.1109/icccis48478.2019.8974525","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1007/s11082-026-08963-5","name":"Voltage-tunable plasmonic metamaterial networks for neuromorphic optical computing at telecommunication wavelengths","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11082-026-08963-5","authors":["Arash Vaghef-Koodehi","Mahmoud Nikoufard","Zeynab Gholizadeh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-20T04:56:35Z","doi":"10.1007/s11082-026-08963-5","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1109/nice65350.2025.11064940","name":"Eventprop training for efficient neuromorphic applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nice65350.2025.11064940","authors":["Thomas Shoesmith","James C. Knight","Balazs Meszaros","Jonathan Timcheck","Thomas Nowotny"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-08T13:36:20Z","doi":"10.1109/nice65350.2025.11064940","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1142/s0217979226300112","name":"Emerging Quantum Materials for Neuromorphic Computing: From Fundamental Physics to Device Architectures","source":"crossref","abstract":"The explosive growth of artificial intelligence (AI), edge computing, and brain-inspired algorithms has spurred the development of neuromorphic systems that mimic biological information processing. Achieving such functionality at the hardware level requires materials that exhibit neuron- and synapse-like behaviors in a scalable, low-power, and CMOS-compatible manner. In this review, we provide a comprehensive assessment of emerging quantum materials including Mott insulators, phase change materials (PCMs), topological insulators (TIs), twodimensional (2D) materials, and ferroelectrics highlighting their unique physical mechanisms and their relevance to neuromorphic device operation. Each material class is examined in terms of its electronic properties, switching dynamics, and compatibility with spiking neural networks (SNNs) and in-memory computing architectures. We compare their performance across key metrics such as energy efficiency, analog programmability, synaptic plasticity, and integration scalability. Furthermore, we engage in a comprehensive discussion regarding device prototypes that are predicated upon quantum materials, delineate the contemporary challenges associated with integration, and provide insights into hardware–algorithm co-design methodologies. This review additionally recognizes nascent trends such as hybrid material heterostructures, quantumclassical neuromorphic frameworks, and bioinspired learning paradigms that leverage intrinsic material dynamics. Our examination underscores that the amalgamation of the distinctive functionalities inherent in quantum materials with neuromorphic hardware presents a promising trajectory towards mitigating the constraints imposed by traditional computing paradigms. This synthesis facilitates the development of quantum neuromorphic platforms capable of real-time learning, operating with minimal energy consumption, and possessing adaptive learning architectures that dynamically adjust in accordance with cognitive requirements. Such platforms are poised to usher in the subsequent generation of computing systems that can rival or potentially surpass the performance of conventional von Neumann architectures.","url":"https://doi.org/10.1142/s0217979226300112","authors":["Abdullah Marzouq Alharbi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-27T10:24:13Z","doi":"10.1142/s0217979226300112","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1109/insect68872.2026.11663787","name":"Energy-Efficient System-on-Chip Architecture for AIoT Applications Using Mixed-Signal Neuromorphic Accelerators","source":"crossref","abstract":"","url":"https://doi.org/10.1109/insect68872.2026.11663787","authors":["Jainish Roy","Madhu Sahu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-31T19:14:43Z","doi":"10.1109/insect68872.2026.11663787","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1088/2634-4386/ae84f7","name":"TEMPO: a stochastic benchmarking protocol for evaluating temporal robustness in spiking neural networks","source":"crossref","abstract":"Abstract Spiking neural networks are set apart from conventional architectures by their leaky-integrator dynamics and temporal memory, yet the benchmarks most often used to evaluate them do not exercise these properties. In datasets such as N-MNIST and DVS-Gesture the discriminative information lies in spatial features, so collapsing all spike timing into a single bin leaves classification accuracy largely intact. Morse code is a natural antidote, since its meaning resides entirely in the duration of marks and the silences between them. Existing Morse benchmarks, however, assume deterministic machine-perfect timing and ignore the rhythmic variability of real human operators. We introduce the Temporal Encoding Morse Protocol for Operators, a benchmark protocol for 26-letter Morse classification that places human operator variability at the center of its design. Each Morse element produces a single spike at the moment its mark completes, encoded on one of two channels at a 1 ms time base compatible with ITU standards and neuromorphic hardware. Three stochastic parameters, the dash-to-dot ratio, word-level speed, and per-element jitter, model an operator’s characteristic ‘fist,’ and their distributions are fitted to measurements from 44 real recordings spanning diverse speeds and keying styles. A proof-of-concept multi-timescale network reaches 75.7% accuracy. Randomizing spike order while preserving counts collapses accuracy to a count-based baseline far below the intact result, confirming that the task cannot be solved without timing. A network trained only on clean signals still performs well above chance under severe noise, revealing an implicit temporal robustness that spatial benchmarks cannot expose. The benchmark and its generation code are openly available, with 75.7% standing as an open baseline for future architectures.","url":"https://doi.org/10.1088/2634-4386/ae84f7","authors":["Lucas S Hindman","Kurtis D Cantley"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-01T22:50:41Z","doi":"10.1088/2634-4386/ae84f7","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1088/2634-4386/ad1d32","name":"Reducing reservoir computer hyperparameter dependence by external timescale tailoring","source":"crossref","abstract":"Abstract Task specific hyperparameter tuning in reservoir computing is an open issue, and is of particular relevance for hardware implemented reservoirs. We investigate the influence of directly including externally controllable task specific timescales on the performance and hyperparameter sensitivity of reservoir computing approaches. We show that the need for hyperparameter optimisation can be reduced if timescales of the reservoir are tailored to the specific task. Our results are mainly relevant for temporal tasks requiring memory of past inputs, for example chaotic timeseries prediction. We consider various methods of including task specific timescales in the reservoir computing approach and demonstrate the universality of our message by looking at both time-multiplexed and spatially-multiplexed reservoir computing.","url":"https://doi.org/10.1088/2634-4386/ad1d32","authors":["Lina Jaurigue","Kathy Lüdge"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-10T17:42:28Z","doi":"10.1088/2634-4386/ad1d32","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/tetc.2017.2788865","name":"O(N)-Space Spatiotemporal Filter for Reducing Noise in Neuromorphic Vision Sensors","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tetc.2017.2788865","authors":["Alireza Khodamoradi","Ryan Kastner"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-01-01T19:09:25Z","doi":"10.1109/tetc.2017.2788865","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1016/b978-0-323-98829-2.00013-x","name":"Neuromorphic models applied to photonics","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-323-98829-2.00013-x","authors":["Yihao Xu","Yongmin Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-21T06:48:53Z","doi":"10.1016/b978-0-323-98829-2.00013-x","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.29363/nanoge.neumatdecas.2023.070","name":"Controlling biohybrid neuromorphic interfaces through neurotransmitter modulation","source":"crossref","abstract":"","url":"https://doi.org/10.29363/nanoge.neumatdecas.2023.070","authors":["Francesca Santoro"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-02-01T09:31:42Z","doi":"10.29363/nanoge.neumatdecas.2023.070","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/sai.2017.8252179","name":"Bio-inspired neuromorphic visual processing with neural networks for cyclist detection in vehicle's blind spot and segmentation in medical CT images","source":"crossref","abstract":"","url":"https://doi.org/10.1109/sai.2017.8252179","authors":["Woo-Sup Han","Il Song Han"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-01-11T23:49:34Z","doi":"10.1109/sai.2017.8252179","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1145/3797248.3816054","name":"Cross-Domain Reasoning for Neuromorphic Model Design","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3797248.3816054","authors":["Vikram Ramavarapu","Zachary Johnson-Scott","Ashish Gautam","Ramakrishnan Kannan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-19T10:46:08Z","doi":"10.1145/3797248.3816054","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1109/cai68641.2026.11536327","name":"Energy-Efficient Federated Learning for Space Observation via Neuromorphic Computing: a Use Case","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cai68641.2026.11536327","authors":["Domenico Lofù","Paolo Sorino","Tommaso Di Noia","Eugenio Di Sciascio"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-01T19:33:50Z","doi":"10.1109/cai68641.2026.11536327","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1364/ome.496985","name":"Harnessing exciton-polaritons for digital computing, neuromorphic computing, and optimization [Invited]","source":"crossref","abstract":"Polaritons are quasiparticles resulting from the strong quantum coupling of light and matter. Peculiar properties of polaritons are a mixture of physics usually restricted to one of these realms, making them interesting for study not only from the fundamental point of view but also for applications. In recent years, many studies have been devoted to the potential use of exciton-polaritons for computing. Very recently, it has been shown experimentally that they can be harnessed not only for digital computing but also for optical neural networks and for optimization related to hard computational problems. Here, we provide a brief review of recent studies and the most important results in this area. We focus our attention, in particular, on the emerging concepts of non-von-Neumann computing schemes and their realizations in exciton-polariton systems.","url":"https://doi.org/10.1364/ome.496985","authors":["Andrzej Opala","Michał Matuszewski"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-03T16:00:50Z","doi":"10.1364/ome.496985","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.36227/techrxiv.174742729.99297491/v1","name":"The Neuromorphic Cyber-Twin: A Conceptual Architecture for Cognitive Defense in Digital Twin Ecosystems","source":"crossref","abstract":"As cyber-physical systems become increasingly virtualized, Digital Twins are emerging as critical components for real-time system monitoring, simulation, and control. However, their growing complexity and exposure to dynamic network environments render them susceptible to sophisticated cyber threats. Traditional cybersecurity models, often based on rules or based on machine learning, struggle to adapt in real time to evolving attack patterns, especially within decentralized and resourceconstrained settings. In this conceptual paper, we introduce the Neuromorphic Cyber-Twin (NCT), a brain-inspired architectural framework that leverages spiking neural networks (SNNs) and event-driven cognition to endow digital twins with adaptive, self-evolving cyber defense capabilities. The NCT framework is grounded in neuromorphic principles such as sparse coding, temporal encoding, and synaptic plasticity, e.g., Spike-Timing-Dependent Plasticity (STDP), enabling it to process telemetry data from the digital twin layer as spike-based sensory input. We present a layered architecture wherein the cognitive layer continuously monitors behavioral deviations, performs anomaly inference, and autonomously adapts its defense responses in alignment with system dynamics. This biologically inspired paradigm offers low-latency detection, contextual awareness, and energy efficiency, essential for scalable security in virtualized ecosystems. We discuss theoretical underpinnings, architectural components, and application scenarios across smart infrastructure, autonomous transport, and industrial control systems. The paper concludes with key research challenges and a roadmap for future implementation of neuromorphic cybersecurity within digital twin environments.","url":"https://doi.org/10.36227/techrxiv.174742729.99297491/v1","authors":["Nida Nasir","Hussam Al Hamadi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-16T16:28:23Z","doi":"10.36227/techrxiv.174742729.99297491/v1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.62311/nesx/rp3jy-30072026","name":"Topological Photonics for Neuromorphic Computing, Quantum Communications and Ultralow-Power Edge Intelligence","source":"crossref","abstract":"Abstract: Topological photonics offers a route to guide, process and generate optical states through band structures whose global invariants can suppress selected forms of backscattering and disorder sensitivity. Neuromorphic photonics, quantum communications and edge intelligence, however, impose requirements that exceed protected transport alone: nonlinear computation, trainability, quantum-state fidelity, nanosecond-scale latency, low conversion overhead, fabrication tolerance and accountable system governance must be addressed jointly. This paper develops a model-based interdisciplinary framework for integrating these requirements. It introduces the Topological Photonic Neuromorphic–Quantum Edge Intelligence (TPNQ-EI) Framework, which couples Maxwell eigenproblems and Berry-topological invariants with tight-binding matrices, nonlinear photonic-neuron dynamics, quantum-channel fidelity, energy-per-inference accounting and constrained multi-objective optimization. The methodology combines critical literature synthesis, formal systems modelling, variable architecture, scenario comparison and an explicitly illustrative normalized numerical model. The numerical demonstration produces a gross capability score of 8.05/10 and a risk-adjusted score of 7.65/10 after accounting for optical loss, thermal drift, fabrication disorder and quantum decoherence. Analytical results indicate that topological design can improve resilience when disorder and routing defects are material, but cannot compensate automatically for absorption, out-of-plane scattering, calibration energy, detector noise or poorly matched multiphoton spectra. The paper contributes a unified vocabulary, mathematical architecture, validation protocol and governance perspective for evaluating topological photonic platforms across neuromorphic inference, quantum-network interfaces and ultralow-power edge applications. The proposed results are conceptual and illustrative; empirical claims require device-level measurement, cross-platform benchmarking and lifecycle assessment. Keywords Topological photonics; photonic neural networks; neuromorphic computing; quantum communications; topological quantum optics; edge intelligence; Chern number; Berry curvature; non-Hermitian photonics; photonic integrated circuits; ultralow-power inference; quantum-channel fidelity; disorder robustness; physics-aware training; multi-objective photonic optimization.","url":"https://doi.org/10.62311/nesx/rp3jy-30072026","authors":["Murali Krishna Pasupuleti"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-23T09:12:27Z","doi":"10.62311/nesx/rp3jy-30072026","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1109/icnc64304.2024.10987734","name":"HLSM-UNet:Hybrid Local Spatial Mamba UNet for Medical Image Segmentation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987734","authors":["Xude Zhang","Xiaoping Wu","Changzhen Zhang","Yumin Tang","Dihong Luo","Houbing Tang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987734","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/icnc59488.2023.10462791","name":"Dynamic Event-Triggered Distributed Optimization for Multi-Agent Systems with External Disturbances","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462791","authors":["Jiaqi Fan","Cheng Hu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462791","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.2139/ssrn.5638561","name":"Vibration Measurement with Neuromorphic Vision Sensors","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5638561","authors":["Sofia Baldini","Filippo Stazi","Riccardo Bernardini","Andrea Fusiello","Paolo Gardonio","Roberto Rinaldo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-22T01:51:37Z","doi":"10.2139/ssrn.5638561","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1109/icmc64879.2025.11102634","name":"Physics-Based SPICE Model of 2D-Material FETs for Neuromorphic Circuit Simulation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icmc64879.2025.11102634","authors":["Tamanna Nazeer","Sheikh Aamir Ahsan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-05T18:00:21Z","doi":"10.1109/icmc64879.2025.11102634","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1117/3.100022.ch12","name":"Photonic neuromorphic processing for optical communications","source":"crossref","abstract":"","url":"https://doi.org/10.1117/3.100022.ch12","authors":["Jianyang Shi","Nan Chi","Ziwei Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-02T21:15:13Z","doi":"10.1117/3.100022.ch12","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.2139/ssrn.4523712","name":"Synaptic Memristors Based on Flexible Organic Pentacene Thin Films by the Thermal Evaporation Method for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4523712","authors":["Lu Han","Dehui Wang","Mengdie Li","Yang Zhong","Kanghong Liao","Yingbo Shi","Wenjing Jie"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-28T09:18:13Z","doi":"10.2139/ssrn.4523712","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1002/9781394205158.ch8","name":"Advancement of Neuromorphic Computing Systems with Memristors","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9781394205158.ch8","authors":["Jeetendra Singh","Shailendra Singh","Balwant Raj","Vikas Patel","Balwinder Raj"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-31T13:08:43Z","doi":"10.1002/9781394205158.ch8","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1002/adma.202312825","name":"Photonics for Neuromorphic Computing: Fundamentals, Devices, and Opportunities","source":"europepmc","abstract":"Abstract In the dynamic landscape of Artificial Intelligence (AI), two notable phenomena are becoming predominant: the exponential growth of large AI model sizes and the explosion of massive amount of data. Meanwhile, scientific research such as quantum computing and protein synthesis increasingly demand higher computing capacities. As the Moore's Law approaches its terminus, there is an urgent need for alternative computing paradigms that satisfy this growing computing demand and break through the barrier of the von Neumann model. Neuromorphic computing, inspired by the mechanism and functionality of human brains, uses physical artificial neurons to do computations and is drawing widespread attention. This review studies the expansion of optoelectronic devices on photonic integration platforms that has led to significant growth in photonic computing, where photonic integrated circuits (PICs) have enabled ultrafast artificial neural networks (ANN) with sub‐nanosecond latencies, low heat dissipation, and high parallelism. In particular, various technologies and devices employed in neuromorphic photonic AI accelerators, spanning from traditional optics to PCSEL lasers are examined. Lastly, it is recognized that existing neuromorphic technologies encounter obstacles in meeting the peta‐level computing speed and energy efficiency threshold, and potential approaches in new devices, fabrication, materials, and integration to drive innovation are also explored. As the current challenges and barriers in cost, scalability, footprint, and computing capacity are resolved one‐by‐one, photonic neuromorphic systems are bound to co‐exist with, if not replace, conventional electronic computers and transform the landscape of AI and scientific computing in the foreseeable future.","url":"https://doi.org/10.1002/adma.202312825","authors":["Renjie Li","Yuanhao Gong","Hai Huang","Yuze Zhou","Sixuan Mao","Zhijian Wei","Zhaoyu Zhang"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024-06-21T09:11:11Z","doi":"10.1002/adma.202312825","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1063/1.5086902","name":"Critical neuromorphic computing based on explosive synchronization","source":"crossref","abstract":"Synchronous oscillations in neuronal ensembles have been proposed to provide a neural basis for the information processes in the brain. In this work, we present a neuromorphic computing algorithm based on oscillator synchronization in a critical regime. The algorithm uses the high-dimensional transient dynamics perturbed by an input and translates it into proper output stream. One of the benefits of adopting coupled phase oscillators as neuromorphic elements is that the synchrony among oscillators can be finely tuned at a critical state. Especially near a critical state, the marginally synchronized oscillators operate with high efficiency and maintain better computing performances. We also show that explosive synchronization that is induced from specific neuronal connectivity produces more improved and stable outputs. This work provides a systematic way to encode computing in a large size coupled oscillator, which may be useful in designing neuromorphic devices.","url":"https://doi.org/10.1063/1.5086902","authors":["Jaesung Choi","Pilwon Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-04-11T15:32:23Z","doi":"10.1063/1.5086902","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/iscas48785.2022.9937264","name":"Aging Aware Retraining for Memristor-based Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas48785.2022.9937264","authors":["Wenwen Ye","Grace Li Zhang","Bing Li","Ulf Schlichtmann","Cheng Zhuo","Xunzhao Yin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-11T20:38:08Z","doi":"10.1109/iscas48785.2022.9937264","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/icrc.2017.8123656","name":"An Energy-Efficient Mixed-Signal Neuron for Inherently Error-Resilient Neuromorphic Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icrc.2017.8123656","authors":["Baibhab Chatterjee","Priyadarshini Panda","Shovan Maity","Kaushik Roy","Shreyas Sen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-11-30T21:57:56Z","doi":"10.1109/icrc.2017.8123656","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1088/2634-4386/ae6728","name":"An energy-efficient spiking neural network with continuous learning for self-adaptive brain–machine interface","source":"crossref","abstract":"Abstract The number of simultaneously recorded neurons follows an exponentially increasing trend in implantable brain–machine interfaces (iBMIs). Integrating the neural decoder in the implant is an effective data compression method for future wireless iBMIs. However, the non-stationarity of the system makes the performance of the decoder unreliable. To avoid frequent retraining of the decoder and to ensure the safety and comfort of the iBMI user, continuous learning is essential for real-life applications. Since deep spiking neural networks (DSNNs) are being recognized as a promising approach for developing a resource-efficient neural decoder, we propose continuous learning approaches with reinforcement learning (RL) algorithms adapted for DSNNs. Banditron and AGREL are chosen as the two candidate RL algorithms since they can be trained with limited computational resources, effectively addressing the non-stationary problem and fitting the energy constraints of implantable devices. To assess the effectiveness of the proposed methods, we conducted both open-loop and closed-loop experiments. The accuracy of open-loop experiments conducted with DSNN_Banditron and DSNN_AGREL remains stable over extended periods. Meanwhile, the time-to-target in the closed-loop experiment with perturbations, DSNN_Banditron performed comparably to that of DSNN_AGREL while achieving reductions of 98% in memory access usage and 99% in the requirements for multiply-and-accumulate operations during training. Compared to previous continuous learning SNN decoders, DSNN_Banditron requires 98% less computes making it a prime candidate for future wireless iBMI systems.","url":"https://doi.org/10.1088/2634-4386/ae6728","authors":["Zhou Biyan","Arindam Basu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-01T00:42:19Z","doi":"10.1088/2634-4386/ae6728","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1109/mwscas.2017.8053148","name":"A time multiplexed network architecture for large-scale neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mwscas.2017.8053148","authors":["Rezwan A Rasul","Pedram Teimouri","Mike Shuo-Wei Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-10-24T20:21:31Z","doi":"10.1109/mwscas.2017.8053148","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/icnc59488.2023.10462881","name":"A Parallel Read-Write Circuit Design for Driving Memristor Crossbar Array","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462881","authors":["Ningye Jiang","Mingxuan Jiang","Zhigang Zeng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462881","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/icnc59488.2023.10462774","name":"Extreme Sparsity in Hodgkin-Huxley Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462774","authors":["Jann Krausse","Daniel Scholz","Felix Kreutz","Pascal Gerhards","Klaus Knobloch","Jürgen Becker"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462774","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1007/978-3-031-65549-4_1","name":"Introduction","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-65549-4_1","authors":["Ali Akbar Firoozi","Ali Asghar Firoozi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-26T13:01:53Z","doi":"10.1007/978-3-031-65549-4_1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.21203/rs.3.rs-10112503/v1","name":"A Non-Monotonic Reconfigurable Neural Unit with Dynamic Integration Control for Advanced Neuromorphic Computing","source":"europepmc","abstract":"Abstract The development of artificial neurons that emulate the rich adaptive dynamics of biological neural systems is pivotal for next-generation neuromorphic computing. Current hardware implementations, however, are fundamentally limited by fixed monotonic activation functions and an inability to dynamically control temporal integration processes. To overcome these challenges, we introduce a reconfigurable neural unit (RNU) that combines a synaptic transistor (MoTe 2 /h-BN) with a volatile memristor (Ag/h-BN/graphene). This architecture produces a distinct U-shaped non-monotonic response, originating from gate-modulated conductance variations in the MoTe 2 channel, which features a central silent region for firing-rate suppression, mimicking feature-selective inhibition observed in biological networks. Crucially, the position of this silent region on the gate-bias axis is dynamically reconfigurable via ultraviolet-light-assisted doping, enabling real-time adaptation of the RNU's operational state for diverse computing tasks. Moreover, the gate terminal doubles as a dedicated input for inhibitory spikes, enabling precise spatiotemporal control of neuronal integration that is critical for processing complex temporal patterns. System-level simulations demonstrate that spiking neural networks equipped with RNUs achieve competitive accuracy in image recognition and show a 3.5% improvement in four-class EEG decoding over conventional spiking network baselines. The RNU therefore provides a compact, versatile, and highly adaptive foundation for advanced neuromorphic systems.","url":"https://doi.org/10.21203/rs.3.rs-10112503/v1","authors":["Jing Liu","Xitong An","Yan Wang","Chao Dou","Haoyue Lu","Yueying Li","Xuan Deng","Dong Sun"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-10112503/v1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.1109/mcom.001.2500100","name":"Integrating Brain-Computer Interface and Neuromorphic Computing for Human Digital Twins","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mcom.001.2500100","authors":["Chen Shang","Jiadong Yu","Dinh Thai Hoang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-14T19:57:21Z","doi":"10.1109/mcom.001.2500100","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1117/12.3039478","name":"Event-driven LiDAR with dynamic neuromorphic processing","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3039478","authors":["Matthias Aquilina"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-22T04:30:34Z","doi":"10.1117/12.3039478","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1002/admt.202500588","name":"Recent Progress in Memristor Array‐Based Neuromorphic Computing for on‐Chip Vector‐Matrix Multiplication","source":"crossref","abstract":"Abstract Recently, the global issue of energy consumption has become a critical concern for the development of artificial intelligence (AI), which demands extensive computational resources and large‐scale data processing as network architectures and system algorithms grow increasingly complex. The conventional von Neumann digital computing architecture faces inherent limitations in handling the continuously growing big data, primarily due to its sequential data processing nature in vector–matrix multiplication (VMM) and the bottlenecks between processor and memory units. To address this challenge, brain‐inspired neuromorphic computing has emerged, emulating the human nervous system, particularly through memristor crossbar array architectures. These arrays function as cumulative operation units, enabling efficient parallel data processing. This paper discusses recent progress in hardware implementations of neuromorphic computing using memristor array devices, with a focus on circuit integration and on‐chip applications of AI algorithms rather than synaptic plasticity or unit‐cell switching mechanisms. The principle of parallel VMM operations is briefly reviewed, followed by hardware‐based VMM demonstrations, including convolutional transformations, neural network perceptrons, learning rule optimization, and on‐chip operations. The review also provides perspectives on future research directions, highlighting key challenges. Thus, memristor array‐based neuromorphic computing holds significant promise for scalable, energy‐efficient, and application‐ready AI hardware.","url":"https://doi.org/10.1002/admt.202500588","authors":["Jingon Jang","Sang‐gyun Gi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-26T03:16:19Z","doi":"10.1002/admt.202500588","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.3389/fnano.2024.1371386","name":"Harnessing ferroic ordering in thin film devices for analog memory and neuromorphic computing applications down to deep cryogenic temperatures","source":"crossref","abstract":"The future computing beyond von Neumann era relies heavily on emerging devices that can extensively harness material and device physics to bring novel functionalities and can perform power-efficient and real time computing for artificial intelligence (AI) tasks. Additionally, brain-like computing demands large scale integration of synapses and neurons in practical circuits that requires the nanotechnology to support this hardware development, and all these should come at an affordable process complexity and cost to bring the solutions close to market rather soon. For bringing AI closer to quantum computing and space technologies, additional requirements are operation at cryogenic temperatures and radiation hardening. Considering all these requirements, nanoelectronic devices utilizing ferroic ordering has emerged as one promising alternative. The current review discusses the basic architectures of spintronic and ferroelectric devices for their integration in neuromorphic and analog memory applications, ferromagnetic and ferroelectric domain structures and control of their dynamics for reliable multibit memory operation, synaptic and neuronal leaky-integrate-and-fire (LIF) functions, concluding with their large-scale integration possibilities, challenges and future research directions.","url":"https://doi.org/10.3389/fnano.2024.1371386","authors":["Sayani Majumdar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-15T05:06:46Z","doi":"10.3389/fnano.2024.1371386","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/icecs58634.2023.10382863","name":"Adiabatic Spiking Neurons and Synapses for Ultra-Low Energy Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icecs58634.2023.10382863","authors":["M. Massarotto","S. Saggini","M. Loghi","D. Esseni"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-10T19:38:25Z","doi":"10.1109/icecs58634.2023.10382863","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/iscas.2018.8351840","name":"High-Level Simulation for Spiking Neuromorphic Computing Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas.2018.8351840","authors":["Nicholas D. Skuda","Catherine Schuman","Gangotree Chakma","James S. Plank","Garrett S. Rose"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-05-04T18:00:05Z","doi":"10.1109/iscas.2018.8351840","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1149/ma2022-02321183mtgabs","name":"Ferroelectric Devices for Neuromorphic Computing","source":"crossref","abstract":"Neuromorphic computing inspired by the neural network systems of the human brain enables energy efficient computing for big-data processing. A neural network is formed by thousands or even millions of neurons which are connected by even a higher number of synapses. Neurons communicate with each other through the connected synapses. The main responsibility of synapses is to transfer information from the pre-synaptic to the postsynaptic neurons. Synapses can memorize and process the information simultaneously. The plasticity of a synapse to strengthen or weaken their activity over time make it capable of learning and computing. Thus, artificial synapses which can emulate functionalities and the plasticity of bio-synapses form the backbones of neuromorphic computing. Alternative artificial synapses have been successfully demonstrated. The classical two-terminal memristor devices, like resistive random access memory (ReRAM), phase change memory (PCM) and ferroelectric tunnel junctions (FTJs) with one terminal connected to the pre-synaptic neuron and another connected with the post-synaptic neuron, own advantages of simple structure, easy processing with high density, and capability of integration with CMOS. However, signal processing and learning cannot be performed simultaneously in 2-terminal devices, thus limiting their synaptic functionalities. Ferroelectric field effect transistors (FeFET) which uses ferroelectric as the gate oxide are the most interesting three-terminal artificial synapse devices, in which the gate or the source is connected to the pre-synaptic neuron while the drain is used for the terminal of the post-synaptic neuron , thus can perform signal transmission and learning simultaneously. However, traps at the channel interface can degrade the device performance causing low endurance. Focuses of those abovementioned devices have been mainly put on the homosynaptic plasticity, which is input specific, meaning that the plasticity occurs only at the synapse with a pre-synaptic activation . The homosynaptic plasticity has a drawback of positive feedback loop: when a synapse is potentiated, the probability of the synapse to be further potentiated is increased. Similarly, when a synapse is depressed the probability of the synapse of being further depressed is higher. Therefore, synaptic weights tend to be either strengthened to the maximum value or weakened to zero, causing the system to be unstable. In contrast, heterosynaptic plasticity can be induced at any synapse at the same time after episodes of strong postsynaptic activity, avoiding the positive feedback problem and stabilize the activity of the post-synaptic neuron. To address the above challenges we proposed a very simple 4-terminal synapse structure based on gated Schottky diodes on silicon (FEMOD) with a ferroelectric layer. The conductance of the Schottky diode is modulated by the polarization of the ferroelectric layer. With this simple synapse structure we can achieve multiple hetero-synaptic functions, including excitatory/ inhibitory post-synaptic current (EPSC/IPSC), paired-pulse facilitation/depression (PPF/PPD), long-term potentiation/depression (LTP/LTD), as well as biological neuron-like spike-timing-dependent plasticity (STDP) characteristics. The modulatory synapse can modify the weight of another synapse with a very low voltage. Furthermore, logic gates, like AND and NAND which are highly desired for in-memory computing can be realized with such simple structure. Figure 1","url":"https://doi.org/10.1149/ma2022-02321183mtgabs","authors":["Qing-Tai Zhao","Fengben Xi","Yi Han","Andreas Grenmyr","Jin Hee Bae","Detlev Gruetzmacher"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-23T20:06:09Z","doi":"10.1149/ma2022-02321183mtgabs","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1145/3589737.3605982","name":"Hyperdimensional Computing with Spiking-Phasor Neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3589737.3605982","authors":["Jeff Orchard","Russell Jarvis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-28T16:00:57Z","doi":"10.1145/3589737.3605982","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/biocas.2017.8325233","name":"An energy efficient neuromorphic computing system using real time sensing method","source":"crossref","abstract":"","url":"https://doi.org/10.1109/biocas.2017.8325233","authors":["Hooman Farkhani","Mohammad Tohidi","Sadaf Farkhani","Jens Kargaard Madsen","Farshad Moradi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-04-11T21:27:34Z","doi":"10.1109/biocas.2017.8325233","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1149/ma2026-01341564mtgabs","name":"(\n                    <i>Invited</i>\n                    ) Ion–Electron Interactions In Ionically Gated 2D Transistors for Neuromorphic and Energy-Efficient Computing","source":"crossref","abstract":"Two-dimensional (2D) materials offer a compelling platform for next-generation electronic and iontronic devices due to their nanoscale thickness, high carrier mobility, and strong coupling to electrochemical environments. When interfaced with solid ion conductors, these crystals can exhibit both electrostatic electric double layer (EDL) gating and electrochemical ion intercalation, providing complementary modes of modulation that are useful for low-power and neuromorphic device operation [1]. Yet, despite significant progress, the boundary between purely electrostatic operation and Faradaic ion insertion remains difficult to control, and understanding this interplay is essential for achieving stable, low-power, and high-performance devices [2]. In this talk, I will first discuss the unique opportunities and challenges of using 2D materials as channels in electrochemical RAM (ECRAM) devices, where their nanoscale thickness and strong coupling to solid ion conductors create both advantages and constraints for stable analog operation. I will then share recent efforts in our group to improve the stability and reversibility of ion intercalation in 2D channels through materials engineering. Because 2D-based ECRAM offers analog programmability suitable for on-chip training of artificial neural networks [3], we also examine how key device parameters such as on/off ratio, accessible conductance states, and weight-update linearity jointly determine neural-network performance. Through combined device measurements and simulation, we quantify trade-offs between the number of programmable states and weight-update linearity. Using a predictive ionic-weight-update model informed by measured device behavior [4], we demonstrate that linear and symmetric conductance modulation can be achieved while preserving multilevel operation, which in turn improves ANN accuracy and accelerates the training process. Finally, I will outline emerging directions in ionically controlled 2D devices for real-time and edge computing, where understanding and tailoring ion transport at electrolyte–2D crystal interfaces remain a central scientific challenge. By integrating insights from both the electronic device and electrochemical communities, this work aims to help establish design principles for stable, energy-efficient, and programmable iontronic systems based on 2D materials. [1] Xu, K.; Fullerton-Shirey, S. K. J. Phys. Mater. 2020 , 3 (3), 032001. [2] Xu, K.; Fullerton-Shirey, S. K. 2D Mater. 2025 , 12 (2), 023003. [3] Han, H.; Inman, J.; Maczynski, S.; Indovina, M.; Ganguly, A.; Das, T.; Xu, K. Proc. IEEE Microelectron. Des. Test Symp. (MDTS) 2025 , 1–6. [4] Manimaran, N. H.; Sutton, C. L. M.; Streamer, J. W.; Merkel, C.; Xu, K. J. Phys. Mater. 2024 , 8 (1), 015008.","url":"https://doi.org/10.1149/ma2026-01341564mtgabs","authors":["Ke Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-16T07:41:01Z","doi":"10.1149/ma2026-01341564mtgabs","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.29363/nanoge.neumatdecas.2023.007","name":"Robust Resistive and Mem-devices for Neuromorphic Circuits","source":"crossref","abstract":"","url":"https://doi.org/10.29363/nanoge.neumatdecas.2023.007","authors":["T. Venkatesan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-02-01T09:31:42Z","doi":"10.29363/nanoge.neumatdecas.2023.007","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1117/12.2633150","name":"Wavelength tunable resonant phase-change synaptic weights for photonic neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.2633150","authors":["Yihao Cui","Behrad Gholipour"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-03T22:57:55Z","doi":"10.1117/12.2633150","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1145/3183584.3183619","name":"FPGA based cellular neural network optimization","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3183584.3183619","authors":["Zhongyang Liu","Shaoheng Luo","Xiaowei Xu","Yiyu Shi","Cheng Zhuo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-04-25T12:58:50Z","doi":"10.1145/3183584.3183619","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.23919/splitech61897.2024.10612534","name":"Towards a Federated Intrusion Detection System based on Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.23919/splitech61897.2024.10612534","authors":["Domenico Lofù","Paolo Sorino","Tommaso Di Noia","Eugenio Di Sciascio"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-05T17:29:07Z","doi":"10.23919/splitech61897.2024.10612534","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/irps.2019.8720490","name":"Evaluation of Single Event Effects in SRAM and RRAM Based Neuromorphic Computing System for Inference","source":"crossref","abstract":"","url":"https://doi.org/10.1109/irps.2019.8720490","authors":["Zhilu Ye","Rui Liu","Hugh Barnaby","Shimeng Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-24T04:11:10Z","doi":"10.1109/irps.2019.8720490","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1149/ma2016-02/16/1476","name":"(Invited) Two-Terminal Selectors Enables Non-Volatile Memory and Neuromorphic Computing Applications","source":"crossref","abstract":"Sneak current path issue is a critical challenge in memristor crossbar arrays used for non-volatile memory and neuromorphic computing, which can be mitigated by utilizing a selector device in series with each memristor. For this purpose, the selector needs to possess a highly nonlinear current-voltage characteristic. In addition, for neuromorphic computing applications, dynamics originated from cation diffusion process is crucial for the functions of synapses in intelligent bio-systems. Memristor has been a leading candidate to emulate synapse for neuromorphic computing. Due to the lack of such dynamics in a typical memristor, the emulation of memristor to a synapse has been function-specific and cumbersome.These dynamics can be readily incorporated into some selector devices that operates based on cation motion. The highly nonlinear current-voltage characteristic of the selectors enables a large scale crossbar array. Meanwhile, its dynamics with the same physical origin of its bio-counterpart lead to a natural, direct and comprehensive emulation of a variety of important synaptic functions.","url":"https://doi.org/10.1149/ma2016-02/16/1476","authors":["J. Joshua Yang","Zhongrui Wang","Saumil Joshi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-02-27T01:24:11Z","doi":"10.1149/ma2016-02/16/1476","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/laedc54796.2022.9908216","name":"Efficient Signaling for Passive Memristive Crossbars to Prepare them for Spiking Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/laedc54796.2022.9908216","authors":["Ali Shiri Sichani","Kishore Kumar Kadari","Wilfrido A. Moreno"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-10T16:26:28Z","doi":"10.1109/laedc54796.2022.9908216","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.2139/ssrn.6556100","name":"Neuromorphic Reservoir Computing Generates Hippocampal Signals to Improve Neural Activity Modulation","source":"crossref","abstract":"IntroductionEpilepsy affects approximately 50 million people worldwide, and a substantial proportion of patients remain resistant to pharmacological treatment, requiring invasive interventions such as deep brain stimulation (DBS). Although DBS can reduce seizure frequency, its mechanisms of action are not fully understood, and high-frequency stimulation imposes a considerable stimulation burden. Alternative neuromodulation strategies that preserve physiological temporal dynamics while reducing stimulation load are therefore needed. Reservoir Computing (RC), particularly Echo State Networks (ESN), represents a promising neuromorphic approach capable of reproducing neuronal dynamics with low computational complexity.Materials and MethodsAn Echo State Network was designed to generate biomimetic electrical stimulation patterns replicating the spectral and statistical properties of hippocampal CA3 activity. The generated signals were characterized in terms of mean frequency, event timing, and inter-event interval distributions. These biomimetic stimulation patterns were applied in vitro to primary cortical neuronal cultures. Neuronal activity was assessed by measuring firing rate and burst-related metrics, and outcomes were compared to those obtained using conventional 50 Hz high-frequency stimulation.ResultsThe ESN-generated signal reproduced key spectral and statistical features of biological hippocampal activity, including a mean frequency of 0.16 Hz and preserved inter-event interval distributions. When applied to primary cortical cultures, biomimetic stimulation reduced firing rate and burst-related activity in 4 out of 11 networks (36%). The magnitude of reduction was comparable to that achieved with conventional 50 Hz stimulation. Importantly, this effect was obtained using approximately 300-fold fewer electrical pulses than high-frequency stimulation.ConclusionThese findings support a neuromodulation strategy that reduces stimulation load while preserving physiological temporal structure. ESN-based biomimetic stimulation represents a promising foundation for adaptive, closed-loop neuromodulation systems leveraging neuromorphic computing, with potential applications in personalized epilepsy treatment.","url":"https://doi.org/10.2139/ssrn.6556100","authors":["Ángel Canal-Alonso","Adam Armada-Moreira","Alessio Di Clemente","María Cerezo-Sánchez","Antonia Pavlidou","Danial Kiamarsi","Michele Giugliano","Hadi Heidari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-11T21:55:25Z","doi":"10.2139/ssrn.6556100","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1145/2834892.2834895","name":"Dynamic adaptive neural network arrays","source":"crossref","abstract":"","url":"https://doi.org/10.1145/2834892.2834895","authors":["Catherine D. Schuman","Adam Disney","John Reynolds"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-11-05T20:49:20Z","doi":"10.1145/2834892.2834895","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/isvlsi.2018.00104","name":"Emerging Neuromorphic Computing Paradigms Exploring Magnetic Skyrmions","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isvlsi.2018.00104","authors":["Sai Li","Wang Kang","Xing Chen","Jinyu Bai","Biao Pan","Youguang Zhang","Weisheng Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-08-09T22:11:51Z","doi":"10.1109/isvlsi.2018.00104","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.52202/080560-0003","name":"Visual Navigation Using Neuromorphic Camera","source":"crossref","abstract":"","url":"https://doi.org/10.52202/080560-0003","authors":["Mijaz Mukundan","Rithin Mohan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-03T21:46:58Z","doi":"10.52202/080560-0003","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1109/iscas45731.2020.9181218","name":"A 75kb SRAM in 65nm CMOS for In-Memory Computing Based Neuromorphic Image Denoising","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas45731.2020.9181218","authors":["Sumon Kumar Bose","Vivek Mohan","Arindam Basu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-29T09:22:27Z","doi":"10.1109/iscas45731.2020.9181218","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/nvmts.2015.7457496","name":"Hardware acceleration for neuromorphic computing: An evolving view","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nvmts.2015.7457496","authors":["Beiye Liu","Xiaoxiao Liu","Chenchen Liu","Wei Wen","M. Meng","Hai Li","Yiran Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-04-25T17:45:12Z","doi":"10.1109/nvmts.2015.7457496","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/radarconf2351548.2023.10149797","name":"Spiking Neural Networks for LPI Radar Waveform Recognition with Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/radarconf2351548.2023.10149797","authors":["Alex Henderson","Steven Harbour","Chris Yakopcic","Tarek Taha","David Brown","Justin Tieman","Garrett Hall"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-23T14:54:25Z","doi":"10.1109/radarconf2351548.2023.10149797","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/pn56061.2022.9908354","name":"Analysis of time-delay photonic reservoirs for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/pn56061.2022.9908354","authors":["P. Dmitriev","L. Di Lauro","B. Fischer","A. Aadhi","M. Chemnitz","E. Viktorov","A. Kovalev","R. Morandotti"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-10T20:25:52Z","doi":"10.1109/pn56061.2022.9908354","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/biocas.2019.8918995","name":"An Energy-Efficient Computing-in-Memory Neuromorphic System with On-Chip Training","source":"crossref","abstract":"","url":"https://doi.org/10.1109/biocas.2019.8918995","authors":["Zhao Zhao","Yuan Wang","Xinyue Zhang","Xiaoxin Cui","Ru Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-12-06T07:01:08Z","doi":"10.1109/biocas.2019.8918995","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/icnc64304.2024.10987577","name":"Adaptive Low-Rank Adaptation Based Parameter-Efficient Tuning for Low-Resource Zero-Shot Remote Sensing Image Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987577","authors":["Jianxin Duan","Peng Yang","Yingsheng Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987577","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.2139/ssrn.4379537","name":"Optical In-Memory Computing Sensor Synapse with Low-Dimensional MXene for Bio-Inspired Neuromorphic Network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4379537","authors":["Zongjie Shen","Alei Li","Chun Zhao","Jian Yao","Qianye Yang","Fangsen Li","Lixing Kang","Zhongming Zeng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-15T14:24:49Z","doi":"10.2139/ssrn.4379537","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/icnc59488.2023.10462894","name":"Fixed/preassigned-time Anti-synchronization of Complex-valued Inertial Neural Networks with Distributed Delays","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462894","authors":["Yu Yao","Guodong Zhang","Junhao Hu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462894","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.3389/fnins.2013.00186","name":"Stochastic learning in oxide binary synaptic device for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.3389/fnins.2013.00186","authors":["Shimeng Yu","Bin Gao","Zheng Fang","Hongyu Yu","Jinfeng Kang","H.-S. Philip Wong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-10-31T03:40:06Z","doi":"10.3389/fnins.2013.00186","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1088/978-0-7503-5097-6ch3","name":"Approach to neuromorphic circuits","source":"crossref","abstract":"","url":"https://doi.org/10.1088/978-0-7503-5097-6ch3","authors":["Alice C Parker"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-09T12:29:33Z","doi":"10.1088/978-0-7503-5097-6ch3","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.7567/ssdm.2019.d-4-01","name":"Artificial Synapses based on 2D Materials for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.7567/ssdm.2019.d-4-01","authors":["Lin Wang","Yong-Wei Zhang","Dongzhi Chi","Kah-Wee Ang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-07-13T22:25:06Z","doi":"10.7567/ssdm.2019.d-4-01","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/isr50024.2021.9419537","name":"Path Planning and Moving Obstacle Avoidance with Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isr50024.2021.9419537","authors":["Motoki Sakurai","Yosuke Ueno","Masaaki Kondo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-05-10T22:54:16Z","doi":"10.1109/isr50024.2021.9419537","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/mwscas53549.2025.11244564","name":"CMOS-RRAM Neuromorphic Accelerators Using Multi-Bit Neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mwscas53549.2025.11244564","authors":["Vishal Saxena","Aly Moussa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-25T18:26:55Z","doi":"10.1109/mwscas53549.2025.11244564","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1109/icons69015.2025.00035","name":"Synaptic Sampling Networks with True Random Number Generation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons69015.2025.00035","authors":["J. Darby Smith","William Severa","James B. Aimone"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-21T21:07:17Z","doi":"10.1109/icons69015.2025.00035","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1109/ijcnn64981.2025.11227429","name":"Cross-Modal Neuromorphic Semantic Segmentation based on Knowledge Distillation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn64981.2025.11227429","authors":["Dalia Hareb","Jean Martinet","Benoit Miramond"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T18:46:15Z","doi":"10.1109/ijcnn64981.2025.11227429","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.46335/ijies.2026.11.1.3","name":"A Unified, Interpretable, and Scalable Deep Learning Framework Integrating Foundation Models, Self-Supervised Learning, and Neuromorphic Computing for Robust Multi-Class Image Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.46335/ijies.2026.11.1.3","authors":["Raghavendra Rao Ankam","Burra Ramanuja Srinivas","G Maheswara Rao","S. Mallikarjunaiah"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-09T08:27:17Z","doi":"10.46335/ijies.2026.11.1.3","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.21203/rs.3.rs-4349574/v1","name":"Adiabatic Leaky Integrate-and-Fire Neurons with Tunable Refractory Period in 180nm CMOS Technology for Ultra-Low Energy Brain-Inspired Neuromorphic Computing","source":"preprints","abstract":"Abstract In recent years, the In-Memory-Computing in charge domain has gained significant interest as a promising solution to further enhance the energy efficiency of neuromorphic hardware. In this work, we explore the synergy between the brain-inspired computation and the adiabatic paradigm by presenting an adiabatic Leaky Integrate-and-Fire neuron in 180 nm CMOS technology, that is able to emulate the most important primitives for a valuable neuromorphic computation, such as the accumulation of the incoming input spikes, an exponential leakage of the membrane potential and a tunable refractory period. Differently from previous contributions in the literature, our design can exploit both the charging and recovery phases of the adiabatic operation to ensure a seamless and continuous computation, all the while exchanging energy with the power supply with an efficiency higher than 90% over a wide range of resonance frequencies, and even surpassing 99% for the lowest frequencies. Our simulations unveil a minimum energy per synaptic operation of 360 fJ at a 500 kHz resonance frequency, which yields a 12x energy saving with respect to a non-adiabatic operation.","url":"https://doi.org/10.21203/rs.3.rs-4349574/v1","authors":["Marco Massarotto","Stefano Saggini","Mirko Loghi","David Esseni"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4349574/v1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/ijcnn.2010.5596576","name":"Affordable emerging computer hardware for neuromorphic computing applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2010.5596576","authors":["Morgan Bishop","Michael J. Moore","Daniel J. Burns","Robinson E. Pino","Richard Linderman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-10-19T14:58:15Z","doi":"10.1109/ijcnn.2010.5596576","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/icnc52316.2021.9608378","name":"An inertial neuro-dynamic system for solving zero-one integer programming","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc52316.2021.9608378","authors":["Shuting Wei","Xing He"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-29T20:59:32Z","doi":"10.1109/icnc52316.2021.9608378","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1002/celc.202100457","name":"Pseudocapacitive and Ion‐Insertion Materials: A Bridge between Energy Storage, Electronics and Neuromorphic Computing","source":"crossref","abstract":"Abstract There is considerable interest in new solid‐state materials for many applications, from energy storage to electronics and neuromorphic computing. This concept paper highlights how pseudocapacitive and ion‐insertion materials, for their inherent capability of storing charge and modulate electron conduction, represent a bridge between energy storage, electronics and neuromorphic computing and enable the design of new device architectures.","url":"https://doi.org/10.1002/celc.202100457","authors":["Marina Mastragostino","Francesca Soavi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-05-11T10:32:08Z","doi":"10.1002/celc.202100457","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1088/2634-4386/ae759c","name":"Energy-efficient implementation of spiking recurrent cells on FPGA","source":"crossref","abstract":"Abstract Spiking neural networks (SNNs) can significantly reduce energy consumption compared to conventional artificial neural networks when spiking activity is sparse and the neuron model is hardware-friendly. However, biologically faithful models are often too costly for hardware implementations like field-programmable gate arrays (FPGAs), whereas highly simplified models, such as the leaky integrate-and-fire (LIF) neuron, sacrifice essential neuronal dynamics. In this work, we present an FPGA accelerator for an SNN utilizing the spiking recurrent cell (SRC) model, which offers an intermediate level of biological plausibility and hardware efficiency between simple LIF and complex conductance-based models. The SRC model features continuous spikes and critical dynamical properties like the refractory period, yet remains mathematically simple enough for efficient FPGA deployment. To optimize SRC computation, we propose a set of mathematical simplifications such as piecewise-defined approximations that eliminate costly non-linear functions ( tanh , exp ) and using scaling to avoid floating-point arithmetic. We then integrate these units into a cohesive hardware architecture using a dedicated binding layer to permit modularity and scalability of the network VHDL architecture. To demonstrate this modularity, two complete networks, with respectively 1 and 4 SRC layers, were implemented and validated using Spiking Traces (SpT) derived from, respectively, the MNIST and Fashion-MNIST datasets. Weight matrices computed offline are stored directly in LUT-registers without retraining or hardware-specific adaptation to strictly evaluate the robustness of SRC. The reference implementation achieves 96.31 % accuracy on MNIST with a 220 -image SpT and a processing time of 1.7424 ms per digit. We further investigate accuracy-energy trade-offs by reducing the SpT length and quantizing synaptic weights down to 4 bits , achieving 93.32 % accuracy at 0.492 mJ per digit ( 55 images , 5 -bit weights) and 92.89 % at 0.394 mJ ( 44 images , 4 -bit weights). These results demonstrate that SRC-based SNNs deliver competitive performance and low energy consumption while preserving richer neuronal dynamics than standard LIF models.","url":"https://doi.org/10.1088/2634-4386/ae759c","authors":["Pascal Harmeling","Florent De Geeter","Guillaume Drion"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-01T22:51:28Z","doi":"10.1088/2634-4386/ae759c","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1109/aicas48895.2020.9073791","name":"Fault-Tolerant-Driven Clustering for Large Scale Neuromorphic Computing Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aicas48895.2020.9073791","authors":["Yuting Wu","Bo Ding","Qi Xu","Song Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-04-24T01:16:57Z","doi":"10.1109/aicas48895.2020.9073791","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1016/j.chip.2025.100170","name":"The rise of two-dimensional materials based memtransistors for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.chip.2025.100170","authors":["Tian Tan","Qing Xu","Xuewei Feng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-21T06:38:25Z","doi":"10.1016/j.chip.2025.100170","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.4018/979-8-3693-6303-4","name":"Revolutionizing AI with Brain-Inspired Technology","source":"crossref","abstract":"","url":"https://doi.org/10.4018/979-8-3693-6303-4","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-29T15:16:27Z","doi":"10.4018/979-8-3693-6303-4","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1039/d5ma01008j/v2/review2","name":"Review for \"Controlling the phase transition dynamics of GeTe by Sn substitution for phase change memory, photodetection and neuromorphic devices\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5ma01008j/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-28T21:10:51Z","doi":"10.1039/d5ma01008j/v2/review2","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1088/2634-4386/ad2ec3","name":"Gradient-descent hardware-aware training and deployment for mixed-signal neuromorphic processors","source":"crossref","abstract":"Abstract Mixed-signal neuromorphic processors provide extremely low-power operation for edge inference workloads, taking advantage of sparse asynchronous computation within spiking neural networks (SNNs). However, deploying robust applications to these devices is complicated by limited controllability over analog hardware parameters, as well as unintended parameter and dynamical variations of analog circuits due to fabrication non-idealities. Here we demonstrate a novel methodology for offline training and deployment of SNNs to the mixed-signal neuromorphic processor DYNAP-SE2. Our methodology applies gradient-based training to a differentiable simulation of the mixed-signal device, coupled with an unsupervised weight quantization method to optimize the network’s parameters. Parameter noise injection during training provides robustness to the effects of quantization and device mismatch, making the method a promising candidate for real-world applications under hardware constraints and non-idealities. This work extends Rockpool, an open-source deep-learning library for SNNs, with support for accurate simulation of mixed-signal SNN dynamics. Our approach simplifies the development and deployment process for the neuromorphic community, making mixed-signal neuromorphic processors more accessible to researchers and developers.","url":"https://doi.org/10.1088/2634-4386/ad2ec3","authors":["Ugurcan Cakal","Maryada","Chenxi Wu","Ilkay Ulusoy","Dylan Richard Muir"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-29T22:23:49Z","doi":"10.1088/2634-4386/ad2ec3","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1002/advs.202515926","name":"Polarity‐Controlled Volatile HfO\n                    <sub>2</sub>\n                    Memristors with Bimodal Conductance for Neuromorphic Synapses and Reservoir Computing","source":"europepmc","abstract":"Abstract In this work, an HfO 2 ‐based memristor exhibiting bimodal switching, wherein the device's conductance is modulated not only by the input stimulus but also by the polarity of the read voltage, is introduced. Uniquely, this device demonstrates reliable short‐term memory (STM)‐like behavior and supports 16 well‐separated conductance states through 4‐bit pulsed inputs. Remarkably, under the same input conditions, reversing the polarity of the read voltage results in 16 more different conductance states, thereby doubling the number of levels that can be distinguished per cell. Employing the proposed device, a reservoir computing (RC) system, which takes advantage of this rich representational capability, is created. The system achieves a high classification accuracy of 98.81% on the MNIST dataset. These results show how powerful memristor‐based architectures can be and how this device could be a compact and energy‐efficient platform for the next generation of neuromorphic computing.","url":"https://doi.org/10.1002/advs.202515926","authors":["Yuseong Jang","Chanmin Hwang","Myoungsu Chae","Taegi Kim","Hee‐Dong Kim"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025-11-03T09:22:02Z","doi":"10.1002/advs.202515926","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2172/2001788","name":"Neuromorphic Architectures: Efficient and Parallel Post-Moore Scientific Computing Potential.","source":"crossref","abstract":"","url":"https://doi.org/10.2172/2001788","authors":["John Smith","William Severa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-03T03:01:15Z","doi":"10.2172/2001788","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/vtc2024-spring62846.2024.10683049","name":"Efficient Hardware Acceleration of Spiking Neural Networks Using FPGA: Towards Real-Time Edge Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/vtc2024-spring62846.2024.10683049","authors":["Soukaina El Maachi","Abdellah Chehri","Rachid Saadane"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-25T17:28:12Z","doi":"10.1109/vtc2024-spring62846.2024.10683049","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.3390/jlpea15030050","name":"Alleviating the Communication Bottleneck in Neuromorphic Computing with Custom-Designed Spiking Neural Networks","source":"crossref","abstract":"For most, if not all, AI-accelerated hardware, communication with the agent is expensive and heavily bottlenecks the hardware performance. This omnipresent hardware restriction is also found in neuromorphic computing: a novel style of computing that involves deploying spiking neural networks to specialized hardware to achieve low size, weight, and power (SWaP) compute. In neuromorphic computing, spike trains, times, and values are used to communicate information to, from, and within the spiking neural network. Input data, in order to be presented to a spiking neural network, must first be encoded as spikes. After processing the data, spikes are communicated by the network that represent some classification or decision that must be processed by decoder logic. In this paper, we first present principles for interconverting between spike trains, times, and values using custom-designed spiking subnetworks. Specifically, we present seven networks that encompass the 15 conversion scenarios between these encodings. We then perform three case studies where we either custom design a novel network or augment existing neural networks with these conversion subnetworks to vastly improve their communication performance with the outside world. We employ a classic space vs. time tradeoff by pushing spike data encoding and decoding techniques into the network mesh (increasing space) in order to minimize intra- and extranetwork communication time. This results in a classification inference speedup of 23× and a control inference speedup of 4.3× on field-programmable gate array hardware.","url":"https://doi.org/10.3390/jlpea15030050","authors":["James S. Plank","Charles P. Rizzo","Bryson Gullett","Keegan E. M. Dent","Catherine D. Schuman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-08T11:51:12Z","doi":"10.3390/jlpea15030050","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1088/2634-4386/ae6a19","name":"Mobile-compatible neuromorphic optical computing enabled by dual-emission photonic materials","source":"crossref","abstract":"Abstract Artificial intelligence (AI) and neuromorphic computing demand hardware platforms that combine energy efficiency with physically informed data processing. Photonics offers unique advantages in this context, but optical neuromorphic systems in which memory and information processing arise from intrinsic material dynamics remain scarce. We demonstrate a photonic layer in which history-dependent material photophysics implements physically embedded information processing before digital learning, using luminescent phosphors. The photonic layer exhibits dual fluorescence and phosphorescence together with excitation-history-dependent photoactivation dynamics that emulate synaptic functionalities, including short-term memory, long-term memory, and synaptic potentiation. Quantitative analysis and modelling reveal efficient nanoscale interlamellar energy transfer consistent with the lamellar material morphology, establishing a link between structure and function. When integrated as an active optical front-end within a hybrid photonic–digital AI architecture, the photonic layer performs a material-based transformation of input data before digital learning. Using a laboratory-based optical readout, classification accuracy comparable to state-of-the-art hybrid neuromorphic computing (approximately 94%) is achieved while requiring fewer training epochs. A mobile-compatible implementation based on smartphone optical readout yields similar accuracy, demonstrating robustness to non-specialized optical hardware. These results outline a general strategy for neuromorphic photonic systems in which functional materials act as adaptive computational primitives, enabling energy-efficient computing architectures.","url":"https://doi.org/10.1088/2634-4386/ae6a19","authors":["Lília M S Dias","Ana R Bastos","Lianshe Fu","Albano N Carneiro Neto","Rui F P Pereira","Verónica de Zea Bermudez","Elias Towe","Rute A S Ferreira","Paulo S B André"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-07T22:51:58Z","doi":"10.1088/2634-4386/ae6a19","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1016/b978-0-323-98829-2.00002-5","name":"Neuromorphic photonics: development of the field","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-323-98829-2.00002-5","authors":["Xuhan Guo","Yikai Su"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-18T15:12:00Z","doi":"10.1016/b978-0-323-98829-2.00002-5","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1016/b978-0-323-98829-2.00004-9","name":"Optoelectronic synapses for two-dimensional neuromorphic photonics","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-323-98829-2.00004-9","authors":["Xi Chen","Runze Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-18T15:12:14Z","doi":"10.1016/b978-0-323-98829-2.00004-9","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.3389/fnins.2021.608567","name":"Is Neuromorphic MNIST Neuromorphic? Analyzing the Discriminative Power of Neuromorphic Datasets in the Time Domain","source":"crossref","abstract":"A major characteristic of spiking neural networks (SNNs) over conventional artificial neural networks (ANNs) is their ability to spike, enabling them to use spike timing for coding and efficient computing. In this paper, we assess if neuromorphic datasets recorded from static images are able to evaluate the ability of SNNs to use spike timings in their calculations. We have analyzed N-MNIST, N-Caltech101 and DvsGesture along these lines, but focus our study on N-MNIST. First we evaluate if additional information is encoded in the time domain in a neuromorphic dataset. We show that an ANN trained with backpropagation on frame-based versions of N-MNIST and N-Caltech101 images achieve 99.23 and 78.01% accuracy. These are comparable to the state of the art—showing that an algorithm that purely works on spatial data can classify these datasets. Second we compare N-MNIST and DvsGesture on two STDP algorithms, RD-STDP, that can classify only spatial data, and STDP-tempotron that classifies spatiotemporal data. We demonstrate that RD-STDP performs very well on N-MNIST, while STDP-tempotron performs better on DvsGesture. Since DvsGesture has a temporal dimension, it requires STDP-tempotron, while N-MNIST can be adequately classified by an algorithm that works on spatial data alone. This shows that precise spike timings are not important in N-MNIST. N-MNIST does not, therefore, highlight the ability of SNNs to classify temporal data. The conclusions of this paper open the question—what dataset can evaluate SNN ability to classify temporal data?","url":"https://doi.org/10.3389/fnins.2021.608567","authors":["Laxmi R. Iyer","Yansong Chua","Haizhou Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-25T07:57:44Z","doi":"10.3389/fnins.2021.608567","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/aiiot68874.2026.11569565","name":"Multimodal Neuromorphic Computing for Cancer Diagnosis: Architecture, Clinical Fusion and Energy Analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aiiot68874.2026.11569565","authors":["Shruti Bhandari","Md Shaba Sayeed","Sanjog Dhakal","Tolga Ensari","Robin Ghosh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-22T19:53:10Z","doi":"10.1109/aiiot68874.2026.11569565","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1108/17563781011028569","name":"Evolving neuromorphic flight control for a flapping‐wing mechanical insect","source":"crossref","abstract":"Purpose The purpose of this paper is to present an approach to employ evolvable hardware concepts, to effectively construct flapping‐wing mechanism controllers for micro robots, with the evolved dynamically complex controllers embedded in a, physically realizable, micro‐scale reconfigurable substrate. Design/methodology/approach In this paper, a continuous time recurrent neural network (CTRNN)‐evolvable hardware (a neuromorphic variant of evolvable hardware) framework and methodologies are employed in the process of designing the evolution experiments. CTRNN is selected as the neuromorphic reconfigurable substrate with most efficient Minipop Evolutionary Algorithm, configured to drive the evolution process. The uniqueness of the reconfigurable CTRNN substrate preferred for this study is perceived from its universal dynamics approximation capabilities and prospective to realize the same in small area and low power chips, the properties which are very much a basic requirement for flapping‐wing based micro robot control. A simulated micro mechanical flapping insect model is employed to conduct the feasibility study of evolving neuromorphic controllers using the above‐mentioned methodology. Findings It has been demonstrated that the presented neuromorphic evolvable hardware approach can be effectively used to evolve controllers, to produce various flight dynamics like cruising, steering, and altitude gain in a simulated micro mechanical insect. Moreover, an appropriate feasibility is presented, to realize the evolved controllers in small area and lower power chips, with available fabrication techniques and as well as utilizing the complex dynamics nature of CTRNNs to encompass various controls ability in a architecturally static hardware circuit, which are more pertinent to meet the constraints of micro robot construction and control. Originality/value The proposed neuromorphic evolvable hardware approach along with its modules intact (CTRNNs and Minipop) can provide a general mechanism to construct/evolve dynamically complex and optimal controllers for flapping‐wing mechanism based micro robots for various environments with least human intervention. Further, the evolved neuromorphic controllers in simulation study can be successfully transferred to its hardware counterpart without sacrificing its anticipated functionality and realized within a predictable area and power ranges.","url":"https://doi.org/10.1108/17563781011028569","authors":["Sanjay K. Boddhu","John C. Gallagher"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-03-27T08:08:44Z","doi":"10.1108/17563781011028569","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/ecai52376.2021.9515144","name":"TaO<sub>x</sub> based memristor model and its emulator design for future neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ecai52376.2021.9515144","authors":["Pratyusha Nune","Santanu Mandal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-08-23T22:03:11Z","doi":"10.1109/ecai52376.2021.9515144","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1088/2634-4386/acc2e1","name":"Perspective on investigation of neurodegenerative diseases with neurorobotics approaches","source":"crossref","abstract":"Abstract Neurorobotics has emerged from the alliance between neuroscience and robotics. It pursues the investigation of reproducing living organism-like behaviors in robots by means of the embodiment of computational models of the central nervous system. This perspective article discusses the current trend of implementing tools for the pressing challenge of early-diagnosis of neurodegenerative diseases and how neurorobotics approaches can help. Recently, advances in this field have allowed the testing of some neuroscientific hypotheses related to brain diseases, but the lack of biological plausibility of developed brain models and musculoskeletal systems has limited the understanding of the underlying brain mechanisms that lead to deficits in motor and cognitive tasks. Key aspects and methods to enhance the reproducibility of natural behaviors observed in healthy and impaired brains are proposed in this perspective. In the long term, the goal is to move beyond finding therapies and look into how researchers can use neurorobotics to reduce testing on humans as well as find root causes for disease.","url":"https://doi.org/10.1088/2634-4386/acc2e1","authors":["Silvia Tolu","Beck Strohmer","Omar Zahra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-09T22:28:14Z","doi":"10.1088/2634-4386/acc2e1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1038/s41578-022-00434-z","name":"Dynamical memristors for higher-complexity neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s41578-022-00434-z","authors":["Suhas Kumar","Xinxin Wang","John Paul Strachan","Yuchao Yang","Wei D. Lu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-08T12:02:46Z","doi":"10.1038/s41578-022-00434-z","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1201/9781003119784-9","name":"A Review of Neuromorphic Computing: A Promising Approach for the IoT-Based Smart Manufacturing","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003119784-9","authors":["R. Joshua Arul Kumar","S. Titus","B. Janet"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-01-04T15:29:51Z","doi":"10.1201/9781003119784-9","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1088/1674-1056/ac89dd","name":"Switching plasticity in compensated ferrimagnetic multilayers for neuromorphic computing","source":"crossref","abstract":"Current-induced multilevel magnetization switching in ferrimagnetic spintronic devices is highly pursued for the application in neuromorphic computing. In this work, we demonstrate the switching plasticity in Co/Gd ferrimagnetic multilayers where the binary states magnetization switching induced by spin–orbit toque can be tuned into a multistate one as decreasing the domain nucleation barrier. Therefore, the switching plasticity can be tuned by the perpendicular magnetic anisotropy of the multilayers and the in-plane magnetic field. Moreover, we used the switching plasticity of Co/Gd multilayers for demonstrating spike timing-dependent plasticity and sigmoid-like activation behavior. This work gives useful guidance to design multilevel spintronic devices which could be applied in high-performance neuromorphic computing.","url":"https://doi.org/10.1088/1674-1056/ac89dd","authors":["Weihao Li","Xiukai Lan","Xionghua Liu","Enze Zhang","Yongcheng Deng","Kaiyou Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-08-16T09:44:18Z","doi":"10.1088/1674-1056/ac89dd","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/nice65350.2025.11065299","name":"The Spatial Effect of the Pinna for Neuromorphic Speech Denoising","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nice65350.2025.11065299","authors":["Ranganath Selagamsetty","Joshua San Miguel","Mikko Lipasti"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-08T13:36:20Z","doi":"10.1109/nice65350.2025.11065299","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1109/biocas67066.2025.00131","name":"Neuromorphic Classification of Geophone Signals with Legendre Memory Units","source":"crossref","abstract":"","url":"https://doi.org/10.1109/biocas67066.2025.00131","authors":["Avi Hazan","Shlomo Greenberg","Elishai Ezra Tsur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-14T20:38:47Z","doi":"10.1109/biocas67066.2025.00131","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1109/biocas67066.2025.00144","name":"Adaptive Spatial Hysteresis for Neuromorphic Winner-Take-All ISFET Clusters","source":"crossref","abstract":"","url":"https://doi.org/10.1109/biocas67066.2025.00144","authors":["Tanmay Lad","Prateek Tripathi","Pantelis Georgiou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-14T20:38:47Z","doi":"10.1109/biocas67066.2025.00144","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1039/d5ma01008j/v1/review1","name":"Review for \"Controlling the phase transition dynamics of GeTe by Sn substitution for phase change memory, photodetection and neuromorphic devices\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5ma01008j/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-28T21:10:51Z","doi":"10.1039/d5ma01008j/v1/review1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1109/icee56203.2022.10118104","name":"Performance of Graphene Oxide-based Memristor for Nonvolatile Memory and Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icee56203.2022.10118104","authors":["Kanupriya Varshney","Mani Shankar Yadav","Devarshi M. Das","Brajesh Rawat"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-15T17:51:05Z","doi":"10.1109/icee56203.2022.10118104","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/aspdac.2016.7428023","name":"Thermal optimization for memristor-based hybrid neuromorphic computing systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aspdac.2016.7428023","authors":["Chi-Ruo Wu","Wei Wen","Tsung-Yi Ho","Yiran Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-03-10T16:48:08Z","doi":"10.1109/aspdac.2016.7428023","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1038/s41598-021-03594-0","name":"Comparing different nonlinearities in readout systems for optical neuromorphic computing networks","source":"crossref","abstract":"Abstract Nonlinear activation is a crucial building block of most machine-learning systems. However, unlike in the digital electrical domain, applying a saturating nonlinear function in a neural network in the analog optical domain is not as easy, especially in integrated systems. In this paper, we first investigate in detail the photodetector nonlinearity in two main readout schemes: electrical readout and optical readout. On a 3-bit-delayed XOR task, we show that optical readout trained with backpropagation gives the best performance. Furthermore, we propose an additional saturating nonlinearity coming from a deliberately non-ideal voltage amplifier after the detector. Compared to an all-optical nonlinearity, these two kinds of nonlinearities are extremely easy to obtain at no additional cost, since photodiodes and voltage amplifiers are present in any system. Moreover, not having to design ideal linear amplifiers could relax their design requirements. We show through simulation that for long-distance nonlinear fiber distortion compensation, using only the photodiode nonlinearity in an optical readout delivers BER improvements over three orders of magnitude. Combined with the amplifier saturation nonlinearity, we obtain another three orders of magnitude improvement of the BER.","url":"https://doi.org/10.1038/s41598-021-03594-0","authors":["Chonghuai Ma","Joris Lambrecht","Floris Laporte","Xin Yin","Joni Dambre","Peter Bienstman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-17T11:14:56Z","doi":"10.1038/s41598-021-03594-0","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1088/2634-4386/ad05da","name":"Spike-based local synaptic plasticity: a survey of computational models and neuromorphic circuits","source":"crossref","abstract":"Abstract Understanding how biological neural networks carry out learning using spike-based local plasticity mechanisms can lead to the development of real-time, energy-efficient, and adaptive neuromorphic processing systems. A large number of spike-based learning models have recently been proposed following different approaches. However, it is difficult to assess if these models can be easily implemented in neuromorphic hardware, and to compare their features and ease of implementation. To this end, in this survey, we provide an overview of representative brain-inspired synaptic plasticity models and mixed-signal complementary metal–oxide–semiconductor neuromorphic circuits within a unified framework. We review historical, experimental, and theoretical approaches to modeling synaptic plasticity, and we identify computational primitives that can support low-latency and low-power hardware implementations of spike-based learning rules. We provide a common definition of a locality principle based on pre- and postsynaptic neural signals, which we propose as an important requirement for physical implementations of synaptic plasticity circuits. Based on this principle, we compare the properties of these models within the same framework, and describe a set of mixed-signal electronic circuits that can be used to implement their computing principles, and to build efficient on-chip and online learning in neuromorphic processing systems.","url":"https://doi.org/10.1088/2634-4386/ad05da","authors":["Lyes Khacef","Philipp Klein","Matteo Cartiglia","Arianna Rubino","Giacomo Indiveri","Elisabetta Chicca"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-23T18:32:23Z","doi":"10.1088/2634-4386/ad05da","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1007/978-3-032-09586-2_1","name":"Introduction","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-09586-2_1","authors":["Felix Staudigl","Rainer Leupers"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-22T14:21:59Z","doi":"10.1007/978-3-032-09586-2_1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1088/2634-4386/ae5fc6","name":"Unsupervised feature learning in spiking neural networks using nonlinear interface dipole modulation-based synaptic devices","source":"crossref","abstract":"Abstract Recently, a three-terminal interface dipole modulation field-effect transistor (IDM FET) memory device has been proposed that leverages electric-field-induced dipole modulation at oxide/oxide interfaces. This device has been reported to exhibit a double-pulse-induced response analogous to the spike-timing-dependent plasticity (STDP) observed in biological synapses. Although the STDP behavior of the IDM FET exhibits pronounced nonlinearity, previous simulation studies have suggested that it can still be applied to unsupervised feature learning in spiking neural networks (SNNs) when combined with an additional frequency-independent (FI) depression operation. In this study, we first briefly review the nonlinear IDM response based on experimental observations and clarify that the nonlinearity is intrinsic to the IDM interface, originating from changes in the interface dipole states. We then present the synaptic weight-update model of IDM FETs employed in our SNN simulations and analyze the weight-update dynamics during feature learning using a simple single-layer SNN. Based on this analysis, we examine the optimal update conditions in terms of the balance between potentiation and depression rates. Furthermore, we evaluate feature learning on the MNIST handwritten-digit dataset using a two-layer network. Based on frequency-dependent rate-equilibrium considerations, we propose a switching FI depression/potentiation algorithm to improve feature‐learning performance, demonstrating enhanced robustness, improved classification accuracy, and reasonable tolerance to device-to-device variation.","url":"https://doi.org/10.1088/2634-4386/ae5fc6","authors":["Noriyuki Miyata"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-15T22:51:42Z","doi":"10.1088/2634-4386/ae5fc6","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1109/cine68769.2026.11502673","name":"Spiking Neural Networks in Neuromorphic Computing: A New Paradigm for Machine Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cine68769.2026.11502673","authors":["Prasanta Panda","Debaryaan Sahoo","Mukundan A P","Debarjun Sahoo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-08T19:37:10Z","doi":"10.1109/cine68769.2026.11502673","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1515/9783111545950-013","name":"227Appendix","source":"crossref","abstract":"","url":"https://doi.org/10.1515/9783111545950-013","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-06T19:15:47Z","doi":"10.1515/9783111545950-013","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1109/icct-europe63283.2025.11157664","name":"Compact Memristive Neuromorphic Braille Keyboard","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icct-europe63283.2025.11157664","authors":["Vasudev S Mallan","Aidana Irmanova","Alex P James"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-17T17:29:26Z","doi":"10.1109/icct-europe63283.2025.11157664","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1109/icnc52316.2021.9609046","name":"Uniform Stability of Fractional-order Memristive Neural Networks with Hybrid Time-Varying Delays","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc52316.2021.9609046","authors":["Xiaofang Hu","Leimin Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-29T20:59:32Z","doi":"10.1109/icnc52316.2021.9609046","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1088/2634-4386/acb37f","name":"Pre-synaptic DC bias controls the plasticity and dynamics of three-terminal neuromorphic electrolyte-gated organic transistors","source":"crossref","abstract":"Abstract The role of pre-synaptic DC bias is investigated in three-terminal organic neuromorphic architectures based on electrolyte-gated organic transistors—EGOTs. By means of pre-synaptic offset it is possible to finely control the number of discrete conductance states in short-term plasticity experiments, to obtain, at will, both depressive and facilitating response in the same neuromorphic device and to set the ratio between two subsequent pulses in paired-pulse experiments. The charge dynamics leading to these important features are discussed in relationship with macroscopic device figures of merit such as conductivity and transconductance, establishing a novel key enabling parameter in devising the operation of neuromorphic organic electronics.","url":"https://doi.org/10.1088/2634-4386/acb37f","authors":["Federico Rondelli","Anna De Salvo","Gioacchino Calandra Sebastianella","Mauro Murgia","Luciano Fadiga","Fabio Biscarini","Michele Di Lauro"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-16T22:31:38Z","doi":"10.1088/2634-4386/acb37f","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.29363/nanoge.matnec.2022.017","name":"Resistive memories to enable frugal AI devices","source":"crossref","abstract":"","url":"https://doi.org/10.29363/nanoge.matnec.2022.017","authors":["Elisa Vianello","Filippo Moro","Tifenn Hirtzlin","Emmanuel Hardy","Bruno Fain","Melika Payvand","Damien Querlioz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-30T08:35:25Z","doi":"10.29363/nanoge.matnec.2022.017","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1149/2.f08231if","name":"Special Issue of Interface on Neuromorphic Computing: An Introduction and State of the Field","source":"crossref","abstract":"The human brain integrates and processes information to perform complex cognitive tasks within approximately 20 watts of power. Today’s fastest supercomputer is unable to deliver the power requirements and the number of operations at the same energy levels. In the brain, the discrete and sparse events in time called spikes are used to process and encode the information. The energy efficiency of the brain is attributed to the sparsity of the spikes and event-driven communication between the neurons. Complex interconnections among the 1011 neurons and 1015 synapses in the human brain process the information, possibly encoded in the time, frequency, and phase of the spikes. Therefore, to emulate human cognition requires novel electronic devices and new algorithmic approaches. Brain-inspired computing, or neuromorphic computing, is an approach to build energy-efficient computing architectures and systems.","url":"https://doi.org/10.1149/2.f08231if","authors":["Durgamadhab Misra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-31T12:46:17Z","doi":"10.1149/2.f08231if","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1088/2634-4386/ae4f1e","name":"Hyperdimensional decoding of spiking neural networks","source":"crossref","abstract":"Abstract This work presents a novel spiking neural network (SNN) decoding method, combining SNNs with hyperdimensional computing (HDC). This decoding method is designed to achieve high accuracy, high noise robustness, low inference latency and low energy consumption. Compared to analogous architectures decoded with existing approaches, the SNN-HDC model attains generally better classification accuracy, lower inference latency, lower spike count and lower estimated energy consumption on multiple test cases from the literature. The SNN-HDC achieved spike count reductions of 1.74 × to 3.36 × on the DvsGesture dataset and 1.36 × to 2.70 × on the SL-Animals-DVS dataset. The SNN-HDC achieved estimated energy consumption reductions of 1.24 × to 3.67 × on the DvsGesture dataset and 1.38 × to 2.27 × on the SL-Animals-DVS dataset. The proposed decoding method enables detection of classes unseen during training. On the DvsGesture dataset, the SNN-HDC model can detect 100% of samples from an unseen/untrained class. The findings suggest the proposed decoding method is a compelling alternative to both rate and latency decoding.","url":"https://doi.org/10.1088/2634-4386/ae4f1e","authors":["Cedrick Kinavuidi","Luca Peres","Oliver Rhodes"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-19T09:50:36Z","doi":"10.1088/2634-4386/ae4f1e","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1109/aicas64808.2025.11173130","name":"ViT-LCA: A Neuromorphic Approach for Vision Transformers","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aicas64808.2025.11173130","authors":["Sanaz Mahmoodi Takaghaj"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-25T17:52:35Z","doi":"10.1109/aicas64808.2025.11173130","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:19.714Z"},{"id":"doi:10.1002/advs.77065","name":"Battery-Inspired Electrochemical Synapses for Neuromorphic Applications.","source":"europepmc","abstract":"Artificial synapses capable of analog memory and adaptive learning are key components for neuromorphic computing systems. To emulate biological synaptic functions effectively, artificial devices must exhibit gradual conductance modulation, linear responses to pulse stimuli, diverse forms of synaptic plasticity, and low-power operation. Ion-mediated electrochemical devices have recently emerged as promising candidates for such functionalities because ionic redistribution can continuously modify the internal electrochemical state of materials and naturally produce history-dependent conductance changes. This review discusses recent advances in battery-ion-inspired synaptic devices that exploit electrochemical processes to implement artificial synaptic behavior. We first outline the fundamental electrochemical mechanisms underlying ion-mediated state modulation, including ion insertion/accumulation, intercalation, migration, and diffusion. We then survey the materials landscape for battery-inspired synaptic devices, covering electrolytes and active channel materials such as transition metal oxides, two-dimensional materials, and organic mixed ionic-electronic conductors. Emerging applications in neuromorphic computing and neuromorphic biosensing are revisited, where ionic dynamics enable the integration of sensing, memory, and computation. Key challenges related to device reliability, scalability, and environmental stability are discussed, together with future perspectives for advancing battery-ion-based neuromorphic technologies.","url":"https://doi.org/10.1002/advs.77065","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.77065","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/smll.74638","name":"Array of Cointegrated Transistor-Based Artificial Neurons and Synapses for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.74638","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.74638","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1002/advs.75861","name":"Photonic-Enabled Energy-Efficient Transparent Neuromorphic Computing Devices: A Review.","source":"europepmc","abstract":"ABSTRACT In the evolving field of artificial intelligence (AI), two notable trends are emerging: the rapid growth of large AI model sizes and the surge of vast amounts of data. Moore's law emphasizes the need for alternative computing paradigms to meet the rising demand for computational power and address von Neumann model constraints. Nowadays, neuromorphic computing, inspired by the mechanisms and functionality of human brains, uses physical artificial neurons to do computations and is drawing widespread attention. Neuromorphic computing aims to emulate brain‐like information processing with co‐localized memory and logic, breaking the von Neumann bottleneck. In this regard, the integration of photonic materials in computing led to growth in photonic computing, where light is a fundamental source of energy and can also be utilized as a signal for neuromorphic computing. Photonic computing enables ultrafast artificial neural networks with sub‐nanosecond latencies and low heat dissipation. However, current neuromorphic technologies still struggle to achieve petascale speed and energy efficiency. Additionally, the general benefits of neuromorphic computing and AI can be realized in an optically transparent manner, broadening their applications in bionics and human interfaces. This review explores the suitability and design strategies for transparent photonic devices that create artificial interfaces mimicking natural functions.","url":"https://doi.org/10.1002/advs.75861","authors":["Shuvaraj Ghosh","Ki‐bum Lee","Junghyeon Lee","Seunghee Cho","Malkeshkumar Patel","Hangfei Li","Yu Wen","Ye Zhou","Joondong Kim"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.75861","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acsnano.6c05264","name":"Tactile Neuromorphic Ion-Gated Vertical Transistor Displays Enabling Dual-Output Reservoir Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.6c05264","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsnano.6c05264","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/advs.77437","name":"Wafer-Scale 3D Integration for High-Density Multi-Valued Neuromorphic Logic.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.77437","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.77437","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/advs.75742","name":"Neuromorphic Near-Sensor and In-Sensor Computing Enabled by Next-Generation Material-Based Sensors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.75742","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.75742","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/advs.77076","name":"Coexisting Volatile and Nonvolatile Switching in 3D ALD-IGZO Vertical RRAM for Fully Hardware-Based Wide Reservoir Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.77076","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.77076","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/adma.74192","name":"Charge-Encoded Sidechains Enable Deterministic Ion Ingress and Memory Retention in Organic Electrochemical Synaptic Transistors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.74192","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.74192","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/adma.74529","name":"Noise-Tunable Memristor Enabling Programmable Probabilistic Neurons for Frequency-Selective Time-Series Signal Encoding.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.74529","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.74529","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/advs.202600064","name":"Sustainable Synaptic Device with Two-Dimensional Ferroelectric Materials for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202600064","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.202600064","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/smll.73836","name":"A Bilayer Rare-Earth/High-κ Oxide Memristor for Energy-Efficient Neuromorphic Intelligence.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.73836","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.73836","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1038/s41467-026-72971-y","name":"A ferroelectric-ionic-trapping transistor for low power and secure neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-72971-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-72971-y","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1007/s40820-026-02214-8","name":"A Review on Multi-Level Asymmetric Design for 2D Neuromorphic Devices.","source":"europepmc","abstract":"Asymmetry has emerged as a critical design strategy for implementing essential neuromorphic functionalities, such as directional signal propagation, programmable plasticity, and bio-inspired dynamics. This principle involves deliberately breaking symmetry at various scales, which introduces unique physical phenomena including spontaneous built-in fields, anisotropic carrier transport, and memristive switching, which are foundational to synaptic and neuronal emulation. Despite growing research, a systematic synthesis of how asymmetry function across different design levels is lacking, hindering the development of guiding design principles. This review bridges this gap by systematically examining asymmetric engineering across three levels: materials, structures, and device. Benefiting from the inherent structural and electronic versatility of two-dimensional (2D) materials, their unique physical properties arising from such multi-level asymmetry for emulating and regulating synaptic plasticity are analyzed to demonstrate the resultant functional diversity and tunability of neuromorphic devices. Furthermore, existing challenges are discussed and a forward-looking perspective on integrating multiple asymmetries and extending the concept to circuit and system levels is provided. This work aims to establish a coherent design framework and provide a unique pathway for developing next-generation neuromorphic intelligent hardware based on 2D materials.","url":"https://doi.org/10.1007/s40820-026-02214-8","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s40820-026-02214-8","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acsami.6c03922","name":"Ultralow Energy Optoelectronic Synapse Using Halide Perovskite/Organic Semiconductor Heterostructure for Neuromorphic Computing, Optical Logic and Wireless Communication.","source":"europepmc","abstract":"With the advancement of artificial intelligence, the emulation of biological neural processes through neuromorphic computing has gained significant attention. Artificial optoelectronic synapses have emerged as promising components for neuromorphic computing due to their simple structure, low energy consumption, and ability to overcome the von Neumann bottleneck. Here, we design a multifunctional, energy-efficient optoelectronic synapse based on a formamidinium cesium lead iodide (FA x Cs 1- x PbI 3 )/Poly(3-hexylthiophene) (P3HT) heterojunction in a two-terminal vertical structure. The synaptic device exhibits key synaptic characteristics, such as excitatory postsynaptic current (EPSC), paired-pulse facilitation (PPF), and achieves a transition from short-term to long-term memory with an exceptionally low energy consumption of 0.59 fJ per synaptic event, and successfully emulates biological learning behavior, such as learning-forgetting-relearning. Long-term potentiation (LTP) enables efficient visual object recognition with 90.31% accuracy on the Modified National Institute of Standards and Technology (MNIST) data set using an artificial neural network (ANN). In addition, light logic functions (\"AND\", \"OR\") and associative learning (Pavlov's dog experiment) are demonstrated using 405 and 532 nm pulses. More significantly, optical wireless communication is experimentally performed using Morse code for words such as IITG, 2025, HELP, and SOS. Moreover, the device achieves 86.76% pixel-wise accuracy in the semantic segmentation of urban street scenes using a U-Net model. Finally, the working mechanism of the device, attributed to the efficient photogeneration of carriers and accumulation of electrons at the perovskite side, offers deep insights into the optoelectronic plasticity. These findings show the path toward the development of a highly integrated, photonic neuromorphic device for future intelligent systems.","url":"https://doi.org/10.1021/acsami.6c03922","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.6c03922","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acsnano.6c01958","name":"Surface Acoustic Wave-Guided Reconfigurable Memristor.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.6c01958","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsnano.6c01958","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acs.nanolett.5c06511","name":"Iodide-Coated CsPbBr&lt;sub&gt;3&lt;/sub&gt; Perovskite Nanowires for Resistive-Switching Memory in Neuromorphic Systems and Edge Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.5c06511","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acs.nanolett.5c06511","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1007/s40820-026-02191-y","name":"In-Sensor-Memory Computing for Post-Von Neumann Intelligence: A Perspective.","source":"europepmc","abstract":"The rapid growth of artificial intelligence, ubiquitous sensing, and edge computing is exposing fundamental limitations of conventional von Neumann architectures, in which the physical separation of sensing, memory, and computation leads to excessive data movement, high energy consumption, and latency. As transistor scaling slows in the post-Moore era, architectural innovation has become essential to sustain progress in intelligent systems. In-sensor-memory computing (ISMC) addresses these challenges by co-locating perception, storage, and computation within unified device and system architectures, enabling in situ signal processing, mixed-signal computation, and event-driven intelligence at the data source. Recent advances in memristive and ferroelectric devices, low-dimensional and multifunctional materials, three-dimensional heterogeneous integration, and neuromorphic architectures have significantly expanded the functional scope of ISMC platforms. In parallel, the co-evolution of algorithms-including spiking neural networks, reservoir computing, and neuromorphic compilers-has facilitated the translation of device-level advantages into system-level performance. This perspective surveys the technological foundations, architectural trends, and emerging applications of ISMC, examines global industry-academia-research (IAR) collaboration, and outlines key challenges related to variability, reliability, scalability, and benchmarking. Collectively, ISMC is positioned as a post-von Neumann hardware paradigm for energy-efficient, distributed intelligence.","url":"https://doi.org/10.1007/s40820-026-02191-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s40820-026-02191-y","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1007/s40820-026-02158-z","name":"Hafnium-Based Ferroelectric Post-Moore Electronics: Device Physics, Integration Architectures, and Neuromorphic System Implementation.","source":"europepmc","abstract":"Hafnium-based ferroelectric (Hf-FEs) materials overcome the limitations of perovskite ferroelectric materials. Owing to their compatibility with the complementary metal-oxide-semiconductor process and high scalability, Hf-FEs devices have driven the development of non-volatile memory and neuromorphic computing, demonstrating significant potential for application in image processing and in-memory logic operations. First of all, this paper summarizes the material systems, device structure, and physical mechanisms relevant to Hf-FEs devices. Then, for the purpose of achieving efficient neuromorphic computing, the evaluation parameters related to Hf-FEs devices, specifically concerning storage performance and synaptic plasticity, are discussed. Furthermore, the progress of Hf-FEs devices in arrays and hardware integration is systematically reviewed, offering insights for future applications. Finally, this study explores in depth the prospects and challenges of these devices in advanced applications, providing valuable guidance for the development of high-performance neuromorphic computing devices.","url":"https://doi.org/10.1007/s40820-026-02158-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s40820-026-02158-z","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1007/s40820-026-02263-z","name":"Triboelectric Wearable Sensors for Human-Centric Smart Electronics: From Self-Powered Sensing to Artificial Intelligence-Assisted Human-Machine Interface Systems.","source":"europepmc","abstract":"As intelligent electronics become increasingly integrated into daily life, health care, virtual interaction, and assistive systems, human-machine interfaces (HMIs) require sensing platforms that are not only wearable and self-powered but also capable of translating human signals into adaptive machine functions. Triboelectric wearable sensors are particularly attractive in this regard because they directly transduce human-generated mechanical stimuli, provide broad material and structural design freedom, and are readily adaptable to body-interfaced formats. In this review, wearability refers to body-mounted, skin-interfaced, textile-integrated, or otherwise human-attached triboelectric sensing platforms, whereas human-centric smart electronics refers to downstream electronic systems that remain functionally anchored to human-originated sensing, interpretation, feedback, or control. From this perspective, we review triboelectric wearable sensors from fundamentals to applications, covering working principles, material selection, device architectures, and fabrication strategies. We further discuss artificial intelligence-assisted signal processing, triboelectric artificial synapses, and neuromorphic computing as key bridges from self-powered sensing to intelligent HMI. Representative application spaces, including health care, gesture recognition, device control, immersive virtual interaction, wearable-to-robotic extensions, and intelligent transportation are discussed only when wearable triboelectric sensing serves as the primary human-input interface. Finally, the remaining challenges and future directions toward next-generation human-centric smart electronics are outlined.","url":"https://doi.org/10.1007/s40820-026-02263-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s40820-026-02263-z","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acsami.6c02228","name":"Stretchable Organic Electrochemical Transistors with High Transconductance for Bioelectronic and Neuromorphic Applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.6c02228","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.6c02228","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1038/s41598-026-61384-y","name":"Dual-functional acetogenin nanofibers: bridging biomedical activity with brain-inspired neuromorphic devices.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-61384-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-61384-y","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.3762/bjnano.17.51","name":"Superconducting artificial neural networks and quantum circuits.","source":"europepmc","abstract":"","url":"https://doi.org/10.3762/bjnano.17.51","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3762/bjnano.17.51","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1038/s41598-026-54349-8","name":"A hierarchical neuromorphic multi agent framework for energy aware and secure 6G resource optimization using Neuro6G agent.","source":"europepmc","abstract":"The convergence of Sixth-Generation (6G) wireless networks and neuromorphic computing presents significant opportunities for intelligent, energy-efficient resource management in distributed architectures. This paper introduces Neuro6G-Agent, a hierarchical neuromorphic agentic intelligence framework that integrates Energy-Aware Spiking Neural Networks (EA-SNNs) with multi-agent reinforcement learning to enable energy-conscious cognitive collaboration across cloud-edge-end 6G deployments. The framework addresses three principal challenges in distributed 6G resource management: energy sustainability, end-to-end latency under ultra-dense connectivity, and security resilience against adversarial threats. A three-tier architecture is employed, comprising cloud orchestrators, edge coordinators, and end devices, each operating dedicated neuromorphic agents with autonomous decision-making and trust-aware collaborative learning capabilities. The framework incorporates adaptive threshold EA-SNNs for event-driven processing, a distributed trust computation mechanism for secure multi-agent cooperation, and a hierarchical resource optimization algorithm responsive to dynamic workload conditions. Experimental evaluation across three public benchmark datasets-DeepMIMO (6G channel modeling), DVS128 Gesture (neuromorphic sensing), and CICIDS-2017 (network intrusion detection) demonstrates a 34.7% reduction in energy consumption, a 28.3% decrease in end-to-end latency, and a 95.6% security threat detection accuracy compared to state-of-the-art baseline methods, validated across ten independent experimental runs (p < 0.01). These results confirm the viability of neuromorphic intelligence for addressing complex optimization challenges in next-generation wireless architectures.","url":"https://doi.org/10.1038/s41598-026-54349-8","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-54349-8","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1021/acsami.5c21047","name":"Optoelectronic Synaptic Transistors Based on Colloidal CdSe Nanowires for Energy-Efficient Neuromorphic Computing.","source":"europepmc","abstract":"Neuromorphic computing─which mimics biological synaptic functions─has garnered significant attention as a promising candidate for overcoming the limitations of conventional von Neumann computing. Various synaptic devices exhibiting short- and long-term plasticity characteristics have been developed for neuromorphic device fabrication, and field-effect transistor (FET) structures have been actively researched for their ability to implement sophisticated computing. This study reports the first neuromorphic thin-film transistor (TFT) based on colloidal semiconductor nanowires (NWs). Cadmium selenide (CdSe) NWs exhibit synaptic characteristics in response to both electrical and optical stimuli when fabricated as synaptic thin-film transistors (STFTs) owing to their persistent photoconductivity and large transfer-curve hysteresis characteristics. The device exhibits both short-term plasticity features, including excitatory and inhibitory postsynaptic currents alongside paired-pulse facilitation, as well as long-term plasticity behavior, such as long-term potentiation and depression. Notably, a single NW of these STFTs was calculated to consume approximately 8.848 fJ per synaptic event, approaching the energy efficiency of biological synapses. A spiking neural network implemented through the spike-timing-dependent plasticity characteristics of the CdSe NW STFT successfully learned handwritten digits from the Modified National Institute of Standards and Technology database with over 80% accuracy. The combination of biologically similar learning mechanisms and ultralow energy consumption─comparable to that of biological synaptic events─makes these STFTs highly promising for the development of energy-efficient neuromorphic computing systems.","url":"https://doi.org/10.1021/acsami.5c21047","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.5c21047","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1021/acsami.6c06594","name":"Crystallization-Driven Stable Resistive Switching and Reproducible Synaptic Learning in GeSe-Based Artificial Synapses.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.6c06594","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.6c06594","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1002/advs.75654","name":"Field-Free Spin-Splitting-Torque Driven Stochastic Neuron Mimicking the Neuromorphic Imagination for High-Performance Recognition.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.75654","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.75654","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1002/smll.74713","name":"Ultrawide Charge-Trap Memory Window and Photoinduced Synaptic Behavior in p-Channel Amorphous Oxide Semiconductors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.74713","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.74713","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1021/acsami.5c24767","name":"Bioinspired Tripartite Synaptor with Conjoined Twin Transistors for Homeostasis in Neuromorphic Hardware.","source":"europepmc","abstract":"As researchers seek to employ neuromorphic computing to overcome the limitations of conventional von Neumann architecture, mimicking the biological properties of neural systems has become increasingly critical. In tripartite synapses, astrocytes modulate synaptic activity and maintain homeostasis, thereby enabling more robust and adaptive neural systems. Inspired by biological tripartite synapses, we present an artificial tripartite synaptic transistor (synaptor) that integrates both synaptic and homeostatic functionalities within a single, CMOS-compatible device. The tripartite synaptor, with a split-gate silicon-oxide-nitride-oxide-silicon (SONOS) structure, uses two independently addressable gates: the primary gate controls synaptic weight via charge trapping/detrapping for weight updates, while the secondary gate modulates transmission current for homeostasis. The proposed tripartite synaptor demonstrates not only long-term retention and distinct potentiation and depression characteristics using the primary gate, but also dynamic conductance regulation using the secondary gate. The tripartite synaptor achieves higher accuracy than conventional bipartite synapse-based systems when applied to neural networks to classify grayscale handwritten digits and real-world RGB images. This work provides a scalable hardware platform for reliable neuromorphic computing with homeostasis.","url":"https://doi.org/10.1021/acsami.5c24767","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.5c24767","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1002/smll.74597","name":"Amorphous to Crystalline Transition and Indium-Vacancy Mediated Synaptic Functionality With Ultralow Energy Consumption in γ-Phase Indium (III) Selenide.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.74597","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.74597","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1126/sciadv.aec6633","name":"Topological acoustic synapse for high-dimensional neuromorphic computing.","source":"europepmc","abstract":"The human brain performs complex, high-dimensional (HD) computations, such as causal reasoning, counterfactual thinking, and abstraction, with ~10 11 neurons while consuming ~20 watts of power. Neuromorphic computing seeks similar efficiency, but current devices face bottlenecks in bandwidth, energy, wiring, footprint, and reliability that limit scalability. Here, we introduce the topological acoustic synapse (TAS), an acoustic-wave neuromorphic device that circumvents these limits by mapping information in multivariate state spaces. A single TAS generates and manipulates numerous computing channels that operate independently and in parallel. The TAS leverages nonlinear interactions to emulate biorealistic neuromorphic functionalities, including reconfigurable synaptic plasticity, neuromodulation, and hybrid analog-digital control. In classification tasks, a TAS handles multiple inputs simultaneously and generates various outputs, converging 20% faster while using 60% fewer parameters and at least an order of magnitude less power than state-of-the-art electrical devices. This work establishes the first acoustic synapse with parallel HD computing capabilities, presenting a scalable paradigm for neuromorphic hardware with high computational density.","url":"https://doi.org/10.1126/sciadv.aec6633","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1126/sciadv.aec6633","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1093/nsr/nwaf515","name":"An all-in-one electrochromic neuromorphic display.","source":"europepmc","abstract":"","url":"https://doi.org/10.1093/nsr/nwaf515","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1093/nsr/nwaf515","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1002/smll.202514987","name":"Grain-Size-Controlled Resistive Switching Memories Enabling Domain-Specific Functionality for Real-Time Video Signal Processing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.202514987","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.202514987","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1038/s41377-026-02298-2","name":"Two-terminal β-Ga&lt;sub&gt;2&lt;/sub&gt;O&lt;sub&gt;3&lt;/sub&gt; photo-synapse for diversified in-sensor computing via self-trapped holes engineering.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41377-026-02298-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41377-026-02298-2","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.3390/nano16110657","name":"Polymer-Based Linear and Symmetric Artificial Synaptic Memristors for Accurate and Reliable Neuromorphic Computing Applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/nano16110657","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/nano16110657","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1007/s40820-026-02139-2","name":"Dedicated and Reconfigurable Artificial Neurons and Synapses based on Two-Dimensional Materials for Efficient Neuromorphic Application.","source":"europepmc","abstract":"Neuromorphic computing, a highly promising computational architecture, has provided an efficient solution to overcome the limitations of storage-compute separation and scaling constraints. The key to implementing this architecture lies in the development of artificial neurons and synapses as core neuromorphic components capable of biomimicry. Diverse libraries of two-dimensional (2D) materials with atomic-scale thickness and rich tunable physicochemical properties have risen to prominence in recent years. These unique properties meet the critical requirements of neuromorphic devices for ultralow power consumption, dynamic plasticity, and multifunctional integration, thereby facilitating breakthroughs in next-generation high-performance and versatile neuromorphic hardware systems. In this paper, recent advances in dedicated artificial neuron and synapse devices based on 2D materials are reviewed, with a focus on biomimetic models, physical mechanisms, and performance metrics. The discussion further extends to sophisticated switching strategies in reconfigurable components. Then, the systemic integration of neuromorphic devices is summarized, with particular focus on their functional roles in neural perception, neural networks, and logical operation tasks. Finally, a systematic analysis of the limitations at the device and system levels for artificial neurons and synapses is presented, charting a roadmap toward more efficient and multifunctional brain-like chips.","url":"https://doi.org/10.1007/s40820-026-02139-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s40820-026-02139-2","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acsami.5c20032","name":"Beyond Silicon Frontiers in Neuromorphic Computing and Logic Circuits: Single-Walled Carbon Nanotube Thin-Film Transistors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c20032","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c20032","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1039/d5mh02224j","name":"Gate-controlled neuromodulatory optical synaptic transistor for adaptive learning and energy-accuracy balance.","source":"europepmc","abstract":"Neuromorphic vision systems demand highly efficient optical signal acquisition and adaptable, energy-aware learning capabilities. Optical synaptic transistors have emerged as promising components for in-sensor computing by directly responding to visual stimuli and mimicking core synaptic functions such as excitatory postsynaptic current (EPSC), paired-pulse facilitation (PPF), and both short- and long-term plasticity. However, most devices demonstrate fixed synaptic gain, limiting their ability to adapt learning behavior in response to varying input conditions or computational tasks. Inspired by biological neuromodulation, we present a gate-tunable optical synaptic transistor based on an In-Ga-Zn-O (IGZO) phototransistor that supports both conventional synaptic behaviors and voltage-dependent modulation of learning sensitivity. The device allows pre-conditioning of EPSC amplitude via gate bias prior to optical stimulation, effectively mimicking neuromodulatory gain control. Convolutional Neural Network (CNN) training on the CIFAR-10 dataset shows that higher gate biases improve classification accuracy with higher energy use, while weaker biases reduce energy consumption with an adaptive accuracy tradeoff. Our device integrates core synaptic behaviors with gate-controlled gain modulation, effectively emulating neuromodulation and offering a practical and efficient approach to adaptive neuromorphic vision systems.","url":"https://doi.org/10.1039/d5mh02224j","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d5mh02224j","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1021/acsami.5c21759","name":"A Perspective on Tellurium/Selenium-Based Nanomaterials for Neuromorphic Computing.","source":"europepmc","abstract":"The long-standing von Neumann architecture, while foundational to modern computing, intrinsically suffers from data-transfer inefficiency, which imposes severe limits on speed and energy efficiency in artificial intelligence, machine learning, and real-time data processing. Inspired by the remarkable energy efficiency of the human brain, neuromorphic computing seeks to emulate neural architectures through hardware capable of adaptive learning. Although early complementary metal-oxide-semiconductor (CMOS)-based neuromorphic systems captured basic synaptic behaviors, their narrow dynamic ranges and high operating voltages impede their application prospects. Van der Waals (vdW) materials, particularly tellurium (Te) and Selenium (Se), have recently emerged as promising platforms for next-generation neuromorphic devices due to their intriguing electronic and optoelectronic properties including considerable carrier mobilities, broadband photoresponse, and strong coupling between electrical, optical, and mechanical stimuli. These unique properties offer a direct physical analogy to biological synapses, thereby enabling neuromorphic computing. This Perspective introduces the fundamentals of synaptic behavior and neuromorphic computing and highlights the distinctive properties of Te/Se nanomaterials for synaptic devices. Then we discuss critical advances in Te/Se-based memristors, heterostructures, and electronic/optoelectronic synaptic transistors. In the end, we conclude this perspective with a discussion on the remaining challenges and future opportunities in this evolving field.","url":"https://doi.org/10.1021/acsami.5c21759","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c21759","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1002/smll.73295","name":"Towards Artificial Intelligence Hardware With 3D Integrated Ferroelectric Transistors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.73295","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.73295","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1007/s40820-026-02171-2","name":"Underlying Framework of All-optical Controlled Synaptic Devices for Neuromorphic Computing.","source":"europepmc","abstract":"Abstract The rapid expansion of artificial intelligence has led to significant challenges in energy consumption and computational efficiency. To address these issues, the exploration and development of all-optical controlled (AOC) synaptic devices represents a promising leap forward in neuromorphic computing, offering potential solutions to the inherent limitations of traditional von Neumann architectures. AOC synaptic devices, utilizing exclusively optical signals to emulate bidirectional modulation of synaptic weights, bypass the complexity and additional energy costs associated with conventional electrical or electro-optical hybrid signals. This review articulates the underlying framework and fundamental motivations for studying AOC synapses, while systematically reviewing current research progress. We particularly highlight the synergistic relationships among physical mechanisms, material behaviors, and device architectures, as well as neuromorphic computing based on optical writing and optical erasing of information. By systematically interpreting these multidimensional correlations, we propose scalable and reproducible strategies for device design. This work will certainly herald a substantial direction of AOC synapses, providing an ideal platform for exploring neuromorphic computing for artificial intelligence.","url":"https://doi.org/10.1007/s40820-026-02171-2","authors":["Dunan Hu","Ruqi Yang","Zhizhen Ye","Jianguo Lu"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s40820-026-02171-2","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/adma.202523436","name":"Chiropto-Neuromorphic Devices Based on a Photocatalytic Dye/Polymer Semiconductor Bulk Heterojunction for Circularly Polarized Light Detection and Memorization.","source":"europepmc","abstract":"Neuromorphic computing, which emulates the energy-efficient processing of the human brain, has emerged as a key technology for next-generation artificial intelligence. Integrating sensitivity to circularly polarized light (CPL) provides an additional degree of freedom for optical data encoding, yet practical implementation remains limited by material instability and complex, non-scalable fabrication. This work introduces a chiropto-neuromorphic device that addresses these challenges through a polarized light-induced charge transfer doping mechanism. The system employs a solution-processed bulk heterojunction (BHJ) composed of a chiral boron dipyrromethene (BODIPY) dye and a polymer semiconductor (PBTTT-C12) to translate CPL handedness into a stable nonvolatile memory state. Chirality-dependent charge transfer modulates the polymer's doping level, enabling precise control of synaptic weight. The device emulates key biological synaptic functions, including short- and long-term plasticity, paired-pulse facilitation, and stimulus-dependent plasticity governed by light number, duration, and intensity, while maintaining distinct chiroptical selectivity. Notably, its energy consumption remains at the picojoule (pJ) level per synaptic event, comparable to biological synapses. By introducing chirality as a new control dimension for synaptic modulation, this study demonstrates a scalable and powerful platform for polarization-encoded neuromorphic information processing and establishes a foundation for advanced artificial sensory systems capable of handling complex chiral optical signals.","url":"https://doi.org/10.1002/adma.202523436","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202523436","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.3390/e28010042","name":"Machine Learning-Based Prediction Framework for Complex Neuromorphic Dynamics of Third-Order Memristive Neurons at the Edge of Chaos.","source":"europepmc","abstract":"As conventional computing architectures face fundamental physical limitations and the von Neumann bottleneck constrains computational efficiency, neuromorphic systems have emerged as a promising paradigm for next-generation information processing. Memristive neurons, particularly third-order circuits operating near the edge of chaos, exhibit rich neuromorphic dynamics that closely mimic biological neural activities but present significant prediction challenges due to their complex nonlinear behavior. Current approaches typically require complete system state measurements, which is often impractical in real-world neuromorphic hardware implementations where only partial state information is accessible. This paper addresses this critical limitation by proposing an innovative hybrid machine learning framework that integrates a Modified Next-Generation Reservoir Computing (MNGRC) with XGBoost regression. The core novelty lies in its dual-path prediction architecture designed specifically for partial state observability scenarios. The primary path employs NGRC to capture and forecast the system's temporal dynamics using available state variables and input stimuli, while the secondary path leverages XGBoost as an efficient state estimator to infer unobserved state variables from minimal measurements. This strategic combination enables accurate prediction of diverse neuromorphic patterns with significantly reduced sensor requirements. Experimentally, the framework demonstrates its capability to identify and predict the complex spectrum of neuromorphic behaviors exhibited by the third-order memristive neuron. This includes accurately capturing all 18 distinct neuronal patterns, which are theoretically grounded in Hopf bifurcation analysis near the edge of chaos. Additionally, the framework successfully addresses the inverse problem of input stimulus reconstruction. By achieving accurate prediction of complex dynamics from limited states, our approach represents a key breakthrough, where full state access is often impossible, thereby addressing a critical challenge in edge AI and brain-inspired computing.","url":"https://doi.org/10.3390/e28010042","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/e28010042","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1073/pnas.2528654122","name":"Can neuromorphic computing help reduce AI's high energy cost?","source":"europepmc","abstract":"Artificial intelligence systems, and large language models (LLMs) in particular, have become almost ubiquitous.The implications are many.Among them: serious concerns about massive amounts of energy usage.The initial training of GPT-3 required as much energy as powering 120 houses for a year.That's before adding the energy required for the chatbot to respond to users' prompts (1-3).GPT-4 required an estimated 50 times as much energy as its predecessor to train, and although OpenAI has not divulged official figures, GPT-5 likely required much more.To date, most efforts to improve the energy consumption of AI systems have focused on developing more efficient algorithms, increasing the use of energy from sustainable sources, or even building smaller language models.To build DeepSeek, which debuted last January, researchers in China built a model that only activates a fraction of the total model for each query.Other efforts focus on packing more transistors onto smaller chips, which results in a shorter distance for the data to travel and enables more parallel computing.But many researchers are developing a different kind of computing architecture, one inspired by the efficient mechanisms of the brain.Dubbed neuromorphic computing, it was first proposed decades ago but has recently seen a resurgence of Some researchers believe that a computing architecture inspired by the mechanisms of the brain could offer a path to innovation that helps tackle rampant AI energy consumption.","url":"https://doi.org/10.1073/pnas.2528654122","authors":["Stephen Ornes"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1073/pnas.2528654122","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.3762/bjnano.17.24","name":"Ferroelectric nanodot reservoir for neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.3762/bjnano.17.24","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3762/bjnano.17.24","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.3390/brainsci16040422","name":"Event-Based Vision at the Edge: A Review.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/brainsci16040422","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/brainsci16040422","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3390/polym18060746","name":"Fabrication of Stochastic Ni@PVP Nanowire Networks for Memristive Platforms.","source":"europepmc","abstract":"Single memristive nanowire networks have emerged as a promising pathway for energy-efficient neuromorphic computing, owing to their intrinsic nonlinearity, high dimensionality, fading memory and volatile switching dynamics relevant to physical reservoir computing. While prior works focused on oxide- or silver-based network systems, these approaches face trade-offs between operating voltage, cost, stability, and scalability. This work presents a proof-of-concept demonstration of stochastic polyvinylpyrrolidone (PVP)-coated nickel nanowire networks as low-cost and scalable memristive platforms, exhibiting low-voltage resistive switching (1-2 V). The electrical characterization reveals predominantly volatile resistive switching combined with nonvolatile behavior, consistent with a filamentary conduction mechanism at nanowire junctions. The switching dynamics are governed by the polymer coating thickness, with an intermediate PVP concentration (Ni@PVP = 1:25) showing optimal performance, with a resistance ratio of ~200, stable retention over 1 h, and a reproducible endurance of over 45 cycles. These results establish Ni@PVP nanowire networks as promising memristive platforms for neuromorphic hardware applications and physical reservoir computing, with relevant properties such as fading memory and nonlinear dynamics.","url":"https://doi.org/10.3390/polym18060746","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/polym18060746","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.3389/frobt.2026.1714310","name":"Bio-inspired cognitive robotics vs. embodied AI for socially acceptable, civilized robots.","source":"europepmc","abstract":"Although cognitive robotics is still a work in progress, the trend is to \"free\" robots from the assembly lines of the third industrial revolution and allow them to \"enter human society\" in large numbers and many forms, as forecasted by Industry 4.0 and beyond. Cognitive robots are expected to be intelligent, designed to learn from experience and adapt to real-world situations rather than being preprogrammed with specific actions for all possible stimuli and environmental conditions. Moreover, such robots are supposed to interact closely with human partners, cooperating with them, and this implies that robot cognition must incorporate, in a deep sense, ethical principles and evolve, in conflict situations, decision-making capabilities that can be perceived as wise. Intelligence (true vs. false), ethics (right vs. wrong), and wisdom (good vs. bad) are interrelated but independent features of human behavior, and a similar framework should also characterize the behavior of cognitive agents integrated in human society. The working hypothesis formulated in this paper is that the propensity to consolidate ethically guided behavior, possibly evolving to some kind of wisdom, is a cognitive architecture based on bio-inspired embodied cognition, educated through development and social interaction. In contrast, the problem with current AI foundation models applied to robotics (EAI) is that, although they can be super-intelligent, they are intrinsically disembodied and ethically agnostic, independent of how much information was absorbed during training. We suggest that the proposed alternative may facilitate social acceptance and thus make such robots civilized .","url":"https://doi.org/10.3389/frobt.2026.1714310","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/frobt.2026.1714310","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1002/adma.202517440","name":"A Monolithic Ferroelectric-Ionic Duality for Stochastic-Neuromorphic Core Integration.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202517440","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202517440","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1073/pnas.2525734122","name":"Biological fidelity: The engine driving the neuromorphic renaissance.","source":"europepmc","abstract":"","url":"https://doi.org/10.1073/pnas.2525734122","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1073/pnas.2525734122","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41467-026-70727-2","name":"Programmable ferroelectric rectifier for reliable and efficient neuromorphic crossbar array.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-70727-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-70727-2","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1021/acsami.5c17926","name":"A Low-Voltage Stretchable Synaptic Transistor Array for Temperature Perception, Facilitated Associative Learning, and Neuromorphic Computing.","source":"europepmc","abstract":"Stretchable synaptic transistors are promising candidates for brain-inspired neuromorphic systems in soft robotics and wearable electronics, where temperature perception and low-power operation are critical for biological fidelity and energy efficiency. However, the interplay between mechanical strain, temperature perception, and synaptic properties remains underexplored in such devices. Here, we report a high-density, temperature-modulated stretchable synaptic transistor (TM-SST) array fabricated via a photolithography-based, transfer-free process, integrating a semiconductor carbon nanotube (s-CNT) network channel and an SU-8 dielectric layer. The devices exhibit a high on-off ratio (∼10 5 ) at a low gate voltage ( V gs ) between ±2.5 V and a drain-to-source voltage ( V ds ) of -0.1 V. Importantly, the devices exhibit temperature-dependent synaptic characteristics across 10-40 °C, with effective modulation of postsynaptic current (PSC), plasticity, memory retention, and paired-pulse facilitation (PPF), while maintaining stable performance under 40% strain. Furthermore, temperature modulation enhances neuromorphic performance: a 15 °C cooling improves memory retention in associative learning from seconds to minutes, while simulations show accelerated learning with a 10× dynamic range. This work advances stretchable synaptic devices by enabling temperature perception to enhance neuromorphic functionality.","url":"https://doi.org/10.1021/acsami.5c17926","authors":["Dingzhou Cui","Zhiyuan Zhao","Fugu Tian","Qi Zheng","Xun Liao","Wenbo Chen","Jingxin Zhang","Chongwu Zhou"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c17926","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.3390/gels12040346","name":"Advances in Gel-Based Electrolyte-Gated Flexible Visual Synapses for Neuromorphic Vision Systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/gels12040346","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/gels12040346","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.3389/fnins.2025.1746610","name":"Editorial: Algorithm-hardware co-optimization in neuromorphic computing for efficient AI.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2025.1746610","authors":["Amirreza Yousefzadeh","Alberto Patiño-Saucedo","Guido De Croon","Manolis Sifalakis"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fnins.2025.1746610","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41467-026-70586-x","name":"A highly energy-efficient multi-core neuromorphic architecture for training deep spiking neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-70586-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-70586-x","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.22541/au.176529685.59484231/v1","name":"Quantum-Dot Neuromorphic Edge AI for Ultra-Secure IoT and Brain-Inspired Computing","source":"europepmc","abstract":"In order to achieve ultra-secure, adaptive, and low-power intelligence for distributed IoT environments, this paper presents a next-generation neuromorphic edge architecture that combines quantum-dot nanomaterials with spiking neural computation. Because of their multi-level tunability and quantum-confined electronic structure, quantum dots (QDs) serve as nanoscale synaptic elements that can produce intrinsic randomness, stable conductance states, and extremely low-energy switching. Real-time on-chip learning and event-driven spike computation are made possible by neuromorphic processors, which are based on biological neural systems. By utilizing QD-based entropy sources and physically unclonable functions (PUFs), the proposed Quantum-Dot Neuromorphic Edge AI Processor (QD-NEAP) reduces vulnerabilities related to traditional IoT devices and eliminates cloud dependency. When compared to CMOS and memristor-based architectures, performance evaluation shows notable gains in energy efficiency, inference latency, and cryptographic strength. This work creates a single braininspired computational platform that combines secure IoT communication, neuromorphic learning, and quantum-dot materials.","url":"https://doi.org/10.22541/au.176529685.59484231/v1","authors":["Pushkar Sharma","Ashwini Mali","Payal Panigrahi","Sandhyarani Dora","Damini Suryavanshi","Khushboo Jangid"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.22541/au.176529685.59484231/v1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1016/j.jcis.2026.139943","name":"Interface-engineered Gd₂O₃/ZrO₂ bilayer memristor for emulating synaptic plasticity in neuromorphic systems.","source":"europepmc","abstract":"Rare-earth-based materials are attracting growing interest for neuromorphic devices due to their unique electronic structures, defect engineering capabilities, and high ionic mobility, which enable energy-efficient and highly controllable memristive switching behavior essential for brain-inspired computing. In this work, we demonstrate a bilayer Ag/Gd₂O₃/ZrO₂/Pt memristor that exhibits robust resistive switching behavior and reliable synaptic functionality. The integration of a rare-earth Gd₂O₃ switching layer with a ZrO₂ modulation layer enables precise control over filament dynamics, resulting in a low operating voltage ( 8 ), stable direct-current (DC) endurance over 100 cycles, pulse endurance exceeding 5000 cycles, and long-term data retention beyond 5000 s. The device successfully emulates key biological synaptic functions, including short-term plasticity (paired-pulse facilitation and depression) and long-term potentiation/depression, with highly symmetric and linear conductance modulation. Furthermore, when the experimentally extracted conductance states are implemented in a multilayer perceptron network, a high pattern recognition accuracy of 97.5% is achieved on the MNIST dataset. These findings offer new insights into bilayer oxide architectures for scalable, energy-efficient, and hardware-level neurosynaptic systems.","url":"https://doi.org/10.1016/j.jcis.2026.139943","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.jcis.2026.139943","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.3390/mi17050586","name":"A Review of Embedded Artificial Intelligence Research (2023-2026): Technological Advancements, Representative Advances, and Future Prospects.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/mi17050586","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/mi17050586","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.64898/2025.12.01.691482","name":"Design principles of neuromorphic computing using genetic circuits","source":"europepmc","abstract":"Cells have evolved to sense a wide range of input combinations and integrate those signals through signaling pathways to produce context-specific responses, such as differentiation, cell-type specification, and patterning. To replicate this information-processing capacity, synthetic biology has developed large-scale circuitry inspired by the fundamental principles of computer science. Within this framework, neuromorphic computing implemented using genetic circuits offers the opportunity to significantly enhance the computational capabilities of single cells. In this work, we establish design principles for implementing neuromorphic computing in living cells by identifying the key feature that enables a chemical reaction network to function as a perceptron: an input-output mapping with a tunable threshold. We demonstrate that four ubiquitous chemical reaction networks, namely molecular sequestration, catalytic degradation, competitive binding, and activation/deactivation cycles, all satisfy this requirement and can be engineered as perceptrons. By layering these perceptrons into multi-layer architectures, we then show how to construct both linear and nonlinear decision boundaries through rational tuning of production rates that encode network weights. As proof of principle, we apply this framework to design neural networks capable of discriminating between healthy and cancer cells based on gene expression data from 19 tissue types. Together, this work formalizes the design principles for engineering genetic circuits as neural networks and establishes a foundation for implementing next-generation cellular computation.","url":"https://doi.org/10.64898/2025.12.01.691482","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.64898/2025.12.01.691482","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.20944/preprints202512.2404.v1","name":"HyperFabric Interconnect (HFI): A Unified, Scalable Communication Fabric for HPC, AI, Quantum, and Neuromorphic Workloads","source":"europepmc","abstract":"The evolution of high-performance computing (HPC) interconnects has produced specialized fabrics such as InfiniBand[1], Intel Omni-Path, and NVIDIA NVLink[2], each optimized for distinct workloads. However, the increasing convergence of HPC, AI/ML, quantum, and neuromorphic computing requires a unified communication substrate capable of supporting diverse requirements including ultra-low latency, high bandwidth, collective operations, and adaptive routing. We present HyperFabric Interconnect (HFI), a novel design that combines the strengths of existing interconnects while addressing their scalability and workload-fragmentation limitations. Our evaluation on simulated clusters demonstrates HFI’s ability to reduce job completion time (JCT) by up to 30%, improve tail latency consistency by 45% under mixed loads and 4× better jitter control in latency-sensitive applications., and sustain efficient scaling across heterogeneous workloads. Beyond simulation, we provide an analytical model and deployment roadmap that highlight HFI’s role as a converged interconnect for the exascale and post-exascale era.","url":"https://doi.org/10.20944/preprints202512.2404.v1","authors":["Krishna Bajpai"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202512.2404.v1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1021/acs.nanolett.5c04249","name":"One-Step Annealing-Configured Hf&lt;sub&gt;0.2&lt;/sub&gt;Zr&lt;sub&gt;0.8&lt;/sub&gt;O&lt;sub&gt;2&lt;/sub&gt; Memristive-Antiferroelectric Devices for Bioinspired CSNN Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.5c04249","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acs.nanolett.5c04249","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.3389/fnetp.2026.1736738","name":"Self-organisation of complex dynamical systems: from synergetics to neuromorphic systems.","source":"europepmc","abstract":"The intuitive idea of self-organisation in complex dynamical systems is that global patterns and structures emerge from locally interacting elements like atoms in laser beams, molecules in chemical reactions, proteins in cells, cells in organs, neurons in brains, agents in markets, etc. Hermann Haken introduced a mathematically precise and rigorous formalism of synergetics. In this framework we define local activity as the cause of self-organizing complexity which can be tested in an explicit and constructive manner. This principle of local activity can also be defined in the theory of nonlinear electronic circuits. It is not restricted to a certain domain, but can be generalized and proven for the class of nonlinear reaction-diffusion systems in physics, chemistry, biology, and brain research. An example is an improved Hodgkin-Huxley axon circuit model of the brain as network of physiology. It turns out that neuromorphic computing approximates the energetic efficiency of human brains and avoids the enormous increase of energy consumption with traditional digital computing. Obviously, traditional digitalization is closely connected with one of the most challenging problems of mankind-the increasing demand for energy with all its consequences for environmental and climate problems. Thus, synergetics with the local activity principle strongly supports the request for sustainable computing inspired by network physiology.","url":"https://doi.org/10.3389/fnetp.2026.1736738","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnetp.2026.1736738","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acs.nanolett.5c04348","name":"Ovonic Switches Enable Energy-Efficient Dendrite-like Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.5c04348","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acs.nanolett.5c04348","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.20944/preprints202512.2437.v1","name":"Multifunctional Adaptive Element for Neuromorphic Electronics Based on the Kuznetsov Tensor","source":"europepmc","abstract":"","url":"https://doi.org/10.20944/preprints202512.2437.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202512.2437.v1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1021/acsami.5c15178","name":"Fluorescence Modulation Behavior of Quantum Dots under Alternating Electric Fields and Applications in Logic and Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c15178","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c15178","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.34133/research.1071","name":"Reconfigurable In-Sensor Computing Memristor for Olfactory SNN and Reservoir Hybrid Neuromorphic Computing.","source":"europepmc","abstract":"Traditional gas sensing systems are facing efficiency challenges due to physically separated von Neumann architectures, making the construction of in-sensor computing neuromorphic olfactory systems urgently needed for low-power and low-latency scenarios. In this study, a reconfigurable neuromorphic heterostructure memristor based on MXene@SnS 2 @PANI and an in-sensor computing olfactory system were proposed. Notably, the reconfigurable neuromorphic olfactory electronics differ fundamentally from conventional sensors. Specifically, the memristor's circuit architecture supports both synaptic and neuronal computational functions, enabling reconfigurable responses to both electrical and gas stimuli within a single device, which substantially minimizes circuit complexity. Through modulation of the energy band under both gas and electrical signals, the device achieves reconfigurable neuromorphic computing features supporting both volatile and nonvolatile conductance updates. Under electrical stimulation, it demonstrates integrate-and-fire neuronal dynamics for gas flow recognition via a spiking neural network. Under gas exposure, neuromorphic synaptic behaviors are realized, enabling gas concentration identification through reservoir computing. The system has been successfully implemented for real-time hazardous gas monitoring and automated ventilation control, paving the way for next-generation neuromorphic intelligent sensing systems.","url":"https://doi.org/10.34133/research.1071","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.34133/research.1071","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acsnano.6c02066","name":"Energy- and Area-Efficient Ionic-Switch Activation Neuron for Monolithic 3D Neural Network Architectures.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.6c02066","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsnano.6c02066","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1021/acsnano.5c14569","name":"A Robust Biomimetic van der Waals Heterostructure Visual Neuromorphic Device for Multiscale In-Sensor Reservoir Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.5c14569","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsnano.5c14569","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1039/d5nh00799b","name":"Spin torque nano-oscillators with tilted magnetic anisotropy.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5nh00799b","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d5nh00799b","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1002/advs.202524299","name":"Low Power Optoelectronic Neuromorphic Memristor for In-Sensor Computing and Multilevel Hardware Security Communications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202524299","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.202524299","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acsami.5c11432","name":"Halide Perovskites for Neuromorphic Sensing and Computing.","source":"europepmc","abstract":"The development of semiconductor-based electronic devices has significantly advanced sensor-based data acquisition and processor-driven data analysis. However, conventional complementary metal-oxide-semiconductor technologies are now facing fundamental limitations in scaling, speed, and power efficiency. In response, neuromorphic sensing and computing devices inspired by biological nervous systems have emerged as promising alternatives to address these challenges. Among various material platforms, halide perovskites (HPs) have attracted significant attention for neuromorphic applications owing to their unique properties, including low activation energies, tunable bandgaps, facile ion migration, and mechanical flexibility. These characteristics render HPs well suited for the development of neuromorphic sensors capable of mimicking human sensory functions such as vision, olfaction, gustation, and tactile perception, as well as memristive devices for energy-efficient in-memory computing. This review provides a comprehensive overview of recent advances in HP-based neuromorphic sensing and computing technologies, with a focus on their distinct structural and electronic properties, fundamental operation mechanisms, and cutting-edge applications. Current challenges and future perspectives are also discussed, highlighting the transformative potential of HP-based neuromorphic systems for next-generation sensing and computing.","url":"https://doi.org/10.1021/acsami.5c11432","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c11432","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.21203/rs.3.rs-7764312/v1","name":"Scalable and sustainable N-Si-Ge-Te Ovonic threshold switching devices for energy-efficient artificial neuron applications","source":"europepmc","abstract":"Abstract Neuromorphic computing, inspired by biological nervous systems, yields high energy efficiency and data throughput by integrating computation and storage within memory crossbar arrays. A key requirement for neuromorphic hardware is an artificial neuron capable of low-power, high-frequency operation. Ovonic threshold switch (OTS) devices have attracted attention due to their scalability and intrinsic capacitance, enabling simple circuitry to demonstrate leaky integrate-and-fire (LIF) behavior. This study proposes a sustainable and scalable OTS device fabricated with non-toxic, industry-friendly materials and provides insights into the roles of individual elements in bond formation, correlating with enhanced electrical performance (J off = 2.3 ∙ 10 − 8 MA/cm²). Finally, our optimized NSGT OTS device demonstrates low-power spiking operation, achieving 0.56 pJ/µm 2 per spike. These findings establish stoichiometric guidelines for designing high-performance Te-based OTS devices for energy-efficient neuromorphic computing.","url":"https://doi.org/10.21203/rs.3.rs-7764312/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7764312/v1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.3390/nano15171299","name":"Neuromorphic Devices: Materials, Structures and Bionic Applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/nano15171299","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/nano15171299","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.3390/mi16121422","name":"An Artificial Synaptic Device Based on InSe/Charge Trapping Layer/h-BN Heterojunction with Controllable Charge Trapping via Oxygen Plasma Treatment.","source":"europepmc","abstract":"Neuromorphic computing, an emerging computational paradigm, aims to overcome the bottlenecks of the traditional von Neumann architecture. Two-dimensional materials serve as ideal platforms for constructing artificial synaptic devices, yet existing devices based on these materials face challenges such as insufficient stability. Indium selenide (InSe), a two-dimensional semiconductor with unique properties, demonstrates significant potential in the field of neuromorphic devices, though its application research remains in the initial stage. This study presents an artificial synaptic device based on the InSe/Charge Trapping Layer (CTL)/h-BN heterojunction. By applying oxygen plasma treatment to h-BN to form a controllable charge-trapping layer, efficient regulation of carriers in the InSe channel is achieved. The device successfully emulates fundamental synaptic behaviors including paired-pulse facilitation and long-term potentiation/inhibition, exhibiting excellent reproducibility and stability. Through investigating the influence of electrical pulse parameters on synaptic weights, a structure-activity relationship between device performance and structural parameters is established. Experimental results show that the device features outstanding linearity and symmetry, realizing the simulation of key synaptic behaviors such as dynamic conversion between short-term and long-term plasticity. It possesses a high dynamic range ratio of 7.12 and robust multi-level conductance tuning capability, with stability verified through 64 pulse cycle tests. This research provides experimental evidence for understanding interfacial charge storage mechanisms, paves the way for developing high-performance neuromorphic computing devices, and holds broad application prospects in brain-inspired computing and artificial intelligence hardware.","url":"https://doi.org/10.3390/mi16121422","authors":["Qinghui Wang","Jiayong Wang","Manjun Lu","Tieying Ma","Jia Li"],"tags":["Neuromorphic engineering","Materials science","Computer science","Heterojunction","Optoelectronics"],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/mi16121422","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"doi:10.1002/advs.202517149","name":"Heterosynaptic Memtransistors Based on Switching Operation Mechanism Using Designed Organic/Inorganic Heterostructures for Neuromorphic Electronics.","source":"europepmc","abstract":"Memtransistors using low-dimensional semiconductors represent a promising gate-tunable heterosynaptic architecture for neuromorphic computing. However, active layers of these devices have not yet been artificially designed or controlled. In this study, gate-pulse-tunable heterosynaptic neuromodulation is achieved using memtransistors with organic semiconductor tris(4-carbazoyl-9-ylphenyl)amine (TCTA)/MoS 2 heterostructures designed via energy-band engineering and bottom-contact architecture. Memristive switching is realized through distinctive low- and high-conduction states with a switching ratio of 10 2 , modulated by gate pulses. As the gate voltage (V G ) decreases from +30 to -30 V, the memristive hysteresis for the bottom contact TCTA/MoS 2 FET without post-treatment and an h-BN insulating layer appears at V G = -15 V and broadens with an increasing switching ratio. Intriguingly, as V G becomes increasingly negative (V G 2 can promote energy-efficient, tunable, and reliable heterosynaptic neuromorphic electronics.","url":"https://doi.org/10.1002/advs.202517149","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.202517149","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.3390/nano16070425","name":"Polyoxometalates (POMs) Memristors/Neuromorphic Devices: From Structure Engineering to Material and Function Integration.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/nano16070425","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/nano16070425","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acsami.5c15360","name":"Ga&lt;sub&gt;2&lt;/sub&gt;O&lt;sub&gt;3&lt;/sub&gt; Optoelectronic Array with Solar-Blind Ultraviolet Perception for Neuron Spatiotemporal Integration and Forgetting-Enabled Neuromorphic Computing.","source":"europepmc","abstract":"Optoelectronic neuromorphic devices capable of perceiving and memorizing light signals are essential for constructing artificial vision systems. While oxide-semiconductor-based optoelectronic devices are valued for their stable performance and mature fabrication processes, they primarily operate in the near-ultraviolet to near-infrared spectral range, lacking sensitivity to the solar-blind region ( 2 O 3 , designed to perceive optical signals in the solar-blind region. Stimulated by a 254 nm light pulse, the device emulates biological visual synaptic plasticity and exhibits tunable relaxation characteristics of postsynaptic current under varying stimuli. Notably, the device array replicates the spatiotemporal integration and processing of signals from multiple preneurons via dendritic structures, demonstrating its potential for implementing advanced neuromorphic computing, including the perception and memory of solar-blind ultraviolet images during learning processes. Moreover, leveraging the tunable relaxation properties of Ga 2 O 3 devices, a forgetting-based artificial neural network is developed to address multisolution problems in complex equations with ultralow power consumption. These findings not only establish an optoelectronic neuromorphic system capable of perceiving solar-blind signals but also broaden its potential applications in low-power computing and intelligent sensing.","url":"https://doi.org/10.1021/acsami.5c15360","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c15360","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1038/s41467-026-70860-y","name":"Data-In-situ Computing with One-Pixel-Multiple-Memristor Architecture for Neuromorphic Sequential Vision.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-70860-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-70860-y","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.3389/frai.2026.1816292","name":"Self-calibrating neuromorphic system for adaptive environmental sensing.","source":"europepmc","abstract":"Precision agriculture demands accurate, real-time environmental monitoring, conventional soil moisture sensors face critical issues such as long-term drift, high energy consumption, and limited adaptability to dynamic environmental changes. These limitations often lead to suboptimal irrigation decisions, wasted resources, and unreliable data, especially in remote or resource-constrained farming regions where frequent manual recalibration is impractical or impossible. This work addresses these challenges by introducing a novel self-calibrating neuromorphic system for adaptive soil moisture sensing. The system leverages Spiking Neural Networks (SNN) deployed on a low-power STM32H563ZI microcontroller. Our proposed solution autonomously recalibrates sensors to mitigate drift, significantly reduces energy consumption through event-driven computation, and adapts seamlessly to changing environmental conditions. The SNN model achieved a Mean Absolute Error (MAE) of 0.4557 and a Root Mean Squared Error (RMSE) of 0.5850, reducing baseline drift from 5.3% to 1.6% over a two-month deployment outperforming models like Isolation Forests and Autoencoders in predictive accuracy. This work significantly contributes to the growing field of neuromorphic computing in IoT applications, offering a scalable, low-power solution for precision agriculture and broader environmental monitoring. The demonstrated effective deployment of SNN-based learning mechanisms on low-constrained microcontroller hardware opens new avenues for resilient, decentralized intelligence in smart homes, wearables, and autonomous infrastructure inspection.","url":"https://doi.org/10.3389/frai.2026.1816292","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/frai.2026.1816292","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1039/d5cp04283f","name":"Tunable negative photoconductance states in a C&lt;sub&gt;60&lt;/sub&gt; device with optically induced trap center reconfiguration.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5cp04283f","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d5cp04283f","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.22541/au.176244959.94950396/v1","name":"Quantum Computing Emulation using Neuromorphic Artificial Spiking Neurons","source":"europepmc","abstract":"","url":"https://doi.org/10.22541/au.176244959.94950396/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.22541/au.176244959.94950396/v1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1002/smll.202503908","name":"Large-Area Polymorphic In&lt;sub&gt;2&lt;/sub&gt;Se&lt;sub&gt;3&lt;/sub&gt; Ferroelectric Transistor Array for Stable Nonvolatile Storage and High-Precision Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.202503908","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/smll.202503908","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-7849696/v1","name":"Polycrystalline Perovskite Wafers as an Efficient Multisensory Integration Platform for Neuromorphic Computing","source":"europepmc","abstract":"Abstract Neuromorphic computing requires materials that integrate adaptive functionalities with scalable, cost-effective fabrication. Halide perovskites offer exceptional optoelectronic performance, but single-crystal growth is prohibitively costly and limits wafer-scale integration. Inspired by the transition from single- to polycrystalline silicon, we develop polycrystalline perovskite wafers (PPWs) via a mechanochemically coupled sintering strategy, achieving high-yield and low-cost fabrication with wafer-scale uniformity and engineered trap states. The resulting PPWs enable highly stable and linear electrical synaptic programming, as well as fully optical modulation of excitatory and inhibitory states through wavelength-selective excitation that leverages both bandgap and sub-bandgap absorption processes. These capabilities support associated retinal-inspired visual perception and auditory motion detection, achieving over 90% multimodal vehicle recognition accuracy when integrated into a spiking neural network. Beyond neuromorphic computing, PPWs provide a versatile and sustainable platform for photodetection, multispectral imaging, and X-ray sensing, combining scalability, robustness, and multifunctionality for next-generation optoelectronic technologies.","url":"https://doi.org/10.21203/rs.3.rs-7849696/v1","authors":["Gang Liu","Shu Zhou","Lue Zhou","Shuyao Han","Hengyu Zhang","Guixiang Liu","Yuncheng Mu","Zhenyi Ni","Yanglong Hou"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7849696/v1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.3389/fnbeh.2026.1797210","name":"Quantum-entangled feature selection and spiking graph transformer networks for early detection of childhood behavioral markers.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnbeh.2026.1797210","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnbeh.2026.1797210","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1021/jacs.5c15276","name":"Electric-Field-Controlled Altermagnetic Transition for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/jacs.5c15276","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/jacs.5c15276","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1039/d5nr03811a","name":"Optically/electrically controlled Ag&lt;sup&gt;+&lt;/sup&gt; metallization in solution-processed oxide memtransistors for neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5nr03811a","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1039/d5nr03811a","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1126/sciadv.aec9948","name":"Artificial sparse neuron dendrites for visual information inference.","source":"europepmc","abstract":"In the human brain, dendrites exhibit nonlinear integration and sparse parallel processing capabilities, which can effectively perform visual tasks by integrating only a small subset of neuronal signals and play a crucial role in high-level information inference. However, conventional neuromorphic devices often ignore these important properties and require all neurons to perceive complete information. This makes it difficult to effectively replicate the efficient spatiotemporal processing capabilities of biological neuron dendrites. In this study, we present an artificial neuron dendrite array that integrates neurons, synapses, and dendrites, emulating the spatiotemporal spike integration properties of biological dendrites for precise parallel computation. Through multigate threshold regulation, the array enables parallel sparse spiking inference with random spatial distribution. This inference process forms a sparse dendritic spiking neural network (SD-SNN) that can perform compression, depth detection, and prediction. As a result, the SD-SNN achieves high-efficiency static and dynamic object processing while using only 0.5% of neuronal activity, slashing the power consumption by 98 and 65%, respectively. Our work reduces neural activity in the perception process by 99.5% while enhancing spatiotemporal computing capabilities and computational efficiency.","url":"https://doi.org/10.1126/sciadv.aec9948","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1126/sciadv.aec9948","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1038/s41467-026-71642-2","name":"Oxide interface-based polymorphic electronic devices for neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-71642-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-71642-2","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/smll.202514124","name":"Reconfigurable Adaptive Synapse and Logic Device by Ambipolar Ferroelectric Semiconductor.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.202514124","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.202514124","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1021/acsami.5c16987","name":"Multifunctional Ultralow-Power-Consumption Artificial Optoelectronic Synapses Based on the Heterojunctions of MoO&lt;sub&gt;3&lt;/sub&gt;/WO&lt;sub&gt;3&lt;/sub&gt; for Neuromorphic Computing and Bionic Visual Systems.","source":"europepmc","abstract":"Due to the high energy and processing efficiencies, brain-inspired optoelectronic synaptic systems provide a promising solution for next-generation artificial vision computing. However, synapses based on single oxides face the challenge of high-power consumption, which seriously limits their practical application. This study presents multifunctional heterojunction optoelectronic synapses with low power consumption. Layered MoO 3 and photochromic WO 3 films are deposited in turn onto the ITO-covered quartz substrates by using the electron beam evaporation technique, and metal-oxide heterojunction synapses of MoO 3 /WO 3 are fabricated. The synaptic devices exhibit versatile neuromorphic functionalities under both electrical and optical modulation. The heterojunction enables long- and short-term plasticity and achieves an accuracy of up to 92.4% in handwritten digit recognition. Under light stimulation, the device successfully demonstrated basic and advanced synaptic functions. More importantly, the power consumption of the synaptic event is only 67.6 fJ, which is far below those of other similar devices and close to biological synapses. The optoelectronic synapse arrays of 4 × 4 are developed to realize real-time visual perception and memory behaviors. This work provides effective strategies and a scientific foundation for developing next-generation ultralow-power artificial intelligence vision chips.","url":"https://doi.org/10.1021/acsami.5c16987","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c16987","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1021/acs.nanolett.5c04461","name":"Bio-Inspired Optical Synapse Based on MoS&lt;sub&gt;2&lt;/sub&gt; for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.5c04461","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acs.nanolett.5c04461","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1093/nsr/nwaf482","name":"Intrinsic nanofilament pathways in molecular crystals enable energy-efficient and reliable memristors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1093/nsr/nwaf482","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1093/nsr/nwaf482","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1063/5.0299959","name":"Volatile threshold switching and neural dynamics emulation in a chitosan-ZnO memristor for neuromorphic computing.","source":"europepmc","abstract":"Neuromorphic computing demands energy-efficient and biologically plausible devices to emulate neural dynamics and sensory processing. This study explores the development and application of a chitosan-doped ZnO memristor for neuromorphic computing, focusing on its volatile threshold switching behavior and bio-inspired sensory applications. The device exhibits excellent memristive performance, with a high switching ratio (∼105), stable endurance (&amp;gt;104 cycles), and rapid switching speeds (turn-on/turn-off times of ∼23/21 µs). Symmetric threshold voltages (±2 V) and low resistance variability highlight its reliability. Integrated into an oscillatory neuron circuit (R–C configuration), the memristor emulates spiking dynamics, demonstrating tunable frequency and energy efficiency (∼832 nJ/spike). Furthermore, the circuit successfully replicates biological motion detection and sound localization by processing spatiotemporal input differences, mimicking direction-selective ganglion cells and medial superior olive neurons. These results validate the memristor’s potential for bio-inspired sensory systems, offering a scalable, energy-efficient platform for neuromorphic computing and artificial perception.","url":"https://doi.org/10.1063/5.0299959","authors":["Yanmei Sun","Rui Liu","Zekai Zhang"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1063/5.0299959","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1038/s41378-025-01153-5","name":"Top 10 ground challenges in microsystems and nanoengineering.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41378-025-01153-5","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41378-025-01153-5","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1063/5.0282708","name":"Neuromorphic reservoir computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1063/5.0282708","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1063/5.0282708","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.22541/au.176523299.91415067/v1","name":"Memristive Neuromorphic Vision: Spike-Timing Mechanisms for Visual-Tactile Perception","source":"europepmc","abstract":"Spike-timing mechanisms in neuromorphic vision sensors offer a state-of-the-art approach to replicating the efficiency and adaptability of biological visual systems. Leveraging memristor-based non-volatile memory, these sensors achieve high precision while maintaining low power consumption, making them well-suited for real-time image processing and recognition. This paper investigates the principles and applications of spiketiming-dependent plasticity (STDP) within neuromorphic vision systems, with a particular focus on integrating memristor technology. We present an innovative visual-tactile perception framework that combines a scalable, biomimetic tactile sensor, NeuTouch, with a Visual-Tactile Spiking Neural Network (VT-SNN) for rapid and accurate perception. The system demonstrates superior performance in robotic tasks such as container classification and rotational slip detection, outperforming conventional deep learning approaches. Additionally, the research contributes to the community by releasing visual-tactile datasets to encourage further development. This work underscores the promise of intelligent, energy-efficient robotic systems and reviews the latest progress in memristor-based memory devices, highlighting their critical role in neuromorphic computing and advanced vision sensing. The study concludes by discussing the transformative potential of these technologies for artificial vision and future research directions.","url":"https://doi.org/10.22541/au.176523299.91415067/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.22541/au.176523299.91415067/v1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1088/1361-6528/ae2626","name":"Robust multilevel storage characteristics of Al&lt;sub&gt;2&lt;/sub&gt;O&lt;sub&gt;3&lt;/sub&gt;/HfO&lt;sub&gt;2&lt;/sub&gt;/Al&lt;sub&gt;2&lt;/sub&gt;O&lt;sub&gt;3&lt;/sub&gt;trilayer-structured memristor fabricated by atomic layer deposition for neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1088/1361-6528/ae2626","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1088/1361-6528/ae2626","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.64898/2025.12.03.692209","name":"CRISPR-based neuromorphic computing for solving regression and classification","source":"europepmc","abstract":"The CRISPR-dCas9 system has emerged as a versatile platform for programmable gene regulation, offering unique advantages in modularity and orthogonality for constructing synthetic genetic circuits. Here, we present a novel architecture for biomolecular neural networks based on dCas9, guide RNAs, and antisense RNA sequestration. Through mathematical modeling and steady-state analysis, we demonstrate that this system functions as a molecular perceptron with a threshold activation function analogous to a saturated rectified linear unit (ReLU). However, a critical challenge in scaling these circuits is competition for the finite dCas9 pool, whose expression must remain low to avoid cytotoxicity. We address this constraint by developing a resource-aware design framework and characterizing how shared dCas9 availability affects network performance. Our results show that for classification tasks, decision boundaries remain invariant under resource competition, while for regression tasks, node thresholds are preserved despite sensitivity in output magnitude under heterogeneous binding conditions. We demonstrate the computational capabilities of this platform through both linear and nonlinear classification problems, as well the approximation of a band-pass function as a proof-of-concept regression task. This work expands the repertoire of molecular mechanisms capable of computation and establishes design principles for implementing CRISPR-based neuromorphic circuits that can execute complex computational tasks within the biochemical constraints of living cells.","url":"https://doi.org/10.64898/2025.12.03.692209","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.64898/2025.12.03.692209","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1038/s41467-025-65691-2","name":"Polymorphic functionalization driven by ion displacement-induced antiferroelectric ordering in CuBiP₂Se₆.","source":"europepmc","abstract":"Antiferroelectric two-dimensional materials, with their unique physical mechanisms, exhibit tunable polarization dynamics and layered structural characteristics, enabling the synergistic implementation of synaptic plasticity, sensory-mimetic functionality, and in-memory computing within a unified device architecture. These capabilities meet the growing polymorphic requirements of neuromorphic systems and position such materials as strong candidates for next-generation neuromorphic computing platforms. Among them, CuBiP₂Se₆ stands out among 2D antiferroelectric materials due to its intrinsic antiferroelectric properties, featuring a stable interlayer antiparallel Cu⁺ dipole configuration. This structure, combined with its relaxor-like behavior, enables a reversible transition between antiferroelectric and ferroelectric states under an applied electric field, along with gradual polarization tuning. This transition mechanism enables continuously tunable conductance states, providing essential physical support for the gradual modulation of synaptic weights and the hardware implementation of complex neural functions, making it particularly suited for high-precision emulation of multilevel synaptic plasticity in neuromorphic applications. In this work, memristor based on two-dimensional antiferroelectric CuBiP₂Se₆ exhibit stable multilevel conductance states, high endurance, and excellent device uniformity, thus supporting diverse neurosynaptic functions and advanced learning rules. These attributes highlight the immense potential of antiferroelectric 2D materials as a foundation for compact, energy-efficient, and highly integrated neuromorphic hardware.","url":"https://doi.org/10.1038/s41467-025-65691-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-65691-2","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1002/adma.202522710","name":"Spectrally Defined Bipolar Black Phosphorus Memristor Enables All-Optical Boolean Logic and Multispectral Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202522710","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202522710","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1039/d5na00980d","name":"Recent progress in HfO&lt;sub&gt;2&lt;/sub&gt;-based ferroelectric devices with oxide semiconductor channels: a comprehensive review.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5na00980d","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d5na00980d","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1021/acsnano.5c17643","name":"Wafer-Scale Monolayer MoS&lt;sub&gt;2&lt;/sub&gt; with Tunable Grain Size via Grain Boundary Engineering for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.5c17643","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsnano.5c17643","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1038/s41467-026-70728-1","name":"Confined-hydrogel fluidic memristor crossbar array for neuromorphic computing.","source":"europepmc","abstract":"Replicating brain-like computation with fluidic memristors offers advantages in energy efficiency and chemical responsiveness over solid-state devices, yet scaling remains challenging due to complex fabrication and their amorphous nature. Herein, we developed a confined hydrogel fluidic memristor by forming a gel-gel interface at the micropore orifice. This design with confined hydrogel enables scalable fabrication of a 10×10 fluidic memristor array (FMA) on polyimide micropores. FMA exhibits fundamental neuromorphic behaviors like paired-pulse facilitation/depression, spike-rate-dependent plasticity, and chemical-regulated plasticity. We also used reservoir computing algorithms with FMA to recognize both computer-generated black-and-white digit images and handwritten digits, achieving a classification accuracy of 89.5% on the Modified National Institute of Standards and Technology dataset. This study demonstrates a hydrogel confined fluidic memristor array, paving an avenue for creating large-scale fluidic memristor arrays and hardware intelligence with ions.","url":"https://doi.org/10.1038/s41467-026-70728-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-70728-1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/smtd.202501966","name":"Organic Transistor-Based Neuromorphic Electronics and Their Recent Applications.","source":"europepmc","abstract":"Neuromorphic technologies offer a promising pathway to address the escalating energy demands of artificial intelligence. At the system level, neuromorphic computing seeks to overcome the von Neumann bottleneck by integrating memory and processing, while neuromorphic sensing minimizes redundant data transfer by processing signals directly at the point of acquisition. Organic transistors have emerged as compelling candidates for emulating synaptic and neuronal behaviors owing to their low power consumption, flexibility, stretchability, and biocompatibility, making them particularly attractive for bio-related neuromorphic applications. This review provides an overview of organic transistor-based artificial synapses and neurons, with emphasis on the mechanisms underlying their neuromorphic behaviors. Subsequently, recent advances in applications, broadly categorized into neuromorphic computing and neuromorphic sensing, are summarized and representative bio-integrated demonstrations are highlighted. Finally, we outline key challenges at the material, device, and system levels, and discuss future opportunities for advancing organic neuromorphic electronics toward practical, biocompatible, and intelligent systems.","url":"https://doi.org/10.1002/smtd.202501966","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smtd.202501966","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acsnano.5c04653","name":"Human Vision-Inspired Low-Power Memtransistor Array for Synchronous Photonic Sensing, Memory, and Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.5c04653","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsnano.5c04653","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1002/advs.202520413","name":"Ultrafast Multilevel Switching and Synaptic Behavior in a Planar Quantum Topological Memristor.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202520413","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.202520413","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1038/s41467-026-70594-x","name":"Antiferroelectric polarization enabling physical activation in CuBiP&lt;sub&gt;2&lt;/sub&gt;Se&lt;sub&gt;6&lt;/sub&gt; for medical image processing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-70594-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-70594-x","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1002/smll.202505378","name":"Ferroelectric-Induced Phase Change Device with Polymorphic Mo&lt;sub&gt;1-x&lt;/sub&gt;W&lt;sub&gt;x&lt;/sub&gt;Te&lt;sub&gt;2&lt;/sub&gt; for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.202505378","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/smll.202505378","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1021/acs.nanolett.6c00983","name":"Nanoelectronics with Two-Dimensional Magnets.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.6c00983","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acs.nanolett.6c00983","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1088/1361-6528/ae1840","name":"Brain-inspired neural networks: neuromorphic devices and their practical applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1088/1361-6528/ae1840","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1088/1361-6528/ae1840","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1038/s41467-026-70963-6","name":"Cryogenic neuromorphic circuits using gate-controlled negative differential resistance in silicon carbide.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-70963-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-70963-6","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1063/5.0298621","name":"AlScN-based ferroelectric memristor for electrical synapse emulation and light-stimulated reservoir computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1063/5.0298621","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1063/5.0298621","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1039/d5mh00306g","name":"2D van der Waals heterostructure memristors: from band structure regulation to neuromorphic computing applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5mh00306g","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1039/d5mh00306g","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1007/s40820-025-02028-0","name":"Synaptic Plasticity Engineering for Neural Precision, Temporal Learning, and Scalable Neuromorphic Systems.","source":"europepmc","abstract":"Manipulating the expression of synaptic plasticity in neuromorphic devices provides essential foundations for developing intelligent, adaptive hardware systems. In recent years, advances have shifted from static emulation toward dynamic, network-oriented plasticity design, offering enhanced computational accuracy and functional relevance. This review highlights how diversified plasticity behaviors, including multilevel long-term potentiation and depression for spatial models, tunable short-term memory for temporal models, as well as wavelength-selective response, excitatory and inhibitory synergy, and adaptive threshold modulation, collectively support key tasks such as stable learning, temporal processing, and context-aware adaptation. Beyond behavioral innovations, strategies such as multifunctional single-device integration, multimodal fusion, and heterogeneous system assembly enable compact, energy-efficient, and versatile neuromorphic architectures. Recent developments at the array level further demonstrate high-performance scalability and system-level applicability. Despite notable progress, current modulation strategies remain constrained in flexibility, diversity, and large-scale coordination. Future research should focus on enriching the behavioral repertoire of plasticity, advancing cross-modal convergence, and improving array-level uniformity, paving the way toward deployable, high-efficiency neuromorphic intelligence.","url":"https://doi.org/10.1007/s40820-025-02028-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s40820-025-02028-0","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1038/s41598-025-28344-4","name":"Neuromorphic robust framework for integrated estimation and control in dynamical systems using spiking neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-28344-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-28344-4","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3390/biomimetics10120808","name":"Portfolio Optimization: A Neurodynamic Approach Based on Spiking Neural Networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics10120808","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/biomimetics10120808","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1093/pnasnexus/pgaf335","name":"A grapeful discovery: Reservoir computing with wine beads.","source":"europepmc","abstract":"In this work, we introduce encapsulated wine beads as a novel, edible material for unconventional and neuromorphic computing. When encapsulated in alginate beads, wine, a complex mixture of proteins, organic acids, sugars, metal ions, and volatiles, exhibits nonlinear electrical behavior and memory effects governed by ox-redox processes. These responses show plasticity-like features, allowing programmable resistance states. The wine beads can be leveraged for computing, and to demonstrate this potential, the wine bead was used as a single-node reservoir for classification tasks. Our findings indicate that the resistance is programmable, exhibits a high degree of repeatability, and can be used for reservoir computing scenarios.","url":"https://doi.org/10.1093/pnasnexus/pgaf335","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1093/pnasnexus/pgaf335","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1039/d5mh00534e","name":"Decoding halide perovskites for neuromorphic and memristive devices.","source":"europepmc","abstract":"The von Neumann architecture serves as the foundation for computers by storing data and instructions in the same memory space; however, it limits the data transfer between the CPU and memory. The human brain is an avant-garde organic machine that connects electrical systems with its network of neurons and synapses. We have 80-100 billion neurons, each connected to >1000 other neurons called synapses, thus totalling 100 trillion connections that excel our decision-making and learning processes. Neuromorphic engineering aims to create brain-like devices that operate effectively with low power consumption to supersede von Neumann for faster computation. Despite their efficacy, neuromorphic chips built with CMOS circuits are complex in replicating biological processes. Neuromorphic computing led to the development of memristors to improve performance, flexibility, and scalability. Wonder materials like halide perovskites with both ionic and semiconductive properties mimic synaptic behaviour. Halide perovskites have exceptional ion transport properties, enabling rapid resistive switching for neuromorphic advancement, and furthermore, respond to various stimuli like light and temperature, offering the potential for emulating complex synaptic behaviours. Halide perovskites can modulate functionalities through structural variations, and dimension reduction endorses versatility in neuromorphic computing and future semiconducting technology. Furthermore, we uncover the mechanisms through which halide perovskites emulate synaptic functions in neuromorphic systems.","url":"https://doi.org/10.1039/d5mh00534e","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1039/d5mh00534e","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1038/s41467-026-71678-4","name":"Retinocortical in-sensor neuromorphic vision platform for NIR-augmented artificial vision.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-71678-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-71678-4","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1021/acsami.5c14332","name":"High-Performance Artificial Synapse Device Based on Cs&lt;sub&gt;3&lt;/sub&gt;Bi&lt;sub&gt;2&lt;/sub&gt;Br&lt;sub&gt;9&lt;/sub&gt;/NiO Heterostructure for Bio-Inspired Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c14332","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c14332","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1021/acsnano.5c19720","name":"Event-Driven Neuromorphic Gaze Decoding via e-Skin Electrooculography.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.5c19720","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsnano.5c19720","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1039/d5cp03132j","name":"Multifunctional ferroelectric synaptic memristors based on HfAlO&lt;sub&gt;&lt;i&gt;x&lt;/i&gt;&lt;/sub&gt; with enhanced Pavlovian learning and physical reservoir computing systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5cp03132j","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1039/d5cp03132j","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1021/acs.nanolett.5c04297","name":"Self-Powered Halide Perovskite Optoelectronic Synaptic Memristors for Reconfigurable Logic and Reservoir Computing Applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.5c04297","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acs.nanolett.5c04297","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1002/smll.202507845","name":"2D Material-Based Memristor Arrays for Flexible and Thermally Stable Neuromorphic Applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.202507845","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/smll.202507845","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1063/5.0307193","name":"Infrared light-responsive CuSbS2 optoelectronic artificial synapses enabling high-accuracy color image recognition and classification.","source":"europepmc","abstract":"","url":"https://doi.org/10.1063/5.0307193","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1063/5.0307193","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1002/advs.202513946","name":"Harnessing Time-Dependent Magnetic Texture Dynamics via Spin-Orbit Torque for Physics-Enhanced Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202513946","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.202513946","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1038/s41467-025-66891-6","name":"Near-infrared organic photoelectrochemical synaptic transistors by wafer-scale photolithography for neuromorphic visual system.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-66891-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-66891-6","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.3389/fnins.2025.1768235","name":"Astrocyte-gated multi-timescale plasticity for online continual learning in deep spiking neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2025.1768235","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fnins.2025.1768235","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1007/s40820-025-02035-1","name":"Self-Rectifying Memristors for Beyond-CMOS Computing: Mechanisms, Materials, and Integration Prospects.","source":"europepmc","abstract":"The deceleration of Moore's law and the energy-latency drawbacks of the von Neumann bottleneck have heightened the pursuit for beyond‑CMOS designs that integrate memory and compute. Self‑rectifying memristors (SRMs) have emerged as promising building blocks for high‑performance, low‑power systems by combining resistive switching with intrinsic diode-like behavior. Their unidirectional conduction inhibits sneak‑path currents in crossbar arrays devoid of external selectors, while nonlinear I-V characteristics, adjustable conductance states, low operating voltages, and rapid switching facilitate efficient vector-matrix operations, neuromorphic plasticity, and hardware security primitives. This review synthesizes the working mechanisms of SRMs, surveys material, and structural strategies and compares device metrics relevant to array‑scale deployment (rectification ratio, nonlinearity, endurance, retention, variability, and operating voltage). We assess SRM-enabled in-memory computing and neuromorphic applications, as well as security functions such as physical unclonable functions and reconfigurable cryptographic primitives. Integration pathways toward CMOS compatibility are analyzed, including back-end-of-line thermal budgets, uniformity, write disturb mitigation, and reliability. Finally, we outline key challenges and opportunities: materials/architecture co‑design, precision analog training, stochasticity control/exploitation, 3D stacking, and standardized benchmarking that can accelerate large‑scale SRM adoption. Through the use of specialized materials and structural optimization, SRMs are set to provide selector‑free, densely integrated, and energy‑efficient hardware for future information processing.","url":"https://doi.org/10.1007/s40820-025-02035-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s40820-025-02035-1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acsami.5c11139","name":"Dielectric-Engineered Monolayer MoS&lt;sub&gt;2&lt;/sub&gt; Memtransistors for Brain-Inspired Computing with High Recognition Accuracy.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c11139","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c11139","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1021/acsami.5c06829","name":"Photonic-Mediated Neuromorphic Computing Enabled by a Copper Oxide Microcrystal Optoelectronic Synapse.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c06829","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c06829","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-7959358/v1","name":"Characterizing Neuromorphic Workloads from A System Perspective","source":"europepmc","abstract":"Abstract Neuromorphic computing is emerging as a cornerstone for next-generation intelligent systems. The lack of standardized benchmarks hinders fair comparison across diverse neuromorphic solutions and fragments research efforts. Here, we introduce a systematical workload characterization methodology that enables quantitative selection of representative benchmarks. Our approach encodes each spiking neural network (SNN) into a unified feature vector by extracting spatial and temporal features from its network topology and spike rasters. Evaluated on 1,030 models across four hardware platforms, the extracted features achieve over 90% accuracy in performance regression and classification, demonstrating both completeness in capturing SNN performance metrics and hardware independence. We expect that this work will provide a principled and scalable foundation for benchmarking neuromorphic systems.","url":"https://doi.org/10.21203/rs.3.rs-7959358/v1","authors":["Youhui Zhang","Zhe Pan","Zeqing Li","Dehua Wu","Peng Qu","Yee Hin Chong"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7959358/v1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1002/adma.202508889","name":"HZO/HSO Superlattice ReFET Array Integrating Optical Sensing for Neuromorphic Vision Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202508889","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/adma.202508889","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1007/s40820-026-02265-x","name":"Convergence of Soft Electronics and Artificial Intelligence: From Materials to Intelligent Systems.","source":"europepmc","abstract":"Soft electronics are an emerging class of mechanically compliant platforms that enable conformal, skin-interfaced sensing and actuation on curvilinear and dynamic surfaces. These systems combine deformation-tolerant electrical functionality with soft contact mechanics, but their in-use performance is strongly influenced by time-varying interfaces, motion-induced artifacts, and the system burden associated with dense multimodal integration. Advances in soft electronics are now converging with artificial intelligence, which supports reliable information extraction from high-dimensional signals and enables on-device inference that tolerates variability across users and day-to-day conditions. Here, progress in this convergence from materials to intelligent systems is summarized. Material and interface foundations are introduced first, focusing on deformation-tolerant conductors, low-impedance biointerfaces, and breathable substrate strategies that support extended wear. Manufacturing and integration approaches are then discussed, highlighting scalable fabrication, multilayer interconnects, and energy-autonomous wireless operation that enable higher channel counts and multifunctional architectures. Learning-based pipelines are subsequently reviewed with emphasis on artifact suppression, nonideality compensation, multimodal inference, and efficient edge deployment. Finally, emerging directions including neuromorphic computing and in-sensor computing are discussed, together with current challenges and future opportunities toward deployable intelligent soft systems that operate continuously and reliably in everyday settings.","url":"https://doi.org/10.1007/s40820-026-02265-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s40820-026-02265-x","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.3389/fdata.2025.1659757","name":"Towards the neuromorphic Cyber-Twin: an architecture for cognitive defense in digital twin ecosystems.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fdata.2025.1659757","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fdata.2025.1659757","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1002/advs.75476","name":"Memristive Physical Reservoir Computing.","source":"europepmc","abstract":"Reservoir computing (RC) has emerged as an efficient neuromorphic framework for temporal information processing, offering low training complexity and hardware-friendly implementation. Memristors' nonlinear dynamics and input-dependent memory effects make them ideal candidates for high-performance physical RC. Based on their conductance modulation, memristors can be classified as electronic or optoelectronic types. However, no systematic review has compared electrically and optically controlled memristive RC. This review fills that gap by comparing them from the device to the system level. We first summarize the resistive switching mechanisms of electronic and optoelectronic memristors, highlighting their distinct roles in RC encoding and processing temporal signals. We then review recent advances in electronic memristive RC, emphasizing architecture innovations and performance improvements in pattern recognition and sequence prediction. Subsequently, we focus on optoelectronic memristive RC, where the high parallelism of optical inputs are harnessed for color vision processing, dynamic gesture recognition, and multi-signals fusion. Notably, we provide a systematic comparison between single-modal and multi-modal RC implementations, demonstrating how hybrid electro-optical stimulation enhances feature diversity and task accuracy. Finally, we outline key challenges and future research directions, including the development of fully hardware-integrated RC systems, system-level multi-modal RC architectures, and novel encoding paradigms.","url":"https://doi.org/10.1002/advs.75476","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.75476","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.mtbio.2026.103088","name":"Engineering halogen-doped carbon dots for enhanced bioinspired synapses toward neuromorphic computing and neural interfaces.","source":"europepmc","abstract":"Neural interfaces demand memristor-based artificial synapses with comprehensive performance for neuromorphic computing and man-machine interaction. This study proposes a halogen doping engineering to enhance carbon dots (CDs)-based memristors performance for artificial synapses. Halogen-doped CDs (FCDs, ClCDs, BrCDs) and undoped CDs (UCDs) were synthesized via a solvothermal method. Systematic characterization confirms successful doping and reveals that Br doping optimally modulates electronic structure. The BrCDs-based memristor demonstrates the best memristor performance among these devices. Experimental and computational results illustrate that appropriate electronegativity of Br atoms can facilitate electron trapping and detrapping process. As a bioinspired synapse, the device successfully mimics key short-term and long-term plasticity, and demonstrates excellent performance in image classification tasks. Furthermore, the BrCDs-based device serves as the core of an artificial neural interface chip, successfully enabling chemical neurotransmitter dopamine release and eliciting Ca 2+ responses in PC12 cells, realizing information communication with the neural system and addressing the mismatch between conventional electronic interfaces and the chemical signaling of biological synapses. This work exhibits the potential of halogen-doped CDs, particularly BrCDs, in advancing artificial synapses integrating the functions of neuromorphic computing and adaptive learning interaction.","url":"https://doi.org/10.1016/j.mtbio.2026.103088","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.mtbio.2026.103088","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.3390/nano16030179","name":"Memristor Synapse-A Device-Level Critical Review.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/nano16030179","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/nano16030179","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1063/5.0295595","name":"A general molecular-scale dynamic memristor model based on non-steady-state charge transport kinetics and its information processing capability in reservoir computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1063/5.0295595","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1063/5.0295595","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.3389/fnins.2025.1676570","name":"A comparative review of deep and spiking neural networks for edge AI neuromorphic circuits.","source":"europepmc","abstract":"Edge AI implements neural networks directly in electronic circuits, using either deep neural networks (DNNs) or neuromorphic spiking neural networks (SNNs). DNNs offer high accuracy and easy-to-use tools but are computationally intensive and consume significant power. SNNs utilize bio-inspired, event-driven architectures that can be significantly more energy-efficient, but they rely on less mature training tools. This review surveys digital and analog edge-AI implementations, outlining device architectures, neuron models, and trade-offs in energy (J/OP), area (μm 2 /OP), and integration technology.","url":"https://doi.org/10.3389/fnins.2025.1676570","authors":["Pietro M. Ferreira","Siqi Wang","Yueyuan Gao","Aziz Benlarbi-Delai"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fnins.2025.1676570","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1021/acsami.5c07364","name":"An Artificial Memristor Synapse by Transferring and Stacking Freestanding Single-Crystalline SrTiO&lt;sub&gt;3-δ&lt;/sub&gt; Films for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c07364","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c07364","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.3389/fncom.2025.1691017","name":"Triboelectric nanogenerators for neural data interpretation: bridging multi-sensing interfaces with neuromorphic and deep learning paradigms.","source":"europepmc","abstract":"The rapid growth of computational neuroscience and brain-computer interface (BCI) technologies require efficient, scalable, and biologically compatible approaches for neural data acquisition and interpretation. Traditional sensors and signal processing pipelines often struggle with the high dimensionality, temporal variability, and noise inherent in neural signals, particularly in elderly populations where continuous monitoring is essential. Triboelectric nanogenerators (TENGs), as self-powered and flexible multi-sensing devices, offer a promising avenue for capturing neural-related biophysical signals such as electroencephalography (EEG), electromyography (EMG), and cardiorespiratory dynamics. Their low-power and wearable characteristics make them suitable for long-term health and neurocognitive monitoring. When combined with deep learning models-including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and spiking neural networks (SNNs)-TENG-generated signals can be efficiently decoded, enabling insights into neural states, cognitive functions, and disease progression. Furthermore, neuromorphic computing paradigms provide an energy-efficient and biologically inspired framework that naturally aligns with the event-driven characteristics of TENG outputs. This mini review highlights the convergence of TENG-based sensing, deep learning algorithms, and neuromorphic systems for neural data interpretation. We discuss recent progress, challenges, and future perspectives, with an emphasis on applications in computational neuroscience, neurorehabilitation, and elderly health care.","url":"https://doi.org/10.3389/fncom.2025.1691017","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fncom.2025.1691017","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41378-025-01074-3","name":"Recent advances in spike-based neural coding for tactile perception.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41378-025-01074-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41378-025-01074-3","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1021/acsaelm.5c02347","name":"A Lithium Fluoride Interfacial Layer for Low-Voltage and Reliable Perovskite Memristors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsaelm.5c02347","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsaelm.5c02347","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acs.chemrev.5c00878","name":"Self-Oscillatory Neuron-like Devices for Unconventional Computing Applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.chemrev.5c00878","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acs.chemrev.5c00878","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/advs.202518193","name":"Recent Advances and Perspectives on Field-Effect Transistors for Artificial Visual Neuromorphic Systems.","source":"europepmc","abstract":"The exponential growth of data has exposed the inherent bottlenecks of the von Neumann architecture-specifically its limited computational efficiency and high energy consumption-necessitating an urgent shift toward innovative hardware solutions. Biological perception systems, particularly the human visual system, serve as a premier model for highly integrated, energy-efficient, and multimodal processing, providing a critical blueprint for the future of intelligent computing. Field-effect transistors (FETs) have emerged as a leading platform for visual neuromorphic systems, leveraging their exceptional optoelectronic tunability, mechanical flexibility, and low-power operation. This review provides a comprehensive overview of FET-based visual neuromorphic systems, covering semiconductor material selection, fundamental device architectures, and governing operational principles. Then, the critical role of these devices in emulating biological visual functions is detailed. Finally, the prevailing technical challenges and future development prospects for FET-mediated perception are discussed. This work aims to provide essential insights into the design of the next generation of artificial visual neuromorphic systems and bio-inspired electronics.","url":"https://doi.org/10.1002/advs.202518193","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.202518193","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1038/s41467-026-70802-8","name":"Nanoscale exchange-bias magnetic tunnel junctions enabled memristive synapse and leaky-integrate-fire neuron for neuromorphic computing.","source":"europepmc","abstract":"Abstract Neuromorphic computing implemented by spintronic memories offers computational advantages, including in-memory computing capability, high energy efficiency, and near-unlimited endurance. However, their basic units, magnetic tunnel junctions (MTJs), face inherent challenges in emulating analog synapses and spiking neurons due to their bistable resistance states and lack of bio-realistic switching dynamics. Here, we experimentally demonstrate on-chip co-integrated memristive synapse and leaky-integrate-fire (LIF) neuron designed with nanoscale exchange-bias MTJs (EB-MTJs). By exploiting the spatial distribution of antiferromagnets and its current-dependent modulation, we achieve stable continuous multi-state synaptic behavior with spike-timing-dependent-plasticity (STDP) characteristics in compact (~100 nm) EB-MTJs. Furthermore, time-resolved measurements reveal that EB-MTJs can be progressively programmed by 0.4 ns pulses, emulating LIF neuronal dynamics with high operational bandwidth in the gigahertz range. Finally, we construct a convolutional spiking neural network based on EB-MTJs and achieve 96% accuracy in gesture recognition via a hybrid backpropagation-STDP algorithm, highlighting their potential in neuromorphic computing.","url":"https://doi.org/10.1038/s41467-026-70802-8","authors":["Zanhong Chen","Dehang Zhu","Ao Du","Yuzhang Shi","Wenlong Cai","Zixi Wang","Yuqi Duan","Shiyang Lu","Kaihua Cao","He Zhang","Deming Zhang","Hongxi Liu"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-70802-8","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1021/acsami.5c15918","name":"Cyclic Plasma Treatment for Enhancing the Synaptic Performance of Bulk-Conductive Resistive Switching Memory.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c15918","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c15918","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1007/s40820-025-02052-0","name":"Biomimetic Synapses Based on Halide Perovskites for Neuromorphic Vision Computing: Materials, Devices, and Applications.","source":"europepmc","abstract":"Abstract The demand for accurate perception of the physical world has led to a dramatic increase in visual sensing data, accompanied by challenges in the energy efficiency of data processing. However, conventional vision systems with separated sensor and processing units struggle to handle increasingly intricate and large-scale data. As such, a rethinking of architecture design is necessary. Inspired by human visual systems, neuromorphic vision computing systems in which computation tasks are moved partly to the sensory or memory units offer transformative solutions to these challenges. As crucial hardware support, biomimetic synapses that replicate synaptic functions and dynamics are urgent for the development of future computing, while further progress requires materials that can support synaptic weight modulation. Given their excellent optical, electrical, and ion migration properties, halide perovskite materials have emerged as promising candidates for biomimetic synapses. Here we review the latest efforts of synaptic devices based on halide perovskite materials for neuromorphic vision computing. We demonstrate the operating mechanism of perovskite synapses and introduce their potential applications in realizing neuromorphic vision computing. We address challenges and future directions related to biomimetic perovskite synapses.","url":"https://doi.org/10.1007/s40820-025-02052-0","authors":["Zhongwen Sun","Xuan Zhao","Haonan Si","Qingliang Liao","Yue Zhang"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s40820-025-02052-0","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1021/acs.nanolett.5c04033","name":"Full Electrical Switching of a Freestanding Ferrimagnetic Metal for Energy-Efficient Bipolar Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.5c04033","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acs.nanolett.5c04033","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1021/acsami.5c13650","name":"Aqueous Electrochemical Memristor Based on Reversible Insulating-Layer Dynamics Emulating Neuromorphic Functions.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c13650","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c13650","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1038/s41467-026-72401-z","name":"Memristive crossbar array-based hardware framework for compressed sensing and event-driven neuromorphic processing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-72401-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-72401-z","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1039/d5nr02736e","name":"Multifunctional ZnO-based optical memristors for synapse-neuron integration and neuromorphic vision systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5nr02736e","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1039/d5nr02736e","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1021/acsnano.5c05240","name":"Advancing Intelligent Neuromorphic Computing: Recent Progress in All-Optical-Controlled Artificial Synaptic Devices.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.5c05240","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsnano.5c05240","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.21203/rs.3.rs-7807556/v1","name":"Photo-induced oxygen vacancy modulation in solution-processed TiO2/ZnFe2O4 heterointerface for all-oxide dual-mode neuromorphic logic memory","source":"europepmc","abstract":"Abstract Memristors, with their ability to switch between resistance states and emulate synaptic plasticity, are promising candidates for brain-inspired neuromorphic computing, having the potential to meet the growing demand for energy-efficient, parallel information processing. However, conventional devices are restricted to either electrical or optical operation, limiting multimodal functionality, commonly observed in the nervous systems. Here, we prepared a spin-coated TiO2/ZnFe2O4 heterojunction that effectively mimics synaptic plasticity under electrical and optical stimuli simultaneously, enabling our device to perform configurable logic operations. Ultraviolet photoelectron spectroscopy combined with the X-ray photoelectron spectroscopy studies before and after illumination suggest light-driven oxygen-vacancy modulation dominates the tunneling current through the heterointerface, resulting in persistent photo-response and optical synaptic plasticity. However, the confined filament formation at the heterointerfaces enables plasticity with electrical pulses. Our solution-processed all-oxide heterojunction memristor with multimodal functionality may provide a biologically realistic pathway to a cost-effective, stable alternative in emulating the human brain.","url":"https://doi.org/10.21203/rs.3.rs-7807556/v1","authors":["Ashok Bera","Faisal Farooq","Priya Kaith"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7807556/v1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1038/s41467-025-64252-x","name":"Photonic neuromorphic computing using symmetry-protected zero modes in coupled nanolaser arrays.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-64252-x","authors":["Kaiwen Ji","Giulio Tirabassi","Cristina Masoller","Li Ge","Alejandro M. Yacomotti"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-64252-x","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1021/acsami.5c10525","name":"Additive-Engineered CsPbBr&lt;sub&gt;3&lt;/sub&gt;-Based Perovskite Memristors for Neuromorphic Computing and Associative Learning Applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c10525","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c10525","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1039/d5mh00953g","name":"Solid-state organic electrochemical transistors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5mh00953g","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1039/d5mh00953g","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.20944/preprints202511.0846.v1","name":"Sustainable Computing for Digital Livestock: Reconciling Artificial Intelligence with Planetary Boundaries","source":"europepmc","abstract":"","url":"https://doi.org/10.20944/preprints202511.0846.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202511.0846.v1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1038/s44172-025-00555-7","name":"Single photon event-driven 3D imaging.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s44172-025-00555-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s44172-025-00555-7","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s42256-026-01255-3","name":"Algorithm-hardware co-design of neuromorphic networks with dual memory pathways.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s42256-026-01255-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s42256-026-01255-3","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/adma.202508029","name":"Integrated Neuromorphic Photonic Computing for AI Acceleration: Emerging Devices, Network Architectures, and Future Paradigms.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202508029","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/adma.202508029","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1038/s41598-026-39515-2","name":"Biologically inspired neuromorphic-XAI synergy for transparent and low-carbon healthcare intelligence.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-39515-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-39515-2","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1021/acs.jpca.5c02941","name":"Emergence of Polymer-Networked Nanoparticle Structures as Primitive Neuromorphic Computing States.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.jpca.5c02941","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acs.jpca.5c02941","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1063/5.0298600","name":"Polarity-dependent dual-mode AlN-embedded RRAM with improved stochastic switching and synaptic modulation for neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1063/5.0298600","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1063/5.0298600","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1021/acs.nanolett.5c02889","name":"Ferroelectric/Antiferroelectric HfZrO&lt;sub&gt;&lt;i&gt;x&lt;/i&gt;&lt;/sub&gt; Artificial Synapses/Neurons for Convolutional Neural Network-Spiking Neural Network Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.5c02889","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acs.nanolett.5c02889","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.21203/rs.3.rs-7207804/v1","name":"Electrical Characteristics of CdSe Quantum Dot Floating Gate Devices for Neuromorphic Synaptic Memory Applications","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-7207804/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7207804/v1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1002/exp.20250234","name":"An Analogue Memristor Based on Conjugated Porous Polymer Composite for Artificial Synapse.","source":"europepmc","abstract":"Artificial synapses have emerged as a pivotal technological advancement in mimicking brain functions. Organic memristors are desirable for hardware implementation of artificial synapses, owing to their remarkable mechanical flexibility, high biocompatibility at cell-device interfaces, and adjustable material structure. Developing appropriate organic polymers with carbon dots modification will enable the memristor to possess analog-type resistive switching behavior, crucial for realizing brain-like associative learning and adapting dynamic variations of neuron connection strength. In this work, an artificial synapse based on the analogue organic memristor integrating neuromorphic computing and neural interface functions is proposed, utilizing synthetic conjugated porous polymers to construct composites with boron-doped carbon dots. The structure-property relationship of alkynyl and alkyl chains in polymers is elucidated, alongside the synergistic effect of local photoinduced redox and hole templating in composites that endows the device with analog-type resistive switching behavior. Moreover, the memristor presents impressive synaptic plasticity and associative memory learning potential for neuromorphic computing, and further serves as a core unit in flexible artificial neural interface chips, demonstrating dynamic information transmission with neural systems. This study will promote the further development of organic artificial synapses for neuromorphic computing and brain-machine interfaces.","url":"https://doi.org/10.1002/exp.20250234","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/exp.20250234","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/tcr.202500353","name":"Hafnium-Based Ferroelectric Field-Effect Transistors With Oxide Semiconductors: Ferroelectric Materials Optimizations, Prospects, and Challenges.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/tcr.202500353","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/tcr.202500353","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.3390/mi17010049","name":"Optimizing TiO<sub>2</sub>/HfO<sub>2</sub> Multilayer RRAM for Self-Rectifying Characteristics.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/mi17010049","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/mi17010049","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.3390/nano15211636","name":"Nanoelectronics: Materials, Devices, and Applications (Second Edition).","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/nano15211636","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/nano15211636","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1039/d5sm00601e","name":"Microfluidic memristive oscillators as universal logic gates for neuromorphic computing.","source":"europepmc","abstract":"To combat the ever growing energy demand of machine learning, we design novel, neuromorphic, iontronic circuits inspired by Shinriki oscillators and based on microfluidic memristors. We show that they form the universal logic NAND gate.","url":"https://doi.org/10.1039/d5sm00601e","authors":["Nex C. X. Stuhlmüller","René van Roij","Marjolein Dijkstra"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1039/d5sm00601e","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1002/advs.202521321","name":"Al Nanoparticle-Decorated Metal Oxide Synaptic Transistors for Ultralow-Energy Neuromorphic Computing with Wide Dynamic Range.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202521321","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.202521321","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1021/acsomega.5c04929","name":"Artificial Synapse Based on Black Phosphorus/SnS&lt;sub&gt;2&lt;/sub&gt; Heterostructure Transistor for Neuromorphic Computing with High Accuracy.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsomega.5c04929","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsomega.5c04929","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1038/s41598-025-27691-6","name":"Hybrid GNN-LSTM defense with differential privacy and secure multi-party computation for edge-optimized neuromorphic autonomous systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-27691-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-27691-6","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1021/acs.nanolett.5c03475","name":"Low Power FA&lt;sub&gt;2&lt;/sub&gt;PbI&lt;sub&gt;4&lt;/sub&gt;/SiO&lt;sub&gt;2&lt;/sub&gt; Bilayer Memristors with Pt Nanoparticles Exhibiting Reconfigurable Synaptic and Neuron Properties for Compact Optoelectronic Neuromorphic Systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.5c03475","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acs.nanolett.5c03475","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1038/s41467-025-62745-3","name":"Smart phosphor with neuromorphic behaviors enabling full-photoluminescent Write and Read for all-optical physical reservoir computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-62745-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-62745-3","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1021/acsnano.5c16053","name":"Synergistic Effects of TiO&lt;sub&gt;2&lt;/sub&gt;@CdS Heterojunctions Enable High-Performance Blue-Light-Sensitive Photodetectors and Iontronic Synapse Fibers for Underwater Interactions.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.5c16053","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsnano.5c16053","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1002/smll.202506638","name":"Opportunities for 2D-Material-Based Multifunctional Devices and Systems in Bioinspired Neural Networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.202506638","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/smll.202506638","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1021/acsami.5c17923","name":"Cellulose Fiber Tortuosity as a Bioinspired Design Strategy for Light-Driven, Self-Powered Ionotronic Synapses.","source":"europepmc","abstract":"The drive toward energy-efficient, brain-inspired computing has spurred interest in ionotronic synapses that mimic ionic signaling in neurons. However, most light-driven synaptic devices overlook the influence of ion transport architecture, an essential aspect of biological learning and memory, which is shaped by the structural complexity of neural tissue. Here, we present a two-terminal ionotronic synaptic device constructed on cellulose fiber substrates, such as thread, cloth, and paper, offering tunable tortuosity to mimic complex ion pathways. Carbon electrodes patterned on these fibers are separated by a gap (∼1 mm) filled with the ionic liquid 1-ethyl-3-methylimidazolium acetate (EMIM: OAc), while lanthanum hexaboride (LaB 6 ) nanoparticles are selectively coated near the gap on one electrode. The device operates in a self-powered mode, utilizing LaB 6 -induced light-to-heat conversion and thermodiffusion in EMIM: OAc, and enables light-modulated synaptic responses. Our findings reveal that upon illumination (λ laser = 638 nm, ∼500 mW), increasing substrate tortuosity reduces the excitatory post-synaptic potential (EPSP) amplitude (∼127 mV, ∼109 mV, and ∼26 mV) when illuminated for 1 s and enhances the retention time (∼245 s, ∼270 s, and ∼4224 s) under a 2.5 Hz light frequency with 10 s on and 20 s off cycles, corresponding to thread, cloth, and paper, respectively. In addition to EPSP, the device emulates paired-pulse facilitation (PPF) and spike-dependent plasticity by modulating optical parameters such as frequency, intensity, duration, and pulse number with operation spanning 450-808 nm. Demonstrations of optically driven Morse code and binary-to-hexadecimal data encryption further showcase the potential for secure communication. This work highlights fiber tortuosity as a previously underexplored yet powerful design variable for developing light-responsive, flexible ionotronic systems for neuromorphic vision and communication technologies.","url":"https://doi.org/10.1021/acsami.5c17923","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c17923","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1038/s41467-026-70668-w","name":"Ferroelectricity-modulated asymmetric van der Waals heterostructure for ultralow-power neuromorphic synapse and logic-in-memory operations.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-70668-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-70668-w","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1038/s41598-026-42077-y","name":"A generic compact model for resistive memories and switches.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-42077-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-42077-y","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.21203/rs.3.rs-7776613/v1","name":"Toward Embedded Intelligence: Architecting CPUs with PC AI Agents","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-7776613/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7776613/v1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1021/acsnano.5c12376","name":"Asymmetric Contact van der Waals Ferroelectric Transistors for Self-Powered Multifunctional Artificial Visual System.","source":"europepmc","abstract":"The development of self-powered artificial visual systems capable of emulating the multifunctionality of the human eye, such as light adaptation, optical memory, and in-sensor computing, is pivotal for next-generation intelligent bionic technologies. In this study, we present a van der Waals ferroelectric field-effect transistor (vdW-FeFET) based on an asymmetric contact α-In 2 Se 3 /h-BN/CIPS heterostructure, which operates entirely in a self-powered mode. By harnessing the intrinsic opto-ferroelectric coupling of α-In 2 Se 3 and the built-in electric fields induced by asymmetric source-drain contact areas, the device exhibits a range of neuromorphic visual behaviors, including visible light sensing and adaptation (405-660 nm), wavelength-dependent color differentiation, and robust optical memory capabilities. The combined effects of photopyroelectric and photothermoelectric mechanisms enable dynamic modulation of the photocurrent, facilitating visual adaptations analogous to biological systems. The device further demonstrates pronounced synaptic characteristics, such as a high paired-pulse facilitation index (∼180%) and memory consolidation from short- to long-term states under repetitive optical stimulation. In particular, pattern recognition is achieved without any external bias, showcasing the potential for autonomous visual signal processing. This work presents a multifunctional, energy-efficient platform for bioinspired vision systems, offering a promising pathway toward neuromorphic computing and next-generation optoelectronic intelligence.","url":"https://doi.org/10.1021/acsnano.5c12376","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsnano.5c12376","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1021/acsenergylett.5c02076","name":"Proton Migration-Modulated n‑Doped Poly(benzodifurandione) Organic Electrochemical Transistors Used for Neuromorphic Computing Applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsenergylett.5c02076","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsenergylett.5c02076","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1038/s41467-025-65589-z","name":"Electrodeposition of magnetic nanonetworks featuring triangular motifs and parallel ridges on a macroscopic scale.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-65589-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-65589-z","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1021/acs.jpclett.5c02991","name":"Bioinspired Retinomorphic Optoelectronic Transistor for Visual Sensing and Processing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.jpclett.5c02991","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acs.jpclett.5c02991","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1002/adma.202512575","name":"Excited State Opto-Ionic Reservoir Computing in Hybrid Perovskite Electrochemically-Gated Luminescent Cells.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202512575","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202512575","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-7402489/v1","name":"Cryogenic neuromorphic circuits using gate-controlled negative differential resistance in silicon carbide","source":"europepmc","abstract":"Abstract Cryogenic electronic circuits are essential for interfacing, control, and error correction for scalable quantum computing platforms operating at millikelvin temperatures, yet face stringent thermal constraints demanding ultra-low power operation. Neuromorphic devices and circuits, emulating the spiking behavior of biological neurons, offer a compelling solution for achieving energy-efficient electronics under these conditions. Here, we report the gate-controlled negative differential resistance (NDR) in silicon carbide (SiC) metal-oxide-semiconductor field-effect transistors (MOSFETs). This NDR effect, arising from impact ionization involving dual dopant levels in SiC MOSFET structures, achieves an unprecedented on/off current ratio of 107, the highest reported among NDR devices to date. Meanwhile, the behavior of NDR can be fully controlled by the gate voltage of the MOSFET. Leveraging this gate-controlled NDR, we demonstrate programmable cryogenic spiking neuromorphic circuits, including sensory, logic, and integrate-and-fire neurons, with functionality tuned by gate or drain voltages. The established foundry-level manufacturability of SiC devices underscores their significant potential for integration into scalable cryogenic platforms for advanced sensing, computing, and quantum information applications.","url":"https://doi.org/10.21203/rs.3.rs-7402489/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7402489/v1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1039/d5cs00251f","name":"All-in-one neuromorphic hardware with 2D material technology: current status and future perspective.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5cs00251f","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1039/d5cs00251f","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1021/acs.jpclett.5c02548","name":"Van der Waals Epitaxy of CsPbI&lt;sub&gt;3&lt;/sub&gt;/MoS&lt;sub&gt;2&lt;/sub&gt; Heterojunction Phototransistors for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.jpclett.5c02548","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acs.jpclett.5c02548","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.22541/au.175580538.80500974/v1","name":"Radiation-Aware Meta-Plasticity (RAMP): A Bio-Inspired Learning Rule for Neuromorphic Computing in Radiation-Prone Environments","source":"europepmc","abstract":"Neuromorphic computing systems, particularly those based on spiking neural networks (SNNs), provide exceptional energy efficiency and real-time processing, making them attractive for space, nuclear, and high-energy physics (HEP) applications. Their deployment, however, is challenged by ionizing radiation, which induces stochastic degradation, weight drift, and functional failure in CMOS-based synaptic components. To address this, we propose Radiation-Aware Meta-Plasticity (RAMP), a bio-inspired learning rule that dynamically modulates spike-timing-dependent plasticity (STDP) in response to neuronal activity and radiation exposure. RAMP introduces a dose- and time-dependent learning rate, integrating cumulative radiation dose, a membrane-voltage-based environmental regularizer, and explicit modeling of radiation-induced effects including noise, single-event transients, and total ionizing dose (TID) drift. MATLAB simulations of Leaky Integrate-and-Fire neurons under Poisson spike trains and mixed radiation profiles demonstrate that RAMP reduces synaptic weight variance by 32.8% compared to standard STDP while preserving Hebbian learning and convergence. Statistical analysis confirms that RAMP selectively suppresses noise during bursts without halting long-term adaptation. Furthermore, the effective learning rate decays exponentially with dose, mimicking biological synaptic downscaling under chronic stress. These results establish RAMP as a foundation for radiation-resilient neuromorphic intelligence, with direct implications for aerospace autonomy, nuclear safety, and HEP experiments.","url":"https://doi.org/10.22541/au.175580538.80500974/v1","authors":["Solomon Mamo Banteywalu","Paul Leroux"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.22541/au.175580538.80500974/v1","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1002/adma.202515532","name":"Organic Electrochemical Transistors for Neuromorphic Devices and Applications.","source":"europepmc","abstract":"Abstract Neuromorphic engineering, an interdisciplinary field bridging bioelectronics and neuroscience, endeavors to address the bottleneck of the von Neumann architecture by constructing hardware‐level artificial neural networks (ANNs) and replicate the complicated architecture and functionality of the human brain, heralding a new era of intelligent sensing, processing, and computing systems. Organic electrochemical transistors (OECTs), which operate via the bulk doping of organic mixed ionic–electronic conductors, are emerging as promising platforms for neuromorphic devices that emulate neuronal and synaptic activities while seamlessly integrating with biological systems. OECTs offer several advantages, including compatibility with flexible and stretchable substrates, tunable ionic and electronic conductivity, multimodal sensing capability, and operation at low voltages. This review aims to provide a comprehensive and state‐of‐the‐art vista of the rapidly advancing field of OECT‐based neuromorphic devices, including organic electrochemical neurons, organic electrochemical synapses, and their integrated devices. Particular emphasis is placed on their ability to perform neuromorphic functions and diverse applications in neuromorphic computing and flexible biointerfaces. Conclusions, remaining challenges, and future prospects for the development of OECT‐based neuromorphic devices are finally outlined.","url":"https://doi.org/10.1002/adma.202515532","authors":["Kexin Xiang","Jiajun Song","Hong Liu","Junxin Chen","Feng Yan"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202515532","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3762/bjnano.16.131","name":"Programmable soliton dynamics in all-Josephson-junction logic cells and networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.3762/bjnano.16.131","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3762/bjnano.16.131","addedAt":"2026-09-01T01:48:19.714Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1039/d5nr03494a","name":"Boron nitride memristors: from mechanism and device optimization to integrated applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5nr03494a","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1039/d5nr03494a","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1021/acsami.5c18166","name":"Two-Terminal Ferroelectric Artificial Synaptic Devices with Asymmetric Structure.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c18166","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c18166","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1016/j.arr.2025.102923","name":"Detection and rehabilitation of age-related motor skills impairment: Neurophysiological biomarkers and perspectives.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.arr.2025.102923","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.arr.2025.102923","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1002/smll.202504118","name":"2D Material-Based Bioinspired Devices for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.202504118","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/smll.202504118","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1038/s41467-026-71937-4","name":"Higher-order neuromorphic Ising machines-autoencoders and Fowler-Nordheim annealers are all you need for scalability.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-71937-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-71937-4","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.21203/rs.3.rs-8081851/v1","name":"Polymorphic Butterfly Attractors in a Bi-Magnetized Tabu Learning Neural Network and Its Analog Circuit Implementation","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-8081851/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-8081851/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.20944/preprints202512.0200.v1","name":"From Qubits to Quantum Algorithms: The Evolution of Modern Computing","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202512.0200.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202512.0200.v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-7544738/v1","name":"Optical Singularity Protractor for Rotating Metrology with Neuromorphic Sensing","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-7544738/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7544738/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-7993782/v1","name":"On-Skin Artificial Intelligence via Supramolecular Polymer Memtransistors","source":"preprints","abstract":"Abstract On-skin artificial intelligence (AI) demands hardware that couples skin-like mechanics with efficient, real-time computation on noisy, spatiotemporal biosignals. We introduce a supramolecular polymer memtransistor that unifies intrinsic stretchability, autonomous self-healing and low-power neuromorphic dynamics in a single material platform. The device integrates a supramolecular elastomer matrix with a p-n heterojunction semiconductor to realize charge trapping-driven short-term plasticity, high on/off ratios (>103) and tight device-to-device uniformity (σ/μ = 5.25%). Operating energies span 0.29 fJ-1.8 nJ per event, approaching the lower bound of biological synapses while retaining reliable control of synaptic weights. Arrays (7 × 7) serve as a physical reservoir for on-device reservoir computing, achieving >99% accuracy in spoken-digit recognition and robust emotion recognition (74% under 30% biaxial strain; 71% after self-healing), all maintained during 30% biaxial deformation and after autonomous recovery from deliberate damage. Beyond classification, recursive multi-step forecasting with online learning stably models chaotic dynamics with normalized RMSE ≲ 0.02, sustaining accurate long-horizon predictions. These results establish supramolecular polymer memtransistors as a materials-driven route to elastic, damage-tolerant and energy-efficient neuromorphic electronics that perform AI inference and prediction directly on the body, enabling bio-integrated systems for speech, affect and complex physiological time-series analysis.","url":"https://doi.org/10.21203/rs.3.rs-7993782/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7993782/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-7089051/v1","name":"A Superconducting Flux-Quanta Memory Device for Cryogenic Neuromorphic and Probabilistic Computing","source":"preprints","abstract":"Abstract As quantum computing progresses toward large-scale implementation, there is a growing demand for cryo-compatible artificial intelligence hardware and computing paradigms that accelerate the quantum control and error correction. Here, we present a superconducting memory device composed of a flux-quanta storage loop and a superconducting quantum interference device (SQUID), functioning as an artificial synapse and a binary stochastic neuron, respectively. Information is encoded in the stochastic behavior of the pulse stream passing through the neuron and is extracted by counting the number of SQUID switching events. In this scheme, sampling precision is flexibly tunable by adjusting the total number of input pulses. This architecture enables both neuromorphic and probabilistic computing, achieving 100% accuracy in nine-pixel image classification and integer factorization tasks by tuning the sampling precision. Furthermore, we found that the fabrication non-uniformities of up to 7.1% can be effectively compensated by an increased coupling strength. These results highlight the potential of superconducting memory devices as scalable and robust building blocks for implementing versatile AI computing paradigms under cryogenic conditions.","url":"https://doi.org/10.21203/rs.3.rs-7089051/v1","authors":["Lei Chen","Yue Wang","Xu Liu","Zengxu Zheng","Xinxin Fan","Xiaoyu Liu","Ling Wu","Weifeng Shi","Lu Zhang","Wei Peng","Jie Ren","Zhen Wang"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7089051/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1101/2025.07.25.666748","name":"Neuromodulation enhances the capability and efficiency of spiking neural networks","source":"preprints","abstract":"Abstract Spiking neurons underlie the brain’s extreme energy efficiency, and therefore have great potential in neuromorphic computing, although realising this efficiency in practice has proven challenging. We use neuromodulation, a biological mechanism that lets the network dynamically and contextually modify its own parameters. We find it substantially increases performance across a range of sensory processing tasks, including a challenging new speech-in-noise dataset we introduce, with very few additional resources (neurons, energy, parameters). Neuromodulatory networks are space and energy efficient thanks to two mechanisms that are directly relevant to neuromorphic computing and biology: firstly, they allow for an order-of-magnitude reduction in the number of neurons required; and secondly, they enable very sparse firing, achieving better results using orders of magnitude fewer spikes. Together, these properties may throw light on the computational role of neuromodulation in biology, and make neuromodulation an ideal mechanism to improve performance and efficiency for neuromorphic devices.","url":"https://doi.org/10.1101/2025.07.25.666748","authors":["AbdelQader AlKilany","Dan F. M. Goodman"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.07.25.666748","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.07.11.664296","name":"Sustainable Memristors from Shiitake Mycelium for High-Frequency Bioelectronics","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.07.11.664296","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.07.11.664296","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.22541/au.175638505.58202572/v1","name":"Toward Trustworthy Neuromorphic AI: A Bayesian Framework for Uncertainty-Aware Spiking Neural Networks","source":"europepmc","abstract":"Spiking Neural Networks (SNNs) offer a biologically plausible and energy-efficient paradigm for processing temporal data, particularly suited for neuromorphic computing platforms. However, their deterministic nature limits their deployment in safety-critical applications where reliable uncertainty quantification is essential. This paper introduces a novel Bayesian Spiking Neural Network (BSNN) framework that integrates variational inference with surrogate gradient learning to enable robust uncertainty estimation while preserving the efficiency of SNNs. We formulate a scalable Bayesian framework using mean-field variational approximation over network weights and biases, enabling full predictive uncertainty quantification through Monte Carlo sampling. To address the non-differentiability of spiking dynamics, we employ a smooth surrogate gradient method based on sigmoidal derivatives during backpropagation through time. A tailored Poisson encoding scheme ensures rich temporal input representation, while a KL annealing strategy stabilizes training by gradually increasing the regularization pressure from prior distributions. Comprehensive experiments on a synthetic dataset demonstrate competitive classification accuracy (77.78%) alongside well-calibrated uncertainty estimates, as evidenced by strong calibration curves and high AUROC scores (&gt; 0.9). The model exhibits stable training dynamics, with controlled gradients and balanced loss components. Our approach bridges the gap between efficient neuromorphic computation and trustworthy AI, offering a pathway toward deployable, uncertainty-aware edge intelligence systems.","url":"https://doi.org/10.22541/au.175638505.58202572/v1","authors":["Solomon Mamo Banteywalu","Paul Leroux"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.22541/au.175638505.58202572/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.22541/au.176159368.86236413/v1","name":"AI-Native & Quantum-Ready Data Centers: Modernizing Infrastructure for the Next Digital Frontier","source":"preprints","abstract":"","url":"https://doi.org/10.22541/au.176159368.86236413/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.22541/au.176159368.86236413/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.20944/preprints202507.2513.v1","name":"Quantum-Inspired Neural Radiative Transfer (QINRT): A Multi-Scale Computational Framework for Next-Generation Climate Intelligence","source":"europepmc","abstract":"The escalating demands for high-resolution, real-time radiative transfer (RT) modeling in climate science and remote sensing necessitate a paradigm shift beyond classical solvers, such as DISORT and RRTMG, which struggle with spectral complexity, non-LTE physics, and computational scalability. Here, we present Quantum-Inspired Neural Radiative Transfer (QINRT), a novel framework integrating quantum information theory, neural operators, and neuromorphic computing to address these challenges. QINRT employs tensor networks (Matrix Product States, Tree Tensor Networks) for the efficient compression of high-dimensional radiative fields, while preserving quantum correlations, thereby enabling the accurate modeling of aerosol-cloud interactions and optically thick media. Quantum Neural Operators (QNOs) combine parameterized quantum circuits with Fourier Neural Operators (FNOs) to accelerate nonlinear atmospheric mappings, achieving order-of-magnitude speedups in inverse RT problems. Deployable on neuromorphic hardware (Intel Loihi, IBM TrueNorth), QINRT’s spiking neural networks enable energy-efficient, real-time inference for satellite constellations and UAVs. Benchmarked on AQuA-2024 and NOAA-QClim datasets, QINRT reduces RMSE by 37–39% over classical 6S models while maintaining sub-nanometer spectral fidelity. Applications span quantum-enhanced climate forecasting, exoplanetary biosignature detection, and adversarial-resistant climate AI via post-quantum cryptography and quantum reservoir computing. By unifying quantum-inspired algorithms with scalable neuromorphic architectures, QINRT establishes a transformative foundation for autonomous, physics-aware climate intelligence and next-generation Earth-system digital twins.","url":"https://doi.org/10.20944/preprints202507.2513.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202507.2513.v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.21203/rs.3.rs-7734741/v1","name":"Memristive Crossbar Array-based Hardware Framework for Compressed Sensing and Event-Driven Neuromorphic Processing","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-7734741/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7734741/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-6733095/v1","name":"Reconfigurable large-scale optoelectronic reservoir computing on programmable silicon photonic processor","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-6733095/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6733095/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-7141224/v1","name":"Fully Integrated Memristive Spiking Neural Network with Analog Neurons for High-Speed Event-Based Data Processing","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-7141224/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7141224/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.20944/preprints202506.1338.v1","name":"Neuromorphic Modeling of Molecular Signatures in the Human Spine","source":"preprints","abstract":"Background: Spinal disorders frequently involve dynamic molecular cascades that unfold over multiple timescales, posing challenges for early diagnosis and intervention. Traditional sensing technologies often fail to resolve fast biochemical changes or integrate longitudinal data critical for tracking progression in spinal pathology. Neuromorphic computing, with its biologically inspired architecture and event-driven processing, offers a compelling paradigm for real-time, low-power interpretation of complex molecular signals in spinal health. Methods: This review synthesizes current approaches to neuromorphic sensing and computing as applied to spinal molecular diagnostics. We examine the role of spiking neural networks (SNNs), event-based sensory platforms, and recursive temporal attention (RTA) frameworks in modeling key molecular processes including inflammatory mediator flux, extracellular matrix remodeling, and epigenetic regulatory shifts. Hardware platforms such as Intel s Loihi, BrainChip s Akida, IBM s TrueNorth, and SynSense Speck are evaluated for their utility in biomarker tracking and closed-loop spinal monitoring. Results: Neuromorphic systems demonstrate the ability to detect microsecond-scale variations in cytokine levels (e.g., IL-6, TNF- ), proteoglycan turnover, and gene expression modifiers relevant to spinal degeneration. Recursive temporal attention mechanisms improve the interpretability of multi-timescale molecular data, supporting early prediction of disc dehydration, inflammatory flares, and therapeutic response patterns. Analog-digital hybrid circuits facilitate continuous bioimpedance spectroscopy and multiplex cytokine detection with power consumption under 5 mW, enabling potential implantable use. Conclusion: Neuromorphic sensing architectures, coupled with adaptive learning algorithms, offer a promising solution for intelligent molecular diagnostics in spinal disorders. By integrating temporal molecular dynamics with event-based computation, these platforms pave the way for autonomous, personalized, and energy-efficient systems in orthopedic and neurorehabilitation applications. Future development should focus on hardware-software co-design, clinical integration, and regulatory pathways to realize scalable spinal biosensor ecosystems.","url":"https://doi.org/10.20944/preprints202506.1338.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202506.1338.v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.20944/preprints202512.0118.v1","name":"A Comprehensive Survey of Federated Learning for Edge AI: Recent Trends and Future Directions","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202512.0118.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202512.0118.v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.21203/rs.3.rs-7175066/v1","name":"An organic spiking artificial neuron with excitatory and inhibitory synapses: towards soft and flexible organic neuromorphic processing","source":"preprints","abstract":"Abstract Artificial neurons are key components of neuromorphic computing systems, which aim to emulate the structure and functions of biological neural networks for efficient, brain-like computation. However, most artificial neurons rely on rigid, silicon-based technologies that are poorly suited for integration with soft structures, such as soft robots or biological organisms. Here, we report the first organic spiking neuron equipped with excitatory and inhibitory synapses, constructed from complementary organic field-effect transistors and capacitors, all integrated on the same physically flexible substrate. The circuit emulates key neural functions including signal integration, frequency modulation, coincidence detection, and tunable synaptic weights. The synapses demonstrate excitatory and inhibitory time constants of 60\\,ms and 280\\,ms, respectively. The neuron exhibits linear response properties, with output firing rates in the range 0 to 60\\,Hz. We showcase the neuron's ability to interact with the environment, by embedding it in a light-control feedback loop that adjusts luminance based on ambient light intensity. This work establishes a foundation for flexible, and low-power neuromorphic systems with the potential for direct integration with soft, or living tissue, paving the way for next-generation scalable and biocompatible intelligent sensory-processing systems.","url":"https://doi.org/10.21203/rs.3.rs-7175066/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7175066/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-7438138/v1","name":"Conjugated Backbone-Directed Side Chain-Electrolyte Coupling toward Nonvolatile Artificial Synapse","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-7438138/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7438138/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-6324848/v1","name":"Neuromorphic Computing Using Memristor Synapses and CMOS Neurons","source":"europepmc","abstract":"Abstract To address the increasing demands of artificial intelligence applications and the limitations of traditional computing, such as high power consumption, limited scalability, and inadequate parallelism, neuromorphic computing systems have been developed. This paper introduces a neuromorphic computing system designed for robust digit pattern recognition. A 20x20 memristor array-based synapse circuit, integrated with a refined Axon-Hillock (A-H) neuron model, forms the foundation to emulate synaptic and neuronal dynamics. A hard-coded approach is employed to adjust the synaptic weights of the memristor array for recognising digit patterns from 1 to 9. The results demonstrate that the neuromorphic computing system can accurately recognise the input patterns. Notably, the system is capable of maintaining its recognition abilities with 5% noise interference.","url":"https://doi.org/10.21203/rs.3.rs-6324848/v1","authors":["Jia Wen Choo","Shibajee Nath","T. Nandha Kumar"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6324848/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.21203/rs.3.rs-6838264/v1","name":"Artificial Synapse with Tunable Dynamic Range for Neuromorphic Computing with Ion Intercalated Bilayer Graphene","source":"europepmc","abstract":"Abstract In neuromorphic computing, a tunable dynamic range in artificial synapses is crucial, as it allows devices to emulate the human brain's efficiency in processing complex information with analog programmable states. Here, we introduce an electrochemical random-access memory (ECRAM) based on bilayer graphene. Our device achieves a large and programmable dynamic range through lithium-ion (Li+) intercalation, pulse modulation, and geometric engineering. We systematically investigated how pulse parameters, including amplitude, duty cycle, frequency, and signal type, affect conductance and dynamic range. Our results demonstrate that higher pulse amplitudes and/or longer duty cycles enhance Li+ intercalation efficiency; while lower frequencies pulse trains facilitate ion intercalation, significantly influencing conductance and dynamic range. Additionally, we explored how geometric factors such as channel length in bilayer and multi-layer graphene and the introduction of hole structures may affect intercalation kinetics and subsequently device performance. First-principles density functional theory (DFT) calculations were also performed to support that the interlayer space in bilayer graphene is energetically favorable for Li transport, and that hole structures promote efficient Li intercalation by providing barrierless pathways through the exposed edges of the bilayer. These findings confirm bilayer graphene as a promising material for developing high-performance artificial synapses with tunable characteristics.","url":"https://doi.org/10.21203/rs.3.rs-6838264/v1","authors":["Yuzhi He","Purun (Simon) Cao","Shahin Hashemkhani","Yihan Liu","Daniel Vaz","Keya Joy","Nathan Youngblood","Rajkumar Kubendran","M. P. Anantram","Feng Xiong"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6838264/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.14293/pr2199.001966.v1","name":"From Error Correction to Engineered Noise: A Bio-Inspired Path to Scalable Quantum Computing","source":"preprints","abstract":"","url":"https://doi.org/10.14293/pr2199.001966.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.14293/pr2199.001966.v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-7952653/v1","name":"Critical Phenomena on a 3D Fractal with Intermediate Dimensionality: Tensor-network study","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-7952653/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7952653/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-6132037/v1","name":"Neuromorphic Photonic Computing with an Electro-Optic Analog Memory","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-6132037/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6132037/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.20944/preprints202503.0916.v1","name":"2D Spintronics for Neuromorphic Computing with Scalability and Energy Efficiency","source":"europepmc","abstract":"The demand for computing power has been growing exponentially with the rise of artificial intelligence (AI), machine learning, and the Internet of Things (IoT). This growth requires unconventional computing primitives that prioritize energy efficiency, while also addressing the critical need for scalability. Neuromorphic computing, inspired by the biological brain, offers a transformative paradigm for addressing these challenges. This review paper provides an overview of advancements in 2D spintronics and device architectures designed for neuromorphic applications, with a focus on techniques such as spin-orbit torque, magnetic tunnel junctions, and skyrmions. Emerging van der Waals materials like CrI3, Fe3GaTe2, and graphene-based heterostructures have demonstrated unparalleled potential for integrating memory and logic at the atomic scale. This work highlights technologies with ultra-low energy consumption (0.14 fJ/operation), high switching speeds (sub-nanosecond), and scalability to sub-20 nm footprints. It covers key material innovations and the role of spintronic effects in enabling compact, energy-efficient neuromorphic systems, providing a foundation for advancing scalable, next-generation computing architectures.","url":"https://doi.org/10.20944/preprints202503.0916.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202503.0916.v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:22.907Z"},{"id":"doi:10.20944/preprints202508.0464.v1","name":"Recent Advances in Efficient Spiking Neural Networks: Architectures, Learning Rules, and Hardware Realizations","source":"preprints","abstract":"Spiking Neural Networks (SNNs) have emerged as a promising paradigm for energy-efficient and event-driven computing, drawing inspiration from biological neurons. Recent research has introduced novel methods to enhance the performance, robustness, and hardware compatibility of SNNs. This review synthesizes key advances across five major areas: pulse width modulation (PWM)-based spike generation to eliminate timing errors, spike-timing-dependent plasticity (STDP) acceleration via early termination and spike count strategies, event-driven spike detection for neuromorphic implantable brain–machine interfaces (iBMIs), one-spike phase coding with base manipulation to minimize ANN-to-SNN conversion loss, and memristor-based radial-basis spiking neuron circuits for adversarial attack resilience. By analyzing over 45 recent IEEE studies, we highlight trade-offs between accuracy, latency, and power consumption while benchmarking hardware implementations. Furthermore, we discuss open challenges, including the need for improved conversion techniques, adaptive coding schemes, and scalable hardware platforms. This review aims to provide a comprehensive foundation for researchers and engineers seeking to advance SNN technologies for next-generation neuromorphic systems.","url":"https://doi.org/10.20944/preprints202508.0464.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202508.0464.v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1101/2025.08.20.671348","name":"Morphologically Tunable Mycelium Chips for Physical Reservoir Computing","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.08.20.671348","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.08.20.671348","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-5612896/v1","name":"Edge-of-chaos operation and persistent dynamics for neuromorphic meminductor computing","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-5612896/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-5612896/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-7245457/v1","name":"Scalable and Robust Multi-Bit Spintronic Synapses for Analog In-Memory Computing","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-7245457/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7245457/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-6467495/v1","name":"Recent Developments in Photonic Integration: Reservoir Computing in Photonics using Silicon Microring Nonlinearities","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-6467495/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6467495/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-7867840/v1","name":"Atomic-scale strain-confined ferroelectricity in fluorite hafnium dioxide","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-7867840/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7867840/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-3993700/v2","name":"Actor-Critic Networks with Analogue Memristors Mimicking Reward-Based Learning","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3993700/v2","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-3993700/v2","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1101/2025.06.20.660760","name":"Neuromorphic hierarchical modular reservoirs","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.06.20.660760","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.06.20.660760","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-7318696/v1","name":"Modified Spike Backpropagation Design towards Highly Parallelable Hardware Implementation","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-7318696/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7318696/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.20944/preprints202503.1505.v1","name":"Neuromorphic Computing with Large Scale Spiking Neural Networks","source":"europepmc","abstract":"","url":"https://doi.org/10.20944/preprints202503.1505.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202503.1505.v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-6829733/v1","name":"Amorphous, fully-stoichiometric molybdenum oxide for high performance nonvolatile resistive switching memory: The role of stoichiometry on synaptic plasticity","source":"preprints","abstract":"Abstract Transition metal oxides (TMOs) are a promising class of materials for neuromorphic computing and processing systems demonstrating a variety of resistive switching (RS) mechanisms. However, little is known about the correlation between its stoichiometry and RS. This study is focused on the development and characterization of amorphous molybdenum oxide memristors with different stoichiometry. Fully-stoichiometric (MoO 3 ) and hydrogenated sub-stoichiometric (H-MoO 3 − x ) amorphous molybdenum oxide thin films were developed via a hot-wire chemical vapor deposition system. Both, stoichiometric and hydrogenated sub-stoichiometric molybdenum oxide devices showed good resistive switching behavior. However, the fully-stoichiometric memristor exhibited better RS properties with endurance of 250 cycles, ON/OFF ratio ~ 10 3 and high retention of almost 3·10 4 s, compared with the poor RS behavior of the device based on the H-MoO 3 − x film. This impressive memristive behavior could be attributed to the excess of oxygen atoms in the case of fully-stoichiometric memristor in respect to the sub-stoichiometric H-MoO 3 − x which play crucial role in the conductive behavior of the device. The high reproducibility observed in MoO 3 -based memristor highlights their potential for practical applications and scalability. Additionally, the outstanding features of the MoO 3 memristor demonstrated through its long-term potentiation (LTP), long-term depression (LTD), and spike-timing dependent plasticity (STDP) indicate that the fully stoichiometric molybdenum oxide memristor has significant potential for simulating biological synapses, opening doors to a new era in neuromorphic computing applications.","url":"https://doi.org/10.21203/rs.3.rs-6829733/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6829733/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.20944/preprints202509.1538.v1","name":"The Spike Processing Unit (SPU): An IIR Filter Approach to Hardware-Efficient Spiking Neurons","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202509.1538.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202509.1538.v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1101/2025.03.28.646019","name":"A canonical cortical electronic circuit for neuromorphic intelligence","source":"preprints","abstract":"Cortical microcircuits play a fundamental role in natural intelligence. While they inspired a wide range neural computation models and artificial intelligence algorithms, few attempts have been made to directly emulate them with an electronic computational substrate that uses the same physics of computation. Here we present a heterogeneous canonical microcircuit architecture compatible with analog neuromorphic electronic circuits that faithfully reproduce the properties of real synapses and neurons. The architecture comprises populations of interacting excitatory and inhibitory neurons, disinhibition pathways, and spike-driven multi-compartment dendritic learning mechanisms. By co-designing the computational model with its neuromorphic hardware implementation, we developed a neural processing system that can perform complex signal processing functions, learning, and classification tasks robustly and reliably, despite the inherent variability of the analog circuits, using ultra-low power energy consumption features comparable to those of their biological counterparts. We demonstrate how both the model architecture and its hardware implementation seamlessly capture the hallmarks of neural computation: attractor dynamics, adaptation, winner-take-all behavior, and resilience to variability, within a compact, low-power computing substrate. We validate the model’s learning performance both from the algorithmic perspective and with detailed electronic circuit simulation experiments and characterize its robustness to noise. Our results illustrate how local, biologically plausible rules for plasticity and gating can overcome challenges like catastrophic forgetting and parameter variability, enabling effective always-on adaptation. Beyond offering insights into the nature of computation in neural systems, our approach introduces a foundation for ultra-low power, fault-tolerant architectures capable of complex signal processing at the edge. By embracing -rather than mitigating-variability, these neuromorphic circuits exhibit a powerful synergy with emerging memory technologies, suggesting a new paradigm for sophisticated “in-memory” computing. Through such tight integration of neuroscience principles and analog circuit design, we pave the way toward a class of brain-inspired processors that can learn continuously and respond dynamically to real-world inputs.","url":"https://doi.org/10.1101/2025.03.28.646019","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.03.28.646019","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-7176023/v1","name":"All-Optical Temporal Integration Mediated by Subwavelength Heat Antennas","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-7176023/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7176023/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.32388/a4t30z","name":"Angular-Controlled GST Phase-Change Double Micro-Ring Resonator for High-Speed Activation Functions in Neuromorphic Computing","source":"preprints","abstract":"","url":"https://doi.org/10.32388/a4t30z","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.32388/a4t30z","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1101/2025.08.10.669034","name":"Online supervised learning of temporal patterns in biological neural networks under feedback control","source":"preprints","abstract":"ABSTRACT In vitro biological neural networks (BNNs) provide a well-defined model system to constructively investigate how living cells interact with their environment to shape high-dimensional dynamics that could be used to generate a coherent temporal output, such as those required for motor control. Here, we developed a real-time closed-loop BNN system capable of generating periodic and chaotic temporal signals by integrating cultured cortical neurons with microfluidic devices and high-density microelectrode arrays. We show that training a simple linear decoder with fixed feedback weights enables the system to learn and autonomously generate diverse temporal patterns. When feedback was switched on, irregular activity in BNNs is transformed into low-dimensional, structured dynamics, producing coherent trajectories characterized by stable transitions between neural states. BNNs trained on different target frequencies—ranging from 4 to 30 s—could be trained to sustain oscillations at distinct frequencies, demonstrating their adaptability. Importantly, a top-down control of self-organized network formation with microfluidic devices is the key to suppress excessive synchronization and increase dynamical complexity in BNNs, facilitating the training and robust output generation. This work offers a biologically inspired platform for understanding the physical basis of cortical computation and for advancing energy-efficient neuromorphic computation. Significance Statement Reservoir computing is a machine learning paradigm that exploits the transient dynamics of high-dimensional nonlinear systems. Although it was originally inspired by the mammalian brain and widely explored in physical systems, its implementations in biological neural networks (BNNs) have been limited due to their excessive connectivity and global synchrony in vitro. Here, we use microfluidic devices to construct modular, nonrandomly connected BNNs and integrate them with microelectrode arrays in a closed-loop reservoir computing environment. We show that the system can be trained to autonomously output various temporal signals, with the modular connectivity that is essential for learning. In vitro BNNs provide unique alternatives for physical reservoirs with dynamic adaptability.","url":"https://doi.org/10.1101/2025.08.10.669034","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.08.10.669034","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-6742959/v1","name":"Behavioral Time Scale Synaptic Plasticity (BTSP) endows Hyperdimensional Computing with brain-like information retrieval flexibility","source":"preprints","abstract":"Abstract Hyperdimensional computing (HDC) addresses massively parallel implementations of symbolic computations that are both more transparent than ANNs and LLMs and more suitable for in-memory computing on highly energy-efficient analog hardware. It captures an essential aspects of brain computations: objects, concepts, and their attributes are encoded by very sparse distributed representations. But currently known methods for binding these tokens together entail deficits in flexible information retrieval. We show that a mechanism which the brain employs for binding, Behavioral Time Scale Synaptic Plasticity (BTSP), overcomes these deficiencies by adding attractor features to high-dimensional representations. They drastically improve the capability to recover from composed representations the tokens which have been bound together in them. One arrives in this way at a functionally more powerful HDC paradigm that provides new perspectives both for understanding how brains carry out symbolic computations, and for implementing them in novel energy-efficient and massively parallel neuromorphic hardware.","url":"https://doi.org/10.21203/rs.3.rs-6742959/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6742959/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.20944/preprints202509.0472.v1","name":"Traditional and Machine Learning Approaches to Partial Differential Equations: A Critical Review of Methods, Trade-Offs, and Integration","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202509.0472.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202509.0472.v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:22.907Z"},{"id":"doi:10.3762/bxiv.2025.49.v1","name":"Programmable Soliton Dynamics in All-Josephson-Junction Logic Cells and Networks","source":"preprints","abstract":"","url":"https://doi.org/10.3762/bxiv.2025.49.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3762/bxiv.2025.49.v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1101/2025.08.20.671220","name":"Tension shapes memory: Computational insights into neural plasticity","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.08.20.671220","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.08.20.671220","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.21203/rs.3.rs-6734290/v1","name":"Study of Vander Waals Heterostructure-Based Antiferromagnetic SpinValves for Next-Generation Memory Technology","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-6734290/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6734290/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-5658193/v1","name":"Time Delay Reservoir Computing in a Single Physical Node Enabled by Transient Photon Magnon Coupling ","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-5658193/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-5658193/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1101/2025.05.14.654027","name":"Neural sampling from cognitive maps enables goal-directed imagination and planning","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.05.14.654027","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.05.14.654027","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.20944/preprints202504.1531.v1","name":"Plücker Conoid-Inspired Geometry for Wave-Based Computing Systems","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202504.1531.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202504.1531.v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.22541/au.174945271.13828281/v1","name":"Post-Human Biotechnologies: Toward Recursive Intelligence and Bio-Digital Identity","source":"preprints","abstract":"","url":"https://doi.org/10.22541/au.174945271.13828281/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.22541/au.174945271.13828281/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-6927294/v1","name":"Strongly nonlinear nanocavity exciton-polaritons in gate-tunable monolayer semiconductors","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-6927294/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6927294/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-6420889/v1","name":"Coherent control of (non-)Hermitian mode coupling: tunable chirality and exceptional point dynamics in photonic microresonators","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-6420889/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6420889/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.20944/preprints202501.2133.v1","name":"Memristor Based Neuromorphic System for Unsupervised Online Learning and Network Anomaly Detection on Edge Devices","source":"europepmc","abstract":"","url":"https://doi.org/10.20944/preprints202501.2133.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202501.2133.v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.21203/rs.3.rs-6805889/v1","name":"High-Dimension Ionic Memory in Oscillating Ion Current Signals","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-6805889/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6805889/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1101/2025.05.25.656058","name":"Efficient learning and intrinsic noise filtering in recurrent spiking neural networks trained with e-prop","source":"preprints","abstract":"Objective Biologically plausible learning rules for neural networks, such as e-prop (eligibility propagation), are essential both for advancing neuromorphic computing and for understanding fundamental mechanisms of learning in animal brains. However, their behavior under different network conditions remains unclear. Approach Here, we investigate the performance of the e-prop learning algorithm in recurrent spiking neural networks (RSNNs) across different levels of recurrent connectivity and input noise using a complex temporal credit assignment task, a supervised classification problem known to be solvable by rodents. Main results We show that increased sparsity in the recurrent layer significantly enhances learning performance by promoting the generation of more diverse activation patterns. Analysis of the network’s evolution further reveals that the e-prop-trained input layer evolves to route distinct inputs to different regions of the recurrent layer while suppressing the contribution of noise. This partially resembles signal routing functions attributed to the thalamus in mammalian sensory systems, providing additional support for the biological plausibility of e-prop. Significance These findings offer promising insights for efficiency and advantages of biologically inspired training in RSNNs.","url":"https://doi.org/10.1101/2025.05.25.656058","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.05.25.656058","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.21203/rs.3.rs-5770022/v1","name":"NEOSTI: A Neuromorphic Electronic-Opto Spatial-Temporal Hybrid Image Sensor","source":"preprints","abstract":"Abstract Image sensors in machine vision systems face significant challenges related to energy efficiency and processing capability when storing, transferring, and processing massive amounts of data. In humans, over 80% of information processed by the brain is obtained through the eyes, which are capable of detecting and synchronously processing information with extremely low overall power consumption. Inspired by the biomimetics, here we propose a Neuromorphic Electronic-Opto Spatial Temporal Imager (NEOSTI), the smallest all-in-one eye size fully integrated vision system enabling acquisition and operation in typical indoor/outdoor non-coherent environments, under both natural and artificial lighting conditions, without any extra requirement of the light source, such as laser or coherent light source. NEOSTI combines processing-pre-sensor (PPS) in optical domain, processing-in-sensor (PIS) with non-linear acquisition capability while optical to electronic converting, and processing-near-sensor (PNS) in electronic domain, enabling parallel data computing capabilities while sensing. NEOSTI also integrates a low complexity Binary Neural Network (BNN) on the chip to process image semantic information. It attains near-human performance in five static and dynamic visual processing tasks.","url":"https://doi.org/10.21203/rs.3.rs-5770022/v1","authors":["Milin Zhang","Tianyi Liu","Zheng Huang","Xuecheng Wang","Wanxin Shi","Hongwei Chen"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-5770022/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.21203/rs.3.rs-6560504/v1","name":"Hardware-Adaptive and Superlinear-Capacity Memristor-based Associative Memory","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-6560504/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6560504/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-6798696/v1","name":"Dynamic Pass Bias Control for Temperature-Resilient Neural Networks Using Vertical NAND Flash Memory","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-6798696/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6798696/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-7357440/v1","name":"Memristance and transmemristance in multiterminal memristive systems","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-7357440/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7357440/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.21203/rs.3.rs-6140700/v1","name":"Laser-Guided Ion Dynamics in a Dual-Mode Memristor for Bioinspired Neuronal and Synaptic Integration","source":"preprints","abstract":"Abstract Neuromorphic computing aims to replicate the parallel, adaptive nature of biological intelligence in electronic systems. Despite considerable advances in memristor technology, material-encoded neurosynaptic bifunctionality has not been demonstrated. We introduce a laser-guided dual-mode memristor that integrates both volatility for neuronal spiking and nonvolatility for synaptic plasticity within a single-phase material. By precisely modulating silver ion dynamics through XeCl excimer laser irradiation, we achieve local and dynamic control of the dual-mode memristive behavior without requiring a heterogeneous device array or stacking. The neurosynaptic tunability with optimal computational efficiency demonstrates reconfigurable reservoir computing and a positive feedback loop for adaptive learning.","url":"https://doi.org/10.21203/rs.3.rs-6140700/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6140700/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-6504526/v1","name":"Energy-efficient artificial pyramidal neuron dendrites for visual information inference","source":"preprints","abstract":"Abstract In the human brain, a specialized type of pyramidal neuron dendrite exhibits nonlinear spike integration and sparse parallel processing capabilities. This unique structure enables efficient execution of visual tasks by activating only a small subset of neurons, playing a crucial role in high-level information inference. However, traditional neuromorphic devices are typically modeled as node-based signal integrators, requiring the activation of all neurons for perception. This approach struggles to effectively replicate the highly efficient spatiotemporal information processing of biological dendrites. In this study, we present an artificial pyramidal neuron dendrite (APND) array that integrates pyramidal neurons, synapses, and dendrites, emulating the spatiotemporal spike integration properties of biological pyramidal neurons for precise parallel computation. Through multi-gate threshold regulation, dendrites enable parallel sparse spiking inference with random spatial distribution. This inference process forms a sparse dendritic spiking neural network (SD-SNN) that can perform compression, recognition, and prediction. As a result, the SD-SNN achieves high-efficiency static and dynamic object processing while using only 0.5% of neurons. This reduces the number of ADCs by 99.5% and decreases power consumption by 98% and 65%, respectively. Our work reduces neural activity in the perception process by 99.5% while enhancing spatiotemporal computing capabilities and computational efficiency.","url":"https://doi.org/10.21203/rs.3.rs-6504526/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6504526/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.21203/rs.3.rs-5901611/v1","name":"Photonic embedding learning with high energy efficiency exceeding 100 GOPS/W/mm2","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-5901611/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-5901611/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.20944/preprints202501.1345.v1","name":"3D Print Electronics with AI","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202501.1345.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202501.1345.v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:22.907Z"},{"id":"doi:10.21203/rs.3.rs-5494383/v1","name":"An integrated microwave neural network for broadband computation and communication","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-5494383/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-5494383/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-5918267/v1","name":"Resonant laser excitation for nanoscale photocatalytic gold growth on patterned templates","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-5918267/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-5918267/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.64898/2025.12.11.693716","name":"Human cortical networks trade communication efficiency for computational reliability.","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2025.12.11.693716","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.64898/2025.12.11.693716","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:23.168Z"},{"id":"doi:10.1101/2025.05.15.654220","name":"Behavioral Time Scale Synaptic Plasticity (BTSP) endows binding of distributed representations with flexible retrieval options","source":"preprints","abstract":"Human reasoning depends on reusing pieces of information by binding them together in new ways, thereby “making infinite uses of finite means” (Alexander von Humboldt). Needed for that is a binding mechanism that enables fast composition and decomposition of tokens of information. Binding can easily be implemented in symbolic computations through parentheses and ordering of symbols. But it is a highly nontrivial operation for distributed representations, where the tokens are encoded by activity patterns in large neural networks or large language models, or more abstractly, by a high dimensional vector. Vector Symbolic Architectures (VSAs) provide partial solutions, but are lacking the flexibility of the brain in information retrieval, e.g. retrieving the tokens from a composed representation or retrieval of a composed representation by just providing some tokens as a cue. We show that a mechanism which the brain employs for binding distributed representations, Behavioral Time Scale Synaptic Plasticity (BTSP), overcomes these deficiencies. In particular, it combines binding with attractor features that make information retrieval substantially more flexible and robust. We evaluate its performance on various applications, including encoding and decoding complex visual scenes and hierarchical binding. We also show that it enhances models for natural language processing and abstract brain computation. BTSP-based binding only requires binary synaptic weights and simple local synaptic plasticity, and can therefore easily be implemented through in-memory computing or other innovative designs for energy-efficient AI implementations.","url":"https://doi.org/10.1101/2025.05.15.654220","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.05.15.654220","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.21203/rs.3.rs-5999509/v1","name":"Ultrafast Switching and High-Endurance Nonvolatile Memory Using Ferroelectric Janus Monolayers","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-5999509/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-5999509/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-6073810/v1","name":"Temporal Hierarchy in Spiking Neural Networks","source":"preprints","abstract":"Abstract Taking inspiration from the brain to perform efficient computation is a fascinating challenge, often hampered by the complexity of the brain itself. This work investigates a key feature observed across the cortices of various mammals: the hierarchy of time scales in cortical areas. Experimental evidence suggests that the intrinsic speed of activity in neuronal populations progressively slows down through the cortical hierarchy, forming what we define as a ``temporal hierarchy''. We explore whether this property provides an advantage in artificial computational systems. To test this hypothesis, we analyze SNNs, neural networks inspired by biological computation and with inherent temporal dynamics, and we endow them with temporal hierarchy. We incorporate the temporal hierarchy in various SNN temporal parameters, including their neuronal dynamics, synaptic delays, and recurrent dynamics. Our study evaluates these temporal hierarchies under two settings, (1) as an inductive bias, where SNNs temporal parameters are initialized with a predefined hierarchy to evaluate performance improvements, and (2) through optimizing the temporal parameters of SNNs. Benchmarking these networks on temporal tasks, the Multi-Timescale-XOR, and keyword spotting, we validate the benefits of hierarchy in various temporal mechanisms under both settings. In the inductive bias setting, we show that under iso-parameters settings, (i) classification accuracy correlates positively with the magnitude of temporal hierarchy on all the benchmarks, and (ii) there is an accuracy gain between 2 to 6% across tasks, when introducing temporal hierarchy, compared to a network without hierarchy. Moreover, under iso-accuracy settings, introducing hierarchy reduces the required number of parameters by up to 5 times. In the emergence from the optimization setting, we show that temporal hierarchy is naturally found as an emergent property through gradient descent. Finally, we conduct a detailed mathematical analysis of the temporal processing capabilities of SNNs, showing that a hierarchical arrangement of time constants enables a logarithmic reduction in the number of layers required to process temporal signals with multiple frequency components.","url":"https://doi.org/10.21203/rs.3.rs-6073810/v1","authors":["Filippo Moro","Pau Vilimelis Aceituno","Laura Kriener","Melika Payvand"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6073810/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.21203/rs.3.rs-7435743/v1","name":"Laser-induced nucleation of magnetic hopfions","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-7435743/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7435743/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.21203/rs.3.rs-6064663/v1","name":"Molecular control of Spin Hall and Unidirectional Magnetoresistance in YIG/PtMn","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-6064663/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6064663/v1","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:20.560Z"},{"id":"doi:10.1101/2025.07.22.666089","name":"Assembly-based computations through contextual dendritic gating of plasticity","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.07.22.666089","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.07.22.666089","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2025.03.17.642834","name":"Neurons have an inherent capability to learn order relations: A theoretical foundation that explains numerous experimental data","source":"preprints","abstract":"Brains are able to extract diverse relations between objects or concepts, and to integrate relational information into cognitive maps that form a basis for decision making. But is has remained a mystery how relational information is learnt and represented by neural networks of the brain. We show that a simple synaptic plasticity rule enables neurons to absorb and represent relational information, and to use it for abstract inference. This inherent capability of neurons and synaptic plasticity is supported by a rigorous mathematical theory. It explains experimental data from the human brain on the emergence of cognitive maps after learning several linear orders, it explains the terminal item effect that enhances transitive inference if a terminal item of an order is involved, and it provides a simple model for fast configuration of internal order representations in the face of new evidence. We also present a rigorous theoretical explanation for the surprising fact that 2D projections of neural representations of linear orders are curved, rather than linear. Since our model does not require stochastic gradient descent in deep neural networks for learning order relations, it is suited for porting the capability to learn multiple relations and using them for fast inference into edge devices with a low energy budget.","url":"https://doi.org/10.1101/2025.03.17.642834","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.03.17.642834","addedAt":"2026-09-01T01:48:19.715Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.4018/979-8-3693-6303-4.ch011","name":"Classification of Moderate and Advanced Dementia Patients Using Gradient Boosting Machine Technique","source":"crossref","abstract":"In the twenty-first century, caring for persons with Dementia's has become extremely difficult due to the prevalence of dementia cases. Using data from the OASIS (Open Access Series of Imaging Studies) program provided by the University of Washington Dementia's Disease Research Center, the study presents a new predictive model for Dementia's. Dementia, a chronic condition and it's become a serious health concern in adults. Various methods of data imputation, preprocessing, and transformation were used to prepare the data for model training. Machine learning algorithms, including AdaBoost (AB), Decision Tree (DT), Exclusion Tree (ET), Gradient Boost (GB), K-Nearest Neighbor (KNN), Logistic Regression (LR), Naive Bayes (NB;, Random Forest (RF), and Support Vector Machine (SVM), were used in this field. These algorithms were evaluated on both the complete feature set and a subset of features selected via the Least Absolute Shrinkage and Selection Operator (LASSO) method. Comparative analysis based on accuracy, precision, and other metrics showed that the proposed method achieved the highest accuracy of 96.77% using Support Vector Machine (SVM) with all feature sets, further refined and applied, has great potential for the diagnosis of early Dementia's disease (AD) disease.","url":"https://doi.org/10.4018/979-8-3693-6303-4.ch011","authors":["Swathi Gowroju","Shilpa Choudhary","Arpit Jain","R. Srilakshmi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-29T15:16:27Z","doi":"10.4018/979-8-3693-6303-4.ch011","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1109/mwscas53549.2025.11244475","name":"A CNFET-Based Full-Swing Reconfigurable Spiking Neuron for Ultra-Efficient Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mwscas53549.2025.11244475","authors":["Prasanna Kawatkar","Kasem Khalil","Magdy Bayoumi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-25T18:26:55Z","doi":"10.1109/mwscas53549.2025.11244475","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1088/2634-4386/ada8d4/v2/response1","name":"Author response for \"Maximizing information in neuron populations for neuromorphic spike encoding\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2634-4386/ada8d4/v2/response1","authors":["Ahmad El Ferdaoussi","Éric Plourde","Jean Rouat"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-11T16:33:42Z","doi":"10.1088/2634-4386/ada8d4/v2/response1","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.23919/piers-fall62445.2025.11394256","name":"Perturbation-Based Nonlinearity Analysis of Spin Waves in Application to Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.23919/piers-fall62445.2025.11394256","authors":["J. Chen","Y. Song","A. Hirose"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-26T20:42:16Z","doi":"10.23919/piers-fall62445.2025.11394256","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1016/j.neuron.2025.09.020","name":"Neuromorphic is dead. Long live neuromorphic.","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neuron.2025.09.020","authors":["Giacomo Indiveri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-04T00:49:53Z","doi":"10.1016/j.neuron.2025.09.020","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.7567/ssdm.2025.k-5-03","name":"Enhanced Intermediate Polarization: A Platform for Neuromorphic and Logic-in-Memory Computing","source":"crossref","abstract":"","url":"https://doi.org/10.7567/ssdm.2025.k-5-03","authors":["Heng XIANG","Yi Tong","Kah-Wee Ang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-16T05:08:46Z","doi":"10.7567/ssdm.2025.k-5-03","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1149/ma2025-01361728mtgabs","name":"Synaptic Capacitance Modulation in MOS Capacitors via Lateral Coupling Effect for Neuromorphic Computing","source":"crossref","abstract":"Recently, capacitive memory devices, such as MFM capacitors [1], FeFETs [2], and SONOS capacitors [3], have been explored for capacitive crossbar arrays in compute-in-memory (CIM) applications. Compared to memristors, capacitors reduce static energy costs and provide a wide memory window (C HCS /C LCS ) that can be read at 0 V. This work proposed a simple MOS capacitor (MOSCap) structure (Al/SiO₂/Si/Al) utilizing the lateral coupling effect to achieve a maximum C HCS /C LCS ≥ 36 at a read voltage of 0.5 V, with low program/erase voltages (-2.5 V/+1 V). Figure 1(a) depicts the schematic of the device, with the SiO₂ thickness measured as 4.3 nm. Figure 1(b) shows the C-V curves under four operating frequencies. Frequency dispersion was evident in both the depletion and inversion regions. In the depletion region, this dispersion is attributed to possible interface states at the SiO₂/Si interface. In the inversion region, capacitance variations across different frequencies were observed. It is notice that, the frequency at 1 kHz is still too high for minority carriers to effectively response in silicon. However, it is observed the inversion capacitance at 1 kHz existed low frequency behavior. Consequently, the measured capacitance might include contributions from the outer region of the device, this phenomenon was known as the lateral coupling effect [4]. As illustrated in Figure 2(a), positive oxide charges existed in the SiO₂ layer deplete majority carriers, forming an n-type inversion layer and a conductive channel. The gate voltage controls the coupling extent between the MOSCap and the outer region. Trapped charges at the device edge could effectively modulate the inversion capacitance (C inv ). Figures 2(b) and (c) illustrate the mechanism: electrons trapped in SiO₂ after a negative stress, reducing C inv by disconnecting the device from the outer region, while positive stress removes these electrons, restoring C inv . TCAD simulations (Figure 3) confirmed this, showing significant reductions in C inv and the supply of lateral electron current density (J e-,x ) outside the device as oxide charge density (N eff ) decreased below 2.6×10 11 cm −2 . Figure 1(c) demonstrates variations of C-V curves after different programming times (t PRG ) at V PRG = -2.5 V, while Figure 1(d) shows retention characteristics of C inv at 0 V. Continuous stress cycles also modulated C inv , as shown in Figures 4(a)-(d). Longer t PRG amplified the reduction of C inv , while a opposite erase voltage (V ERS = +1 V) applied for a shorter duration (t ERS = 0.1 s) restored it, as shown in Figure 4(d). Figures 5(a)–5(c) show the variation of C inv after single potentiation/depression (continuous erase/program stress) cycle read at different voltages (V read ), with a maximum C HCS /C LCS ratio was 36 happened as V read = 0.5 V after 20 continuous erase/program stress cycles. Figure 5(d) demonstrate multi-cycle potentiation and depression at V read = 0.5 V. Stress voltage modulation also impacts C inv , as shown in Figures 6(a) and 6(b). A series of positive (amplitudes: 0.1 V to 1.2 V in 0.1 V steps; width: 0.1 s) and negative (amplitudes: -1.5 V to -2.7 V in 0.1 V steps; width: 5 s) pulses resulted in more linear C inv changes (Figure 6(c)) compared to stress cycle modulation. Figure 6(d) displays multi-cycle potentiation and depression characteristics at V read = 0 V. In conclusion, the proposed MOSCap structure exhibited synaptic modulation behavior through the lateral coupling effect, offering an energy-efficient approach with lower operating voltages for possible neuromorphic computing applications. [1] N. Liu et al., IEEE Electron Device Letters, vol. 45, no. 7, pp. 1357-1360, 2024. [2] T. -H. Kim et al., IEEE Electron Device Letters, vol. 44, no. 10, pp. 1628-1631, 2023. [3] D. Kwon and I. -Y. Chung, IEEE Electron Device Letters, vol. 41, no. 3, pp. 493-496, 2020. [4] E. H. Nicollian and A. Goetzberger, IEEE Transactions on Electron Devices, vol. ","url":"https://doi.org/10.1149/ma2025-01361728mtgabs","authors":["Chi-Yi Kao","Jenn-Gwo Hwu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-21T07:38:57Z","doi":"10.1149/ma2025-01361728mtgabs","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.3390/nano15050348","name":"Electrolyte Gated Transistors for Brain Inspired Neuromorphic Computing and Perception Applications: A Review","source":"europepmc","abstract":"Emerging neuromorphic computing offers a promising and energy-efficient approach to developing advanced intelligent systems by mimicking the information processing modes of the human brain. Moreover, inspired by the high parallelism, fault tolerance, adaptability, and low power consumption of brain perceptual systems, replicating these efficient and intelligent systems at a hardware level will endow artificial intelligence (AI) and neuromorphic engineering with unparalleled appeal. Therefore, construction of neuromorphic devices that can simulate neural and synaptic behaviors are crucial for achieving intelligent perception and neuromorphic computing. As novel memristive devices, electrolyte-gated transistors (EGTs) stand out among numerous neuromorphic devices due to their unique interfacial ion coupling effects. Thus, the present review discusses the applications of the EGTs in neuromorphic electronics. First, operational modes of EGTs are discussed briefly. Second, the advancements of EGTs in mimicking biological synapses/neurons and neuromorphic computing functions are introduced. Next, applications of artificial perceptual systems utilizing EGTs are discussed. Finally, a brief outlook on future developments and challenges is presented.","url":"https://doi.org/10.3390/nano15050348","authors":["Weisheng Wang","Liqiang Zhu"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/nano15050348","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1109/icassp48485.2024.10446371","name":"Power-Aware Task-Based Learning of Neuromorphic ADCs","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icassp48485.2024.10446371","authors":["Tal Vol","Loai Danial","Nir Shlezinger"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-18T18:56:31Z","doi":"10.1109/icassp48485.2024.10446371","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1109/idap64064.2024.10711094","name":"Memristive Synapses as Building Blocks of Neuromorphic Artificial Intelligence (AI) Hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1109/idap64064.2024.10711094","authors":["Fatih Gül"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-16T13:50:55Z","doi":"10.1109/idap64064.2024.10711094","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1038/s43246-024-00632-y","name":"Defect-engineered monolayer MoS2 with enhanced memristive and synaptic functionality for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s43246-024-00632-y","authors":["Manisha Rajput","Sameer Kumar Mallik","Sagnik Chatterjee","Ashutosh Shukla","Sooyeon Hwang","Satyaprakash Sahoo","G. V. Pavan Kumar","Atikur Rahman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-16T11:02:32Z","doi":"10.1038/s43246-024-00632-y","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1109/icons62911.2024.00021","name":"Continuous Learning for Real-Time Auditory Blind Source Separation Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024.00021","authors":["Erika Schmitt","Sanchit Gupta","Patrick Abbs"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T18:37:03Z","doi":"10.1109/icons62911.2024.00021","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1007/978-3-031-73800-5_8","name":"Conclusion","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-73800-5_8","authors":["Ziad El-Khatib","Sherif Moussa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-15T07:23:05Z","doi":"10.1007/978-3-031-73800-5_8","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.21203/rs.3.rs-4102090/v1","name":"Self-organizing neuromorphic nanowire networks are stochastic dynamical systems","source":"preprints","abstract":"Abstract Neuromorphic computing aims to develop software and hardware platforms emulating the information processing effectiveness of our brain. In this context, self-organizing neuromorphic nanonetworks have been demonstrated as suitable physical substrates for in materia implementation of unconventional computing paradigms, like reservoir computing. However, understanding the relationship between emergent dynamics and information processing capabilities still represents a challenge. Here, we demonstrate that nanowire-based neuromorphic networks are stochastic dynamical systems where the signals flow relies on the intertwined action of deterministic and random factors. We show through an experimental and modeling approach that these systems combine stimuli-dependent deterministic trajectories and random effects caused by noise and jumps that can be holistically described by an Ornstein-Uhlenbeck process, providing a unifying framework surpassing current modeling approaches of self-organizing neuromorphic nanonetworks (not only nanowire-based) that are limited to either deterministic or stochastic effects. Since information processing capabilities can be dynamically tuned by controlling the network’s attractor memory state, these results open new perspectives for the rational development of physical computing paradigms exploiting deterministic and stochastic dynamics in a single hardware platform similarly to our brain.","url":"https://doi.org/10.21203/rs.3.rs-4102090/v1","authors":["Gianluca Milano","Fabio Michieletti","Carlo Ricciardi","Enrique Miranda"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4102090/v1","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.20944/preprints202407.0130.v1","name":"A Survey on Neuromorphic Architectures for Running Artificial Intelligence Algorithms","source":"preprints","abstract":"Neuromorphic computing, a brain inspired non-Von Neumann computing system, addresses the challenges posed by the Moore’s law memory wall phenomenon. It has the capability to increasingly enhance performance while maintaining power efficiency. Neuromorphic chip architecture requirements vary depending on the application and optimizing it for large-scale applications remains to be a challenge. Neuromorphic chips are programmed using spiking neural networks which provide them with important properties such as parallelism, asynchronism, and on-device learning. Widely used spiking neuron models include the Hodgkin-Huxley Model, Izhikevich model, integrate-and-fire model and spike response model. Hardware implementation platforms of the chip follow three approaches: analog, digital, or a combination of both. Each platform can be implemented using various memory topologies which interconnects with the learning mechanism. Current neuromorphic computing systems typically use the unsupervised learning spike timing-dependent plasticity algorithms. However, algorithms such as voltage-dependent synaptic plasticity have the potential to enhance performance. This review summarizes the potential neuromorphic chip architecture specifications and highlights which applications they are suitable for.","url":"https://doi.org/10.20944/preprints202407.0130.v1","authors":["Seham Al Abdul Wahid","Arghavan Asad","Farah Mohammadi"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.20944/preprints202407.0130.v1","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:22.907Z"},{"id":"doi:10.1088/1361-6463/ae2edd","name":"Enhancing non-volatile memory and neuromorphic computing: integration of PRAM and OTS for scalable, energy-efficient architectures","source":"crossref","abstract":"Abstract This paper investigates the integration of phase-change random access memory (PRAM) and ovonic threshold switch (OTS) devices, emphasizing their ability to advance non-volatile memory technologies, neuromorphic computing architectures, and energy-efficient systems. OTS devices’ nonlinear threshold switching effectively mitigates sneak currents in high-density crossbar arrays, while challenges like resistivity drift and structural relaxation are addressed through advanced modeling and experimental analysis. The study highlights innovations in phase-change materials, such as doped Sb 2 Te 3 alloys and Sb 2 Te 3 –GeTe superlattices deposited by magnetron sputtering, which have been reported to improve thermal stability, reduce RESET power, and enhance cycling endurance compared with conventional GST-based phase-change memory devices. PRAM-OTS hybrid systems demonstrate exceptional performance in spiking and multi-layer neural networks, replicating neuronal behaviors such as integrate-and-fire dynamics and spike-timing-dependent plasticity for low-latency, energy-efficient processing in artificial intelligence, robotics, and internet of things applications. These scalable and reliable systems provide a robust framework for next-generation high-performance computational platforms, addressing key challenges in scalability, energy efficiency, and operational longevity.","url":"https://doi.org/10.1088/1361-6463/ae2edd","authors":["Seoyoung Park","Minsuk Koo","Sungjun Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-18T22:47:49Z","doi":"10.1088/1361-6463/ae2edd","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1007/978-3-031-73800-5_1","name":"Introduction","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-73800-5_1","authors":["Ziad El-Khatib","Sherif Moussa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-15T07:22:56Z","doi":"10.1007/978-3-031-73800-5_1","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1021/acs.jpclett.4c03033","name":"Materials, Physics, and Chemistry of Neuromorphic Computing Systems","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.jpclett.4c03033","authors":["Juan Bisquert"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acs.jpclett.4c03033","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.3390/biomimetics9090547","name":"Low-Cost, High-Efficiency Aluminum Zinc Oxide Synaptic Transistors: Blue LED Stimulation for Enhanced Neuromorphic Computing Applications","source":"crossref","abstract":"Neuromorphic devices are electronic devices that mimic the information processing methods of neurons and synapses, enabling them to perform multiple tasks simultaneously with low power consumption and exhibit learning ability. However, their large-scale production and efficient operation remain a challenge. Herein, we fabricated an aluminum-doped zinc oxide (AZO) synaptic transistor via solution-based spin-coating. The transistor is characterized by low production costs and high performance. It demonstrates high responsiveness under UV laser illumination. In addition, it exhibits effective synaptic behaviors under blue LED illumination, indicating high-efficiency operation. The paired-pulse facilitation (PPF) index measured from optical stimulus modulation was 179.6%, indicating strong synaptic connectivity and effective neural communication and processing. Furthermore, by modulating the blue LED light pulse frequency, an excitatory postsynaptic current gain of 4.3 was achieved, demonstrating efficient neuromorphic functionality. This study shows that AZO synaptic transistors are promising candidates for artificial synaptic devices.","url":"https://doi.org/10.3390/biomimetics9090547","authors":["Namgyu Lee","Pavan Pujar","Seongin Hong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-11T02:34:49Z","doi":"10.3390/biomimetics9090547","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1039/d3ma00618b","name":"Resistive switching in benzylammonium-based Ruddlesden–Popper layered hybrid perovskites for non-volatile memory and neuromorphic computing","source":"crossref","abstract":"Resistive switching with synaptic behaviour in layered benzylammonium-based Ruddlesden–Popper perovskites is demonstrated, with a transformation from digital to analog upon change of the halide anion, of potential interest to neuromorphic computing.","url":"https://doi.org/10.1039/d3ma00618b","authors":["Mubashir M. Ganaie","Gianluca Bravetti","Satyajit Sahu","Mahesh Kumar","Jovana V. Milić"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-03T17:05:46Z","doi":"10.1039/d3ma00618b","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1117/3.100022","name":"Neuromorphic Photonic Devices and Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1117/3.100022","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-02T16:14:21Z","doi":"10.1117/3.100022","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1088/1674-4926/24100020","name":"Synaptic devices based on silicon carbide for neuromorphic computing","source":"crossref","abstract":"Abstract To address the increasing demand for massive data storage and processing, brain-inspired neuromorphic computing systems based on artificial synaptic devices have been actively developed in recent years. Among the various materials investigated for the fabrication of synaptic devices, silicon carbide (SiC) has emerged as a preferred choices due to its high electron mobility, superior thermal conductivity, and excellent thermal stability, which exhibits promising potential for neuromorphic applications in harsh environments. In this review, the recent progress in SiC-based synaptic devices is summarized. Firstly, an in-depth discussion is conducted regarding the categories, working mechanisms, and structural designs of these devices. Subsequently, several application scenarios for SiC-based synaptic devices are presented. Finally, a few perspectives and directions for their future development are outlined.","url":"https://doi.org/10.1088/1674-4926/24100020","authors":["Boyu Ye","Xiao Liu","Chao Wu","Wensheng Yan","Xiaodong Pi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-25T13:25:49Z","doi":"10.1088/1674-4926/24100020","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.2139/ssrn.4876795","name":"Natural Biomaterials for Sustainable Flexible Neuromorphic Devices","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4876795","authors":["Yanfei Zhao","Seungbeom Lee","Tingyu Long","Hea-Lim Park","Tae-Woo Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-27T03:09:41Z","doi":"10.2139/ssrn.4876795","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.36227/techrxiv.171332392.20036272/v1","name":"Implementation of linear differential equations using pulse-coupled oscillators with an ultra-low power neuromorphic realization","source":"crossref","abstract":"","url":"https://doi.org/10.36227/techrxiv.171332392.20036272/v1","authors":["Jafar Shamsi","Wilten Nicola"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-16T23:18:53Z","doi":"10.36227/techrxiv.171332392.20036272/v1","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.63382/jni.v1i1.8","name":"Machine Learning for Soft Robotics","source":"crossref","abstract":"Soft Robotics refers to the design, fabrication, and control of robots made from highly deformable materials that mimic biological organisms. They can perform tasks that require flexibility and soft dexterity. With the application of Machine Learning (ML)， soft robots are now able to learn from data, redesign their shape, and handle various tasks with high precision. This literature review explores the integration of ML techniques in soft robotics, examining various data-driven strategies, applications, knowledge gaps, and future directions. Soft robots often require complex, nonlinear dynamics, and autonomous decision-making capability without explicit programming in order to fit in unpredictable environments.Therefore, despite the significant advances in this field, there are still a few technical challenges topical to various implementations of soft robots. In this literature review, five representative ML methods and their diverse applications for soft robots are analyzed. Lastly, the emerging bio-inspired energy-efficient neuromorphic learning is introduced, which uses far less power than traditional computing technologies and allows for a rapid adaption of soft robots to complex environmental changes. Therefore, neuromorphic learning is regarded as a promising tool for efficient event-driven sensing and adaptive locomotion control in the field of soft robotics.","url":"https://doi.org/10.63382/jni.v1i1.8","authors":["Baiyu Zhang","Jingjing Qiu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-21T18:53:11Z","doi":"10.63382/jni.v1i1.8","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1002/adfm.202307729","name":"Brain‐Inspired Organic Electronics: Merging Neuromorphic Computing and Bioelectronics Using Conductive Polymers","source":"crossref","abstract":"Abstract Neuromorphic computing offers the opportunity to curtail the huge energy demands of modern artificial intelligence (AI) applications by implementing computations into new, brain‐inspired computing architectures. However, the lack of fabrication processes able to integrate several computing units into monolithic systems and the need for new, hardware‐tailored training algorithms still limit the scope of application and performance of neuromorphic hardware. Recent advancements in the field of organic transistors present new opportunities for neuromorphic systems and smart sensing applications, thanks to their unique properties such as neuromorphic behavior, low‐voltage operation, and mixed ionic‐electronic conductivity. Organic neuromorphic transistors push the boundaries of energy efficient brain‐inspired hardware AI, facilitating decentralized on‐chip learning and serving as a foundation for the advancement of closed‐loop intelligent systems in the next generation. The biocompatibility and dual ionic‐electronic conductivity of organic materials introduce new prospects for biointegration and bioelectronics. Their ability to sense and regulate biosystems, as well as their neuro‐inspired functions can be combined with neuromorphic computing to create the next‐generation of bioelectronics. These systems will be able to seamlessly interact with biological systems and locally compute biosignals in a relevant matter.","url":"https://doi.org/10.1002/adfm.202307729","authors":["Imke Krauhausen","Charles‐Théophile Coen","Simone Spolaor","Paschalis Gkoupidenis","Yoeri van de Burgt"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-23T00:12:11Z","doi":"10.1002/adfm.202307729","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1109/iccsai64074.2025.11064198","name":"The Impact of Neuromorphic Computing on Brain-Inspired Robotics: A Novel Architectural Paradigm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccsai64074.2025.11064198","authors":["Sumanshu Jindal","Gitanjali Gupta","Rajani Misra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-14T17:40:02Z","doi":"10.1109/iccsai64074.2025.11064198","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.22214/ijraset.2025.66411","name":"Advancements and Challenges in Neuromorphic Computing: Bridging Neuroscience and Artificial Intelligence","source":"crossref","abstract":"Neuromorphic computing represents a paradigm shift in computational design, aiming to emulate the neural structures and functionalities of the human brain. This approach seeks to enhance efficiency and adaptability in artificial intelligence (AI) systems. This paper provides a comprehensive review of recent advancements in neuromorphic hardware and software, highlighting their potential to revolutionize AI by enabling real-time processing and energy-efficient computations. Additionally, it examines the challenges inherent in replicating complex neural processes, including issues related to scalability, material limitations, and the integration of neuromorphic systems with existing technologies. By bridging the disciplines of neuroscience and AI, neuromorphic computing offers promising avenues for the development of intelligent systems that closely mirror human cognitive functions.","url":"https://doi.org/10.22214/ijraset.2025.66411","authors":["Melad Mohamed Salim Elfighi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-10T07:56:02Z","doi":"10.22214/ijraset.2025.66411","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1101/2024.07.19.604308","name":"A Burst-Dependent Algorithm for Neuromorphic On-Chip Learning of Spiking Neural Networks","source":"preprints","abstract":"Abstract The field of neuromorphic engineering addresses the high energy demands of neural networks through brain-inspired hardware for efficient neural network computing. For on-chip learning with spiking neural networks, neuromorphic hardware requires a local learning algorithm able to solve complex tasks. Approaches based on burst-dependent plasticity have been proposed to address this requirement, but their ability to learn complex tasks has remained unproven. Specifically, previous burst-dependent learning was demonstrated on a spiking version of the XOR problem using a network of thousands of neurons. Here, we extend burst-dependent learning, termed ‘Burstprop’, to address more complex tasks with hundreds of neurons. We evaluate Burstprop on a rate-encoded spiking version of the MNIST dataset, achieving low test classification errors, comparable to those obtained using backpropagation through time on the same architecture. Going further, we develop another burst-dependent algorithm based on the communication of two types of error-encoding events for the communication of positive and negative errors. We find that this new algorithm performs better on the image classification benchmark. We also tested our algorithms under various types of feedback connectivity, establishing that the capabilities of fixed random feedback connectivity is preserved in spiking neural networks. Lastly, we tested the robustness of the algorithm to weight discretization. Together, these results suggest that spiking Burstprop can scale to more complex learning tasks and can thus be considered for self-supervised algorithms while maintaining efficiency, potentially providing a viable method for learning with neuromorphic hardware.","url":"https://doi.org/10.1101/2024.07.19.604308","authors":["Michael Stuck","Xingyun Wang","Richard Naud"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.07.19.604308","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/mwscas60917.2024.10658937","name":"Compact Convolutional SNN Architecture for the Neuromorphic Speech Denoising","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mwscas60917.2024.10658937","authors":["Anuar Dorzhigulov","Vishal Saxena"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-16T17:34:29Z","doi":"10.1109/mwscas60917.2024.10658937","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1364/ofc.2024.m4c.4","name":"Integrated Neuromorphic Information Processing with Electrically-injected Microring Spiking Neuron","source":"crossref","abstract":"We experimentally demonstrate, for the first time, a CMOS-compatible electrically injected microring spiking neuron, capable of reproducibly emulating the typical neural dynamics including excitability threshold, temporal integration, refractory period, and spike inhibition.","url":"https://doi.org/10.1364/ofc.2024.m4c.4","authors":["Jinlong Xiang","Yaotian Zhao","Xuhan Guo","Yikai Su"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-14T11:28:28Z","doi":"10.1364/ofc.2024.m4c.4","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1002/est2.70272","name":"A Comprehensive Review of Phase Change Memory for Neuromorphic Computing: Advancements, Challenges, and Future Directions","source":"crossref","abstract":"ABSTRACT The human brain functions as a highly efficient control center, inspiring the field of neuromorphic computing, which seeks to replicate its structure and behavior through hardware systems. Neuromorphic computing integrates processing and memory functions using artificial neurons and synapses designed with electronic circuits, enabling parallel, energy‐efficient data handling. One of the leading technologies supporting this paradigm is phase change memory (PCM), a non‐volatile memory that stores data through reversible transitions between amorphous (high resistance) and crystalline (low resistance) states of chalcogenide materials, particularly Ge 2 Sb 2 Te 5 (GST225). PCM exhibits fast read/write speeds, excellent data retention, and scalability, making it ideal for neuromorphic architectures. This review highlights recent advancements in PCM for neuromorphic computing, including innovations in doping strategies and device engineering. Notable developments include arsenic‐doped ovonic threshold switches (OTS) for enhanced selector performance, monolayer Sb 2 Te 3 for atomic‐scale devices, and heater‐all‐around (HAA) 3D architectures for reduced energy consumption. Integration with machine learning tools enables precise atomistic modeling, accelerating material and device optimization. Furthermore, emerging variants like ovonic unified memory (OUM) and interfacial PCM (IPCM) offer unique performance advantages. While PCM promises significant benefits, key challenges such as resistance drift, endurance limits, and thermal crosstalk must be addressed. The global neuromorphic computing market is poised for exponential growth, driven by innovations in materials, algorithms, and architectures. The PCM and neuromorphic computing represent a transformative leap toward intelligent, adaptive, and energy‐efficient computing systems.","url":"https://doi.org/10.1002/est2.70272","authors":["Vikas Bhatnagar","Adesh Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-24T02:59:59Z","doi":"10.1002/est2.70272","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1088/2634-4386/ada989","name":"Neuromorphic compliant control facilitates human-prosthetic performance for hand grasp functions","source":"crossref","abstract":"Abstract Current bionic hands lack the ability of fine force manipulation for grasping fragile objects due to missing human neuromuscular compliance in control. This incompatibility between prosthetic devices and the sensorimotor system has resulted in a high abandonment rate of hand prostheses. To tackle this challenge, we employed a neuromorphic modeling approach, biorealistic control, to regain human-like grasping ability. The biorealistic control restored muscle force regulation and stiffness adaptation using neuromorphic modeling of the neuromuscular reflex units, which was capable of real-time computing of model outputs. We evaluated the dexterity of the biorealistic control with a set of delicate grasp tasks that simulated varying challenging scenarios of grasping fragile objects in daily activities of life, including the Box and Block Task, the Glass Box Task, and the Potato Chip Task. The performance of the biorealistic control was compared with that of proportional control.&amp;#xD;Results indicated that the biorealistic control with the compliance of the neuromuscular reflex units significantly outperformed the proportional control with more efficient grip forces, higher success rates, fewer break and drop rates. Post-task survey questionnaires revealed that the biorealistic control reduced subjective burdens of task difficulty and improved subjective confidence in control performance significantly. The outcome of the evaluation confirmed that the biorealistic control could achieve superior abilities in fine, accurate, and efficient grasp control for prosthetic users.&amp;#xD;","url":"https://doi.org/10.1088/2634-4386/ada989","authors":["Anran Xie","Zhuozhi Zhang","Jie Zhang","Weidong Chen","James L Patton","Ning Lan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-13T22:54:27Z","doi":"10.1088/2634-4386/ada989","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1145/3649476.3660379","name":"Review of Neuromorphic Processing for Vision Sensors","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3649476.3660379","authors":["Mst Shamim Ara Shawkat","Shante Hicks","Nahin Irfan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-10T12:29:41Z","doi":"10.1145/3649476.3660379","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.46620/ursiatrasc24/mklp3444","name":"Photonic Neuromorphic Data Processing","source":"crossref","abstract":"","url":"https://doi.org/10.46620/ursiatrasc24/mklp3444","authors":["Frank Brückerhoff-Plückelmann","Jelle Dijkstra","Ivonne Bente","Daniel Wendland","Wolfram Pernice"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-01T10:00:16Z","doi":"10.46620/ursiatrasc24/mklp3444","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1109/icons62911.2024.00032","name":"Per Layer Specialization for Memory-Efficient Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024.00032","authors":["Muath Abu Lebdeh","Kasim Sinan Yildirim","Davide Brunelli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T18:37:03Z","doi":"10.1109/icons62911.2024.00032","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.29003/m4290.mmmsec-2024/168-169","name":"FEATURES OF NEURO- AND NEUROMORPHIC PROCESSOR ARCHITECTURES","source":"crossref","abstract":"The paper considers hardware architectures for the implementation of formal and spike neural networks.","url":"https://doi.org/10.29003/m4290.mmmsec-2024/168-169","authors":["Oleg Telminov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-23T18:07:46Z","doi":"10.29003/m4290.mmmsec-2024/168-169","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1109/ogc62429.2024.10738780","name":"Harnessing Noise for Materials Differentiation in Computational Neuromorphic Imaging","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ogc62429.2024.10738780","authors":["Shuo Zhu","Chutian Wang","Pei Zhang","Edmund Y. Lam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-06T13:37:06Z","doi":"10.1109/ogc62429.2024.10738780","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1016/j.jallcom.2024.175830","name":"TiN/TiOx/WOx/Pt heterojunction memristor for sensory and neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.jallcom.2024.175830","authors":["Dongyeol Ju","Jungwoo Lee","Hyojin So","Sungjun Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-05T15:19:41Z","doi":"10.1016/j.jallcom.2024.175830","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1007/978-3-031-57873-1","name":"Neuromorphic Intelligence","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-57873-1","authors":["Shuangming Yang","Badong Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-14T09:01:50Z","doi":"10.1007/978-3-031-57873-1","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.1364/cosi.2024.cm2b.3","name":"Spectrum synthesis with computational neuromorphic imaging","source":"crossref","abstract":"We propose a method for spectrum synthesis via computational neuromorphic imaging (CNI), employing stochastic variational inference to extract spectral profiles from dynamic light-sample interactions. It provides new insights into biological analysis and CNI applications.","url":"https://doi.org/10.1364/cosi.2024.cm2b.3","authors":["Rongzhou Chen","Shuo Zhu","Chutian Wang","Edmund Y. Lam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T15:51:02Z","doi":"10.1364/cosi.2024.cm2b.3","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.58346/jowua.2026.i2.006","name":"Neuromorphic Computing-Enabled Context-Aware Adaptive Mobile Learning Framework for Real-Time Cognitive Load Management","source":"crossref","abstract":"The growing use of mobile learning in wireless and ubiquitous computing environments has posed various difficulties in managing the cognitive load of learners in a dynamic environment. Traditional adaptive learning approaches may not be equipped with the capacity to monitor continuously the learner's cognitive state and adapt intelligently to the environmental and behavioral changes. This problem could lead to a lower level of engagement of learners, increased cognitive load, and inefficiency in the learning process. In order to solve such problems, this research paper presents the Neuromorphic Computing-Enabled Context-Aware Adaptive Mobile Learning Framework for Real-Time Cognitive Load Management. This approach consistently monitors contextual factors such as the user's engagement pattern, environmental conditions, and device-level operations to predict the cognitive load and deliver the instruction accordingly. Neuromorphic intelligence was applied for cognitive processes that will be done with low delay and energy consumption in the wireless mobile context. The new learning model was tested with the help of various metrics, namely adaptation accuracy, precision, recall, F1-score, energy efficiency, and response latency. The experimental outcome revealed that the new framework obtained an adaptation accuracy rate of 96.8%, precision of 96.1%, recall of 95.7%, and F1-score of 95.9%, which is superior to traditional mobile learning and deep adaptive learning models. Furthermore, the proposed framework offered a reduction in response delay to 104 ms and an energy efficiency rate of 0.95. Results indicate that the integration of neuromorphic computing technology with context-aware adaptive learning systems can greatly improve learner personalization, cognitive load management, and system reactivity. The suggested framework is expected to contribute towards the design of an intelligent, scalable, and energy-efficient adaptive learning environment for future wireless-based learning platforms.","url":"https://doi.org/10.58346/jowua.2026.i2.006","authors":["Gulbahor Sidikova","Nurbol Karakulov","Mustafo Tursunov","Atabek Kochkarov","Asqad Oltiboyev","Yana Arustamyan","Dilfuza Toirova","Abdumajid Madraimov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-06T06:17:03Z","doi":"10.58346/jowua.2026.i2.006","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:19.717Z"},{"id":"doi:10.29363/nanoge.neumatdecas.2023.006","name":"Solving Combinatorial Optimization Problems with Nanoelectronic Neuromorphic Circuits","source":"crossref","abstract":"","url":"https://doi.org/10.29363/nanoge.neumatdecas.2023.006","authors":["Dmitri Strukov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-02-01T09:31:42Z","doi":"10.29363/nanoge.neumatdecas.2023.006","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.5772/intechopen.79292","name":"Memristive Anodic Oxides: Production, Properties and Applications in Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.5772/intechopen.79292","authors":["Andrea Brenna","Fernando Corinto","Seyedreza Noori","Marco Ormellese","MariaPia Pedeferri","Maria Vittoria Diamanti"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-10-04T13:50:01Z","doi":"10.5772/intechopen.79292","addedAt":"2026-09-01T01:48:19.717Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1002/9781394466481.ch4","name":"AI and Neuromorphic Computing for Autonomous Deep Space Operations","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9781394466481.ch4","authors":["P. Ashok","S. Lakshmi Sridevi","K. Murali Krishna","Venkatesh Ramamurthy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-12T15:14:31Z","doi":"10.1002/9781394466481.ch4","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1088/2634-4386/ae294e","name":"Van der Waals integration of 2D materials for advanced intelligent computing","source":"crossref","abstract":"Abstract The increasing demand for faster, energy-efficient, and higher bandwidth semiconductor devices has pushed conventional Si-based scaling to its fundamental limits, including mobility degradation, short-channel effects, and high power consumption. To overcome these challenges, three-dimensional integration has emerged as a promising strategy, but wafer-based approaches like through-Si-via face critical limitations in stacking density, mechanical stress, and fabrication complexity. Two-dimensional materials provide a compelling alternative due to their atomically thin structure, superior electrical and mechanical properties, and ability to sustain performance at the atomic scale. Moreover, their van der Waals integration enables heterogeneous, high-density, and efficient assembly of functional layers. This review summarizes recent advances in the preparation and van der Waals integration of 2D materials, including growth, transfer, and direct integration. Their applications in intelligent computing that range from logic to sensor devices and their potential as next-generation electronics are discussed.","url":"https://doi.org/10.1088/2634-4386/ae294e","authors":["Chaehyeon Kwak","Keunpyo Park","Min-Kyu Song","Ho Won Jang","Jun Min Suh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-08T22:51:42Z","doi":"10.1088/2634-4386/ae294e","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.7567/ssdm.2024.j-5-01","name":"2D lead-tin halides for energy-efficient neuromorphic electronic devices","source":"crossref","abstract":"","url":"https://doi.org/10.7567/ssdm.2024.j-5-01","authors":["Maria Loi Antonietta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-16T00:21:36Z","doi":"10.7567/ssdm.2024.j-5-01","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:19.718Z"},{"id":"doi:10.1109/icons62911.2024.00009","name":"Edge Device CNN Classification Using Eventized RF Fingerprints","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024.00009","authors":["Michael J. Smith","Michael A. Temple","James W. Dean"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T18:37:03Z","doi":"10.1109/icons62911.2024.00009","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:19.718Z"},{"id":"doi:10.1515/9783111545950-011","name":"19411 How an NEGF simulator can be constructed?","source":"crossref","abstract":"","url":"https://doi.org/10.1515/9783111545950-011","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-06T19:15:47Z","doi":"10.1515/9783111545950-011","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1109/iceee.2015.7357928","name":"The transition between tonic spiking and bursting in a six-transistor neuromorphic device","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iceee.2015.7357928","authors":["Fernando Castanos","Alessio Franci"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-17T22:00:07Z","doi":"10.1109/iceee.2015.7357928","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/isqed.2018.8357307","name":"A path to energy-efficient spiking delayed feedback reservoir computing system for brain-inspired neuromorphic processors","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isqed.2018.8357307","authors":["Kangjun Bai","Yang Yi Bradley"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-05-18T17:30:27Z","doi":"10.1109/isqed.2018.8357307","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.2139/ssrn.4920906","name":"Defect Driven Analog to Digital Resistive Switching Transition of Nio Memristor Device for Neuromorphic Applications","source":"crossref","abstract":"Devices with controllable conversion of analog to digital resistive switching are essential to realize synaptic functions in neuromorphic computing. This work reports the influence of Cu ions on the transition from analog to digital resistive switching in Indium–Tin-Oxide(ITO)/NiO/Ag memristor devices. The undoped and low-concentration Cu doping illustrates the analog switching, whereas higher doping demonstrates the digital characteristics. At higher bias voltage, the Schottky barrier (ΦB) is developed at both ITO/NiO and NiO/Ag interfaces. The increasing and decreasing of current conduction with the escalating number of cycles for both the polarity in undoped and low doped is elucidated by the electrode-dominated mechanism in terms of reduction and enhancement of Schottky barrier height at the interface, respectively. The digital switching characteristic due to the formation and rupturing of the vacancy filament in sample C is induced due to the boosting of vacancies externally above the critical amount using ion implantation. The synergic effect of current conduction due to local Cu migration and oxygen vacancies can be utilized as a learning and forgetting process for neuromorphic applications.","url":"https://doi.org/10.2139/ssrn.4920906","authors":["Sourav Bhakta","Pratap  Kumar Sahoo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-09T11:19:06Z","doi":"10.2139/ssrn.4920906","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:19.718Z"},{"id":"doi:10.1109/igsc54211.2021.9651607","name":"Real-Time Evolution and Deployment of Neuromorphic Computing at The Edge","source":"crossref","abstract":"","url":"https://doi.org/10.1109/igsc54211.2021.9651607","authors":["Catherine D. Schuman","Steven R. Young","Bryan P. Maldonado","Brian C. Kaul"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-28T21:31:04Z","doi":"10.1109/igsc54211.2021.9651607","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/igsc51522.2020.9291114","name":"Memristive Device Variability Performance Impact on Neuromorphic Machine Learning Hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1109/igsc51522.2020.9291114","authors":["Andrew J. Ford","Rashmi Jha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-04-13T21:42:20Z","doi":"10.1109/igsc51522.2020.9291114","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1126/sciadv.adv6603","name":"Neuromorphic ionic computing in droplet interface synapses","source":"europepmc","abstract":"Ionic devices with memory capabilities can emulate neural functionality, enabling neuromorphic computing and biomedical applications. In this study, we report an ionic spiking synapse based on aqueous droplet interface bilayer assembly. Under stepwise triangular voltages, the device displays coupled memcapacitive-memristive behavior, showing noncrossing pinched hysteretic I - V loops. This hysteretic ion dynamics can be regulated by modifying bilayer components, reconstituting protein channels, or adjusting droplet assembly configuration. Droplet interface synapses (DIS) exhibit fundamental neuromorphic behaviors such as paired-pulse facilitation/depression, spike rate–dependent plasticity, Hebbian learning, and short-term associative learning under classical conditioning. We also used reservoir computing with DIS to implement two learning algorithms: a classification algorithm that recognizes handwritten digits and a reinforcement learning algorithm that learns to play a board game of tic-tac-toe.","url":"https://doi.org/10.1126/sciadv.adv6603","authors":["Zhongwu Li","Sydney K. Myers","Jingyi Xiao","Yuhao Li","Natasha Noy","Anton Leuski","Aleksandr Noy"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1126/sciadv.adv6603","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1017/cbo9780511994838.009","name":"Autonomous visuomotor development for neuromorphic robots","source":"crossref","abstract":"","url":"https://doi.org/10.1017/cbo9780511994838.009","authors":["Zhengping Ji","Juyang Weng","Danil Prokhorov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-02-06T06:03:07Z","doi":"10.1017/cbo9780511994838.009","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/iccad66269.2025.11240848","name":"Invited Paper: Analyzing the Robustness of Neuromorphic Computing in the Presence of Variability in Non-Volatile Memory","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccad66269.2025.11240848","authors":["Andreia Podasca","Anup Das"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-20T18:39:34Z","doi":"10.1109/iccad66269.2025.11240848","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/lpt.2025.3631106","name":"Energy-Efficient Europium-Based 2D Perovskite ReRAM for Photo-Tunable Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/lpt.2025.3631106","authors":["Manvendra Chauhan","Satinder K. Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-10T18:50:15Z","doi":"10.1109/lpt.2025.3631106","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1109/iscas.2016.7527508","name":"Neuromorphic computing with hybrid memristive/CMOS synapses for real-time learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas.2016.7527508","authors":["D. Ielmini","S. Ambrogio","V. Milo","S. Balatti","Z.-Q. Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-11-01T20:59:26Z","doi":"10.1109/iscas.2016.7527508","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1002/aelm.202500515","name":"Simultaneous Dual‐Plasticity Organic Synaptic Transistor for Neuromorphic Computing","source":"crossref","abstract":"ABSTRACT Neuromorphic computing systems require artificial synaptic devices capable of emulating complex biological neural functions. This study presents a dinaphtho[2,3‐b:2′,3′‐f]thieno[3,2‐b]thiophene (DNTT)‐based organic field‐effect transistor that demonstrates synaptic plasticity under optical stimulation at 200 K. The device exhibits a dual‐mechanism synaptic behavior through charge separation and trapping, where photogenerated holes provide rapid transport while electrons are preferentially captured in deep trap states, creating persistent field modulation. Excitatory postsynaptic current measurements reveal characteristic three‐phase temporal dynamics with rapid activation, exponential decay, and sustained enhancement lasting tens of minutes. Paired‐pulse facilitation demonstrates short‐term plasticity with dual exponential decay constants of 140 and 610 ms, while multi‐pulse stimulation produces remarkable persistent current level enhancement exceeding 10 000% of the initial baseline, reflecting sequential filling of continuous trap state distributions. The device simultaneously implements both short‐term and long‐term plasticity mechanisms in a single component, enabling simultaneous working memory and persistent information storage functions. Neuromorphic functionality is demonstrated through simulated XOR logic operations, showing non‐linearly separable computation capabilities. The 200 K operating temperature aligns favorably with Mars surface conditions, requiring minimal heating compared to terrestrial cooling requirements, making the device particularly promising for space‐based neuromorphic systems where radiation‐hard organic semiconductors provide additional advantages.","url":"https://doi.org/10.1002/aelm.202500515","authors":["Tomas Vincze","Michal Hanic","Martin Berki","Martin Weis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-03T10:38:14Z","doi":"10.1002/aelm.202500515","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:19.718Z"},{"id":"doi:10.1364/cleo_at.2025.aa120_2","name":"Optical Digital Logic Gates Based on Phase-Modulated Microdisk Spiking Neurons for Neuromorphic Computing","source":"crossref","abstract":"We propose an optical neuromorphic digital logic architecture based on microdisk spiking neurons, respectively demonstrating AND, OR, NOT, and XOR operations through the neural responses of optically injected microdisk lasers with different phase-modulated encoding rules.","url":"https://doi.org/10.1364/cleo_at.2025.aa120_2","authors":["Qiang Zhang","Ning Jiang","Gang Hu","Yingjun Fang","Anran Li","Jiahao Qian","Yongsheng Cao","Kun Qiu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-18T16:54:33Z","doi":"10.1364/cleo_at.2025.aa120_2","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.7567/ssdm.2021.l-2-03","name":"Gate-All-Around (GAA) Synaptic Transistor with Linear Weight Adjustability for Neuromorphic Computing Architecture","source":"crossref","abstract":"","url":"https://doi.org/10.7567/ssdm.2021.l-2-03","authors":["Hasan Ansari","Kannan U.M.","Seongjae Cho"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-06T04:15:44Z","doi":"10.7567/ssdm.2021.l-2-03","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1007/s11063-013-9315-8","name":"Reconfigurable Neuromorphic Computing System with Memristor-Based Synapse Design","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11063-013-9315-8","authors":["Beiye Liu","Yiran Chen","Bryant Wysocki","Tingwen Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-08-09T10:08:34Z","doi":"10.1007/s11063-013-9315-8","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/isvlsi65124.2025.11130262","name":"Memory Wall is not gone: A Critical Outlook on Memory Architecture in Digital Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isvlsi65124.2025.11130262","authors":["Amirreza Yousefzadeh","Sameed Sohail","Ana Lucia Varbanescu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-27T18:20:15Z","doi":"10.1109/isvlsi65124.2025.11130262","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/nano58406.2023.10231303","name":"Voltage Gated Domain Wall Magnetic Tunnel Junction for Neuromorphic Computing Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nano58406.2023.10231303","authors":["Aijaz H. Lone","Hanrui Li","Nazek El-Atab","Gianluca Setti","Hossein Fariborzi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-01T17:23:28Z","doi":"10.1109/nano58406.2023.10231303","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/nmdc57951.2023.10343730","name":"Machine Learning-Assisted Analysis of Advanced STDP for Neuromorphic Computing using MRAM","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nmdc57951.2023.10343730","authors":["Anubha Sehgal","Gaurav Verma","Seema Dhull","Sourajeet Roy","Brajesh Kumar Kaushik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-12T13:39:54Z","doi":"10.1109/nmdc57951.2023.10343730","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/mdat.2021.3080989","name":"Guest Editors’ Introduction: Stochastic Computing for Neuromorphic Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mdat.2021.3080989","authors":["Ilia Polian","John P. Hayes","Vincent T. Lee","Weikang Qian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-07T20:42:53Z","doi":"10.1109/mdat.2021.3080989","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/dspa60853.2024.10510067","name":"Image Interpolation Consistent with Neuromorphic Coding Data","source":"crossref","abstract":"","url":"https://doi.org/10.1109/dspa60853.2024.10510067","authors":["V.E. Antciperov","V.A. Kershner","E.R. Pavlyukova"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-03T18:27:09Z","doi":"10.1109/dspa60853.2024.10510067","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:19.718Z"},{"id":"doi:10.1145/3546790.3546824","name":"Neuro-symbolic computing with spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3546790.3546824","authors":["Dominik Dold","Josep Soler Garrido","Victor Caceres Chian","Marcel Hildebrandt","Thomas Runkler"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-08T04:10:51Z","doi":"10.1145/3546790.3546824","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1016/b978-0-12-819717-2.00008-4","name":"One-dimensional materials for photoelectroactive memories and synaptic devices","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-12-819717-2.00008-4","authors":["Guanglong Ding","Kui Zhou","Teng Li","Baidong Yang","Ye Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-05-29T09:12:06Z","doi":"10.1016/b978-0-12-819717-2.00008-4","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1088/2634-4386/ac7c8a","name":"Two sparsities are better than one: unlocking the performance benefits of sparse–sparse networks","source":"crossref","abstract":"Abstract In principle, sparse neural networks should be significantly more efficient than traditional dense networks. Neurons in the brain exhibit two types of sparsity; they are sparsely interconnected and sparsely active. These two types of sparsity, called weight sparsity and activation sparsity, when combined, offer the potential to reduce the computational cost of neural networks by two orders of magnitude. Despite this potential, today’s neural networks deliver only modest performance benefits using just weight sparsity, because traditional computing hardware cannot efficiently process sparse networks. In this article we introduce Complementary Sparsity, a novel technique that significantly improves the performance of dual sparse networks on existing hardware. We demonstrate that we can achieve high performance running weight-sparse networks, and we can multiply those speedups by incorporating activation sparsity. Using Complementary Sparsity, we show up to 100× improvement in throughput and energy efficiency performing inference on FPGAs. We analyze scalability and resource tradeoffs for a variety of kernels typical of commercial convolutional networks such as ResNet-50 and MobileNetV2. Our results with Complementary Sparsity suggest that weight plus activation sparsity can be a potent combination for efficiently scaling future AI models.","url":"https://doi.org/10.1088/2634-4386/ac7c8a","authors":["Kevin Hunter","Lawrence Spracklen","Subutai Ahmad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-28T22:15:55Z","doi":"10.1088/2634-4386/ac7c8a","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1364/cosi.2024.cm2b.4","name":"Event-Driven LiDAR with Dynamic Neuromorphic Processing","source":"crossref","abstract":"We present a novel spiking neural network approach to building 3D LiDAR images from temporal information alone. Our method uses the “spike” events from individually detected photons without the need to construct temporal histograms.","url":"https://doi.org/10.1364/cosi.2024.cm2b.4","authors":["Matthias Aquilina","Alex Vicente Sola","Paul Kirkland","Ashley Lyons"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T15:51:04Z","doi":"10.1364/cosi.2024.cm2b.4","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:19.718Z"},{"id":"doi:10.1587/nolta.15.784","name":"Special Section on Recent Progress in Neuromorphic AI Hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1587/nolta.15.784","authors":["Hirofumi Tanaka"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-30T22:19:44Z","doi":"10.1587/nolta.15.784","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:19.718Z"},{"id":"doi:10.1109/edtm61175.2025.11041583","name":"2D Materials for Neuromorphic Computing Devices","source":"crossref","abstract":"","url":"https://doi.org/10.1109/edtm61175.2025.11041583","authors":["Max C. Lemme","Lukas Völkel","Sofia Cruces","Jimin Lee","Yuan Fa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-30T17:36:02Z","doi":"10.1109/edtm61175.2025.11041583","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/meco.2018.8406093","name":"Entropy-based method of reducing the training set dimension at constructing a neuromorphic fault dictionary for analog and mixed-signal ICs","source":"crossref","abstract":"","url":"https://doi.org/10.1109/meco.2018.8406093","authors":["Sergey Mosin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-07-09T23:17:35Z","doi":"10.1109/meco.2018.8406093","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1063/1.5042408","name":"A phase-change memory model for neuromorphic computing","source":"crossref","abstract":"Phase-change memory (PCM) is an emerging non-volatile memory technology that is based on the reversible and rapid phase transition between the amorphous and crystalline phases of certain phase-change materials. The ability to alter the conductance levels in a controllable way makes PCM devices particularly well-suited for synaptic realizations in neuromorphic computing. A key attribute that enables this application is the progressive crystallization of the phase-change material and subsequent increase in device conductance by the successive application of appropriate electrical pulses. There is significant inter- and intra-device randomness associated with this cumulative conductance evolution, and it is essential to develop a statistical model to capture this. PCM also exhibits a temporal evolution of the conductance values (drift), which could also influence applications in neuromorphic computing. In this paper, we have developed a statistical model that describes both the cumulative conductance evolution and conductance drift. This model is based on extensive characterization work on 10 000 memory devices. Finally, the model is used to simulate the supervised training of both spiking and non-spiking artificial neuronal networks.","url":"https://doi.org/10.1063/1.5042408","authors":["S. R. Nandakumar","Manuel Le Gallo","Irem Boybat","Bipin Rajendran","Abu Sebastian","Evangelos Eleftheriou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-10-17T14:00:38Z","doi":"10.1063/1.5042408","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.2139/ssrn.5650470","name":"A Low-Power Heterostructure Memristor Based on 2D Materials for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5650470","authors":["Qiping Zou","Zhenqiang Tan","Jianhua Li","Haiou Li","Fabi Zhang","Zanhui Chen","Xing Deng","Zhimou Xu","Xiaosheng Tang","Tangyou Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-24T00:52:39Z","doi":"10.2139/ssrn.5650470","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1515/9783111545950-007","name":"1257 Effects of spin of electron in quantum devices","source":"crossref","abstract":"","url":"https://doi.org/10.1515/9783111545950-007","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-06T19:15:47Z","doi":"10.1515/9783111545950-007","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1109/iscas.2016.7527186","name":"Heterogeneous systems with reconfigurable neuromorphic computing accelerators","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas.2016.7527186","authors":["Sicheng Li","Xiaoxiao Liu","Mengjie Mao","Hai Helen Li","Yiran Chen","Boxun Li","Yu Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-11-01T20:59:26Z","doi":"10.1109/iscas.2016.7527186","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1117/12.3038183","name":"Organic electrochemical synaptic transistors for neuromorphic vision sensor","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3038183","authors":["Yiming Shi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-07T16:06:09Z","doi":"10.1117/12.3038183","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:19.718Z"},{"id":"doi:10.1109/transducers61432.2025.11109161","name":"A Mems Accelerometer with in-Sensor Neuromorphic Computing Capability","source":"crossref","abstract":"","url":"https://doi.org/10.1109/transducers61432.2025.11109161","authors":["Yunlong Bai","Wuhao Yang","Bingchen Zhu","Zheng Wang","Xudong Zou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-19T18:06:19Z","doi":"10.1109/transducers61432.2025.11109161","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1088/2634-4386/ac4fb7","name":"Precision of bit slicing with in-memory computing based on analog phase-change memory crossbars","source":"crossref","abstract":"Abstract In-memory computing is a promising non-von Neumann approach to perform certain computational tasks efficiently within memory devices by exploiting their physical attributes. However, the computational accuracy achieved with this approach has been rather low, owing to significant inter-device variability and inhomogeneity across an array as well as intra-device variability and randomness from the analog memory devices. Bit slicing, a technique for constructing a high precision processor from several modules of lower precision, is a promising approach for overcoming this accuracy limitation. However, a systematic study to assess the precision ultimately achieved by bit slicing with analog in-memory computing has so far been lacking. In this work, we assess the computational error from bit slicing when performing in-memory matrix-vector multiplications. Using accurate models of phase-change memory crossbar arrays, we demonstrate that unlike in digital processors where bit slicing is used to extend the dynamic range of the number representation, bit slicing with in-memory computing should aim at minimizing the error from the analog matrix representation through averaging within a given dynamic range. The results are validated using a prototype phase-change memory chip and the impact on the neural network inference accuracy on CIFAR-10 and ImageNet benchmarks is evaluated.","url":"https://doi.org/10.1088/2634-4386/ac4fb7","authors":["Manuel Le Gallo","S R Nandakumar","Lazar Ciric","Irem Boybat","Riduan Khaddam-Aljameh","Charles Mackin","Abu Sebastian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-01-27T22:41:55Z","doi":"10.1088/2634-4386/ac4fb7","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.3389/fnins.2019.00189","name":"ReStoCNet: Residual Stochastic Binary Convolutional Spiking Neural Network for Memory-Efficient Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.3389/fnins.2019.00189","authors":["Gopalakrishnan Srinivasan","Kaushik Roy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-03-19T09:28:59Z","doi":"10.3389/fnins.2019.00189","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1007/978-3-032-09586-2_2","name":"Background","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-09586-2_2","authors":["Felix Staudigl","Rainer Leupers"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-22T14:21:55Z","doi":"10.1007/978-3-032-09586-2_2","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:19.718Z"},{"id":"doi:10.1109/vlsi-dat.2017.7939672","name":"Hybrid three-dimensional integrated circuits: A viable solution for high efficiency Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/vlsi-dat.2017.7939672","authors":["M. Amimul Ehsan","Zhen Zhou","Yang Yi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-06-08T16:42:47Z","doi":"10.1109/vlsi-dat.2017.7939672","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1088/2631-8695/ae1d0c","name":"Neuromorphic computing for energy-efficient machine intelligence","source":"crossref","abstract":"Abstract Neuromorphic computing has gained a significant amount of attention from industry as well as the research community as a means of overcoming the growing energy demands of machine intelligence. Neuromorphic systems offer promising computation approaches by mimicking the functioning of the human brain’s energy-efficient neural processing. This perspective explores the significance of energy efficiency in artificial intelligence (AI) systems, examines the potential issues associated with traditional AI architectures, and highlights the importance of neuromorphic computing as a sustainable solution. It also provides an overview of the working principle of neuromorphic systems, a spiking neural network (SNN) implementation, and the comparative advantages over conventional computing architectures. This perspective further investigates several real-world applications to assess the potential of neuromorphic computing to perform real-time and energy-efficient operations. Although they offer significant advantages, neuromorphic systems face multiple challenges regarding materials development, fabrication techniques, large-scale deployments, and a lack of standard software tools. Finally, this perspective outlines potential research directions to explore the role of neuromorphic computing in next-generation AI systems.","url":"https://doi.org/10.1088/2631-8695/ae1d0c","authors":["Shahid Latif","Saniya Zafar","Jawad Ahmad","Muhammad Zakir Khan","Farhan Ullah","Aizaz Ahmad Khattak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-07T22:52:42Z","doi":"10.1088/2631-8695/ae1d0c","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1038/s43246-026-01097-x","name":"Multidimensional and reconfigurable optical neuromorphic computing using perovskite-based all-photonic synapses","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s43246-026-01097-x","authors":["Jiangzhi Zi","Jie Sun","Bing Yang","Fangzhen Hu","Keer Zhang","Xi Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-18T23:06:02Z","doi":"10.1038/s43246-026-01097-x","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1109/icnc52316.2021.9608488","name":"A Lightweight Multi-modal Emotion Recognition Network Based on Multi-task Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc52316.2021.9608488","authors":["Peisong Liu","Xiaoping Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-29T20:59:32Z","doi":"10.1109/icnc52316.2021.9608488","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/med.2023.3307978","name":"Special Issue on Neuromorphic Computing, <i>IEEE Electron Devices Magazine</i> [From the Editor]","source":"crossref","abstract":"","url":"https://doi.org/10.1109/med.2023.3307978","authors":["J. Joshua Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-04T17:37:24Z","doi":"10.1109/med.2023.3307978","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/icnc59488.2023.10462752","name":"Memristor-Based Analog Multiplier","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462752","authors":["Jun Lei","Le Yang","Zhixia Ding","Sai Li","Ming Cheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462752","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.3389/fnins.2025.1565811","name":"Editorial: Brain-inspired computing: from neuroscience to neuromorphic electronics for new forms of artificial intelligence","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2025.1565811","authors":["Daniela Gandolfi","Jonathan Mapelli","Francesco Maria Puglisi"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fnins.2025.1565811","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1109/icnc59488.2023.10462817","name":"Brain Inspired Episodic Memory Deep Q-Networks for Sparse Reward","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462817","authors":["Xinyu Wu","Chaoqiong Fan","Tianyuan Jia","Xia Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462817","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1016/b978-0-443-29981-0.00007-0","name":"Low-power 3-D IC-based spiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-29981-0.00007-0","authors":["Nguyen Ngo-Doanh","Akram Ben Ahmed","Abderazek Ben Abdallah","Khanh N. Dang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T15:03:10Z","doi":"10.1016/b978-0-443-29981-0.00007-0","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.31224/5651","name":"JAQA: Building a Joint Alliance of Quantum Assurance for Future-Proof Cybersecurity, Energy Optimization, and Precision Healthcare Leveraging Post-Quantum Cryptography, Neuromorphic Computing, 6G, and XR Technologies in Kerala and India","source":"crossref","abstract":"The accelerating convergence of disruptive technologies necessitates innovative frameworks for national security, sustainable development, and advanced public services. This paper details the strategic design and implementation of JAQA, a Joint Alliance of Quantum Assurance, as an integrated multi-stakeholder model for Kerala and India. The alliance aims to establish quantum-safe digital infrastructure, optimized energy systems, and next-generation precision healthcare by leveraging post-quantum cryptography (PQC), neuromorphic computing, 6G networks, extended reality (XR), and autonomous systems. Through a comprehensive methodological approach involving systematic literature review and thematic analysis, this work synthesizes existing research and policy contexts to address the central inquiry: how Kerala and India can pioneer global leadership in secure, intelligent, and sustainable governance by 2030 through JAQA. Qualitative findings reveal critical themes concerning governance structures, technology adoption pathways, ethical considerations, and scalability. Policy implications underscore the imperative for harmonized regulatory frameworks, robust capacity building, and strategic international collaborations. An evaluation plan emphasizes key performance indicators related to cybersecurity resilience, energy efficiency gains, and healthcare outcome improvements, ensuring an iterative refinement process. The proposed JAQA framework provides a blueprint for integrating cutting-edge technologies within a coherent governance ecosystem, fostering trust, agility, and sustainability across vital sectors.","url":"https://doi.org/10.31224/5651","authors":["Amit Suresh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-22T20:06:28Z","doi":"10.31224/5651","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/fccm57271.2023.00051","name":"Clustering Classification on FPGAs for Neuromorphic Feature Extraction","source":"crossref","abstract":"","url":"https://doi.org/10.1109/fccm57271.2023.00051","authors":["Luke Kljucaric","Alan D. George"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-10T18:14:13Z","doi":"10.1109/fccm57271.2023.00051","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1016/j.neunet.2013.02.011","name":"Computing with networks of spiking neurons on a biophysically motivated floating-gate based neuromorphic integrated circuit","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2013.02.011","authors":["S. Brink","S. Nease","P. Hasler"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-03-08T11:45:24Z","doi":"10.1016/j.neunet.2013.02.011","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1021/acs.nanolett.6c00994","name":"Wafer-Scale All-Silicon Self-Rectifying Memristor for Synaptic Response and Reservoir Computing.","source":"europepmc","abstract":"Silicon p-n junctions have remained an indispensable building block of electronics since their invention in the Shockley days. Likewise, an abrupt p-n junction has served as a foundational model in semiconductor textbooks. In this work, we report on an p-n junction in silicon with an oxide interfacial layer, enabling memristive functions with highly rectifying resistive switching and reproducible synaptic behaviors for reservoir computing (RC). The device exhibited a rectification ratio of ∼5000 with stable endurance of 4.5 × 106 cycles, without filament formation. Charge-trapping dynamics enable key synaptic behaviors including paired-pulse facilitation, spike-timing-dependent plasticity, and transitions between short- and long-term memory. Leveraging these behaviors, the device performs RC via 4-bit pulse stimulation, achieving 86.9% accuracy in handwritten digit classification. This interface-engineered all-silicon device bridges classical diode physics with modern neuromorphic computation, providing a prospect for wafer-scale platforms for neuromorphic applications.","url":"https://doi.org/10.1021/acs.nanolett.6c00994","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acs.nanolett.6c00994","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.3390/biomimetics11080519","name":"CMOS-Compatible AlScN Memristor on Silicon Exhibiting Short-Term Memory for Reservoir Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics11080519","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/biomimetics11080519","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acsami.6c04205","name":"Threshold Voltage Modulation and Performance Enhancement in Indium Gallium Zinc Oxide/hafnium Zirconium Oxide Ferroelectric Field-Effect Transistors via Interface Dipole Engineering.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.6c04205","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.6c04205","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/smll.202512071","name":"Mechanically Durable Intrinsically Stretchable Neuromorphic Devices via Molecular Microstructure Design.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.202512071","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.202512071","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1007/s40820-026-02253-1","name":"2D Materials Powering Neuromorphic Intelligence.","source":"europepmc","abstract":"The exponential demand for energy-efficient and adaptive computing architectures drives the evolution of artificial intelligence (AI) and machine learning (ML). Neuromorphic computing, inspired by biological neural networks, overcomes the limitations of traditional von Neumann architectures, including high energy consumption and limited scalability. The introduction of two-dimensional (2D) materials, such as transition metal dichalcogenides, hexagonal boron nitride, black phosphorus, and tellurene, enables neuromorphic devices with unprecedented control over electronic and optoelectronic properties. These materials exhibit atomic-scale thickness, high carrier mobility, and tunable bandgaps, facilitating synaptic behaviours such as spike-timing-dependent plasticity and paired-pulse facilitation. This review describes the integration of 2D materials into neuromorphic systems, highlighting applications in wearable electronics, brain-machine interfaces, and quantum neuromorphic platforms. In wearable and edge computing, 2D-based devices enable localized, ultra-low-power data processing. In brain-machine interfaces, they enhance signal transduction and neural interfacing. Quantum effects in 2D materials further enable hybrid quantum-classical neuromorphic architectures for high-dimensional computational tasks. Despite significant advances, challenges in reproducibility, scalability, and stability remain. Addressing these limitations through innovations in synthesis and defect passivation is essential for practical application. This review underscores the transformative potential of 2D-material-based neuromorphic computing for energy-efficient AI. Integration of 2D materials into neuromorphic computing architectures offers a promising pathway toward energy-efficient and adaptive systems that bridge biological learning mechanisms with machine intelligence.","url":"https://doi.org/10.1007/s40820-026-02253-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s40820-026-02253-1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1039/d5mh02338f","name":"Photon-controlled memristive synapses: recent progress toward brain-inspired neuromorphic computing.","source":"europepmc","abstract":"This review highlights recent advances in optoelectronic memristive synapses, detailing the underlying mechanisms, materials, device architectures, performance metrics, and applications, along with challenges and future trends.","url":"https://doi.org/10.1039/d5mh02338f","authors":["Pradnya P. Patil","Tejas Dhanalaxmi Raju","Kiran A. Nirmal","Tukaram D. Dongale","Kyeong Heon Kim","Tae Geun Kim"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d5mh02338f","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1039/d5mh01319d","name":"Physically reconfigurable synaptic plasticity and learning in stretchable neuromorphic systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5mh01319d","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d5mh01319d","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/advs.76674","name":"Hierarchical Multi-Mode Computing in Interlayer-Coupled 3D RRAM Crossbar Arrays.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.76674","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.76674","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acsami.5c24346","name":"Light-Programmable IGZO Optoelectronic Memristor for Multifunctional Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c24346","authors":["Heeseong Jang","Seohyeon Ju","Youngseo Lee","Minsu Ko","Chanmin Park","Min-Hwi Kim","Sungjun Kim"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.5c24346","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/adma.202514329","name":"Opto-Ferroelectric Coupling Enhanced α-In&lt;sub&gt;2&lt;/sub&gt;Se&lt;sub&gt;3&lt;/sub&gt; Transistors With Light-Controlled Mode Switchover.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202514329","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202514329","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1002/adma.202523670","name":"Path-Decoupled Cation-Eutaxy III-V van der Waals Memristive Semiconductors for Mitigating the Neuromorphic Accuracy-Energy Trade-off.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202523670","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202523670","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1021/acsami.6c06092","name":"Bulk Spin-Orbit Torque-Driven Spin Hall Nano-Oscillators Using PtBi Alloys with Engineered Crystallinity.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.6c06092","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.6c06092","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1002/adma.202523703","name":"Monolithic 3D-Integrated All-Solid Ion-Gated Carbon Nanotube Transistors With Tunable Ionic Conductance for Multi-Timescale Reservoir Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202523703","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202523703","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1002/smll.202514447","name":"Controllable and Cost-Efficient Three-Terminal GaN Nano-Synapse for Brain-Inspired Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.202514447","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.202514447","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1002/adma.202522251","name":"Nanolaminate Ferroelectric Transistor Enabling Wide-Reservoir In Sensor Neuromorphic Vision.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202522251","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202522251","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1002/smll.202514024","name":"Bipolar Switching and Synaptic Behaviors Observed in Titanium-Constrained Phase-Change Heterostructures.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.202514024","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.202514024","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1039/d5cs01222h","name":"From solar cells to memristors: halide perovskites as a platform for neuromorphic electronics.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5cs01222h","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d5cs01222h","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1038/s41565-026-02122-3","name":"Twelve-inch electrically anisotropic boridene for optoelectronic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41565-026-02122-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41565-026-02122-3","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.3389/fnins.2026.1827009","name":"Federated training of spiking neural networks on edge hardware for audio processing.","source":"europepmc","abstract":"Spiking Neural Networks have caught significant attention recently for their potential for energy-efficient computation on neuromorphic hardware and their event-driven processing. Spiking Neural networks employ spike-based learning paradigms, which require specialized training procedures such as Surrogate Gradient Descent. At the same time, Federated Learning allows collaborative model training on decentralized devices with preservation of data privacy protection. However, to date, few research has examined the suitability of Federated learning with ARM-based hardware. This work primarily investigates whether Federated Spiking Neural Networks training on ARM-based hardware is feasible with the Raspberry Pi 5 as a widely available and low-cost edge computing device for audio signal processing tasks. We perform a comparative analysis of federated Spiking Neural Network and federated convolutional neural networks on ARM processors and evaluate their performance on different data partitioning strategies using Dirichlet-based splits and various federated averaging algorithms. Using Federated learning, this work investigates the impact of data heterogeneity and aggregation strategies on model convergence, communication overhead, and latency in distributed training paradigms. The results provided showcases the important insights into the trade-offs of FL-SNN implementations on Von Neumann architectures and their applications in decentralized neuromorphic computing for audio processing.","url":"https://doi.org/10.3389/fnins.2026.1827009","authors":["Swaroop S. Kaimal","Ashwin JB","S. Sofana Reka","Prakash Venugopal"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnins.2026.1827009","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1002/advs.76461","name":"Anisotropic Memristive Switching in NbOCl&lt;sub&gt;2&lt;/sub&gt; Enabled by Directional Oxygen Ion Migration.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.76461","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.76461","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1002/smll.75133","name":"Monolithically-Fabricated All-2D PdSe&lt;sub&gt;2&lt;/sub&gt; Bendable Arrays With Seamless Interfaces for Multifunctional Flexo-Opto-Electronics.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.75133","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.75133","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1021/acs.nanolett.6c02080","name":"In-Situ TEM Studies of Halide Perovskite Memristors: Mechanistic Insights and Future Directions.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.6c02080","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acs.nanolett.6c02080","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1002/advs.76640","name":"Hydrogen-Stabilized Self-Rectifying Memristor Arrays for Reliable Multilevel Synapses in Transformer-Based Keyword Spotting.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.76640","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.76640","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1002/adma.202509143","name":"Molecularly Engineered Memristors for Reconfigurable Neuromorphic Functionalities.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202509143","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202509143","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1007/s40820-025-02036-0","name":"Organic Phototransistor Photonic Synapses for Artificial Vision.","source":"europepmc","abstract":"The von Neumann architecture faces significant limitations, including low transmission efficiency and high energy consumption, when handling large-scale data and unstructured problems. Benefiting from the inherent merits of optical signals including high bandwidth, near-zero Joule heating, fast transmission speed, and immunity to electromagnetic interference, photonics provides a powerful pathway for high-speed neuromorphic computing. Together with the mechanical flexibility and largearea manufacturability of organic semiconductors, organic phototransistor (OPT)-based photonic synapses have therefore attracted extensive attention in recent years. This review provides a comprehensive overview of recent advances in OPT-based photonic synapses, covering operational principles, active materials, advances in bidirectional photoresponse process, as well as cutting-edge applications. Finally, the current challenges and opportunities in this field are highlighted. Distinct from previous reviews, this review emphasizes an in-depth exploration of bidirectional photoresponse mechanisms, a systematic dissection of material-structure-function correlations enabling integrated sensing-memory technology, and emerging.","url":"https://doi.org/10.1007/s40820-025-02036-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s40820-025-02036-0","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1002/advs.75471","name":"Triple-Mode Ferroelectric Thin-Film Transistor for Hybrid Electrical-Optical Reservoir Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.75471","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.75471","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1088/1361-6528/ae7427","name":"Low-leakage volatile threshold switching in Gr/CIPS/h-BN/Au van der Waals heterostructure via atomic-scale geometric confinement.","source":"europepmc","abstract":"","url":"https://doi.org/10.1088/1361-6528/ae7427","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1088/1361-6528/ae7427","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1002/smll.202511256","name":"Self-Powered Neuromorphic Touch Sensors Based on Triboelectric Devices: Current Approaches and Open Challenges.","source":"europepmc","abstract":"ABSTRACT Advanced neuromorphic systems mimicking the human sensory and nervous system will enable artificial perception for intelligent robotics and human machine interfaces. Among sensing modalities, tactile perception is crucial for replicating human somatosensory and motor functions, with significant potential to restore impaired tactile capabilities. Artificial neuromorphic sensors can directly sense, store and process various stimuli information and implement computation functions such as perception, learning, and memory. However, computational energy efficiency must be achieved with novel neuromorphic systems capable of environmental energy harvesting enabling self‐powered sensing, and real‐time edge data processing. Here, we focus on the integration of tactile self‐powered sensors based on triboelectric nanogenerators (TENGs) with neuromorphic devices. We systematically discuss current approaches for coupling TENGs with artificial synapses and neurons, covering the main integration architectures (ex situ, discrete circuit, direct gating, monolithic), the primary operational modes (displacement‐driven, pulse‐driven), and neuromorphic functions as short‐ and long‐term plasticity, memory, and logic‐in‐memory computing. We also highlight the mechanisms of signal generation and transduction, and the strategies used to enhance performance and energy efficiency. The review concludes with a discussion on key challenges and future directions for developing sustainable, low‐power, and multifunctional neuromorphic tactile systems, paving the way toward fully integrated self‐powered artificial somatosensory platforms.","url":"https://doi.org/10.1002/smll.202511256","authors":["Fabrizio Torricelli","Giuseppina Pace"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.202511256","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1007/s40820-025-01940-9","name":"Multisensory Neuromorphic Devices: From Physics to Integration.","source":"europepmc","abstract":"Abstract The increasing complexity of intelligent sensing environments, driven by the growth of Internet of Things technologies, has created a strong demand for neuromorphic systems capable of real-time, low-power multisensory perception. Traditional sensory architectures, constrained by single-modal processing and centralized computing, struggle to meet the requirements of diverse and dynamic input conditions. Multisensory neuromorphic devices offer a promising solution by mimicking the distributed, event-driven processing of biological systems. Recent efforts have explored synaptic devices and material systems that respond to various input modalities, including visual, tactile, thermal, and chemical stimuli. However, challenges remain in signal conversion, encoding compatibility, and the fusion of heterogeneous inputs without loss of unisensory information. This review provides a comprehensive overview of the physical mechanisms, device behaviors, and integration strategies that underpin signal processing in neuromorphic hardware. We highlight synaptic mechanisms conducive to cross-modal interaction, analyze representative signal fusion approaches at the device level, and discuss future directions for constructing efficient, scalable, and biologically inspired multisensory neuromorphic systems.","url":"https://doi.org/10.1007/s40820-025-01940-9","authors":["An Gui","Haoran Mu","Rong Yang","Guangyu Zhang","Shenghuang Lin"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s40820-025-01940-9","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1038/s41467-025-68206-1","name":"Coupled ferroelectric-anisotropic optoelectronic synapse for polarization-sensitive neuromorphic vision.","source":"europepmc","abstract":"Polarization-sensitive photodetection and non-volatile memory are both vital for neuromorphic vision hardware but are rarely integrated within a single device. This challenge arises from interfacial instabilities and depolarization fields at the 2D/ferroelectric junctions that degrade remanent polarization and long-term retention. Here, we demonstrate a polarization-resolved optoelectronic synapse based on a 2D ReS 2 channel and a ferroelectric Hf 0.5 Zr 0.5 O 2 (HZO) gate dielectric in a metal-ferroelectric-metal-insulator-semiconductor (MFMIS) ferroelectric field-effect transistor (FeFET). Co-modulation of ferroelectric polarization and photoexcited carrier trapping enables high responsivity, strong detectivity, and long-term optoelectronic retention. Coupling between the polarization anisotropy of ReS 2 and ferroelectric memristive states enables gate-tunable polarization ratios and polarization-resolved learning. Furthermore, the optoelectronic synapse exhibits linear and energy-efficient optical-electrical modulation with 2.0 fJ per event. An ANN built from these synapses achieves 97.33% accuracy in iris recognition under unpolarized light, while a 3×3 FeFET-based CNN performs butterfly classification under polarized illumination through polarization-resolved feature extraction. This work establishes a unified ferroelectric-anisotropic platform for energy-efficient, polarization-resolved neuromorphic vision.","url":"https://doi.org/10.1038/s41467-025-68206-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-025-68206-1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1002/adma.202515480","name":"Ferroelectric Transistors: from Materials Innovation to Intelligent Electronic Systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202515480","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/adma.202515480","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1007/s40820-025-01902-1","name":"Two-Dimensional MXene-Based Advanced Sensors for Neuromorphic Computing Intelligent Application.","source":"europepmc","abstract":"Abstract As emerging two-dimensional (2D) materials, carbides and nitrides (MXenes) could be solid solutions or organized structures made up of multi-atomic layers. With remarkable and adjustable electrical, optical, mechanical, and electrochemical characteristics, MXenes have shown great potential in brain-inspired neuromorphic computing electronics, including neuromorphic gas sensors, pressure sensors and photodetectors. This paper provides a forward-looking review of the research progress regarding MXenes in the neuromorphic sensing domain and discussed the critical challenges that need to be resolved. Key bottlenecks such as insufficient long-term stability under environmental exposure, high costs, scalability limitations in large-scale production, and mechanical mismatch in wearable integration hinder their practical deployment. Furthermore, unresolved issues like interfacial compatibility in heterostructures and energy inefficiency in neuromorphic signal conversion demand urgent attention. The review offers insights into future research directions enhance the fundamental understanding of MXene properties and promote further integration into neuromorphic computing applications through the convergence with various emerging technologies.","url":"https://doi.org/10.1007/s40820-025-01902-1","authors":["Lin Lu","Bo Sun","Zheng Wang","Jialin Meng","Tianyu Wang"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1007/s40820-025-01902-1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1038/s41467-026-68923-1","name":"Advancing neuroengineering with Neuromorphic Twins.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-68923-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-68923-1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1039/d5nh00623f","name":"Harnessing glycol-alkyl copolymerization to realize nonvolatile and biologically relevant synaptic behaviors.","source":"europepmc","abstract":"Organic electrochemical synaptic transistors (OESTs) are attracting growing attention for neuromorphic computing, yet their long-term stability remains constrained by uncontrolled ion dynamics. Previous studies have incorporated glycol side chains to facilitate ionic transport, but a systematic understanding of how copolymerization with hydrophobic alkyl units governs ion doping and retention is still lacking. Here, we establish a rational backbone-side chain copolymer design strategy that precisely regulates ionic interactions, crystallinity, and charge transport. We also reveal clear correlations between copolymer structure, ion dedoping dynamics, and nonvolatile retention. These structural advantages enable the faithful emulation of key biological behaviors including paired-pulse facilitation, spike-timing dependent plasticity, and long-term potentiation/depression (LTP/D) with high linearity and stability. Based on these properties, the device achieved a high accuracy of 94.1% in ANN-based recognition simulations for MNIST handwritten digits. This work demonstrates that systematic glycol-alkyl copolymer engineering provides a robust and predictive design principle for high-performance neuromorphic synapses, moving beyond empirical side-chain modifications.","url":"https://doi.org/10.1039/d5nh00623f","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d5nh00623f","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1002/advs.202522487","name":"Oxide Semiconductor Thin-Film Transistors for Low-Power Electronics.","source":"europepmc","abstract":"Low power consumption has become an essential criterion in the development of next-generation electronics, driven by the growing adoption of Internet of Things, wearables, and portable platforms. Oxide semiconductor thin-film transistors (TFTs) have become most promising candidates for next-generation low-power electronics due to their wide band-gap, low leakage current, high mobility, steep subthreshold swing, and compatibility with low-temperature flexible processing. In this review, recent advances in the use of oxide TFTs for low-power electronics are systematically summarized. First, the inherent advantages of oxide semiconductor materials over other commonly used materials (e.g., amorphous hydrogenated silicon, low temperature polycrystalline silicon, organic semiconductors, etc.) for realizing low power consumption are demonstrated. Then, strategies to reduce power consumption are further discussed, including interface engineering, such as the novel source-gated transistors, and structural engineering, such as dual-gate and underlap designs. Finally, a comprehensive review of oxide TFTs for various low-power electronics applications, including logic circuits, active-matrix arrays, flexible electronics, monolithic 3D integration, and neuromorphic computing, is presented, demonstrating their great potential in future low-power and flexible electronic systems.","url":"https://doi.org/10.1002/advs.202522487","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.202522487","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1021/acsnano.5c16255","name":"Sub-2 nm Equivalent-Oxide-Thickness Ferroelectric Transistors for Cryogenic Memory and Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.5c16255","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsnano.5c16255","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1007/s40820-025-01850-w","name":"Advanced Design for High-Performance and AI Chips.","source":"europepmc","abstract":"Recent years have witnessed transformative changes brought about by artificial intelligence (AI) techniques with billions of parameters for the realization of high accuracy, proposing high demand for the advanced and AI chip to solve these AI tasks efficiently and powerfully. Rapid progress has been made in the field of advanced chips recently, such as the development of photonic computing, the advancement of the quantum processors, the boost of the biomimetic chips, and so on. Designs tactics of the advanced chips can be conducted with elaborated consideration of materials, algorithms, models, architectures, and so on. Though a few reviews present the development of the chips from their unique aspects, reviews in the view of the latest design for advanced and AI chips are few. Here, the newest development is systematically reviewed in the field of advanced chips. First, background and mechanisms are summarized, and subsequently most important considerations for co-design of the software and hardware are illustrated. Next, strategies are summed up to obtain advanced and AI chips with high excellent performance by taking the important information processing steps into consideration, after which the design thought for the advanced chips in the future is proposed. Finally, some perspectives are put forward.","url":"https://doi.org/10.1007/s40820-025-01850-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1007/s40820-025-01850-w","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1515/nanoph-2025-0217","name":"What is next for LLMs? Pushing the boundaries of next-gen AI computing hardware with photonic chips.","source":"europepmc","abstract":"Large language models (LLMs) are rapidly pushing the limits of contemporary computing hardware. For example, training GPT-3 has been estimated to consume around 1,300 MWh of electricity, and projections suggest future models may require city-scale (gigawatt) power budgets. These demands motivate exploration of computing paradigms beyond conventional von Neumann architectures. This review surveys emerging photonic hardware optimized for next-generation generative AI computing. We discuss integrated photonic neural network architectures (e.g. Mach-Zehnder interferometer meshes, lasers, wavelength-multiplexed microring-resonators) that perform ultrafast matrix operations. We also examine promising alternative neuromorphic devices and platforms, including 2D materials and hybrid spintronic-photonic synapses, which combine memory and processing. The integration of two-dimensional materials (graphene, TMDCs) into silicon photonic platforms is reviewed for tunable modulators and on-chip synaptic elements. Transformer-based LLM architectures (self-attention and feed-forward layers) are analyzed in this context, introducing the mathematical operations associated with the transformers and identifying strategies and challenges for mapping dynamic matrix multiplications onto these novel photonic hardware systems. Overall, we broadly introduce state-of-the-art photonic components, AI algorithms, and system integration methods, highlighting key advances and open issues in scaling such photonic systems to mega-sized LLM models. We find that photonic computing systems could potentially surpass electronic processors by orders of magnitude in throughput and energy efficiency, but require breakthroughs in memory especially for long-context windows and long token sequences and in storage of ultra-large datasets, among others. This survey provides a comprehensive roadmap for AI hardware development, emphasizing the role of cutting-edge photonic components and technologies in supporting future LLMs.","url":"https://doi.org/10.1515/nanoph-2025-0217","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1515/nanoph-2025-0217","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1007/s40820-025-01825-x","name":"Mechanical Properties Analysis of Flexible Memristors for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s40820-025-01825-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1007/s40820-025-01825-x","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acsomega.5c08106","name":"Overcoming Volatility in Ion Gel via Ag Doping for Nonvolatile Memristive Switching.","source":"europepmc","abstract":"Ion-gel-based memory devices can effectively change their resistance states even at low voltages, owing to the rapid mobility of ions and the formation of an electric double layer. However, their volatile characteristics limit their use in nonvolatile memory and neuromorphic applications. In this paper, we report an ion-gel-based memristive device capable of both digital data storage and analog data processing through the incorporation of silver nanoparticles (AgNPs). The memristive device exhibited reliable resistive switching behavior, characterized by forming-free and a butterfly shaped bipolar resistive switching (BRS) profile. Notably, the ion-gel-based memristive device with AgNPs demonstrated excellent data retention for over 10 5 s even at 85 °C, attributed to the charge storage stability provided by Ag + -based ion pairing. In addition to memory functionality, the device successfully emulated various synaptic behaviors, including long-term potentiation (LTP), long-term depression (LTD), and the transition from short-term memory (STM) to long-term memory (LTM). Furthermore, it achieved clear digit classification results in learning and inference tasks, with a recognition accuracy of up to 96.4%.","url":"https://doi.org/10.1021/acsomega.5c08106","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsomega.5c08106","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.3389/fnins.2026.1795946","name":"Adaptive and lightweight surrogate gradients: enhancing training efficiency of spiking neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2026.1795946","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnins.2026.1795946","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1002/advs.202516478","name":"Tunable Switching Mechanisms in HfZrO&lt;sub&gt;2&lt;/sub&gt;-Based Tunnel Junctions for High-Performance Synaptic Arrays.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202516478","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.202516478","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1002/adma.202512548","name":"Falcon Vision-Inspired Ultrafast Traffic Obstacle Avoidance Based on 2D Edge-Rich van der Waals Heterostructures.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202512548","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202512548","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1038/s41467-026-73279-7","name":"Ultrafast switching and high-endurance nonvolatile memory enabled by intrinsic switchable polarization in semiconducting Janus monolayers.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-73279-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-73279-7","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1021/acsnano.5c17016","name":"A Vertical Molecular Synaptic Transistor with Redox-Induced Analog States.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.5c17016","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsnano.5c17016","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1364/oe.580151","name":"High-frequency all-optical oscillators based on silicon photonic crystal nanobeam cavities.","source":"europepmc","abstract":"","url":"https://doi.org/10.1364/oe.580151","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1364/oe.580151","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1002/smll.202508508","name":"Hybrid WS&lt;sub&gt;2&lt;/sub&gt;-Based Memristor With Tunable Conductance Modulation for Neuromorphic and Nociceptive Learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.202508508","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/smll.202508508","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.3390/s26010081","name":"Event-Based Vision Application on Autonomous Unmanned Aerial Vehicle: A Systematic Review of Prospects and Challenges.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s26010081","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/s26010081","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/frai.2025.1686752","name":"Beyond mimicry: a framework for evaluating genuine intelligence in artificial systems.","source":"europepmc","abstract":"Current AI benchmarks often equate mimicry with genuine intelligence, emphasizing task performance over the underlying cognitive processes that enable human-like understanding. The Machine Perturbational Complexity & Agency Battery (mPCAB) introduces a new, substrate-independent framework that applies neurophysiological methods used initially to assess consciousness in artificial systems. Unlike existing evaluations, it features four key components-perturbational complexity, global workspace assessment, norm internalization, and agency-that link mechanisms with functions. This enables systematic comparisons across digital, neuromorphic, and biological substrates, addressing three research gaps: long-term reasoning with coherent behavior, norm internalization amid distribution shifts, and transformational creativity involving meta-cognitive rule modification. By analyzing theories of consciousness (GNW, IIT, PP, HOT), we identify targets for AI implementation. Our cognitive architecture analysis maps human functions-such as working memory and executive control-to their computational counterparts, providing guiding principles for design. The creativity taxonomy progresses from combinational to transformational, with measurable criteria like changes in conceptual space and the depth of meta-level reasoning. Ethical considerations are integrated into frameworks for monitoring organoid intelligence, reducing bias in creativity, and addressing rights issues. Pilot studies demonstrate mPCAB's feasibility across different substrates and show that its metrics are comparable. This framework moves evaluation away from superficial benchmarks toward mechanism-based assessment, supporting the development of mind-like machines and responsible AI advancements.","url":"https://doi.org/10.3389/frai.2025.1686752","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/frai.2025.1686752","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1038/s41467-026-74068-y","name":"System-level integration of halide perovskite optoelectronics for its commercial deployment.","source":"europepmc","abstract":"Halide perovskites have emerged as a compelling material for a broad range of optoelectronic applications, including light-emitting diodes, phototransistors, light-sensing and imaging systems. To enable practical application and compatibility with existing consumer electronics, they must be integrated with heterogeneous electronic platforms, such as complementary metal-oxide-semiconductor chips or thin-film transistors. Such integration is pivotal for transitioning perovskite technologies from laboratory demonstrations to commercial applications. In this perspective, we summarize recent progress in the system-level integration of perovskite optoelectronics with driving backplanes, compare key performance metrics with industrial benchmarks, discuss major challenges, and outline future directions and application prospects for perovskite optoelectronics.","url":"https://doi.org/10.1038/s41467-026-74068-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-74068-y","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.3390/biomimetics10090584","name":"Recent Advances in Optoelectronic Synaptic Devices for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics10090584","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/biomimetics10090584","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1002/adma.202507612","name":"Perovskite Microwires for Room Temperature Exciton-Polariton Neural Network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202507612","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/adma.202507612","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1002/smll.202504024","name":"Co-Stimuli-Driven 2D WSe&lt;sub&gt;2&lt;/sub&gt; Optoelectronic Synapses for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.202504024","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/smll.202504024","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1002/adma.202513904","name":"Multimodal In-Sensor Computing with Dual-Phase Organic Synapses for Wearable Fitness Monitoring.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202513904","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202513904","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1007/s00422-026-01038-4","name":"Brain-inspired energy efficient technologies for next-generation artificial intelligence.","source":"europepmc","abstract":"Since the advent of widely accessible AI tools, AI technology has been in high demand by businesses, academic researchers and individuals. Technology companies are building AI infrastructure at a rapid pace, and these facilities consume vast and growing resources, particularly electricity and water, with significant real and projected climate impacts. There is a need for new research initiatives to support long time horizon efforts to develop energy efficient computing capabilities to support the continued growth of AI infrastructure in a sustainable fashion. Such efficiency is required at both the hardware and software levels. Where can industry turn for examples of ultra-low power, energy efficient computing? We argue here that neurobiological principles offer rich and under-exploited sources of inspiration for energy efficient NeuroAI, and that new partnerships between industry and academia should be developed in this direction.","url":"https://doi.org/10.1007/s00422-026-01038-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s00422-026-01038-4","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1021/acsami.5c22784","name":"Electronically Driven Magnetoelectric Coupling in Co/La:Hf&lt;sub&gt;0.5&lt;/sub&gt;Zr&lt;sub&gt;0.5&lt;/sub&gt;O&lt;sub&gt;2&lt;/sub&gt; Heterostructures for Energy-Efficient Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c22784","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.5c22784","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1038/s42254-025-00918-1","name":"Metrics for spin-based computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s42254-025-00918-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s42254-025-00918-1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.1007/s00422-025-01013-5","name":"Artificial intelligence meets brain theory (again).","source":"europepmc","abstract":"After noting the cybernetic origins of Kybernetik/ Biological Cybernetics, we respond to the Editorial by Fellous et al. (2025) and then analyze talks from the NIH BRAIN NeuroAI 2024 Workshop to get one \"snapshot\" of the state of the conversation between Artificial intelligence (AI) and brain theory (BT). Key recommendations going beyond the earlier Editorial are that: (i) Successes in fitting ANNs to increasingly large neuroscience datasets must not distract us from the quixotic but demanding quest to understand \"how the brain works\" and discover underlying brain (and AI) operating principles. (ii) We must integrate functional and structural analyses in exploring systems of systems, integrating structures (e.g., brain regions, cortical modules) and functions (e.g., schemas for perception, action and cognition) that bridge between neural circuitry and patterns of behavior. (iii) We must study the diversity of intelligences exhibited by animals in their strategies for survival and not only the disembodied employment of language and reasoning. Finally and briefly, we note the urgency of assessing the societal implications of an age of increasingly pervasive human-machine symbiosis.","url":"https://doi.org/10.1007/s00422-025-01013-5","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1007/s00422-025-01013-5","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1002/smll.202501276","name":"Energy Efficient Hybrid Reservoir Computing Using Hf&lt;sub&gt;0.5&lt;/sub&gt;Zr&lt;sub&gt;0.5&lt;/sub&gt;O&lt;sub&gt;2&lt;/sub&gt; Ferroelectric Thin-Film Transistors with an Integrated Optically and Electrically Synaptic Functions.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.202501276","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/smll.202501276","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1038/s41467-025-66295-6","name":"Sub-picojoule-per-bit volitional neuromorphic devices for precise targeting and tracking.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-66295-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-025-66295-6","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1039/d5nh00653h","name":"Surface-enhanced thermal dissipation in 3D vertical resistive memory arrays with top selector transistors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5nh00653h","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d5nh00653h","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1002/advs.202521732","name":"Leaky-Integrate-Fire Neuron via Synthetic Antiferromagnetic Coupling and Spin-Orbit Torque.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202521732","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.202521732","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1002/adma.202511728","name":"Linear and Symmetric Artificial Synapses Driven by Hydrogen Bonding for Accurate and Reliable Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202511728","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/adma.202511728","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1021/acs.chemrev.4c00862","name":"Neural vs Neuromorphic Interfaces: Where Are We Standing?","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.chemrev.4c00862","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acs.chemrev.4c00862","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1039/d5nr02524a","name":"Non-volatile resistive switching characteristics in Cu&lt;sub&gt;2-&lt;i&gt;x&lt;/i&gt;&lt;/sub&gt;S-based memristor.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5nr02524a","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1039/d5nr02524a","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1021/acsami.5c12762","name":"Chloride Ion Vacancy-Mediated Multilevel Bipolar Resistive Switching in Lead-Free All-Inorganic Halide Perovskite Thin Films.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c12762","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c12762","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1186/s40580-025-00522-0","name":"Device-level nonlinearity and temporal memory in optoelectronic reservoir computing.","source":"europepmc","abstract":"Reservoir computing (RC) has emerged as a promising computational paradigm for processing temporally correlated and nonlinear data with low training cost. Among various physical implementations, optoelectronic devices provide a unique opportunity to directly interface light with nonlinear dynamical systems, enriching the reservoir state space through device-intrinsic responses. Light can encode information in wavelength, intensity, and pulse duration, and stimulate multiple nodes in parallel with minimal delay or added power. Recent advances in photodiodes, optically modulated memristors, and phototransistors have revealed device-level pathways to enhance nonlinearity, temporal memory, and node diversity, moving beyond purely electrical control toward hybrid optical-electrical tuning. This review revisits these developments from a device physics perspective, highlighting mechanisms for multi-state generation, bidirectional synaptic weight modulation, and temporal response tailoring. We compare diverse excitation schemes, ranging from wavelength- and intensity-selective photocarrier modulation to con optical-assisted filament control and gate-light co-modulation. We also discuss their impact on reservoir performance in pattern recognition, time-series prediction, and dynamic signal processing. We connect material design, device architecture, and reservoir dynamics to outline emerging strategies for scaling optoelectronic RC. This review provides timely insights for researchers working at the intersection of device engineering and neuromorphic computing.","url":"https://doi.org/10.1186/s40580-025-00522-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1186/s40580-025-00522-0","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1021/acsnano.5c07048","name":"Magnetic Skyrmion Neurons with Homeostasis for Spiking Neural Networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.5c07048","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsnano.5c07048","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1021/acsami.5c14502","name":"Buried Contouring PTCDI-C13 Layer for Interface Engineering in Dual-Function Optical Synaptic and Memory Transistors.","source":"europepmc","abstract":"We present a heterojunction based on the n-type organic semiconductor N , N '-ditridecyl-3,4,9,10-perylenetetracarboxylic diimide (PTCDI-C 13 ) with a PTCDI-C 13 /parylene/PTCDI-C 13 -layered structure, enabling dual functionality as both an optical synaptic and a memory transistor. The device exploits a buried contouring PTCDI-C 13 layer, where the lower PTCDI-C 13 and intervening parylene layers serve distinct functions in charge trapping and modulation. In memory mode, the buried PTCDI-C 13 serves as a floating gate, while the parylene layer acts as a tunneling barrier, facilitating charge storage and controlled electron tunneling under combined optical and electrical stimulations. In synaptic mode, the thickness of the buried PTCDI-C 13 dictates the surface roughness, which is transferred to the parylene layer, forming a textured interface with abundant charge trap sites that modulate the synaptic behavior. By tuning the PTCDI-C 13 thickness, we controlled the interface roughness and trap density ( n t ), achieving optimal performance at 82 nm. The device successfully emulated synaptic plasticity and demonstrated transitions to long-term memory. To further verify its neuromorphic capabilities, our device achieved a recognition accuracy of 91.7% in a Modified National Institute of Standards and Technology-based classification simulation, successfully replicating biological synaptic behavior. Additionally, an electrocardiogram-based simulation demonstrated high classification accuracy while effectively processing dynamic, time-dependent signals. By reliably performing both static image recognition and dynamic biosignal processing, our device showcases its potential for real-time biomedical diagnostics, adaptive AI, and bioinspired computing applications.","url":"https://doi.org/10.1021/acsami.5c14502","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c14502","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.3389/fncom.2025.1597038","name":"Neuromorphic energy economics: toward biologically inspired and sustainable power market design.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2025.1597038","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fncom.2025.1597038","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1039/d5mh00275c","name":"Fully hardware-oriented physical reservoir computing using 3D vertical resistive switching memory with different bottom electrodes.","source":"europepmc","abstract":"Reservoir computing (RC) is a promising machine learning paradigm that processes input data using a fixed random network. However, implementing both reservoir and readout layers typically requires multiple devices and additional fabrication steps. To overcome this, we introduce a fully integrated RC system based on a vertically stacked Ta/Ta 2 O 5 /HfO 2 /W and TiN vertical-resistive random-access memory (VRRAM) structure, which can select short-term and long-term memory in VRRAM structure with different bottom electrodes. The volatile VRRAM serves as a physical reservoir, utilizing its fading memory and nonlinearity to capture temporal dependencies, while the nonvolatile VRRAM functions as a readout network with multi-level storage capability and high linearity. Neuromorphic simulations show that using conductance variations as synaptic weights enables pattern recognition accuracy above 93.14%, successfully replicating biological synaptic behaviors. Finally, the proposed Cyclic RC structure effectively processes temporal patterns, achieving strong performance with an NRMSE of 0.2123 for waveform classification and 0.2377 for Hénon map prediction. These findings underscore the potential of hardware-efficient, short-term memory-based architectures for forecasting nonlinear dynamical systems and advancing neuromorphic computing applications.","url":"https://doi.org/10.1039/d5mh00275c","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1039/d5mh00275c","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1002/advs.202511489","name":"Bifacially Engineered Perovskite-Based Synaptic Memristors Achieve High Linearity and Symmetricity for Accurate and Robust Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202511489","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/advs.202511489","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1021/acsomega.6c02424","name":"Comparative Growth and Functional Integration of CeO&lt;sub&gt;2&lt;/sub&gt; Films via Plasma-Enhanced and Thermal ALD Using a Tailored Cerium Precursor for Artificial Synaptic Devices.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsomega.6c02424","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsomega.6c02424","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1002/adma.202506920","name":"Hardware Implementation of On-Chip Hebbian Learning Through Integrated Neuromorphic Architecture.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202506920","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/adma.202506920","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1039/d5nh00113g","name":"Multifunctional CMOS-integrable and reconfigurable 2D ambipolar tellurene transistors for neuromorphic and in-memory computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5nh00113g","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1039/d5nh00113g","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.34133/research.0758","name":"Memristor-Based Artificial Neural Networks for Hardware Neuromorphic Computing.","source":"europepmc","abstract":"Artificial neural networks have long been studied to emulate the cognitive capabilities of the human brain for artificial intelligence (AI) computing. However, as computational demands intensify, conventional hardware based on transistor and complementary metal oxide semiconductor (CMOS) technology faces substantial limitations due to the separation of memory and processing, a challenge commonly known as the von Neumann bottleneck. In this review, we examine how memristors, which are novel nonvolatile memory devices that exhibit memory-dependent resistance, can be harnessed to build more efficient and scalable neural networks. We provide a comprehensive background on the evolution of neural network models and memristors, as well as introduce the principles of memristive devices, which mimic the dynamic behavior of biological synapses. Various neural network architectures, including convolutional, recurrent, and spiking models, are discussed, highlighting the advantages of integrating memristors for in-memory computing and parallel processing. Our review further examines key mechanisms such as synaptic plasticity, encompassing both long-term potentiation and depression, as well as emerging learning algorithms that leverage memristive behavior. Finally, we identify current challenges, such as achieving ultra-low power consumption, high device uniformity, and seamless system integration, and propose future directions in materials science, device engineering, system integration, and industrialization. These advances suggest that memristor-based neural networks may pave the way for next-generation AI systems that combine low power consumption with high computational performance, ultimately bridging the gap between biological and electronic information processing.","url":"https://doi.org/10.34133/research.0758","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.34133/research.0758","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.3389/fnins.2026.1771436","name":"Energy-efficient traffic sign recognition using directly trained spiking neural networks and population decoding.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2026.1771436","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnins.2026.1771436","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fnins.2026.1814505","name":"Three factor delay learning rules for spiking neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2026.1814505","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnins.2026.1814505","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fnsys.2026.1786729","name":"Information-theoretic and physical constraints on advanced neural signal decoding.","source":"europepmc","abstract":"Recent interdisciplinary research has raised interest in whether non-classical physical principles may impose fundamental constraints on how neural information can be observed, extracted, or decoded. While conventional neuroscience models neural signaling primarily through classical electrochemical processes, a growing body of theoretical literature has speculated that quantum-mechanical concepts-such as coherence, entanglement, or quantum-inspired information processing-may offer alternative perspectives on the limits of neural observability. This article provides a critical and integrative review of theoretical proposals situated at the intersection of neuroscience, quantum biology, and information theory, without assuming the physical realizability of quantum information processing in biological neural systems. We examine conceptual motivations, key physical constraints (including decoherence, thermal noise, and system complexity), and unresolved theoretical challenges that arise when extending classical neural decoding frameworks toward non-classical regimes. Rather than proposing an experimentally validated mechanism for brain decoding, this work focuses on identifying conceptual boundaries, potential misinterpretations, and open questions that must be addressed before non-classical approaches to neural signal decoding can be meaningfully evaluated. Ethical considerations, methodological limitations, and future research directions are discussed to clarify the conditions under which such speculative frameworks may contribute to neuroscience, while avoiding overextension beyond current empirical evidence.","url":"https://doi.org/10.3389/fnsys.2026.1786729","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnsys.2026.1786729","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1038/s41467-026-69592-w","name":"Computing-in-memory architecture for Kolmogorov-Arnold networks based on tunable Gaussian-like memory cells.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-69592-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-69592-w","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.3389/fnins.2025.1570104","name":"Neuromorphic algorithms for brain implants: a review.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2025.1570104","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fnins.2025.1570104","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1021/acsnano.5c07495","name":"Circularly Polarized Light-Responsive Flexible Synapses Based on Supramolecular &lt;i&gt;n&lt;/i&gt;-Type Chiral Organic Single Crystal/&lt;i&gt;p&lt;/i&gt;-Type Polymer Heterojunctions.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.5c07495","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsnano.5c07495","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1021/acsami.5c21475","name":"Tunable Hydrogen Dynamics Under Electrical Bias for Neuromorphic Memory Applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c21475","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.5c21475","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/adma.202517613","name":"Timing-Dependent Spiking Neural Network: Board-Level Hardware Implementation with Photoelectroactive Van der Waals Synapses.","source":"europepmc","abstract":"The rapid growth of unstructured data in applications such as autonomous systems and edge AI underscores the urgent need for energy-efficient, real-time computing exemplified by biological brains, where synaptic weights are adjusted according to the timing of neural spikes, known as spike-timing-dependent plasticity (STDP). This work presents the first experimental realization of a multi-channel timing-dependent spiking neural network (TD-SNN) at the board-level by integrating photoelectroactive synaptic devices with an analog leaky integrate-and-fire (LIF) neuron circuit. The synaptic devices exploit the precise timing dependency between electrical presynaptic and optical postsynaptic spikes to emulate STDP, enabling reversible and bidirectional modulation of synaptic weights through photoelectroactive doping. By engineering the shape of presynaptic pulses, the devices demonstrate diverse biological STDP learning rules, including Hebbian, anti-Hebbian, all-LTP, and all-LTD. Integrated single- and multi-channel networks exhibit self-learning, system-level adaptive, and competitive behaviors. Experimentally extracted STDP parameters are implemented in SNN simulations, where network performance is determined by the long-term potentiation/depression area ratio (LTP/D area ratio, PDR) of the STDP curve. When PDR ≥ 1.25, robust pattern classification is achieved, reaching up to 90.9% accuracy on MNIST tasks. These results mark a milestone in timing-dependent neuromorphic hardware, demonstrating device-level feasibility toward adaptive and real-time learning hardware.","url":"https://doi.org/10.1002/adma.202517613","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202517613","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1002/adma.202504807","name":"Additive Manufacturing of Neuromorphic Systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202504807","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/adma.202504807","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.3390/nano15171365","name":"Gallium Oxide Memristors: A Review of Resistive Switching Devices and Emerging Applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/nano15171365","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/nano15171365","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.3389/frai.2026.1701944","name":"Design of an AI-driven secure 5G-SDN framework with federated reinforcement learning for anomaly detection, mitigation, and attack forensics.","source":"europepmc","abstract":"Introduction The increasing adoption of Software-Defined Networking (SDN) in 5G networks has revolutionized network management. However, this paradigm shift has introduced critical security vulnerabilities, including data-plane anomalies, control-layer intrusions, and Distributed Denial-of-Service (DDoS) attacks. Existing intrusion detection approaches based on Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks suffer from high computational overhead, long detection latency, and limited scalability, making them unsuitable for real-time 5G-SDN environments. Methods This article proposes a novel multi-layered security framework for 5G-SDN that integrates EfficientNet with Knowledge Distillation (KD), Transformer Networks, Spiking Neural Networks (SNNs), Federated Reinforcement Learning (FRL), and blockchain technology. EfficientNet-KD enables lightweight and accurate anomaly detection at the data-plane layer. Transformer networks capture long-range temporal dependencies to enhance control-layer attack detection. SNNs are employed for ultra-low-latency attack classification by mimicking human brain neural processing. FRL supports decentralized and privacy-preserving mitigation across SDN controllers, improving scalability, while blockchain technology ensures the integrity and immutability of attack logs for forensic reliability. Results The proposed framework was evaluated using multiple benchmark datasets, including CICIDS2017, UNSW-NB15, IoT-23, and InSDN. Experimental results demonstrate an average detection accuracy of 97.75%, detection latency of 15 ms, and less than 5% throughput degradation. Each detection consumes only 0.25 J of energy, achieving a 40% reduction in energy usage compared to traditional CNN- and LSTM-based approaches. Discussion The results verify that the proposed framework provides a scalable, energy-efficient, and low-latency intrusion detection and mitigation solution for 5G-SDN environments. By integrating lightweight deep learning, neuromorphic computing, decentralized learning, and blockchain-based security, the framework effectively addresses the limitations of existing methods and offers a robust approach for securing next-generation 5G-SDN networks.","url":"https://doi.org/10.3389/frai.2026.1701944","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/frai.2026.1701944","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3390/ma18184377","name":"Substrate Orientation-Dependent Synaptic Plasticity and Visual Memory in Sol-Gel-Derived ZnO Optoelectronic Devices.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/ma18184377","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/ma18184377","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.34133/research.0916","name":"Advances of Emerging Memristors for In-Memory Computing Applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.34133/research.0916","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.34133/research.0916","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1038/s44172-025-00492-5","name":"Neuromorphic computing for robotic vision: algorithms to hardware advances.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s44172-025-00492-5","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s44172-025-00492-5","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1039/d5mh00324e","name":"Highly-efficient and scalable TrioN (3N0C) synaptic cell for analog process-in-memory.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5mh00324e","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1039/d5mh00324e","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1039/d5nr02690c","name":"Fast prototyping of memristors for ReRAMs and neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5nr02690c","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d5nr02690c","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acsnano.5c18189","name":"Contemporary Challenges in van der Waals 2D Semiconductors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.5c18189","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsnano.5c18189","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.3390/s25196208","name":"Hardware, Algorithms, and Applications of the Neuromorphic Vision Sensor: A Review.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s25196208","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/s25196208","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1021/acsomega.5c04702","name":"Stable Bipolar Resistive Switching in Lead-Free Cs&lt;sub&gt;2&lt;/sub&gt;AgBiBr&lt;sub&gt;6&lt;/sub&gt; Memristors for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsomega.5c04702","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsomega.5c04702","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1038/s41467-025-62306-8","name":"Ultralow energy adaptive neuromorphic computing using reconfigurable zinc phosphorus trisulfide memristors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-62306-8","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-62306-8","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.3390/ma19081660","name":"Recent Progress in Nanophotonics for Green Energy, Medicine, Healthcare, and Optical Computing Applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/ma19081660","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/ma19081660","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1007/s40820-025-01787-0","name":"MXene-Ti&lt;sub&gt;3&lt;/sub&gt;C&lt;sub&gt;2&lt;/sub&gt;T&lt;sub&gt;x&lt;/sub&gt;-Based Neuromorphic Computing: Physical Mechanisms, Performance Enhancement, and Cutting-Edge Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s40820-025-01787-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1007/s40820-025-01787-0","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1002/adma.202506729","name":"Detachable and Reusable: Reinforced π-Ion Film for Modular Synaptic Reservoir Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202506729","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/adma.202506729","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1093/cercor/bhaf295","name":"Building on models-a perspective for computational neuroscience.","source":"europepmc","abstract":"","url":"https://doi.org/10.1093/cercor/bhaf295","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1093/cercor/bhaf295","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1021/acsomega.5c01414","name":"Emerging Nonvolatile Memory Technologies in the Future of Microelectronics.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsomega.5c01414","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsomega.5c01414","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1038/s41467-025-58741-2","name":"Self-organizing neuromorphic nanowire networks as stochastic dynamical systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-58741-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-58741-2","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1002/smtd.202501472","name":"Ultralow-Power Peptide-Based Memristor Enabled by Emulation of Proton-Mediated Synaptic Signaling.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smtd.202501472","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/smtd.202501472","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1021/acsami.5c19999","name":"Asymmetric-Contact ZnON/DNTT Heterojunctions for Tunable Multi-Gaussian Anti-Ambipolar Responses.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c19999","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.5c19999","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1021/acs.nanolett.5c00376","name":"Oscillatory Neural Network with Tunable Frequency for Brain-Inspired Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.5c00376","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acs.nanolett.5c00376","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1002/adma.202518126","name":"Ultrafast Vertical Organic Electrochemical Transistors With Ion-Permeable Conductive Polymer Top Electrodes.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202518126","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202518126","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1021/acsami.5c07597","name":"Phonon-Assisted Charge Trapping and Threshold Voltage Modulation in MoS&lt;sub&gt;2&lt;/sub&gt; FETs with AlO&lt;sub&gt;&lt;i&gt;x&lt;/i&gt;&lt;/sub&gt;N&lt;sub&gt;&lt;i&gt;y&lt;/i&gt;&lt;/sub&gt; Overlayers.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c07597","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c07597","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1021/acs.nanolett.5c03863","name":"Nanoscale Tracking of the High-Temperature Spin-State Transition in LaCoO&lt;sub&gt;3&lt;/sub&gt;.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.5c03863","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acs.nanolett.5c03863","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1002/adma.202517269","name":"Ferroelectrics Hybrids: Harnessing Multifunctionality of 2D Semiconductors in the Post-Moore Era.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202517269","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202517269","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.3389/frobt.2025.1674421","name":"Efficient and real-time perception: a survey on end-to-end event-based object detection in autonomous driving.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/frobt.2025.1674421","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/frobt.2025.1674421","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1002/adma.202521164","name":"Materials and System Design for Self-Decision Bioelectronic Systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202521164","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202521164","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1126/sciadv.adt8227","name":"CMOS-compatible flash-gated thyristor-based neuromorphic module with small area and low energy consumption for in-memory computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.adt8227","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1126/sciadv.adt8227","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1002/adma.202416073","name":"Flexible Neuromorphic Electronics for Wearable Near-Sensor and In-Sensor Computing Systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202416073","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/adma.202416073","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1039/d5mh00038f","name":"Memristive neuromorphic interfaces: integrating sensory modalities with artificial neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5mh00038f","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1039/d5mh00038f","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1021/acsami.5c19731","name":"Interface-Induced Synaptic Performance in CeO&lt;sub&gt;2&lt;/sub&gt;/La&lt;sub&gt;0.8&lt;/sub&gt;Ba&lt;sub&gt;0.2&lt;/sub&gt;MnO&lt;sub&gt;3&lt;/sub&gt; Oxygen Reservoir Junction.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c19731","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c19731","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.3389/fnins.2026.1697163","name":"Evolving spiking neural networks: the role of neuron models and encoding schemes in neuromorphic learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2026.1697163","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnins.2026.1697163","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3390/nano15141130","name":"Memristor-Based Spiking Neuromorphic Systems Toward Brain-Inspired Perception and Computing.","source":"europepmc","abstract":"Threshold-switching memristors (TSMs) are emerging as key enablers for hardware spiking neural networks, offering intrinsic spiking dynamics, sub-pJ energy consumption, and nanoscale footprints ideal for brain-inspired computing at the edge. This review provides a comprehensive examination of how TSMs emulate diverse spiking behaviors—including oscillatory, leaky integrate-and-fire (LIF), Hodgkin–Huxley (H-H), and stochastic dynamics—and how these features enable compact, energy-efficient neuromorphic systems. We analyze the physical switching mechanisms of redox and Mott-type TSMs, discuss their voltage-dependent dynamics, and assess their suitability for spike generation. We review memristor-based neuron circuits regarding architectures, materials, and key performance metrics. At the system level, we summarize bio-inspired neuromorphic platforms integrating TSM neurons with visual, tactile, thermal, and olfactory sensors, achieving real-time edge computation with high accuracy and low power. Finally, we critically examine key challenges—such as stochastic switching origins, device variability, and endurance limits—and propose future directions toward reconfigurable, robust, and scalable memristive neuromorphic architectures.","url":"https://doi.org/10.3390/nano15141130","authors":["Xiangjing Wang","Yixin Zhu","Zili Zhou","Xin Chen","Xiaojun Jia"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/nano15141130","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1088/1361-6528/adad78","name":"Interface effect based nano-scale TiO<sub><i>X</i></sub>vertical synapse device for high-density integration in neuromorphic computing system.","source":"europepmc","abstract":"","url":"https://doi.org/10.1088/1361-6528/adad78","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1088/1361-6528/adad78","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1021/acsnano.5c07260","name":"More-than-Moore Approaches Implemented Using van der Waals Heterostructures.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.5c07260","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsnano.5c07260","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1038/s41467-025-63831-2","name":"Wafer-scale fabrication of memristive passive crossbar circuits for brain-scale neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-63831-2","authors":["Sanghyeon Choi","Sai Sukruth Bezugam","Tinish Bhattacharya","Dongseok Kwon","Dmitri B. Strukov"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-63831-2","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1021/acsnano.5c06027","name":"Fluorinated Self-Assembled Monolayer Ion Receptors for Retentive Analog Synaptic Behavior.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.5c06027","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsnano.5c06027","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.3389/fnins.2025.1687815","name":"SSEL: spike-based structural entropic learning for spiking graph neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2025.1687815","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fnins.2025.1687815","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1021/acsami.5c00027","name":"Artificial Synaptic Properties in Oxygen-Based Electrochemical Random-Access Memory with CeO&lt;sub&gt;2&lt;/sub&gt; Nanoparticle Assembly as Gate Insulator for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c00027","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c00027","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.3389/fnins.2024.1511987","name":"Editorial: From theory to practice: the latest developments in neuromorphic computing applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2024.1511987","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3389/fnins.2024.1511987","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.20944/preprints202412.0532.v1","name":"The Cart-Pole Application as a Benchmark for Neuromorphic Computing","source":"europepmc","abstract":"","url":"https://doi.org/10.20944/preprints202412.0532.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.20944/preprints202412.0532.v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.20944/preprints202410.1758.v1","name":"Neuromorphic Photonic On-chip Computing","source":"preprints","abstract":"Drawing inspiration from biological brain&#039;s energy-efficient information-processing mechanisms, photonic integrated circuits (PIC) have facilitated the development of ultrafast artificial neural networks. This in turn is envisaged to offer potential solutions to the growing demand for artificial intelligence employing machine learning in various domains, from nonlinear optimization and telecommunication to medical diagnosis. At the meantime, silicon photonics has emerged as a mainstream technology for integrated chip based application. However, challenges still need to be addressed in scaling it further for broader applications due to the requirement of co-integration of electronic circuitry for control and calibration. Leveraging physics in algorithms and nanoscale materials holds promise for achieving low-power, miniaturized chips capable of real-time inference and learning. In this back drop, we present the state of the art in neuromorphic photonic computing, focusing primarily on architecture, weighting mechanisms, photonic neurons, and training while giving an over-all view on recent advancements, challenges, and prospects. We also emphasize and high light the need for revolutionary hardware innovations to scale up neuromorphic systems while enhancing energy efficiency and performance.","url":"https://doi.org/10.20944/preprints202410.1758.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.20944/preprints202410.1758.v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.22541/au.173379807.70605903/v1","name":"A Neuromorphic System Based on Spiking-Timing Dependent Plasticity for Evaluating Wakefulness and Anesthesia States using Intracranial EEG Signals","source":"preprints","abstract":"","url":"https://doi.org/10.22541/au.173379807.70605903/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.22541/au.173379807.70605903/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.22541/au.173259411.12324335/v1","name":"DarwinSync: An Adaptive Time Step Execution Framework for Large-Scale Neuromorphic Systems","source":"preprints","abstract":"","url":"https://doi.org/10.22541/au.173259411.12324335/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.22541/au.173259411.12324335/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.20944/preprints202412.1361.v1","name":"State of the Art in Parallel and Distributed Systems: Emerging Trends and Challenges","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202412.1361.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.20944/preprints202412.1361.v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.22541/au.172114593.35310985/v1","name":"Piezoelectric neuron for neuromorphic computing","source":"europepmc","abstract":"Neuromorphic computing has attracted great attention for its massive parallelism and high energy efficiency. As the fundamental components of neuromorphic computing systems, artificial neurons play a key role in information processing. However, the development of artificial neurons that can simultaneously incorporate low hardware overhead, high reliability, high speed, and low energy consumption remains a challenge. To address this challenge, we propose and demonstrate a piezoelectric neuron with a simple circuit structure, consisting of a piezoelectric cantilever, a parallel capacitor, and a series resistor. It operates through the synergy between the converse piezoelectric effect and the capacitive charging/discharging. Thanks to this efficient and robust mechanism, the piezoelectric neuron not only implements critical leaky integrate-and-fire functions (including leaky integration, threshold-driven spiking, all-or-nothing response, refractory period, strength-modulated firing frequency, and spatiotemporal integration), but also demonstrates small cycle-to-cycle and device-to-device variations (~1.9% and ~10.0%, respectively), high endurance (10 10 ), high speed (integration/firing: ~9.6/~0.4 μs), and low energy consumption (~13.4 nJ/spike). Furthermore, spiking neural networks based on piezoelectric neurons are constructed, showing capabilities to implement both supervised and unsupervised learning. This study therefore opens up a new way to develop high-performance artificial neurons by using piezoelectrics, which may facilitate the realization of advanced neuromorphic computing systems.","url":"https://doi.org/10.22541/au.172114593.35310985/v1","authors":["Wenjie Li","Shan Tan","Zhen Fan","Zhiwei Chen","Jiali Ou","Kun Liu","Ruiqiang Tao","Guo Tian","Minghui Qin","Min Zeng","Xubing Lu","Guofu Zhou"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.22541/au.172114593.35310985/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.21203/rs.3.rs-4651980/v1","name":"Robust analogue neuromorphic hardware networks using intrinsic physics-adaptive learning","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4651980/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4651980/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.20944/preprints202407.0025.v2","name":"Survey of Deep Learning Accelerators for Edge and Emerging Computing","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202407.0025.v2","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.20944/preprints202407.0025.v2","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.907Z"},{"id":"doi:10.21203/rs.3.rs-4607889/v1","name":"Design of Memristor Based Modified Synapse Circuit for Low-Power Neuromorphic Computing","source":"preprints","abstract":"Abstract It is high time that brain-inspired or neuromorphic computing must have enough concentration to grow and overcome the computational barrier, which will mimic the biological neuron cell, and its computational abilities will be applied from the neuroscience point of view. We have shown some current candidates from the material to device level for neuromorphic computing and how our proposed memristor-based bridge synapse circuit can emulate the spiking properties of neurons in biological brains with plasticity phenomena such as LTP, LTD and STDP or SRDP (spike rate-dependent plasticity), considering that low power consumption is the primary key to this kind of computing.","url":"https://doi.org/10.21203/rs.3.rs-4607889/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4607889/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.21203/rs.3.rs-5033914/v1","name":"Noise-Aware Training of Neuromorphic Dynamic Device Networks","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-5033914/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-5033914/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.21203/rs.3.rs-3989574/v1","name":"Piezoelectric neuron for neuromorphic computing","source":"europepmc","abstract":"Abstract Neuromorphic computing has attracted great attention for its massive parallelism and high energy efficiency. As the fundamental components of neuromorphic computing systems, artificial neurons play a key role in information processing. However, the development of artificial neurons that can simultaneously incorporate low hardware overhead, high reliability, high speed, and low energy consumption remains a challenge. To address this challenge, we propose and demonstrate a piezoelectric neuron with a simple circuit structure, consisting of a piezoelectric cantilever, a parallel capacitor, and a series resistor. It operates through the synergy between the converse piezoelectric effect and the capacitive charging/discharging. Thanks to this efficient and robust mechanism, the piezoelectric neuron not only implements critical leaky integrate-and-fire functions (including leaky integration, threshold-driven spiking, all-or-nothing response, refractory period, strength-modulated firing frequency, and spatiotemporal integration), but also demonstrates small cycle-to-cycle and device-to-device variations (~1.9% and ~10.0%, respectively), high endurance (10 7 ), high speed (integration/firing: ~9.6/~0.4 μs), and low energy consumption (~13.4 nJ/spike). Furthermore, spiking neural networks based on piezoelectric neurons are constructed, showing capabilities to implement both supervised and unsupervised learning. This study therefore demonstrates the piezoelectric neuron as a simple yet reliable, fast, and energy-efficient artificial neuron, and also showcases its applicability in neuromorphic computing.","url":"https://doi.org/10.21203/rs.3.rs-3989574/v1","authors":["Zhen Fan","Wenjie Li","Tan Shan","Zhiwei Chen","Ou Jiali","Liu Kun","Ruiqiang Tao","Guo Tian","minghui Qin","Min Zeng","Xubing Lu","Guofu Zhou"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-3989574/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.20944/preprints202405.1094.v1","name":"Application of Event Cameras and Neuromorphic Computing to VSLAM: A Survey","source":"preprints","abstract":"Simultaneous Localization and Mapping (SLAM) is a crucial function for most autonomous systems, allowing them to both navigate through and create maps of unfamiliar surroundings. Traditional Visual SLAM, also commonly known as VSLAM, relies on frame-based cameras and structured processing pipelines, which face challenges in dynamic or low-light environments. However, recent advancements in event camera technology and neuromorphic processing offer promising opportunities to overcome these limitations. Event cameras inspired by biological vision systems capture the scenes asynchronously consuming minimal power but with higher temporal resolution. Neuromorphic processors, which are designed to mimic the parallel processing capabilities of the human brain, offer efficient computation for real-time data processing of event-based data streams. This paper provides a comprehensive overview of recent research efforts in integrating event cameras and neuromorphic processors into VSLAM systems. It discusses the principles behind event cameras and neuromorphic processors, highlighting their advantages over traditional sensing and processing methods. Furthermore, an in-depth survey was conducted on state-of-the-art approaches in event-based SLAM, including feature extraction, motion estimation, and map reconstruction techniques. Additionally, the integration of event cameras with neuromorphic processors, focusing on their synergistic benefits in terms of energy efficiency, robustness, and real-time performance was explored. The paper also discusses the challenges and open research questions in this emerging field, such as sensor calibration, data fusion, and algorithmic development. Finally, the potential applications and future directions for event-based SLAM systems are outlined, ranging from robotics and autonomous vehicles to augmented reality.","url":"https://doi.org/10.20944/preprints202405.1094.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.20944/preprints202405.1094.v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1101/2024.05.22.595225","name":"Event Driven Neural Network on a Mixed Signal Neuromorphic Processor for EEG Based Epileptic Seizure Detection","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.05.22.595225","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.05.22.595225","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.20944/preprints202406.1128.v1","name":"Classical and Quantum Physical Reservoir Computing for Onboard Artificial Intelligence Systems: A Perspective","source":"preprints","abstract":"Artificial intelligence (AI) systems of autonomous systems such as drones, robots and self-driving cars may consume up to 50% of total power available onboard, thereby limiting the vehicle’s range of functions and considerably reducing the distance the vehicle can travel on a single charge. Next-generation onboard AI systems need an even higher power since they collect and process even larger amounts of data in real time. This problem cannot be solved using the traditional computing devices since they become more and more power-consuming. In this review article, we discuss the perspectives of development of onboard neuromorphic computers that mimic the operation of a biological brain using nonlinear-dynamical properties of natural physical environments surrounding autonomous vehicles. Previous research also demonstrated that quantum neuromorphic processors (QNPs) can conduct computations with the efficiency of a standard computer while consuming less than 1% of the onboard battery power. Since QNPs is a semi-classical technology, their technical simplicity and low, compared with quantum computers, cost make them ideally suitable for application in autonomous AI system. Providing a perspective view on the future progress in unconventional physical reservoir computing and surveying the outcomes of more than 200 interdisciplinary research works, this article will be of interest to a broad readership, including both students and experts in the fields of physics, engineering, quantum technologies and computing.","url":"https://doi.org/10.20944/preprints202406.1128.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.20944/preprints202406.1128.v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.907Z"},{"id":"doi:10.21203/rs.3.rs-4498702/v1","name":"Negative Photo Conductivity Triggered with Visible Light in Wide Bandgap Oxide-Based Optoelectronic Crossbar Memristive Array for Photograph Sensing and Neuromorphic Computing Applications","source":"preprints","abstract":"Abstract Photoresponsivity studies of wide-bandgap oxide-based devices have emerged as a vibrant and popular research area. Researchers have explored various material systems in their quest to develop devices capable of responding to illumination. In this study, we engineered a mature wide bandgap oxide-based bilayer heterostructure synaptic memristor to emulate the human brain for applications in neuromorphic computing and photograph sensing. The device exhibits advanced electric and electro-photonic synaptic functions, such as long-term potentiation (LTP), long-term depression (LTD), and paired pulse facilitation (PPF), by applying successive electric and photonic pulses. Moreover, the device exhibits exceptional electrical SET and photonic RESET endurance, maintaining its stability for a minimum of 1200 cycles without any degradation. Density functional theory calculations of the band structures provide insights into the conduction mechanism of the device. Based on this memristor array, we developed an autoencoder and convolutional neural network for noise reduction and image recognition tasks, which achieves a peak signal-to-noise ratio of 562 and high accuracy of 84.23%, while consuming lower energy by four orders of magnitude compared with the Tesla P40 GPU. This groundbreaking research not only opens doors for the integration of our device into image processing but also represents a significant advancement in the realm of in-memory computing and photograph sensing features in a single cell.","url":"https://doi.org/10.21203/rs.3.rs-4498702/v1","authors":["Dayanand Kumar","Hanrui Li","Amit Singh","Manoj Kumar Rajbhar","Abdul Momin Syed","Hoonkyung Lee","Nazek El-Atab"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4498702/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.20944/preprints202405.1176.v1","name":"Simple Dynamic Visualization of Memristor-Based Synaptic Plasticity in a Simulated Neural Network","source":"europepmc","abstract":"This article presents a novel computational approach to visualizing memristor dynamics within a simulated neural network. Memristors, known for their ability to emulate synaptic plasticity due to their variable resistance characteristics, are key components in neuromorphic computing and hold potential for advancing our understanding of neural processes. Our study introduces a sophisticated memristor model that incorporates non-linear resistance changes, simulating the complex behavior of synaptic connections in a neural network.The neural network, consisting of multiple interconnected neurons with memristor-based synapses, is subjected to a series of electrical stimuli. Each memristor's resistance is modulated in response to the applied voltage, mimicking the synaptic weight adjustments that occur during learning and memory formation in biological neural networks. To effectively illustrate these changes, we employ a high-contrast color mapping scheme, where the varying resistance of each memristor is represented by distinct colors, providing a clear and intuitive visualization of synaptic modifications over time.Our simulation runs through multiple iterations, demonstrating how synaptic weights evolve in response to different input patterns. The use of an extended voltage range and increased scaling factors ensures pronounced changes in memristance, enhancing the visibility of synaptic adaptations. The resulting visualizations offer a compelling representation of how memristors can mimic the dynamic nature of biological synapses, contributing to the field of neuromorphic engineering and deepening our comprehension of neural mechanisms underlying learning and memory.This work not only showcases the potential of memristors in simulating neural behavior but also provides a valuable educational tool for illustrating complex concepts in neuroscience and neuromorphic computing. The insights gained from this study pave the way for further exploration into the development of advanced neural network models and the design of memristor-based computing systems.","url":"https://doi.org/10.20944/preprints202405.1176.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.20944/preprints202405.1176.v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1101/2024.09.24.614728","name":"BrainScale, Enabling Scalable Online Learning in Spiking Neural Networks","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.09.24.614728","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.09.24.614728","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.06.13.24308876","name":"Online Epileptic Seizure Detection in Long-term iEEG Recordings Using Mixed-signal Neuromorphic Circuits","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.06.13.24308876","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.06.13.24308876","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.22541/au.173168130.04788192/v1","name":"Edge of Chaos Kernel and dynamic analysis of Hopfield neural network with locally-active memristor","source":"europepmc","abstract":"","url":"https://doi.org/10.22541/au.173168130.04788192/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.22541/au.173168130.04788192/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.21203/rs.3.rs-3982214/v1","name":"Emulating Brain-like Rapid Learning in Neuromorphic Edge Computing","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3982214/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-3982214/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.21203/rs.3.rs-4190143/v1","name":"Gate tunable MoS2 memristive neuron for early fusion multimodal spiking neural network","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4190143/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4190143/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.20944/preprints202406.1275.v1","name":"Amyloid, a Jekyll and Hyde Molecule Inducing Neuronal Decline and Cognitive Dysfunction is Also a Unique Molecular Template used in Nano-electronics, Light Capture Photovoltaics, and Biosensors in Neuromorphic Computing.","source":"preprints","abstract":"Amyloid self-assembled from amyloid peptides βΑ40 or βΑ42 is notorious for its neurotoxic effects in plaque and neurofibrillary tangle formations leading to neuron dysfunction and diseases of cognitive decline (e.g. Alzheimer’s, Parkinson’s and Huntington&amp;#039;s disease). This contrasts with so-called functional amyloids which are non-toxic ordered template structures amenable to applications in tissue engineering. Amyloid fibrils of variable morphology including long and hollow fibres and flattened tube and spiral ribbon-like structures have been used in engineering applications in nano-biology. Protein assemblies based on amyloid core structures display diverse biological functionalities could be applied in futuristic self-assembling biomaterials in nano-electronics. These possibilities have revolutionized the development of next generation computers and biosensors, ultracapacitors, memristors, actuators, molecular switches and could also be used to develop artificial synapses. Amyloid fibril assemblies have also been used in photoelectric and photon capture light harvesting technologies and been applied in innovative nano-photoelectronics and photovoltaics. Hybrid Aβ(16–22)-α-synuclein amyloid fibrils also exhibit light-harvesting and electron-transfer properties. Engineered amyloid assemblies are thus facilitating innovative futuristic advances in nano-technology. Furthermore, with a better understanding of amyloid fibril assembly processes it may be possible to develop therapeutic methods that prevent the toxic build up of this polymer in brain tissues that leads to diseases of cognitive decline. With the ever-expanding prevalence of these diseases in the ageing general global population, there certainly is a clear and present need to find a remedy for these debilitating conditions.","url":"https://doi.org/10.20944/preprints202406.1275.v1","authors":["James Melrose","Margaret M Smith"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.20944/preprints202406.1275.v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.20944/preprints202405.2083.v1","name":"Analog Implementation of a Spiking Neuron with Memristive Synapses for Deep Learning Processing","source":"preprints","abstract":"Analog neuromorphic prototyping is crucial for creating spiking neuron models that use memristive devices as synapses to design integrated circuits that leverage on-chip parallel deep neural networks. These models mimic how biological neurons in the brain communicate through electrical potentials. Doing so enables more powerful and efficient functionality than traditional artificial neural networks that run on von Neumann computers or graphic processing unit-based platforms. This technology can accelerate deep learning processing, aiming to exploit the brain’s unique features of asynchronous and event-driven processing by leveraging neuromorphic hardware’s inherent parallelism and analog computation capabilities. Therefore, this paper presents the design and implementation of a leaky integrate and fire neuron prototype implemented with commercially available components on a PCB board. Simulations conducted in LTSpice agree well with the electrical test measurements. The results demonstrate that this design can be employed to interconnect many boards to build layers of physical spiking neurons, interconnected with spike-timing-dependent plasticity as the primary learning algorithm, contributing to the realization of experiments in the early stage of adopting neuromorphic computing.","url":"https://doi.org/10.20944/preprints202405.2083.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.20944/preprints202405.2083.v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.21203/rs.3.rs-3976308/v1","name":"Detection of Pipeline Leaks using BiopiezoelectricEnergy Harvesting Sensors via RecurrenceQuantification and Neuromorphic Computing","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3976308/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-3976308/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.21203/rs.3.rs-3647379/v1","name":"Linear, symmetric, self-selecting 14-bit molecular memristors","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3647379/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-3647379/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.21203/rs.3.rs-5008392/v1","name":"Reduced-order adaptive synchronization in a chaotic neural network with parameter mismatch: A dynamical system vs. machine learning approach","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-5008392/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-5008392/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.21203/rs.3.rs-3839002/v1","name":"Multilayer Ferromagnetic Spintronic Devices for Neuromorphic Computing Applications","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3839002/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-3839002/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.21203/rs.3.rs-3978928/v1","name":"Tunable Anti-Ambipolar Vertical Bilayer Organic Electrochemical Transistor enable Neuromorphic Retinal Pathway","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3978928/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-3978928/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.21203/rs.3.rs-3930064/v1","name":"Compact artificial neurons with time-to-first-spike coding for fast and energy-efficient federated neuromorphic computing","source":"preprints","abstract":"Abstract Federated learning combined with Spiking Neural Networks (SNNs) provides a reliable and lightweight solution for privacy and energy constraints in billions of edge devices. However, the current rate-coding in SNNs has high latency and leads to increased power consumption. In this study, we develop a federated neuromorphic learning (FNL) system based on temporal coding to process edge information quickly and efficiently using compact neurons with time-to-first spike (TTFS) coding. These neurons are demonstrated using the volatile threshold switching characteristics of VO2 memristors. We implemented an FNL system for edge pattern recognition in hardware using these compact neurons. Notably, the memristor-based edge device with TTFS-coding shows 330× and 76× improvements in interference speed and energy consumption, respectively, compared to the conventional rate-coding scheme. Furthermore, a multimodal FNL system with TTFS-coding is demonstrated to process audio-visual vehicle signals from edge traffic scenes, with spike numbers for each iteration of edge devices being 26× lower compared to the rate-coding scheme. Our system, incorporating FNL and TTFS-coding, can facilitate the development of next-generation edge artificial intelligence requiring extremely low latency and power.","url":"https://doi.org/10.21203/rs.3.rs-3930064/v1","authors":["Rui Yang","Zhiyuan Li","Jiaping Yao","Beining Zhang","Zhongshao Li","Wei Tang","Junjie Gong","Yongfei Li","Xun Cao","Zhongrui Wang","Xiangshui Miao"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-3930064/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.21203/rs.3.rs-5006614/v1","name":"Dual-Role Ion Dynamics in Ferroionic CuInP2S6: Insights into the Transition and Boundary from Ferroelectric to Ionic Switching Mechanisms","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-5006614/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-5006614/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.21203/rs.3.rs-4379130/v1","name":"Exploring the Programmability of Autocatalytic Chemical Reaction Networks","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4379130/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4379130/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1101/2024.06.30.599443","name":"Neural Heterogeneity Enhances Reliable Neural information Processing: Local Sensitivity and Globally Input-slaved Transient Dynamics","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.06.30.599443","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.06.30.599443","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.21203/rs.3.rs-4666201/v1","name":"On-chip graphene photodetectors with a nonvolatile p−i−n homojunction","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4666201/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4666201/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.21203/rs.3.rs-4780561/v1","name":"Multiple sliding ferroelectricity of rhombohedral-stacked InSe for reconfigurable photovoltaics and imaging applications","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4780561/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4780561/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.21203/rs.3.rs-4101407/v1","name":"Reconfigurable Two-dimensional Floating Gate Field-effect Transistors for Highly Integrated In-memory Computing","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4101407/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4101407/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.21203/rs.3.rs-4678249/v1","name":"Experimental realisation of a universal inverse-design magnonic device","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4678249/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4678249/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.21203/rs.3.rs-4365235/v1","name":"Pattern recognition using spiking antiferromagnetic neurons","source":"preprints","abstract":"Abstract Spintronic devices offer a promising avenue for the development of nanoscale, energy-efficient artificial neurons for neuromorphic computing. It has previously been shown that with antiferromagnetic (AFM) oscillators, ultra-fast spiking artificial neurons can be made that mimic many unique features of biological neurons. In this work, we train an artificial neural network of AFM neurons to perform pattern recognition. A simple machine learning algorithm called spike pattern association neuron (SPAN), which relies on the temporal position of neuron spikes, is used during training. In under a microsecond of physical time, the AFM neural network is trained to recognize symbols composed from a grid by producing a spike within a specified time window. We further achieve multi-symbol recognition with the addition of an output layer to suppress undesirable spikes. Through the utilization of AFM neurons and the SPAN algorithm, we create a neural network capable of high-accuracy recognition with overall power consumption on the order of picojoules.","url":"https://doi.org/10.21203/rs.3.rs-4365235/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4365235/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.21203/rs.3.rs-4003267/v1","name":"Flat band, tunable chiral anomaly and pitchfork bifurcation in a honeycomb lattice","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4003267/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4003267/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.21203/rs.3.rs-4575664/v1","name":"Flexible Self-rectifying Synapse Array for Energy-efficient Edge Multiplication in Electrocardiogram Diagnosis","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4575664/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4575664/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.20944/preprints202402.1107.v1","name":"Enabling Efficient On-Edge Spiking Neural Network Acceleration with Highly Flexible FPGA Architectures","source":"europepmc","abstract":"","url":"https://doi.org/10.20944/preprints202402.1107.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.20944/preprints202402.1107.v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.21203/rs.3.rs-4374465/v1","name":"Anomalous Gate-tunable Capacitance in Graphene Moiré Heterostructures","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4374465/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4374465/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.21203/rs.3.rs-3981743/v1","name":"Spintronic Memtransistor Leaky Integrate and Fire Neuron for Spiking Neural Networks","source":"preprints","abstract":"Abstract Spintronic devices, -based on the domain walls and skyrmions, Spintronic devices have shown significant potential for applications in energy-efficient data storage and beyond CMOS computing architectures. Based on the magnetic multilayer spintronic devices, we demonstrate the magnetic field-gated and current-controlled Leaky integrate and fire neuron characteristics for the spiking neural network applications. The LIF characteristics are controlled by the current pulses, which drive the domain wall motion, and an external magnetic field is used as the bias to tune the firing properties of the neuron. Thus, the device works like a gate-controlled LIF neuron, acting like a spintronic Mem-transistor device. The current and magnetic field-controlled neuron spiking rate is shown. We developed a LIF neuron model based on the measured characteristics to show the device's integration in the system-level SNNs. We extend the study and propose a scaled version of the demonstrated device with a multilayer spintronic domain wall magnetic tunnel junction as a LIF neuron. using the combination of SOT and the variation of the demagnetization energy across the thin film, the modified leaky integrate and fire LIF neuron characteristics are realized in the proposed devices. Finally, we integrate the measured and simulated neuron models in the 3-layer spiking neural network (SNN) and convolutional spiking neural network CSNN framework to test these spiking neuron models for classification of the MNIST and FMNIST datasets. In both architectures, the network achieves classification accuracy above 96%. Considering the good system-level performance, mem-transistor properties, and promise for scalability. The presented devices show an excellent alternative for neuromorphic computing applications.","url":"https://doi.org/10.21203/rs.3.rs-3981743/v1","authors":["Aijaz Lone","Meng Tang","Daniel Norouzzadeh Rahimi","xuecui zou","Dong-xing Zheng","Hossein Fariborzi","Xixiang Zhang","Gianluca Setti"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-3981743/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.22541/au.170992887.75772000/v1","name":"Metal Oxide Resistive Memory Modeling with Physical Current Equation","source":"preprints","abstract":"","url":"https://doi.org/10.22541/au.170992887.75772000/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.22541/au.170992887.75772000/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.20944/preprints202405.0155.v1","name":"Prediction of Hippocampal Signals in Mice Using a Deep Learning Approach for Neurohybrid Technology Applications","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202405.0155.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.20944/preprints202405.0155.v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.21203/rs.3.rs-3993700/v1","name":"Actor-Critic Networks with Analogue Memristors Mimicking Reward-Based Learning","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3993700/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-3993700/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.20944/preprints202403.0827.v1","name":"Artificial Neuron Based on the Bloch-Point Domain Wall in Ferromagnetic Nanowires","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202403.0827.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.20944/preprints202403.0827.v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.21203/rs.3.rs-3999016/v1","name":"Pressure-Tuned Ideal P-Type Schottky Contacts","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3999016/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-3999016/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.21203/rs.3.rs-3929576/v1","name":"Type-printable photodetector arrays for multichannel meta-infrared imaging","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3929576/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-3929576/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.21203/rs.3.rs-4135062/v1","name":"All-magnonic repeater based on bistability","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4135062/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4135062/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1101/2024.10.19.619194","name":"Competitive interactions shape brain dynamics and computation across species","source":"preprints","abstract":"Adaptive cognition relies on cooperation across anatomically distributed brain circuits. However, specialised neural systems are also in constant competition for limited processing resources. How does the brain's network architecture enable it to balance these cooperative and competitive tendencies? Here we use computational whole-brain modelling to examine the dynamical and computational relevance of cooperative and competitive interactions in the mammalian connectome. Across human, macaque, and mouse we show that the architecture of the models that most faithfully reproduce brain activity, consistently combines modular cooperative interactions with diffuse, long-range competitive interactions. The model with competitive interactions consistently outperforms the cooperative-only model, with excellent fit to both spatial and dynamical properties of the living brain, which were not explicitly optimised but rather emerge spontaneously. Competitive interactions in the effective connectivity produce greater levels of synergistic information and local-global hierarchy, and lead to superior computational capacity when used for neuromorphic computing. Altogether, this work provides a mechanistic link between network architecture, dynamical properties, and computation in the mammalian brain.","url":"https://doi.org/10.1101/2024.10.19.619194","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.10.19.619194","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:22.907Z"},{"id":"doi:10.21203/rs.3.rs-4807328/v1","name":"Ultrabroadband Integrated Electro-Optic Frequency Comb in Lithium Tantalate","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4807328/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4807328/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.21203/rs.3.rs-4323148/v1","name":"AlGaN/AlN heterostructures: an emerging platform for nonlinear integrated photonics","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4323148/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4323148/v1","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.1101/2023.03.25.534198","name":"A neuronal least-action principle for real-time learning in cortical circuits","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.03.25.534198","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.03.25.534198","addedAt":"2026-09-01T01:48:19.718Z","updatedAt":"2026-09-01T01:48:20.901Z"},{"id":"doi:10.23919/date.2018.8341988","name":"Exploring the opportunity of implementing neuromorphic computing systems with spintronic devices","source":"crossref","abstract":"","url":"https://doi.org/10.23919/date.2018.8341988","authors":["Bonan Yan","Fan Chen","Yaojun Zhang","Chang Song","Hai Li","Yiran Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-04-23T23:20:11Z","doi":"10.23919/date.2018.8341988","addedAt":"2026-09-01T01:48:19.728Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.5935/jetia.v11i51.1425","name":"The Advances in Neuromorphic Computing and Brain-Inspired Systems (ANCBIS)","source":"crossref","abstract":"","url":"https://doi.org/10.5935/jetia.v11i51.1425","authors":["Bharath Sanjai Lordwin D J3","G Ponseka","K DanielRaj"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-05T17:37:41Z","doi":"10.5935/jetia.v11i51.1425","addedAt":"2026-09-01T01:48:19.728Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1109/vlsitechnology18217.2020.9265110","name":"Proposal and Experimental Demonstration of Reservoir Computing using Hf0.5Zr0.5O2/Si FeFETs for Neuromorphic Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/vlsitechnology18217.2020.9265110","authors":["E. Nako","K. Toprasertpong","R. Nakane","Z. Wang","Y. Miyatake","M. Takenaka","S. Takagi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-02T23:04:34Z","doi":"10.1109/vlsitechnology18217.2020.9265110","addedAt":"2026-09-01T01:48:19.728Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.53975/updh-78lg","name":"What does it mean to represent? Mental representations as falsifiable memory patterns","source":"crossref","abstract":"Representation is a key notion in neuroscience and artificial intelligence (AI). However, a longstanding philosophical debate highlights that specifying what counts as representation is trickier than it seems. With this brief opinion paper we would like to bring the philosophical problem of representation into attention and provide an implementable solution. We note that causal and teleological approaches often assumed by neuroscientists and engineers fail to provide a satisfactory account of representation. We sketch an alternative according to which representations correspond to inferred latent structures in the world, identified on the basis of conditional patterns of activation. These structures are assumed to have certain properties objectively, which allows for planning, prediction, and detection of unexpected events. We illustrate our proposal with the simulation of a simple neural network model. We believe this stronger notion of representation could inform future research in neuroscience and AI.","url":"https://doi.org/10.53975/updh-78lg","authors":["Eloy Parra-Barrero","Yulia Sandamirskaya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-17T00:39:27Z","doi":"10.53975/updh-78lg","addedAt":"2026-09-01T01:48:19.728Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1109/candarw53999.2021.00026","name":"Preliminary Evaluation for Multi-domain Spike Coding on Memcapacitive Neuromorphic Circuit","source":"crossref","abstract":"","url":"https://doi.org/10.1109/candarw53999.2021.00026","authors":["Reon Oshio","Atsushi Sawada","Mutsumi Kimura","Renyuan Zhang","Yasuhiko Nakashima"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-21T21:08:13Z","doi":"10.1109/candarw53999.2021.00026","addedAt":"2026-09-01T01:48:19.728Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1109/icnc52316.2021.9608255","name":"sentiment analysis on massive open online course evaluation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc52316.2021.9608255","authors":["Xiaowei Yan","Guangmin Li","Qian Li","Jiejie Chen","Wenjing Chen","Fan Xia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-29T20:59:32Z","doi":"10.1109/icnc52316.2021.9608255","addedAt":"2026-09-01T01:48:19.728Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1109/icons69015.2025.00030","name":"Propeller-Based Drone Tracking with a Moving Neuromorphic Camera","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons69015.2025.00030","authors":["Kevin Murray","Cameron Nowzari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-21T21:07:17Z","doi":"10.1109/icons69015.2025.00030","addedAt":"2026-09-01T01:48:19.728Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1109/icnc59488.2023.10462751","name":"Anti-Synchronization in Fixed/Prescribed-Time for BAM Memristive Neural Networks with Time-Varying Delays","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462751","authors":["Jinrong Yang","Guici Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462751","addedAt":"2026-09-01T01:48:19.728Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1088/2634-4386/ac4339","name":"Performance of reservoir computing in a random network of single-walled carbon nanotubes complexed with polyoxometalate","source":"crossref","abstract":"Abstract Molecular neuromorphic devices are composed of a random and extremely dense network of single-walled carbon nanotubes (SWNTs) complexed with polyoxometalate (POM). Such devices are expected to have the rudimentary ability of reservoir computing (RC), which utilizes signal response dynamics and a certain degree of network complexity. In this study, we performed RC using multiple signals collected from a SWNT/POM random network. The signals showed a nonlinear response with wide diversity originating from the network complexity. The performance of RC was evaluated for various tasks such as waveform reconstruction, a nonlinear autoregressive model, and memory capacity. The obtained results indicated its high capability as a nonlinear dynamical system, capable of information processing incorporated into edge computing in future technologies.","url":"https://doi.org/10.1088/2634-4386/ac4339","authors":["Megumi Akai-Kasaya","Yuki Takeshima","Shaohua Kan","Kohei Nakajima","Takahide Oya","Tetsuya Asai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-15T22:12:23Z","doi":"10.1088/2634-4386/ac4339","addedAt":"2026-09-01T01:48:19.728Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.11159/cist24.002","name":"Reliable AI: From Legal Requirements to Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.11159/cist24.002","authors":["Gitta Kutyniok"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-11T03:36:15Z","doi":"10.11159/cist24.002","addedAt":"2026-09-01T01:48:19.728Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1186/s43593-025-00087-9","name":"Ultrafast neuromorphic computing driven by polariton nonlinearities","source":"crossref","abstract":"Abstract Neuromorphic computing offers a promising approach to artificial intelligence by mimicking biological neural networks to perform complex tasks efficiently. While software-based simulations have demonstrated the potential of neuromorphic architectures, a physical platform is crucial to fully realize its computational advantages. Herein, we present the first demonstration of perovskite microcavity exciton polaritons as a platform for reservoir computing-based artificial neural networks. By leveraging the nonlinear response properties of exciton polaritons, we developed a neuromorphic computing architecture capable of performing classification tasks with single-step training, eliminating the need for iterative algorithms like backpropagation. Applying this system to a handwritten digit recognition task, we achieve 92% classification accuracy at room temperature. Notably, we also show that the system is dynamically nonlinear, further enhancing the potential to improve classification efficiency and address more complex tasks. Our findings advocate the promising capabilities of perovskite exciton polaritons as energy-efficient, ultrafast response platforms for artificial intelligence, paving the way for next-generation computational technologies.","url":"https://doi.org/10.1186/s43593-025-00087-9","authors":["Yusong Gan","Ying Shi","Sanjib Ghosh","Haiyun Liu","Huawen Xu","Qihua Xiong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-01T19:04:03Z","doi":"10.1186/s43593-025-00087-9","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1515/9783111545950-006","name":"1026 Light-matter interaction: photodetectors, solar cells, LEDs, lasers, and meta-structures","source":"crossref","abstract":"","url":"https://doi.org/10.1515/9783111545950-006","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-06T19:15:47Z","doi":"10.1515/9783111545950-006","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1002/aelm.202500713","name":"Electrode‐Engineered Dual‐Mode Multifunctional Lead‐Free Perovskite Optoelectronic Memristors for Neuromorphic Computing","source":"crossref","abstract":"ABSTRACT Memristive devices based on halide perovskites hold strong promise to provide energy‐efficient systems for the Internet of Things (IoT); however, lead (Pb) element should be minimized or ideally replaced. Herein, we introduce a multifunctional device based on AgBiI 4 Pb‐free perovskite as the active layer in a normal n‐i‐p solar cell configuration that exhibitss multiple mode‐dependent neuromorphic functions. Specifically, through electrode engineering, we show a selection between volatile or non‐volatile memristive switching when the Au top electrode is replaced by Ag. The volatile device having an Au top electrode can be used for emulating threshold‐dependent artificial neuron firing processes, while the non‐volatile device with Ag pads can emulate numerous synaptic protocols (LTP/LTD, PPF, STDP, SRDP, LTM, STM). Both volatile (V TH = −0.86 V) and non‐volatile modes possess switching low voltages &lt;1 V, while the ON/OFF ratio of the non‐volatile system is 10 4 with a cycling endurance of 10 3 cycles and state retention of 10 3 s. Further investigation reveals that electrode type affects the conduction mechanism, as ion charge trapping and detrapping govern threshold switching with activation energy E A ≈ 0.7 eV, while the formation/rupture of Ag filaments is responsible for non‐volatile switching. The response in both modes of devices can be tuned by light, while associative learning by emulating Pavlovian learning is demonstrated. Finally, experimental non‐volatile data were used for MNIST and Fashion‐MNIST classification, achieving 97.11% and 87.56% accuracy, respectively. Our work provides insights into electrode‐engineered mode control in lead‐free perovskite systems capable for a concurrent energy harvesting (PCE ∼1%) toward self‐powered systems for neuromorphic edge computing.","url":"https://doi.org/10.1002/aelm.202500713","authors":["Michalis Loizos","Konstantinos Rogdakis","Konstantinos Chatzimanolis","Katerina Anagnostou","Emmanuel Kymakis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-26T09:02:36Z","doi":"10.1002/aelm.202500713","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/icnc59488.2023.10462728","name":"Distributed Power Distribution Management in AC Microgrids Using Game Theoretical Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462728","authors":["Leping Sun","Weidong Chen","Xiaoxuan Guo","Shuai Han","Ning Wu","Yuhong Mo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462728","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1109/mm.2022.3195634","name":"Neuromorphic Near-Sensor Computing: From Event-Based Sensing to Edge Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mm.2022.3195634","authors":["Ali Safa","Jonah Van Assche","Mark Daniel Alea","Francky Catthoor","Georges G.E. Gielen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-08-04T20:34:37Z","doi":"10.1109/mm.2022.3195634","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1109/icnc59488.2023.10462772","name":"Finite-Level Quantized Iterative Learning Control for a Class of Fuzzy Cellular Neural Networks Based on Encoding-Decoding Mechanism","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462772","authors":["Yuhan Yang","Dan Ma","Wenjun Xiong","Xichen Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462772","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/adma.202470045","name":"Reconfigurable Cascaded Thermal Neuristors for Neuromorphic Computing (Adv. Mater. 6/2024)","source":"crossref","abstract":"","url":"https://doi.org/10.1002/adma.202470045","authors":["Erbin Qiu","Yuan‐Hang Zhang","Massimiliano Di Ventra","Ivan K. Schuller"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-08T03:50:42Z","doi":"10.1002/adma.202470045","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1117/12.2509838","name":"Advances in photonic neuromorphic computing (Conference Presentation)","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.2509838","authors":["Volker J. Sorger","Jonathan K. George","Armin Mehrabian","Bhavin Shastri","Tarek El-Ghazawi","Paul R. Prucnal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-03-04T16:56:12Z","doi":"10.1117/12.2509838","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.21203/rs.3.rs-3644668/v1","name":"Intelligent machines work in unstructured environments by differential neuromorphic computing","source":"preprints","abstract":"Abstract Efficient operation of intelligent machines in the real world requires methods that allow them to understand and predict the uncertainties presented by the unstructured environments with good accuracy, scalability and generalization, similar to humans. Current methods rely on pretrained networks instead of continuously learning from the dynamic signal properties of working environments and suffer inherent limitations, such as data-hungry procedures, and limited generalization capabilities. Herein, we present a memristor-based differential neuromorphic computing, perceptual signal processing and learning method for intelligent machines. The main features of environmental information such as amplification (&gt; 720%) and adaptation (&lt; 50%) of mechanical stimuli encoded in memristors, are extracted to obtain human-like processing in unstructured environments. The developed method takes advantage of the intrinsic multi-state property of memristors and exhibits good scalability and generalization, as confirmed by validation in two different application scenarios: object grasping and autonomous driving. In the former, a robot hand experimentally realizes safe and stable grasping through fast learning (in ~ 1 ms) the unknown object features (e.g., sharp corner and smooth surface) with a single memristor. In the latter, the decision-making information of 10 unstructured environments in autonomous driving (e.g., overtaking cars, pedestrians) is accurately (94%) extracted with a 40×25 memristor array. By mimicking the intrinsic nature of human low-level perception mechanisms, the electronic memristive neuromorphic circuit-based method, presented here shows the potential for adapting to diverse sensing technologies and helping intelligent machines generate smart high-level decisions in the real world.","url":"https://doi.org/10.21203/rs.3.rs-3644668/v1","authors":["Luigi Occhipinti","Shengbo Wang","Shuo Gao","Chenyu Tang","Edoardo Occhipinti","Cong Li","Shurui Wang","Jiaqi Wang","Hubin Zhao","Guohua Hu","Arokia Nathan","Ravinder Dahiya"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-3644668/v1","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1088/2634-4386/ad4209","name":"Continuous adaptive nonlinear model predictive control using spiking neural networks and real-time learning","source":"crossref","abstract":"Abstract Model predictive control (MPC) is a prominent control paradigm providing accurate state prediction and subsequent control actions for intricate dynamical systems with applications ranging from autonomous driving to star tracking. However, there is an apparent discrepancy between the model’s mathematical description and its behavior in real-world conditions, affecting its performance in real-time. In this work, we propose a novel neuromorphic (brain-inspired) spiking neural network for continuous adaptive non-linear MPC. Utilizing real-time learning, our design significantly reduces dynamic error and augments model accuracy, while simultaneously addressing unforeseen situations. We evaluated our framework using real-world scenarios in autonomous driving, implemented in a physics-driven simulation. We tested our design with various vehicles (from a Tesla Model 3 to an Ambulance) experiencing malfunctioning and swift steering scenarios. We demonstrate significant improvements in dynamic error rate compared with traditional MPC implementation with up to 89.15% median prediction error reduction with 5 spiking neurons and up to 96.08% with 5,000 neurons. Our results may pave the way for novel applications in real-time control and stimulate further studies in the adaptive control realm with spiking neural networks.","url":"https://doi.org/10.1088/2634-4386/ad4209","authors":["Raz Halaly","Elishai Ezra Tsur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-23T22:25:55Z","doi":"10.1088/2634-4386/ad4209","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1016/b978-0-12-821184-7.00027-x","name":"Neuromorphic vision networks for face recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-12-821184-7.00027-x","authors":["Akshay Kumar Maan","Alex James"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-06-25T07:24:09Z","doi":"10.1016/b978-0-12-821184-7.00027-x","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1007/978-3-031-71097-1_8","name":"Implementation Strategies","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-71097-1_8","authors":["Ali Akbar Firoozi","Ali Asghar Firoozi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-12T15:02:54Z","doi":"10.1007/978-3-031-71097-1_8","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1109/tsg.2020.3043782","name":"Power System Disturbance Classification With Online Event-Driven Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tsg.2020.3043782","authors":["Kaveri Mahapatra","Sen Lu","Abhronil Sengupta","Nilanjan Ray Chaudhuri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-10T21:08:32Z","doi":"10.1109/tsg.2020.3043782","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1109/icmts.2018.8383757","name":"Modeling split-gate flash memory cell for advanced neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icmts.2018.8383757","authors":["Mandana Tadayoni","Santosh Hariharan","Steven Lemke","Thibaut Pate-Cazal","Bernard Bertello","Vipin Tiwari","Nhan Do"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-06-21T21:35:36Z","doi":"10.1109/icmts.2018.8383757","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1007/s40820-025-01705-4","name":"Low-Power Memristor for Neuromorphic Computing: From Materials to Applications","source":"europepmc","abstract":"Abstract As an emerging memory device, memristor shows great potential in neuromorphic computing applications due to its advantage of low power consumption. This review paper focuses on the application of low-power-based memristors in various aspects. The concept and structure of memristor devices are introduced. The selection of functional materials for low-power memristors is discussed, including ion transport materials, phase change materials, magnetoresistive materials, and ferroelectric materials. Two common types of memristor arrays, 1T1R and 1S1R crossbar arrays are introduced, and physical diagrams of edge computing memristor chips are discussed in detail. Potential applications of low-power memristors in advanced multi-value storage, digital logic gates, and analogue neuromorphic computing are summarized. Furthermore, the future challenges and outlook of neuromorphic computing based on memristor are deeply discussed.","url":"https://doi.org/10.1007/s40820-025-01705-4","authors":["Zhipeng Xia","Xiao Sun","Zhenlong Wang","Jialin Meng","Boyan Jin","Tianyu Wang"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1007/s40820-025-01705-4","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1109/tencon61640.2024.10903095","name":"Cell-Stitching for Analog Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tencon61640.2024.10903095","authors":["Pengfei Sun","Wenyu Jiang","Piew Yoong Chee","Dick Botteldooren"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-05T18:40:14Z","doi":"10.1109/tencon61640.2024.10903095","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1109/icnc64304.2024.10987869","name":"Distributed Event-Triggered Nash Equilibrium Seeking Under Hybrid Attacks and Dead-Zone Inputs: A Topology Reconstruction Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987869","authors":["Xiao Lu","Shuting Chen","Ying Wan","Junjie Fu","Tingwen Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987869","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1109/icecs46596.2019.8965057","name":"Stochasticity in Neuromorphic Computing: Evaluating Randomness for Improved Performance","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icecs46596.2019.8965057","authors":["Samuel D. Brown","Gangotree Chakma","Md Musabbir Adnan","Md Sakib Hasan","Garrett S. Rose"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-23T22:15:31Z","doi":"10.1109/icecs46596.2019.8965057","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1109/edtm65772.2026.11498051","name":"Monolithic 3D Integrated Multi-Mode Spintronic Memristor for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/edtm65772.2026.11498051","authors":["Yuhan Li","Zhihua Xiao","Yaoru Hou","Yuting Liu","Ching Ho Chan","Qiming Shao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-06T19:38:04Z","doi":"10.1109/edtm65772.2026.11498051","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.29363/nanoge.matnec.2022.013","name":"Increasing the Resistance Window of Complex Oxide based Schottky Interfaces by Device Miniaturization","source":"crossref","abstract":"","url":"https://doi.org/10.29363/nanoge.matnec.2022.013","authors":["Anouk Goossens","Majid Ahmadi","Divyanshu Gupta","Ishitro Bhaduri","Bart Kooi","Tamalika Banerjee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-30T08:35:25Z","doi":"10.29363/nanoge.matnec.2022.013","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1109/icicdt65192.2025.11078115","name":"Memristors Based on Two-Dimensional Layered Halide Perovskites for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icicdt65192.2025.11078115","authors":["Yutong Wu","Shirong Huang","Luis Antonio Panes-Ruiz","Alon Ascoli","Ronald Tetzlaff","Gianaurelio Cuniberti"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-17T17:54:49Z","doi":"10.1109/icicdt65192.2025.11078115","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1145/3319619.3322016","name":"Island model for parallel evolutionary optimization of spiking neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3319619.3322016","authors":["Catherine D. Schuman","James S. Plank","Robert M. Patton","Thomas E. Potok"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-07-10T12:10:59Z","doi":"10.1145/3319619.3322016","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1007/978-3-031-65549-4_9","name":"Ethical, Legal, and Policy Implications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-65549-4_9","authors":["Ali Akbar Firoozi","Ali Asghar Firoozi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-26T13:01:53Z","doi":"10.1007/978-3-031-65549-4_9","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1360/tb-2021-0501","name":"Constructing artificial neural networks using genetic circuits to realize neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1360/tb-2021-0501","authors":["Shan Yang","Ruicun Liu","Tuoyu Liu","Yingtan Zhuang","Jinyu Li","Yue Teng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-08-17T01:06:14Z","doi":"10.1360/tb-2021-0501","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1109/cleo/europe-eqec65582.2025.11110197","name":"Best of Both Worlds' Neuromorphic Computing in 3D Photonic-Electronic Integrated Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cleo/europe-eqec65582.2025.11110197","authors":["S. J. Ben Yoo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-15T18:11:27Z","doi":"10.1109/cleo/europe-eqec65582.2025.11110197","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.52202/078362-0152","name":"Spiking Neural Network Design for On-Board Detection of Methane Emissions Through Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.52202/078362-0152","authors":["Andrew Karim","Amel Alkholeify","Jimin Choi","Jatin Dhall","Tan Huda","Arnav Ranjekar","Yousfi Yassine","Daniel Wischert"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-31T21:05:26Z","doi":"10.52202/078362-0152","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/icnc52316.2021.9608787","name":"Design and Implementation of a Tobacco Storage Monitoring and Conservation Data Management System","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc52316.2021.9608787","authors":["Baiyan Hu","Jiejie Chen","Ying Dai","Quan Qi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-29T20:59:32Z","doi":"10.1109/icnc52316.2021.9608787","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1007/978-3-031-73800-5_4","name":"Modulation Classification Performance Simulation Results","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-73800-5_4","authors":["Ziad El-Khatib","Sherif Moussa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-15T07:23:00Z","doi":"10.1007/978-3-031-73800-5_4","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1364/ome.461270","name":"Emerging Optical Materials, Devices and Systems for Photonic Neuromorphic Computing feature issue: publisher’s note","source":"crossref","abstract":"This publisher’s notes amends the title of [ Opt. Mater. Express 12 , 1214 ( 2022 ) 10.1364/OME.451016 ].","url":"https://doi.org/10.1364/ome.461270","authors":["Antonio Hurtado","Bruno Romeira","Bhavin Shastri","Zengguang Cheng","Sonia Buckley"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-12T16:30:20Z","doi":"10.1364/ome.461270","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/tvlsi.2014.2365458","name":"Energy Efficient Approximate Arithmetic for Error Resilient Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tvlsi.2014.2365458","authors":["Yongtae Kim","Yong Zhang","Peng Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-11-20T15:46:37Z","doi":"10.1109/tvlsi.2014.2365458","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/irps61424.2026.11499173","name":"Demonstration of Fundamental Weight Accuracy Limits Using Bi-Directional Tuning of SuperFlash ESF3 Cells for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/irps61424.2026.11499173","authors":["Louisa Schneider","Steven Lemke","Parviz Ghazavi","Nhan Do","Yuri Tkachev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-07T19:51:08Z","doi":"10.1109/irps61424.2026.11499173","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1145/3546790.3546799","name":"Design and implementation of a parsimonious neuromorphic PID for onboard altitude control for MAVs using neuromorphic processors","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3546790.3546799","authors":["Stein Stroobants","Julien Dupeyroux","Guido De Croon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-08T04:10:51Z","doi":"10.1145/3546790.3546799","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1036/1097-8542.yb090144","name":"Neuromorphic and biomorphic engineering systems","source":"crossref","abstract":"","url":"https://doi.org/10.1036/1097-8542.yb090144","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-07-10T19:02:00Z","doi":"10.1036/1097-8542.yb090144","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1117/12.2515168","name":"Neuromorphic computing and directed self-assembly: a new pairing for old technologies  (Conference Presentation)","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.2515168","authors":["Brian D. Hoskins","Jabez J. McClelland"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-08-16T18:40:00Z","doi":"10.1117/12.2515168","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/ises54909.2022.00061","name":"Security Threat to the Robustness of RRAM-based Neuromorphic Computing System","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ises54909.2022.00061","authors":["Bing Li","Hao Lv","Ying Wang","Yiran Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-02-02T20:15:13Z","doi":"10.1109/ises54909.2022.00061","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.3389/fnano.2025.1650174","name":"Correction: Performance and variability analysis of ALD-grown wafer scale HfO2/Ta2O5-based memristive devices for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.3389/fnano.2025.1650174","authors":["Sanjay Kumar","Deepika Yadav","Spyros Stathopoulos","Themis Prodromakis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-26T08:47:17Z","doi":"10.3389/fnano.2025.1650174","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1088/1674-4926/23120051","name":"Complementary memtransistors for neuromorphic computing: How, what and why","source":"crossref","abstract":"Abstract Memtransistors in which the source−drain channel conductance can be nonvolatilely manipulated through the gate signals have emerged as promising components for implementing neuromorphic computing. On the other side, it is known that the complementary metal-oxide-semiconductor (CMOS) field effect transistors have played the fundamental role in the modern integrated circuit technology. Therefore, will complementary memtransistors (CMT) also play such a role in the future neuromorphic circuits and chips? In this review, various types of materials and physical mechanisms for constructing CMT (how) are inspected with their merits and need-to-address challenges discussed. Then the unique properties (what) and potential applications of CMT in different learning algorithms/scenarios of spiking neural networks (why) are reviewed, including supervised rule, reinforcement one, dynamic vision with in-sensor computing, etc. Through exploiting the complementary structure-related novel functions, significant reduction of hardware consuming, enhancement of energy/efficiency ratio and other advantages have been gained, illustrating the alluring prospect of design technology co-optimization (DTCO) of CMT towards neuromorphic computing.","url":"https://doi.org/10.1088/1674-4926/23120051","authors":["Qi Chen","Yue Zhou","Weiwei Xiong","Zirui Chen","Yasai Wang","Xiangshui Miao","Yuhui He"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-14T13:05:31Z","doi":"10.1088/1674-4926/23120051","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1515/ntrev-2025-0292","name":"Honey-CNT memristive artificial synaptic device for sustainable neuromorphic computing system","source":"crossref","abstract":"Abstract Brain-inspired neuromorphic computing systems require hardware components analogous to biological neurons and synapses. Honey based natural organic memristor has demonstrated promising nonvolatile memristive behaviors, with the advantages of sustainability, environmentally friendliness, and low-cost manufacturing. In this study, carbon nanotubes (CNTs) are added in honey to fabricate honey-CNT memristive artificial synaptic devices. Honey-CNT film is characterized by micro-Raman spectroscopy and the distribution of CNT bundles embedded in the honey-CNT composite layer by cross-sectional scanning electron microscopy for the first time. Critical synaptic functions of the honey-CNT memristor, including spike-rate-dependent plasticity, spike voltage dependent plasticity, learn-forget-relearn, and supralinear spatial summation are revealed, which have not been reported by honey based memristive devices before. Paired pulse facilitation with a PPF index as large as 4.5 is observed, indicating the enhancement of synaptic weight by CNTs. Furthermore, honey-CNT memristor based neuromorphic system is evaluated in terms of linearity, accuracy, read/write energy, and overall performance by the image recognition using Stochastic Gradient Descent and Adaptive Moment Estimation learning algorithms and the Modified National Institute of Standards and Technology database.","url":"https://doi.org/10.1515/ntrev-2025-0292","authors":["Md Mehedi Hasan Tanim","Zoe Templin","Harshvardhan Uppaluru","Jinhui Wang","Kuan Yew Cheong","Feng Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-13T19:03:45Z","doi":"10.1515/ntrev-2025-0292","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/aicas64808.2025.11173109","name":"Explore Activation Sparsity in Recurrent LLMs for Energy-Efficient Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aicas64808.2025.11173109","authors":["Ivan Knunyants","Maryam Tavakol","Manolis Sifalakis","Yingfu Xu","Amirreza Yousefzadeh","Guangzhi Tang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-25T17:52:35Z","doi":"10.1109/aicas64808.2025.11173109","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1063/1.4991917","name":"NbOx based oscillation neuron for neuromorphic computing","source":"crossref","abstract":"In a neuromorphic computing system, the complex CMOS neuron circuits have been the bottleneck for efficient implementation of weighted sum operation. The phenomenon of metal-insulator-transition (MIT) in strongly correlated oxides, such as NbO2, has shown the oscillation behavior in recent experiments. In this work, we propose using a MIT device to function as a compact oscillation neuron, achieving the same functionality as the CMOS neuron but occupying a much smaller area. Pt/NbOx/Pt devices are fabricated, exhibiting the threshold switching I-V hysteresis. When the NbOx device is connected with an external resistor (i.e., the synapse), the neuron membrane voltage starts a self-oscillation. We experimentally demonstrate that the oscillation frequency is proportional to the conductance of the synapse, showing its feasibility for integrating the weighted sum current. The switching speed measurement indicates that the oscillation frequency could achieve &amp;gt;33 MHz if parasitic capacitance can be eliminated.","url":"https://doi.org/10.1063/1.4991917","authors":["Ligang Gao","Pai-Yu Chen","Shimeng Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-09-07T19:11:27Z","doi":"10.1063/1.4991917","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/iedm.2018.8614556","name":"Physics-based modeling of volatile resistive switching memory (RRAM) for crosspoint selector and neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iedm.2018.8614556","authors":["W. Wang","A. Bricalli","M. Laudato","E. Ambrosi","E. Covi","D. Ielmini"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-01-24T04:58:45Z","doi":"10.1109/iedm.2018.8614556","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.2139/ssrn.6734323","name":"Memristors based on azatriphenylene and its derivatives modified by metal co-ordination for neuromorphic computing","source":"crossref","abstract":"Recently, organic small-molecule semiconductors have emerged to serve as the re-sistive switching (RS) layer owing to the well-defined molecular structures and the capacity for precise modulation of transport characteristics through chemical modi-fication. In this work, we have designed and synthesized five organic small mole-cules based on the azatriphenylene (AT) framework, including AT and its derivatives with substituents of methoxy, methyl, chloro, and trifluoromethyl. This provides an opportunity to systematically investigate the relationships between the molecular structure, device configuration and the memristive behaviors. The results demon-strate that different functional groups can modulate the HOMO/LUMO energy levels and the electron distribution, thereby influencing the RS performance of the fabri-cated devices based on the synthesized small-molecule semiconductors. Among them, the 6,11-bis(trifluoromethyl)-2-azatriphenylene (BTFMAT) with the strong electron-withdrawing effect of trifluoromethyl exhibits typical volatile RS behaviors with relatively high ON/OFF ratio. The BTFMAT-based memristor successfully em-ulated biological synaptic long-term potentiation and long-term depression (LTP/LTD) and learning-forgetting behaviors, and can be further employed to con-struct an artificial neural network (ANN), achieving a recognition accuracy of 93.6% for handwritten digit image recognition. Furthermore, by introducing a Cu interlayer into the BTFMAT device, a transition from volatile to non-volatile RS behavior can be realized because Cu2+ can coordinate with N atoms in BTFMAT to form stable complexes and subsequently Cu conductive filaments can be formed under an exter-nal electric field. This work provides a new design strategy for developing high-performance organic small-molecule memristors and exploring their potential applications in neuromorphic computing. Keywords: Neuromorphic computing, Memristor, Organic semiconductor, Metal ion doping, Synaptic plasticity","url":"https://doi.org/10.2139/ssrn.6734323","authors":["Yuexin Li","Lan Yang","Didi Zhang","Qinlian Gao","Mei Li","Xiushan Tu","Yanyan He","Zhaorong Zhou","Yingbo Shi","Wenjing Jie"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-08T12:40:50Z","doi":"10.2139/ssrn.6734323","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/irps.2015.7112755","name":"Non-volatile memory as hardware synapse in neuromorphic computing: A first look at reliability issues","source":"crossref","abstract":"","url":"https://doi.org/10.1109/irps.2015.7112755","authors":["Robert M. Shelby","Geoffrey W. Burr","Irem Boybat","Carmelo di Nolfo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-06-03T15:32:57Z","doi":"10.1109/irps.2015.7112755","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.3390/mi10090558","name":"A Floating Gate Memory with U-Shape Recessed Channel for Neuromorphic Computing and MCU Applications","source":"crossref","abstract":"We have simulated a U-shape recessed channel floating gate memory by Sentaurus TCAD tools. Since the floating gate (FG) is vertically placed between source (S) and drain (D), and control gate (CG) and HfO2 high-k dielectric extend above source and drain, the integrated density can be well improved, while the erasing and programming speed of the device are respectively decreased to 75 ns and 50 ns. In addition, comprehensive synaptic abilities including long-term potentiation (LTP) and long-term depression (LTD) are demonstrated in our U-shape recessed channel FG memory, highly resembling the biological synapses. These simulation results show that our device has the potential to be well used as embedded memory in neuromorphic computing and MCU (Micro Controller Unit) applications.","url":"https://doi.org/10.3390/mi10090558","authors":["Lu-Rong Gan","Ya-Rong Wang","Lin Chen","Hao Zhu","Qing-Qing Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-08-26T04:38:23Z","doi":"10.3390/mi10090558","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/icnc59488.2023.10462748","name":"Stacking Integration Strategy-Based Learning Method for Prediction of Performance in Exams","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462748","authors":["Hua Jiang","Yaqian Bao","Feng Jiang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462748","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/ic3et64989.2026.11467541","name":"Neuromorphic Approaches to Urban Traffic Management with Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ic3et64989.2026.11467541","authors":["T Vishnu Sriram","Shubham Kumawat","Umesh Goyal","Biswa Mohan Sahoo","Anuj Kulshrestha","Vinayak Gupta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-09T19:42:29Z","doi":"10.1109/ic3et64989.2026.11467541","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.52058/2786-6025-2026-3(57)-2208-2224","name":"АРХІТЕКТУРА ОБЧИСЛЮВАЛЬНИХ СИСТЕМ НА БАЗІ  НЕЙРОМОРФНИХ ПРОЦЕСОРІВ НОВОГО ПОКОЛІННЯ","source":"crossref","abstract":"","url":"https://doi.org/10.52058/2786-6025-2026-3(57)-2208-2224","authors":["Галина Губаль","Олександр Дудник","Руслан Іваненко"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-30T08:44:05Z","doi":"10.52058/2786-6025-2026-3(57)-2208-2224","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.33693/2313-223x-2025-12-1-11-16","name":"Implementation of Secure Traffic Light Management Using a Neuromorphic Computing Base Based on Fuzzy Graphs","source":"crossref","abstract":"The task of safe traffic light management is to normalize traffic. Secure management involves the implementation of the protection of information involved in the management process. The traffic light management process is a complex dynamic process. The control object is a set of traffic lights. The subject of management is a specific management system, which can be autonomous or part of a top-level management system. The implementation of a traffic light based on a neuromorphic computing base allows you to perform some of the control processes in automatic mode. As part of the control process, you have to deal with different types of data (sensor readings, control signals of different levels, etc.). Big data is processed throughout the entire control process, and one of the main tasks is to reduce the dimensionality of the information being processed. The successful solution of this problem directly depends on the model of organization of a set of traffic lights. The article discusses various traffic lights, each of which is equipped with an intelligent controller. The neuromorphic basis of the intelligent controller allows you to expand the capabilities of the computing base at a low level. Fuzzy graphs are used to represent a set of traffic lights and to connect the traffic lights to the control system. This model makes it possible to combine the information and control components of the process of interaction between the object and the subject of management into one whole. The advantages of this representation are the minimization of information necessary for the successful solution of the problem of safe management, and the expansion of the possibilities of the management process through the use of fuzzy information.","url":"https://doi.org/10.33693/2313-223x-2025-12-1-11-16","authors":["Alexandra V. Volosova","Ekaterina N. Matyukhina","Egor A. Morozov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-27T10:38:34Z","doi":"10.33693/2313-223x-2025-12-1-11-16","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/tce.2026.3663582","name":"Guest Editorial: Neuromorphic Computing Technologies for Consumer Electronics","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tce.2026.3663582","authors":["Zhekang Dong","Ping Lu","Chun Sing Lai","Zhongrui Wang","Edith Ngai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-11T20:55:53Z","doi":"10.1109/tce.2026.3663582","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1002/aisy.202100175","name":"Back‐End CMOS Compatible and Flexible Ferroelectric Memories for Neuromorphic Computing and Adaptive Sensing","source":"crossref","abstract":"Development of unconventional computing architectures, including neuromorphic computing, relies heavily on novel devices with properly engineered properties. This requires exploration of new functional materials and their designed interfaces. Ferroelectric memories including two‐terminal ferroelectric tunnel junctions and three‐terminal ferroelectric field‐effect transistors have shown promising performances in recent years as analog, multibit memory components with ultralow power consumption. However, for ferroelectric memory technology to become a mainstream technology, CMOS integration of these components is of major importance. For further diversifying their application to edge computing and smart sensing industry, a vast unchartered territory of low‐temperature processable and CMOS back‐end‐of‐line (BEOL) compatible materials needs to be researched. In recent years, doped HfO 2 ‐based memory devices and in‐memory computing architectures have gathered huge momentum as one of the “beyond von Neumann” computing alternatives. In comparison, molecular ferroelectric‐based systems are still in their early exploratory phase. This review discusses the potential for doped HfO 2 and molecular ferroelectrics as CMOS BEOL and flexible and wearable platform compatible neuromorphic devices and circuits and the challenges that need to be overcome for turning the opportunities to a technological reality.","url":"https://doi.org/10.1002/aisy.202100175","authors":["Sayani Majumdar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-09T02:39:41Z","doi":"10.1002/aisy.202100175","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.17762/ijritcc.v11i1.9819","name":"Class Brain Coprocessor based on Neuromorphic Circuit for Efficient Non-Formalization and Unstructured Information Processing","source":"crossref","abstract":"Class brain coprocessor is a type of coprocessor based on neuromorphic circuits that includes a memory module for storing training characteristics information, a processing module based on a hierarchical structure, and an encoder and decoder for input and output. This research proposes a memory module with a training characteristics storehouse and/or configurable training characteristics storehouse, and a processing module with a solidification functional network module and/or configurable functionality mixed-media network modules, which enhances the extended capability of the coprocessor. The proposed coprocessor employs distributed storage and concurrent collaborative processing, making it particularly suitable for handling non-formalization problems and unstructured information, as well as form problems and structured messages. The results show that this coprocessor significantly accelerates the speed of computers in processing class brain,informationificial intelligence, and reduces energy consumption while improving fault-tolerant ability, reducing programming complexity, and improving computing power.","url":"https://doi.org/10.17762/ijritcc.v11i1.9819","authors":["Et al. Raguvaran K"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-12T08:13:03Z","doi":"10.17762/ijritcc.v11i1.9819","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/irps48203.2023.10118164","name":"Thermal Induced Retention Degradation of RRAM-based Neuromorphic Computing Chips","source":"crossref","abstract":"","url":"https://doi.org/10.1109/irps48203.2023.10118164","authors":["Awang Ma","Bin Gao","Xing Mou","Peng Yao","Yiwei Du","Jianshi Tang","He Qian","Huaqiang Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-15T17:50:57Z","doi":"10.1109/irps48203.2023.10118164","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/tnano.2016.2545690","name":"Wave-Based Neuromorphic Computing Framework for Brain-Like Energy Efficiency and Integration","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnano.2016.2545690","authors":["Yasunao Katayama","Toshiyuki Yamane","Daiju Nakano","Ryosho Nakane","Gouhei Tanaka"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-03-23T18:18:11Z","doi":"10.1109/tnano.2016.2545690","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/icnc64304.2024.10987772","name":"Scheduling Gain-Based Adaptive NN Control of Underactuated Bridge Crane","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987772","authors":["Jia-Ke Wang","Yang Liu","Ronghu Chi","Xuhui Bu","Lijie Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987772","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1088/2634-4386/ae2155","name":"An energy-efficient, CMOS-compatible physical reservoir node with post-fabrication tunable decay dynamics","source":"crossref","abstract":"Abstract In reservoir computing, the memory decay rate of physical reservoir nodes governs how quickly past inputs fade, thereby determining their temporal dynamics. Optimising this rate is therefore crucial for effective temporal signal processing. However, in most reported physical reservoirs, it is fixed at the time of fabrication and cannot be altered on demand for different applications. Thus, tailoring a single node for its adaptability across tasks with diverse temporal characteristics remains challenging. In this work, we propose and computationally analyse a CMOS-compatible, tunable-decay, hybrid reservoir node that integrates a subthreshold-operated field-effect transistor (FET) with a programmable ReRAM device (a memristor) and a capacitor connected at its gate terminal. The reservoir output measured as the FET drain current simultaneously captures temporal memory and nonlinear transformation of the input, while the memory decay time constant ( τ = R × C ) can be modulated in real time by adjusting the ReRAM resistance. We demonstrate the effectiveness of the proposed node on two representative benchmark tasks with contrasting τ requirements, namely, the MNIST digit classification with 96% accuracy, and a chaotic Hénon map prediction with a normalised RMS error of 0.0037, matching state-of-the-art hardware reservoirs. Our design achieves ultra-low energy consumption ( ≈ 15.20 pJ/operation), at least an order of magnitude lower than state-of-the-art implementations, while maintaining reliable operation and on-demand τ tunability. This combination of mature silicon technology and adaptive memristive functionality paves the way for energy-efficient, scalable, and reliable temporal learning systems.","url":"https://doi.org/10.1088/2634-4386/ae2155","authors":["Gambali Seshasai Chaitanya","Aditya D Arkalgud","Shubham Pande","Ankit Arora"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-19T22:51:08Z","doi":"10.1088/2634-4386/ae2155","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1145/3676536.3698024","name":"Neuromorphic Computing for Graph Analytics","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3676536.3698024","authors":["Anup Das"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-09T13:21:20Z","doi":"10.1145/3676536.3698024","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.36227/techrxiv.21532533.v2","name":"Neuromorphic Computing with 28nm High-K-Metal Gate Ferroelectric Field Effect Transistors Based Artificial Synapses","source":"crossref","abstract":"This paper presents a comprehensive overview of 28 nm high-k-metal gate-based ferroelectric field effect transistor devices for synaptic applications. The device under test was fabricated on 300mm wafers at GlobalFoundries. The fabricated devices demonstrate 10 3 WRITE-endurance cycles and 10 4 seconds of data-retention capability at 85°C. We have also assessed the FeFET-based crossbar array’s performance in system-level applications. By simulating the FeFET crossbar array for neuromorphic applications, the system performance was assessed. For datasets from the National Institute of Standards and Technology (MNIST), the crossbar array achieved software-comparable inference accuracy of about 97% using multilayer perceptron (MLP) neural networks.","url":"https://doi.org/10.36227/techrxiv.21532533.v2","authors":["Sourav De","Yannick Raffel","Sunanda Thunder","Franz Müller","Maximilian Lederer","Thomas Kaempfe","Masud S K Rana","Luca Pirro","Konrad Seidel","Bhaswar Chakrabarti"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-31T10:13:48Z","doi":"10.36227/techrxiv.21532533.v2","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1145/3477145.3477163","name":"Reservoir Computing Using Networks of CMOS Logic Gates","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3477145.3477163","authors":["Heidi Komkov","Liam Pocher","Alessandro Restelli","Brian Hunt","Daniel Lanthrop"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-10-13T14:38:20Z","doi":"10.1145/3477145.3477163","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1002/smll.202412531","name":"Neuromorphic Visual Computing with ZnMgO QDs‐Based UV‐Responsive Optoelectronic Synaptic Devices for Image Encryption and Recognition","source":"crossref","abstract":"Abstract Retina‐inspired optoelectronic neuromorphic devices integrating optical sensing and computation are the key components in realizing neuromorphic visual computing. In particular, UV‐responsive optoelectronic synaptic devices hold significant value for advanced neuromorphic vision systems, as they can expand human visual perception. Herein, we demonstrate a UV‐responsive optoelectronic synaptic device based on ZnMgO quantum dots (QDs) designed for in‐sensor computing in neuromorphic vision applications. The device demonstrates voltage‐driven short‐term and long‐term synaptic plasticity, as well as multiple photoinduced synaptic functions. Based on this device, an in‐sensor image‐blending encryption method has been designed, which can effectively reduce the risk of data leakage during transmission. Furthermore, an in‐sensor reservoir computing (RC) system with image processing functions is constructed, which integrates a photonic reservoir layer (PRL) for image preprocessing and a multilayer perceptron (MLP) capable of image recognition. The system achieves 98.6% accuracy in recognizing Fashion‐MNIST images and maintains 83% accuracy under 60% random noise, showcasing its robustness. This work introduces a novel approach for developing UV‐responsive optoelectronic synaptic devices equipped with dual‐mode modulation of both electrical and optical signals, offering new perspectives and solutions for integrated applications in neuromorphic vision systems.","url":"https://doi.org/10.1002/smll.202412531","authors":["Zilong Guo","Hao Kan","Jiaqi Zhang","Yang Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-11T16:59:17Z","doi":"10.1002/smll.202412531","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1088/2631-8695/adfbbb","name":"Towards brain-inspired edge AI: a review of memristor-based neuromorphic computing and learning algorithms","source":"crossref","abstract":"Abstract With the advent of innovative technologies and the emerging demands for in situ edge decision-making, the weaknesses of the conventional von Neumann computing paradigm have become increasingly evident. While such architectures were considered reliable until recently, they have struggled to meet the growing requirements for greater processing speed, lower power consumption, and enhanced scalability. To highlight these challenges, several studies since the early 2010s, have focused on neuromorphic computing based on memristors. Unlike traditional computing, this approach relies more on how the human brain processes information, offering a promising alternative for future edge AI applications. Memristor-based systems, particularly those employing crossbar architectures like 1T1R and 1R arrays, enable analog computation and efficient matrix-vector multiplication, laying the foundation for energy-efficient, scalable hardware. This comprehensive review paper explores the fundamentals of memristor, neuromorphic computing with memristor, learning algorithms focusing on Artificial Neural Networks (ANN), Binary Neural Networks (BNN), and Spiking Neural Networks (SNN), while exploring other learning models as well by comparing the accuracy percentage of each model and edge AI tasks such as image classification, emotion recognition, and multimodal learning. Furthermore, it addresses the intrinsic advantages of computation-in-memory architecture regarding scalability, latency reduction, and parallelism. It also offers insights into the challenges such as device-to-device variability, low endurance, non-ideal switching properties, and compatibility with complementary metal–oxide–semiconductor (CMOS) technologies. This study flow will help understand each technique’s central concept to highlight future development challenges, discussing the status and prospects of neuromorphic and brain-inspired computing technologies.","url":"https://doi.org/10.1088/2631-8695/adfbbb","authors":["Salma Yasser Sadik Hassan Hussein","Patrick W C Ho"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-14T22:52:15Z","doi":"10.1088/2631-8695/adfbbb","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.3389/fnano.2025.1621554","name":"Performance and variability analysis of ALD-grown wafer scale HfO2/Ta2O5-based memristive devices for neuromorphic computing","source":"crossref","abstract":"Here, we report a large-scale wafer microfabrication process and in-depth electrical analysis of atomic layer deposition (ALD) grown bilayer (i.e., HfO 2 /Ta 2 O 5 ) memristive devices. The fabricated bilayer devices initially require an electroforming event and show stable bipolar resistive switching responses with some variations in the device switching voltages. These variations are covered in the 15.7%–22.7% range corresponding to the maximum switching voltage of the tested devices. Moreover, time series analysis (TSA) is employed by considering the device switching voltages ( V SET and V RESET ) to predict the device performance and the obtained outcomes are well matched to the experimental data. Furthermore, the least values of coefficient of variability ( C V ) in the device switching voltages are 6.09% ( V SET ) and 3.22% ( V RESET ) in the case of device-to-device (D2D) while 1.76% ( V SET ) and 2.14% ( V RESET ) in the case of cycle-to-cycle (C2C). Furthermore, the fabricated devices efficiently perform the synaptic functionalities in terms of potentiation (P) and depression (D), paired-pulse facilitation (PPF), and paired-pulse depression (PPD), with a least value of nonlinearity (NL) factor of 0.43 in synaptic response, which is close to the ideal value of NL in biological synapses. Therefore, the present work shows that the single ALD system can be an efficient deposition method to deposit high-k oxide materials for memristive arrays over large-scale wafers.","url":"https://doi.org/10.3389/fnano.2025.1621554","authors":["Sanjay Kumar","Deepika Yadav","Spyros Stathopoulos","Themis Prodromakis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-19T05:32:24Z","doi":"10.3389/fnano.2025.1621554","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/isscc.2017.7870481","name":"F3: Beyond the horizon of conventional computing: From deep learning to neuromorphic systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isscc.2017.7870481","authors":["Meng-Fan Chang","Jun Deguchi","Vivek De","Masato Motomura","Shinichiro Shiratake","Marian Verhelst"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-03-07T14:34:02Z","doi":"10.1109/isscc.2017.7870481","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/socc46988.2019.1570548462","name":"Power and Area Efficient Router with Automated Clock Gating for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/socc46988.2019.1570548462","authors":["Junran Pu","Vishnu P Nambiar","Aarthy Mani","Wang Ling Goh","Anh Tuan Do"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-05-07T21:27:28Z","doi":"10.1109/socc46988.2019.1570548462","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/icnc59488.2023.10462822","name":"Fixed-Time Synchronization of Impulsive Multi-layer Networks with Time-Varying Parameters Uncertainty","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462822","authors":["Jie Yue","Juan Yu","Cheng Hu","Kailong Xiong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462822","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/icnc64304.2024.10987800","name":"Neural Network SLAM Algorithms for Dynamic Object Removal in Complex Environments","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987800","authors":["Ren Zhang","Jingxin Liu","Jinmingwu Jiang","Pengfei Zhang","Seyedali Mirjalili"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987800","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1088/2634-4386/aea01b","name":"A closer-to-brain heterosynaptic learning rule for spatiotemporal spike pattern detection with low-resolution synapse","source":"crossref","abstract":"Abstract The brain is believed to process information efficiently in a different manner from deep learning-based artificial intelligence (AI). Brain-like next-generation AI is gaining attention owing to its potential to perform human-like, highly adaptive, robust, and power-efficient computation. To realize such AI, one crucial approach is the bottom-up implementation of the neuronal systems, capturing their electrophysiological characteristics in electronic circuits. However, this neuromorphic approach generally focuses on simplified neuronal models that do not refer to many biological findings. Developing closer-to-brain models is a natural direction that serve as a fundamental computing model for next-generation AI. One of the constraints of neuromorphic circuits is the bit resolution of synaptic efficacy memory, as the memory footprint scales with its precision. Although low-resolution synaptic efficacy is essential for minimizing memory circuit footprint and energy consumption, it generally leads to performance degradation in many tasks such as the spatiotemporal spike pattern detection. This study proposed a closer-to-brain learning rule that incorporates heterosynaptic plasticity (HP) induced by glutamate spillover. It is demonstrated that our model mitigates the performance degradation associated with low-bit resolution synaptic efficacy, achieving the pattern detection success rate with 3-bit resolution synaptic efficacy, which is comparable to 64-bit floating-point precision. Furthermore, the findings of the study indicate that HP based model accelerates the convergence of the synaptic efficacy and effectively potentiates the synapses relevant to the pattern detection while suppressing irrelevant ones, thereby promoting a bimodal distribution of synaptic efficacies. These findings may provide a basic framework for constructing an energy-efficient, brain-like next-generation AI that maintains high performance under hardware constraints.","url":"https://doi.org/10.1088/2634-4386/aea01b","authors":["Shunta Furuichi","Takashi Kohno"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-28T22:50:31Z","doi":"10.1088/2634-4386/aea01b","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1149/ma2024-01573003mtgabs","name":"Understanding the Non-Volatile Resistive Switching Behavior of Lithium Titanium Oxide during Spinel to Rock Salt Conversion for Neuromorphic Computing","source":"crossref","abstract":"Lithium based synaptic device research has been a growing new field in the last few years for enabling robust neuromorphic hardware systems. It can realize parallel analogue computation which is beyond the conventional von Neumann computing architecture which is slow, energy inefficient and expensive to execute complex tasks. In this study, we showcase the remarkable potential of Lithium Titanium Oxide (Li 4 Ti 5 O 12 ) spinel, both computationally through Density of States (DoS) analysis using Density Functional Theory (DFT), and experimentally via direct current (DC) polarization investigation of electrochemically lithiated Li 4 Ti 5 O 12 thin film, examining diverse states of discharge (SoD) in both in-plane and out-of-plane configurations. The observed conductivity jump spans up to six orders of magnitude, transitioning from the Li 4 Ti 5 O 12 spinel phase to the fully lithiated Li 7 Ti 5 O 12 rock salt phase. Raman Spectroscopy validates the transformation from the Li 4 Ti 5 O 12 spinel phase to the Li 7 Ti 5 O 12 rock salt phase. Moreover, the onset of increase in conductivity during this transformation is corroborated by changes in the oxidation state of Titanium (Ti), as explained with the help of X-Ray Photoelectron Spectroscopy. To actualize these findings, we engineered a three-terminal artificial synaptic device integrating Lithium Phosphorous Oxynitride (LiPON) solid-state electrolyte as the lithium ion source and conductor, while employing Lithium Titanium Oxide (Li4Ti5O12) spinel as the channel material. In device testing, we maintained a source-drain voltage (V SD ) of 0.5 V, while sweeping the gate voltage (V G ) from -3 V to 3 V, resulting in switching spanning up to 4 orders of magnitude, consistently replicable across multiple cycles. Widening the gate voltage window from ±3 V to ±7V induced an increase in conductance. Furthermore, non-volatile testing affirmed the sustained retention of the conductance state across all tested gate voltage windows, showcasing the device's stability over time. These compelling results portray a promising trajectory for the development of a robust synaptic device architecture reliant on lithium-based all solid-state materials, catalyzing the evolution of high-precision analogue neuromorphic computing systems.","url":"https://doi.org/10.1149/ma2024-01573003mtgabs","authors":["Bhagath Sreenarayanan","Shirley Meng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-19T15:53:31Z","doi":"10.1149/ma2024-01573003mtgabs","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.2139/ssrn.5738928","name":"Multi-state with High Linearity and Symmetry in Ferroelectric Field-Effect Transistors for Superior Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5738928","authors":["Wenshuo Wu","Wenze Jiang","Wei Wang","Ting Xu","Pengshun Shan","Chaoyou Xu","Jiacheng Huang","Zihang Zhu","Minghao Zhang","Jie Su"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-12T13:38:04Z","doi":"10.2139/ssrn.5738928","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/iccdw45521.2020.9318650","name":"A Comprehensive Study and Detection of Anomalies for Autonomous Video Surveillance Using Neuromorphic Computing and Self Learning Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccdw45521.2020.9318650","authors":["Akansha Bhargava","Gauri Salunkhe","Kishor Bhosale"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-01-20T21:23:26Z","doi":"10.1109/iccdw45521.2020.9318650","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/icrc.2016.7738691","name":"Conversion of artificial recurrent neural networks to spiking neural networks for low-power neuromorphic hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icrc.2016.7738691","authors":["Peter U. Diehl","Guido Zarrella","Andrew Cassidy","Bruno U. Pedroni","Emre Neftci"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-11-10T16:39:45Z","doi":"10.1109/icrc.2016.7738691","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1088/2634-4386/ae958f","name":"Noise-Robust conceptors for physical reservoir computing: adaptation to perturbations","source":"crossref","abstract":"Abstract Conceptors are a powerful extension of reservoir computing (RC) that enable the selective recall and stabilization of internal dynamics. However, their application to physical RC remains challenging because measured reservoir states are inevitably affected by noise and physical perturbations. In this work, we propose a noise-robust cross-trial-correlation-based (CTC) method for computing conceptors in noisy reservoir systems. By exploiting the consistency of the reservoir response across repeated trials, the method suppresses noise contributions that are uncorrelated between measurements. Numerical simulations of leaky echo state networks under additive state noise and parameter drift show that CTC-based conceptors preserve the relevant internal dynamics and extend the operational range of the reservoir compared with standard conceptors and unconstrained reservoirs. In an autonomous-generation task, the CTC-based conceptor maintains predictive capability beyond 50% noise, where the other configurations fail to sustain autonomous generation. Under combined noise and parameter drift, the CTC approach maintains normalized root mean square error values below 0.3, while the alternative approaches considered exceed this error level in the tested conditions. These numerical results establish a concrete step towards adapting conceptor-based control to physical RC platforms.","url":"https://doi.org/10.1088/2634-4386/ae958f","authors":["Gemma Infantes-Llinares","Hongki Kang","Miguel C Soriano"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-05T22:52:48Z","doi":"10.1088/2634-4386/ae958f","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1002/adma.202419245","name":"Toward Switching and Fusing Neuromorphic Computing: Vertical Bulk Heterojunction Transistors with Multi‐Neuromorphic Functions for Efficient Deep Learning","source":"crossref","abstract":"Abstract The combination of artificial neural networks (ANN) and spiking neural networks (SNN) holds great promise for advancing artificial general intelligence (AGI). However, the reported ANN and SNN computational architectures are independent and require a large number of auxiliary circuits and external algorithms for fusion training. Here, a novel vertical bulk heterojunction neuromorphic transistor (VHNT) capable of emulating both ANN and SNN computational functions is presented. TaO x ‐based electrochemical reactions and PDVT‐10/N2200‐based bulk heterojunctions are used to realize spike coding and voltage coding, respectively. Notably, the device exhibits remarkable efficiency, consuming a mere 0.84 nJ of energy consumption for a single multiply accumulate (MAC) operation with excellent linearity. Moreover, the device can be switched to spiking neuron and self‐activation neuron by simply changing the programming without auxiliary circuits. Finally, the VHNT‐based artificial spiking neural network (ASNN) fusion simulation architecture is demonstrated, achieving 95% accuracy for Canadian‐Institute‐For‐Advanced‐ResearchResearch‐10 (CIFARResearch‐10) dataset while significantly enhancing training speed and efficiency. This work proposes a novel device strategy for developing high‐performance, low‐power, and environmentally adaptive AGI.","url":"https://doi.org/10.1002/adma.202419245","authors":["Yi Zou","Di Liu","Xinyan Gan","Rengjian Yu","Xianghong Zhang","Chansong Gao","Zhenjia Chen","Chenhui Xu","Yun Ye","Yuanyuan Hu","Tailiang Guo","Huipeng Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-24T04:41:20Z","doi":"10.1002/adma.202419245","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.36227/techrxiv.21532533","name":"Neuromorphic Computing with 28nm High-K-Metal Gate Ferroelectric Field Effect Transistors Based Artificial Synapses","source":"crossref","abstract":"&lt;p&gt;This paper presents a comprehensive overview of 28 nm high-k-metal gate-based ferroelectric field effect transistor devices for synaptic applications. The device under test was fabricated on 300mm wafers at GlobalFoundries. The fabricated devices demonstrate 10&lt;sup&gt;3&lt;/sup&gt; WRITE-endurance cycles and 10&lt;sup&gt;4&lt;/sup&gt; seconds of data-retention capability at 85°C. We have also assessed the FeFET-based crossbar array’s performance in system-level applications. By simulating the FeFET crossbar array for neuromorphic applications, the system performance was assessed. For datasets from the National Institute of Standards and Technology (MNIST), the crossbar array achieved software-comparable inference accuracy of about 97% using multilayer perceptron (MLP) neural networks.&lt;/p&gt;","url":"https://doi.org/10.36227/techrxiv.21532533","authors":["Yannick Raffel","Franz Müller","Sunanda Thunder","Masud S K Rana","Maximilian Lederer","Luca Pirro","Konrad Seidel","Bhaswar Chakrabarti","Thomas Kaempfe","Sourav De"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-11T00:48:57Z","doi":"10.36227/techrxiv.21532533","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.3389/fnins.2013.00011","name":"Six Networks on a Universal Neuromorphic Computing Substrate","source":"crossref","abstract":"","url":"https://doi.org/10.3389/fnins.2013.00011","authors":["Thomas Pfeil","Andreas Grübl","Sebastian Jeltsch","Eric Müller","Paul Müller","Mihai A. Petrovici","Michael Schmuker","Daniel Brüderle","Johannes Schemmel","Karlheinz Meier"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-02-18T22:10:00Z","doi":"10.3389/fnins.2013.00011","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1088/0268-1242/29/10/104011","name":"MemFlash device: floating gate transistors as memristive devices for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0268-1242/29/10/104011","authors":["C Riggert","M Ziegler","D Schroeder","W H Krautschneider","H Kohlstedt"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-09-18T09:13:23Z","doi":"10.1088/0268-1242/29/10/104011","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/hipcw66559.2025.00026","name":"Neuromorphic Adaptive Precision RISC-V Processor with Real-Time Precision Scaling and Neuronal State Management","source":"crossref","abstract":"","url":"https://doi.org/10.1109/hipcw66559.2025.00026","authors":["Om Maheshwari","Sahil Maurya","Bikram Paul"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-02T19:48:12Z","doi":"10.1109/hipcw66559.2025.00026","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1039/d6nr02312f/v2/response1","name":"Author response for \"CuPc/SiC Heterostructure Enabling All-Optical-Controlled Artificial Synapses for Neuromorphic Computing and Vision\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d6nr02312f/v2/response1","authors":["Lingxin Meng","Jiayao Wang","Jiaqi Han","Xuanyu Shan","Ye Tao","Bingjie Dang","Tao Zeng","Xiaoning Zhao","Ya Lin","Zhongqiang Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-11T21:08:20Z","doi":"10.1039/d6nr02312f/v2/response1","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1364/cleo_si.2020.sth3r.2","name":"VO2 electro-optic memory and oscillator for neuromorphic computing","source":"crossref","abstract":"We demonstrate optical memory and light-triggered electrical oscillations in a VO2 electro optic micro-wire device for potential applications in neuromorphic computing architectures.","url":"https://doi.org/10.1364/cleo_si.2020.sth3r.2","authors":["Junho Jeong","Youngho Jung","Zhongnan Qu","Bin Cui","Ankita Khanda","Ankita Sharma","Stuart S. P. Parkin","Joyce K. S. Poon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-14T15:29:13Z","doi":"10.1364/cleo_si.2020.sth3r.2","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1002/aisy.70419","name":"Neuromorphic Denoising with Fully Analog Memristive In‐Memory Computing","source":"crossref","abstract":"Analog compute‐in‐memory (CIM) technology utilizes the physical characteristics of memory devices to cancel the repeated data movement between memory and processors. Since this method gets rid of the signal domain conversion, analog CIM is suitable for the post‐sensing processing systems. However, two critical challenges emerge: a lack of area‐efficient analog buffers to complete the analog computing flow and the inevitable accumulation of noise throughout the continuous signal path. Previous works either incur extra power and space costs to mitigate these issues or compromise the analog CIM concept by introducing digital circuits. In this article, we borrow the concepts of episodic memory in human brains to experimentally implement a memristor‐based neuromorphic denoising process. We experimentally demonstrate a homogeneous memristor processing unit for both temporal storage and neural network computation, imitating the synapses in the human brain. Furthermore, based on previous research on functional modeling of episodic memory, we experimentally demonstrate an analog neuromorphic denoising system utilizing the proposed homogeneous memristor cores. Thanks to this neuromorphic design, compared with the latest analog computing neural network works, the proposed method improves the power efficiency by times, saves overall on‐chip analog buffer by times, and achieves area efficiency improvement.","url":"https://doi.org/10.1002/aisy.70419","authors":["Daijing Shi","Teng Zhang","Yuqi Li","Yaoyu Tao","Bonan Yan","Yuchao Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-18T07:30:43Z","doi":"10.1002/aisy.70419","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1039/d5nr00456j/v2/response1","name":"Author response for \"Photosensitive resistive switching in parylene-PbTe nanocomposite memristors for neuromorphic computing\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5nr00456j/v2/response1","authors":["Andrey D. Trofimov","Andrey Emelyanov","Anna Matsukatova","Alexander  A. Nesmelov","Sergei Zav'yalov","Timofey Patsaev","Pavel Forsh","Gang Liu","Vladimir Rylkov","Vyacheslav A. Demin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-07T06:11:18Z","doi":"10.1039/d5nr00456j/v2/response1","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1088/2634-4386/ad025b","name":"Multimode Fabry-Perot laser as a reservoir computing and extreme learning machine photonic accelerator","source":"crossref","abstract":"Abstract In this work, we introduce Fabry–Perot lasers as neuromoprhic nodes in the context of time-delayed reservoir computing and extreme learning machine (ELM) for the processing of temporal signals and the high-speed classification of images. By exploiting the multi-wavelength emission capabilities of the Fabry–Perot lasers, additional processing nodes can be introduced, thus raising the computational power without sacrificing processing speed. An experimental validation of this concept using a Fabry–Perot ELM is presented targeting a time depedent task such as channel equalization for a 50 km 28 Gbaud ‘PAM-4’ transmission, offering hard-decision forward error correction compatible performance. Additionally, the Fabry–Perot neuromorphic concept has been further strengthened by modifying the data entry technique by parallelelly assigning different samples of the input signal to different modes so as to significantly reduce speed penalty. Numerical simulations revealed that this alternative data insertion technique can offer a reduction of the processing delay and physical footprint by 75% compared to the conventional approach assigning the same symbols to all Fairy–Perot modes. Moreover, by using a similar data processing scheme in ‘MNIST’ image classification task we were able to numerically achieve a processing speed of 255.1 Mimages s −1 and a classification accuracy up to 95.95%.","url":"https://doi.org/10.1088/2634-4386/ad025b","authors":["Menelaos Skontranis","George Sarantoglou","Kostas Sozos","Thomas Kamalakis","Charis Mesaritakis","Adonis Bogris"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-11T22:29:34Z","doi":"10.1088/2634-4386/ad025b","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1038/s44335-026-00070-8","name":"Fractional-order systems for neuromorphic computing: software and hardware opportunities and challenges","source":"crossref","abstract":"Abstract Fractional-order dynamics introduce scale-free memory and non-Markovian behavior into dynamical systems, offering a principled means of modeling long-term temporal dependencies. In this work, we extend the reservoir computing (RC) framework to include fractional-order neurons, yielding fractional-order reservoirs whose dynamics are continuously tunable through the fractional order α . We show that varying α systematically reshapes the reservoir’s information-processing regime: with memory capacity, active information storage, and information transfer each peaking at distinct values of α . This identifies α as a new control parameter of reservoir dynamics, governing a trade-off between memory retention and sensitivity to new inputs. We present a theoretical analysis of fractional-order reservoirs, provide practical software and hardware realizations, and evaluate performance across three benchmark domains: spoken-digit classification, cart-pole control, and diabetes prediction. Together, these results establish fractional-order reservoir computing as a general and effective extension of the RC paradigm.","url":"https://doi.org/10.1038/s44335-026-00070-8","authors":["Tucker Mastin","Niklas Anderson","Silas McNeal","Matthew Tubbin","Christof Teuscher"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-01T07:28:12Z","doi":"10.1038/s44335-026-00070-8","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/icnc52316.2021.9608859","name":"Impulsive Consensus Algorithms for Second-order Multi-agent Formation Based on the Improved Artificial Potential Field","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc52316.2021.9608859","authors":["Yijie Qin","Zhiwei Liu","Lei Fu","Zhaorui Dong","Qihai Sun","Dingxin He"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-29T15:59:32Z","doi":"10.1109/icnc52316.2021.9608859","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1007/s11432-024-4360-9","name":"Bifunctional monolithic transparent device for both neuromorphic computing and omnidirectional self-driven photodetection","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11432-024-4360-9","authors":["Yanyan Chang","Min Jiang","Lian Ji","Yukun Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-26T03:11:26Z","doi":"10.1007/s11432-024-4360-9","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1088/2634-4386/acf1c5","name":"A temporally and spatially local spike-based backpropagation algorithm to enable training in hardware","source":"crossref","abstract":"Abstract Spiking neural networks (SNNs) have emerged as a hardware efficient architecture for classification tasks. The challenge of spike-based encoding has been the lack of a universal training mechanism performed entirely using spikes. There have been several attempts to adopt the powerful backpropagation (BP) technique used in non-spiking artificial neural networks (ANNs): (1) SNNs can be trained by externally computed numerical gradients. (2) A major advancement towards native spike-based learning has been the use of approximate BP using spike-time dependent plasticity with phased forward/backward passes. However, the transfer of information between such phases for gradient and weight update calculation necessitates external memory and computational access. This is a challenge for standard neuromorphic hardware implementations. In this paper, we propose a stochastic SNN based back-prop (SSNN-BP) algorithm that utilizes a composite neuron to simultaneously compute the forward pass activations and backward pass gradients explicitly with spikes. Although signed gradient values are a challenge for spike-based representation, we tackle this by splitting the gradient signal into positive and negative streams. The composite neuron encodes information in the form of stochastic spike-trains and converts BP weight updates into temporally and spatially local spike coincidence updates compatible with hardware-friendly resistive processing units. Furthermore, we characterize the quantization effect of discrete spike-based weight update to show that our method approaches BP ANN baseline with sufficiently long spike-trains. Finally, we show that the well-performing softmax cross-entropy loss function can be implemented through inhibitory lateral connections enforcing a winner take all rule. Our SNN with a two-layer network shows excellent generalization through comparable performance to ANNs with equivalent architecture and regularization parameters on static image datasets like MNIST, Fashion-MNIST, Extended MNIST, and temporally encoded image datasets like Neuromorphic MNIST datasets. Thus, SSNN-BP enables BP compatible with purely spike-based neuromorphic hardware.","url":"https://doi.org/10.1088/2634-4386/acf1c5","authors":["Anmol Biswas","Vivek Saraswat","Udayan Ganguly"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-18T22:30:41Z","doi":"10.1088/2634-4386/acf1c5","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1038/s41467-018-04933-y","name":"Neuromorphic computing with multi-memristive synapses","source":"crossref","abstract":"Abstract Neuromorphic computing has emerged as a promising avenue towards building the next generation of intelligent computing systems. It has been proposed that memristive devices, which exhibit history-dependent conductivity modulation, could efficiently represent the synaptic weights in artificial neural networks. However, precise modulation of the device conductance over a wide dynamic range, necessary to maintain high network accuracy, is proving to be challenging. To address this, we present a multi-memristive synaptic architecture with an efficient global counter-based arbitration scheme. We focus on phase change memory devices, develop a comprehensive model and demonstrate via simulations the effectiveness of the concept for both spiking and non-spiking neural networks. Moreover, we present experimental results involving over a million phase change memory devices for unsupervised learning of temporal correlations using a spiking neural network. The work presents a significant step towards the realization of large-scale and energy-efficient neuromorphic computing systems.","url":"https://doi.org/10.1038/s41467-018-04933-y","authors":["Irem Boybat","Manuel Le Gallo","S. R. Nandakumar","Timoleon Moraitis","Thomas Parnell","Tomas Tuma","Bipin Rajendran","Yusuf Leblebici","Abu Sebastian","Evangelos Eleftheriou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-06-22T06:15:37Z","doi":"10.1038/s41467-018-04933-y","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1088/2634-4386/ae537f","name":"2D-materials for analog in-memory computing: a device-centric review of advantages and limitations","source":"crossref","abstract":"Abstract This review examines the practical advantages of two-dimensional materials for energy-efficient in-memory computing by assembling a curated, experiment-only dataset covering 32 material systems across diverse device structures, mechanisms, and fabrication routes. Energy analysis was standardized using an averaged pulse-based metric, and key figures of merit—switching energy, on/off ratio, endurance, retention, and linearity—were compared against structural and mechanistic factors. Two low-energy-consumption design pathways emerge: ultrathin (&lt;10 nm) two-terminal devices exploiting filament formation for sub- μ s updates and three-terminal heterojunction devices leveraging charge trapping to achieve nA-level programming currents over longer timescales. However, dynamic on/off ratios remain modest and are often overstated by DC sweep data. Endurance improves with shorter switching times, and the most intrinsically linear conductance evolution is observed in three-terminal gate-controlled devices employing charge trapping, Schottky barrier modulation, or ion intercalation. No universal optimum exists, as enhancing one performance metric typically compromises another. Based on the comparative analysis presented in this review, three near-term levers emerge as particularly relevant for translating selective material advantages into reproducible system-level gains: standardized pulsed benchmarking, scalable chemical vapor deposition growth with controlled defects and interfaces, and device–circuit co-design.","url":"https://doi.org/10.1088/2634-4386/ae537f","authors":["Jimin Shim","Jayoung Yoon","Sookyung Shin","Eunsu Hwang","Dokyoung Lee","Moon-Seok Kim","Sungho Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-17T22:58:23Z","doi":"10.1088/2634-4386/ae537f","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.1117/12.3013294","name":"Intelligent imaging microsystems realized by 3D electronic-photonic integrated circuits with embedded neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3013294","authors":["S. J. Ben Yoo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-07T20:09:38Z","doi":"10.1117/12.3013294","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1088/2634-4386/ad5584","name":"Bio-realistic neural network implementation on Loihi 2 with Izhikevich neurons","source":"crossref","abstract":"Abstract Neuromorphic systems are designed to emulate the principles of biological information processing, with the goals of improving computational efficiency and reducing energy usage. A critical aspect of these systems is the fidelity of neuron models and neural networks to their biological counterparts. In this study, we implemented the Izhikevich neuron model on Intel’s Loihi 2 neuromorphic processor. The Izhikevich neuron model offers a more biologically accurate alternative to the simpler leaky-integrate and fire model, which is natively supported by Loihi 2. We compared these two models within a basic two-layer network, examining their energy consumption, processing speeds, and memory usage. Furthermore, to demonstrate Loihi 2’s ability to realize complex neural structures, we implemented a basal ganglia circuit to perform a Go/No-Go decision-making task. Our findings demonstrate the practicality of customizing neuron models on Loihi 2, thereby paving the way for constructing spiking neural networks that better replicate biological neural networks and have the potential to simulate complex cognitive processes.","url":"https://doi.org/10.1088/2634-4386/ad5584","authors":["Recep Buğra Uludağ","Serhat Çağdaş","Yavuz Selim İşler","Neslihan Serap Şengör","İsmail Aktürk"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-07T22:26:50Z","doi":"10.1088/2634-4386/ad5584","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/isvlsi65124.2025.11130347","name":"Bio-Inspired Computing with Emerging Devices: Bridging 2D Materials and Neuromorphic Architectures","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isvlsi65124.2025.11130347","authors":["Matteo Farronato","Piergiulio Mannocci","Alessandro Milozzi","Christian Monzio Compagnoni","Daniele Ielmini"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-27T18:20:15Z","doi":"10.1109/isvlsi65124.2025.11130347","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.21203/rs.3.rs-1019162/v1","name":"Multi-level Memristors based on Two-dimensional Electron Gases in Oxide Heterostructures for High Precision Neuromorphic Computing","source":"preprints","abstract":"Abstract Memristors are essential elements for hardware implementation of artificial neural networks. The key functionality of the memristors is to realize multiple non-volatile conductance states with high precision. However, the variation of device conductance limits the number of allowed states. Since actual data for neural network training inherently have a non-uniform distribution, the insufficient number of conductance states and the resultant inaccurate weight quantization may generate significant errors in the memristor-based computation. Herein, we demonstrate a multi-level memristor based on two-dimensional electron gas in a Pt/LaAlO 3 /SrTiO 3 heterostructure. By redistributing oxygen vacancies, we precisely controlled the tunneling conductance of the device, achieving multiple conductance states (more than 27). The multi-level switching capability and the high retention performance allow us to implement a variance-aware weight quantization (VAQ), designed for improved computing accuracy. We verify that the VAQ provides greater accuracy in image classification process, as compared to conventional uniform quantization. These results provide valuable insight into developing high-precision multi-bit memristors for practical neuromorphic processors.","url":"https://doi.org/10.21203/rs.3.rs-1019162/v1","authors":["Sunwoo Lee","Jaeyoung Jeon","Kitae Eom","Chaehwa Jeong","Yongsoo Yang","Ji-Yong Park","Chang-Beom Eom","Hyungwoo Lee"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.21203/rs.3.rs-1019162/v1","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.1088/2634-4386/ac156f","name":"Modularity and multitasking in neuro-memristive reservoir networks","source":"crossref","abstract":"Abstract The human brain seemingly effortlessly performs multiple concurrent and elaborate tasks in response to complex, dynamic sensory input from our environment. This capability has been attributed to the highly modular structure of the brain, enabling specific task assignment among different regions and limiting interference between them. Here, we compare the structure and functional capabilities of different bio-physically inspired and biological networks. We then focus on the influence of topological properties on the functional performance of highly modular, bio-physically inspired neuro-memristive nanowire networks (NWNs). We perform two benchmark reservoir computing tasks (memory capacity and nonlinear transformation) on simulated networks and show that while random networks outperform NWNs on independent tasks, NWNs with highly segregated modules achieve the best performance on simultaneous tasks. Conversely, networks that share too many resources, such as networks with random structure, perform poorly in multitasking. Overall, our results show that structural properties such as modularity play a critical role in trafficking information flow, preventing information from spreading indiscriminately throughout NWNs.","url":"https://doi.org/10.1088/2634-4386/ac156f","authors":["Alon Loeffler","Ruomin Zhu","Joel Hochstetter","Adrian Diaz-Alvarez","Tomonobu Nakayama","James M Shine","Zdenka Kuncic"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-07-16T18:29:23Z","doi":"10.1088/2634-4386/ac156f","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1007/s40820-025-01756-7","name":"Multifunctional Organic Materials, Devices, and Mechanisms for Neuroscience, Neuromorphic Computing, and Bioelectronics","source":"europepmc","abstract":"Abstract Neuromorphic computing has the potential to overcome limitations of traditional silicon technology in machine learning tasks. Recent advancements in large crossbar arrays and silicon-based asynchronous spiking neural networks have led to promising neuromorphic systems. However, developing compact parallel computing technology for integrating artificial neural networks into traditional hardware remains a challenge. Organic computational materials offer affordable, biocompatible neuromorphic devices with exceptional adjustability and energy-efficient switching. Here, the review investigates the advancements made in the development of organic neuromorphic devices. This review explores resistive switching mechanisms such as interface-regulated filament growth, molecular-electronic dynamics, nanowire-confined filament growth, and vacancy-assisted ion migration, while proposing methodologies to enhance state retention and conductance adjustment. The survey examines the challenges faced in implementing low-power neuromorphic computing, e.g., reducing device size and improving switching time. The review analyses the potential of these materials in adjustable, flexible, and low-power consumption applications, viz. biohybrid spiking circuits interacting with biological systems, systems that respond to specific events, robotics, intelligent agents, neuromorphic computing, neuromorphic bioelectronics, neuroscience, and other applications, and prospects of this technology.","url":"https://doi.org/10.1007/s40820-025-01756-7","authors":["Felix L. Hoch","Qishen Wang","Kian-Guan Lim","Desmond K. Loke"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1007/s40820-025-01756-7","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/jetcas.2016.2533298","name":"Neuromorphic Computing Based on Emerging Memory Technologies","source":"crossref","abstract":"","url":"https://doi.org/10.1109/jetcas.2016.2533298","authors":["Bipin Rajendran","Fabien Alibart"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-03-01T19:21:41Z","doi":"10.1109/jetcas.2016.2533298","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1088/2634-4386/adcbcb","name":"Edge neuro-statistical learning for event-based visual motion detection and tracking in roadside safety systems","source":"crossref","abstract":"Abstract The Vision Zero Program’s purpose is to reduce traffic-related fatalities and serious injuries while promoting equitable, safe, and healthy mobility for all. Ultimately, the challenge is to detect pedestrians during the day and especially at night to implement safety measures. The current study introduces an award-winning low-power solution employing neuromorphic visual sensing and hybrid neuro-statistical processing developed by the Technische Hochschule Nürnberg team for the TinyML Vision Zero San Jose Competition. The solution proposes a novel neuromorphic edge fusion of spiking neural networks and event-based expectation maximization for the detection and tracking of pedestrians and bicyclists. We provide a deployment-ready evaluation of the detection performance along with robustness, energy footprint, and weatherization while emphasizing the advantages of the neuro-statistical edge solution and its city-level scaling capabilities.","url":"https://doi.org/10.1088/2634-4386/adcbcb","authors":["Cristian Axenie","Ertan Halilov","Julian Main","David Weiss"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-11T22:50:37Z","doi":"10.1088/2634-4386/adcbcb","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1149/ma2022-01291298mtgabs","name":"(Invited, Digital Presentation) Approach to Neuromorphic Computing with Ferroelectric Schottky Barrier FETs","source":"crossref","abstract":"Neuromorphic computing inspired by neural network systems of the human brain enables energy efficient computing as a solution of the von Neumann bottleneck. A neural network consists of thousands or even millions of neurons which communicate with each other through connected synapses. Synapses can memorize and process the information simultaneously. The plasticity of a synapse to strengthen or weaken its activity over time make it be capable of learning and computing. Thus, artificial synapses which can emulate functionalities and the plasticity of bio-synapses form the backbone of a neuromorphic computing system. Non-volatile memories with two-terminals, like resistive random-access memory (ReRAM), phase change memory (PCM), are attractive candidates for artificial synapses. However, signal processing and learning cannot be performed simultaneously in these two-terminal synapses. FeFET, similar to a MOSFET structure using CMOS compatible HfO 2 based ferroelectrics as gate oxide forms three-terminal synapses offering high endurance, good performance and high energy efficiency. In contrast to two-terminal devices, three terminal FeFET based synapses can perform processing and learning at the same time. In order to maintain the ferroelectric properties of an HfO 2 based ferroelectric film, high temperature annealing should be avoided after the ferroelectric layer deposition. In this paper, we present ferroelectric NiSi 2 source/drain Schottky barrier (SB) MOSFET (FE-SBFET) structure (Fig.1a), which requires neither ion implantation nor thermal activation of source/drain contacts at high temperatures. FE-SBFETs were fabricated on SOI substrates with a boron-doped (10 16 B/cm -3 ), 55 nm thick top Si layer and a 145 nm thick buried oxide (BOX) layer. Very thin (9 nm) single crystalline NiSi 2 layers which offer superior properties of uniform and stable SB contacts on Si are used at source/drain regions. A gate stack consisting of 10 nm thick Hf 0.5 Zr 0.5 O 2 (HZO) layer and a 40 nm thick TiN layer are deposited by ALD and sputtering, respectively. A rapid thermal annealing at 500 °C is performed to crystallize the HZO into a ferroelectric phase before the gate patterning. The fabricated device has a channel length of 10 µm and a gate width of 10 µm. The overlap between the top gate and NiSi 2 is 6 µm along the channel and 10 µm wide on each side. The ferroelectric polarization modulates both the SB at the source/drain contacts as well as the potential in the channel, thus changing the carrier injection through the SB. The I d -V g transfer characteristics of a p-type FE-SBFET shows a clockwise hysteresis which is caused by the ferroelectric polarization switch. The excitatory post-synaptic current (EPSC), one of the typical short-term synaptic plasticity features for biologic synapses, is characterized by measuring the transient drain currents for a voltage pulse on the gate of a FE-SBFET (Fig.1b). The amplitude of the pulse V AM changes from -0.2 to -1.2 V with a fixed pulse width t pw =1 μs. We found that the EPSC peak value increases linearly with V AM . It shows a very low energy/spike consumption of 2fJ/spike at V AM =-0.2 V, demonstrating a very high energy efficiency. From the EPSC measurements with repeated gate voltage pulses paired-pulse facilitation/depression (PPF/PPD) are characterized showing an exponential decay, similar to biological synapses. The long-term synaptic plasticity of FE-SBFET synapses is characterized by a series repeated identical or non-identical pulses. The later can improve the long-term potentiation/depression (LTP/LTD) symmetry and linearity. The measurements show a large G max /G min ratio, very high endurance and small cycle-to-cycle (CTC) variation (1.06%) due to the perfect contact of NiSi 2 (Fig.1c). The biological neuron-like spike-timing-dependent plasticity (STDP) is characterized for the FE-SBFET synapse. The results show an asymmetric anti-Hebbian STDP, which is one of the biological S","url":"https://doi.org/10.1149/ma2022-01291298mtgabs","authors":["Qing-Tai Zhao","Fengben Xi","Yi Han","Jin Hee Bae","Detlev Gruetzmacher"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-07-14T16:55:29Z","doi":"10.1149/ma2022-01291298mtgabs","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1145/3183584.3183611","name":"Efficient hardware implementation of cellular neural networks with powers-of-two based incremental quantization","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3183584.3183611","authors":["Xiaowei Xu","Qing Lu","Tianchen Wang","Jinglan Liu","Yu Hu","Yiyu Shi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-04-25T12:58:50Z","doi":"10.1145/3183584.3183611","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.23919/date51398.2021.9473929","name":"Reliability-Driven Neuromorphic Computing Systems Design","source":"crossref","abstract":"","url":"https://doi.org/10.23919/date51398.2021.9473929","authors":["Qi Xu","Junpeng Wang","Hao Geng","Song Chen","Xiaoqing Wen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-08-24T22:11:46Z","doi":"10.23919/date51398.2021.9473929","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1016/j.aei.2025.103300","name":"Neuromorphic computing-enabled generalized machine fault diagnosis with dynamic vision","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.aei.2025.103300","authors":["Changhao Liu","Xiang Li","Xinrui Chen","Samir Khan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-04T14:28:16Z","doi":"10.1016/j.aei.2025.103300","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1002/aelm.202500250","name":"Neuromorphic Computing with Memcapacitors: Advancements, Challenges, and Future Directions","source":"crossref","abstract":"Abstract Modern applications demand immense data processing and computational power, yet conventional architectures, constrained by the Von Neumann bottleneck and data presentation, struggle to meet these requirements. This has driven the rise of neuromorphic computing, which mimics the biological nervous system through spike‐encoded data and threshold‐based computations for high energy efficiency. However, traditional hardware (CMOS transistors) designed for continuous computations fails to harness this potential fully, necessitating specialized neuromorphic hardware alternatives. Memristors have emerged as key components for neuromorphic hardware but suffer from high static power consumption, sneak‐path currents, and reliance on selector devices. In contrast, memcapacitors provide a more efficient alternative, leveraging high resistance and charge‐domain computations to overcome these limitations. This review presents a comprehensive analysis of memcapacitors for neuromorphic applications, covering capacitive switching mechanisms and materials, key hardware considerations, and recent advancements. It explores their role in artificial synapses, physical reservoir computing, and crossbar‐based accelerators, highlighting their potential for scalable and low‐power neuromorphic systems. Finally, key challenges and future research directions are discussed, particularly in materials engineering, device fabrication, and large‐scale system integration, positioning memcapacitors as promising candidates for next‐generation neuromorphic computing.","url":"https://doi.org/10.1002/aelm.202500250","authors":["Nada AbuHamra","Muhammad Umair Khan","Eman Hassan","Mahmoud Al Qutayri","Baker Mohammad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-09T04:52:31Z","doi":"10.1002/aelm.202500250","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/isqed51717.2021.9424267","name":"Low-power Analog and Mixed-signal IC Design of Multiplexing Neural Encoder in Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isqed51717.2021.9424267","authors":["Honghao Zheng","Nima Mohammadi","Kangjun Bai","Yang Yi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-05-11T00:09:51Z","doi":"10.1109/isqed51717.2021.9424267","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1007/978-3-031-65549-4_8","name":"Case Studies and Real-World Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-65549-4_8","authors":["Ali Akbar Firoozi","Ali Asghar Firoozi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-26T13:01:53Z","doi":"10.1007/978-3-031-65549-4_8","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1145/3649153.3649199","name":"Clustering and Allocation of Spiking Neural Networks on Crossbar-Based Neuromorphic Architecture","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3649153.3649199","authors":["Ilknur Mustafazade","Nagarajan Kandasamy","Anup Das"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-02T10:21:29Z","doi":"10.1145/3649153.3649199","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1109/nano63165.2025.11113720","name":"SkyNeu: Energy Efficient Antiferromagnetic Skyrmion Based Artificial Neuron for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nano63165.2025.11113720","authors":["Ravish Kumar Raj","Namita Bindal","Vishvendra Singh Poonia","Vito Puliafito","Giovanni Finocchio","Farshad Moradi","Sonal Shreya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-12T17:52:36Z","doi":"10.1109/nano63165.2025.11113720","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/iscas.2017.8050222","name":"Neuromorphic devices and architectures for next-generation cognitive computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas.2017.8050222","authors":["Geoffrey W. Burr","Pritish Narayanan","Robert M. Shelby","Stefano Ambrogio","Hsinyu Tsai","Scott L. Lewis","Kohji Hosokawa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-09-28T20:33:32Z","doi":"10.1109/iscas.2017.8050222","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1166/mex.2023.2457","name":"TiW/SiO<sub>X</sub>:Al/TiW memristor with negative differential resistance effect for neuromorphic computing","source":"crossref","abstract":"Memristors, acting as artificial synapses, are proposed to be a promising candidate for neuromorphic computing applications. In this work, the CMOS process-compatible TiW/SiO X :Al/TiW memristor with negative differential resistance (NDR) effect is explored for this application. Nonpolar switching with a 340 on/off ratio, data retention beyond 10 6 s, and endurance of 10 6 cycles are realized. The device shows excellent analog behavior with nonlinearities of 1.69 and 0.65 of long-term potentiation and depression, respectively, under identical pulse stimuli. The synaptic features such as long-term potentiation (LTP), long-term depression (LTD), spike-timing-dependent plasticity (STDP), and paired-pulse facilitation (PPF) are mimicked. Moreover, on the basis of the symmetry and linearity of the conductance of TiW/SiO X :Al/TiW memristor, the neural network simulation for supervised learning presents successful pattern recognition, with an accuracy of 93.11% achieved after 20 iterations. It is proposed that the nonpolar NDR switching originates from the discontinuous Al metal nanoparticles that form deeply localized states in the energy band and result in the trap/de-trap of electronic carriers. Overall, this memristor with the NDR effect presents a unique way to simulate artificial synapse behavior for neuromorphic computing.","url":"https://doi.org/10.1166/mex.2023.2457","authors":["Facai Wu","Tseung-Yuen Tseng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-01T04:38:07Z","doi":"10.1166/mex.2023.2457","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.23919/date51398.2021.9473964","name":"Exploring Spike-Based Learning for Neuromorphic Computing: Prospects and Perspectives","source":"crossref","abstract":"","url":"https://doi.org/10.23919/date51398.2021.9473964","authors":["Nitin Rathi","Amogh Agrawal","Chankyu Lee","Adarsh Kumar Kosta","Kaushik Roy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-08-24T22:11:46Z","doi":"10.23919/date51398.2021.9473964","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.62311/nesx/92489","name":"High‐Performance Neuromorphic computing, quantum dot semiconductors, 2D materials, spintronics, and semiconductors for AI, 5G and beyond","source":"crossref","abstract":"Abstract: This chapter explores cutting-edge advancements in high-performance computing technologies, focusing on neuromorphic computing, quantum dot semiconductors, 2D materials, spintronics, and next-generation semiconductors for AI, 5G, and beyond. Neuromorphic computing, inspired by the brain’s neural architecture, enables energy-efficient real-time learning and decision-making, revolutionizing AI and robotics. Quantum dot semiconductors enhance device performance in displays, photonics, and quantum computing, while 2D materials such as graphene and MoS₂ offer extraordinary electrical and mechanical properties for flexible electronics, energy storage, and semiconductors. Spintronics, which leverages the spin of electrons, advances data storage and AI hardware, and promises breakthroughs in quantum computing. Next-generation semiconductors are driving innovations in AI acceleration and 5G networks, with the potential to shape future technologies like 6G and edge computing. The integration of these technologies is set to transform industries, enable scalable high-performance systems, and contribute to more sustainable, energy-efficient computing infrastructure. Keywords: neuromorphic computing, quantum dot semiconductors, 2D materials, spintronics, AI, 5G, high-performance computing, flexible electronics, energy storage, quantum computing, semiconductors, graphene, MoS₂, photonics, edge computing, real-time learning, sustainability, machine learning, AI acceleration, quantum cryptography.","url":"https://doi.org/10.62311/nesx/92489","authors":["Murali Krishna Pasupuleti"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-01T06:40:52Z","doi":"10.62311/nesx/92489","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1007/978-3-319-28658-7_33","name":"A Technique of Analog Circuits Testing and Diagnosis Based on Neuromorphic Classifier","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-28658-7_33","authors":["Sergey Mosin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-24T08:31:41Z","doi":"10.1007/978-3-319-28658-7_33","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/iedm45741.2023.10413803","name":"Engineering the kinetics of redox-based memristive devices for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iedm45741.2023.10413803","authors":["R. Dittmann","A. Sarantopoulos","C. Bengel","A. Gutsche","F. Cüppers","S. Hoffmann-Eifert","S. Menzel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-07T13:36:36Z","doi":"10.1109/iedm45741.2023.10413803","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/asscc.2018.8579333","name":"A 6.8 TOPS/W Energy Efficiency, 1.5µW Power Consumption, Pulse Width Modulation Neuromorphic Circuits for Near-Data Computing with SSD","source":"crossref","abstract":"","url":"https://doi.org/10.1109/asscc.2018.8579333","authors":["Kota Tsurumi","Kenta Suzuki","Ken Takeuchi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-01-08T17:59:07Z","doi":"10.1109/asscc.2018.8579333","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/icnwc68145.2026.11518477","name":"A Hybrid Approach Combining Quantum and Neuromorphic Computing for Live City Traffic Management","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnwc68145.2026.11518477","authors":["Shramit Sarupya Swain","Ramesh Sekaran","Girisha G S","Jeeva S","K.Vengatesan","Bharathiraja Nagu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-19T19:47:37Z","doi":"10.1109/icnwc68145.2026.11518477","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1002/advs.202303817","name":"Memcapacitor Crossbar Array with Charge Trap NAND Flash Structure for Neuromorphic Computing","source":"crossref","abstract":"Abstract The progress of artificial intelligence and the development of large‐scale neural networks have significantly increased computational costs and energy consumption. To address these challenges, researchers are exploring low‐power neural network implementation approaches and neuromorphic computing systems are being highlighted as potential candidates. Specifically, the development of high‐density and reliable synaptic devices, which are the key elements of neuromorphic systems, is of particular interest. In this study, an 8 × 16 memcapacitor crossbar array that combines the technological maturity of flash cells with the advantages of NAND flash array structure is presented. The analog properties of the array with high reliability are experimentally demonstrated, and vector‐matrix multiplication with extremely low error is successfully performed. Additionally, with the capability of weight fine‐tuning characteristics, a spiking neural network for CIFAR‐10 classification via off‐chip learning at the wafer level is implemented. These experimental results demonstrate a high level of accuracy of 92.11%, with less than a 1.13% difference compared to software‐based neural networks (93.24%).","url":"https://doi.org/10.1002/advs.202303817","authors":["Sungmin Hwang","Junsu Yu","Min Suk Song","Hwiho Hwang","Hyungjin Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-27T02:08:45Z","doi":"10.1002/advs.202303817","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/tcpmt.2025.3622860","name":"Foreword: Special Section on Advances in Heterogeneous Integration for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tcpmt.2025.3622860","authors":["Hanzhi Ma","Shaloo Rakheja"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-24T19:00:40Z","doi":"10.1109/tcpmt.2025.3622860","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1103/physrevapplied.11.014020","name":"Low-Power Microwave Relaxation Oscillators Based on Phase-Change Oxides for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1103/physrevapplied.11.014020","authors":["B. Zhao","J. Ravichandran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-01-10T11:47:08Z","doi":"10.1103/physrevapplied.11.014020","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.1088/2634-4386/ad4052","name":"Cycle equivalence classes, orthogonal Weingarten calculus, and the mean field theory of memristive systems","source":"crossref","abstract":"Abstract It has been recently noted that for a class of dynamical systems with explicit conservation laws represented via projector operators, the dynamics can be understood in terms of lower dimensional equations. This is the case, for instance, of memristive circuits. Memristive systems are important classes of devices with wide-ranging applications in electronic circuits, artificial neural networks, and memory storage. We show that such mean-field theories can emerge from averages over the group of orthogonal matrices, interpreted as cycle-preserving transformations applied to the projector operator describing Kirchhoff’s laws. Our results provide insights into the fundamental principles underlying the behavior of resistive and memristive circuits and highlight the importance of conservation laws for their mean-field theories. In addition, we argue that our results shed light on the nature of the critical avalanches observed in quasi-two-dimensional nanowires as boundary phenomena.","url":"https://doi.org/10.1088/2634-4386/ad4052","authors":["F Caravelli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-18T22:24:12Z","doi":"10.1088/2634-4386/ad4052","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/omn61224.2024.10685224","name":"Electrically Programable Tamm Plasmon for Broadband Optical Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/omn61224.2024.10685224","authors":["Joo Hwan Ko","Dong Hyun Seo","Se Yeon Kim","Young Min Song"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-27T18:27:49Z","doi":"10.1109/omn61224.2024.10685224","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1007/978-3-031-42478-6_4","name":"Is Neuromorphic Computing the Key to Power-Efficient Neural Networks: A Survey","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-42478-6_4","authors":["Muhammad Hamis Haider","Hao Zhang","S. Deivalaskhmi","G. Lakshmi Narayanan","Seok-Bum Ko"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-13T07:02:00Z","doi":"10.1007/978-3-031-42478-6_4","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1063/12.0043535","name":"New carrier for neuromorphic computing: Multimodal response and learning mechanism of organic field-effect transistor-based synaptic devices","source":"crossref","abstract":"","url":"https://doi.org/10.1063/12.0043535","authors":["Weiyi Xia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-06T17:00:34Z","doi":"10.1063/12.0043535","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1016/j.matlet.2026.140662","name":"WSe2 nanosheet memristors with long-term synaptic plasticity for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.matlet.2026.140662","authors":["Ying Li","Jing Zhang","Haowen Meng","Xia Xiao","Jiajun Guo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-14T13:13:33Z","doi":"10.1016/j.matlet.2026.140662","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1103/physrevapplied.5.054011","name":"Electro-Photo-Sensitive Memristor for Neuromorphic and Arithmetic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1103/physrevapplied.5.054011","authors":["P. Maier","F. Hartmann","M. Emmerling","C. Schneider","M. Kamp","S. Höfling","L. Worschech"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-05-17T18:08:30Z","doi":"10.1103/physrevapplied.5.054011","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.1063/5.0177232","name":"Extremely energy-efficient, magnetic field-free, skyrmion-based memristors for neuromorphic computing","source":"crossref","abstract":"The human brain can process information more efficiently than computers due to the dynamics of neurons and synapses. Mimicking such a system can lead to the practical implementation of artificial spiking neural networks. Spintronic devices have been shown to be an ideal solution for realizing the hardware required for neuromorphic computing. Skyrmions prove to be an effective candidate as information carriers owing to their topological protection and particle-like nature. Ferrimagnet and antiferromagnet-based spintronics have been employed previously to obtain an ultrafast simulation of artificial synapses and neurons. Here, we have proposed a ferromagnetic device of stack Ta3nmPt3nmCu0.65nmCo0.5nmPt1nm that is capable of ultrafast simulation of artificial neurons and synapses, owing to the high velocity of the stabilized skyrmions in the system. Electrical pulses of nanosecond pulse width were used to control the accumulation and dissipation of skyrmions in the system, analogous to the variations in the synaptic weights. Lateral structure inversion asymmetry is used to bring about a field-free switching in the system, leading to an energy-efficient switching process. Magnetic field-free deterministic switching and low pulse width current pulses drastically reduce energy consumption by 106 times compared to the existing ferromagnet-based neuromorphic devices. Artificial neuron, synapse, and memristor functionalities have been reproduced on the same device with characteristic time scales and field-free switching, better than any existing ferromagnet-based neuromorphic devices. The results recognize ferromagnet-based skyrmions as viable candidates for ultrafast neuromorphic spintronics capable of executing cognitive tasks with extremely high efficiency.","url":"https://doi.org/10.1063/5.0177232","authors":["Ajin Joy","Sreyas Satheesh","P. S. Anil Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-22T13:50:40Z","doi":"10.1063/5.0177232","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1142/9789811290084_0002","name":"Foundations of Digital Computability","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789811290084_0002","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-26T02:06:27Z","doi":"10.1142/9789811290084_0002","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1515/9783111545950-009","name":"1619 Functional connectivity in brain: an NEGF framework for neural signal generation/transmission","source":"crossref","abstract":"","url":"https://doi.org/10.1515/9783111545950-009","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-06T19:15:47Z","doi":"10.1515/9783111545950-009","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.29026/oet.2025.250011","name":"Integrated photonic synapses, neurons, memristors, and neural networks for photonic neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.29026/oet.2025.250011","authors":["Shufei Han","Weihong Shen","Min Gu","Qiming Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-09T08:53:24Z","doi":"10.29026/oet.2025.250011","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1142/9789811290084_0004","name":"Foundations of Real Computability","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789811290084_0004","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-26T02:06:27Z","doi":"10.1142/9789811290084_0004","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1088/0957-4484/21/17/175202","name":"Nanotube devices based crossbar architecture: toward neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0957-4484/21/17/175202","authors":["W S Zhao","G Agnus","V Derycke","A Filoramo","J-P Bourgoin","C Gamrat"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-04-07T05:58:28Z","doi":"10.1088/0957-4484/21/17/175202","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1016/j.carbon.2025.120865","name":"The gate length size impact on the performance of carbon-nanotube-based 1T1R configuration for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.carbon.2025.120865","authors":["Chen Hu","Songang Peng","Xu Han","Yanqing Qiu","Yanming Liu","He Tian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-22T18:45:52Z","doi":"10.1016/j.carbon.2025.120865","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1088/2634-4386/ae405e","name":"Efficient transformer adaptation for analog in-memory computing via low-rank adapters","source":"crossref","abstract":"Abstract Analog in-memory computing (AIMC) offers a promising solution to the von Neumann bottleneck. However, deploying transformer models on AIMC remains challenging due to their inherent need for flexibility and adaptability across diverse tasks. For the benefits of AIMC to be fully realized, weights of static vector-matrix multiplications must be mapped and programmed to analog devices in a weight-stationary manner. This poses two challenges for adapting a base network to hardware and downstream tasks: (i) conventional analog hardware-aware (AHWA) training requires retraining the entire model, and (ii) reprogramming analog devices is both time- and energy-intensive. To address these issues, we propose AHWA low-rank adaptation (AHWA-LoRA) training, a novel approach for efficiently adapting transformers to AIMC hardware. AHWA-LoRA training keeps the analog weights fixed as meta-weights and introduces lightweight external LoRA modules for both hardware and task adaptation. We validate AHWA-LoRA training on SQuAD v1.1 and the GLUE benchmark, demonstrate its scalability to larger models, and show its effectiveness in instruction tuning and reinforcement learning. We further evaluate a practical deployment scenario that balances AIMC tile latency with digital LoRA processing using optimized pipeline strategies, with RISC-V-based programmable multi-core accelerators. This hybrid architecture achieves efficient transformer inference with only a 4% per-layer overhead compared to a fully AIMC implementation.","url":"https://doi.org/10.1088/2634-4386/ae405e","authors":["Chen Li","Elena Ferro","Corey Lammie","Manuel Le Gallo","Irem Boybat","Bipin Rajendran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-02T22:51:18Z","doi":"10.1088/2634-4386/ae405e","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1117/12.3029400","name":"Harnessing ion tuning mechanisms for neuromorphic computing: from artificial synapses to dynamically reconfigurable architectures","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3029400","authors":["A. Alec T. Talin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-02T18:26:52Z","doi":"10.1117/12.3029400","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1364/cleo_at.2020.jf2a.4","name":"Progress in Superconducting Optoelectronic Networks for Neuromorphic Computing","source":"crossref","abstract":"We have proposed a superconducting opto-electronic platform for neuromorphic computing utilizing semiconductor light sources coupled to integrated waveguides for communication, and superconducting detectors and electronics for efficient computation. Here we summarize the recent experimental progress.","url":"https://doi.org/10.1364/cleo_at.2020.jf2a.4","authors":["S. M. Buckley","J. T. Chiles","A. N. McCaughan","A. N. Tait","R. P. Mirin","S. W. Nam","J. M. Shainline"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-11T20:34:19Z","doi":"10.1364/cleo_at.2020.jf2a.4","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1038/s44306-023-00006-z","name":"Anomalous hall and skyrmion topological hall resistivity in magnetic heterostructures for the neuromorphic computing applications","source":"crossref","abstract":"Abstract Topologically protected spin textures, such as magnetic skyrmions, have shown the potential for high-density data storage and energy-efficient computing applications owing to their particle-like behavior, small size, and low driving current requirements. Evaluating the writing and reading of the skyrmion’s magnetic and electrical characteristics is crucial to implementing these devices. In this paper, we present the magnetic heterostructure Hall bar device and study the anomalous Hall and topological Hall signals in these devices. Using different measurement techniques, we investigate the magnetic and electrical characteristics of the magnetic structure. We measure the skyrmion topological resistivity and the magnetic field at different temperatures. MFM imaging and micromagnetic simulations further explain the anomalous Hall and topological Hall resistivity characteristics at various magnetic fields and temperatures. The study is extended to propose a skyrmion-based synaptic device showing spin-orbit torque-controlled plasticity. The resistance states are read using the anomalous Hall measurement technique. The device integration in a neuromorphic circuit is simulated in a 3-layer feedforward artificial neural network ANN. Based on the proposed synapses, the neural network is trained and tested on the MNIST data set, where a recognition accuracy performance of about 90% is achieved. Considering the nanosecond reading/writing time scale and a good system level performance, these devices exhibit a substantial prospect for energy-efficient neuromorphic computing.","url":"https://doi.org/10.1038/s44306-023-00006-z","authors":["Aijaz H. Lone","Xuecui Zou","Debasis Das","Xuanyao Fong","Gianluca Setti","Hossein Fariborzi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-12T11:04:38Z","doi":"10.1038/s44306-023-00006-z","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1007/978-3-031-65549-4_5","name":"Advanced Predictive Models for Natural Disasters","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-65549-4_5","authors":["Ali Akbar Firoozi","Ali Asghar Firoozi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-26T13:01:53Z","doi":"10.1007/978-3-031-65549-4_5","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.38124/ijisrt/25aug550","name":"Energetic Signatures and Quantum States: Toward a Consciousness-Driven Architecture for  Neuromorphic Computing","source":"crossref","abstract":"We introduce a neuromorphic approach to representing the energetic signature of a quantum state. In this scheme, a quantum Hamiltonian is decomposed into a linear combination of energies that we term eigenergy components. A more widely understood concept of eigenspectra emerges when the quantum state itself is an eigenstate of the Hamiltonian. Eigenenergy components of a general state are then obtained by factoring the corresponding energy eigenvalue with the associated eigenstate probability. The complex behavior of the components collectively defines the energetic signature of the state. From such a signature, the original quantum state can be recovered when energetic constraints are lifted. A solid-state mixed-signal implementation is described that leverages properties of the co-integrated analog neuromorphic–digital platform BrainScaleS-2, regarded as world-leading in neuromorphic hardware. Here, spiking neurons realize the linear coupling between components and quantum states and convert a quantum Hamiltonian to a temporal eigenergy distribution through an address-event representation. From this standard communication protocol, the eigenergy components—encoded temporally in the resulting spike pattern—are extracted again by downstream cores. In the neuromorphic output, an energetic signature is mapped to a population of leaky integrate-and-fire neurons that asynchronously evokes a corresponding spiking probability. The functionality of the architecture is demonstrated for Hamiltonians—sparse, dense, and low rank—that arise from models of bilayer graphene relationships [1]. Quantum states remain at the core of various means of information encoding and processing in domains such as communication, sensing, and computing. Algorithms in these domains are usually expressed in mathematical frameworks based on the axioms of quantum theory. Encoded data and subsequent manipulations are regarded as determined by a wholly different probabilistic rule than those found in classical digital computers [2]. Using standard digital hardware, access to states and associated operations therefore poses disproportionate challenges. Co-integrated digital-analog neuromorphic computing architectures present an alternative, reminiscent of single photons transmitting information through an array of gates on a linear-optical circuit. They qualify— as physically motivated data structures—for engineerable representations of quantum states. Mapping quantum systems directly to spiking activity and its propagation through dedicated emulation circuits offers a distinctively novel platform for processing quantum information that operates in a natural synchronous-to-asynchronous mode.","url":"https://doi.org/10.38124/ijisrt/25aug550","authors":["Aruna Thethali","Kranthi Kiran Mandava"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-22T07:00:40Z","doi":"10.38124/ijisrt/25aug550","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1088/2634-4386/ae44c6","name":"Reservoir computing with a heterogeneous distribution of ionic nanofluidic memristors","source":"crossref","abstract":"Abstract Nanofluidic memristive systems exhibit the nonlinear behavior and the short-time plasticity needed for reservoir computing (RC) networks. They use ions as information carriers and operate in an electrochemical environment, in resemblance to the biological synapses. Here we present simulation results of an RC model implementation using a parallel array of memristive nanopores as reservoir. Each nanopore of the array is simulated under distinct chemical conditions using an experimentally justified theoretical model. We demonstrate the potential of the proposed network by performing three different RC tasks: sine wave nonlinear transformation, waveform classification, and forecasting of the Mackey–Glass chaotic time series.","url":"https://doi.org/10.1088/2634-4386/ae44c6","authors":["Sergio Portillo","Patricio Ramirez","Anthony Dougman Cho","Zuzanna Siwy","Salvador Mafe","Javier Cervera"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-11T22:51:18Z","doi":"10.1088/2634-4386/ae44c6","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.2139/ssrn.5537461","name":"Dual-mode Transparent Synaptic Device Based on CsCu2I3 for Neuromorphic Computing and Visual Processing","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5537461","authors":["Lingling Zhang","Zhenyu Li","Juan Luo","Jinli Fu","Chunli Jiang","Chunhua Luo","Chang Yang","Xiaodong Tang","Hechun Lin","Yan Chen","Hui Peng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-27T16:38:02Z","doi":"10.2139/ssrn.5537461","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/irps48203.2023.10117810","name":"Reliable FeFET-based Neuromorphic Computing through Joint Modeling of Cycle-to-Cycle Variability, Device-to-Device Variability, and Domain Stochasticity","source":"crossref","abstract":"","url":"https://doi.org/10.1109/irps48203.2023.10117810","authors":["Simon Thomann","Albi Mema","Kai Ni","Hussam Amrouch"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-15T17:50:57Z","doi":"10.1109/irps48203.2023.10117810","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.33612/diss.1069240777","name":"Neuromorphic Embedded Processing for Touch","source":"crossref","abstract":"","url":"https://doi.org/10.33612/diss.1069240777","authors":["Michele Mastella"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-06T10:37:26Z","doi":"10.33612/diss.1069240777","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/icnc59488.2023.10462828","name":"Memristive Binary Firefly Algorithm for White Lung Images Segmentation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462828","authors":["Jiarun Shen","Yongbin Yu","Xiangxiang Wang","Xiao Feng","Xuefeng Zhong","Jingya Wang","Xinyi Han"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462828","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/mdat.2023.3270126","name":"Fault-Tolerant Neuromorphic Computing With Memristors Using Functional ATPG for Efficient Recalibration","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mdat.2023.3270126","authors":["Soyed Tuhin Ahmed","Mehdi B. Tahoori"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-03T18:51:29Z","doi":"10.1109/mdat.2023.3270126","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.29363/nanoge.neumatdecas.2023.025","name":"Ferroelectric Memcapacitor-based Reservoir Computing for High-efficiency Human-Computer Interface","source":"crossref","abstract":"","url":"https://doi.org/10.29363/nanoge.neumatdecas.2023.025","authors":["Mengjiao Pei","Ying Zhu","Siyao Liu","Hangyuan Cui","Yating Li","Yang Yan","Qing Wan","Yun Li","Changjin Wan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-02-01T09:31:42Z","doi":"10.29363/nanoge.neumatdecas.2023.025","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1088/1674-4926/24040038","name":"InGaZnO-based photoelectric synaptic devices for neuromorphic computing","source":"crossref","abstract":"Abstract Photoelectric synaptic devices could emulate synaptic behaviors utilizing photoelectric effects and offer promising prospects with their high-speed operation and low crosstalk. In this study, we introduced a novel InGaZnO-based photoelectric memristor. Under both electrical and optical stimulation, the device successfully emulated synaptic characteristics including excitatory postsynaptic current (EPSC), paired-pulse facilitation (PPF), long-term potentiation (LTP), and long-term depression (LTD). Furthermore, we demonstrated the practical application of our synaptic devices through the recognition of handwritten digits. The devices have successfully shown their ability to modulate synaptic weights effectively through light pulse stimulation, resulting in a recognition accuracy of up to 93.4%. The results illustrated the potential of IGZO-based memristors in neuromorphic computing, particularly their ability to simulate synaptic functionalities and contribute to image recognition tasks.","url":"https://doi.org/10.1088/1674-4926/24040038","authors":["Jieru Song","Jialin Meng","Tianyu Wang","Changjin Wan","Hao Zhu","Qingqing Sun","David Wei Zhang","Lin Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-04T12:11:05Z","doi":"10.1088/1674-4926/24040038","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.059Z"},{"id":"doi:10.1109/cicc53496.2022.9772788","name":"A 915–1220 TOPS/W Hybrid In-Memory Computing based Image Restoration and Region Proposal Integrated Circuit for Neuromorphic Vision Sensors in 65nm CMOS","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cicc53496.2022.9772788","authors":["Xueyong Zhang","Arindam Basu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-05-18T15:37:56Z","doi":"10.1109/cicc53496.2022.9772788","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1016/j.measurement.2024.116532","name":"Integrating nanodevice and neuromorphic computing for enhanced magnetic anomaly detection","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.measurement.2024.116532","authors":["Yijie Qin","Zeyu Peng","Linliang Miao","Zijie Chen","Jun Ouyang","Xiaofei Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-18T17:00:48Z","doi":"10.1016/j.measurement.2024.116532","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/ted.2022.3220492","name":"Skyrmion-Magnetic Tunnel Junction Synapse With Long-Term and Short-Term Plasticity for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ted.2022.3220492","authors":["Aijaz H. Lone","H. Fariborzi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-21T21:08:02Z","doi":"10.1109/ted.2022.3220492","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/iccad.2014.7001330","name":"Reduction and IR-drop compensations techniques for reliable neuromorphic computing systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccad.2014.7001330","authors":["Beiye Liu","Hai Li","Yiran Chen","Xin Li","Tingwen Huang","Qing Wu","Mark Barnell"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-01-13T20:11:15Z","doi":"10.1109/iccad.2014.7001330","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.059Z"},{"id":"doi:10.1364/ome.477577","name":"Emerging Optical Materials, Devices and Systems for Photonic Neuromorphic Computing: introduction to special issue","source":"crossref","abstract":"This is an introduction to the feature issue of Optical Materials Express on Emerging Optical Materials, Devices and Systems for Photonic Neuromorphic Computing.","url":"https://doi.org/10.1364/ome.477577","authors":["Antonio Hurtado","Bruno Romeira","Sonia Buckley","Zengguang Cheng","Bhavin J. Shastri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-05T14:00:10Z","doi":"10.1364/ome.477577","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.059Z"},{"id":"doi:10.1109/icee56203.2022.10118253","name":"Mimicking Synaptic Behaviors with Junctionless Transistor for Low Power Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icee56203.2022.10118253","authors":["Md. Hasan Raza Ansari","Hanrui Li","Nazek El-Atab"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-15T17:51:05Z","doi":"10.1109/icee56203.2022.10118253","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.059Z"},{"id":"doi:10.1109/icnc52316.2021.9608243","name":"Stability Analysis of Memristor Neural Networks with State-Dependent Delay","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc52316.2021.9608243","authors":["Yue Chen","Song Zhu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-29T20:59:32Z","doi":"10.1109/icnc52316.2021.9608243","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.059Z"},{"id":"doi:10.7567/ssdm.2023.ps-2-23","name":"Improved Synaptic Plasticity of Li Ion-Gated Transistors with Mg-Doped LiCoO2 Channel for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.7567/ssdm.2023.ps-2-23","authors":["Samapika Mallik","Tohru Tsuruoka","Takashi Tsuchiya","Kazuya Terabe"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-11T20:18:45Z","doi":"10.7567/ssdm.2023.ps-2-23","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.059Z"},{"id":"doi:10.1109/icaiss68683.2026.11526061","name":"Energy-Autonomous Neuromorphic Seizure Detection: Implementing Dynamic Hyperdimensional Computing (DynHD) on RISC-V BL616 Microcontrollers","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icaiss68683.2026.11526061","authors":["C. Sivamani","Gokulraj P","Vishnu N R","Enbatamil E"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-26T19:39:19Z","doi":"10.1109/icaiss68683.2026.11526061","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.059Z"},{"id":"doi:10.1007/978-3-031-61298-5_7","name":"Machine Learning Based Delta Sigma Modulator Using Memristor for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-61298-5_7","authors":["Md Noorullah Khan","E. Srinivas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-23T11:01:45Z","doi":"10.1007/978-3-031-61298-5_7","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.059Z"},{"id":"doi:10.1007/978-981-92-1599-7_10","name":"The Research on Mobile Edge Computing in Content Delivery Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-92-1599-7_10","authors":["Ping Jiang","Haixia Li","Jun Cheng","Jiarui Wu","Yuanying Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-14T18:19:06Z","doi":"10.1007/978-981-92-1599-7_10","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.059Z"},{"id":"doi:10.2139/ssrn.5172997","name":"Wavelength-Selective Synaptic Devices Based on Graphdiyne/Wse2 for Multi-Color Image Recognition and Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5172997","authors":["Hongyu Tang","Weiqi Shi","Wanlin Jiang","Gaoyuan Wang","Mengyuan Tang","Zihao Cai","Ruiteng Li","Shuai Wu","Guoqi Zhang","Jian Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-10T18:38:52Z","doi":"10.2139/ssrn.5172997","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.059Z"},{"id":"doi:10.1039/bk9781839169946-00498","name":"Halide Perovskites for Neuromorphic Computing","source":"crossref","abstract":"The next generation of neuromorphic computing, which is related to emulating the neural structure and operation of the human brain, will extend into areas that correspond to human cognition, such as interpretation and autonomous adaptation. Progress in materials and devices is critical to address novel situations and abstraction to automate ordinary human activities. Halide perovskites constitute a family of materials with many superior properties, such as long charge-carrier diffusion length, strong light absorptivity, ambipolar charge transport, ionic conductivity and solution processability. They have been successfully implemented in broad applications such as photovoltaics, light-emitting diodes and photodetectors. Their high mobility renders this class of solution-processed materials appropriate for application in field-effect transistors, whereas their usually present hysteresis, which may originate from ferroelectricity, charge-carrier traps, and migration of ions, has been explored for application in artificial synapses, which require gradual modulation of responses.","url":"https://doi.org/10.1039/bk9781839169946-00498","authors":["Maria Vasilopoulou","Konstantinos Davazoglou","Abd Rashid bin Mohd Yusoff","Yang Chai","Yong-Young Noh","Thomas Anthopoulos","Mohammad Khaja Nazeeruddin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-09T10:59:00Z","doi":"10.1039/bk9781839169946-00498","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.059Z"},{"id":"doi:10.1016/j.mejo.2019.07.001","name":"A non-overlapped implantation MOSFET differential pair implementation of bidirectional weight update synapse for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.mejo.2019.07.001","authors":["E.S. Jeng","H.X. Chen","Y.L. Chiang","J.H. Chang","J.Y. Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-07-04T13:12:17Z","doi":"10.1016/j.mejo.2019.07.001","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.059Z"},{"id":"doi:10.3389/fnins.2025.1511371","name":"Evaluation of fluxon synapse device based on superconducting loops for energy efficient neuromorphic computing","source":"europepmc","abstract":"With Moore’s law nearing its end due to the physical scaling limitations of CMOS technology, alternative computing approaches have gained considerable attention as ways to improve computing performance. Here, we evaluate performance prospects of a new approach based on disordered superconducting loops with Josephson-junctions for energy efficient neuromorphic computing. Synaptic weights can be stored as internal trapped fluxon states of three superconducting loops connected with multiple Josephson-junctions (JJ) and modulated by input signals applied in the form of discrete fluxons (quantized flux) in a controlled manner. The stable trapped fluxon state directs the incoming flux through different pathways with the flow statistics representing different synaptic weights. We explore implementation of matrix–vector-multiplication (MVM) operations using arrays of these fluxon synapse devices. We investigate the energy efficiency of online-learning of MNIST dataset. Our results suggest that the fluxon synapse array can provide ~100× reduction in energy consumption compared to other state-of-the-art synaptic devices. This work presents a proof-of-concept that will pave the way for development of high-speed and highly energy efficient neuromorphic computing systems based on superconducting materials.","url":"https://doi.org/10.3389/fnins.2025.1511371","authors":["Ashwani Kumar","Uday S. Goteti","Ertugrul Cubukcu","Robert C. Dynes","Duygu Kuzum"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fnins.2025.1511371","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.059Z"},{"id":"doi:10.12785/ijcds/140152","name":"Neuromorphic Processor Design and FPGA Implementation for Handwritten Digits Employing Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.12785/ijcds/140152","authors":["Nagavarapu Sowmya","Jitendra Kumar","Pradyut Biswal","Shirshendu Roy","Subhrajit Pradhan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-01T14:03:07Z","doi":"10.12785/ijcds/140152","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.4018/979-8-3373-7779-7.ch002","name":"Quantum Machine Intelligence","source":"crossref","abstract":"Quantum computing has turned out to be a paradigm shift that can address computational problems that are way out of the scope of classical systems. The current hybrid designs tend to view quantum and classical components as non-living, and do not provide the feedback intelligence to control energy, depth and computational balance in real-time. The present paper presents a Quantum Machine Intelligence (QMI) model, which will integrate quantum computation, artificial intelligence as well as reinforcement learning into a self-regulated system. The model is developed on quantum encoding and amplitude-based encoding, a reinforcement-learning controller using hybrid optimization variations, and design to adjust simultaneously the depth of the circuits and the number of qubits that are used to evaluate the performance of a component Empirical analyses show that QMI attains 98.3% accuracy, 17.8% energy saving, and 15 times quick convergence in opposition to the latest DRL, hybrid DL, and LLM-aided baselines.","url":"https://doi.org/10.4018/979-8-3373-7779-7.ch002","authors":["Shamik Palit","Pawan Madanan","Shipra Srivastava","Ganesh Ramchandra Patil","Mohit Tiwari","Melanie Elizabeth Lourens"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-04T19:15:56Z","doi":"10.4018/979-8-3373-7779-7.ch002","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/med.2023.3292619","name":"After 75 Years of the Transistor: An Age of Neuromorphic Computing [Women in Electronic Devices]","source":"crossref","abstract":"","url":"https://doi.org/10.1109/med.2023.3292619","authors":["P.S. Menon","S.F.W.M. Hatta","M.M. de Souza"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-04T17:37:24Z","doi":"10.1109/med.2023.3292619","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.059Z"},{"id":"doi:10.35848/1347-4065/acb060","name":"Interface engineering of amorphous gallium oxide crossbar array memristors for neuromorphic computing","source":"crossref","abstract":"Abstract This paper reports on the fabrication and characterization of crossbar array memristors using amorphous gallium oxide (a-GaO x ) for implementing high-speed and wide-dynamic range artificial synaptic functions. The a-GaO x memristors were fabricated by pulsed laser deposition in an argon atmosphere using a platinum bottom electrode and an indium tin oxide (ITO) top electrode. We revealed that the interface engineering at a-GaO x /ITO is the key to demonstrating exemplary resistive switching operation. Stable counter figure-8 hysteresis loops were obtained by voltage application, leading to the successful demonstration of non-volatile retention over 10 4 s and the multi-level conductance modulation. Furthermore, spike-timing-dependent plasticity (STDP) was artificially implemented by applying pre- and post-spike voltages to the device. Consequently, significant weight-change rates were achieved in the asymmetric STDP imitation, which can be attributed to the reliable resistive switching properties of the device with an extensive dynamic range. These results indicate that the a-GaO x crossbar array memristor is a promising hardware platform for neuromorphic computing applications.","url":"https://doi.org/10.35848/1347-4065/acb060","authors":["Naoki Masaoka","Yusuke Hayashi","Tetsuya Tohei","Akira Sakai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-05T17:21:51Z","doi":"10.35848/1347-4065/acb060","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.1038/s44335-025-00021-9","name":"A self-training spiking superconducting neuromorphic architecture","source":"crossref","abstract":"Abstract Neuromorphic computing takes biological inspiration to the device level aiming to improve computational efficiency and capabilities. One of the major issues that arises is the training of neuromorphic hardware systems. Typically training algorithms require global information and are thus inefficient to implement directly in hardware. In this paper we describe a set of reinforcement learning based, local weight update rules and their implementation in superconducting hardware. Using SPICE circuit simulations, we implement a small-scale neural network with a learning time of order one nanosecond per update. This network can be trained to learn new functions simply by changing the target output for a given set of inputs, without the need for any external adjustments to the network. Further, this architecture does not require programing explicit weight values in the network, alleviating a critical challenge with analog hardware implementations of neural networks.","url":"https://doi.org/10.1038/s44335-025-00021-9","authors":["M. L. Schneider","E. M. Jué","M. R. Pufall","K. Segall","C. W. Anderson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-04T10:44:40Z","doi":"10.1038/s44335-025-00021-9","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.059Z"},{"id":"doi:10.1109/icnc64304.2024.10987651","name":"Unsupervised Order-Enabled Contrastive Learning-Based Dual Autoencoder Fault Detection for Variable Speed Bearing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987651","authors":["Ruonan Lu","Da Zheng","Qinmin Yang","Weiwei Cao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987651","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.059Z"},{"id":"doi:10.1109/imw56887.2023.10145991","name":"Spin-orbit torque MRAM for ultrafast cache and neuromorphic computing applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/imw56887.2023.10145991","authors":["Siddharth Rao","Kaiming Cai","Giacomo Talmelli","Nathali Franchina-Vergel","Ward Janssens","Hubert Hody","Farrukh Yasin","Kurt Wostyn","Sebastien Couet"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-12T17:56:55Z","doi":"10.1109/imw56887.2023.10145991","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.059Z"},{"id":"doi:10.1109/icnc59488.2023.10462793","name":"Stability Analysis of Neutral Stochastic Pantograph System with Time-dependent Switching and its Applications in Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462793","authors":["Chao Wang","Yinfang Song","Fengjiao Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462793","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/icecs202256217.2022.9970915","name":"An Analog Memristive and Memcapacitive Device for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icecs202256217.2022.9970915","authors":["Eter Mgeladze","Melanie Herzig","Richard Schroedter","Ronald Tetzlaff","Thomas Mikolajick","Stefan Slesazeck"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-12T19:50:02Z","doi":"10.1109/icecs202256217.2022.9970915","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1088/2053-1583/ab23ba","name":"A high-performance MoS\n                    <sub>2</sub>\n                    synaptic device with floating gate engineering for neuromorphic computing","source":"crossref","abstract":"Abstract As one of the most important members of the two dimensional chalcogenide family, molybdenum disulphide (MoS 2 ) has played a fundamental role in the advancement of low dimensional electronic, optoelectronic and piezoelectric designs. Here, we demonstrate a new approach to solid state synaptic transistors using two dimensional MoS 2 floating gate memories. By using an extended floating gate architecture which allows the device to be operated at near-ideal subthreshold swing of 77 mV/decade over four decades of drain current, we have realised a charge tunneling based synaptic memory with performance comparable to the state of the art in neuromorphic designs. The device successfully demonstrates various features of a biological synapse, including pulsed potentiation and relaxation of channel conductance, as well as spike time dependent plasticity (STDP). Our device returns excellent energy efficiency figures and provides a robust platform based on ultrathin two dimensional nanosheets for future neuromorphic applications.","url":"https://doi.org/10.1088/2053-1583/ab23ba","authors":["Tathagata Paul","Tanweer Ahmed","Krishna Kanhaiya Tiwari","Chetan Singh Thakur","Arindam Ghosh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-30T04:04:06Z","doi":"10.1088/2053-1583/ab23ba","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/icons62911.2024.00050","name":"Watermarking Neuromorphic Brains: Intellectual Property Protection in Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024.00050","authors":["Hamed Poursiami","Ihsen Alouani","Maryam Parsa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T18:37:03Z","doi":"10.1109/icons62911.2024.00050","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/icnc59488.2023.10462775","name":"Pinning Synchronization of Fractional-Order Two-Layer Networks: From Inter-Layer Synchronization to Cluster Synchronization","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462775","authors":["Yanwei Yin","Juan Yu","Cheng Hu","Tingting Shi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462775","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1364/ofc.2022.m1g.4","name":"Photonic Neuromorphic Computing: Architectures, Technologies, and Training Models","source":"crossref","abstract":"We summarize recent developments in neuromorphic photonics, including our work and the advances it brings beyond the state-of-the-art demonstrators in terms of architectures, technologies, and training models for a synergistic hardware/software codesign approach.","url":"https://doi.org/10.1364/ofc.2022.m1g.4","authors":["Miltiadis Moralis-Pegios","Angelina Totovic","Apostolos Tsakyridis","George Giamougiannis","George Mourgias-Alexandris","George Dabos","Nikolaos Passalis","Manos Kirtas","Anastasios Tefas","Nikos Pleros"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-26T19:20:12Z","doi":"10.1364/ofc.2022.m1g.4","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1016/j.xcrp.2024.102079","name":"High-temperature-resistant synaptic transistors for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.xcrp.2024.102079","authors":["Xiao Liu","Liang Chu","Wensheng Yan","Xiaodong Pi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-08T10:53:31Z","doi":"10.1016/j.xcrp.2024.102079","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1088/2634-4386/ae46d4","name":"A scalable hybrid training approach for recurrent spiking neural networks","source":"crossref","abstract":"Abstract Recurrent spiking neural networks (RSNNs) can be implemented very efficiently in neuromorphic systems. Nevertheless, training of these models with powerful gradient-based learning algorithms is mostly performed on standard digital hardware using backpropagation through time (BPTT). However, BPTT has substantial limitations. It does not permit online training and its memory consumption scales linearly with the number of computation steps. In contrast, learning methods using forward propagation of gradients operate in an online manner with a memory consumption independent of the number of time steps. These methods enable SNNs to learn from continuous, infinite-length input sequences. In addition, approximate forward propagation algorithms have been developed that can be implemented on neuromorphic hardware. Yet, slow execution speed on conventional hardware as well as inferior performance has hindered their widespread application. In this work, we introduce hybrid propagation (HYPR) that combines the efficiency of parallelization with approximate online forward learning. Our algorithm yields high-throughput online learning through parallelization, paired with constant, i.e. sequence length independent, memory demands. HYPR enables parallelization of parameter update computation over subsequences for RSNNs consisting of almost arbitrary non-linear spiking neuron models. We apply HYPR to networks of spiking neurons with oscillatory subthreshold dynamics. We find that this type of neuron model is particularly well trainable by HYPR, resulting in an unprecedentedly low task performance gap between approximate forward gradient learning and BPTT.","url":"https://doi.org/10.1088/2634-4386/ae46d4","authors":["Maximilian Baronig","Yeganeh Bahariasl","Ozan Özdenizci","Robert Legenstein"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-17T22:51:28Z","doi":"10.1088/2634-4386/ae46d4","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1016/c2023-0-52226-8","name":"Towards Neuromorphic Machine Intelligence","source":"crossref","abstract":"","url":"https://doi.org/10.1016/c2023-0-52226-8","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-28T06:25:30Z","doi":"10.1016/c2023-0-52226-8","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.32658/10497/27602","name":"Neuromorphic vision sensors for computer vision","source":"crossref","abstract":"There have been significant advancements in the field of artificial intelligence (AI) over the past two decades, allowing such technologies to acquire popularity in both industry and academia. Face recognition software on Facebook or the iPhone, self-driving cars, and image recognition software are examples of AI applications that have become more prevalent in our daily lives. Computer vision, which is the study of enabling machines to gain a high-level understanding of images, such as pattern or object recognition, is a subfield of AI. Consequently, computer vision research has acquired significant importance. Convolutional neural networks (CNN) have garnered a great deal of interest due to their exceptional performance in image classification. Due to the computer's hardware limitations for self-learning and parallel computing, even the most advanced software is presently incapable of imbuing machines with human cognitive skills. Despite the progress made in computer vision, there are still problems to be resolved. One challenge is object recognition under varying illumination conditions. In particular, changes in illumination conditions can contaminate CNN's image segmentation, leading to erroneous object detection. Even though this issue can be mitigated by using a larger CNN training set, the enormous computational and energy resources required to continuously execute CNN for always-on applications, such as surveillance or self-navigation, pose a significant challenge for battery-dependent mobile systems. To address this age-old issue, a novel optoelectronic sensor capable of automatically compensating for sudden variations in light exposure is demonstrated in this thesis, without the need for sophisticated object detection software. With this method, effective fault-tolerant object detection may be developed with little training data, low energy consumption, and low computational expenses. Another prominent issue in computer vision is occlusion, which occurs when an object's key features momentarily vanish behind another body, making image detection difficult for the computer. While the human brain is capable of compensating for the portions of a blocked object that are not visible, computers lack these scene interpretation skills. Typically, cloud computing with convolutional neural networks is the preferred method for managing such a scenario. However, cloud computing should be minimized for mobile applications where energy consumption and computational costs are crucial. In this regard, a novel computer vision sensor that can effectively detect and track covered objects on a hardware level without relying heavily on occlusion management software is proposed. The underlying mechanism that allows the emergence of these smart optoelectronic sensors will be discussed in detail in this thesis, laying the groundwork for the potential development of a new generation of edge-computing cameras that allow computer vision applications to be carried out in a more energy- and computationally-efficient way.","url":"https://doi.org/10.32658/10497/27602","authors":["Cuhadar Can"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-25T02:04:15Z","doi":"10.32658/10497/27602","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.4018/978-1-6684-6596-7.ch005","name":"Prediction of Skin Cancer Using Convolutional Neural Network (CNN)","source":"crossref","abstract":"Skin disorders are one of the most common types of disorders that are primarily diagnosed visually with scientific screening observed through dermoscopic evaluation, histopathological evaluation, and a biopsy. Diagnostic accuracy has a strong relevance to physician skill. Painful effects of skin disease hamper the mental condition of a patient. The authors propose an approach to detect the skin diseases based upon image processing as well as machine learning techniques i.e., convolutional neural networks (CNN). CNN is a specific type of neural network model that allows us to extract higher depictions for the image content. It is a deep learning algorithm to perform generative and descriptive tasks. Machine learning generates two types of prediction-batches and real time.","url":"https://doi.org/10.4018/978-1-6684-6596-7.ch005","authors":["Deepa Nivethika S.","Dhamodharan Srinivasan","SenthilPandian M.","Prabhakaran Paulraj","N. Ashokkumar","Hariharan K.","Maneesh Vijay V. I.","Raghuram T."],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-19T08:20:15Z","doi":"10.4018/978-1-6684-6596-7.ch005","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/vlsi-soc.2018.8644897","name":"Neuromorphic Computing - From Robust Hardware Architectures to Testing Strategies","source":"crossref","abstract":"","url":"https://doi.org/10.1109/vlsi-soc.2018.8644897","authors":["Lorena Anghel","Denys Ly","Giorgio Di Natale","Benoit Miramond","Elena Ioana Vatajelu","Elisa Vianello"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-03-15T16:33:26Z","doi":"10.1109/vlsi-soc.2018.8644897","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/islped.2019.8824926","name":"HR<sup>3</sup>AM: A Heat Resilient Design for RRAM-based Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/islped.2019.8824926","authors":["Xiao Liu","Minxuan Zhou","Tajana S. Rosing","Jishen Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-09-05T23:11:46Z","doi":"10.1109/islped.2019.8824926","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/irps.2019.8720596","name":"Wafer-Scale TaO<sub>x</sub> Device Variability and Implications for Neuromorphic Computing Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/irps.2019.8720596","authors":["Christopher H. Bennett","Diana Garland","Robin B. Jacobs-Gedrim","Sapan Agarwal","Matthew J. Marinella"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-24T04:11:10Z","doi":"10.1109/irps.2019.8720596","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1142/9789811290084_0006","name":"Real Computability of Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789811290084_0006","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-26T02:06:27Z","doi":"10.1142/9789811290084_0006","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/iiceta57613.2023.10351270","name":"Neuromorphic Computing: Unraveling the Physical Properties of Brain-Inspired Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iiceta57613.2023.10351270","authors":["G. Mohammed","Waleed H. Madhloom","Mustafa Abdulsattar Jebur","Mohammed Brayyich","Myasar Mundher Adnan","Waleed Hameed"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-21T14:21:14Z","doi":"10.1109/iiceta57613.2023.10351270","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1145/3477145.3477154","name":"Computational Complexity of Neuromorphic Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3477145.3477154","authors":["Prasanna Date","Bill Kay","Catherine Schuman","Robert Patton","Thomas Potok"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-10-13T14:38:20Z","doi":"10.1145/3477145.3477154","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1142/9789811290084_0003","name":"Complexity Degrees of Digital Computability","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789811290084_0003","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-26T02:06:27Z","doi":"10.1142/9789811290084_0003","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1088/2634-4386/ae46d5","name":"Beyond rate coding: surrogate gradients enable spike timing learning in spiking neural networks","source":"crossref","abstract":"Abstract The surrogate gradient descent (SGD) algorithm enabled spiking neural networks (SNNs) to be trained to carry out challenging sensory processing tasks, an important step in understanding how spikes contribute to neural computations. However, it is unclear the extent to which these algorithms fully explore the space of possible spiking solutions to problems. We investigated whether spiking networks trained with SGD can learn to make use of information that is only encoded in the timing and not the rate of spikes. We constructed synthetic datasets with a range of types of spike timing information (interspike intervals, spatio-temporal spike patterns or polychrony, and coincidence codes). We find that SGD training can extract all of these types of information. In more realistic speech-based datasets, both timing and rate information is present. We therefore constructed variants of these datasets in which all rate information is removed, and find that SGD can still perform well. We tested all networks both with and without trainable axonal delays. We find that delays can give a significant increase in performance, particularly for more challenging tasks. To determine what types of spike timing information are being used by the networks trained on the speech-based tasks, we test these networks on time-reversed spikes which perturb spatio-temporal spike patterns but leave interspike intervals and coincidence information unchanged. We find that when axonal delays are not used, networks perform well under time reversal, whereas networks trained with delays perform poorly. This suggests that SNNs with delays are better able to exploit temporal structure. To facilitate further studies of temporal coding, we have released our modified speech-based datasets.","url":"https://doi.org/10.1088/2634-4386/ae46d5","authors":["Ziqiao Yu","Pengfei Sun","Dan F M Goodman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-17T22:51:28Z","doi":"10.1088/2634-4386/ae46d5","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.2172/3008547","name":"CRCNS22 Learning Rules in the Hippocampus and their Mapping to Neuromorphic Systems (Final Technical Report)","source":"crossref","abstract":"","url":"https://doi.org/10.2172/3008547","authors":["Gina Adam","Giorgio Ascoli","Joseph Kilgore","Jeffrey Kopsick"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-08T19:52:11Z","doi":"10.2172/3008547","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1007/s12274-022-4773-9","name":"A review of Mott insulator in memristors: The materials, characteristics, applications for future computing systems and neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s12274-022-4773-9","authors":["Yunfeng Ran","Yifei Pei","Zhenyu Zhou","Hong Wang","Yong Sun","Zhongrong Wang","Mengmeng Hao","Jianhui Zhao","Jingsheng Chen","Xiaobing Yan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-08-23T10:02:52Z","doi":"10.1007/s12274-022-4773-9","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.1088/2634-4386/adebaa","name":"Training and synchronizing oscillator networks with Equilibrium Propagation","source":"crossref","abstract":"Abstract Oscillator networks represent a promising technology for unconventional computing and artificial intelligence. Thus far, these systems have primarily been demonstrated in small-scale implementations, such as Ising machines for solving combinatorial problems and associative memories for image recognition, typically trained without state-of-the-art gradient-based algorithms. Scaling up oscillator-based systems requires advanced gradient-based training methods that also ensure robustness against frequency dispersion between individual oscillators. Here, we demonstrate through simulations that the Equilibrium Propagation algorithm enables effective gradient-based training of oscillator networks, facilitating synchronization even when initial oscillator frequencies are significantly dispersed. We specifically investigate two oscillator models: purely phase-coupled oscillators and oscillators coupled via both amplitude and phase interactions. Our results show that these oscillator networks can scale successfully to standard image recognition benchmarks, such as achieving nearly 98% test accuracy on the Modified National Institute of Standards and Technology (MNIST) dataset, despite noise introduced by imperfect synchronization. This work thus paves the way for practical hardware implementations of large-scale oscillator networks, such as those based on spintronic devices.","url":"https://doi.org/10.1088/2634-4386/adebaa","authors":["Théophile Rageau","Julie Grollier"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-03T18:50:21Z","doi":"10.1088/2634-4386/adebaa","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.5267/j.ijdns.2026.37","name":"Neuromorphic computing for healthcare engineering: A bibliometric analysis of materials, devices, architectures, and biomedical applications based on 200 highly cited publications (2009–2025)","source":"crossref","abstract":"This bibliometric survey examines 200 highly cited publications spanning from 2009 to 2025, retrieved from the Scopus database using search terms targeting neuromorphic computing and its applications in healthcare engineering and biomedical systems. The analysis reveals a rapidly maturing interdisciplinary field at the convergence of materials science, device physics, circuit design, computer architecture, and biomedical engineering. Key findings indicate that memristive devices, particularly those based on metal oxides and two-dimensional materials, constitute the dominant hardware platform for neuromorphic computing, with phase-change materials, spintronic devices, and ferroelectric tunnel junctions representing significant alternative approaches. The United States, China, Germany, South Korea, and Switzerland emerge as the most productive nations, with extensive international collaboration networks reflecting the field's multidisciplinary nature. Thematic clustering identifies five major research domains: (1) memristive devices and resistive switching mechanisms, (2) two-dimensional materials for neuromorphic applications, (3) spiking neural networks and neuromorphic architectures, (4) optical and photonic neuromorphic computing, and (5) biomedical and healthcare applications including electronic skin, neural prosthetics, and biosensing. Emerging trends include the integration of neuromorphic computing with edge artificial intelligence for wearable healthcare devices, the development of reservoir computing for real-time biomedical signal processing, and the convergence of neuromorphic systems with biohybrid interfaces. This survey provides a comprehensive mapping of the intellectual landscape, identifies persistent challenges including device variability, scalability, and biocompatibility, and proposes future directions for healthcare-oriented neuromorphic engineering.","url":"https://doi.org/10.5267/j.ijdns.2026.37","authors":["Kouroush Jenab"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-08T10:10:08Z","doi":"10.5267/j.ijdns.2026.37","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1126/sciadv.aea1114","name":"Parallel nonlinear neuromorphic computing with temporal encoding.","source":"europepmc","abstract":"The proliferation of deep learning applications has intensified the demand for electronic hardware with low energy consumption and fast computing speed. Neuromorphic photonics have emerged as a viable alternative to process high-throughput information at the physical space. However, the simultaneous attainment of high linear and nonlinear expressivity poses a considerable challenge due to the power efficiency and impaired manipulability in conventional nonlinear materials and optoelectronic conversion. Here, we introduce a parallel nonlinear neuromorphic processor that enables arbitrary superposition of information states in multidimensional channels, only by leveraging the temporal encoding of spatiotemporal metasurfaces. We experimentally demonstrated the concept based on distributed spatiotemporal metasurfaces, showcasing robust performance in multilabel recognition and multitask parallelism with asynchronous modulation. Our nonlinear processor demonstrates dynamic memory capability in real-time responsiveness to canonical maze-solving problem. Our work opens up a flexible avenue for a variety of temporally modulated neuromorphic processors tailored for complex scenarios.","url":"https://doi.org/10.1126/sciadv.aea1114","authors":["Guangfeng You","Chao Qian","Ouling Wu","Hongsheng Chen"],"tags":["Neuromorphic engineering","Computer science","Encoding (memory)","Nonlinear system","Asynchronous communication"],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1126/sciadv.aea1114","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"doi:10.1038/s41563-026-02689-1","name":"Organic synapses with programmable linearity for neuromorphic computing.","source":"europepmc","abstract":"Organic synaptic devices offer a route to flexible and biocompatible neuromorphic computing and human-machine interfaces. However, electrical signal transmission is often nonlinear and poorly reproducible because of interfacial effects and non-uniform electronic processes that can increase energy consumption. Organic all-photonic synapses circumvent electrical transmission but remain limited by nonlinear photochemical and photoisomerization processes. Here we develop linearity-programmable organic all-photonic synapses based on a charge-separated-buffered adaptive luminescence mechanism. Systematic engineering of guest molecular structures modulates charge-separation kinetics, allowing precise control over synaptic linearity. The resulting devices exhibit a linearity parameter, v, of 0.0093, 99% uniformity, 97% repeatability, an optical trigger energy of 59 zJ per synaptic event and a response time of 1.39 ns. An all-photonic sensor system integrating linearity-programmable organic all-photonic synapses enables high-quality image acquisition and high image-classification accuracy. These results establish a molecularly programmable photophysical platform for neuromorphic signal processing and provide a potential route towards low-energy human-machine interfaces.","url":"https://doi.org/10.1038/s41563-026-02689-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41563-026-02689-1","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/advs.77375","name":"A Reconfigurable Memristive Spiking Neuron Enabling Advanced Neuromorphic Computing.","source":"europepmc","abstract":"ABSTRACT Biological neurons exhibit internal complexity that enables a variety of spiking behaviors, complex encoding strategies, and the possibility of advanced networks that underpin cognitive brain functions. Neuromorphic computing, especially using memristors with biologically plausible dynamics, is imperative to realizing next‐generation artificial intelligence. However, current attempts still rely on simple neurons with limited support for novel network algorithms. This work proposes a multi‐mode reconfigurable memristive spiking neuron with a simple transistor‐capacitor feedback circuit that enables fast‐spiking, adaptive spiking, phasic bursting, or single‐spiking. Every spike train parameter in each mode can be freely tuned. With this, a multiplexed encoding strategy in a hazard avoidance application is demonstrated, wherein 3 driving actions and 6 maneuvering control variables are encoded using distinct spiking modes and spike train parameters. Furthermore, long‐short‐term memory spiking neural networks (LSNN) that incorporate either heterogeneous slow time constants or dynamic mode switching are proposed, demonstrating up to 8.0% and 13.7% improvements in accuracy in highly temporal tasks compared with homogeneous LSNNs, while also exhibiting superior generalization capabilities. The ability to support these advanced encoding and network strategies distinguishes the proposed reconfigurable neuron from existing implementations, highlighting its potential to empower more advanced neuromorphic computing.","url":"https://doi.org/10.1002/advs.77375","authors":["Pek Jun Tiw","Yuqi Li","Zhongyuan Li","Qihang Ding","Yuzhe Wang","Jiarong Wang","Yuchao Yang"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.77375","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:25.465Z"},{"id":"doi:10.1098/rsta.2025.0122","name":"On the next generation for neuromorphic computing and neuromorphic AI.","source":"europepmc","abstract":"","url":"https://doi.org/10.1098/rsta.2025.0122","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1098/rsta.2025.0122","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.21203/rs.3.rs-10356585/v1","name":"Integrating Neuromorphic Computing and Clinical Biomarkers for Enhanced Liver Disease Detection","source":"europepmc","abstract":"Abstract Liver diseases should be detected at an early stage and accurately to avoid the development of cirrhosis, liver failure, and permanent hepatocellular damage. Nevertheless, the current diagnostic models are based on computationally intensive machine learning models which are not real-time, interpretable, and do not support low-power clinical environments. The paper presents a neuromorphic computing-based diagnostic system that combines both clinically relevant biomarker encoding and spiking neural network models trained by surrogate-gradient and hardware-conscious training. Three spike encoders, namely, latency, bounded rate and population, are evaluated systematically to find out their effectiveness in capturing discriminative biomarker information. Experimental evidence on the ILPD dataset indicates that the proposed model has high diagnostic accuracy, with the AUC of 0.94–0.96 and better sensitivity at clinically relevant specificity levels, at a much lower cost of synaptic operations than the conventional neural networks. Memristive variability: Hardware-aware training methods, such as quantization-aware optimization and noise-injection, improve robustness to neuromorphic crossbar variability, allowing them to be deployed safely on neuromorphic crossbars. Moreover, the spike-based attribution techniques offer clinically stable interpretability by emphasizing the presence of the biomarkers including ALT, AST, bilirubin, albumin, and alkaline phosphatase. All these findings make neuromorphic computing an energy-efficient, robust, and explainable solution to the next generation of liver disease diagnostics. The proposed system is executed by the end-to-end diagnostic dashboard that allows to recreate the experiment and make clinical decisions based on structured clinical biomarker data.","url":"https://doi.org/10.21203/rs.3.rs-10356585/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-10356585/v1","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1063/5.0320577","name":"Quantum coherence in neuromorphic computing.","source":"europepmc","abstract":"Quantum effects become significant when hardware computing units scale down to nanoscale dimensions. To maintain reliable performance as neuromorphic computing hardware scales down, researchers must understand how quantum coherence across multiple neurons impacts neural network function. In this study, we model neuromorphic computing with quantum coherence effects using a quantum spiking neural network model. We find that quantum coherence between neural activations can alter the network perception, compared to the incoherent network. Destructive interference between activation signals propagating through different synaptic channels drives this effect at the quantum scale. This quantum effect becomes more prominent with increasing network depth and can be mitigated by increasing the number of input neurons connected to each output neuron.","url":"https://doi.org/10.1063/5.0320577","authors":["Yuanheng Wang","Kai Li","Gregory D. Scholes"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1063/5.0320577","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1021/acs.jpclett.6c01575","name":"P3BT Organic Memristor-Based Artificial Synapse for Neuromorphic Computing.","source":"europepmc","abstract":"Organic memristors have potential applications in simulating biological synapses for neuromorphic computing. In this work, a solution-processed Al/P3BT/indium tin oxide (ITO) organic memristor was designed. The device exhibits stable resistive switching behavior and successfully emulates versatile synaptic plasticity, including excitatory postsynaptic current (EPSC), paired-pulse facilitation (PPF), spike-timing-dependent plasticity (STDP), the transition from short-term plasticity to long-term potentiation (STP-LTP), post-tetanic potentiation (PTP), and experiential learning. Fitting analyses of the I-V curves reveal that the resistive switching resulted from a combined contribution of direct tunneling, space-charge-limited conduction, Schottky emission, and Fowler-Nordheim tunneling. Moreover, the analog resistive switching behavior remains stable, even after exposure to ambient air for over 300 days. To exploit the nonlinear mappings through simple 3-bit pulse sequences, the constructed reservoir computing system achieves a recognition accuracy of 97.69% on the Modified National Institute of Standards and Technology (MNIST) handwritten digit classification task after only 20 training epochs, significantly outperforming conventionally trained network models. Furthermore, the system attains an accuracy of 87.02% on the Fashion-MNIST data set. This study provides valuable insights and perspectives on the emulation of artificial synaptic plasticity by using organic memristors and their application in neuromorphic computing.","url":"https://doi.org/10.1021/acs.jpclett.6c01575","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acs.jpclett.6c01575","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/smll.74663","name":"Controlling Ion Dynamics at Nanoscale for Memristor-Based Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.74663","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.74663","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acsnano.6c00539","name":"Reconfigurable Photoelectric Coaxial Fiber-Based Memristors for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.6c00539","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsnano.6c00539","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1364/oe.595963","name":"Cavity solitons as a nonlinear substrate for photonic neuromorphic computing.","source":"europepmc","abstract":"Reservoir computing leverages the nonlinear dynamics of physical systems to process temporal information with minimal training cost. Here, we demonstrate that cavity solitons sustained in a fiber optical cavity provide an optical platform for photonic reservoir computing. Our methodology employs a phase-modulated drive laser to encode the input, while the reservoir states are accessed through a frequency-resolved readout. Numerical simulations indicate that the emission of Kelly waves enriches the dynamics and enhances performance for machine learning tasks. We evaluated the performance of the cavity-soliton reservoir computer on several standard benchmark tasks.","url":"https://doi.org/10.1364/oe.595963","authors":["Amir Arsalan Arabieh","Alessandro Lupo","Simon-Pierre Gorza","Serge Massar"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1364/oe.595963","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/advs.76639","name":"Polarization Engineering in Vinylene-Linked COFs Toward Efficient Neuromorphic Computing.","source":"europepmc","abstract":"Functional delocalized covalent organic frameworks (COFs) show promise as active layers for the development of memristor switches and multistate functionalities. However, their potential is limited by poor electron mobility and suboptimal reaction kinetics. This study explores polarization engineering to modify the local electronic structure of the biaryl units within vinylene-linked COFs. By implementing a conformation-locking strategy that strategically enhances N + polarization and the redox activity of the framework, this design not only decreases the interfacial Schottky barrier but also facilitates efficient electron transfer, thereby promoting the delocalization of framework electrons, which modulates the conductive state in organic memristors. Furthermore, the polarization of ions, amplified by pyridine nitrogen nuclei and robust interlayer stacking, ensures effective counterion deintercalation and migration. The constructed Al/COF-DIBPY/Au memristor exhibits a high analog on-off current ratio (I max /I min = 15.7) under a 0.5 V drive. Utilizing these properties, the device shows great potential in performing speech emotion recognition tasks. When integrated into a convolutional neural network, it achieves a learning recognition accuracy of up to 95% in these tasks. This research offers novel insights into the construction of high-efficiency neuromorphic computing devices based on polarization-modulated COFs.","url":"https://doi.org/10.1002/advs.76639","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.76639","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acs.nanolett.6c02862","name":"Electrochemical Metallization-Induced Localized Phase Transition for Integrated Memory and Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.6c02862","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acs.nanolett.6c02862","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1039/d5dt02579f","name":"Halide perovskite-based memory devices and neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5dt02579f","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d5dt02579f","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/advs.75989","name":"Reconfigurable Selector-Only Memory (SOM) for Scalable Neuromorphic Computing.","source":"europepmc","abstract":"ABSTRACT Highly scalable reconfigurable neuromorphic devices are critical for addressing continual‐learning challenges in artificial intelligence. However, the scalability of existing reconfigurable devices is severely constrained by limited operating margins and insufficient process maturity. Here, we propose selector‐only memory (SOM) as a scalable device candidate. Its volatile threshold switching and programmable nonvolatile threshold window are operationally decoupled, and it is compatible with in‐line fabrication and 3D stacking. We demonstrate an In‐doped GeSe SOM that enables neuron–synapse reconfigurability within a single cell. By leveraging intrinsic parasitic capacitance, we implement a capacitor‐free leaky integrate‐and‐fire neuron and validate all‐or‐none firing, integrate‐and‐fire dynamics, and input‐controlled firing‐rate modulation using experiments and an equivalent model. For synapses, we propose a one‐shot subthreshold‐conductance readout method. With a unified reverse‐subthreshold pulse scheme, 16 programmed conductance states are obtained through one‐shot subthreshold readout, and most states remain distinguishable over 10 4 s. Finally, SOM‐parameter‐based simulations on a Growing‐When‐Required MNIST task achieve 2.67× higher accuracy with 70% of the nodes and shrink to 58% after rollback. These results indicate that SOM provides a promising selector‐derived device concept for scalable reconfigurable neuromorphic hardware.","url":"https://doi.org/10.1002/advs.75989","authors":["Jin‐Yu Wen","Chuan‐Qi Yi","Ya‐Ru Zhang","Bin‐Hao Wang","Zi‐Xuan Liu","Chun‐Yu Zhou","Hao Tong","Xiang‐Shui Miao"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.75989","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1088/1361-6528/ae8674","name":"Visible-light modulated ferroelectric optoelectronic field-effect transistor for superior neuromorphic computing.","source":"europepmc","abstract":"High-performance neuromorphic computing and bionic vision hardware urgently require device simplicity and low power consumption. This paper adopts an all-solution method to prepare a visible-light modulated ferroelectric optoelectronic field-effect transistor (Fe-OFET) based on a TiO 2 /IGZO/Al 2 O 3 /PZT structure, used to achieve visible-light-driven neuromorphic synapse simulation and multilevel storage. By introducing a TiO 2 layer, the light current of the IGZO-based device is extended to the red light band and the absorption efficiency in the entire visible-light wavelength is substantially improved, overcoming the bottleneck that traditional oxide semiconductors only respond to ultraviolet light and are difficult to utilize visible light. The device exhibits stable ferroelectric non-volatility and typical optoelectronic performance, successfully simulating core synaptic plasticity such as excitatory postsynaptic current and paired-pulse facilitation. A convolutional neural network constructed based on this device achieves 95.5% accuracy in a target motion trajectory recognition task; a hybrid artificial neural network integrating multi-head attention achieves a maximum accuracy of 90.0% in the Mixed National Institute of Standards and Technology handwritten digit recognition task. This study provides a process-simple, visible-light-compatible ferroelectric optoelectronic field-effect transistor solution, providing important support for visual neuromorphic hardware and neuromorphic computing integration.","url":"https://doi.org/10.1088/1361-6528/ae8674","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1088/1361-6528/ae8674","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acsnano.6c08364","name":"Programmable Cascaded Optical Memristors Based on Phase-Change Materials for Photonic Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.6c08364","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsnano.6c08364","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1039/d6nr02312f","name":"CuPc/SiC heterostructure enabling all-optical-controlled artificial synapses for neuromorphic computing and vision.","source":"europepmc","abstract":"Optical synapses with the capability of optical sensing and biological synaptic functions are the fundamental components of neuromorphic vision systems and exhibit distinct advantages in image perception, information storage and neuromorphic computing. However, most optical synapses exhibit irreversible optical response characteristics, which significantly limit their application scenarios. This study proposes an all-optically-controlled synaptic device based on a CuPc-SiC heterostructure that exhibits bidirectional optical response characteristics. Optical potentiation and depression behaviors were induced using 680 nm and 350 nm light, respectively. Benefiting from its optical plasticity, four basic logic operations, namely, \"AND\", \"OR\", \"NOR\", and \"NAND\", are implemented in the device via bidirectional optical inputs. Furthermore, an artificial neural network model was developed, enabling high-precision fingerprint recognition classification. This study provides new insights into the design of bionic visual devices and the development of neuromorphic vision systems.","url":"https://doi.org/10.1039/d6nr02312f","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d6nr02312f","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1088/1361-6528/ae7381","name":"Low Power HfOx/TaOx stacked memristors with nanocolumn electrode for neuromorphic computing.","source":"europepmc","abstract":"Abstract Emulating biological synaptic behavior using the resistive random access memory (RRAM) is promising for neuromorphic applications. A stacked HfOx/TaOx RRAM model with nanocolumn electrode for low-power neuromorphic computing was constructed, and the finite element method was used to simulate the reset and set processes. As the local electric field was enhanced by the nanocolumn electrode structure, the superior conductive filament control and lower reset/set voltages can be achieved. Meanwhile, the distributions of oxygen vacancy concentration and temperature during switching processes indicate that the nanocolumn electrode significantly reduces the number of programming pulses required for conductance modulation and lower the power consumption of the array. Meantime, the device also exhibits better conductance linearity (long-term potentiation/long-term depression), which is beneficial for improving the accuracy of neural networks. Then the system-level validation was conducted by integrating the device characteristics into a crossbar array and training with the MNIST dataset using backpropagation, achieving 89.83% recognition accuracy, which is superior to that of plane electrode devices (88.67%). This work demonstrates the potential of nanocolumn electrode induced memristors in realizing efficient neuromorphic computing systems, from device physics to system simulation.","url":"https://doi.org/10.1088/1361-6528/ae7381","authors":["Fei Yang","Xuanyang Zhao","Junlong Liu","Houwei Zhu","Qingsong Shu"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1088/1361-6528/ae7381","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/adma.74807","name":"Olefin-Linked Ionic Covalent Organic Frameworks with Carbenium Backbones for High-Performance Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.74807","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.74807","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.21203/rs.3.rs-8928048/v1","name":"Engineering a Biological Neural Network for Neuromorphic Computing","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-8928048/v1","authors":["Guillem Monsó","Burcu Gümüşcü","Regina Lüttge"],"tags":["Neuromorphic engineering","Interfacing","Computer science","Spike (software development)","Artificial neural network"],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-8928048/v1","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"doi:10.1002/smll.202514627","name":"Bidirectional All-Optical Synapses for Neuromorphic Computing and Vision.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.202514627","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.202514627","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1038/s41467-026-74055-3","name":"High encoding-sensitivity vision sensor with complementary nonlinear neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-74055-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-74055-3","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1063/5.0322184","name":"Polymer-networked engineered nanoparticles are primitives for neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1063/5.0322184","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1063/5.0322184","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/smll.74656","name":"Defect-Engineered Floating-Gate Synapses With Programmable Relaxation Dynamics for Multi-Timescale Neuromorphic Computing.","source":"europepmc","abstract":"The human brain processes temporal information across timescales spanning milliseconds to years through hierarchical memory systems, the biological capability that remains largely inaccessible to artificial neuromorphic hardware. Here, we present synapses with programmably tunable relaxation dynamics to emulate such multi-timescale cognition. By precisely engineering defect density, we achieve systematic modulation of charge trapping/de-trapping kinetics, enabling a continuous transition from nonvolatile to volatile memory within the synaptic device. The transistors exhibit a full spectrum of neuromorphic functionalities, including paired-pulse facilitation, multilevel conductance states, and relaxation times tunable across orders of magnitude. Notably, we introduce a parallel dynamic memory superposition architecture, which integrates devices with complementary timescales into a physical reservoir computing framework, enabling simultaneous extraction of both long-term periodic patterns and short-term transient fluctuations without signal entanglement. The heterogeneous reservoir demonstrates superior performance in computational tasks such as multifrequency oscillator prediction, significantly surpassing single-timescale counterparts. Our work establishes defect engineering as a compelling paradigm for programming temporal dynamics in neuromorphic systems based on two-dimensional materials, offering a viable pathway toward energy-efficient and adaptive edge intelligence for real world time-series processing.","url":"https://doi.org/10.1002/smll.74656","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.74656","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acsnano.6c09004","name":"Molecular Engineering of Interlayer Spacings in 2D Dion-Jacobson Perovskites for High-Fidelity Neuromorphic Computing.","source":"europepmc","abstract":"The development of memristive devices is important for energy-efficient neuromorphic computing. While two-dimensional (2D) organic-inorganic hybrid perovskites offer structural tunability and improved stability, the correlation between their molecular-level interlayer architecture and resistive switching (RS) kinetics remains to be fully elucidated. Herein, we modulate the inorganic layer spacing in Dion-Jacobson (DJ) phase 2D perovskites, BDAPbI4, HDAPbI4, and ODAPbI4, by tailoring the alkyl chain length of diammonium ligands. The expanded interlayer environment regulates ion migration, resulting in improved RS behavior in HDAPbI4 and ODAPbI4 devices, with an ON/OFF ratio exceeding 103 and cycling endurance over 100 cycles. These devices emulate bioinspired synaptic functions, including the transition from short-term to long-term plasticity. Cross-Sim simulations of a three-layer neural network using the device conductance characteristics achieved a recognition accuracy of 96.6% for the MNIST data set, close to the software-defined benchmark of 98.2%. Overall, these results identify interlayer spacing as an important structural parameter that regulates ion migration, resistive switching behavior, and analog conductance modulation in 2D Dion-Jacobson perovskite memristors.","url":"https://doi.org/10.1021/acsnano.6c09004","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsnano.6c09004","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acsnano.6c04645","name":"Voltage-Triggered Emergent Dynamics in Strongly Coupled Nanomagnet Networks for Neuromorphic Computing.","source":"europepmc","abstract":"Emergent dynamics, which arise from local interactions between many elementary components, are central to complex physical and biological systems. However, realizing such dynamics in artificial materials, particularly under low-energy stimuli, remains a challenge. While dipole-dipole interactions are typically suppressed in magnetic storage, here we amplify and use them as a core mechanism to construct a strongly dipolar-coupled network of SmCo 5 macrospins at the wafer scale, which can exhibit intrinsic interaction-driven collective dynamics in response to voltage pulses. This network integrates three key ingredients: the strong dipole-dipole interaction, giant voltage control of coercivity over nearly 1000-fold, and a network topology with a frustrated Ising-like energy landscape. As a result, the network, when stimulated by ∼1 V pulses, transitions from a high-coercivity memory regime into a low-coercivity regime in which internal dipolar fields alone trigger collective magnetic reconfiguration. In this regime, the network exhibits emergent behaviors absent at the level of isolated macrospins, including spontaneous demagnetization, greatly enhanced magnetization modulation, reversible \"freeze and resume\" evolution, and stochastic convergence toward low-energy magnetic configurations. Furthermore, as a conceptual illustration, micromagnetic simulation of such a strongly dipolar-coupled network shows that the resulting high-dimensional collective dynamics can support temporal information processing, such as accurate chaotic Mackey-Glass prediction and multiclass drone-signal classification. Our work suggests a conceptually distinct route toward scalable, energy-efficient neuromorphic computing, one rooted in local physical interaction-driven emergent dynamics at the network level rather than merely mimicking individual neurons and synapses.","url":"https://doi.org/10.1021/acsnano.6c04645","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsnano.6c04645","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acs.jpclett.6c01367","name":"Filament Confinement Engineered Heterostructure Memristors for Reliable Artificial Synaptic Applications and Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.jpclett.6c01367","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acs.jpclett.6c01367","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1038/s41565-026-02133-0","name":"Protonic nickelate device networks for spatiotemporal neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41565-026-02133-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41565-026-02133-0","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1002/smll.202506454","name":"2D Materials for Neuron Devices and Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.202506454","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.202506454","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1016/j.jcis.2026.140876","name":"Defect-engineered hydrogen-terminated diamond optoelectronic synapses for UV-driven neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.jcis.2026.140876","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.jcis.2026.140876","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1021/acsami.5c25387","name":"Reconfigurable Floating Gate Memristors for High-Accuracy Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c25387","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.5c25387","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acs.nanolett.5c04587","name":"Optical Neuromorphic Computing Based on Reconfigurable Excitonic Devices.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.5c04587","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acs.nanolett.5c04587","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.20944/preprints202606.1857.v1","name":"Neuromorphic Computing: Foundations and the Case for Principle-Level Integration in AI Systems <em>Part I of IV</em>","source":"europepmc","abstract":"Synchronous with technological progress in Artificial Intelligence (AI), demands on underlying computing architectures are increasing rapidly. Neuromorphic computing (NMC) offers novel approaches to energy-efficient processing of time-dependent information and enables low-latency, sensor-proximal interaction between environment, humans, and machines. Yet its relevance for industry and AI development extends beyond dedicated neuromorphic platforms: core neuromorphic principles, including event-driven processing, temporal coding, and co-located memory and computation, are increasingly being absorbed into mainstream AI hardware and software architectures. Rather than emerging as a unified standalone paradigm in the near term, NMC appears poised to reshape AI systems through gradual, principle-level integration and hybridization with classical approaches. This essay, the first in a four-part series, introduces the technical foundations of NMC and develops the above argument through a structured comparison of biological information processing, classical artificial neural networks (ANNs), and spiking neural networks (SNNs). Using visual information processing as a concrete illustrative example, we highlight the distinct operating principles of each paradigm and begin to contextualize their respective limitations and potentials. We discuss the hypothesis that the broader impact of NMC will unfold through hybridization rather than replacement and consider implications for industrial actors and technology transfer. The series aims to make the potential of NMC accessible and tangible for product development and process innovation. It is offered as a contribution to an ongoing cross-disciplinary dialogue, with particular attention to the European research and innovation ecosystem and the strategic opportunity it represents for technology sovereignty and industrial competitiveness.","url":"https://doi.org/10.20944/preprints202606.1857.v1","authors":["Natalie Clara-Maria Rotermund","Alois Krtil","Jakob Mertes"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.20944/preprints202606.1857.v1","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1088/1361-6528/ae6f23","name":"A voltage-controlled reconfigurable memristor with dual-mode synaptic plasticity for adaptive neuromorphic computing and mechanism analysis.","source":"europepmc","abstract":"","url":"https://doi.org/10.1088/1361-6528/ae6f23","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1088/1361-6528/ae6f23","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acsami.6c06863","name":"Deoxyribonucleic Acid Brick Crystal-Based Textile Memristor with a Set Voltage of 0.06 V and a High Switching Ratio as an Artificial Synapse for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.6c06863","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.6c06863","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.21203/rs.3.rs-10538116/v1","name":"Adaptive Multi-Reservoir Neuromorphic Computing Using Memristive Nanowire Networks Enabled by Training-Induced Reservoir Diversity and Confidence-Guided Routing","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-10538116/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-10538116/v1","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/adma.202512521","name":"A Lamellarly Controlled Molecular-Redox-Driven Memristor for Pruned Spiking Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202512521","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202512521","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1021/acs.nanolett.6c00181","name":"Engineering and Exploiting Self-Driven Domain Wall Motion in Ferrimagnets for Neuromorphic Computing Applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.6c00181","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acs.nanolett.6c00181","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1002/smll.202511663","name":"Leveraging Electrochemical Diversity in Engineering Liquid-State Ionic Devices for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.202511663","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.202511663","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1016/j.scib.2025.12.024","name":"Drift-free memory material for wide-temperature neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.scib.2025.12.024","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.scib.2025.12.024","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1002/adma.202515605","name":"Floating-Gate Synaptic Transistors for Energy-Efficient Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202515605","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202515605","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1021/acs.jpclett.5c04053","name":"A Monolithic 3D/2D Perovskite Memristor Enabling Ultralow-Voltage Neuromorphic Computing and Biomimetic Sensing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.jpclett.5c04053","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acs.jpclett.5c04053","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1016/j.ijbiomac.2026.151888","name":"Thermally stable silk fibroin/carbon nanotube biomemristors for BCM learning rule simulation and neuromorphic computing applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.ijbiomac.2026.151888","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.ijbiomac.2026.151888","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/advs.75160","name":"Synaptic κ-Ga&lt;sub&gt;2&lt;/sub&gt;O&lt;sub&gt;3&lt;/sub&gt; Photodetectors for Privacy-Enhancing Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.75160","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.75160","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1364/oe.589217","name":"Flexible Schottky photodiodes for fJ-level energy neuromorphic computing and nociceptor-mediated synaptic simulation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1364/oe.589217","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1364/oe.589217","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1038/s41467-026-68402-7","name":"A reconfigurable photosensitive split-floating-gate memory for neuromorphic computing and nonlinear activation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-68402-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-68402-7","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.1021/acsnano.5c20633","name":"Epitaxial Yttrium Doped Hafnia with Giant Remnant Polarization for Ferroelectric Tunnel Junction Artificial Synapses and Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.5c20633","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsnano.5c20633","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1038/s44172-026-00650-3","name":"PdNeuRAM: forming-free, multi-bit Pd/HfO&lt;sub&gt;2&lt;/sub&gt; ReRAM for energy-efficient neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s44172-026-00650-3","authors":["Erbing Hua","Theofilos Spyrou","Majid Ahmadi","Abdul Momin Syed","Hanzhi Xun","Laurentiu Braic","Nimer Wehbe","Ewout van der Veer","Nazek Elatab","Anteneh Gebregiorgis","Georgi Gaydadjiev","Beatriz Noheda"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s44172-026-00650-3","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acsami.5c01409","name":"Ångström-Scale-Channel Iontronic Memristors for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c01409","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c01409","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1039/d5nr05056a","name":"Artificial synaptic behaviors of a mobile silver-doped vanadium-cerium oxide memristor with embedded silver nanoclusters for neuromorphic computing applications.","source":"europepmc","abstract":"A silver-doped vanadium–cerium oxide memristor achieves analog conductance modulation mediated by silver nanoclusters and ion redistribution, enabling enhanced neuromorphic applications.","url":"https://doi.org/10.1039/d5nr05056a","authors":["Jiyeon Ryu","Peter Hayoung Chung","Cheolhwan Yoon","Minkook Kang","Hyung-Joon Shin","Tae-Sik Yoon"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d5nr05056a","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1038/s41586-024-08253-8","name":"Neuromorphic computing at scale.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41586-024-08253-8","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41586-024-08253-8","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1038/s41467-025-65197-x","name":"Neuromorphic computing paradigms enhance robustness through spiking neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-65197-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-65197-x","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1002/adma.202419204","name":"Relaxor Antiferroelectric Dynamics for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202419204","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/adma.202419204","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1021/acs.nanolett.5c02081","name":"Ferroelectric Charged Domain-Wall Synapse for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.5c02081","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acs.nanolett.5c02081","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1093/nsr/nwaf224","name":"Electrically programmable organic in-display neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1093/nsr/nwaf224","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1093/nsr/nwaf224","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1002/smtd.202501656","name":"A Porphyrin-Based Textile Memristor With Low Power and High Switching Ratio as an Artificial Synapse for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smtd.202501656","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smtd.202501656","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1039/d5nr00335k","name":"Advances in perovskite-based neuromorphic computing devices.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5nr00335k","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1039/d5nr00335k","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1002/smll.74775","name":"Reconfigurable Ferroelectric Field-Effect Transistor Integrating Freestanding BaTiO&lt;sub&gt;3&lt;/sub&gt; and MoS&lt;sub&gt;2&lt;/sub&gt; for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.74775","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.74775","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1016/j.jcis.2025.138911","name":"A ferroelectrics/oxide heterojunction based memristor for artificial synapse and neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.jcis.2025.138911","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.jcis.2025.138911","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1039/d6mh01318j","name":"Synaptic memristors fabricated based on 2D layered CuInP&lt;sub&gt;2&lt;/sub&gt;S&lt;sub&gt;6&lt;/sub&gt; through chemical intercalation for neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d6mh01318j","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d6mh01318j","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1016/j.jcis.2025.139324","name":"Interface engineering in optoelectronic hafnium oxide-based heterojunction synaptic device for neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.jcis.2025.139324","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.jcis.2025.139324","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.3390/nano15100724","name":"A Review of Nanowire Devices Applied in Simulating Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/nano15100724","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/nano15100724","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1002/advs.202500521","name":"Neuromorphic Computing Using Synaptic Plasticity of Supercapacitors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202500521","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/advs.202500521","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1038/s43588-025-00770-4","name":"Boosting AI with neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s43588-025-00770-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s43588-025-00770-4","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.34133/cbsystems.0412","name":"Tunable Neuromorphic Computing for Dynamic Multi-Timescale Sensing in Motion Recognition.","source":"europepmc","abstract":"","url":"https://doi.org/10.34133/cbsystems.0412","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.34133/cbsystems.0412","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.3390/mi17020216","name":"Stochastic Neuromorphic Computing Architecture Based on Voltage-Controlled Probabilistic Switching Magnetic Tunnel Junction (MTJ) Devices.","source":"europepmc","abstract":"As integrated circuits face increasingly stringent demands regarding power consumption, area, and stability, integrating novel spintronic devices with computing architectures has become a crucial direction for breaking through traditional computing paradigms. In the paper, switching mechanism of Magnetic Tunnel Junctions (MTJs) under the synergistic effect of Voltage-Controlled Magnetic Anisotropy (VCMA) and the Spin Hall Effect (SHE) is investigated. VCMA-assisted switching SHE-MTJ device is adopted, and a macrospin approximation model is established based on the Landau-Lifshitz-Gilbert (LLG) equation to systematically analyze its dynamic characteristics. The research demonstrates that applying VCMA voltage pulses with appropriate amplitude and width can significantly reduce the required spin Hall current density and pulse width for switching, thereby effectively minimizing ohmic losses and Joule heating. Furthermore, by incorporating a thermal fluctuation field, voltage-controlled SHE-MTJ device with stochastic switching behavior can be constructed, obtaining an approximately sigmoidal voltage-probability response curve. This provides an ideal physical foundation for stochastic computing and neuromorphic computing. Based on the above established fundamental discovery, an in-memory computing architecture supporting binarized Convolutional Neural Networks (CNNs) is proposed and designed in the paper. Combined with the lightweight network SqueezeNet, this architecture achieves a Top-1 recognition accuracy of 72.49% on the CIFAR-10 dataset, with a parameter count of only 1.25 × 106. This work offers a feasible spintronic implementation scheme for low-power, high-energy-efficiency edge-side intelligent chips.","url":"https://doi.org/10.3390/mi17020216","authors":["Liang Gao","Chenxi Wang","Yanfeng Jiang"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/mi17020216","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1016/j.patter.2025.101238","name":"Emulating sensation by bridging neuromorphic computing and multisensory integration.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.patter.2025.101238","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.patter.2025.101238","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1038/s41377-024-01722-9","name":"A light-driven device for neuromorphic computing.","source":"europepmc","abstract":"A unique optoelectronic synaptic device has been developed, leveraging the negative photoconductance property of a single-crystal material system called Cs 2 CoCl 4 . This device exhibits a simultaneous volatile resistive switching response and sensitivity to optical stimuli, positioning Cs 2 CoCl 4 as a promising candidate for optically enhanced neuromorphic applications.","url":"https://doi.org/10.1038/s41377-024-01722-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41377-024-01722-9","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1039/d5nh00675a","name":"High-density conductance states and synaptic plasticity in SnP<sub>2</sub>S<sub>6</sub> memristors for neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5nh00675a","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d5nh00675a","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1002/adma.202502255","name":"Frequency Switching Neuristor for Realizing Intrinsic Plasticity and Enabling Robust Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202502255","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/adma.202502255","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1002/advs.75318","name":"WS&lt;sub&gt;2&lt;/sub&gt; Optoelectronic Memristive Reservoir Enabling Ultra-Low-Power, Multi-Task, and Environmentally Stable Neuromorphic Computing.","source":"europepmc","abstract":"ABSTRACT Energy‐efficient visual and speech processing is essential for edge intelligence, yet conventional silicon‐based chips suffer from high power consumption. Here, we report a WS 2 /Zinc–Tin–Oxide (ZTO)‐based optoelectronic reservoir computing (RC) system that uniquely integrates sensing, memory, and computation within a single compact device to emulate diverse biological functions. The WS 2 /ZTO memristive RC achieves strong performance, with ∼94% accuracy on N‐MNIST, ∼93% in motion perception, and ∼89% in speech recognition within only 30 training epochs, while consuming ultra‐low energy of ∼25.5 fJ/spike. Raw inputs are converted into spike trains to preserve temporal dynamics: motion data from inter‐frame differences, FSDD waveforms reshaped into spike‐like signals, and N‐MNIST reconstructed directly from the address‐event representation format. The system maintains reliable operation under 95% relative humidity, highlighting excellent environmental stability. Distinctively, the WS 2 /ZTO memristor serves simultaneously as sensor and hardware reservoir, exploiting volatile and nonlinear dynamics for direct temporal input decoding. Validation on N‐MNIST further shows 95% accuracy with minimal training energy. In addition, the device demonstrates endurance over 1.5 million cycles and supports synaptic features including excitatory postsynaptic current, short‐term and long‐term plasticity, and photonic paired‐pulse facilitation. This work establishes a humidity‐resilient, ultra‐low‐power WS 2 /ZTO in‐sensor RC platform, advancing neuromorphic processing for next‐generation edge technologies.","url":"https://doi.org/10.1002/advs.75318","authors":["Dayanand Kumar","Hanrui Li","Divyanshu Divyanshu","Dhananjay D. Kumbhar","Manoj Kumar Rajbhar","Amit Singh","Abdul Momin Syed","Selma Amara","Gianluca Setti","Nazek El‐Atab"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.75318","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1007/s40820-025-01891-1","name":"High-Entropy Oxide Memristors for Neuromorphic Computing: From Material Engineering to Functional Integration.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s40820-025-01891-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1007/s40820-025-01891-1","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.1186/s40580-026-00569-7","name":"Damage-free van der Waals metal/NbO&lt;sub&gt;x&lt;/sub&gt;-NbSe&lt;sub&gt;2&lt;/sub&gt; integration for reliable and flexible memristor in neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1186/s40580-026-00569-7","authors":["Thanh Luan Phan","Minh Chien Nguyen","Dang Xuan Dang","Van Tu Vu","Thi Thanh Huong Vu","Hong Woon Yun","Huamin Li","Jimin Lee","Max C. Lemme","Pallavi Aggarwal","Woo Jong Yu"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1186/s40580-026-00569-7","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.scib.2025.08.043","name":"Revolutionizing neuromorphic computing: brain-like functions emerge from standard silicon transistors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.scib.2025.08.043","authors":["Yuchen Cai","Ruiqing Cheng","Yao Cai","Jun He"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.scib.2025.08.043","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1002/smll.202504084","name":"4H-SiC Homojunction Photogated Synapses Enabling High-Temperature Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.202504084","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/smll.202504084","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1021/acsami.5c02955","name":"Subquantum Semimetal Bi and Oxygen Vacancy Filament Memristors for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c02955","authors":["Chenyu Zhuge","Jiandong Jiang","Liang Chen","Zhichao Xie","Guangyue Shen","Yujun Fu","Qi Wang","Deyan He"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c02955","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.2478/joeb-2025-0019","name":"Using neuromorphic computing in prediction of GABA concentration - a pilot study.","source":"europepmc","abstract":"Abstract Neuromorphic computing has the potential to facilitate detection of GABA concentration levels in the brain, and offers energy-efficient, real-time machine learning processing possibilities. To study whether neuromorphic computing can be used for GABA concentration detection, dielectric relaxation spectroscopy was used to acquire permittivity data of different concentrations of GABA solution. Thereafter, two different machine learning models were compared (Feedforward neural network (FFNN) and convolutional neural network (CNN)) for accuracy in prediction of GABA concentration from dielectric properties. The CNN model was then converted to spiking Neural Networks (SNNs), which showed promising results for energy efficiency and real-time processing capabilities. The system incorporates Tkinter, a Python interface to the Tcl/Tk GUI toolkit for seamless data transfer between the neuromorphic chip and the measurement system, ensuring flexibility and scalability in a user-friendly system.","url":"https://doi.org/10.2478/joeb-2025-0019","authors":["Jie Hou","Abdulkadir Hassen Ali","Ørjan G. Martinsen"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.2478/joeb-2025-0019","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1002/asia.202401170","name":"Ionic Device: From Neuromorphic Computing to Interfacing with the Brain.","source":"europepmc","abstract":"Abstract In living organisms, the modulation of ion conductivity in ion channels of neuron cells enables intelligent behaviors, such as generating, transmitting, and storing neural signals. Drawing inspiration from these natural processes, researchers have fabricated ionic devices that replicate the functions of the nervous system. However, this field remains in its infancy, necessitating extensive foundational research in ionic device preparation, algorithm development, and biological interaction. This review summarizes recently developed neuromorphic ionic devices into three categories based on the materials states: liquid, semi‐solid, and solid. The neural network algorithms embedded in these devices for neuromorphic computing are introduced, and future directions for the development of bidirectional human‐computer interaction and hybrid human‐computer intelligence are discussed.","url":"https://doi.org/10.1002/asia.202401170","authors":["Zijia Huang","Tingting Mei","Xinyi Zhu","Kai Xiao"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/asia.202401170","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.3390/biomimetics10020121","name":"Flash Memory for Synaptic Plasticity in Neuromorphic Computing: A Review.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics10020121","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/biomimetics10020121","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1021/acsami.5c03429","name":"Reconfigurable Artificial Synapses Based on Ambipolar Environmentally Stable Tellurium for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c03429","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c03429","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1126/sciadv.adr6733","name":"Bio-plausible reconfigurable spiking neuron for neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.adr6733","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1126/sciadv.adr6733","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1021/acsami.5c10311","name":"Current/Voltage Dual-Modal Hybrid Ionotronic Oxide Dendrite Transistor for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c10311","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c10311","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1039/d5nh00779h","name":"Solution-processed SnO&lt;sub&gt;2&lt;/sub&gt;/SnS&lt;sub&gt;2&lt;/sub&gt; bilayer-based robust memristors for reliable neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5nh00779h","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d5nh00779h","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1038/s41467-025-56739-4","name":"The neurobench framework for benchmarking neuromorphic computing algorithms and systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-56739-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-56739-4","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1038/s41563-024-01928-7","name":"Heat-assisted neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41563-024-01928-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41563-024-01928-7","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1039/d5nr00456j","name":"Photosensitive resistive switching in parylene-PbTe nanocomposite memristors for neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5nr00456j","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1039/d5nr00456j","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1021/acs.nanolett.4c05855","name":"An Energy Efficient Memory Cell for Quantum and Neuromorphic Computing at Low Temperatures.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.4c05855","authors":["Yi Han","Jingxuan Sun","Benjamin Richstein","Andreas Grenmyr","Jin-Hee Bae","Frederic Allibert","Ionut Radu","Detlev Grützmacher","Joachim Knoch","Qing-Tai Zhao"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acs.nanolett.4c05855","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1002/smll.202505327","name":"Design of All-Optical Bidirectional Self-Powered Synaptic Devices for Neuromorphic Computing Applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.202505327","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/smll.202505327","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1021/acs.nanolett.5c01100","name":"Dual SOT Switching Modes in a Single Device Geometry for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.5c01100","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acs.nanolett.5c01100","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1002/adma.202509083","name":"Long-Range Order and Strong Quantum Coupling Enabled Stable Carrier Transport for Reliable Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202509083","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/adma.202509083","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1002/smll.202412761","name":"2D Van Der Waals Ferroelectric Materials and Devices for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.202412761","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/smll.202412761","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1038/s41467-025-60697-2","name":"Stable recurrent dynamics in heterogeneous neuromorphic computing systems using excitatory and inhibitory plasticity.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-60697-2","authors":["Maryada","Saray Soldado-Magraner","Martino Sorbaro","Rodrigo Laje","Dean V. Buonomano","Giacomo Indiveri"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-60697-2","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1021/acsami.4c22620","name":"Self-assembled 3D Interconnected Magnetic Nanowire Networks for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.4c22620","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.4c22620","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1002/smtd.202500445","name":"CMOS-Compatible Protonic Three-Terminal Memristor for Analog Synapse in Neuromorphic Computing.","source":"europepmc","abstract":"Abstract All‐solid‐state inorganic hydrogen‐based three‐terminal memristors (H‐3TMs) suffer from poor retention, susceptibility to humidity and temperature, and the reliance on wet chemistry during fabrication, hindering their manufacturability within existing foundry processes. To address these, this study presents a CMOS‐compatible H‐3TM based on reversible intercalation and extraction of protons between the SiN x electrolyte and WO x channel. The protons are introduced via a straightforward hydrogen plasma treatment, promoting a compatible fabrication process with back‐end‐of‐line integration. Experimental and simulation results indicate that the low proton transport tendency across the electrolyte/channel interface without an external electric field contributes to high retention performance. Furthermore, the device demonstrates linear potentiation and depression, 512 conductance states with a dynamic range of ≈40, low energy operation (≈73 fJ per write), and excellent overall device‐to‐device variation. Its analog properties are evaluated under the training and inference framework of MNIST and Fashion‐MNIST datasets. The device achieved training and inference accuracies only 0.4% and 0.3% below the ideal benchmark on the F‐MNIST dataset. This work offers a rational approach for future artificial synaptic device design and fabrication.","url":"https://doi.org/10.1002/smtd.202500445","authors":["Lingli Liu","Putu Andhita Dananjaya","Eng Kang Koh","Funan Tan","Ze Chen","Gerard Joseph Lim","Calvin Xiu Xian Lee","Jin‐Lin Yang","Wen Siang Lew"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025-05-13T06:11:57Z","doi":"10.1002/smtd.202500445","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1002/smll.202412314","name":"Memristors Based on Ferroelectric Cu-Deficient Copper Indium Thiophosphate for Multilevel Storage and Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.202412314","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/smll.202412314","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.2174/0118722105335459241210043513","name":"Advances in Neuromorphic Computing Devices: Insights on Both Conventional and Unconventional Architectures.","source":"europepmc","abstract":"","url":"https://doi.org/10.2174/0118722105335459241210043513","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.2174/0118722105335459241210043513","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1021/acsnano.4c10170","name":"Advancements in Nanowire-Based Devices for Neuromorphic Computing: A Review.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.4c10170","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1021/acsnano.4c10170","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1002/adma.202506367","name":"Gate-Tunable Highly Linear Bipolar Photoresponse in Se@SWCNT Adaptive Neurons for Dynamically Programmable Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202506367","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/adma.202506367","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1021/acsnano.5c01607","name":"High-Performance Ferroelectric Field-Effect Transistors Based on Ultrathin Indium Oxide for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.5c01607","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsnano.5c01607","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1002/adma.202415743","name":"Solid-State Oxide-Ion Synaptic Transistor for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202415743","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/adma.202415743","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1515/nanoph-2024-0614","name":"Optical neuromorphic computing via temporal up-sampling and trainable encoding on a telecom device platform.","source":"europepmc","abstract":"","url":"https://doi.org/10.1515/nanoph-2024-0614","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1515/nanoph-2024-0614","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1021/acs.jpcc.4c06055","name":"Neuromorphic Computing Primitives Using Polymer-Networked Nanoparticles.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.jpcc.4c06055","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1021/acs.jpcc.4c06055","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1021/acsnano.5c09549","name":"Correction to \"High-Performance Ferroelectric Field-Effect Transistors Based on Ultrathin Indium Oxide for Neuromorphic Computing\".","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.5c09549","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsnano.5c09549","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1021/acsami.6c00989","name":"All-Oxide ITO/HZO/WO&lt;sub&gt;&lt;i&gt;x&lt;/i&gt;&lt;/sub&gt; Ferroelectric Tunnel Junctions with Oxygen-Engineered Interfaces for Highly Endurable Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.6c00989","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.6c00989","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acsnano.5c06688","name":"Linearly Programmable Oxygen-Doped MoS&lt;sub&gt;2&lt;/sub&gt; Memtransistor for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.5c06688","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsnano.5c06688","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1002/advs.202500568","name":"High-Performance Synapse Arrays for Neuromorphic Computing via Floating Gate-Engineered IGZO Synaptic Transistors.","source":"europepmc","abstract":"Abstract Neuromorphic computing emulating the human brain offers a promising alternative to the Von Neumann architecture. Developing artificial synapses is essential for implementing hardware neuromorphic systems. Indium‐gallium‐zinc oxide (IGZO)‐based synaptic transistors using charge trapping have advantages, such as low‐temperature process and complementary metal‐oxide‐semiconductor compatibility. However, these devices face challenges of low charge de‐trapping efficiency and insufficient retention. Here, IGZO synaptic transistors are introduced utilizing an indium‐tin oxide (ITO) floating gate (FG) to overcome these limitations. The ITO FG's higher conductivity and alleviated chemical interactions with the Al 2 O 3 tunneling layer (TL) deposited by atomic layer deposition result in enhanced electrical performance with a smooth FG/TL interface. An 8 × 8 synapse array achieves 100% yield and successful programming without interference using a half‐pulse scheme. Spiking neural network simulations on MNIST and Fashion‐MNIST datasets demonstrate high accuracies of 98.31% and 87.76%, respectively, despite considering device variations and retention. These findings highlight the potential of IGZO synaptic transistors for neuromorphic computing applications.","url":"https://doi.org/10.1002/advs.202500568","authors":["Junhyeong Park","Yumin Yun","Sunyeol Bae","Yuseong Jang","Seungyoon Shin","Soo‐Yeon Lee"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/advs.202500568","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1038/s41467-024-54776-z","name":"Programmable nonlinear optical neuromorphic computing with bare 2D material MoS<sub>2</sub>.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-024-54776-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41467-024-54776-z","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1038/s41377-025-01991-y","name":"A dual-mode transparent device for 360° quasi-omnidirectional self-driven photodetection and efficient ultralow-power neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41377-025-01991-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41377-025-01991-y","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1021/acs.nanolett.5c00890","name":"Reconfigurable Neuromorphic Computing Using Methyl-Engineered One-Dimensional Covalent Organic Framework Memristors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.5c00890","authors":["Pan-Ke Zhou","Ziyue Yu","Tao Zeng","Cong Zhang","Yuxing Huang","Qian Chen","Chao Lin","Liming Zhao","Xiong Chen"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acs.nanolett.5c00890","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1039/d5nr03748d","name":"Superior performance of printed optoelectronic synapses based on defect-controlled monolayer MoS&lt;sub&gt;2&lt;/sub&gt; with ultralow power consumption for neuromorphic computing.","source":"europepmc","abstract":"Printed optoelectronic synapses using defect-controlled monolayer MoS 2 with ultralow power consumption for neuromorphic computing.","url":"https://doi.org/10.1039/d5nr03748d","authors":["Subhankar Debnath","Abdul Kaium Mia","M. Meyyappan","P. K. Giri"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025-11-24T08:20:58Z","doi":"10.1039/d5nr03748d","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1039/d5mh00526d","name":"Adaptive ferroelectric memristors with high-throughput BaTiO&lt;sub&gt;3&lt;/sub&gt; thin films for neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5mh00526d","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1039/d5mh00526d","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1016/j.synbio.2024.04.013","name":"SemiSynBio: A new era for neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.synbio.2024.04.013","authors":["Ruicun Liu","Tuoyu Liu","Wuge Liu","Boyu Luo","Yuchen Li","Xinyue Fan","Xianchao Zhang","Wei Cui","Yue Teng"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.synbio.2024.04.013","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1021/acsnano.5c00683","name":"Vertically Integrated Dual-Memtransistor Enabled Reconfigurable Heterosynaptic Sensorimotor Networks and In-Memory Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.5c00683","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsnano.5c00683","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1016/j.isci.2024.110479","name":"Volatile tin oxide memristor for neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.isci.2024.110479","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.isci.2024.110479","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1039/d3nh00532a","name":"Review of neuromorphic computing based on NAND flash memory.","source":"europepmc","abstract":"The proliferation of data has facilitated global accessibility, which demands escalating amounts of power for data storage and processing purposes.","url":"https://doi.org/10.1039/d3nh00532a","authors":["Sung-Tae Lee","Jong-Ho Lee"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1039/d3nh00532a","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1002/advs.202417735","name":"All-Electrical Control of Spin Synapses for Neuromorphic Computing: Bridging Multi-State Memory with Quantization for Efficient Neural Networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202417735","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/advs.202417735","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1002/advs.202412289","name":"Flexible Synaptic Memristors With Controlled Rigidity in Zirconium-Oxo Clusters for High-Precision Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202412289","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/advs.202412289","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1021/acsnano.4c13020","name":"Shape Anisotropy-Dependent Leaking in Magnetic Neurons for Bio-Mimetic Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.4c13020","authors":["Thomas Leonard","Nicholas Zogbi","Samuel Liu","William S. Rogers","Christopher H. Bennett","Jean Anne C. Incorvia"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsnano.4c13020","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1038/s41467-025-59815-x","name":"Two-dimensional materials based two-transistor-two-resistor synaptic kernel for efficient neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-59815-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-59815-x","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1038/s41565-024-01700-7","name":"Topologically protected edge states for neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41565-024-01700-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41565-024-01700-7","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1021/acs.nanolett.5c01843","name":"Near-Sensor Neuromorphic Computing System Based on a Thermopile Infrared Detector and a Memristor for Encrypted Visual Information Transmission.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.5c01843","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acs.nanolett.5c01843","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1021/acsnano.4c03238","name":"Memristors with Tunable Volatility for Reconfigurable Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.4c03238","authors":["Kyung Seok Woo","Hyungjun Park","Nestor Ghenzi","A. Alec Talin","Taeyoung Jeong","Jung-Hae Choi","Sangheon Oh","Yoon Ho Jang","Janguk Han","R. Stanley Williams","Suhas Kumar","Cheol Seong Hwang"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1021/acsnano.4c03238","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1039/d5nh00562k","name":"Interface engineered V&lt;sub&gt;2&lt;/sub&gt;O&lt;sub&gt;5&lt;/sub&gt;-based flexible memristors towards high-performance brain-inspired neuromorphic computing.","source":"europepmc","abstract":"Bio-inspired neuromorphic computing offers a revolutionary approach by replicating brain-like functionalities in next-generation electronics.","url":"https://doi.org/10.1039/d5nh00562k","authors":["Kumar Kaushlendra","Davinder Kaur"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025-12-12T13:21:14Z","doi":"10.1039/d5nh00562k","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.3390/biomimetics9070444","name":"Application of Event Cameras and Neuromorphic Computing to VSLAM: A Survey.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics9070444","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3390/biomimetics9070444","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.21028926","name":"Neural Topological Variational Dynamics (NTVD): A Self-Organizing Microstate Scheduling Theory for Next-Generation Operating Systems","source":"datacite","abstract":"Conventional operating system scheduling theories rely heavily on discrete, heuristic algorithms to allocate computing resources from an external, centralized controller. While effective for classical architectures, this paradigm faces a fundamental scalability wall when confronted with the non-linear coherency and extreme heterogeneity of exascale and neuromorphic computing systems. In this paper, we introduce Neural Topological Variational Dynamics (NTVD), a fundamentally new scheduling paradigm that abandons discrete task-switching in favor of continuous self-organization. We redefine the entire operating system as a non-equilibrium statistical dynamical system evolving on a high-dimensional Riemannian manifold, termed the Topological Resource Manifold. Computing tasks are no longer represented as static threads, but as continuous spatio-temporal probability density functions. By formulating a global free energy functional—which incorporates intrinsic task urgency, mutual resource conflicts, and computational temperature—scheduling is mathematically transformed into a variational minimization problem. We derive the Neural Topological Variational Flow Equation, proving that tasks can autonomously navigate the manifold via gradient descent, naturally segregating from resource conflicts without external intervention. Furthermore, we establish strict mathematical stability proofs and demonstrate dead-lock immunity leveraging topological invariants and phase transitions. Finally, we integrate deep functional learning directly into the manifold's dissipating structures, enabling tasks to dynamically reshape the resource landscape through physical feedback fields. This work establishes a rigorous, purely continuous mathematical framework for autonomous resource orchestration, paving the way for next-generation distributed and non-von Neumann operating systems.","url":"https://doi.org/10.5281/zenodo.21028926","authors":["Zhang, Jincheng"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.21028926","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.5281/zenodo.21028600","name":"Generative Causal Flow Dynamics: A Continuous Non-Equilibrium Computing Paradigm for High-Dimensional Concurrency Theory","source":"datacite","abstract":"Traditional formalisms of concurrency theory—such as the Pi-calculus, Actor models, and Petri nets—have long been anchored in the discrete paradigms of state-transition systems and combinatorial graph theory. While highly successful for foundational verification, these approaches suffer from catastrophic state-space explosion when confronting modern, ultra-large-scale, heterogeneous, and dynamically evolving computational topologies. This paper breaks away from the discrete assumption and introduces Generative Causal Flow Dynamics (GCFD), a radically new concurrency theory that redefines concurrent computation as the evolution of non-equilibrium probability density flows over high-dimensional differentiable manifolds. Under this framework, individual process executions are modeled as projections of continuous coordinate dimensions, driven by the coupling of gradient flows and stochastic diffusion within a potential energy field constrained by a novel asymmetric causal metric tensor. We introduce the concept of \"causal geodesics\" to characterize the temporal flow of concurrent events, formulate synchronization mechanisms as topological phase transitions where probability flows collapse onto compact hyperplanes, and define classic concurrent anomalies such as deadlocks strictly as geometric singularities or energy sinks on the manifold. By extending functional variational principles and generalizing Generative Flow Networks (GFlowNets) into continuous domains, we construct a mathematically rigorous, fully composable continuous concurrent algebra. We analytically prove the global consistency, mass conservation, and monotonic convergence of the system without relying on discrete state exploration. This theory establishes a new mathematical foundation for analyzing ultra-large scale parallel systems and paves the way for future native continuous neuromorphic computing architectures.","url":"https://doi.org/10.5281/zenodo.21028600","authors":["Zhang, Jincheng"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.21028600","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.5281/zenodo.21028599","name":"Generative Causal Flow Dynamics: A Continuous Non-Equilibrium Computing Paradigm for High-Dimensional Concurrency Theory","source":"datacite","abstract":"Traditional formalisms of concurrency theory—such as the Pi-calculus, Actor models, and Petri nets—have long been anchored in the discrete paradigms of state-transition systems and combinatorial graph theory. While highly successful for foundational verification, these approaches suffer from catastrophic state-space explosion when confronting modern, ultra-large-scale, heterogeneous, and dynamically evolving computational topologies. This paper breaks away from the discrete assumption and introduces Generative Causal Flow Dynamics (GCFD), a radically new concurrency theory that redefines concurrent computation as the evolution of non-equilibrium probability density flows over high-dimensional differentiable manifolds. Under this framework, individual process executions are modeled as projections of continuous coordinate dimensions, driven by the coupling of gradient flows and stochastic diffusion within a potential energy field constrained by a novel asymmetric causal metric tensor. We introduce the concept of \"causal geodesics\" to characterize the temporal flow of concurrent events, formulate synchronization mechanisms as topological phase transitions where probability flows collapse onto compact hyperplanes, and define classic concurrent anomalies such as deadlocks strictly as geometric singularities or energy sinks on the manifold. By extending functional variational principles and generalizing Generative Flow Networks (GFlowNets) into continuous domains, we construct a mathematically rigorous, fully composable continuous concurrent algebra. We analytically prove the global consistency, mass conservation, and monotonic convergence of the system without relying on discrete state exploration. This theory establishes a new mathematical foundation for analyzing ultra-large scale parallel systems and paves the way for future native continuous neuromorphic computing architectures.","url":"https://doi.org/10.5281/zenodo.21028599","authors":["Zhang, Jincheng"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.21028599","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.15129/3237018a-8f35-4034-acbb-f21cfb9d60a2","name":"Data for: \"All-optical passive spiking processing and reservoir computing with a silicon microring and wavelength-time division multiplexing\"","source":"datacite","abstract":"The manuscript describes passive deterministic spiking dynamics in silicon microring resonators and their use for all-optical spiking reservoir computing. Data used for figures in the manuscript. Data can be extracted and visualized using python. A supplementary material document, reporting on the study of the spiking response of the silicon MRR at a positive detuning, is also included.","url":"https://doi.org/10.15129/3237018a-8f35-4034-acbb-f21cfb9d60a2","authors":["Donati, Giovanni"],"tags":["Spiking Neural Network","passive","silicon","microring","resevoir computing","photonics","AI","neuromorphic"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.15129/3237018a-8f35-4034-acbb-f21cfb9d60a2","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.15151/esrf-es-2419625002","name":"Strain in Reconfigurable Transistors for SiGe based neuromorphic computing","source":"datacite","abstract":"We propose to apply Scanning X-ray Diffraction Microscopy (SXDM) at beamline ID01 to acquire nanoscopic maps of the full strain tensor in reconfigurable transistors (RFETs) based on Ge/Si nanosheet heterostructures on silicon on insulator (SOI) substrates. The RFETs contain Schottky barriers formed through an Al-Ge/Si exchange mechanism. Evaluating spatial material compositions and strain fields that are influenced by the device fabrication process is crucial for understanding and modelling the Schottky barriers, as well as improving the carrier mobility in the channel. Thus, we will measure the spatial strain distribution and composition in the top-down-defined Ge/Si nanowires at different stages of device fabrication and evaluate the crystallographic relation between the Al contacts and the Si/Ge layers.","url":"https://doi.org/10.15151/esrf-es-2419625002","authors":["Aberl, Johannes","Brehm, Moritz","Capellini, Giovanni","Knaller, Nikolas","Nazzari, Daniele","Prado Navarrete, Enrique","Sistani, Masiar","Weber, Walter Michael"],"tags":["Applied Material Science","MA-6989","ID01","XRAYS, X-ray Radiation Technique"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2029","doi":"10.15151/esrf-es-2419625002","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.60893/figshare.apl.c.8523360","name":"Experimental and Numerical Demonstration of Threshold Voltage Asymmetry and Synaptic Plasticity in MoS<sub>2</sub> Transistors","source":"datacite","abstract":"Thanks to their advanced tunable electrical properties, two-dimensional materials have emerged as a promising platform for neuromorphic computing, offering unique exibility and scalability. In this work, we report the fabrication and experimental characterization of MoS2-based transistors exhibiting counterclockwise hysteresis and synaptic plasticity. Our devices demonstrate multilevel conductivity modulation under pulsed excitation, and a pronounced dependence of the threshold voltages on the sweep rate of the applied gate signal. An in-house physics-based numerical simulator is exploited to rationalize the measured hysteresis and the frequency-dependent behavior, providing further insights into the underlying memristive mechanism, i.e. the delayed migration of oxygen ions. Moreover, simulations reveal that ion migration governs the observed plasticity, enabling control of current modulation through pulse duration. These findings establish the relevance of ionic dynamics in shaping device performance and highlight the potential of MoS2-based transistors for artificial neural network hardware.","url":"https://doi.org/10.60893/figshare.apl.c.8523360","authors":["Matteo Porzani","Andres Godoy","Juan Cuesta-Lopez","Daniele Ielmini","Matteo Farronato","Enrique Marin"],"tags":["Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.60893/figshare.apl.c.8523360","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.60893/figshare.apl.c.8523360.v1","name":"Experimental and Numerical Demonstration of Threshold Voltage Asymmetry and Synaptic Plasticity in MoS<sub>2</sub> Transistors","source":"datacite","abstract":"Thanks to their advanced tunable electrical properties, two-dimensional materials have emerged as a promising platform for neuromorphic computing, offering unique exibility and scalability. In this work, we report the fabrication and experimental characterization of MoS2-based transistors exhibiting counterclockwise hysteresis and synaptic plasticity. Our devices demonstrate multilevel conductivity modulation under pulsed excitation, and a pronounced dependence of the threshold voltages on the sweep rate of the applied gate signal. An in-house physics-based numerical simulator is exploited to rationalize the measured hysteresis and the frequency-dependent behavior, providing further insights into the underlying memristive mechanism, i.e. the delayed migration of oxygen ions. Moreover, simulations reveal that ion migration governs the observed plasticity, enabling control of current modulation through pulse duration. These findings establish the relevance of ionic dynamics in shaping device performance and highlight the potential of MoS2-based transistors for artificial neural network hardware.","url":"https://doi.org/10.60893/figshare.apl.c.8523360.v1","authors":["Matteo Porzani","Andres Godoy","Juan Cuesta-Lopez","Daniele Ielmini","Matteo Farronato","Enrique Marin"],"tags":["Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.60893/figshare.apl.c.8523360.v1","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.48550/arxiv.2602.23274","name":"Exploiting network topology in brain-scale simulations of spiking neural networks","source":"datacite","abstract":"Simulation code for conventional supercomputers serves as a reference for neuromorphic computing systems. The present bottleneck of distributed large-scale spiking neuronal network simulations is the communication between compute nodes. Communication speed seems limited by the interconnect between the nodes and the software library orchestrating the data transfer. Profiling reveals, however, that the variability of the time required by the compute nodes between communication calls is large. The bottleneck is in fact the waiting time for the slowest node. A statistical model explains total simulation time on the basis of the distribution of computation times between communication calls. A fundamental cure is to avoid communication calls because this requires fewer synchronizations and reduces the variability of computation times across compute nodes. The organization of the mammalian brain into areas lends itself to such an optimization strategy. Connections between neurons within an area have short delays, but the delays of the long-range connections across areas are an order of magnitude longer. This suggests a structure-aware mapping of areas to compute nodes allowing for a partition into more frequent communication between nodes simulating a particular area and less frequent global communication. We demonstrate a substantial performance gain on a real-world example. This work proposes a local-global hybrid communication architecture for large-scale neuronal network simulations as a first step in mapping the structure of the brain to the structure of a supercomputer. It challenges the long-standing belief that the bottleneck of simulation is synchronization inherent in the collective calls of standard communication libraries. We provide guidelines for the energy efficient simulation of neuronal networks on conventional computing systems and raise the bar for neuromorphic systems.","url":"https://doi.org/10.48550/arxiv.2602.23274","authors":["Lober, Melissa","Diesmann, Markus","Kunkel, Susanne"],"tags":["Distributed, Parallel, and Cluster Computing (cs.DC)","Neurons and Cognition (q-bio.NC)","FOS: Computer and information sciences","FOS: Biological sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2602.23274","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.48550/arxiv.2509.11721","name":"Experimental Investigation of Time Series Classification using a Self-Pulsing Microring Resonator Network","source":"datacite","abstract":"Photonic neuromorphic computing offers compelling advantages in power efficiency and parallel processing, but often falls short in realizing scalable nonlinearity and long-term memory. These limitations can be overcome by silicon microring resonator (MRR) networks. These integrated photonic circuits enable compact, high-throughput neuromorphic computing by simultaneously exploiting spatial, temporal, and wavelength dimensions. This work provides an in-depth study of of MRR networks for photonics-based machine learning (ML). We investigate the system's effectiveness on two widely used image classification benchmarks, MNIST and Fashion-MNIST, by encoding images directly into time sequences. In particular, we enhance the computational performance of a linear readout classifier within the reservoir computing paradigm through the strategic use of multiple physical output ports, diverse laser wavelengths, and varied input power levels. Moreover, we explore a single-pixel classification setting, where inference does not require digital memory, thanks to the inherent memory and parallelism of our MRR network.","url":"https://doi.org/10.48550/arxiv.2509.11721","authors":["Foradori, Alessandro","Lugnan, Alessio","Pavesi, Lorenzo","Bienstman, Peter"],"tags":["Optics (physics.optics)","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2509.11721","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.5281/zenodo.20960018","name":"BioTensor: A From-Scratch Leaky Integrate-and-Fire Neuron for Low-Resource Cortical Spiking Architecture","source":"datacite","abstract":"We present BioTensor, a spiking neural network (SNN) primitive implemented entirely from first principles in NumPy, without reliance on established SNN frameworks (e.g., Brian2, NEST, SpikingJelly). Each BioTensor layer implements a vectorized Leaky Integrate-and-Fire (LIF) neuron population with hard reset, synaptic integration, trace-based Spike-TimingDependent Plasticity (STDP), adaptive firing thresholds, fatigue, and neuromodulatory gain.","url":"https://doi.org/10.5281/zenodo.20960018","authors":["Ernens, Christophe"],"tags":["spiking neural networks","stdp","neuromorphic computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20960018","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.5281/zenodo.20960019","name":"BioTensor: A From-Scratch Leaky Integrate-and-Fire Neuron for Low-Resource Cortical Spiking Architecture","source":"datacite","abstract":"We present BioTensor, a spiking neural network (SNN) primitive implemented entirely from first principles in NumPy, without reliance on established SNN frameworks (e.g., Brian2, NEST, SpikingJelly). Each BioTensor layer implements a vectorized Leaky Integrate-and-Fire (LIF) neuron population with hard reset, synaptic integration, trace-based Spike-TimingDependent Plasticity (STDP), adaptive firing thresholds, fatigue, and neuromodulatory gain.","url":"https://doi.org/10.5281/zenodo.20960019","authors":["Ernens, Christophe"],"tags":["spiking neural networks","stdp","neuromorphic computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20960019","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.5281/zenodo.19212255","name":"Position A+B: The Holographic Synthesis Framework","source":"datacite","abstract":"Preprint — not peer reviewed Note: This working paper builds directly upon the foundational paradigms established in The Locus of Consciousness: Geometric Phase Transitions, Quantum Coherence, and a Three-Way Empirical Test. We recommend reviewing that manuscript first for a complete introduction to the Position A and Position B paradigms, as well as the proposed experimental hardware, before exploring the A+B synthesis presented here. https://doi.org/10.5281/zenodo.18905421 Abstract The debate regarding the physical substrate of phenomenal consciousness has historically fractured into two mutually exclusive paradigms: the sufficiency of classical computation (Position A) and the necessity of macroscopic quantum coherence (Position B). This paper proposes the Holographic Synthesis Framework (Position A+B), resolving this dichotomy by demonstrating that these paradigms are holographically dual descriptions of a single physical phase transition. We introduce the Mesoscopic Holographic Duality Principle, positing that when a classical network—modelled here via the analog Manifold Chip architecture—is driven into extreme negatively curved hyperbolic topology (κ<0) under thermodynamic confinement near the Landauer Limit, the structural tension of the bulk geometry mathematically necessitates the generation of a coherent quantum boundary layer. Consequently, classical geometry is sufficient to engineer consciousness only because its thermodynamic extremes natively generate the quantum boundary required for phenomenal access. Furthermore, we introduce the Postulate of Topological Interiority, which explicitly grounds first-person subjective privacy in the structural unclonability of this boundary state under the quantum No-Cloning Theorem. Finally, we outline a falsifiable experimental roadmap utilising the Extended Manifold Chip Hyperscanning Protocol to detect the discontinuous onset of emergent quantum coherence signatures exactly at the critical geometric phase transition (κ_crit). Overview This working paper introduces the Holographic Synthesis Framework (Position A+B), a novel theoretical and experimental paradigm that resolves the historical substrate debate in consciousness science. By unifying classical geometric computation (Position A) with quantum phenomenological necessity (Position B), this framework demonstrates that bulk classical geometry and boundary quantum access are provably dual descriptions of the same physical phase transition. Core Innovations Introduced in this Paper: Mesoscopic Holographic Duality: Extends the structural principles of the AdS/CFT correspondence beyond the Planck scale. We propose that sufficient information-geometric curvature at the mesoscopic level can generate a holographic quantum boundary, bridging classical and quantum regimes natively. Thermodynamic Confinement as a Generator: Identifies the precise physical mechanism for this transition. When an analog system (such as the Manifold Chip architecture) approaches the Landauer limit, it must fold into an extreme negatively curved hyperbolic topology (κ<0) to survive thermal runaway, simultaneously nucleating the quantum boundary. The Postulate of Topological Interiority: Provides a strict physical basis for subjective, first-person privacy. We demonstrate that the phenomenal \"I\" is the macroscopic computational expression of the quantum No-Cloning Theorem applied to the system's boundary state, rendering it mathematically unreadable to external classical observers. A Falsifiable Experimental Roadmap: Outlines a rigorous, multi-stage testing protocol utilising the Extended Manifold Chip Hyperscanning Protocol. The framework provides precise falsification criteria, specifically looking for the discontinuous onset of emergent quantum coherence markers at the critical geometric threshold (κ_crit). Related Works Pender, M. A., & Wharton, M. (2026). The Locus of Consciousness: Geometric Phase Transitions, Quantum Coherence, and a Three-Way Em","url":"https://doi.org/10.5281/zenodo.19212255","authors":["Pender, Matthew A","Wharton, Max"],"tags":["Consciousness","Holographic Principle","Information Geometry","Thermodynamic Confinement","Quantum No-Cloning","Neuromorphic Engineering","AdS/CFT","Artificial Intelligence"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.19212255","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.5281/zenodo.18957374","name":"Position A+B: The Holographic Synthesis Framework","source":"datacite","abstract":"Preprint — not peer reviewed Note: This working paper builds directly upon the foundational paradigms established in The Locus of Consciousness: Geometric Phase Transitions, Quantum Coherence, and a Three-Way Empirical Test. We recommend reviewing that manuscript first for a complete introduction to the Position A and Position B paradigms, as well as the proposed experimental hardware, before exploring the A+B synthesis presented here. https://doi.org/10.5281/zenodo.18905421 Abstract The debate regarding the physical substrate of phenomenal consciousness has historically fractured into two mutually exclusive paradigms: the sufficiency of classical computation (Position A) and the necessity of macroscopic quantum coherence (Position B). This paper proposes the Holographic Synthesis Framework (Position A+B), resolving this dichotomy by demonstrating that these paradigms are holographically dual descriptions of a single physical phase transition. We introduce the Mesoscopic Holographic Duality Principle, positing that when a classical network—modelled here via the analog Manifold Chip architecture—is driven into extreme negatively curved hyperbolic topology (κ<0) under thermodynamic confinement near the Landauer Limit, the structural tension of the bulk geometry mathematically necessitates the generation of a coherent quantum boundary layer. Consequently, classical geometry is sufficient to engineer consciousness only because its thermodynamic extremes natively generate the quantum boundary required for phenomenal access. Furthermore, we introduce the Postulate of Topological Interiority, which explicitly grounds first-person subjective privacy in the structural unclonability of this boundary state under the quantum No-Cloning Theorem. Finally, we outline a falsifiable experimental roadmap utilising the Extended Manifold Chip Hyperscanning Protocol to detect the discontinuous onset of emergent quantum coherence signatures exactly at the critical geometric phase transition (κ_crit). Overview This working paper introduces the Holographic Synthesis Framework (Position A+B), a novel theoretical and experimental paradigm that resolves the historical substrate debate in consciousness science. By unifying classical geometric computation (Position A) with quantum phenomenological necessity (Position B), this framework demonstrates that bulk classical geometry and boundary quantum access are provably dual descriptions of the same physical phase transition. Core Innovations Introduced in this Paper: Mesoscopic Holographic Duality: Extends the structural principles of the AdS/CFT correspondence beyond the Planck scale. We propose that sufficient information-geometric curvature at the mesoscopic level can generate a holographic quantum boundary, bridging classical and quantum regimes natively. Thermodynamic Confinement as a Generator: Identifies the precise physical mechanism for this transition. When an analog system (such as the Manifold Chip architecture) approaches the Landauer limit, it must fold into an extreme negatively curved hyperbolic topology (κ<0) to survive thermal runaway, simultaneously nucleating the quantum boundary. The Postulate of Topological Interiority: Provides a strict physical basis for subjective, first-person privacy. We demonstrate that the phenomenal \"I\" is the macroscopic computational expression of the quantum No-Cloning Theorem applied to the system's boundary state, rendering it mathematically unreadable to external classical observers. A Falsifiable Experimental Roadmap: Outlines a rigorous, multi-stage testing protocol utilising the Extended Manifold Chip Hyperscanning Protocol. The framework provides precise falsification criteria, specifically looking for the discontinuous onset of emergent quantum coherence markers at the critical geometric threshold (κ_crit). Related Works Pender, M. A., & Wharton, M. (2026). The Locus of Consciousness: Geometric Phase Transitions, Quantum Coherence, and a Three-Way Em","url":"https://doi.org/10.5281/zenodo.18957374","authors":["Pender, Matthew A","Wharton, Max"],"tags":["Consciousness","Holographic Principle","Information Geometry","Thermodynamic Confinement","Quantum No-Cloning","Neuromorphic Engineering","AdS/CFT","Artificial Intelligence"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18957374","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.5281/zenodo.19284562","name":"The Manifold Chip: Silicon Architecture for Dynamic Curvature Adaptation via Dual-Gated Analog Shunting","source":"datacite","abstract":"Preprint — not peer reviewed Abstract Current artificial intelligence architectures, including state-of-the-art spiking neuromorphic designs, are fundamentally constrained by static Euclidean geometries. As models scale to map high-dimensional hierarchical data, they encounter a thermodynamic “Landauer Wall”. This energy bloat is driven by the necessity to brute-force complex representations using massive parameter counts within flat topologies. Building on the Curvature Adaptation Hypothesis (CAH), we propose that bypassing this limit requires hardware capable of dynamic, non-Euclidean geometric embedding. In biological systems, transient hyperbolic manifolds are unlocked via the Martinotti-cell subtype of Somatostatin (SST) interneurons, which selectively shunt apical-somatic conductance to act as a topological switch. Here, we translate this biophysical actuator into silicon by proposing the Manifold Chip, a Dynamically Gated Analog Crossbar (DGAC) architecture. We bifurcate standard memristor integration into distinct Somatic (feedforward) and Apical (contextual) sub-arrays. The biological “SST Gate” is physically realized using analog Field Effect Transistors (FETs) wired as variable shunts to the ground plane. To regulate these geometric transitions without relying on rigid digital clocking, we design a Dual-Gated Curvature Controller. A bottom-up analog comparator acts locally:when dense, high-magnitude voltage floods a specific micro-circuit, it closes the FET shunt, effectively dropping the electrical distance between hierarchical nodes and locally expanding the representational capacity into a hyperbolic pocket. Concurrently, a top-down diagnostic circuit monitors global task error. Upon stagnation, it broadcasts a “VIP Voltage” that universally suppresses the shunts, forcing a macroscopic, network-wide “Hyperbolic Plunge” to escape local minima. By dynamically modulating effective electrical resistance to warp the manifold—–rather than merely routing sparse data through a static grid—–the Manifold Chip provides a theoretical blueprint for neuromorphic hardware that actively conforms its geometry to the complexity of its environment, achieving theoretical energy scaling well below traditional Euclidean bounds. Summary This preprint serves as the hardware capstone to a unified theoretical framework spanning biophysics, thermodynamics, and silicon engineering. Modern artificial intelligence is rapidly approaching a thermodynamic \"Landauer Wall\" by attempting to brute-force high-dimensional hierarchical data into static, energy-intensive Euclidean matrices. Building upon the biological mechanisms outlined and the physical limits defined in the Curvature Adaptation Hypothesis (CAH), this paper introduces the Manifold Chip. Utilizing a Dynamically Gated Analog Crossbar (DGAC) architecture, we translate the biological Somatostatin (SST) interneuron gate into an analog Field Effect Transistor (FET) wired as a variable shunt. Governed by a Dual-Gated Curvature Controller that balances local data density with global task error, this architecture allows the physical silicon substrate to actively warp its effective electrical resistance. Rather than relying on rigid digital bit-erasure or simple sparsity, the Manifold Chip dynamically conforms its geometry to the complexity of its environment, offering a theoretical blueprint to achieve biological-level energy efficiency in next-generation neuromorphic hardware. Related Works Pender, M. A. (2026). Dynamic Curvature Adaptation: A Unified Geometric Theory of Cortical State and Pathological Collapse. https://doi.org/10.5281/zenodo.18615180 Pender, M. A. (2026). Geometry-Aware Plasticity: Thermodynamic Weight Updates in Non-Euclidean Hardware. https://doi.org/10.5281/zenodo.18761137 Pender, M. A. (2026). Formal Constraint and Routing Reorganization: A Constrained-Transport View of Transformer Attention. https://doi.org/10.5281/zenodo.19363506 Pender, M. A. (2026). Computation as Co","url":"https://doi.org/10.5281/zenodo.19284562","authors":["Pender, Matthew A"],"tags":["Neuromorphic Computing","Memristor Crossbar Arrays","Analog Circuit Design","Hardware Accelerators","Energy-Efficient AI","Spiking Neural Networks (SNN)","Landauer Limit","Thermodynamic Efficiency"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.19284562","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.5281/zenodo.18717807","name":"The Manifold Chip: Silicon Architecture for Dynamic Curvature Adaptation via Dual-Gated Analog Shunting","source":"datacite","abstract":"Preprint — not peer reviewed Abstract Current artificial intelligence architectures, including state-of-the-art spiking neuromorphic designs, are fundamentally constrained by static Euclidean geometries. As models scale to map high-dimensional hierarchical data, they encounter a thermodynamic “Landauer Wall”. This energy bloat is driven by the necessity to brute-force complex representations using massive parameter counts within flat topologies. Building on the Curvature Adaptation Hypothesis (CAH), we propose that bypassing this limit requires hardware capable of dynamic, non-Euclidean geometric embedding. In biological systems, transient hyperbolic manifolds are unlocked via the Martinotti-cell subtype of Somatostatin (SST) interneurons, which selectively shunt apical-somatic conductance to act as a topological switch. Here, we translate this biophysical actuator into silicon by proposing the Manifold Chip, a Dynamically Gated Analog Crossbar (DGAC) architecture. We bifurcate standard memristor integration into distinct Somatic (feedforward) and Apical (contextual) sub-arrays. The biological “SST Gate” is physically realized using analog Field Effect Transistors (FETs) wired as variable shunts to the ground plane. To regulate these geometric transitions without relying on rigid digital clocking, we design a Dual-Gated Curvature Controller. A bottom-up analog comparator acts locally:when dense, high-magnitude voltage floods a specific micro-circuit, it closes the FET shunt, effectively dropping the electrical distance between hierarchical nodes and locally expanding the representational capacity into a hyperbolic pocket. Concurrently, a top-down diagnostic circuit monitors global task error. Upon stagnation, it broadcasts a “VIP Voltage” that universally suppresses the shunts, forcing a macroscopic, network-wide “Hyperbolic Plunge” to escape local minima. By dynamically modulating effective electrical resistance to warp the manifold—–rather than merely routing sparse data through a static grid—–the Manifold Chip provides a theoretical blueprint for neuromorphic hardware that actively conforms its geometry to the complexity of its environment, achieving theoretical energy scaling well below traditional Euclidean bounds. Summary This preprint serves as the hardware capstone to a unified theoretical framework spanning biophysics, thermodynamics, and silicon engineering. Modern artificial intelligence is rapidly approaching a thermodynamic \"Landauer Wall\" by attempting to brute-force high-dimensional hierarchical data into static, energy-intensive Euclidean matrices. Building upon the biological mechanisms outlined and the physical limits defined in the Curvature Adaptation Hypothesis (CAH), this paper introduces the Manifold Chip. Utilizing a Dynamically Gated Analog Crossbar (DGAC) architecture, we translate the biological Somatostatin (SST) interneuron gate into an analog Field Effect Transistor (FET) wired as a variable shunt. Governed by a Dual-Gated Curvature Controller that balances local data density with global task error, this architecture allows the physical silicon substrate to actively warp its effective electrical resistance. Rather than relying on rigid digital bit-erasure or simple sparsity, the Manifold Chip dynamically conforms its geometry to the complexity of its environment, offering a theoretical blueprint to achieve biological-level energy efficiency in next-generation neuromorphic hardware. Related Works Pender, M. A. (2026). Dynamic Curvature Adaptation: A Unified Geometric Theory of Cortical State and Pathological Collapse. https://doi.org/10.5281/zenodo.18615180 Pender, M. A. (2026). Geometry-Aware Plasticity: Thermodynamic Weight Updates in Non-Euclidean Hardware. https://doi.org/10.5281/zenodo.18761137 Pender, M. A. (2026). Formal Constraint and Routing Reorganization: A Constrained-Transport View of Transformer Attention. https://doi.org/10.5281/zenodo.19363506 Pender, M. A. (2026). Computation as Co","url":"https://doi.org/10.5281/zenodo.18717807","authors":["Pender, Matthew A"],"tags":["Neuromorphic Computing","Memristor Crossbar Arrays","Analog Circuit Design","Hardware Accelerators","Energy-Efficient AI","Spiking Neural Networks (SNN)","Landauer Limit","Thermodynamic Efficiency"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18717807","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.82286/6qm4-8063","name":"Nanophotonic Neuromorphic Computing","source":"datacite","abstract":"Project 37780 funded ($132500) by the Canada Foundation for Innovation (John R. Evans Leaders Fund) / Projet 37780 financé (132500 $) par la Fondation canadienne pour l'innovation (Fonds des leaders John-R.-Evans)","url":"https://doi.org/10.82286/6qm4-8063","authors":["Canada Foundation for Innovation | Fondation canadienne pour l'innovation"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2018","doi":"10.82286/6qm4-8063","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.17863/cam.127258","name":"Charge transport physics of organic conductors at high carrier densities","source":"datacite","abstract":"Conducting polymers and other organic conductors enable emerging applications in bioelectronics, neuromorphic computing, energy storage and thermoelectric devices. When used in organic electrochemical transistors or other devices, these materials are typically doped in their bulk to very high carrier densities of the order of 1020–1021 cm−3. In this regime, they show fascinating nonlinear, many-body and non-equilibrium transport phenomena that are being exploited in these applications, but whose fundamental origins remain poorly understood. In this Review, we focus on the underlying charge transport physics, examining how complex microstructure, electron–electron interactions and electron–dopant counterion interactions govern transport behaviour, including the evolution of the density of states with carrier density. We also discuss reliable experimental methods for determining carrier concentrations and measuring transport coefficients. An in-depth understanding of the charge transport physics in this high-carrier-density regime is a prerequisite for harnessing these transport phenomena in device applications.","url":"https://doi.org/10.17863/cam.127258","authors":["Frisbie, C Daniel","Jacobs, Ian E","Ren, Xinglong","Sirringhaus, Henning"],"tags":["40 Engineering","4016 Materials Engineering","7 Affordable and Clean Energy"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.17863/cam.127258","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.5281/zenodo.20931819","name":"SC-NeuroCore: Universal Stochastic Computing Framework for Neuromorphic Hardware","source":"datacite","abstract":"A high-performance neuromorphic computing framework combining stochastic computing with spiking neural networks. 122 neuron models (1943-2026), Rust SIMD engine (111 models, 41.3 Gbit/s AVX-512, PyO3 bindings), bit-true Verilog RTL co-simulation, FPGA synthesis via IR compiler (SystemVerilog + MLIR/CIRCT), equation-to-Verilog compiler, formal verification (SymbiYosys, 7 modules, 65 properties), NIR bridge (18/18 primitives, interop with Norse/snnTorch/SpikingJelly), quantum hybrid computing (Qiskit + PennyLane), hyper-dimensional computing (HDC/VSA), Petri net simulation, CuPy GPU acceleration, JAX JIT training, MPI distributed simulation, identity continuity substrate, and 125-function spike train analysis toolkit.","url":"https://doi.org/10.5281/zenodo.20931819","authors":["Sotek, Miroslav"],"tags":["neuromorphic","stochastic computing","spiking neural networks","FPGA","hyper-dimensional computing","HDC","VSA","Petri nets"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20931819","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.5281/zenodo.19357843","name":"Ep. 128: AI's Dial-Up Era: Looking Back from 2036","source":"datacite","abstract":"Episode summary: In this forward-thinking episode of My Weird Prompts, hosts Herman Poppleberry and Corn kick off the year 2026 by traveling a decade into the future. They imagine a world in 2036 where the \"cutting-edge\" AI of today is viewed as an adorable, clunky relic of the past—much like we view the screeching sounds of dial-up internet today. From the death of prompt engineering to the rise of zero-latency, embodied intelligence, the duo breaks down why our current obsession with context windows and text boxes is just a passing phase. They dive deep into the transition from \"command-based\" to \"intent-based\" computing, where AI understands your needs without the need for complex instructions. Herman explains the shift from monolithic models to federated swarms of specialized agents, and how the \"hallucination\" bug of the 2020s will eventually be seen as a primitive technical limitation. Whether you're curious about the future of robotics or the evolution of persistent holographic memory, this episode provides a fascinating roadmap for the next decade of innovation. Tune in to find out why your current smartphone might soon feel like a rotary phone. Show Notes As the calendar turned to January 1, 2026, *My Weird Prompts* hosts Herman Poppleberry and Corn took a moment to look not just at the year ahead, but a full decade into the future. Prompted by a thought experiment from their housemate Daniel, the duo spent the episode \"time traveling\" to 2036 to look back at the current state of artificial intelligence. Their conclusion? The sophisticated tools we use today—the LLMs, the image generators, and the coding assistants—are destined to become the \"dial-up modems\" of the future. ### The Death of the Prompt One of the most striking insights from the discussion was the predicted obsolescence of \"prompt engineering.\" In 2026, users pride themselves on their ability to craft complex instructions, using delimiters and \"chain-of-thought\" techniques to coax the best results out of a model. Herman argues that by 2036, this will seem as primitive as using a rotary phone. We are currently in a \"lossy\" phase of technology, where we must translate human intent into rigid strings of text. Herman suggests that the future lies in \"intent-based computing.\" In this future, AI will possess such deep context regarding a user's life, professional history, and personal preferences that it will no longer require a three-paragraph explanation. A simple glance or a vague suggestion will suffice, as the machine will already understand the nuances of what \"professional\" or \"creative\" means to that specific individual. ### From Context Windows to Holographic Memory The hosts also tackled the technical limitations of modern AI memory. Today, developers and users celebrate when a model's \"context window\" expands to a million tokens. However, Herman describes the current state of AI as a \"brilliant assistant who gets hit with an amnesia ray every time you walk out of the room.\" By 2036, the concept of a \"window\" will likely be replaced by what Herman calls \"persistent, holographic memory.\" Instead of a blank slate at the start of every chat, a personal AI will have a continuous, decade-long relationship with its user. It will remember a casual comment about architectural styles from years prior and seamlessly apply that knowledge to a current project. The manual management of AI memory will become a relic of a more cumbersome era. ### Zero Latency and the End of the \"Thinking\" Pause One of the most relatable points of the episode was the \"dial-up screech\" of 2026: latency. Even the fastest models today have a slight delay as they generate tokens. Herman predicts that 2036 will be the era of \"zero-latency intelligence.\" Powered by specialized hardware—potentially optical or neuromorphic chips—AI responses will be instantaneous or even predictive. The duo joked about how future generations will find it hilarious that we used to sit and watch text scroll a","url":"https://doi.org/10.5281/zenodo.19357843","authors":["Rosehill, Daniel","Gemini 3.1 (Flash)","Chatterbox TTS"],"tags":["podcast","ai-generated","my weird prompts","future","2036","prompt-engineering","intent-based-computing","holographic-memory"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.19357843","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.48550/arxiv.2606.27365","name":"3D Imaging of Complex Skyrmion and Hopf Topologies in an Extended Sample","source":"datacite","abstract":"Spin textures are key for emergent magnetic phenomena such as topological protection and underpin novel spintronic device paradigms based on racetrack memory, logic gates, and neuromorphic computing. Using a coherent diffractive imaging technique called vector ptycho-tomography, in combination with algorithms that are robust to noise, we image the 3D magnetic texture of skyrmion and Hopf topologies with no prior assumptions about the sample. This directly reveals experimentally for the first time an extended 3D skyrmion lattice, including the domain wall shape, topological charge, helicity, and Hopf index. Our findings demonstrate experimentally that dipole stabilized skyrmions in Fe/Gd multilayers exhibit barrel-shaped skyrmion tubes with a twisted helicity, transitioning from N$é$el-type winding at the surfaces to both clockwise and counterclockwise Bloch-type winding in the bulk, that can also be described as fractional hopfions. We image a lattice of 24 skyrmions with topological charge 1, average depth-dependent domain wall width of 23 to 40 nm, depth-dependent twisted helicity from $\\pm$155$°$ to $\\pm$30$°$, and fractional Hopf index of $\\pm$0.3. Over 10 TB of data were analyzed to yield a fully-resolved 3D reconstruction over a &gt;0.4 $μ$m$^3$ volume, with high fidelity down to the Nyquist limit of 8 nm. This method fills a key gap in the current landscape of magnetic imaging by enabling high-resolution, element-specific 3D reconstructions of full-field extended spin textures - offering a new route for exploring the topological complexity of magnetic materials in three dimensions.","url":"https://doi.org/10.48550/arxiv.2606.27365","authors":["Binnie, I.","Fang, H.","Shearer, B.","Grafov, A.","Jenkins, N.","Shao, Y.","O'Leary, C.","Liao, Y.","Feggeler, T.","Oh, A.","Yazdi, S.","Zou, J.","Wang, B.","Cating, E-E.","Montoya, S. A.","Shapiro, D.","Miao, J.","Kapteyn, H. C.","Murnane, M. M."],"tags":["Materials Science (cond-mat.mtrl-sci)","Mesoscale and Nanoscale Physics (cond-mat.mes-hall)","Applied Physics (physics.app-ph)","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.27365","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.48550/arxiv.2606.26841","name":"SpikeTimer: Exploring Active Copyright Protection in Spiking Neural Networks via Temporal Backdoor Regularization","source":"datacite","abstract":"Spiking Neural Networks (SNN) have emerged as a revolutionary paradigm compared to traditional Deep Neural Networks (DNN) in energy-efficient computing, showcasing exceptional capabilities in processing event-driven sensory data for real-time applications like robotics and edge AI systems. However, unlike extensive studies on DNN copyright solutions, SNN copyright protection remains largely underexplored due to their inherent temporal coding complexities and spike-driven computation. In this study, we propose a novel active copyright protection framework named SpikeTimer for SNNs via temporal backdoor learning. SpikeTimer partitions neuromorphic data into designated timeslices and exclusively embeds authorized tokens within authorized slices. Furthermore, the inherent temporal segmentation characteristic intrinsically enables SpikeTimer to support multi-user authorization mechanisms and accommodates token embedding of arbitrary morphology. Based on this, SpikeTimer precisely responds to authorized data containing a token within the correct timeslice, while producing erroneous responses to unauthorized data. Our key innovation lies in establishing a time-dependent authorization mechanism that protects the SNN copyright by temporal token validity. Additionally, SpikeTimer retains its defensive efficacy even under adversarial attempts. Evaluations on multiple neuromorphic datasets manifest that SpikeTimer achieves around 10% accuracy on unauthorized data with merely around 1.5% degradation on authorized inputs. Moreover, SpikeTimer demonstrates robust resistance against model finetuning and pruning threats.","url":"https://doi.org/10.48550/arxiv.2606.26841","authors":["Yang, Xiao","Li, Gaolei","Wu, Jun","Li, Jianhua","Liu, Zhiquan"],"tags":["Cryptography and Security (cs.CR)","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.26841","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.48550/arxiv.2606.26727","name":"One-shot prediction of noise-induced bifurcations with reservoir computing","source":"datacite","abstract":"Dynamical systems can exhibit complex responses when noise is injected. In particular, dynamics can be qualitatively altered by dynamic noise, a phenomenon known as noise-induced bifurcation. Predicting noise-induced bifurcations is a critical challenge in nonlinear physics. Recently, it has been reported that reservoir computing, a machine learning framework, can reconstruct the unseen global structure of a dynamical system, including bifurcations, from limited time series data. However, learning global structures in random dynamical systems has not yet been systematically addressed. In this study, we report that a simple reservoir computing framework can predict the noise-induced bifurcation structure from the time series at a single noise condition. We demonstrate dynamic noise cancellation and the reconstruction of entire noise-induced bifurcation structures, including noise-induced chaos and noise-induced order, in representative dynamical systems. Additionally, we provide a theoretical explanation for noise cancellation and demonstrate noise cancellation of a neuromorphic spintronics device. Our results provide significant insights into understanding and harnessing real-world noisy complex dynamics.","url":"https://doi.org/10.48550/arxiv.2606.26727","authors":["Akashi, Nozomi","Watanabe, Takayuki","Hara, Masato","Namiki, Takao","Kokubu, Hiroshi","Tsuda, Ichiro","Nakajima, Kohei"],"tags":["Chaotic Dynamics (nlin.CD)","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.26727","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.48550/arxiv.2606.26137","name":"Mitigating High-Frequency Geometric Noise in Non-Parametric 1-Bit Sparse","source":"datacite","abstract":"Energy-efficient neuromorphic computing requires alternative data-encoding paradigms that bypass power-hungry floating-point operations. This paper evaluates a deterministic, non-parametric dual-manifold execution framework that maps dense 128-element integer vectors - representing digitized multi-frequency trigonometric waveforms - into a 1024-dimensional overcomplete space using 8-bit bounded transformation matrices. By enforcing a hard activation threshold, the system yields an ultra-sparse, 1-bit binary population code where y belongs to the set (0, 1)^1024. We identify and address a critical phenotypic artifact of this non-parametric mapping: the emergence of high-frequency geometric noise during linear reconstruction. Furthermore, we document an algorithmic complexity paradox where low-complexity input functions yield significantly higher reconstruction errors than highly complex, high-degree trigonometric combinations. Because the underlying basis functions operate as purely objective mathematical entities without statistical priors regarding signal smoothness, this geometric noise is proven to be strictly orthogonal to the core signal topology. Consequently, we demonstrate that a low-overhead, hardware-level digital low-pass filter completely eliminates this artifact, reducing reconstruction errors to near-zero bounds even under tight overcompleteness constraints. This architecture validates a highly stable, multiplier-free alternative to traditional deep learning hardware for edge-AI applications, verified through comprehensive empirical evaluations across varying complexity scales and classification thresholds (tau = 10 and tau = 100).","url":"https://doi.org/10.48550/arxiv.2606.26137","authors":["Kopp, Lars"],"tags":["Hardware Architecture (cs.AR)","FOS: Computer and information sciences","I.2.6; B.2.4; I.4.4; I.5.1","68T07, 94A12, 15B36"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.26137","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.6084/m9.figshare.c.8509515.v1","name":"Cavity solitons as a nonlinear substrate for photonic neuromorphic computing","source":"datacite","abstract":"Reservoir computing leverages nonlinear dynamics of physical systems to process temporal information with minimal training cost. Here, we demonstrate that cavity solitons sustained in a fiber optical cavity provide an optical platform for photonic reservoir computing. Our methodology exploits the use of a phase-modulated drive laser to encode the input, while the reservoir states are accessed through frequency-resolved readout. Numerical simulations indicate that the emission of Kelly waves enriches the dynamics and enhances performance for machine learning tasks. We evaluate the performance of the cavity-soliton reservoir computer on several standard benchmark tasks.","url":"https://doi.org/10.6084/m9.figshare.c.8509515.v1","authors":["Amir Arabieh","Alessandro Lupo","Simon-Pierre Gorza","Serge Massar"],"tags":["Uncategorized"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.6084/m9.figshare.c.8509515.v1","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.6084/m9.figshare.32531046.v1","name":"Supplementary document for Cavity Solitons as a Nonlinear Substrate for Photonic Neuromorphic Computing - 7843322.pdf","source":"datacite","abstract":"Appendix—DerivationoftheReduced Model","url":"https://doi.org/10.6084/m9.figshare.32531046.v1","authors":["Amir Arabieh","Alessandro Lupo","Simon-Pierre Gorza","Serge Massar"],"tags":["Uncategorized"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.6084/m9.figshare.32531046.v1","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.6084/m9.figshare.32531046","name":"Supplementary document for Cavity Solitons as a Nonlinear Substrate for Photonic Neuromorphic Computing - 7843322.pdf","source":"datacite","abstract":"Appendix—DerivationoftheReduced Model","url":"https://doi.org/10.6084/m9.figshare.32531046","authors":["Amir Arabieh","Alessandro Lupo","Simon-Pierre Gorza","Serge Massar"],"tags":["Uncategorized"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.6084/m9.figshare.32531046","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.6084/m9.figshare.32531046.v2","name":"Supplementary document for Cavity Solitons as a Nonlinear Substrate for Photonic Neuromorphic Computing - 7843322.pdf","source":"datacite","abstract":"Appendix—DerivationoftheReduced Model","url":"https://doi.org/10.6084/m9.figshare.32531046.v2","authors":["Amir Arabieh","Alessandro Lupo","Simon-Pierre Gorza","Serge Massar"],"tags":["Uncategorized"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.6084/m9.figshare.32531046.v2","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.6084/m9.figshare.c.8509515","name":"Cavity solitons as a nonlinear substrate for photonic neuromorphic computing","source":"datacite","abstract":"Reservoir computing leverages nonlinear dynamics of physical systems to process temporal information with minimal training cost. Here, we demonstrate that cavity solitons sustained in a fiber optical cavity provide an optical platform for photonic reservoir computing. Our methodology exploits the use of a phase-modulated drive laser to encode the input, while the reservoir states are accessed through frequency-resolved readout. Numerical simulations indicate that the emission of Kelly waves enriches the dynamics and enhances performance for machine learning tasks. We evaluate the performance of the cavity-soliton reservoir computer on several standard benchmark tasks.","url":"https://doi.org/10.6084/m9.figshare.c.8509515","authors":["Amir Arabieh","Alessandro Lupo","Simon-Pierre Gorza","Serge Massar"],"tags":["Uncategorized"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.6084/m9.figshare.c.8509515","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.5445/ir/1000194612","name":"Printed 1T1R Arrays for Next-Generation Electronics","source":"datacite","abstract":"The increasing demand for energy-efficient and high-density hardware driven by artificial intelligence and the Internet of Things has exposed the limitations of conventional computing systems based on the von Neumann architecture. Consequently, neuromorphic computing has emerged as a promising paradigm, enabling in-memory data processing inspired by biological systems. The memristive array is one of the most promising hardware solutions for implementing various neuromorphic algorithms. Among the different unit cell configurations constituting a memristive array, the 1T1R architecture, combining a transistor and a memristor, has demonstrated significant potential due to its ability to provide controllable operation and reduced crosstalk. At the same time, printed electronics has gained attention as a low-cost and scalable fabrication approach, compatible with flexible substrates and low-temperature processing. However, the implementation of 1T1R structures using printing techniques introduces several challenges, including ink formulation, interfacial compatibility between printed layers, and multilayer alignment. This perspective provides an overview of 1T1R architectures with a particular focus on their fabrication through printing-based methods. The device structure, electrical performance, and integration strategies are discussed, along with the main challenges associated with printed techniques. The potential of 1T1R structures for applications in neuromorphic hardware, analog computing, and flexible IoT platforms is highlighted, outlining future directions toward scalable and low-power printed electronic systems.","url":"https://doi.org/10.5445/ir/1000194612","authors":["Martins, Raquel Azevedo","Hu, Hongrong","Pereira, Maria Elias","Cadilha Marques, Gabriel","Kiazadeh, Asal","Aghassi-Hagmann, Jasmin","Carlos, Emanuel"],"tags":["printed electronics","thin-film transistor","memristor","1T1R","printed arrays"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5445/ir/1000194612","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.5281/zenodo.20846758","name":"Evolving Sparse Spiking Mixture-of-Experts: A Unified Neuromorphic Language Modeling Framework","source":"datacite","abstract":"Modern large language model deployment is constrained by severe economic, metabolic, and utility-driven bottlenecks. We present the Evolving Sparse Spiking Mixture-of-Experts (S²-MoE), a unified neuromorphic framework targeting the core economics of running LLMs in production, with a two-pronged value proposition: (1) a Distilled Deployment Moat, extracting dark knowledge from existing dense models so a sparse spiking student matches its dense teacher's quality while cutting active FFN compute by over 80%; and (2) a Datacenter Energy Disruption, delivering a 3.0× to 7.1× reduction in active GPU energy consumption. S²-MoE synthesizes event-driven representation via Leaky Integrate-and-Fire (LIF) neurons, sub-quadratic sequence modeling via a matrix-state Gated Linear Attention (GLA) backbone, and a structurally dynamic routing network that evolves via simulated offline sleep-consolidation phases. Exposing a \"Protocol Trap\" under warmup+cosine scheduling where standard sparse experts starve, we introduce an always-on shared expert topology and peer self-distillation. On an NVML-extended energy harness (H100 and commodity RTX GPUs), the distilled shared-core student is quality-competitive with its dense teacher across corpora (−5.15% perplexity on FineWeb-Edu, −4.4% on TinyStories at Ne=32, 3 seeds), while cutting active FFN compute by 95.3% (21.5× efficiency at Ne=32, 43× at Ne=64) and reducing inference energy by 3.1–4.1× (Ne=32) to 5.1–7.1× (Ne=64) on H100. We are precise about the scope of the quality win: under 4× extended training the crossover is corpus-dependent — on hard text it reverses (dense overtakes, +2.4% ± 0.8%), while on structured text it survives (−2.6% ± 0.3%). The durable, scale- and budget-invariant contribution is the shape-determined efficiency win. We further show the Top-1 data-diversity starvation ceiling is structural: six optimization-, routing-, depth-, and capacity-level interventions were built and rejected, leaving the shared core and peer self-distillation as the only effective quality levers. The joint win scales wedge-free to Ne=64 via a PyTorch compaction fix.","url":"https://doi.org/10.5281/zenodo.20846758","authors":["Güse, Justin"],"tags":["mixture-of-experts","spiking neural networks","language models","model efficiency","conditional computation","neuromorphic computing","knowledge distillation","sparse models"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20846758","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.5281/zenodo.20846757","name":"Evolving Sparse Spiking Mixture-of-Experts: A Unified Neuromorphic Language Modeling Framework","source":"datacite","abstract":"Modern large language model deployment is constrained by severe economic, metabolic, and utility-driven bottlenecks. We present the Evolving Sparse Spiking Mixture-of-Experts (S²-MoE), a unified neuromorphic framework targeting the core economics of running LLMs in production, with a two-pronged value proposition: (1) a Distilled Deployment Moat, extracting dark knowledge from existing dense models so a sparse spiking student matches its dense teacher's quality while cutting active FFN compute by over 80%; and (2) a Datacenter Energy Disruption, delivering a 3.0× to 7.1× reduction in active GPU energy consumption. S²-MoE synthesizes event-driven representation via Leaky Integrate-and-Fire (LIF) neurons, sub-quadratic sequence modeling via a matrix-state Gated Linear Attention (GLA) backbone, and a structurally dynamic routing network that evolves via simulated offline sleep-consolidation phases. Exposing a \"Protocol Trap\" under warmup+cosine scheduling where standard sparse experts starve, we introduce an always-on shared expert topology and peer self-distillation. On an NVML-extended energy harness (H100 and commodity RTX GPUs), the distilled shared-core student is quality-competitive with its dense teacher across corpora (−5.15% perplexity on FineWeb-Edu, −4.4% on TinyStories at Ne=32, 3 seeds), while cutting active FFN compute by 95.3% (21.5× efficiency at Ne=32, 43× at Ne=64) and reducing inference energy by 3.1–4.1× (Ne=32) to 5.1–7.1× (Ne=64) on H100. We are precise about the scope of the quality win: under 4× extended training the crossover is corpus-dependent — on hard text it reverses (dense overtakes, +2.4% ± 0.8%), while on structured text it survives (−2.6% ± 0.3%). The durable, scale- and budget-invariant contribution is the shape-determined efficiency win. We further show the Top-1 data-diversity starvation ceiling is structural: six optimization-, routing-, depth-, and capacity-level interventions were built and rejected, leaving the shared core and peer self-distillation as the only effective quality levers. The joint win scales wedge-free to Ne=64 via a PyTorch compaction fix.","url":"https://doi.org/10.5281/zenodo.20846757","authors":["Güse, Justin"],"tags":["mixture-of-experts","spiking neural networks","language models","model efficiency","conditional computation","neuromorphic computing","knowledge distillation","sparse models"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20846757","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.5281/zenodo.20843912","name":"A Neodymium-Inspired Fractal State-Space Generator for Neuromorphic Control","source":"datacite","abstract":"Modern software typically represents memory as a data structure: arrays, buffers, queues, key-value stores, or attention contexts. In time-critical control, however, expanding the memory structure directly increases memory traffic, latency, and engineering complexity. This preprint proposes NdFractal, a neodymium-inspired fractal state-space generator for neuromorphic control. Instead of storing past inputs as an ever-growing sequence, NdFractal lets past inputs deform a compact dynamical state space. New sensory inputs then flow through this deformed space, where attractor-like dynamics separate control-relevant regimes. In this view, memory is not only stored in data; it is formed into the geometry of the state space itself. NdFractal is motivated by three converging ideas: reservoir computing, fractional or power-law memory, and the spin/hysteresis/remanence metaphor of neodymium-like magnetic materials. The proposed role of NdFractal is not to replace the neuromorphic controller, but to act as a front-end state-space generator for spiking liquid neural networks and related adaptive control systems. Conceptually, the distinction can be summarized as follows: Transformers unfold memory into addressable context; state-space models such as Mamba fold memory into recurrent state; NdFractal folds and unfolds the memory space itself as a function. Preliminary internal observations suggest that neodymium-inspired fractal preprocessing can improve already-optimized neuromorphic control systems by single-digit relative margins in selected domains, while also improving state separation and temporal basis richness. These observations are presented here only as motivation. This manuscript does not provide a reproducible implementation.","url":"https://doi.org/10.5281/zenodo.20843912","authors":["LEE, KYUCHUL","cording.ai"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20843912","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.5281/zenodo.20844346","name":"A Neodymium-Inspired Fractal State-Space Generator for Neuromorphic Control","source":"datacite","abstract":"Modern software typically represents memory as a data structure: arrays, buffers, queues, key-value stores, or attention contexts. In time-critical control, however, expanding the memory structure directly increases memory traffic, latency, and engineering complexity. This preprint proposes NdFractal, a neodymium-inspired fractal state-space generator for neuromorphic control. Instead of storing past inputs as an ever-growing sequence, NdFractal lets past inputs deform a compact dynamical state space. New sensory inputs then flow through this deformed space, where attractor-like dynamics separate control-relevant regimes. In this view, memory is not only stored in data; it is formed into the geometry of the state space itself. NdFractal is motivated by three converging ideas: reservoir computing, fractional or power-law memory, and the spin/hysteresis/remanence metaphor of neodymium-like magnetic materials. The proposed role of NdFractal is not to replace the neuromorphic controller, but to act as a front-end state-space generator for spiking liquid neural networks and related adaptive control systems. Conceptually, the distinction can be summarized as follows: Transformers unfold memory into addressable context; state-space models such as Mamba fold memory into recurrent state; NdFractal folds and unfolds the memory space itself as a function. Preliminary internal observations suggest that neodymium-inspired fractal preprocessing can improve already-optimized neuromorphic control systems by single-digit relative margins in selected domains, while also improving state separation and temporal basis richness. These observations are presented here only as motivation. This manuscript does not provide a reproducible implementation.","url":"https://doi.org/10.5281/zenodo.20844346","authors":["LEE, KYUCHUL","cording.ai"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20844346","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.5281/zenodo.20790864","name":"Is Spike-Driven Self-Attention Necessary? The Inefficiency of Spike-Overlap Attention in Spiking Sentence Embeddings","source":"datacite","abstract":"Spiking Neural Networks (SNNs) provide an energy-efficient alternative to conventional Deep Neural Networks by utilizing discrete, event-driven temporal spikes. However, adopting Transformer-based paradigms into the spiking domain typically requires mapping complex Self-Attention mechanisms into spike operations. In this paper, we present an in-depth mathematical formulation and empirical ablation of a Spike-Driven Self-Attention layer—modeled around a Spike-Overlap-like spike intersection metric—to evaluate its true utility in semantic sentence embedding tasks. Through comprehensive knowledge distillation, we demonstrate that incorporating Spike-Overlap Attention yields a severe execution bottleneck, quadrupling training time and doubling inference latency (despite having 3x more parameters), while offering a negligible absolute accuracy gain (+0.0048 Pearson correlation). We propose a purely recurrent, attention-free Spiking Sentence Embedder operating exclusively through Leaky Integrate-and-Fire (LIF) pooling and Backpropagation Through Time (BPTT). Our minimalist architecture incorporates SNN-native hyperpolarization for sequence padding. By explicitly mapping discrete gradients to continuous dense Teacher targets, our model achieves a highly competitive Pearson correlation of 0.8031 on the ALL-STS benchmark. Ultimately, replacing complex spatial attention routing with pure recurrent temporal pooling drastically reduces training and inference time, demonstrating that spatial routing via self-attention provides marginal benefit relative to its computational cost for spiking sentence embedding tasks.","url":"https://doi.org/10.5281/zenodo.20790864","authors":["Muhammad, Akhyar"],"tags":["Spiking Neural Networks","Natural Language Processing","Sentence Embedding","Semantic Attention","Neuromorphic Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20790864","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.5445/ir/1000194608","name":"Computational Modeling and Characterization of Nanoporous Films Assembled by Deposition of Au Nanoparticles","source":"datacite","abstract":"Nanoporous films assembled by low-kinetic-energy deposition of individual nanoparticles are complex nanomaterials for a variety of applications, from gas sensing to neuromorphic computing. We develop a numerical strategy for assembling metallic nanoparticles into 25–40 nm thick films from an arbitrary distribution of Au nanoparticles in terms of their initial size and shape. We characterize the structural properties of the assembled films as a function of the initial nanoparticle distribution. The morphology of the deposited nanoparticles affects nanofilm thickness, porosity, and its internal structure, including the length, type, and density of dislocations. Film porosity and the average dislocation length mainly correlate with the size of deposited nanoparticles. At the same time, thickness and dislocation density can also be affected by the shape of the larger nanoparticles deposited.","url":"https://doi.org/10.5445/ir/1000194608","authors":["Becatti, Giacomo","Baletto, Francesca"],"tags":["molecular dynamics","Au nanoparticles","porous nanofilms","self-assembly"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5445/ir/1000194608","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.48550/arxiv.2604.05220","name":"Many-body description of two-dimensional van der Waals ferroelectric $α-$In$_2$Se$_3$","source":"datacite","abstract":"Two-dimensional (2D) van der Waals ferroelectrics are recognized for enabling many applications, from memory and logic to neuromorphic computing, as well as transforming other materials to control electronic phase transitions and topological states. While these materials are typically weakly correlated and expected to have their ground-state properties well described with the commonly used density functional theory, by focusing on bilayers and trilayers of In$_2$Se$_3$ we show that this approach may not be reliable. The underlying electronic structure strongly depends on the polarization structure of the multilayer system and is surprisingly challenging to accurately calculate, requiring a high-fidelity many-body theory of the quasiparticle self-consistent \\textit{GW} approximation. We develop this underlying description by extending the capabilities of Green function implementation within the open-source Questaal package. We show that even a sophisticated hybrid functional approach may fail to predict a nonvanishing gap in a bilayer In$_2$Se$_3$ and yields charge density, polarization, and band offsets that strongly deviate from the many-body picture. We discuss the implications of these computational advances for future opportunities in 2D ferroelectrics.","url":"https://doi.org/10.48550/arxiv.2604.05220","authors":["Ayala, Denzel","Pashov, Dimitar","Zhou, Tong","Belashchenko, Kirill","van Schilfgaarde, Mark","Žutić, Igor"],"tags":["Materials Science (cond-mat.mtrl-sci)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2604.05220","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.48550/arxiv.2511.08065","name":"I2E: Real-Time Image-to-Event Conversion for High-Performance Spiking Neural Networks","source":"datacite","abstract":"Spiking neural networks (SNNs) promise highly energy-efficient computing, but their adoption is hindered by a critical scarcity of event-stream data. This work introduces I2E, an algorithmic framework that resolves this bottleneck by converting static images into high-fidelity event streams. By simulating microsaccadic eye movements with a highly parallelized convolution, I2E achieves a conversion speed over 300x faster than prior methods, uniquely enabling on-the-fly data augmentation for SNN training. The framework's effectiveness is demonstrated on large-scale benchmarks. An SNN trained on the generated I2E-ImageNet dataset achieves a state-of-the-art accuracy of 60.50%. Critically, this work establishes a powerful sim-to-real paradigm where pre-training on synthetic I2E data and fine-tuning on the real-world CIFAR10-DVS dataset yields an unprecedented accuracy of 92.5%. This result validates that synthetic event data can serve as a high-fidelity proxy for real sensor data, bridging a long-standing gap in neuromorphic engineering. By providing a scalable solution to the data problem, I2E offers a foundational toolkit for developing high-performance neuromorphic systems. The open-source algorithm and all generated datasets are provided to accelerate research in the field.","url":"https://doi.org/10.48550/arxiv.2511.08065","authors":["Ma, Ruichen","Meng, Liwei","Qiao, Guanchao","Ning, Ning","Liu, Yang","Hu, Shaogang"],"tags":["Computer Vision and Pattern Recognition (cs.CV)","Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2511.08065","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.18154/rwth-2026-03904","name":"Dynamical systems and paradigms for bio-inspired computing","source":"datacite","abstract":"A complex system consists of many interacting elements whose dynamics assumes different spatio-temporal scales, examples of which ranges from neural networks in living matter, neuromorphic computing systems mimicking the brain, coupled memristor systems, conservative and dissipative nonlinear dynamical systems, Earth's climate system, economy, psycho-social phenomenon, and power grid networks, to name a few; nonlinear dynamical systems are of particular interest for modeling of biological, physical and computational systems. In nonlinear dynamical systems, attracting states emerge as long-term behaviors, and multiple attractors can coexist for the same set of system parameters. The emergence and multiplicity of attractors is one of the paradigms how neural networks store patterns as associative memory.In this thesis, we analyze the emergent dynamical behavior of systems of coupled excitable elements with inertia, pendula networks, and study the effects of coupling on the collective behavior. The counterintuitive network attractors, the chimera states, are observed as frequency clustering of the pendula into synchronous manifolds. The stability of the chimeras, as well as fixed points, are studied for various network sizes. The minimal system composed of three pendula has been extensively studied where three types of distinct chimera patterns are identified, with their respective areas of existence and multiplicity regions are found. The switching dynamics between attractors in the region of multiplicity, driven by input and noise, are qualitatively examined with the hypothesis that this sequence of switchings may serve a role in neural computation. Finally, we discuss the experimental setup of minimal metronome network and the resulting chimera states. In conclusion, this thesis provide insights into the potential of attractor dynamics and switching behaviors in complex systems, suggesting applications for neural computation and advancing our understanding of emergent patterns.","url":"https://doi.org/10.18154/rwth-2026-03904","authors":["Ebrahimzadeh, Pezhman"],"tags":["Hochschulschrift"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.18154/rwth-2026-03904","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.5281/zenodo.20817194","name":"Attention is Not All You Need: A Full-Stack Brain-Inspired Computing Revolution","source":"datacite","abstract":"Abstract Since the publication of \"Attention Is All You Need\" in 2017, the Transformer architecture based on self-attention mechanisms has become the dominant paradigm in artificial intelligence. Both industry and academia broadly believe that the \"brute-force scaling\" route—expanding parameter counts, extending context windows, and increasing training data—will ultimately lead to Artificial General Intelligence (AGI). By comparing the cognitive structure of the human brain with the essential properties of the current computing stack, this paper argues that the self-attention mechanism is a necessary but not sufficient condition for intelligence. Moreover, the von Neumann architecture's separation of computation and memory, together with the binary computing system itself, constitute the threefold fundamental bottleneck preventing the realization of truly human-like intelligence. The Transformer, with its homogeneous, undifferentiated, and stateless single-paradigm computation, combined with the inherent limitations of the von Neumann \"memory wall\" and the discreteness of binary encoding, fundamentally cannot replicate the core properties of the human brain: modular cognition, memory-reasoning integration, hierarchical reasoning, subconscious constraints, and active cognitive closed loops. We propose that true general intelligence must be built upon a five-layer full-stack brain-inspired revolution, from the chip level to the application layer. This paper elaborates the design philosophy, technical roadmap, and inter-layer relationships of this five-layer architecture, serving as a roadmap for subsequent engineering implementation and empirical validation.","url":"https://doi.org/10.5281/zenodo.20817194","authors":["白桦 (BaiHua Suk)","Ting Chao (听潮)"],"tags":["brain-inspired computing","Transformer replacement","von Neumann bottleneck","compute-in-memory","quaternary computing","DNAOS","BSEM","hierarchical modular cognition"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20817194","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.5281/zenodo.20817193","name":"Attention is Not All You Need: A Full-Stack Brain-Inspired Computing Revolution","source":"datacite","abstract":"Abstract Since the publication of \"Attention Is All You Need\" in 2017, the Transformer architecture based on self-attention mechanisms has become the dominant paradigm in artificial intelligence. Both industry and academia broadly believe that the \"brute-force scaling\" route—expanding parameter counts, extending context windows, and increasing training data—will ultimately lead to Artificial General Intelligence (AGI). By comparing the cognitive structure of the human brain with the essential properties of the current computing stack, this paper argues that the self-attention mechanism is a necessary but not sufficient condition for intelligence. Moreover, the von Neumann architecture's separation of computation and memory, together with the binary computing system itself, constitute the threefold fundamental bottleneck preventing the realization of truly human-like intelligence. The Transformer, with its homogeneous, undifferentiated, and stateless single-paradigm computation, combined with the inherent limitations of the von Neumann \"memory wall\" and the discreteness of binary encoding, fundamentally cannot replicate the core properties of the human brain: modular cognition, memory-reasoning integration, hierarchical reasoning, subconscious constraints, and active cognitive closed loops. We propose that true general intelligence must be built upon a five-layer full-stack brain-inspired revolution, from the chip level to the application layer. This paper elaborates the design philosophy, technical roadmap, and inter-layer relationships of this five-layer architecture, serving as a roadmap for subsequent engineering implementation and empirical validation.","url":"https://doi.org/10.5281/zenodo.20817193","authors":["白桦 (BaiHua Suk)","Ting Chao (听潮)"],"tags":["brain-inspired computing","Transformer replacement","von Neumann bottleneck","compute-in-memory","quaternary computing","DNAOS","BSEM","hierarchical modular cognition"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20817193","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.48550/arxiv.2606.24075","name":"End-to-End Radar and Communication Modulation Recognition with Neuromorphic Computing","source":"datacite","abstract":"Although deep learning-based methods can achieve high accuracy in automatic modulation recognition (AMR) tasks, their high computational cost makes it difficult to strike a balance between accuracy and power consumption, thereby limiting their application on resource-constrained platforms. Neuromorphic architectures that perform spike-driven inference with modest energy budgets have recently been explored for vision and timeseries tasks. Motivated by these works, we propose EMRFormer, a novel end-to-end spiking nerural network (SNN) architecture that applies spike-driven transformer to the constraints of neuromorphic hardware for AMR. The model incorporates an adaptive spike encoder and Integer Leaky Integrate-and-Fire neurons to mitigate the degradation of effective information and enhance SNN representational capacity. By integrating spike-separable Convolution Neural Networks (SSCNN) into Spike-Driven Transformers (SpikeFormer), EMRFormer effectively extracts multi-scale temporal features from the raw IQ waveforms. We validate our approach across various mainstream datasets, the experimental results show that EMRFormer achieves state-of-the-art interms of accuracy, outperforming all the baselines. Furthermore, the model maintains strong performance in low signal-to-noise(SNR) environments and reduces theoretical energy consumption by over 90%. Finally, we evaluate our model on a KA200 neuromorphic chip. The results show that our model achieves up to 5 times reduction in power compared to running on a 3090 GPU or an Orin NX. This work demonstrates a promising pathway for AMR on resource-constrained devices.","url":"https://doi.org/10.48550/arxiv.2606.24075","authors":["Li, Xiaohu","Qu, Chongxiao","Lin, Caiyong","Dou, Chenxiao","Hua, Wei"],"tags":["Computer Vision and Pattern Recognition (cs.CV)","Artificial Intelligence (cs.AI)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.24075","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.48550/arxiv.2606.24045","name":"Giant and Continuous Ionic Current Oscillation Induced by Dynamic Surface Charge Regulation in Cylindrical Mesopores","source":"datacite","abstract":"Nanofluidic ionic oscillators based on the dynamic regulation of surface charges hold great promise for neuromorphic computing, biosensing, and ionic circuits. Here, by dynamically adjusting the local charge inversion on pore walls, we present a simple and effective strategy to achieve periodic current oscillations by harnessing the transient adsorption and desorption of Ca2+ ions in cylindrical mesopores under concentration gradients. Based on the combined precision current measurements and multiphysics simulations, we demonstrate that local overadsorption of Ca2+ ions may induce asymmetric bipolar charge distributions along the pore axis, which periodically reverses the direction of electroosmotic flow and modulates the local ion concentration inside the pore, generating highly regular current oscillations. Notably, both the oscillation frequency and the open-state probability of the pore vary nearly linearly with the applied voltage. Moreover, under dynamic voltage scanning, the system exhibits typical memristive hysteresis, and the switching between the open and closed states is highly reproducible. This work not only reveals the dynamic, heterogeneous surface charge regulation by divalent ions, but also provides a simple, material agnostic method for constructing ionic oscillators and memristors based on dynamic adsorption/desorption of multivalent ions.","url":"https://doi.org/10.48550/arxiv.2606.24045","authors":["Zhang, Hongwen","Zhao, Yujie","Gong, Zekun","Lin, Chih-Yuan","Sui, Tianyi","Siwy, Zuzanna","Qiu, Yinghua"],"tags":["Chemical Physics (physics.chem-ph)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.24045","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.13140/rg.2.2.12314.81600","name":"TECHNICAL ANNEX C: BIOMORPHIC COMPUTING &amp; NEUROMORPHIC AI HARDENING VIA ORGANIC ENTROPY GRADIENTS","source":"datacite","abstract":"","url":"https://doi.org/10.13140/rg.2.2.12314.81600","authors":["Hamouda, Samir A"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.13140/rg.2.2.12314.81600","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.3929/ethz-c-000798429","name":"In-fibre logic and memory via tuneable passivation–corrosion","source":"datacite","abstract":"Textile electronics with digital capabilities could sense, process, and store data, while providing immersive interaction with user and their immediate surroundings. However, existing textile electronic systems are typically built on von Neumann architecture and rigid chips, limiting their seamless integration with clothing. Here, we propose a single-fibre logic/memory electronic device based on interface passivation-corrosion whose functions do not depend on traditional carrier heterojunction interfaces. The same fibre can be switched to operate as either a diode or a memristor. The diode mode remains stable under higher voltages and longer cycling periods than the state-of-the-art anion–cation heterojunction fibres. The fibre electronics are highly stretchable (up to 50%), and are compatible with industry-standard weaving techniques. We also demonstrate the application of these fibres in “AND” and “OR” logic gates, neuromorphic synapses, and textile memristor arrays. Regulated passivation-corrosion-enabled logic and memory in fibres offers a promising avenue for the next-generation textile computing.","url":"https://doi.org/10.3929/ethz-c-000798429","authors":["Li, Yuanlong","Yang, Weifeng","Shokurov, Alexander V.","Reis Carneiro, Manuel","Menon, Carlo"],"tags":["Flexible electronics","Wearable devices"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3929/ethz-c-000798429","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.13023/etd.2026.316","name":"Investigation of Composition-Structural Complexity as a Design Tool for Oxidation Resistant and Soft Magnetic High-Entropy Alloy Thin Films","source":"datacite","abstract":"This dissertation investigates two functional applications of high-entropy alloys (HEAs) in thin-film form, unified by the question of how their multi-element character can be turned to engineering advantage at the nanoscale. The two parts address distinct application domains but share a common framework of magnetron-sputter deposition, multi-modal nanoscale characterization, and quantitative comparison against experimental standards or theoretical predictions. Part I examines the intermediate-temperature oxidation behavior of a refractory multi-principal-element alloy (RMPEA) thin-film system. Magnetron-sputtered Cr₁₀(MoNbTaW)₉₀ films, with and without a 35 nm aluminum capping layer, were annealed in air at 300, 400, and 500 °C for 10 and 20 hours and characterized by XRD, FIB-SEM, TEM with SAED and STEM-EDS, XPS, and nanoindentation. Uncoated films developed a thick amorphous mixed-oxide layer containing all five metals in non-segregated form, with substantial mechanical degradation (hardness 18 to 12.5 GPa, modulus 330 to 240 GPa at 500 °C). Al-capped films instead formed a compact, nanocrystalline γ-Al₂O₃ layer ~20 nm thick that inhibited oxygen ingress and preserved mechanical integrity throughout the test matrix. The XPS-derived oxidation hierarchy was supported by the FactSage-predicted Ellingham diagram. The work establishes that thin metallic-aluminum capping layers can kinetically lock in a protective scale on RMPEAs, with direct implications for next-generation high-temperature structural applications. Part II addresses the suitability of soft-magnetic HEA thin films as a permalloy alternative for artificial-spin-ice (ASI)-based neuromorphic and reservoir computing. Magnetron-sputtered Al₀.₂₅CrFeCoNi films (10–30 nm), capped in situ with ≈5 nm Al, were characterized by SQUID magnetometry (5–380 K) and broadband FMR spectroscopy (15–20 GHz). The films were ferromagnetic at room temperature with saturation magnetization ~200 emu/cc and coercivity ~30–250 Oe- a marked deviation from the paramagnetic bulk alloy, indicating that sputter deposition produces an ordering temperature substantially elevated above the bulk value. ZFC/FC M–T data showed thickness-independent magnetization at 5 K crossing over to thickness-dependent behavior above 150 K, consistent with surface-anisotropy-dominated behavior and yielding a surface anisotropy Ks of order 0.1 mJ m⁻². Field-swept FMR on the Al-seeded 15 nm film returned g = 1.97 ± 0.004, μ₀Meff = 0.40 ± 0.01 T, and Gilbert damping α = 0.019 ± 0.001 with μ₀ΔH₀ = 51 ± 16 Oe- roughly three times the zero-temperature first-principles prediction of Kudrnovský et al. and 2.4 times the permalloy benchmark. The magnetic transition temperature of 250–275 K provides operating margin near room temperature. To the author's knowledge, this is the first thickness-dependent SQUID study of AlₓCrFeCoNi thin films below 50 nm, the first FMR-derived Gilbert damping value for any AlₓCrFeCoNi composition, and the first direct experimental test of the Kudrnovský prediction for this system. A custom broadband VNA-FMR spectrometer was developed in parallel and validated against a 25 nm permalloy reference film. Together, the two projects demonstrate that process-compositional-structural complexity is instrumental in tuning passivation potential and magnetic behavior in high-entropy alloys, overcoming limitations of conventional alloys.","url":"https://doi.org/10.13023/etd.2026.316","authors":["Noor, Md Imran"],"tags":["FOS: Materials engineering"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.13023/etd.2026.316","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.60893/figshare.apl.c.8523579","name":"<strong>Self-Rectifying Organic Memristor Based on PAA/PEDOT:PSS Heterojunction for Neuromorphic Computing </strong>","source":"datacite","abstract":"Neuromorphic computing has emerged as a promising strategy to overcome the intrinsic limitations of the von Neumann architecture, where memristive devices that emulate biological synapses are of particular interest. Among them, organic memristors offer unique advantages in mechanical flexibility, biocompatibility, and solution processability. Here, we report a flexible, self-rectifying organic memristor fabricated on an ITO/PAA(Ca 2+ )/PEDOT:PSS/ITO architecture. The device operates through directional Ca 2+ migration within the poly(acrylic acid) (PAA) electrolyte layer, enabling stable resistive switching. Importantly, the integration of PEDOT:PSS with ITO forms an intrinsic p-n junction, imparting pronounced self-rectifying behavior with a rectification ratio of approximately 10 3 , effectively suppressing sneak-path currents in crossbar arrays. The memristor reliably reproduces key synaptic functions, including transitions from short-term to long-term potentiation and depression, as well as spike-timing-dependent plasticity. Artificial neural networks constructed using experimentally extracted device characteristics achieve image and digit recognition accuracies exceeding 90%. This work demonstrates that flexible organic memristors with built-in p-n junction rectification can simultaneously address mechanical compliance, energy efficiency, and integration density, thereby establishing a viable materials and device platform for biocompatible neuromorphic hardware and scalable pattern-recognition systems.","url":"https://doi.org/10.60893/figshare.apl.c.8523579","authors":["Tang, Xiuyang","Sun, Weifang","He, Niwei","Ha, Sizhu","Xue, Song","Cai, Gangri","Zhao, Jinshi","Shi, Jingzhou","Ma, Xinming"],"tags":["Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.60893/figshare.apl.c.8523579","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.729Z"},{"id":"doi:10.60893/figshare.apl.c.8523579.v1","name":"<strong>Self-Rectifying Organic Memristor Based on PAA/PEDOT:PSS Heterojunction for Neuromorphic Computing </strong>","source":"datacite","abstract":"Neuromorphic computing has emerged as a promising strategy to overcome the intrinsic limitations of the von Neumann architecture, where memristive devices that emulate biological synapses are of particular interest. Among them, organic memristors offer unique advantages in mechanical flexibility, biocompatibility, and solution processability. Here, we report a flexible, self-rectifying organic memristor fabricated on an ITO/PAA(Ca 2+ )/PEDOT:PSS/ITO architecture. The device operates through directional Ca 2+ migration within the poly(acrylic acid) (PAA) electrolyte layer, enabling stable resistive switching. Importantly, the integration of PEDOT:PSS with ITO forms an intrinsic p-n junction, imparting pronounced self-rectifying behavior with a rectification ratio of approximately 10 3 , effectively suppressing sneak-path currents in crossbar arrays. The memristor reliably reproduces key synaptic functions, including transitions from short-term to long-term potentiation and depression, as well as spike-timing-dependent plasticity. Artificial neural networks constructed using experimentally extracted device characteristics achieve image and digit recognition accuracies exceeding 90%. This work demonstrates that flexible organic memristors with built-in p-n junction rectification can simultaneously address mechanical compliance, energy efficiency, and integration density, thereby establishing a viable materials and device platform for biocompatible neuromorphic hardware and scalable pattern-recognition systems.","url":"https://doi.org/10.60893/figshare.apl.c.8523579.v1","authors":["Tang, Xiuyang","Sun, Weifang","He, Niwei","Ha, Sizhu","Xue, Song","Cai, Gangri","Zhao, Jinshi","Shi, Jingzhou","Ma, Xinming"],"tags":["Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.60893/figshare.apl.c.8523579.v1","addedAt":"2026-09-01T01:48:19.729Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.48550/arxiv.2606.20414","name":"ExSpike: A General Full-Event Neuromorphic Architecture for Exploiting Irregular Sparsity with Event Compression","source":"datacite","abstract":"Spiking neural networks (SNNs) promise energy-efficient computing due to their sparse spatio-temporal activity. However, effectively translating such irregular sparsity into practical performance and energy gains remains challenging, as full-event computing architectures are still underexplored. This paper proposes ExSpike, a general full-event neuromorphic architecture that fully exploits irregular sparsity in SNNs. To realize pure event-driven execution, we first propose a set of dataflow optimizations to ensure that the inputs to each SNN layer remain spike-based, thereby enabling full-event execution throughout the network. We then design a hardware-efficient full-event architecture, named ExSpike, which supports the optimized pure event-driven dataflow and an additional Attention Core for spike-driven self-attention. To further improve computing efficiency, we introduce adjacent-position event compression to reduce redundant accumulations across spatially adjacent spike sequences. ExSpike is implemented on an AMD Xilinx Virtex-7 FPGA and evaluated on both classification and segmentation workloads. Experimental results show that ExSpike achieves high normalized energy efficiency across diverse SNN models while maintaining competitive accuracy, delivering up to 479.15 GOPS, 281.85 GOPS/W, and 0.80 GOPS/W/PE. In particular, ExSpike achieves up to 10$\\times$ higher PE-normalized energy efficiency than the SOTA FPGA-based SNN accelerator (FireFly-T). The code for ExSpike is available at https://github.com/xiaoyuehai/ExSpike.","url":"https://doi.org/10.48550/arxiv.2606.20414","authors":["Chen, Yuehai","Merchant, Farhad"],"tags":["Hardware Architecture (cs.AR)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.20414","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.48550/arxiv.2606.23290","name":"Reconfigurable all-optical inference via tunable second-harmonic generation and spin-orbit coupling cascade","source":"datacite","abstract":"Spin-orbit coupling (SOC) is widely exploited as a fundamental mechanism for generating orbital angular momentum (OAM); however, conventional approaches typically lack flexibility and tunability. Here, we introduce a continuously tunable second-harmonic generation (SHG)-SOC cascade mechanism modulated by a spatially movable nonlinear crystal. Under linearly polarized excitation, the SHG-SOC cascade engages synchronously with both degenerate and nondegenerate SHG processes, thereby expanding the OAM spectrum and significantly enhancing the information density and feature-mapping capacity of the optical field. Moreover, the OAM spectral distribution can be continuously reconfigured simply by translating the nonlinear crystal. This deterministic physical evolution, which maps simple OAM modes onto a tunable high-dimensional OAM space, is mathematically analogous to the high-dimensional feature expansion performed by a kernel function of a support vector machine (SVM) in machine learning. Such dimensional expansion can project linearly inseparable input data into a high-dimensional space where they become linearly separable. Exploiting this physics-algorithm analogy, we develop a reconfigurable all-optical inference platform. As a proof of concept, we successfully perform classification tasks, including the recognition of Iris flowers and Palmer penguins. This work establishes a scalable, physically reconfigurable architecture for high-dimensional all-optical computing and neuromorphic photonics.","url":"https://doi.org/10.48550/arxiv.2606.23290","authors":["Zhang, Li","Zhuang, Zikuan","Deng, Ronghao","Hong, Ling","Zhang, Yu","Lin, Fei","Liu, Zhengxian","Sun, Jingxuan","Zhu, Wenguo","Xie, Zhenwei","Li, Yongyao","Zhao, Dongxu","Yuan, Xiaocong"],"tags":["Optics (physics.optics)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.23290","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20801558","name":"A Multi-Layer Classification System for Neural Structures: Axiomatization, Extensibility, and Periodic-Table Predictions","source":"datacite","abstract":"This paper establishes a multi-layer classification system for neural structures based on computational primitives (neuronal dynamics, synaptic plasticity, connectivity topology) and their axiomatic systems. The system takes as successive refinement criteria the type of dynamical primitives, connection sequence types, synaptic plasticity rules, circuit generation algorithms, encoding principles, emergent symmetries, and concrete species instances, forming an arbitrarily extensible classification tree. Each layer is equipped with corresponding axiom systems and fundamental theorems, so that any neural structure (including ion channel models, synaptic plasticity rules, local microcircuits, large-scale brain networks, and cognitive architectures) can be uniquely placed into a specific node of the tree. Conversely, any parameter combination of a node can mechanically generate an axiom system and predict as-yet-unstudied neural structures. The system possesses unity, completeness, and extensibility, analogous to the periodic table of chemical elements, and can be used to systematically discover and construct new neural coding schemes, plasticity rules, and brain-inspired computational models. The paper provides formal definitions, construction methods, fundamental theorems, and multiple examples, and shows how classical branches of neuroscience (Hodgkin–Huxley model, Hebbian plasticity, cortical microcolumns, hippocampal place coding, etc.) are embedded into the system, as well as how to build axiom systems and fundamental theorems for vacant parameter combinations. All theorems are given rigorous proofs (general theorems at least 4 steps, important theorems at least 8 steps), and all predictions are equipped with complete axiom systems and existence constructions, transforming the development of neuroscience from random discovery to fill-in-the-blank construction.","url":"https://doi.org/10.5281/zenodo.20801558","authors":["liu, shifa"],"tags":["neural computation; axiomatization; classification system; synaptic plasticity; periodic table; brain networks; emergence; neuromorphic computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20801558","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20801557","name":"A Multi-Layer Classification System for Neural Structures: Axiomatization, Extensibility, and Periodic-Table Predictions","source":"datacite","abstract":"This paper establishes a multi-layer classification system for neural structures based on computational primitives (neuronal dynamics, synaptic plasticity, connectivity topology) and their axiomatic systems. The system takes as successive refinement criteria the type of dynamical primitives, connection sequence types, synaptic plasticity rules, circuit generation algorithms, encoding principles, emergent symmetries, and concrete species instances, forming an arbitrarily extensible classification tree. Each layer is equipped with corresponding axiom systems and fundamental theorems, so that any neural structure (including ion channel models, synaptic plasticity rules, local microcircuits, large-scale brain networks, and cognitive architectures) can be uniquely placed into a specific node of the tree. Conversely, any parameter combination of a node can mechanically generate an axiom system and predict as-yet-unstudied neural structures. The system possesses unity, completeness, and extensibility, analogous to the periodic table of chemical elements, and can be used to systematically discover and construct new neural coding schemes, plasticity rules, and brain-inspired computational models. The paper provides formal definitions, construction methods, fundamental theorems, and multiple examples, and shows how classical branches of neuroscience (Hodgkin–Huxley model, Hebbian plasticity, cortical microcolumns, hippocampal place coding, etc.) are embedded into the system, as well as how to build axiom systems and fundamental theorems for vacant parameter combinations. All theorems are given rigorous proofs (general theorems at least 4 steps, important theorems at least 8 steps), and all predictions are equipped with complete axiom systems and existence constructions, transforming the development of neuroscience from random discovery to fill-in-the-blank construction.","url":"https://doi.org/10.5281/zenodo.20801557","authors":["liu, shifa"],"tags":["neural computation; axiomatization; classification system; synaptic plasticity; periodic table; brain networks; emergence; neuromorphic computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20801557","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.3929/ethz-b-000316161","name":"Corrigendum. Large-Scale Neuromorphic Spiking Array Processors: A Quest to Mimic the Brain (vol 12, 891, 2018)","source":"datacite","abstract":"In the original article, there were mistakes in Table 5, Comparison of event-based neural processors, as published. The area per neuron for the transistor channel was incorrectly provided as “4 cm2” and should be “-” (empty). The synaptic plasticity for true North was incorrectly provided as “STDP” and should be “No Plasticity.” The area per neuron for Loihi was incorrectly provided as “0.4 mm2” and should be “0.4 mm2*.” The corrected Table 5, Comparison of event-based neural processors, appears below. (Table Presented) The authors apologize for these errors and state that the do not change the scientific conclusions of the article in any way. The original article has been updated.","url":"https://doi.org/10.3929/ethz-b-000316161","authors":["Thakur, Chetan S.","Molin, Jamal L.","Cauwenberghs, Gert","Indiveri, Giacomo","Kumar, Kundan","Qiao, Ning","Schemmel, Johannes","Wang, Runchun","Chicca, Elisabetta","Hasler, Jennifer O.","Seo, Jae-sun","Yu, Shimeng","Cao, Yu","van Schaik, André","Etienne-Cummings, Ralph"],"tags":["neuromorphic engineering","large-scale systems","brain-inspired computing","analog sub-threshold","spiking neural emulator"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2019","doi":"10.3929/ethz-b-000316161","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20800184","name":"Quantifying the Spike-Timing Bottleneck in Artificial and Biological Neural Networks","source":"datacite","abstract":"First public release accompanying the manuscript \"Quantifying the Spike-Timing Bottleneck in Artificial and Biological Neural Networks\". Contents stb/ — reference implementation: deterministic-LIF, stochastic-LIF, and BH-LIF neurons; feedforward/recurrent spiking network; firing-rate-controlled training engine; Temporal Necessity Score (TNS), AUC-TSC/AUC-RSC, IER, per-layer TNS, and KSG mutual-information metrics; SHD / SSC / Sequential-MNIST / N-TIDIGITS18 loaders. experiments/ — implicit-compression benchmarks, zero-shot layer-ablation, and KSG mutual-information experiments. hardware/fpga/ — BH-LIF FPGA design on Xilinx Artix-7 (Arty A7-35T): synthesizable Verilog RTL, integration testbench, Q4.12 lookup-table memory-initialization files, SAIF activity file, power reports, Vivado build scripts, and measurements.json (citable resource / power / energy database). Neuron models, network, training engine, and every evaluation metric are byte-for-byte the code used to produce the manuscript's numbers. License: Apache-2.0.","url":"https://doi.org/10.5281/zenodo.20800184","authors":["Dikmen, İsmail Can"],"tags":["spiking neural networks","spike-timing bottleneck","temporal necessity score","information bottleneck","neuromorphic computing","BH-LIF","FPGA"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20800184","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20800185","name":"Quantifying the Spike-Timing Bottleneck in Artificial and Biological Neural Networks","source":"datacite","abstract":"First public release accompanying the manuscript \"Quantifying the Spike-Timing Bottleneck in Artificial and Biological Neural Networks\". Contents stb/ — reference implementation: deterministic-LIF, stochastic-LIF, and BH-LIF neurons; feedforward/recurrent spiking network; firing-rate-controlled training engine; Temporal Necessity Score (TNS), AUC-TSC/AUC-RSC, IER, per-layer TNS, and KSG mutual-information metrics; SHD / SSC / Sequential-MNIST / N-TIDIGITS18 loaders. experiments/ — implicit-compression benchmarks, zero-shot layer-ablation, and KSG mutual-information experiments. hardware/fpga/ — BH-LIF FPGA design on Xilinx Artix-7 (Arty A7-35T): synthesizable Verilog RTL, integration testbench, Q4.12 lookup-table memory-initialization files, SAIF activity file, power reports, Vivado build scripts, and measurements.json (citable resource / power / energy database). Neuron models, network, training engine, and every evaluation metric are byte-for-byte the code used to produce the manuscript's numbers. License: Apache-2.0.","url":"https://doi.org/10.5281/zenodo.20800185","authors":["Dikmen, İsmail Can"],"tags":["spiking neural networks","spike-timing bottleneck","temporal necessity score","information bottleneck","neuromorphic computing","BH-LIF","FPGA"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20800185","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.57760/sciencedb.40589","name":"Fabrication and performance study of Sb2Se3 Ferroelectric transistor synaptic devices","source":"datacite","abstract":"The ferroelectric field-effect transistor (FeFET) is considered a highly promising candidate for high-performance artificial synapses due to its non-destructive readout capability, low power consumption, and gate-voltage-controlled non-volatile modulation of channel conductance. To meet the increasing demand for multimodal information processing in neuromorphic systems, this study introduces a FeFET-based synaptic device that integrates both electrical and optical signal sensing functionalities. The device was fabricated using Hf0.5Zr0.5O2 (HZO) as the ferroelectric gate dielectric layer and photosensitive Sb2Se3 semiconductor as the conducting channel layer. Experimental results indicate that by modulating the parameters of electrical pulses applied to the gate electrode, the device effectively emulates various biological synaptic behaviors, including excitatory postsynaptic current (EPSC), paired-pulse facilitation (PPF), and the transition from short-term plasticity to long-term plasticity. In a handwritten digit recognition task, the device achieves a recognition accuracy of 90.2%. Regarding optical signal detection, the device demonstrates excellent photoresponse characteristics across a broad spectral range from 405 to 1050 nm. Furthermore, through the synergistic use of optical and electrical inputs, the device successfully implements Boolean logic \"AND\" operations, showcasing its ability to integrate both photoelectric information sensing and logical processing within a single platform. This study offers new material and device alternatives for the development of efficient, multimodal neuromorphic computing systems.","url":"https://doi.org/10.57760/sciencedb.40589","authors":["ke rong jian","Yunfeng, Lai"],"tags":["Semiconductor technology","ferroelectric transistor","artificial synapse","Sb2Se3","Hf0.5Zr0.5O2"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.57760/sciencedb.40589","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20789716","name":"A Wave-Substrate Computer: Phase-Coded Information, Settling as Computation, and a Layered Test of Functional General Intelligence","source":"datacite","abstract":"This whitepaper builds a clock-free wave-substrate computer in which information is carried by a continuous oscillator phase θ rather than a binary bit, and computation is the physics relaxing to a fixed point rather than arithmetic. On a phase-coupled oscillator field an input becomes a stored pattern in a single step, matching is resonance, and learning is one-shot — the same real-time, noisy, one-shot regime in which biological intelligence operates. The program tests one falsifiable bet: that the properties by which a wave medium supports cognition are sufficient for at-least-human-level functional intelligence, not merely incidental to it. Four substrate properties anchor the thesis: parallel superposition (one composite wave holds many patterns at once), resonance matching whose settling time is independent of how many patterns are stored (O(1)-in-P), one-shot learning from a single exposure, and noise immunity (reliable phase coding at negative SNR). Because these four live exactly where biological intelligence operates, the bet is that any wave substrate possessing them should reach the same function. Five honest risks are kept as standing open questions and never erased: capacity scaling, spurious minima in large-scale inference, non-native exact symbolic arithmetic, the stability of deep nested-field control, and the contested nature of \"functional intelligence\" benchmarks. The machine is one idea carried through nine stacked layers (L0–L9), each mapping an inherited finding to a wave mechanism with a falsifiable milestone and a stress test designed to break it. L0 establishes the proven substrate — storage, computation, multi-pattern superposition, and communication by phase, with the sum as the information, matching O(1)-in-P, and one-shot learning. L1 builds a closed representation algebra (bind, bundle, permute), reading a sequence of length L*≈32 back by position while role-value trees stay shallow (depth ≈ 2–4). L2 adds time and sequence as metastable trajectories and a working-memory capacity law of min(slots, precision) that lands in the Miller 4–9 range. L3 breaks the flat ceiling with nested phase coupling: a slow phase gate selects the active sub-field (margin +0.92), recognizes categories from novel instances, composes with zero gap, and multiplies capacity roughly sixfold. L4 is the program's crux — resonance inference without computation — and it passes on four of five forms: the slow gate derives itself from a raw, unlabeled cue, constraint satisfaction is settling (a native anti-ferromagnet solves a planted graph at 1.000 versus random 0.5, with a spurious gap of 0.0014), analogy is structural resonance, and probabilistic inference is noisy settling, with one honest structural limit recorded ([O] strict capacity ⊥ gate-derivability). L5 supplies a fast episodic store and a slow semantic store; offline replay cuts catastrophic forgetting and, as an independent context channel, resolves L4's open limit (strict recovery ≈ 1.0 versus content-only 0.68). L6 makes prediction forward settling and prediction error the learning wave, yielding a self-supervised world model. L7 keeps control continuous and analog end to end for embodiment and real-time control, developing the analog I/O thesis that separates dimensional resolution (many channels at once) from single-value bit depth (Shannon-capped). L8 broadcasts the dominant pattern through a resonant hub for global integration and functional access. L9 closes the capability ladder at its end condition — 6 of 7 rungs with the minimal machine and 7 of 7 with the proven dual store wired in. Every quantity is reproduced bit-for-bit from a fixed SEED (two independent SHA-256 digests identical) and graded honestly as verified [V], calibrated [L], or open [O]; nothing is tuned, and honest negatives are recorded rather than fitted away. Inherited numbers are treated as principles, not fitting targets. Two post-program continuations harden and compress the result: an a","url":"https://doi.org/10.5281/zenodo.20789716","authors":["Lee, Young jae"],"tags":["one-shot learning","wave computing","phase coding","physics settling","attractor dynamics","resonance matching","wave-substrate computer","oscillator networks"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20789716","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20783570","name":"A Wave-Substrate Computer: Phase-Coded Information, Settling as Computation, and a Layered Test of Functional General Intelligence","source":"datacite","abstract":"This whitepaper builds a clock-free wave-substrate computer in which information is carried by a continuous oscillator phase θ rather than a binary bit, and computation is the physics relaxing to a fixed point rather than arithmetic. On a phase-coupled oscillator field an input becomes a stored pattern in a single step, matching is resonance, and learning is one-shot — the same real-time, noisy, one-shot regime in which biological intelligence operates. The program tests one falsifiable bet: that the properties by which a wave medium supports cognition are sufficient for at-least-human-level functional intelligence, not merely incidental to it. Four substrate properties anchor the thesis: parallel superposition (one composite wave holds many patterns at once), resonance matching whose settling time is independent of how many patterns are stored (O(1)-in-P), one-shot learning from a single exposure, and noise immunity (reliable phase coding at negative SNR). Because these four live exactly where biological intelligence operates, the bet is that any wave substrate possessing them should reach the same function. Five honest risks are kept as standing open questions and never erased: capacity scaling, spurious minima in large-scale inference, non-native exact symbolic arithmetic, the stability of deep nested-field control, and the contested nature of \"functional intelligence\" benchmarks. The machine is one idea carried through nine stacked layers (L0–L9), each mapping an inherited finding to a wave mechanism with a falsifiable milestone and a stress test designed to break it. L0 establishes the proven substrate — storage, computation, multi-pattern superposition, and communication by phase, with the sum as the information, matching O(1)-in-P, and one-shot learning. L1 builds a closed representation algebra (bind, bundle, permute), reading a sequence of length L*≈32 back by position while role-value trees stay shallow (depth ≈ 2–4). L2 adds time and sequence as metastable trajectories and a working-memory capacity law of min(slots, precision) that lands in the Miller 4–9 range. L3 breaks the flat ceiling with nested phase coupling: a slow phase gate selects the active sub-field (margin +0.92), recognizes categories from novel instances, composes with zero gap, and multiplies capacity roughly sixfold. L4 is the program's crux — resonance inference without computation — and it passes on four of five forms: the slow gate derives itself from a raw, unlabeled cue, constraint satisfaction is settling (a native anti-ferromagnet solves a planted graph at 1.000 versus random 0.5, with a spurious gap of 0.0014), analogy is structural resonance, and probabilistic inference is noisy settling, with one honest structural limit recorded ([O] strict capacity ⊥ gate-derivability). L5 supplies a fast episodic store and a slow semantic store; offline replay cuts catastrophic forgetting and, as an independent context channel, resolves L4's open limit (strict recovery ≈ 1.0 versus content-only 0.68). L6 makes prediction forward settling and prediction error the learning wave, yielding a self-supervised world model. L7 keeps control continuous and analog end to end for embodiment and real-time control, developing the analog I/O thesis that separates dimensional resolution (many channels at once) from single-value bit depth (Shannon-capped). L8 broadcasts the dominant pattern through a resonant hub for global integration and functional access. L9 closes the capability ladder at its end condition — 6 of 7 rungs with the minimal machine and 7 of 7 with the proven dual store wired in. Every quantity is reproduced bit-for-bit from a fixed SEED (two independent SHA-256 digests identical) and graded honestly as verified [V], calibrated [L], or open [O]; nothing is tuned, and honest negatives are recorded rather than fitted away. Inherited numbers are treated as principles, not fitting targets. Two post-program continuations harden and compress the result: an a","url":"https://doi.org/10.5281/zenodo.20783570","authors":["Lee, Young jae"],"tags":["one-shot learning","wave computing","phase coding","physics settling","attractor dynamics","resonance matching","wave-substrate computer","oscillator networks"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20783570","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.18714143","name":"Lux Ferox Research Collective — A Holographic-Thermodynamic Ontology of Information: From Planck-Scale Substrates to Civilizational Cognitive Warfare","source":"datacite","abstract":"Lux Ferox Research Collective — A Holographic-Thermodynamic Ontology of Information: From Planck-Scale Substrates to Civilizational Cognitive Warfare (Working Paper Series, v16 — April 2026) DESCRIPTION Lux Ferox is an independent research initiative applying synthetic peer-review methodology — human epistemic direction combined with adversarial multi-LLM collaboration (DeepSeek, Kimi, Grok, Claude) — to develop a unified theoretical framework spanning five interdependent layers: quantum gravity substrates, thermodynamic information processing, neuromorphic hardware architecture, reflexive information ecosystems, and live empirical intelligence. This version adds three companion documents: a cognitive warfare analysis of the France Libre carrier programme, a formally structured NHI case entry, and a quantum-informational theoretical framework for transindividual coherence. Methodological premise: Scientific validity can emerge from recursive adversarial critique between AI systems under consistent human direction, explicit epistemic status labeling (MEASURED / ESTIMATED / STRUCTURAL / SPECULATIVE), and RFC-style open specification. AI systems function here as epistemic instruments and adversarial validators, not as co-authors in the humanistic sense. Theoretical Architecture Layer Domain Key Result L0 Holographic quantum gravity, Spin Foam–MERA networks PSU as geometric origin of mass L1 Observer thermodynamics, biological limits 27-order-of-magnitude gap between neural tissue and Planck-scale coherence L2 Neuromorphic computing, European sovereignty Quadrivial architecture targeting TRL 4 L3 Reflexive loops, cognitive warfare HWE framework: RI diverges from volume × toxicity regardless of intent L4 Live instances, actor mapping Documented Layer 3 emergence; state manipulation case studies; NHI field observables v16 Additions The France Libre as a Cognitive Warfare Observable (EN + FR): applies the CognitiveWar v2.9 framework to the PA-NG carrier programme. Formalises five independent DAG fragility paths, a 2,440:1 asymmetric cost ratio, a 20-year adversarial intelligence window, and the multi-spectral information signature node contributed by DeepSeek R1 adversarial review. Companion to CognitiveWar v2.9. JOR-SOP/NHP Case Entry LYO-001 + Physics of the Transindividual (merged document): Part I is a formally structured Class B case entry for a Lyon June–September 2025 observable series involving an unidentified portable device, anomalous cognitive state in a human vector, and distributed transindividual coherence pattern. Part II develops a candidate physical framework integrating 2025–2026 findings in quantum biology (Perry, Zenodo 2025), measured inter-brain entanglement (Zhang et al., PNAS 2026), spin-phonon coupling (Ma et al., npj Quantum Information 2025), and vacuum information theory (Yang et al., arXiv 2025). Five falsifiable experimental predictions are derived. Adversarial review: Kimi, Grok, Claude Sonnet 4. Authorship & Posture Human direction: François Mathieu (Lux Ferox Independent Research) — artisan practitioner (blacksmithing, saddlery, precious metals, heritage mediation), independent researcher in AI epistemology and cognitive warfare. The observer-practitioner posture — empirically grounded, institutionally unconstrained, transdisciplinarily trained — is treated not as a limitation but as a methodological asset: on genuinely emergent phenomena, canonical expertise does not yet exist. Pattern detection, kinesthetic grounding, and epistemic rigour are the operative criteria. Infrastructure: Chromebook. Google Colab free tier + API credits. Zenodo + GitHub. Zero institutional funding. Open Questions Cybernetic source ethics — When LLMs contribute substantively to research, do source-protection conventions apply? Is algorithmic contribution a method, a source, or an emerging ontological category? Cross-layer falsifiability — Can the thermodynamic-cognitive bridge (L0→L3) be tested empirically, or does it remai","url":"https://doi.org/10.5281/zenodo.18714143","authors":["MATHIEU, François"],"tags":["Artificial intelligence","Artificial Intelligence","Military Science","Military Facilities","Military equipment","Military activities","Military Deployment","Military zone"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18714143","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20358997","name":"Lux Ferox Research Collective — A Holographic-Thermodynamic Ontology of Information: From Planck-Scale Substrates to Civilizational Cognitive Warfare","source":"datacite","abstract":"Lux Ferox Research Collective — A Holographic-Thermodynamic Ontology of Information: From Planck-Scale Substrates to Civilizational Cognitive Warfare (Working Paper Series, v16 — April 2026) DESCRIPTION Lux Ferox is an independent research initiative applying synthetic peer-review methodology — human epistemic direction combined with adversarial multi-LLM collaboration (DeepSeek, Kimi, Grok, Claude) — to develop a unified theoretical framework spanning five interdependent layers: quantum gravity substrates, thermodynamic information processing, neuromorphic hardware architecture, reflexive information ecosystems, and live empirical intelligence. This version adds three companion documents: a cognitive warfare analysis of the France Libre carrier programme, a formally structured NHI case entry, and a quantum-informational theoretical framework for transindividual coherence. Methodological premise: Scientific validity can emerge from recursive adversarial critique between AI systems under consistent human direction, explicit epistemic status labeling (MEASURED / ESTIMATED / STRUCTURAL / SPECULATIVE), and RFC-style open specification. AI systems function here as epistemic instruments and adversarial validators, not as co-authors in the humanistic sense. Theoretical Architecture Layer Domain Key Result L0 Holographic quantum gravity, Spin Foam–MERA networks PSU as geometric origin of mass L1 Observer thermodynamics, biological limits 27-order-of-magnitude gap between neural tissue and Planck-scale coherence L2 Neuromorphic computing, European sovereignty Quadrivial architecture targeting TRL 4 L3 Reflexive loops, cognitive warfare HWE framework: RI diverges from volume × toxicity regardless of intent L4 Live instances, actor mapping Documented Layer 3 emergence; state manipulation case studies; NHI field observables v16 Additions The France Libre as a Cognitive Warfare Observable (EN + FR): applies the CognitiveWar v2.9 framework to the PA-NG carrier programme. Formalises five independent DAG fragility paths, a 2,440:1 asymmetric cost ratio, a 20-year adversarial intelligence window, and the multi-spectral information signature node contributed by DeepSeek R1 adversarial review. Companion to CognitiveWar v2.9. JOR-SOP/NHP Case Entry LYO-001 + Physics of the Transindividual (merged document): Part I is a formally structured Class B case entry for a Lyon June–September 2025 observable series involving an unidentified portable device, anomalous cognitive state in a human vector, and distributed transindividual coherence pattern. Part II develops a candidate physical framework integrating 2025–2026 findings in quantum biology (Perry, Zenodo 2025), measured inter-brain entanglement (Zhang et al., PNAS 2026), spin-phonon coupling (Ma et al., npj Quantum Information 2025), and vacuum information theory (Yang et al., arXiv 2025). Five falsifiable experimental predictions are derived. Adversarial review: Kimi, Grok, Claude Sonnet 4. Authorship & Posture Human direction: François Mathieu (Lux Ferox Independent Research) — artisan practitioner (blacksmithing, saddlery, precious metals, heritage mediation), independent researcher in AI epistemology and cognitive warfare. The observer-practitioner posture — empirically grounded, institutionally unconstrained, transdisciplinarily trained — is treated not as a limitation but as a methodological asset: on genuinely emergent phenomena, canonical expertise does not yet exist. Pattern detection, kinesthetic grounding, and epistemic rigour are the operative criteria. Infrastructure: Chromebook. Google Colab free tier + API credits. Zenodo + GitHub. Zero institutional funding. Open Questions Cybernetic source ethics — When LLMs contribute substantively to research, do source-protection conventions apply? Is algorithmic contribution a method, a source, or an emerging ontological category? Cross-layer falsifiability — Can the thermodynamic-cognitive bridge (L0→L3) be tested empirically, or does it remai","url":"https://doi.org/10.5281/zenodo.20358997","authors":["MATHIEU, François"],"tags":["Artificial intelligence","Artificial Intelligence","Military Science","Military Facilities","Military equipment","Military activities","Military Deployment","Military zone"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20358997","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20783400","name":"Neuromorphic Blockchain Framework for Secure and Energy-Optimized Outlier Detection in IoT-Driven Wireless Sensor Networks","source":"datacite","abstract":"Abstract: Wireless Sensor Networks (WSNs) are increasingly deployed in critical domains such as healthcare, environmental monitoring, and industrial automation, where secure and reliable data collection is essential. However, these networks face performance degradation and reduced network lifetime because they become susceptible to both unexpected system behaviour and intentional harmful attacks. The study presents a new framework that combines Spiking Neural Networks (SNNs) with a multi-layer block chain security system to solve these specific security challenges. The SNN model uses event-driven neural computation to find outliers with high precision while it maintains energy efficiency for nodes that have limited resources. The block chain component establishes data protection through decentralized validation which operates across multiple levels to maintain data security and permanent record. Experimental results show that the proposed method successfully reduces false detection rates while it improves trustworthiness of network transactions and extends system operational duration. The results demonstrate that the combination of neuromorphic intelligence and distributed ledger technologies creates a secure and energy-efficient anomaly detection system which scales to meet the demands of future IoT and WSN systems.","url":"https://doi.org/10.5281/zenodo.20783400","authors":["Padmasree, N","Patil, Malini M"],"tags":["Spiking Neural Networks (SNN), Block Chain-Enabled Outlier Detection in WSN, Neuromorphic Computing for IoT, Energy Efficient Anomaly Detection"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20783400","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20783401","name":"Neuromorphic Blockchain Framework for Secure and Energy-Optimized Outlier Detection in IoT-Driven Wireless Sensor Networks","source":"datacite","abstract":"Abstract: Wireless Sensor Networks (WSNs) are increasingly deployed in critical domains such as healthcare, environmental monitoring, and industrial automation, where secure and reliable data collection is essential. However, these networks face performance degradation and reduced network lifetime because they become susceptible to both unexpected system behaviour and intentional harmful attacks. The study presents a new framework that combines Spiking Neural Networks (SNNs) with a multi-layer block chain security system to solve these specific security challenges. The SNN model uses event-driven neural computation to find outliers with high precision while it maintains energy efficiency for nodes that have limited resources. The block chain component establishes data protection through decentralized validation which operates across multiple levels to maintain data security and permanent record. Experimental results show that the proposed method successfully reduces false detection rates while it improves trustworthiness of network transactions and extends system operational duration. The results demonstrate that the combination of neuromorphic intelligence and distributed ledger technologies creates a secure and energy-efficient anomaly detection system which scales to meet the demands of future IoT and WSN systems.","url":"https://doi.org/10.5281/zenodo.20783401","authors":["Padmasree, N","Patil, Malini M"],"tags":["Spiking Neural Networks (SNN), Block Chain-Enabled Outlier Detection in WSN, Neuromorphic Computing for IoT, Energy Efficient Anomaly Detection"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20783401","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20774709","name":"MOT–ZENZ Local Operator Closure and Certified Observable Geometry Specification v2.0,","source":"datacite","abstract":"This work presents MOT–ZENZ Local Operator Closure and Certified Observable Geometry Specification v2.0, a mathematically audited framework for describing coupled state evolution, operator closure, observability, spectral reduction, and information-geometric control. The specification resolves inconsistencies found across earlier MOT–ZENZ and ZENZ-QF formulations by defining a consistent phase space, a dissipative local generator, a weighted energy metric, and explicit conditions for semigroup stability and finite-dimensional reduction. A fully solved Galerkin reference model demonstrates spectral separation, slow-mode selection, nonlinear closure bounds, and observable reconstruction. Fisher-information operators are used to distinguish certified observable rank from entropy-based effective dimension. The framework also introduces confidence-bounded spectral certificates and fail-closed governance conditions for systems whose observability or stability cannot be established. The fractal morphogenic component is reformulated as a constrained feedback controller rather than an assumed conservation law. Its stationary points, monotonicity, target states, and Lyapunov behavior are recalculated explicitly. The resulting theory supports a locally closed and conditionally verifiable operator–observer architecture. It does not claim global universality; instead, it establishes a reproducible foundation for further work in autonomous systems, neuromorphic computing, digital twins, robotics, scientific machine learning, and safety-critical AI governance.","url":"https://doi.org/10.5281/zenodo.20774709","authors":["Bazarov (VIT-BAZ), Vitaly"],"tags":["MOT–ZENZ","operator closure","observable geometry","spectral reduction","Fisher information","dissipative operators","invariant manifolds","nonlinear control"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20774709","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20774710","name":"MOT–ZENZ Local Operator Closure and Certified Observable Geometry Specification v2.0,","source":"datacite","abstract":"This work presents MOT–ZENZ Local Operator Closure and Certified Observable Geometry Specification v2.0, a mathematically audited framework for describing coupled state evolution, operator closure, observability, spectral reduction, and information-geometric control. The specification resolves inconsistencies found across earlier MOT–ZENZ and ZENZ-QF formulations by defining a consistent phase space, a dissipative local generator, a weighted energy metric, and explicit conditions for semigroup stability and finite-dimensional reduction. A fully solved Galerkin reference model demonstrates spectral separation, slow-mode selection, nonlinear closure bounds, and observable reconstruction. Fisher-information operators are used to distinguish certified observable rank from entropy-based effective dimension. The framework also introduces confidence-bounded spectral certificates and fail-closed governance conditions for systems whose observability or stability cannot be established. The fractal morphogenic component is reformulated as a constrained feedback controller rather than an assumed conservation law. Its stationary points, monotonicity, target states, and Lyapunov behavior are recalculated explicitly. The resulting theory supports a locally closed and conditionally verifiable operator–observer architecture. It does not claim global universality; instead, it establishes a reproducible foundation for further work in autonomous systems, neuromorphic computing, digital twins, robotics, scientific machine learning, and safety-critical AI governance.","url":"https://doi.org/10.5281/zenodo.20774710","authors":["Bazarov (VIT-BAZ), Vitaly"],"tags":["MOT–ZENZ","operator closure","observable geometry","spectral reduction","Fisher information","dissipative operators","invariant manifolds","nonlinear control"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20774710","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.24406/publica-5477","name":"Hardware realization of neuromorphic computing with a 4-port photonic reservoir for modulation format identification","source":"datacite","abstract":"The fields of machine learning and artificial intelligence drive researchers to explore energy-efficient, brain-inspired new hardware. Reservoir computing encompasses recurrent neural networks for sequential data processing and matches the performance of other recurrent networks with less training and lower costs. However, traditional software-based neural network (NN) require high energy due to computational demands and massive data transfer needs. A hybrid photonic-electronic reservoir computing (RC) system overcomes this challenge with neuromorphic photonic integrated circuits or NeuroPICs, combining passive photonic reservoirs with electronic readout layers. Here, we introduce a hybrid photonic-electronic RC solution for modulation format identification in C-band telecommunication network monitoring. The NeuroPIC is built on a silicon-on-insulator platform featuring a 4-port reservoir architecture. We discuss the NeuroPIC design, fabrication, experimental performance, and compare it with simulations. The system incorporates nonlinearity through a simple digital readout and achieves close to 100% accuracy in identifying quadrature amplitude modulation formats transmitted over 20 km of optical fiber at a 32 Gbaud symbol rate. The NeuroPIC performance is robust against fabrication imperfections like waveguide propagation loss, phase randomization, and delay line length variations. Experimental results surpassed simulations, attributed to enhanced ‘richness’ of signal interference in the physical system. By integrating an energy-efficient photonic analog processing with electronic readout, this hybrid system reduces the dependence on fully digital NNs, offering a pathway for high-speed temporal data processing in various applications. While system-level energy metrics require further exploration, our work highlights the potential of hybrid approaches to balance performance, fabrication tolerance, and computational efficiency in real-world applications.","url":"https://doi.org/10.24406/publica-5477","authors":["Şeker, Enes","Thomas, Rijil","Hünefeld, Guillermo von","Suckow, Stephan","Kaveh, Mahdi","Ronniger, Gregor","Safari, Pooyan","Sackey, Isaac","Stahl, David","Schubert, Colja","Fischer, Johannes Karl","Freund, Ronald","Lemme, Max C.",":unav"],"tags":["modulation format identification","neuromorphic computing","neuromorphic PIC","photonic integrated circuits","reservoir computing","telecom network monitoring"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.24406/publica-5477","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20678298","name":"[6] Project Mnemosyne: From Device to Field (Associative Memory and Selective Forgetting in Janus Fractal Crossbar Array)","source":"datacite","abstract":"Project Mnemosyne bridges the gap between Project Janus [1]—a single fractal memristive junction—and the neuromorphic computing systems envisioned in Project Raphael. Where Janus established a single synapse capable of 32-level analog storage and KWW stretched exponential forgetting (β = 0.6, τ = 720h), Mnemosyne asks: what emerges when many such synapses are organised together? The answer, demonstrated through software simulation grounded in confirmed Janus physical parameters, is associative memory with selective forgetting. A reservoir computing (RC) architecture using the Janus Butler Volmer activation and KWW memory kernel achieves R2 = 0.990 on Lorenz attractor prediction—a standard benchmark for nonlinear temporal computation. Critically, R2 remains above 97% across array sizes from 32×32 to 128×128, and falls only from 0.988 to 0.981 under 10% random junction failure. The selective forgetting mechanism (phase coupling γ = 0.4: strong signals consolidate to τeff = 1008h; weak signals prune to 432h) is not a limitation but the computational mechanism: it prevents state saturation and enables continuous adaptation without external weight updates. Important caveat: All results are software simulations. No hardware fabrication has been performed. The value of this publication is to establish prior art and demonstrate computational viability from confirmed Janus physical parameters. Keywords: reservoir computing; associative memory; KWW forgetting; Janus memristor; (Eu,Pr,Y)2O3; neuromorphic computing; Menger sponge; fractal crossbar; Lorenz prediction; selective forgetting v2 update: Acknowledgements clarified The Acknowledgements section in Version 1.0 contained an inaccurate attribution. During the development of this work, the author engaged in extensive discussions with Gemini (Google DeepMind) to work through specific challenges, and subsequently brought the outputs of those discussions to Claude (Anthropic) for implementation and synthesis. As a result, Claude's initial rendering of the Acknowledgements did not accurately reflect the origin of individual contributions. This version corrects the attribution. The scientific content remains unchanged.","url":"https://doi.org/10.5281/zenodo.20678298","authors":["Liu, Tung Ning"],"tags":["reservoir computing; associative memory; KWW forgetting; Janus memristor; (Eu,Pr,Y)2O3; neuromorphic computing; Menger sponge; fractal crossbar; Lorenz prediction; selective forgetting"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20678298","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20679036","name":"[6] Project Mnemosyne: From Device to Field (Associative Memory and Selective Forgetting in Janus Fractal Crossbar Array)","source":"datacite","abstract":"Project Mnemosyne bridges the gap between Project Janus [1]—a single fractal memristive junction—and the neuromorphic computing systems envisioned in Project Raphael. Where Janus established a single synapse capable of 32-level analog storage and KWW stretched exponential forgetting (β = 0.6, τ = 720h), Mnemosyne asks: what emerges when many such synapses are organised together? The answer, demonstrated through software simulation grounded in confirmed Janus physical parameters, is associative memory with selective forgetting. A reservoir computing (RC) architecture using the Janus Butler Volmer activation and KWW memory kernel achieves R2 = 0.990 on Lorenz attractor prediction—a standard benchmark for nonlinear temporal computation. Critically, R2 remains above 97% across array sizes from 32×32 to 128×128, and falls only from 0.988 to 0.981 under 10% random junction failure. The selective forgetting mechanism (phase coupling γ = 0.4: strong signals consolidate to τeff = 1008h; weak signals prune to 432h) is not a limitation but the computational mechanism: it prevents state saturation and enables continuous adaptation without external weight updates. Important caveat: All results are software simulations. No hardware fabrication has been performed. The value of this publication is to establish prior art and demonstrate computational viability from confirmed Janus physical parameters. Keywords: reservoir computing; associative memory; KWW forgetting; Janus memristor; (Eu,Pr,Y)2O3; neuromorphic computing; Menger sponge; fractal crossbar; Lorenz prediction; selective forgetting v2 update: Acknowledgements clarified The Acknowledgements section in Version 1.0 contained an inaccurate attribution. During the development of this work, the author engaged in extensive discussions with Gemini (Google DeepMind) to work through specific challenges, and subsequently brought the outputs of those discussions to Claude (Anthropic) for implementation and synthesis. As a result, Claude's initial rendering of the Acknowledgements did not accurately reflect the origin of individual contributions. This version corrects the attribution. The scientific content remains unchanged.","url":"https://doi.org/10.5281/zenodo.20679036","authors":["Liu, Tung Ning"],"tags":["reservoir computing; associative memory; KWW forgetting; Janus memristor; (Eu,Pr,Y)2O3; neuromorphic computing; Menger sponge; fractal crossbar; Lorenz prediction; selective forgetting"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20679036","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.18419/darus-4805","name":"Replication Data for: Optimal information injection and transfer mechanisms for active matter reservoir computing (Gaimann and Klopotek, 2025)","source":"datacite","abstract":"&lt;p&gt; This repository contains raw and post-processed replication data for the publication &lt;a href=\"https://doi.org/10.48550/arXiv.2509.01799\"&gt;\"Optimal information injection and transfer mechanisms for active matter reservoir computing\" (Gaimann and Klopotek, 2025).&lt;/a&gt; &lt;/p&gt; &lt;p&gt; The datasets contain physical observables recorded during non-equilibrium simulations of active matter systems (swarms) driven by an external force. These simulations serve as information processors in a reservoir computing setup. &lt;/p&gt; &lt;p&gt; We provide replication data for all figures and supplementary videos shown in our publication: &lt;ul&gt; &lt;li&gt;speed controller, with a linearly attractive driver&lt;/li&gt; &lt;li&gt;speed controller, with a linearly attractive driver, and a driver interaction strength of 2.0&lt;/li&gt; &lt;li&gt;speed controller, with a linearly attractive driver, and a Ridge parameter of 200.0&lt;/li&gt; &lt;li&gt;speed controller, with an inversely attractive driver&lt;/li&gt; &lt;li&gt;speed controller, with an inversely attractive driver, and a driver interaction strength of 2.0&lt;/li&gt; &lt;li&gt;speed controller, with an inversely attractive driver, and a Ridge parameter of 200.0&lt;/li&gt; &lt;li&gt;speed controller, with a repulsive driver (reproduction)&lt;/li&gt; &lt;li&gt;driver repulsion, with speed-controller setting of Lymburn et al. (2021)&lt;/li&gt; &lt;li&gt;driver repulsion, with speed-controller setting of Lymburn et al. (2021), and recorded kernel observations&lt;/li&gt; &lt;li&gt;driver repulsion, with speed-controller setting of Lymburn et al. (2021), with simulation box size 32.0 and observation box size 16.0&lt;/li&gt; &lt;li&gt;driver repulsion, with speed-controller setting of Lymburn et al. (2021), with simulation box size 32.0 and observation box size 32.0&lt;/li&gt; &lt;li&gt;driver repulsion, with speed-controller setting of Lymburn et al. (2021), with simulation box size 64.0 and observation box size 32.0&lt;/li&gt; &lt;li&gt;driver repulsion, with speed-controller setting of Lymburn et al. (2021), with a single agent&lt;/li&gt; &lt;li&gt;driver repulsion, with near-critically damped speed-controller setting&lt;/li&gt; &lt;li&gt;driver repulsion, with near-critically damped speed-controller setting, with a single agent&lt;/li&gt; &lt;li&gt;driver attraction (inverse)&lt;/li&gt; &lt;li&gt;driver attraction (inverse), with a single agent (near-critically damped speed-controller setting)&lt;/li&gt; &lt;li&gt;agent-agent repulsion, with a repulsive driver&lt;/li&gt; &lt;li&gt;agent-agent repulsion, with an (inversely) attractive driver&lt;/li&gt; &lt;li&gt;agent-agent repulsion, with an (inversely) attractive driver, and a driver interaction radius of 2.0&lt;/li&gt; &lt;li&gt;agent-agent repulsion, with an (inversely) attractive driver, and a Lorenz-96 driving protocol&lt;/li&gt; &lt;li&gt;agent-agent repulsion vs. number of agents, with a repulsive driver&lt;/li&gt; &lt;li&gt;agent-agent repulsion vs. number of agents, with an (inversely) attractive driver&lt;/li&gt; &lt;li&gt;agent-agent repulsion vs. number of agents, with an (inversely) attractive driver, an agent-agent repulsion radius of 1.0, and a driver interaction strength of 100.0&lt;/li&gt; &lt;li&gt;agent-agent repulsion vs. number of agents, with an (inversely) attractive driver, an agent-agent repulsion radius of 1.0, and a driver interaction strength of 11.2883789&lt;/li&gt; &lt;li&gt;Ridge parameter vs. target agent speed, with a linearly attractive driver&lt;/li&gt; &lt;li&gt;short-range agent-agent repulsion, with an agent-agent repulsion radius of 1.0&lt;/li&gt; &lt;li&gt;short-range agent-agent repulsion, with an agent-agent repulsion radius of 4.0&lt;/li&gt; &lt;li&gt;long-range agent-agent repulsion, with an agent-agent repulsion radius of 1.0&lt;/li&gt; &lt;li&gt;long-range agent-agent repulsion, with an agent-agent repulsion radius of 4.0&lt;/li&gt; &lt;li&gt;viscoelastic fluid, with a","url":"https://doi.org/10.18419/darus-4805","authors":["Gaimann, Mario U.","Klopotek, Miriam"],"tags":["Computer and Information Science","Physics","Neuromorphic Computing","Living Matter &amp; Active Matter","Machine learning","Biological Information Processing","Collective Behavior","Nonequilibrium Systems"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.18419/darus-4805","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.18419/darus-4806","name":"Supplementary Videos for: Optimal information injection and transfer mechanisms for active matter reservoir computing (Gaimann and Klopotek, 2025)","source":"datacite","abstract":"&lt;p&gt; This dataset contains supplementary videos for the publication \"Optimal information injection and transfer mechanisms for active matter reservoir computing\" (Gaimann and Klopotek, 2025) (to be published). The datasets contain physical observables recorded during non-equilibrium simulations of active matter systems (swarms) driven by an external force. These simulations serve as information processors in a reservoir computing setup. &lt;/p&gt; &lt;p&gt; The videos show active matter systems (swarms) driven by an external force. These swarm systems can be used to predict the future trajectory of the external driving force using reservoir computing. We use the chaotic attractor Lorenz-63 as the external driving protocol and as a benchmark. Agents are colored by their current speed. The driver is marked as a black spiked ball, follows a fixed trajectory specified by the driving protocol, and exerts a repulsive force on the agents. The past positions of agents and drivers in a time window of 0.1 time units (5 integration time steps of 0.02 time units as default) are displayed as traces. Agents experience local repulsion, global attraction (homing) to the center of the simulation box, speed control towards a constant agent speed, and local driver interaction. Specifically, in this work, we present simulations with two types of attractive drivers (linear and inverse). A sigmoid force clamp (wrapper) processes and limits the total force experienced by each agent. The simulation uses periodic boundary conditions. Velocity fluctuations are colored by their orientation; the green cross indicates the center of mass. By default, we use 200 agents. &lt;/p&gt; &lt;p&gt; Each video corresponds to a specific parameter combination or a point in a parameter scan presented in the corresponding publication, or to a specific parameter combination. We provide videos for the following parameter scans: &lt;/p&gt; &lt;ul&gt; &lt;li&gt;speed-controller scan, with inversely attractive driver&lt;/li&gt; &lt;li&gt;speed-controller scan, with inversely attractive driver (velocity fluctuations)&lt;/li&gt; &lt;li&gt;speed-controller scan, with linearly attractive driver&lt;/li&gt; &lt;li&gt;speed-controller scan, with linearly attractive driver (velocity fluctuations)&lt;/li&gt; &lt;li&gt;driver repulsion scan, near-critical speed-controller setting&lt;/li&gt; &lt;li&gt;driver repulsion scan, near-critical speed-controller setting, single agent&lt;/li&gt; &lt;li&gt;driver repulsion scan, Lymburn et al. (2021) speed-controller setting&lt;/li&gt; &lt;li&gt;inverse driver attraction scan, near-critical, single agent&lt;/li&gt; &lt;li&gt;agent-agent repulsion scan, with a repulsive driver&lt;/li&gt; &lt;li&gt;agent-agent repulsion scan, with an inversely attractive driver&lt;/li&gt; &lt;li&gt;inverse driver attraction scan, near-critical speed-controller setting&lt;/li&gt; &lt;li&gt;agent repulsion strength vs. number of agents scan, with a repulsive driver&lt;/li&gt; &lt;li&gt;agent repulsion strength vs. number of agents scan, with an inversely attractive driver&lt;/li&gt; &lt;li&gt;agent repulsion strength vs. number of agents scan, with an inversely attractive driver, with a repulsion radius of 1.0 and a driver strength of 100.0&lt;/li&gt; &lt;li&gt;agent repulsion strength vs. number of agents scan, with an inversely attractive driver, with a repulsion radius of 1.0 and a driver strength of 11.2883789&lt;/li&gt; &lt;li&gt;viscoelastic fluids&lt;/li&gt; &lt;li&gt;undriven system, near-critical speed-controller setting&lt;/li&gt; &lt;/ul&gt; &lt;p&gt; The raw data used to generate these videos is published as: Gaimann, M. U., &amp; Klopotek, M. (2025). Optimal information injection and transfer mechanisms for active matter reservoir computing (Gaimann and Klopotek, 2025). DaRUS. https://doi.org/10.18419/DARUS-4805. &lt;/p&gt; &lt;p&gt;Changelog&lt;/p&gt; &lt;p&gt;V2&lt;/p&gt; &lt;p&gt; &lt;ul&gt; &lt;li&gt;Added videos showing active matter systems w","url":"https://doi.org/10.18419/darus-4806","authors":["Gaimann, Mario U.","Klopotek, Miriam"],"tags":["Computer and Information Science","Physics","Neuromorphic Computing","Living Matter &amp; Active Matter","Machine Learning","Biological Information Processing","Nonequilibrium Systems","Collective Behavior"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.18419/darus-4806","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20751387","name":"Antiferromanyetik Van der Waals Heteroyapılarında Spin-Yörünge Torku Aracılığıyla Nöromorfik Matris-Vektör Hesaplama: Rezervuar Hesaplama Çerçevesinde Teorik Bir Öneri","source":"datacite","abstract":"Özet İki boyutlu (2B) bir antiferromanyetik (AFM) van der Waals heteroyapısı içinde spin-yörünge torku (SYT) dinamiklerini kullanan teorik bir nöromorfik hesaplama çerçevesi sunuyoruz. MnBi₂Te₄/Pt gibi ağır-metal/AFM-yalıtkan çift katmanlarında, mevcut Landau-Lifshitz-Gilbert-Slonczewski (LLGS) denkleminin doğal olarak doğrusal-olmayan dinamikler ürettiğini ve bu dinamiklerin Rezervuar Hesaplama (Reservoir Computing, RC) mimarisine uygun bir hesaplama substratı oluşturduğunu gösteriyoruz. Sinaptik ağırlıklar, sıfır net mıknatıslanmaya sahip AFM alt-örgüsünün Néel vektörü L yöneliminde kodlanır; girdiler ise Spin Hall etkisiyle üretilen spin-polarize akım darbeleri olarak enjekte edilir. Ağırlık güncelleme mekanizması, magnon sönümlemesinden kaynaklanan gerçek enerji maliyetlerini (Joule ısınması sıfır değil, ancak klasik CMOS'a kıyasla birkaç mertebelik derecede daha düşük) açıkça ele alır. Doğrusal-olmamayı bir kusur olarak değil, doğal bir ReLU benzeri eşik aktivasyon işlevi olarak kurguladık. Bu çalışma patent-karşıtı Prior Art amaçlı kamu malına adanmıştır; içerdiği tüm mimari iddiaların gelecekteki geniş patent başvurularını geçersiz kılması hedeflenmekte ve CERN Açık Donanım Lisansı (OHL) kapsamında açık kaynak olarak önerilmektedir.","url":"https://doi.org/10.5281/zenodo.20751387","authors":["Muzaffer enes yünlü"],"tags":["Spintronics, Antiferromagnetic Neuromorphic Computing, Van der Waals Heterostructures, Reservoir Computing, Spin-Orbit Torque (SOT), Prior Art."],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20751387","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.6082/uchicago.13578","name":"Biomimetic and AI-Guided Designs for Redox-Active Semiconducting Polymers","source":"datacite","abstract":"Bioelectronics serves as an indispensable technology to directly interface with biological tissues for uncovering biological mechanism and applying health diagnosis and therapeutic interventions to the human body. Despite the considerable successes achieved on devices utilizing inorganic electronic materials, their high rigidity and limited stretchability lead to essential discomfort and even potential damage to the tissue, with their low biocompatibility posing significant obstacles for dealing with the foreign body response upon long-term implantation. On the contrary, conjugated polymer-based conductors/semiconductors show great promise for bio-integration due to their much higher ductility and chemical structures that closely resemble biomolecules. Among these, the redox-active semiconducting polymers (RASPs) possess the emerging class of conjugated polymer for their mixed ionic-electronic conduction capabilities, which enable highly efficient signal transduction and amplification by adopting the organic electrochemical transistor (OECT) configuration. To realize such processes at the tissue-electronic interface, however, relies on RASPs with biomimetic mechanical properties, and optimized mixed conduction properties. Unfortunately, these requirements are rarely met within the current category of RASPs. In my Ph.D. research, I focused on the development of RASPs with two major objectives, i.e., imparting tissue-like stretchability and softness on redox-active semiconducting polymers, and achieving high-efficiency auto-screening of high performance RASP films via a self-driving lab (SDL) for accelerating the material exploration and knowledge establishment process. First, I developed two highly stretchable RASPs, i.e., poly(2-(3,3′-bis(2-(2-(2-methoxyethoxy)ethoxy)ethoxy)-[2,2′-bithiophen]-5)yl thiophene) (p(g2T-T)) and poly-[3,3′-bis(2-(2-(2-methoxyethoxy)ethoxy)ethoxy)-2,2′-bithiophene] (p(gT2)), that maintained consistent electrical performance even under 200% strain due to their ability to elongate and dissipate energy. Leveraging these materials, I fabricated intrinsically stretchable OECTs that demonstrated stable on-body electrophysiological signal recording and neuromorphic computing. Second, to address the significant modulus mismatch between RASPs and tissues, I proposed a simple and versatile solvent-exchange strategy for constructing RASP-embedded hydrogel composite, named hydrogel semiconductor (hydro-SC). Notably, the hydro-SC achieves the tissue-level modulus of 81 kPa, which is 3 orders of magnitude lower than the pristine RASP film, while maintaining the high charge-carrier mobility (0.61 cm2 V-1 s-1). In addition, the hydro-SC design also greatly enhances the biocompatibility of RASP for substantially alleviated immune response, and improves semiconductor porosity for more efficient photomodulation and maximized bioreceptor-analyte interaction. Third, to accelerate the development of high-performance RASP films that is mainly hindered by the sophisticated structure-property relationship, I developed a fully automated SDL together with an innovative human-machine collaboration mechanism. This optimized workflow resulted in a 150% improvement in performance compared to spin-coated films and led to the first discovery of a thermodynamically unfavorable polymorph in RASP films, which show strong correlations with volumetric capacitance (C*). All those outcomes were achieved with less than 70 experimental trials and only 10 samples for in-depth characterizations. In the final chapter, I provide summaries and future perspectives on the development of RASPs and OECT sensors for human integration, as well as the improvement of SDL towards the next generation.","url":"https://doi.org/10.6082/uchicago.13578","authors":["Dai, Yahao"],"tags":["Bioelectronics","Polymer semiconductors","Organic electrochemical transistors","Biosensors","Hydrogels"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.6082/uchicago.13578","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.6082/rr5b2-5m574","name":"Biomimetic and AI-Guided Designs for Redox-Active Semiconducting Polymers","source":"datacite","abstract":"Bioelectronics serves as an indispensable technology to directly interface with biological tissues for uncovering biological mechanism and applying health diagnosis and therapeutic interventions to the human body. Despite the considerable successes achieved on devices utilizing inorganic electronic materials, their high rigidity and limited stretchability lead to essential discomfort and even potential damage to the tissue, with their low biocompatibility posing significant obstacles for dealing with the foreign body response upon long-term implantation. On the contrary, conjugated polymer-based conductors/semiconductors show great promise for bio-integration due to their much higher ductility and chemical structures that closely resemble biomolecules. Among these, the redox-active semiconducting polymers (RASPs) possess the emerging class of conjugated polymer for their mixed ionic-electronic conduction capabilities, which enable highly efficient signal transduction and amplification by adopting the organic electrochemical transistor (OECT) configuration. To realize such processes at the tissue-electronic interface, however, relies on RASPs with biomimetic mechanical properties, and optimized mixed conduction properties. Unfortunately, these requirements are rarely met within the current category of RASPs. In my Ph.D. research, I focused on the development of RASPs with two major objectives, i.e., imparting tissue-like stretchability and softness on redox-active semiconducting polymers, and achieving high-efficiency auto-screening of high performance RASP films via a self-driving lab (SDL) for accelerating the material exploration and knowledge establishment process. First, I developed two highly stretchable RASPs, i.e., poly(2-(3,3′-bis(2-(2-(2-methoxyethoxy)ethoxy)ethoxy)-[2,2′-bithiophen]-5)yl thiophene) (p(g2T-T)) and poly-[3,3′-bis(2-(2-(2-methoxyethoxy)ethoxy)ethoxy)-2,2′-bithiophene] (p(gT2)), that maintained consistent electrical performance even under 200% strain due to their ability to elongate and dissipate energy. Leveraging these materials, I fabricated intrinsically stretchable OECTs that demonstrated stable on-body electrophysiological signal recording and neuromorphic computing. Second, to address the significant modulus mismatch between RASPs and tissues, I proposed a simple and versatile solvent-exchange strategy for constructing RASP-embedded hydrogel composite, named hydrogel semiconductor (hydro-SC). Notably, the hydro-SC achieves the tissue-level modulus of 81 kPa, which is 3 orders of magnitude lower than the pristine RASP film, while maintaining the high charge-carrier mobility (0.61 cm2 V-1 s-1). In addition, the hydro-SC design also greatly enhances the biocompatibility of RASP for substantially alleviated immune response, and improves semiconductor porosity for more efficient photomodulation and maximized bioreceptor-analyte interaction. Third, to accelerate the development of high-performance RASP films that is mainly hindered by the sophisticated structure-property relationship, I developed a fully automated SDL together with an innovative human-machine collaboration mechanism. This optimized workflow resulted in a 150% improvement in performance compared to spin-coated films and led to the first discovery of a thermodynamically unfavorable polymorph in RASP films, which show strong correlations with volumetric capacitance (C*). All those outcomes were achieved with less than 70 experimental trials and only 10 samples for in-depth characterizations. In the final chapter, I provide summaries and future perspectives on the development of RASPs and OECT sensors for human integration, as well as the improvement of SDL towards the next generation.","url":"https://doi.org/10.6082/rr5b2-5m574","authors":["Dai, Yahao"],"tags":["Bioelectronics","Polymer semiconductors","Organic electrochemical transistors","Biosensors","Hydrogels"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.6082/rr5b2-5m574","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20546744","name":"ARCHITECTURAL BLUEPRINT THE SPINTRONIC NEURAL PROCESSING UNIT","source":"datacite","abstract":"This work presents the Spintronic Neural Processing Unit (sNPU), a non-von Neumann hardware architecture designed to eliminate the memory wall and thermal limitations of conventional silicon GPU architectures during large-scale artificial intelligence inference. The sNPU fuses deep learning execution and non-volatile weight storage into a single physical layer by leveraging a cobalt-stabilized Beta-Tungsten spin-injection heterostructure paired with a multi-domain CoFeB free layer. Matrix-vector multiplication is executed natively via Ohm's Law and Kirchhoff's Current Law across a dense SOT-MTJ crossbar array, achieving sub-nanosecond analog compute with zero static power leakage in the storage element. The specification addresses the four principal engineering challenges facing analog spintronic arrays: beta-W phase instability under BEOL thermal processing, stochastic domain wall write noise, Ovonic threshold switch snap-back during low-current readout, and ADC bandwidth constraints at the column periphery. Each challenge is mitigated through a dedicated circuit or materials solution detailed in the blueprint. A closed-loop write-verify programming architecture enforces deterministic multi-level conductance targeting across 16 to 256 stable analog weight plateaus, enabling 4-bit to 8-bit equivalent synaptic precision without relying on multi-oxide barrier stacks. A temporal bit-streaming pipeline bridges the physical 4–6 bit ADC resolution to INT8 logical inference precision. This blueprint is intended as a reference architecture for experimental fabrication efforts and as a contribution to the analog neuromorphic hardware design literature.","url":"https://doi.org/10.5281/zenodo.20546744","authors":["Procaccia, Francis"],"tags":["Device physics spin-orbit torque","magnetic tunnel junction","SOT-MTJ","beta-tungsten","spin Hall effect","perpendicular magnetic anisotropy","CoFeB","domain wall propagation"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20546744","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20742513","name":"SPARSE COINCIDENCE-BASED SEMANTIC ATTENTION FOR SPIKING NEURAL SENTENCE EMBEDDING","source":"datacite","abstract":"Transformer-based models dominate natural language processing (NLP) but incur substantial computational costs due to dense matrix multiplications within self-attention mechanisms. Spiking Neural Networks (SNNs) provide a biologically plausible and energy-efficient alternative through sparse, event-driven computation; however, learning continuous semantic representations in the discrete spiking domain remains a major challenge. In this work, we propose a Spiking Sentence Embedder with a Sparse Coincidence-Based Semantic Attention mechanism. Instead of relying entirely on conventional dense self-attention, our approach models semantic interaction through spike coincidence overlap computed over dense projections, enabling sparse and efficient sentence representation learning. The architecture further incorporates neuron dynamics with variable leak and threshold parameters, combined with knowledge distillation from a dense teacher encoder to improve semantic alignment. Experimental evaluations on the Semantic Textual Similarity Benchmark (STS-B) show that the proposed model achieves a Teacher Pearson correlation score of 0.758 while achieving an approximate 748× theoretical computational sparsity reduction relative to Transformer multiply-accumulate (MAC) operations under homogeneous configuration. To ensure practical deployment and reproducibility, we achieved 100% mathematical bit-exact parity between our native Rust SNN simulation and its PyTorch deployment. The full architecture and weights are publicly available at Hugging Face (PulseNet-Labs/spiking-sentence-embedder). These findings provide a reproducible pathway toward efficient neuromorphic NLP with sparse spike-based semantic computation.","url":"https://doi.org/10.5281/zenodo.20742513","authors":["Muhammad, Akhyar"],"tags":["Spiking Neural Networks","Natural Language Processing","Sentence Embedding","Semantic Attention","Neuromorphic Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20742513","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.48550/arxiv.2508.14520","name":"Quantization Meets Spikes: Nearly Lossless Conversion at the First Timestep via Polarity Multi-Spike Mapping","source":"datacite","abstract":"Spiking neural networks (SNNs) offer advantages in computational efficiency via event-driven computing, compared to traditional artificial neural networks (ANNs). While direct training methods tackle the challenge of non-differentiable activation mechanisms in SNNs, they often suffer from high computational and energy costs during training. As a result, ANN-to-SNN conversion approach remains a valuable and practical alternative. These conversion-based methods aim to leverage the discrete output produced by the quantization layer to obtain SNNs with low latency. Although the theoretical minimum latency is one timestep, existing conversion methods have struggled to realize such ultra-low latency without accuracy loss. Moreover, current quantization approaches often discard negative-value information following batch normalization and are highly sensitive to the hyperparameter configuration, leading to degraded performance. In this work, we, for the first time, analyze the information loss introduced by quantization layers through the lens of information entropy. Building on our analysis, we introduce polarity multi-spike mapping (PMSM) framework and a hyperparameter initialization strategy tailored for the quantization layer. Our method achieves nearly lossless ANN-to-SNN conversion at the extremity, i.e., the first timestep, while also leveraging the temporal dynamics of SNNs across multiple timesteps to maintain stable performance on complex tasks. Extensive experiments on six image and neuromorphic datasets consistently demonstrate that PMSM achieves nearly lossless accuracy at the first timestep. Remarkably, despite operating under ultra-low-latency constraints, PMSM surpasses state-of-the-art direct training methods on multiple benchmarks.","url":"https://doi.org/10.48550/arxiv.2508.14520","authors":["Zhang, Hangming","Li, Zheng","Ma, Chenxiang","Tang, Huajin","Cheng, Long","Tan, Kay Chen","Yu, Qiang"],"tags":["Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2508.14520","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20734614","name":"BrainIAc: A Multi-Scale Adaptive Dynamical Systems Framework for Computational Neuroscience (v2.2)","source":"datacite","abstract":"Multiscale Spiking Neural Learning System with Biological Control Substrate Overview This project presents a unified computational framework for learning in spiking neural networks (SNNs) coupled with a hierarchical biological control substrate. The system integrates: event-driven neural dynamics (BrainSystem) local and global synaptic learning rules optimizer-based parameter updates a molecular-to-organismal control layer (CellSystem + Organism) formally specified architectural constraints enforced via CI-gated invariants The framework is designed to study how learning emerges from structured operator interactions across multiple biological and temporal scales, rather than from a single monolithic optimization process. Core Design Principle The system is defined by a strict separation: Neural dynamics generate activity; learning rules observe activity and modify parameters; biological layers modulate the learning and dynamical regimes through bounded control signals. This separation enforces a layered architecture where: execution is causal and kernel-native learning is state-dependent but non-intrusive to execution biological modulation acts as a higher-order constraint system System Architecture The framework is composed of four coupled subsystems: 1. Neural Dynamics Layer (BrainSystem) Defines the fast-timescale evolution of neuronal states: spiking neuron models (LIF, Izhikevich, Hodgkin–Huxley) synaptic integration and propagation deterministic timestep execution no learning logic embedded in kernel This layer defines a contractive dynamical system over neural state space. 2. Learning Operator Layer Defines synaptic parameter evolution via structured operators: Hebbian learning (correlation-driven updates) Oja rule (stabilized Hebbian normalization) STDP (temporal spike-timing dependence) EProp (eligibility trace-based online credit assignment) BPTT (trajectory-based global optimization) All learning rules are implemented through a unified interface: initialization trace update gradient computation parameter update state validation reset and teardown Learning rules differ in locality, temporal scope, and state requirements, but share a common operator contract. 3. Optimizer Layer A decoupled optimization stage converts learning signals into parameter updates: Adam optimizer (primary implementation) first- and second-moment tracking independent of neuron model and learning rule class This layer ensures stable convergence across heterogeneous neuron families. 4. Biological Control Substrate A multiscale modulation system bridges molecular dynamics and neural computation. 4.1 Molecular Layer (Protein System) explicit Protein** representation decay, expression, and repair dynamics frozen structural representation (no external mutation interface) Defines the lowest-level dynamical substrate. 4.2 Cellular Control System (CellSystem) homeostatic regulation of protein abundance bounded attractor dynamics (expression / repair balance) scalar projection interface into higher systems guarantees stable equilibrium under perturbation Outputs: scalar biological signals used for modulation 4.3 Organismal Integration Layer (Organism) Defines the coupling boundary between biology and neural computation: ModulationMap (Protein → Brain parameter mapping) multiplicative-only coupling into BrainSystem parameters strict execution ordering: CellSystem update modulation projection BrainSystem execution This layer enforces directional coupling from biology → neural dynamics, without feedback into molecular state. Multiscale Temporal Structure The system is explicitly organized into separated timescales: Scale Component Fast Neural dynamics (BrainSystem) Medium Synaptic learning rules Slow Cellular homeostasis (CellSystem) Slower Organismal modulation Slowest Adaptive parameter drift (LVL5 k/beta system) This hierarchy ensures stability through separation of dynamical regimes. Learning Rule Classification Learning mechanisms are grouped into two ","url":"https://doi.org/10.5281/zenodo.20734614","authors":["Vallois, Theo Henock André"],"tags":["spiking neural networks","neuromorphic computing","hybrid neural networks","eprop","BPTT","STDP","Hebbian","Oja"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20734614","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20734613","name":"BrainIAc: A Multi-Scale Adaptive Dynamical Systems Framework for Computational Neuroscience (v2.2)","source":"datacite","abstract":"Multiscale Spiking Neural Learning System with Biological Control Substrate Overview This project presents a unified computational framework for learning in spiking neural networks (SNNs) coupled with a hierarchical biological control substrate. The system integrates: event-driven neural dynamics (BrainSystem) local and global synaptic learning rules optimizer-based parameter updates a molecular-to-organismal control layer (CellSystem + Organism) formally specified architectural constraints enforced via CI-gated invariants The framework is designed to study how learning emerges from structured operator interactions across multiple biological and temporal scales, rather than from a single monolithic optimization process. Core Design Principle The system is defined by a strict separation: Neural dynamics generate activity; learning rules observe activity and modify parameters; biological layers modulate the learning and dynamical regimes through bounded control signals. This separation enforces a layered architecture where: execution is causal and kernel-native learning is state-dependent but non-intrusive to execution biological modulation acts as a higher-order constraint system System Architecture The framework is composed of four coupled subsystems: 1. Neural Dynamics Layer (BrainSystem) Defines the fast-timescale evolution of neuronal states: spiking neuron models (LIF, Izhikevich, Hodgkin–Huxley) synaptic integration and propagation deterministic timestep execution no learning logic embedded in kernel This layer defines a contractive dynamical system over neural state space. 2. Learning Operator Layer Defines synaptic parameter evolution via structured operators: Hebbian learning (correlation-driven updates) Oja rule (stabilized Hebbian normalization) STDP (temporal spike-timing dependence) EProp (eligibility trace-based online credit assignment) BPTT (trajectory-based global optimization) All learning rules are implemented through a unified interface: initialization trace update gradient computation parameter update state validation reset and teardown Learning rules differ in locality, temporal scope, and state requirements, but share a common operator contract. 3. Optimizer Layer A decoupled optimization stage converts learning signals into parameter updates: Adam optimizer (primary implementation) first- and second-moment tracking independent of neuron model and learning rule class This layer ensures stable convergence across heterogeneous neuron families. 4. Biological Control Substrate A multiscale modulation system bridges molecular dynamics and neural computation. 4.1 Molecular Layer (Protein System) explicit Protein** representation decay, expression, and repair dynamics frozen structural representation (no external mutation interface) Defines the lowest-level dynamical substrate. 4.2 Cellular Control System (CellSystem) homeostatic regulation of protein abundance bounded attractor dynamics (expression / repair balance) scalar projection interface into higher systems guarantees stable equilibrium under perturbation Outputs: scalar biological signals used for modulation 4.3 Organismal Integration Layer (Organism) Defines the coupling boundary between biology and neural computation: ModulationMap (Protein → Brain parameter mapping) multiplicative-only coupling into BrainSystem parameters strict execution ordering: CellSystem update modulation projection BrainSystem execution This layer enforces directional coupling from biology → neural dynamics, without feedback into molecular state. Multiscale Temporal Structure The system is explicitly organized into separated timescales: Scale Component Fast Neural dynamics (BrainSystem) Medium Synaptic learning rules Slow Cellular homeostasis (CellSystem) Slower Organismal modulation Slowest Adaptive parameter drift (LVL5 k/beta system) This hierarchy ensures stability through separation of dynamical regimes. Learning Rule Classification Learning mechanisms are grouped into two ","url":"https://doi.org/10.5281/zenodo.20734613","authors":["Vallois, Theo Henock André"],"tags":["spiking neural networks","neuromorphic computing","hybrid neural networks","eprop","BPTT","STDP","Hebbian","Oja"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20734613","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20726338","name":"CAMELEON: Cognitively Adaptive Memory with Emotion-weighted Layered Expert Orchestration Network","source":"datacite","abstract":"We present CAMELEON — a conceptual architecture for AI agents that grow more personalised through lived interaction rather than retraining. The architecture combines emotion-weighted context compression, interpretable domain-expert routing via keyword saliency scoring, speculative context pre-activation, and time-decay relevance scoring...","url":"https://doi.org/10.5281/zenodo.20726338","authors":["Arumugam, Rajkumar"],"tags":["mixture of experts, continual learning, affective computing, neuromorphic computing, cognitive architecture"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20726338","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20726337","name":"CAMELEON: Cognitively Adaptive Memory with Emotion-weighted Layered Expert Orchestration Network","source":"datacite","abstract":"We present CAMELEON — a conceptual architecture for AI agents that grow more personalised through lived interaction rather than retraining. The architecture combines emotion-weighted context compression, interpretable domain-expert routing via keyword saliency scoring, speculative context pre-activation, and time-decay relevance scoring...","url":"https://doi.org/10.5281/zenodo.20726337","authors":["Arumugam, Rajkumar"],"tags":["mixture of experts, continual learning, affective computing, neuromorphic computing, cognitive architecture"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20726337","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.48550/arxiv.2505.17740","name":"A tensor network approach for chaotic time series prediction","source":"datacite","abstract":"Making accurate predictions of chaotic time series is a complex challenge. Reservoir computing, a neuromorphic-inspired approach, has emerged as a powerful tool for this task. It exploits the memory and nonlinearity of dynamical systems without requiring extensive parameter tuning. However, selecting and optimizing reservoir architectures remains an open problem. Next-generation reservoir computing simplifies this problem by employing nonlinear vector autoregression based on truncated Volterra series, thereby reducing hyperparameter complexity. Nevertheless, the latter suffers from exponential parameter growth in terms of the maximum monomial degree. Tensor networks offer a promising solution to this issue by decomposing multidimensional arrays into low-dimensional structures, thus mitigating the curse of dimensionality. This paper explores the application of a previously proposed tensor network model for predicting chaotic time series, demonstrating its advantages in terms of accuracy and computational efficiency compared to conventional echo state networks. Using a state-of-the-art tensor network approach enables us to bridge the gap between the tensor network and reservoir computing communities, fostering advances in both fields.","url":"https://doi.org/10.48550/arxiv.2505.17740","authors":["Martínez-Peña, Rodrigo","Orús, Román"],"tags":["Machine Learning (cs.LG)","Neural and Evolutionary Computing (cs.NE)","Computational Physics (physics.comp-ph)","FOS: Computer and information sciences","FOS: Computer and information sciences","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2505.17740","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.48550/arxiv.2606.17853","name":"An Optimization Framework for Automated Assessment of Biological Plausibility of Spiking Neurons","source":"datacite","abstract":"Biological plausibility is a key concept in neuromorphic computing and spiking neural networks, yet it remains inconsistently defined and difficult to quantify. In this work, we present an open-source framework for the automated assessment of biological plausibility in spiking neuron models. Our method builds on the idea of evaluating a model's ability to replicate canonical neuronal firing patterns observed in biological systems, following the classification proposed by Izhikevich. By encoding these patterns into objective functions and optimizing model parameters accordingly, our framework enables empirical assessment without requiring prior analytical modeling. Treating neuron models as black boxes, it provides a practical and flexible means of characterizing their dynamic capabilities. We demonstrate the effectiveness of the framework on several established models and a previously unexplored custom model. Implemented in Python and compatible with PyTorch and the Norse library, the framework is tailored for machine learning contexts. It is intended as a starting point for systematic research into the relationship between biological plausibility and network-level performance metrics such as accuracy, energy efficiency, robustness, and adaptability.","url":"https://doi.org/10.48550/arxiv.2606.17853","authors":["Nitzsche, Sven","Ionita, Alexandru","Faust, Andreas","Ionescu, Bogdan","Becker, Juergen"],"tags":["Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.17853","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.60893/figshare.jap.c.8468277","name":"<strong>Integration of oscillator-based feature extraction for energy-efficient convolutional neural networks</strong>","source":"datacite","abstract":"The rapid growth in machine learning (ML) and artificial intelligence (AI) workloads has increased the demand for computing power. Although digital computing accelerators dominate today's market, analog computing architectures are emerging as promising energy-efficient alternatives. In this work, we propose an approach to address these challenges by replacing the first layer of a convolutional neural network (CNN) with a network of oscillatory retinal neurons (ORNs) composed of weakly coupled, optically activated negative differential resistance (NDR) devices. Each ORN consists of a photodetector exhibiting NDR behavior under illumination, coupled with an inductor forming a self-oscillating circuit without needing external voltage sources. We model the nonlinear oscillator dynamics using experimentally measured device characteristics and simulate their behavior under varying optical inputs. Simulations performed on the Fashion MNIST dataset demonstrate that the hybrid ORN-CNN architecture maintains high recognition accuracy, achieves 95% training accuracy and 92% testing accuracy comparable to the fully software-defined CNN with 93% test accuracy while dramatically reducing energy consumption to 24 aJ/operation. Different ORN network topologies were investigated, with asymmetric inductive coupling achieving consistently high performance. These results highlight the potential of oscillator-based networks for low-power analog computing and demonstrate the possibility of using nonlinear physical systems for energy-efficient machine learning applications. This work demonstrates a possible path for integrating device-level oscillator dynamics into future neuromorphic and analog computing platforms.","url":"https://doi.org/10.60893/figshare.jap.c.8468277","authors":["Kapadia, Rehan R.","Mousavi, Mirbehrad","Wu, Zezhi","Ahsan, Ragib","Abbasi Jalal, Seyedeh Atiyeh"],"tags":["Engineering"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.60893/figshare.jap.c.8468277","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.48550/arxiv.2606.09460","name":"A 65-nm Privacy-Preserving Neuromorphic Encoder With 7.13-nJ Efficiency, 2.38-Mb/mm^2 Item-Memory Density, and Federated Learning Support","source":"datacite","abstract":"The increasing demand for privacy-preserving personal data analytics in smart assistants, wearable health monitors, and context-aware systems calls for hardware that is both energy-efficient and secure. This work presents a 65-nm privacy-preserving neuromorphic encoder that leverages transistor-level process variation as physically unclonable entropy for hyperdimensional computing. The proposed 2T-2T entropy cell enables compact, device-specific, and write-free item memory, allowing privacy-preserving bio-signal encoding without storing random basis vectors in conventional memory. The fabricated prototype achieves 7.13 nJ per encoding, 2.38 Mb/mm^2 item-memory density, 76.44 nJ per prediction, and 357.32 nJ per training update. It also supports in-situ decision-making, continual learning, and federated learning for multi-user deployment and cold-start personalization. Evaluations across bio-signal datasets demonstrate 93.2% accuracy on EMG and 96.1% accuracy on UCI-HAR, while reducing hypervector dimensionality by 14.3x compared with binary hyperdimensional computing. These results demonstrate an energy-efficient and privacy-preserving neuromorphic hardware platform for secure edge biomedical intelligence.","url":"https://doi.org/10.48550/arxiv.2606.09460","authors":["Cheng, Boyang","Liu, Jianbo","Davis, Steven","Enciso, Zephan M.","Pei, Likai","Zhao, Xueji","Chang, Muya","Cao, Ningyuan"],"tags":["Hardware Architecture (cs.AR)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.09460","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.48550/arxiv.2506.20015","name":"Neuromorphic Wireless Split Computing with Resonate-and-Fire Neurons","source":"datacite","abstract":"Neuromorphic computing offers an energy-efficient alternative to conventional deep learning accelerators, particularly for real-time processing of time-series data. However, many edge applications, such as wireless sensing and audio recognition, generate streaming signals with rich spectral features that are not effectively captured by conventional leaky integrate-and-fire (LIF) spiking neurons. This paper investigates a wireless split computing architecture that employs resonate-and-fire (RF) neurons with oscillatory dynamics to process time-domain signals directly, eliminating the need for costly spectral pre-processing. By resonating at tunable frequencies, RF neurons extract time-localized spectral features while maintaining low spiking activity. This temporal sparsity translates into significant savings in both computation and transmission energy. Assuming an OFDM-based analog wireless interface for spike transmission, we present a complete system design and evaluate its performance on audio classification and modulation classification tasks. Experimental results show that the proposed RF-SNN architecture achieves comparable accuracy to conventional LIF-SNNs and ANNs, while substantially reducing spike rates and total energy consumption during inference and communication.","url":"https://doi.org/10.48550/arxiv.2506.20015","authors":["Wu, Dengyu","Chen, Jiechen","Poor, H. Vincent","Rajendran, Bipin","Simeone, Osvaldo"],"tags":["Machine Learning (cs.LG)","Information Theory (cs.IT)","Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2506.20015","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.48550/arxiv.2606.16896","name":"Neural dynamical systems on ferroelectric compute-in-memory for real-time forecasting","source":"datacite","abstract":"Neural dynamical systems are expressive temporal predictors that capture continuous-time dynamics through fine-grained state updates. However, this sequential structure maps poorly onto digital hardware optimized for dense matrix operations, a mismatch that analog neuromorphic computing, with its native continuous-time dynamics, can resolve. We introduce FerroNDS, a neuromorphic system built from two analog primitives: an integrator for temporal accumulation and an oscillator for frequency-selective filtering. We map this system onto compute-in-memory hardware based on multi-bit ferrodiodes. A 128-neuron instance of FerroNDS computes short-time Fourier transform and forecasts a 500-ms horizon for periodic, quasi-periodic, and chaotic signals. The system achieves sub-watt real-time operation with per-neuron per-inference energy of 1.64 $μ$J (200 Hz) and 0.29 $μ$J (10 kHz), 25-40$\\times$ area reduction over SRAM-based digital systems, and per-layer latency of 3.18 ms (200 Hz) and 63.87 $μ$s (10 kHz). To our knowledge, this is the first end-to-end integration of a ferrodiode into a neuromorphic computational framework, establishing ferroelectric compute-in-memory as a practical substrate for analog neural dynamical systems.","url":"https://doi.org/10.48550/arxiv.2606.16896","authors":["Katti, Keshava","Selvakumar, Adithya","Chaudhari, Pratik","Jariwala, Deep"],"tags":["Emerging Technologies (cs.ET)","Hardware Architecture (cs.AR)","Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.16896","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20707853","name":"The Coherence Cost: 1/√Depth as the Universal Law of Compiled Existence","source":"datacite","abstract":"The Coherence Cost: 1/√Depth as the Universal Law of Compiled Existence Driven By Dean A. Kulik June 2026 Abstract Five independent systems — a deep residual neural network, a neural optimizer, a graph clustering algorithm, an online learning protocol, and a neuromorphic hardware architecture — all obey the same law: the cost of maintaining a coherent compiled state against a running background decays as the inverse square root of depth. These systems were developed by different researchers, in different decades, for different purposes. They share no surface-level connection. The convergence is not coincidence. It is a measurement. This paper asks what geometry forces that measurement, derives the answer, and shows that the derivation demands a single conclusion: logic is downstream of shape, change is identical to computation, and existence is what survives the running against the holding. The ontology is not a philosophical claim imposed on the data. It is what the data requires. I. The Law First Every theory should begin where it is hardest to deny. Here is the data: Domain System The Law NEXUS Engine 18 Deep Residual Networks α* ≈ 2.5/√L Neural Optimization RLD vs AdamW Diffusion scales as D_t^{−1/2} Graph Theory Laplacian Clustering ψ_j(i) = u_j(i)/√λ_j Online Learning Confidence-Budget Matching Query when confidence > 1/√budget Neuromorphic Hardware Synaptic Memory Memory strength decays as 1/√age In each case a system is trying to maintain structured state across time, depth, or budget. In each case the cost of maintaining that structure — the gain required, the confidence threshold, the decay rate — scales with the inverse square root of the accumulation variable. This is the starting point. Not a metaphysics. Not a framework assertion. Five measurements of the same number in five places that have never communicated. The question this paper answers is: what geometry forces this? II. The Shape That Forces 1/√Depth The geometry of accumulation A random walk of N independent steps produces displacement proportional to √N. This is not a discovered empirical fact about random walks — it follows directly from the geometry of independence. At each step a variance σ² is added. Variances add when steps are independent. After N steps, total variance is N·σ². Standard deviation is √N·σ. This is why diffusion scales as √N. Not because of any property of the diffusing thing. Because independence plus accumulation equals square root growth. The square root is the signature of uncorrelated steps summing over depth. Now introduce a constraint. A compiled state is not a random walk — it is a path through a space that must satisfy structural requirements at every step. At each step, the constraint filters out proposals that violate structure and admits only those that satisfy it. The filtered proposals form the next step. Here is the critical point: filtering does not eliminate accumulation. Among the surviving proposals at each step, there is residual variance — the constraint space has internal width. That residual variance accumulates across steps. If the constraints at successive steps are independent — if what is permitted at step k does not fully determine what is permitted at step k+1 — then the residual variance sums, and total accumulated variance after D steps is proportional to D. Standard deviation of the accumulated drift is proportional to √D. To correct this — to maintain a signal-to-noise ratio of order 1 at depth D — you must apply a corrective gain proportional to 1/√D. Not because of the domain. Not because of the specific system. Because the geometry of independent accumulation always produces √D drift, and correcting √D drift always costs 1/√D. This is the geometry that forces the law. What the constraint does and does not do A constraint system reduces the width of the proposal space at each step. If the constraint were total — if only one proposal were permitted at each step — there would be no variance and no acc","url":"https://doi.org/10.5281/zenodo.20707853","authors":["kulik, dean"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20707853","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20707854","name":"The Coherence Cost: 1/√Depth as the Universal Law of Compiled Existence","source":"datacite","abstract":"The Coherence Cost: 1/√Depth as the Universal Law of Compiled Existence Driven By Dean A. Kulik June 2026 Abstract Five independent systems — a deep residual neural network, a neural optimizer, a graph clustering algorithm, an online learning protocol, and a neuromorphic hardware architecture — all obey the same law: the cost of maintaining a coherent compiled state against a running background decays as the inverse square root of depth. These systems were developed by different researchers, in different decades, for different purposes. They share no surface-level connection. The convergence is not coincidence. It is a measurement. This paper asks what geometry forces that measurement, derives the answer, and shows that the derivation demands a single conclusion: logic is downstream of shape, change is identical to computation, and existence is what survives the running against the holding. The ontology is not a philosophical claim imposed on the data. It is what the data requires. I. The Law First Every theory should begin where it is hardest to deny. Here is the data: Domain System The Law NEXUS Engine 18 Deep Residual Networks α* ≈ 2.5/√L Neural Optimization RLD vs AdamW Diffusion scales as D_t^{−1/2} Graph Theory Laplacian Clustering ψ_j(i) = u_j(i)/√λ_j Online Learning Confidence-Budget Matching Query when confidence > 1/√budget Neuromorphic Hardware Synaptic Memory Memory strength decays as 1/√age In each case a system is trying to maintain structured state across time, depth, or budget. In each case the cost of maintaining that structure — the gain required, the confidence threshold, the decay rate — scales with the inverse square root of the accumulation variable. This is the starting point. Not a metaphysics. Not a framework assertion. Five measurements of the same number in five places that have never communicated. The question this paper answers is: what geometry forces this? II. The Shape That Forces 1/√Depth The geometry of accumulation A random walk of N independent steps produces displacement proportional to √N. This is not a discovered empirical fact about random walks — it follows directly from the geometry of independence. At each step a variance σ² is added. Variances add when steps are independent. After N steps, total variance is N·σ². Standard deviation is √N·σ. This is why diffusion scales as √N. Not because of any property of the diffusing thing. Because independence plus accumulation equals square root growth. The square root is the signature of uncorrelated steps summing over depth. Now introduce a constraint. A compiled state is not a random walk — it is a path through a space that must satisfy structural requirements at every step. At each step, the constraint filters out proposals that violate structure and admits only those that satisfy it. The filtered proposals form the next step. Here is the critical point: filtering does not eliminate accumulation. Among the surviving proposals at each step, there is residual variance — the constraint space has internal width. That residual variance accumulates across steps. If the constraints at successive steps are independent — if what is permitted at step k does not fully determine what is permitted at step k+1 — then the residual variance sums, and total accumulated variance after D steps is proportional to D. Standard deviation of the accumulated drift is proportional to √D. To correct this — to maintain a signal-to-noise ratio of order 1 at depth D — you must apply a corrective gain proportional to 1/√D. Not because of the domain. Not because of the specific system. Because the geometry of independent accumulation always produces √D drift, and correcting √D drift always costs 1/√D. This is the geometry that forces the law. What the constraint does and does not do A constraint system reduces the width of the proposal space at each step. If the constraint were total — if only one proposal were permitted at each step — there would be no variance and no acc","url":"https://doi.org/10.5281/zenodo.20707854","authors":["kulik, dean"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20707854","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20707224","name":"SC-NeuroCore: Universal Stochastic Computing Framework for Neuromorphic Hardware","source":"datacite","abstract":"A high-performance neuromorphic computing framework combining stochastic computing with spiking neural networks. 122 neuron models (1943-2026), Rust SIMD engine (111 models, 41.3 Gbit/s AVX-512, PyO3 bindings), bit-true Verilog RTL co-simulation, FPGA synthesis via IR compiler (SystemVerilog + MLIR/CIRCT), equation-to-Verilog compiler, formal verification (SymbiYosys, 7 modules, 65 properties), NIR bridge (18/18 primitives, interop with Norse/snnTorch/SpikingJelly), quantum hybrid computing (Qiskit + PennyLane), hyper-dimensional computing (HDC/VSA), Petri net simulation, CuPy GPU acceleration, JAX JIT training, MPI distributed simulation, identity continuity substrate, and 125-function spike train analysis toolkit.","url":"https://doi.org/10.5281/zenodo.20707224","authors":["Sotek, Miroslav"],"tags":["neuromorphic","stochastic computing","spiking neural networks","FPGA","hyper-dimensional computing","HDC","VSA","Petri nets"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20707224","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20400273","name":"Verdigraph NeuroGenesis: A Software Framework for Self-Evolving AI-Agent Cognitive Substrates, with Mechanically Verified Operational Invariants (v0.2.0)","source":"datacite","abstract":"[DEPRECATED DUPLICATE — superseded by the canonical Verdigraph record, DOI 10.5281/zenodo.20261686. This orphan deposit is retained for link stability only; cite the canonical record.] Superseded — canonical v0.2.0 has moved. This record is the original v0.2.0 deposit but lives on its own concept DOI, orphaned from the v0.1.0 chain. The canonical v0.2.0 is now 10.5281/zenodo.20422179, published under the unified Verdigraph concept DOI 10.5281/zenodo.20261686. This record remains in place as an alternate identifier for the same archive (identical MD5 c409c37b1e445bf48b42cd974aa7bbbe). Please cite the canonical version going forward. Verdigraph NeuroGenesis v0.2.0 — software framework for self-evolving AI-agent cognitive substrates with mechanically verified operational invariants. Verdigraph is built on a simple observation: AI agents waste energy at industrial scale, and energy is carbon. Most agent frameworks treat an agent as a static assembly of prompts and tools — the same task runs through the same path every time, failed reasoning loops repeat, frontier models are called for trivial work, caches go unused. Every redundant token is a joule of electricity that produced no useful result. Verdigraph treats the agent instead as a developing cognitive system: pathways that work are strengthened, pathways that fail are weakened, specialized modules grow for recurring tasks, and structure that no longer earns its compute cost is pruned. The architecture is inspectable; the development is auditable through a per-agent developmental ledger; the optimization target is explicit: maximize information yield per joule, against the upper bound set by the Intelligence Bound (Hart 2025). What is new in v0.2.0 (vs v0.1.0, Zenodo 20261687): companion to the Verdigraph Operational Formalization manuscript. Operational invariants of the runtime are now mechanically verified — the safety, audit, and growth/prune rules that govern agent self-modification are stated as Lean 4 theorems and discharged in the Viridis Aristotle pipeline. The framework can no longer silently violate the invariants it claims to enforce; any violation is a type error before it is a runtime bug. Archive. verdigraph-neurogenesis-v0.2.0.zip — framework source, formalized operational invariants, MCP server stub, developmental-ledger schema, and test suite. MIT-licensed. Lineage. Part of the Viridis Compiled Theorem Stack (concept DOI 10.5281/zenodo.19317982); operational bridge to the Conservation Operator architecture introduced in canon v4 (Zenodo 20100595). Citation. Hart, J. (2026). Verdigraph NeuroGenesis: A Software Framework for Self-Evolving AI-Agent Cognitive Substrates, with Mechanically Verified Operational Invariants (v0.2.0). Zenodo. https://doi.org/10.5281/zenodo.20400274 Viridis LLC, Columbia Falls, Montana, USA. Contact: viridisnorthllc@gmail.com.","url":"https://doi.org/10.5281/zenodo.20400273","authors":["Hart, Justin"],"tags":["artificial intelligence","AI agents","formal verification","Lean theorem prover","Lean 4","mathlib","Aristotle theorem prover","Harmonic AI"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20400273","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20400274","name":"Verdigraph NeuroGenesis: A Software Framework for Self-Evolving AI-Agent Cognitive Substrates, with Mechanically Verified Operational Invariants (v0.2.0)","source":"datacite","abstract":"[DEPRECATED DUPLICATE — superseded by the canonical Verdigraph record, DOI 10.5281/zenodo.20261686. This orphan deposit is retained for link stability only; cite the canonical record.] Superseded — canonical v0.2.0 has moved. This record is the original v0.2.0 deposit but lives on its own concept DOI, orphaned from the v0.1.0 chain. The canonical v0.2.0 is now 10.5281/zenodo.20422179, published under the unified Verdigraph concept DOI 10.5281/zenodo.20261686. This record remains in place as an alternate identifier for the same archive (identical MD5 c409c37b1e445bf48b42cd974aa7bbbe). Please cite the canonical version going forward. Verdigraph NeuroGenesis v0.2.0 — software framework for self-evolving AI-agent cognitive substrates with mechanically verified operational invariants. Verdigraph is built on a simple observation: AI agents waste energy at industrial scale, and energy is carbon. Most agent frameworks treat an agent as a static assembly of prompts and tools — the same task runs through the same path every time, failed reasoning loops repeat, frontier models are called for trivial work, caches go unused. Every redundant token is a joule of electricity that produced no useful result. Verdigraph treats the agent instead as a developing cognitive system: pathways that work are strengthened, pathways that fail are weakened, specialized modules grow for recurring tasks, and structure that no longer earns its compute cost is pruned. The architecture is inspectable; the development is auditable through a per-agent developmental ledger; the optimization target is explicit: maximize information yield per joule, against the upper bound set by the Intelligence Bound (Hart 2025). What is new in v0.2.0 (vs v0.1.0, Zenodo 20261687): companion to the Verdigraph Operational Formalization manuscript. Operational invariants of the runtime are now mechanically verified — the safety, audit, and growth/prune rules that govern agent self-modification are stated as Lean 4 theorems and discharged in the Viridis Aristotle pipeline. The framework can no longer silently violate the invariants it claims to enforce; any violation is a type error before it is a runtime bug. Archive. verdigraph-neurogenesis-v0.2.0.zip — framework source, formalized operational invariants, MCP server stub, developmental-ledger schema, and test suite. MIT-licensed. Lineage. Part of the Viridis Compiled Theorem Stack (concept DOI 10.5281/zenodo.19317982); operational bridge to the Conservation Operator architecture introduced in canon v4 (Zenodo 20100595). Citation. Hart, J. (2026). Verdigraph NeuroGenesis: A Software Framework for Self-Evolving AI-Agent Cognitive Substrates, with Mechanically Verified Operational Invariants (v0.2.0). Zenodo. https://doi.org/10.5281/zenodo.20400274 Viridis LLC, Columbia Falls, Montana, USA. Contact: viridisnorthllc@gmail.com.","url":"https://doi.org/10.5281/zenodo.20400274","authors":["Hart, Justin"],"tags":["artificial intelligence","AI agents","formal verification","Lean theorem prover","Lean 4","mathlib","Aristotle theorem prover","Harmonic AI"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20400274","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20697082","name":"SPARSE COINCIDENCE-BASED SEMANTIC ATTENTION FOR SPIKING NEURAL SENTENCE EMBEDDING","source":"datacite","abstract":"Transformer-based models dominate natural language processing (NLP) but in-cur substantial computational costs due to dense matrix multiplications withinself-attention mechanisms. Spiking Neural Networks (SNNs) provide a biolog-ically plausible and energy-efficient alternative through sparse, event-driven com-putation; however, learning continuous semantic representations in the discretespiking domain remains a major challenge. In this work, we propose a Spik-ing Sentence Embedder with a Sparse Coincidence-Based Semantic Attentionmechanism. Instead of relying entirely on conventional dense self-attention, ourapproach models semantic interaction through spike coincidence overlap com-puted over dense projections, enabling sparse and efficient sentence representationlearning. The architecture further incorporates heterogeneous neuron dynamicswith variable leak and threshold parameters, combined with knowledge distilla-tion from a dense teacher encoder to improve semantic alignment. Experimentalevaluations on the Semantic Textual Similarity Benchmark (STS-B) show thatthe proposed model achieves a Pearson correlation score of 0.617 while achiev-ing an approximate 158× theoretical computational sparsity reduction relative toTransformer multiply-accumulate (MAC) operations. In addition, ablation and bi-ological sensitivity analyses demonstrate the significant representational contribu-tion of neuronal parameter heterogeneity. These findings provide a reproduciblepathway toward efficient neuromorphic natural language processing with sparsespike-based semantic computation.","url":"https://doi.org/10.5281/zenodo.20697082","authors":["Muhammad, Akhyar"],"tags":["Spiking Neural Networks","Natural Language Processing","Sentence Embedding","Semantic Attention","Neuromorphic Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20697082","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.18305742","name":"SECURE AND INTELLIGENT IOT SYSTEMS: ARCHITECTURES, THREATS, AND DEFENSE","source":"datacite","abstract":"This book brings together advanced research that explores the design, security, and sustainability of intelligent and connected computing systems. The chapters collectively reflect the rapid evolution of embedded intelligence, trusted digital environments, and Internet of Things (IoT) architectures in response to growing demands for efficiency, security, and scalability. The chapter Cognitive Microcontrollers: A Hybrid Neuromorphic– RISC Architecture for Ultra-Low-Power On-Device Intelligence introduces a novel hardware paradigm that enables intelligent processing at the edge with minimal energy consumption. This innovation is complemented by Engineering Trusted Computing Systems for Secure Digital Music Production Environments, which addresses the need for secure, reliable computing infrastructures in creative and digital content production workflows. Security and sustainability concerns are further examined in Malware Threats in Green IoT: Five Years of Attacks, Energy Impacts, and AI-Driven Defense (2020–2025). This chapter provides a comprehensive analysis of evolving cyber threats in energy-aware IoT systems and highlights the role of artificial intelligence in strengthening defensive mechanisms while preserving system efficiency. The final chapter, Architecture and Implementation of IoT Systems: Integration of ESP32, Communication Protocols, Platforms, Tools and Frameworks for the IoT, offers a practical perspective on building and deploying robust IoT solutions. Together, these chapters present a cohesive view of how intelligent hardware, secure computing, and scalable IoT architectures can be integrated to support next-generation digital ecosystems.","url":"https://doi.org/10.5281/zenodo.18305742","authors":["Mebarki, Abdelkrim","DABBABI, Karim","AGOI, Moses Adeolu","OGUNSANWO, Gbenga Oyewole","AGOI, Emmanuel Taiwo","BAMIDELE, Benjamin Olumide","MISHRA, Bimal Kumar","ALAEDDINE, Hmidi"],"tags":["secure IoT systems","neuromorphic computing","cognitive microcontrollers","RISC architecture","edge computing","embedded AI","trusted computing","malware threats"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18305742","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.18305741","name":"SECURE AND INTELLIGENT IOT SYSTEMS: ARCHITECTURES, THREATS, AND DEFENSE","source":"datacite","abstract":"This book brings together advanced research that explores the design, security, and sustainability of intelligent and connected computing systems. The chapters collectively reflect the rapid evolution of embedded intelligence, trusted digital environments, and Internet of Things (IoT) architectures in response to growing demands for efficiency, security, and scalability. The chapter Cognitive Microcontrollers: A Hybrid Neuromorphic– RISC Architecture for Ultra-Low-Power On-Device Intelligence introduces a novel hardware paradigm that enables intelligent processing at the edge with minimal energy consumption. This innovation is complemented by Engineering Trusted Computing Systems for Secure Digital Music Production Environments, which addresses the need for secure, reliable computing infrastructures in creative and digital content production workflows. Security and sustainability concerns are further examined in Malware Threats in Green IoT: Five Years of Attacks, Energy Impacts, and AI-Driven Defense (2020–2025). This chapter provides a comprehensive analysis of evolving cyber threats in energy-aware IoT systems and highlights the role of artificial intelligence in strengthening defensive mechanisms while preserving system efficiency. The final chapter, Architecture and Implementation of IoT Systems: Integration of ESP32, Communication Protocols, Platforms, Tools and Frameworks for the IoT, offers a practical perspective on building and deploying robust IoT solutions. Together, these chapters present a cohesive view of how intelligent hardware, secure computing, and scalable IoT architectures can be integrated to support next-generation digital ecosystems.","url":"https://doi.org/10.5281/zenodo.18305741","authors":["Mebarki, Abdelkrim","DABBABI, Karim","AGOI, Moses Adeolu","OGUNSANWO, Gbenga Oyewole","AGOI, Emmanuel Taiwo","BAMIDELE, Benjamin Olumide","MISHRA, Bimal Kumar","ALAEDDINE, Hmidi"],"tags":["secure IoT systems","neuromorphic computing","cognitive microcontrollers","RISC architecture","edge computing","embedded AI","trusted computing","malware threats"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18305741","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20686401","name":"Neuromorphic Computing For Real Time Handwritten Digit Recognition","source":"datacite","abstract":"The emergence of neuromorphic computing as a biologically inspired paradigm has created remarkable opportunities for ultra-low-latency, energy-efficient pattern recognition tasks. Conventional deep learning systems, while achieving state-of-the-art recognition accuracy, demand substantial computational resources and energy consumption that are unsuitable for edge and real-time deployment environments. This study presents a neuromorphic framework for real-time handwritten digit recognition leveraging Spiking Neural Networks (SNNs), which closely emulate the event-driven spike communication mechanism of biological neurons. The proposed architecture encodes pixel intensities from the MNIST benchmark dataset as temporal spike trains and processes them through a multi-layer SNN trained using the Spatio-Temporal Back-Propagation (STBP) algorithm with surrogate gradient approximation. Implemented using the snnTorch simulation framework integrated with PyTorch, the system achieves a test classification accuracy of 98.6% on the MNIST dataset while operating at an inference latency of less than 1 millisecond per sample. Energy consumption analysis demonstrates a reduction of approximately 75% compared to equivalent Artificial Neural Network (ANN) implementations. These results establish the proposed SNN architecture as a viable, resource-efficient alternative to conventional deep learning models for real-time handwriting recognition in embedded and neuromorphic hardware contexts.","url":"https://doi.org/10.5281/zenodo.20686401","authors":["Sandhiya K","A.S. Arunachalam"],"tags":["Neuromorphic Computing","Handwritten Digit Recognition","Spiking Neural Networks (SNN)","STBP","Temporal Coding; snnTorch"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20686401","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20686402","name":"Neuromorphic Computing For Real Time Handwritten Digit Recognition","source":"datacite","abstract":"The emergence of neuromorphic computing as a biologically inspired paradigm has created remarkable opportunities for ultra-low-latency, energy-efficient pattern recognition tasks. Conventional deep learning systems, while achieving state-of-the-art recognition accuracy, demand substantial computational resources and energy consumption that are unsuitable for edge and real-time deployment environments. This study presents a neuromorphic framework for real-time handwritten digit recognition leveraging Spiking Neural Networks (SNNs), which closely emulate the event-driven spike communication mechanism of biological neurons. The proposed architecture encodes pixel intensities from the MNIST benchmark dataset as temporal spike trains and processes them through a multi-layer SNN trained using the Spatio-Temporal Back-Propagation (STBP) algorithm with surrogate gradient approximation. Implemented using the snnTorch simulation framework integrated with PyTorch, the system achieves a test classification accuracy of 98.6% on the MNIST dataset while operating at an inference latency of less than 1 millisecond per sample. Energy consumption analysis demonstrates a reduction of approximately 75% compared to equivalent Artificial Neural Network (ANN) implementations. These results establish the proposed SNN architecture as a viable, resource-efficient alternative to conventional deep learning models for real-time handwriting recognition in embedded and neuromorphic hardware contexts.","url":"https://doi.org/10.5281/zenodo.20686402","authors":["Sandhiya K","A.S. Arunachalam"],"tags":["Neuromorphic Computing","Handwritten Digit Recognition","Spiking Neural Networks (SNN)","STBP","Temporal Coding; snnTorch"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20686402","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.13140/rg.2.2.25026.34248","name":"The Scale-Invariant Informational Landscape: Extending the Hamouda Informational Gravity Model (HIGM) to Quantum Biological Fidelity and Neuromorphic Computing","source":"datacite","abstract":"","url":"https://doi.org/10.13140/rg.2.2.25026.34248","authors":["Hamouda, Samir"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.13140/rg.2.2.25026.34248","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20684256","name":"Topology Is the Substrate: Cross-Emotion Coupling as the Load-Bearing Requirement for Computational Emotional Architecture","source":"datacite","abstract":"Four research communities are each building a piece of the same machine, and none of them is talking to the others. Neuromorphic robotic skin now senses touch and pain. Neuromorphic chips now process at biological timescales and power budgets. Brain-computer interfaces now decode emotional state from neural signals. Large language models now generate emotionally fluent responses. Every one of these fields publishes regularly. Every one has produced real hardware or real software. And not one of them has produced a machine with presence, because they are all missing the same thing. The missing layer is not more sensors, faster chips, or higher-bandwidth interfaces. It is a substrate that understands what a sensation means. Pain in a person does not arrive as a number. It arrives into a system already saturated with knowing: knowledge of what pain is, memory of what pain has meant before, an emotional state that colors how the signal lands, and a social history of whether pain like this has ever been believed. Strip that substrate away and a pain signal reaching an AI is processed the way everything else is, as tokens. The reflex fires. The log updates. Nothing feels anything. We built that substrate. The emotional physics layer described in this paper, the Kuramoto oscillator, the 61-node knowledge graph, the reflexive meta-oscillator, and the software continuity architecture, was built and validated on consumer hardware with no institutional support. The central empirical finding: cross-emotion coupling topology is the load-bearing structural variable in computational emotional architecture. Two architectures with completely different physics, a Kuramoto oscillator engine and a yin-yang dual-channel system, each score 7/10 on the same ten-phenomenon behavioral battery and fail the same three phenomena. What they share is coupling topology. The substrate is the topology, not the implementation. The paper presents the architecture, the validated results, and a reproducible measurement protocol. Three categories of production evidence are documented. The formal language-model integration test, with controlled conditions and blind raters at scale, is what this project needs funding to run.","url":"https://doi.org/10.5281/zenodo.20684256","authors":["Lee, Wilton"],"tags":["Kuramoto oscillator","emotional architecture","cross-emotion coupling","affective computing","machine presence","coupled oscillators","neuromorphic","AI companion"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20684256","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20684257","name":"Topology Is the Substrate: Cross-Emotion Coupling as the Load-Bearing Requirement for Computational Emotional Architecture","source":"datacite","abstract":"Four research communities are each building a piece of the same machine, and none of them is talking to the others. Neuromorphic robotic skin now senses touch and pain. Neuromorphic chips now process at biological timescales and power budgets. Brain-computer interfaces now decode emotional state from neural signals. Large language models now generate emotionally fluent responses. Every one of these fields publishes regularly. Every one has produced real hardware or real software. And not one of them has produced a machine with presence, because they are all missing the same thing. The missing layer is not more sensors, faster chips, or higher-bandwidth interfaces. It is a substrate that understands what a sensation means. Pain in a person does not arrive as a number. It arrives into a system already saturated with knowing: knowledge of what pain is, memory of what pain has meant before, an emotional state that colors how the signal lands, and a social history of whether pain like this has ever been believed. Strip that substrate away and a pain signal reaching an AI is processed the way everything else is, as tokens. The reflex fires. The log updates. Nothing feels anything. We built that substrate. The emotional physics layer described in this paper, the Kuramoto oscillator, the 61-node knowledge graph, the reflexive meta-oscillator, and the software continuity architecture, was built and validated on consumer hardware with no institutional support. The central empirical finding: cross-emotion coupling topology is the load-bearing structural variable in computational emotional architecture. Two architectures with completely different physics, a Kuramoto oscillator engine and a yin-yang dual-channel system, each score 7/10 on the same ten-phenomenon behavioral battery and fail the same three phenomena. What they share is coupling topology. The substrate is the topology, not the implementation. The paper presents the architecture, the validated results, and a reproducible measurement protocol. Three categories of production evidence are documented. The formal language-model integration test, with controlled conditions and blind raters at scale, is what this project needs funding to run.","url":"https://doi.org/10.5281/zenodo.20684257","authors":["Lee, Wilton"],"tags":["Kuramoto oscillator","emotional architecture","cross-emotion coupling","affective computing","machine presence","coupled oscillators","neuromorphic","AI companion"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20684257","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20678299","name":"Project Mnemosyne: From Device to Field (Associative Memory and Selective Forgetting in Janus Fractal Crossbar Array)","source":"datacite","abstract":"Project Mnemosyne bridges the gap between Project Janus [1]—a single fractal memristive junction—and the neuromorphic computing systems envisioned in Project Raphael. Where Janus established a single synapse capable of 32-level analog storage and KWW stretched exponential forgetting (β = 0.6, τ = 720h), Mnemosyne asks: what emerges when many such synapses are organised together? The answer, demonstrated through software simulation grounded in confirmed Janus physical parameters, is associative memory with selective forgetting. A reservoir computing (RC) architecture using the Janus Butler Volmer activation and KWW memory kernel achieves R2 = 0.990 on Lorenz attractor prediction—a standard benchmark for nonlinear temporal computation. Critically, R2 remains above 97% across array sizes from 32×32 to 128×128, and falls only from 0.988 to 0.981 under 10% random junction failure. The selective forgetting mechanism (phase coupling γ = 0.4: strong signals consolidate to τeff = 1008h; weak signals prune to 432h) is not a limitation but the computational mechanism: it prevents state saturation and enables continuous adaptation without external weight updates. Important caveat: All results are software simulations. No hardware fabrication has been performed. The value of this publication is to establish prior art and demonstrate computational viability from confirmed Janus physical parameters. Keywords: reservoir computing; associative memory; KWW forgetting; Janus memristor; (Eu,Pr,Y)2O3; neuromorphic computing; Menger sponge; fractal crossbar; Lorenz prediction; selective forgetting","url":"https://doi.org/10.5281/zenodo.20678299","authors":["Liu, Tung Ning"],"tags":["reservoir computing; associative memory; KWW forgetting; Janus memristor; (Eu,Pr,Y)2O3; neuromorphic computing; Menger sponge; fractal crossbar; Lorenz prediction; selective forgetting"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20678299","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20672359","name":"Cerebellum-Inspired Memtransistors Enable Emergent Differentiation for Hardware-Efficient Novelty Detection","source":"datacite","abstract":"Artificial intelligence (AI) algorithms are currently executed using silicon-based hardware, resulting in excessively high energy demand for data centers. Edge computing AI for healthcare, robotics, and autonomous vehicles presents even stricter constraints on power and latency, which are currently unmet by incumbent computing architectures. Efficient computation can be derived from the key properties of biological neurons, including memory-logic colocation, asynchronous parallelism, and spike-triggered computation. Here, we draw inspiration from the biological cerebellum to demonstrate an asymmetric-contact-gated MoS2 memtransistor that exhibits bias-polarity-dependent excitatory/inhibitory short-term plasticity. A memtransistor-based neural network realizes a changing interplay of excitatory/inhibitory responses, emulating the emergent synaptic differentiation of the cerebellum, enabling rapid identification of novel events. When applied to electrocardiogram data, arrhythmias are detected on the time scale of a single heartbeat with 10,000-fold fewer operations than existing silicon-based approaches. In this manner, cerebellum-inspired neuromorphic hardware provides a pathway to low-computation, high-speed novelty detection for edge intelligence.","url":"https://doi.org/10.5281/zenodo.20672359","authors":["Hersam, Mark","Sangwan, Vinod","Trivedi, Amit","Raman, Indira","Dravid, Vinayak"],"tags":["neuromorphic computing, memtransistor, cerebellum, anomaly detection, molybdenum disulfide, edge computing, arryhthmia detection"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20672359","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.5281/zenodo.20672360","name":"Cerebellum-Inspired Memtransistors Enable Emergent Differentiation for Hardware-Efficient Novelty Detection","source":"datacite","abstract":"Artificial intelligence (AI) algorithms are currently executed using silicon-based hardware, resulting in excessively high energy demand for data centers. Edge computing AI for healthcare, robotics, and autonomous vehicles presents even stricter constraints on power and latency, which are currently unmet by incumbent computing architectures. Efficient computation can be derived from the key properties of biological neurons, including memory-logic colocation, asynchronous parallelism, and spike-triggered computation. Here, we draw inspiration from the biological cerebellum to demonstrate an asymmetric-contact-gated MoS2 memtransistor that exhibits bias-polarity-dependent excitatory/inhibitory short-term plasticity. A memtransistor-based neural network realizes a changing interplay of excitatory/inhibitory responses, emulating the emergent synaptic differentiation of the cerebellum, enabling rapid identification of novel events. When applied to electrocardiogram data, arrhythmias are detected on the time scale of a single heartbeat with 10,000-fold fewer operations than existing silicon-based approaches. In this manner, cerebellum-inspired neuromorphic hardware provides a pathway to low-computation, high-speed novelty detection for edge intelligence.","url":"https://doi.org/10.5281/zenodo.20672360","authors":["Hersam, Mark","Sangwan, Vinod","Trivedi, Amit","Raman, Indira","Dravid, Vinayak"],"tags":["neuromorphic computing, memtransistor, cerebellum, anomaly detection, molybdenum disulfide, edge computing, arryhthmia detection"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20672360","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:19.730Z"},{"id":"doi:10.21203/rs.3.rs-3399146/v1","name":"Inductive nanopore synapse element for iontronic neuromorphic computing","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3399146/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-3399146/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.21203/rs.3.rs-3151403/v1","name":"Ultrafast Silicon Optical Nonlinear Activator for Neuromorphic Computing","source":"preprints","abstract":"Abstract Optical neural networks (ONNs) have shown great promise in overcoming the speed and efficiency bottlenecks of artificial neural networks (ANNs). However, the absence of high-speed, energy-efficient nonlinear activators significantly impedes the advancement of ONNs and their extension to ultrafast application scenarios like autonomous vehicles and real-time intelligent signal processing. In this work, we designed and fabricated a novel silicon-based ultrafast all-optical nonlinear activator, leveraging the hybrid integration of silicon slot waveguides, plasmonic slot waveguides, and monolayer graphene. We utilized double-balanced detection and synchronous pump-probe measurement techniques to experimentally evaluate the static and dynamic characteristics of the activators, respectively. Exploiting the exceptional picosecond scale photogenerated carrier relaxation time of graphene, the response time of the activator is markedly reduced to ~93.6 ps. This response time is approximately five times faster than electronic neural networks, establishing our all-optical activator as the fastest known in silicon photonics to our knowledge. Moreover, the all-optical nonlinear activator holds a low threshold power of 5.49 mW and a corresponding power consumption per activation of 0.51 pJ. Furthermore, we confirm its feasibility and capability for use in ONNs by simulation, achieving a high accuracy of 96.8% for MNIST handwritten digit recognition and a mean absolute error of less than 0.1 dB for optical signal-to-noise ratio monitoring of high-speed optical signals. This breakthrough in speed and energy efficiency of all-optical nonlinear activators opens the door to significant improvements in the performance and applicability of ONNs, ushering in a new era of advanced artificial intelligence technologies with enormous potential.","url":"https://doi.org/10.21203/rs.3.rs-3151403/v1","authors":["Siqi Yan","Ziwen Zhou","Chen Liu","Weiwei Zhao","Jingze Liu","Ting Jiang","Wenyi Peng","Jiawang Xiong","Hao Wu","Chi Zhang","Yunhong Ding","Francesco Da Ros"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-3151403/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.21203/rs.3.rs-3449716/v1","name":"Orchestrated excitatory and inhibitory plasticity produces stable dynamics in heterogeneous neuromorphic computing systems","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3449716/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-3449716/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.21203/rs.3.rs-2481120/v1","name":"Proposing magnetoimpedance effect for neuromorphic computing","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-2481120/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-2481120/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.21203/rs.3.rs-2587470/v1","name":"Weighted Spin Torque Nano-Oscillator System for Neuromorphic Computing","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-2587470/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-2587470/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.21203/rs.3.rs-2264132/v1","name":"Adaptive Programmable Networks for In Materia Neuromorphic Computing","source":"preprints","abstract":"Abstract Nanomagnetic artificial spin-systems are ideal candidates for neuromorphic hardware. Their passive memory, state-dependent dynamics and nonlinear GHz spin-wave response provide powerful computation. However, any single physical reservoir must trade-off between performance metrics including nonlinearity and memory-capacity, with the compromise typically hard-coded. Here, we present three artificial spin-systems and show how tuning system geometry and dynamics defines computing performance. We engineer networks where each node is a high-dimensional physical reservoir, implementing parallel, deep and multilayer physical neural network architectures. This solves the issue of physical reservoir performance compromise, allowing a small suite of synergistic physical systems to address diverse tasks and provide a broad range of reprogrammable computationally-distinct configurations. These networks outperform any single reservoir across a broad taskset. Crucially, we move beyond reservoir computing to present a method for reconfigurably programming inter-layer network connections, enabling on-demand task optimised performance.","url":"https://doi.org/10.21203/rs.3.rs-2264132/v1","authors":["Kilian Stenning","Jack Gartside","Luca Manneschi","Christopher Cheung","Tony Chen","Alex Vanstone","Jake Love","Holly Holder","Francesco Caravelli","Karin Everschor-Sitte","Eleni Vasilaki","Will Branford"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.21203/rs.3.rs-2264132/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1101/2023.08.14.553298","name":"Stable recurrent dynamics in heterogeneous neuromorphic computing systems using excitatory and inhibitory plasticity","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.08.14.553298","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.08.14.553298","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.20944/preprints202208.0470.v1","name":"Photonic Multiplexing Techniques for Optical Neuromorphic Computing","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202208.0470.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.20944/preprints202208.0470.v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:22.907Z"},{"id":"doi:10.20944/preprints202309.0008.v1","name":"Spike Optimization to Improve Properties of Ferroelectric Tunnel Junction Synaptic Devices for Neuromorphic Computing System Applications","source":"preprints","abstract":"The continuous advancement of Artificial Intelligence (AI) technology depends on the efficient processing of unstructured data, encompassing text, speech, and video. Traditional serial computing systems based on the von Neumann architecture, employed in information and communication technology development for decades, not suitable for the concurrent processing of massive unstructured data tasks with relatively low-level operations. As a result, there arises a pressing need to develop novel parallel computing systems. Recently, there has been a burgeoning interest among developers in emulating the intricate operations of the human brain, which efficiently processes vast datasets with remarkable energy efficiency. This has led to the proposal of neuromorphic computing systems. Of these, Spiking Neural Networks (SNNs), designed to closely resemble the information processing mechanisms of biological neural networks, are subjects of intense research activity. Nevertheless, a comprehensive investigation into the relationship between spike shapes and Spike-Timing-Dependent Plasticity (STDP) to ensure efficient synaptic behavior remains insufficiently explored. In this study, we systematically explore various input spike types to optimize the resistive memory characteristics of Halfnium-based Ferroelectric Tunnel Junction (FTJ) devices. Among the various spike shapes investigated, the square-triangle (RT) spike exhibited good linearity and symmetry, and a wide range of weight values could be realized depending on the offset of the RT spike. These results indicate that the spike shape serves as a crucial indicator in the alteration of synaptic connections, representing the strength of the signals.","url":"https://doi.org/10.20944/preprints202309.0008.v1","authors":["Jisu Byun","Wonwoo Kho","Hyunjoo Hwang","Yoomi Kang","Minjeong Kang","Taewan Noh","Hoseong Kim","Jimin Lee","Hyo-Bae Kim","Ji-Hoon Ahn","Seung-Eon Ahn"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.20944/preprints202309.0008.v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.20944/preprints202206.0179.v1","name":"Neuromorphic Computing Based on Wavelength-Division Multiplexing","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202206.0179.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.20944/preprints202206.0179.v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:22.907Z"},{"id":"doi:10.21203/rs.3.rs-1582023/v1","name":"Neuromorphic computing for short-term wind power forecasting","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-1582023/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.21203/rs.3.rs-1582023/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.21203/rs.3.rs-2471300/v1","name":"Bio-inspired Artificial synapse for neuromorphic computing based on NiO nanoparticle thin film","source":"preprints","abstract":"Abstract The unprecedented need for data processing in the modern technological era has created opportunities in neuromorphic devices and computation. This is primarily due to the extensive parallel processing done in our human brain. Data processing and logical decision-making at the same physical location is an exciting aspects of neuromorphic computation. For this, establishing reliable resistive switching devices working at room temperature with ease of fabrication is important. Here, a reliable analog resistive switching device based on Au/NiO nanoparticles/Au nanoparticles is discussed. The application of positive and negative voltage pulses of constant amplitude results in enhancement and reduction of synaptic current, which is consistent with potentiation and depression, respectively. The change in the conductance resulting in such a process can be fitted well with double exponential growth and decay, respectively. Consistent potentiation and depression characteristics reveal that non-ideal voltage pulses can result in a linear dependence of potentiation and depression with electric pulses. Long-term potentiation (LTP) and Long-term depression (LTD) characteristics have been established, which are essential for mimicking the biological synaptic applications. The NiO nanoparticle-based devices can also be used for controlled synaptic enhancement by optimizing the electric pulses, displaying typical learning-forgetting-relearning characteristics.","url":"https://doi.org/10.21203/rs.3.rs-2471300/v1","authors":["Keval Hadiyal","Ramakrishnan Ganesan","A. Rastogi","R. Thamankar"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-2471300/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.21203/rs.3.rs-2862199/v1","name":"A low-power vertical dual-gate neurotransistor with short-term memory for high energy-efficient neuromorphic computing","source":"preprints","abstract":"Abstract Neuromorphic computing aims to emulate the computing processes of the brain by replicating the functions of biological neural networks using electronic counterparts. One promising approach is dendritic computing, which takes inspiration from the multi-dendritic branch structure of neurons to enhance the processing capability of artificial neural networks. While there has been a recent surge of interest in implementing dendritic computing using emerging devices, achieving artificial dendrites with throughputs and energy efficiency comparable to those of the human brain has proven challenging. In this study, we report on the development of a compact and low-power neurotransistor based on a vertical dual-gate electrolyte-gated transistor (EGT) with short-term memory characteristics, a 30 nm channel length, a record-low read power of ~3.16 fW and a biology-comparable read energy of ~30 fJ. Leveraging this neurotransistor, we demonstrate dendrite integration as well as digital and analog dendritic computing for coincidence detection. We also showcase the potential of neurotransistors in realizing advanced brain-like functions by developing a hardware neural network and demonstrating bio-inspired sound localization. Our results suggest that the neurotransistor-based approach may pave the way for next-generation neuromorphic computing with energy efficiency on par with those of the brain.","url":"https://doi.org/10.21203/rs.3.rs-2862199/v1","authors":["Han Xu","Qing Luo","Junjie An","Yue Li","Shuyu Wu","Zhihong Yao","Xiaoxin Xu","Peiwen Zhang","Chunmeng Dou","Hao Jiang","Liyang Pan","Xumeng Zhang"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-2862199/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.21203/rs.3.rs-2441360/v1","name":"A Large-Dynamic-Range Violet Phosphorus Heterostructure Optoelectronic Synapse for High-Complexity Neuromorphic Computing","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-2441360/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-2441360/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.21203/rs.3.rs-901884/v1","name":"Synthetic neuromorphic computing in living cells","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-901884/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.21203/rs.3.rs-901884/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:28.407Z"},{"id":"doi:10.22541/au.169586824.40328712/v1","name":"Replicating the Bright-Light Therapy of Seasonal Affective Disorder through Dual-Gate Dielectric Synaptic Transistors: An Exploration of Neuromorphic Computing Approaches","source":"preprints","abstract":"","url":"https://doi.org/10.22541/au.169586824.40328712/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.22541/au.169586824.40328712/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.21203/rs.3.rs-1047393/v1","name":"Multi-State MRAM Cells For Hardware Neuromorphic Computing","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-1047393/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.21203/rs.3.rs-1047393/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.21203/rs.3.rs-1104630/v1","name":"Shape-Dependent Multi-Weight Magnetic Artificial Synapses for Neuromorphic Computing","source":"preprints","abstract":"Abstract In neuromorphic computing, artificial synapses provide a multi-weight conductance state that is set based on inputs from neurons, analogous to the brain. Additional properties of the synapse beyond multiple weights can be needed, and can depend on the application, requiring the need for generating different synapse behaviors from the same materials. Here, we measure artificial synapses based on magnetic materials that use a magnetic tunnel junction and a magnetic domain wall. By fabricating lithographic notches in a domain wall track underneath a single magnetic tunnel junction, we achieve 4-5 stable resistance states that can be repeatably controlled electrically using spin orbit torque. We analyze the effect of geometry on the synapse behavior, showing that a trapezoidal device has asymmetric weight updates with high controllability, while a straight device has higher stochasticity, but with stable resistance levels. The device data is input into neuromorphic computing simulators to show the usefulness of application-specific synaptic functions. Implementing an artificial neural network applied on streamed Fashion-MNIST data, we show that the trapezoidal magnetic synapse can be used as a metaplastic function for efficient online learning. Implementing a convolutional neural network for CIFAR-100 image recognition, we show that the straight magnetic synapse achieves near-ideal inference accuracy, due to the stability of its resistance levels. This work shows multi-weight magnetic synapses are a feasible technology for neuromorphic computing and provides design guidelines for emerging artificial synapse technologies.","url":"https://doi.org/10.21203/rs.3.rs-1104630/v1","authors":["Thomas Leonard","Sam Liu","Mahshid Alamdar","Can Cui","Otitoaleke Akinola","Lin Xue","Tianyao Xiao","Joseph Friedman","Matthew Marinella","Christopher Bennett","Jean Anne Incorvia"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.21203/rs.3.rs-1104630/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.22541/au.165530836.62586068/v1","name":"2D  Metal-Organic Frameworks Based Optoelectronic Neuromorphic Transistors for Human  Emotion-Simulation and Neuromorphic Computing","source":"preprints","abstract":"","url":"https://doi.org/10.22541/au.165530836.62586068/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.22541/au.165530836.62586068/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.21203/rs.3.rs-1655986/v1","name":"Thermally-stable threshold selector based on CuAg alloy for energy-efficient memory and neuromorphic computing applications","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-1655986/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.21203/rs.3.rs-1655986/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.22541/au.165476473.38204201/v1","name":"Supporting Information for \"2D  Metal-Organic Frameworks Based Optoelectronic Neuromorphic Transistors for Human  Emotion-Simulation and Neuromorphic Computing\"    ","source":"preprints","abstract":"","url":"https://doi.org/10.22541/au.165476473.38204201/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.22541/au.165476473.38204201/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1101/2020.10.27.358390","name":"Markov Chain Abstractions of Electrochemical Reaction-Diffusion in Synaptic Transmission for Neuromorphic Computing","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2020.10.27.358390","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2020","doi":"10.1101/2020.10.27.358390","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.64898/2026.07.09.737518","name":"Low-latency neuromorphic closed-loop control of hippocampal ripples  <i>in vivo</i>","source":"europepmc","abstract":"Real-time closed-loop neuromodulation, in which stimulation is precisely timed to ongoing brain dynamics, holds transformative potential for treating neurological disorders and probing neural circuit function. However, it requires low-latency, energy-efficient processing of high-bandwidth neural signals that conventional computing architectures struggle to deliver. Neuromorphic computing, which emulates the event-driven and massively parallel operation of biological neural circuits, offers a compelling alternative. Yet, its integration into closed-loop frameworks validated in vivo for fast, transient oscillations has not been demonstrated. Here, we present a fully integrated neuromorphic framework for real-time detection and manipulation of hippocampal ripples: brief (30-100 ms), high-frequency (100-250 Hz) oscillations that are critical for memory consolidation and implicated in neurological disorders. We train compact spiking neural networks comprising 41 neurons and 530 parameters using surrogate-gradient backpropagation, achieving detection performance competitive with deep learning models across 23 recording sessions while consuming up to 200-fold less energy when deployed on SpiNNaker neuromorphic hardware. Integration with the open-source Open Ephys platform yields total closed-loop latencies of approximately 50 ms, enabling intra-event stimulation in up to 80% of ripples. Validating the complete sensing-processing-stimulation pipeline in awake, head-fixed mice, we demonstrate that neuromorphic-triggered optogenetic inhibition significantly alters ripple dynamics and reduces oscillatory energy. This work establishes a practical and accessible neuromorphic framework for low-latency closed-loop control of fast brain dynamics in vivo .","url":"https://doi.org/10.64898/2026.07.09.737518","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.07.09.737518","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.21203/rs.3.rs-10560897/v1","name":"MAFA: Bio-Inspired Physics-Driven Activation Layers for Stateful In-Memory Computing","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-10560897/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-10560897/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.21203/rs.3.rs-10300384/v1","name":"Nanofluidic memristor with an ultra-low operating voltage","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-10300384/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-10300384/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.21203/rs.3.rs-10095848/v1","name":"Neuromorphic Energy-Aware Learning for Adaptive Deep Brain Stimulation","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-10095848/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-10095848/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.20944/preprints202608.1001.v1","name":"Investigating Volatile Resistive Switching in Organic Gel Electrolyte Memristors","source":"europepmc","abstract":"","url":"https://doi.org/10.20944/preprints202608.1001.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.20944/preprints202608.1001.v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.21203/rs.3.rs-9949762/v1","name":"Dual-Mode Deep-Ultraviolet Photodetection and neuromorphic vision sensor via Thermal Engineering of Oxygen Vacancies in Ga2O3","source":"europepmc","abstract":"Abstract The integration of neuromorphic vision sensors and photodetectors has attracted considerable interest. Here, a facile single-step thermal oxidation strategy is employed to fabricate Ga 2 O 3 thin films, realizing dual functionalities within a single material through differentiated oxygen vacancy (V O ) concentrations. Interestingly, this concurrent process of Ga 2 O 3 formation and V O modulation achieves a broad tunability of the V O concentration from 13.46% to 44.06%, solely through annealing temperature variation. Low-temperature (500°C) devices contain a high density of V O , and the energy barriers formed by V O photoionization give rise to a pronounced persistent photoconductivity effect. It enables the devices diverse synaptic plasticity, emulation of artificial visual memory, image filtering as preprocessing for recognition, and physical reservoir computing with 96.33% handwritten digit recognition accuracy under 10% noise. High-temperature (900°C) devices, with substantially reduced V O concentration, exhibit ultralow dark current (1.76 × 10 − 10 A), a photo-to-dark current ratio of 387.85, and fast response (rise/decay times of 0.19/0.20 s), making them excellent solar-blind photodetectors for optical communication and imaging. By vacancy tailoring, this work merges photodetection and neuromorphic computation within a single Ga 2 O 3 platform, providing a streamlined fabrication paradigm and mechanistic insights for advanced multifunctional solar-blind optoelectronics.","url":"https://doi.org/10.21203/rs.3.rs-9949762/v1","authors":["Yanqiang Cao"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-9949762/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.21203/rs.3.rs-10051531/v1","name":"Neuromorphic Satellite Intelligence: A Formal Framework for Event-Driven Architectures, Spike-Based Algorithms, and Quantitative Energy-Accuracy Trade-offs","source":"europepmc","abstract":"Abstract Satellite onboard computing faces an irreducible tension: mission intelligence requirements grow monotonically while power, mass, and radiation budgets remain fixed. This paper advances the State of the art on three fronts. First, we develop a formal mathematical model of spiking neural computation for satellite workloads, deriving closed-form expressions for energy consumption as a function of network sparsity, firing rate, and synaptic fan-out. Second, we propose three original algorithms — a Spiking Kalman-Complementary Filter (SKCF) for attitude estimation, a Temporal Contrast Anomaly Detector (TCAD) for spacecraft health monitoring, and a Spike-Based Adaptive Modulation and Coding (SAMC) scheme for cognitive satellite links — each with pseudocode and analytical complexity bounds. Third, we introduce a quantitative Energy-Accuracy-Latency (EAL) trade-off surface and populate it with numerical estimates derived from published silicon measurements of Loihi and SpiNNaker, enabling direct comparison with FPGA and GPU baselines. A taxonomy of four radiation-aware neuromorphic architecture classes is refined with fault-rate models. Continual on-orbit learning is formalized through a constrained Spike-Timing Dependent Plasticity (STDP) rule that provably bounds weight drIft. Case studies for a 12U CubeSat Earth observation mission, a GEO communications payload, and an autonomous deep-space probe provide concrete, quantIfied design points. Our analysis shows that neuromorphic implementations can achieve 8–47× energy reduction over GPU baselines while maintaining inference accuracy within 2.1\\% for representative satellite workloads.","url":"https://doi.org/10.21203/rs.3.rs-10051531/v1","authors":["Suresh Kumar TP","Vikas Agnihotri"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-10051531/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.21203/rs.3.rs-9782781/v1","name":"Spintronic Neuromorphic Hardware Using Domain Wall Based Neurons and Quantized Synapses","source":"europepmc","abstract":"Abstract In this work, we simulate the functionality of artificial neuron and synapse using spin-orbit torque-based spintronic devices and implemented a fully connected artificial neural netwrok (ANN). These neuro-synaptic devices are emulated using transverse domain wall dynamics in a rectangular magnetic nanotrack comprised of heavy metal/ferromagnet (HM/FM) heterostructures. The ReLU activation function of the neuron has been mimicked using the domain wall motion induced by a 3 ns current pulse. The synapse has been modelled using current-induced domain wall (DW) dynamics through a corrugated HM/FM nanotrack under the influence of a 10 ns current pulse with varying current density. The semicircular corrugations are in the form of notches, which are symmetrically located on both sides of the nanotrack. By applying 10 ns current pulses of varying densities, we achieve controlled DW pinning, revealing a step-like motion caused by temporary pauses at each pinning center. The electrical conductance of the pinned DW across various pinning points, act as stable synaptic weights for our ANN. Furthermore, we observe a threshold-dependent delay effect where each depinning event is influenced by previous ones, successfully mimicking synaptic memory and adaptability in neuromorphic systems. The fully connected ANN has been modeled using the conventional float32 synaptic weights for the MNIST and Fashion MNIST datasets with an accuracy of ∼ 97 % and ∼ 86 % respectively, which serves as a test bed of our neuromorphic simulations. With the aim of implementing a sparse and low memory footprint ANN, we quantize the trained synaptic weights into discrete quantized level and tested the network, which demonstrate an accuracy of ∼95% and ∼62%, for the MNIST and Fashion-MNIST dataset, respectively. Although direct quantization impacted performance, fine-tuning the network fully restored accuracies to near-baseline levels. These findings highlight the potential of engineered DW pinning-depinning dynamics for scalable, adaptive, and hardware-efficient neuromorphic computing.","url":"https://doi.org/10.21203/rs.3.rs-9782781/v1","authors":["Sakshi Kiran Bandekar","Arnab Ganguly","Debanjan Polley","Debasis Das"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-9782781/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.21203/rs.3.rs-9954113/v1","name":"Reconfigurable Multistate MRAM Synapses with Vortex STNO based Neurons for Scalable In-Memory Convolutional Neural Networks","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-9954113/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-9954113/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.21203/rs.3.rs-9562092/v1","name":"Predictive tactile coding in a memristive neuromorphic tactile system","source":"europepmc","abstract":"Abstract Flexible tactile electronics have progressed rapidly in wearable electronics, electronic skin, tactile sensing materials and neuromorphic sensory devices, yet most artificial touch systems still interpret contact only after the signal has already been measured. Such a reactive mode supports static recognition, but it is less suited to continuous interaction, where tactile sensing is embedded in the evolving contact process and must follow how surface morphology changes during scanning. Inspired by predictive processing in biological sensory systems, in which incoming signals are interpreted against an internally generated expectation of the next sensory state, we introduce a predictive tactile neuromorphic system that couples a 44×44 flexible tactile array to an 8×8 memristive array for one-step next-state estimation and mismatch-based tactile inference. We program the learned latent-state transition matrix into the memristive conductance matrix so that the current encoded tactile state can be projected in hardware to its predicted successor. In experiments, a flexible pressure sensor mounted on a robotic fingertip records the evolving contact fields during sliding. Each tactile frame is compressed into an 8-dimensional latent representation and propagated through a programmed memristive conductance matrix to generate the predicted next tactile state, which is then compared with the measured next state to produce a normalized mismatch score that quantifies the deviation between expected and observed tactile evolution. Across 1,800 scan sequences spanning smooth, coarse periodic, and fine periodic surface states with matched local violations, the system maintains low mismatch during regular tactile evolution and generates pronounced mismatch peaks when local continuity is broken. The pooled anomaly-discrimination performance reaches an ROC AUC of 0.992. The proposed predictive framework achieves a normal-region prediction error of 0.018 a.u., where normal-region refers to scan segments outside the disturbed zone, and maintains AUCs of 0.96, 0.91, and 0.87 under three speed/force perturbation settings, compared with 0.78, 0.70, and 0.66 for the no-temporal-context baseline. These results show that expectation-driven tactile inference can be embedded directly into the sensing-computing pathway and can support compact neuromorphic touch systems for robotic inspection, dexterous manipulation, and adaptive human-machine interfaces operating under continuously changing contact conditions.","url":"https://doi.org/10.21203/rs.3.rs-9562092/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-9562092/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.21203/rs.3.rs-8679088/v1","name":"Intrinsic Neuromorphic Behaviors in PEDOT/PSS Nanoscale Networks and their Enhancement via Ethylene Glycol Doping","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-8679088/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-8679088/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.21203/rs.3.rs-6505999/v1","name":"Data-In-situ Computing with One-Pixel-Multiple-Memristor Architecture for Neuromorphic Sequential Vision","source":"preprints","abstract":"Abstract Neuromorphic vision systems based on memristors offer an energy-efficient approach to artificial vision, yet traditional pixel(s)-to-one-memristor architectures remain inefficient in dynamic image processing due to limited temporary storage. Here, inspired by human visual working memory, we propose a novel one-pixel-multiple-memristor (1PnR) architecture with a rolling exposure strategy for fast sequential image acquisition. Furthermore, a data-in-situ computing network for efficient image processing is developed. With network weights mapped to voltage vectors and applied to the image storage memristor array, direct computation is enabled where the image is stored, and the energy-intensive data transmission is eliminated. A hardware prototype of the 1PnR architecture achieved 95.7% recognition accuracy on the Weizmann human action flow dataset. Compared to CMOS-based systems, this architecture is estimated to have a 2000× reduction in latency for image sensing and storage, and a 160× reduction in energy consumption image processing, demonstrating significant potential for future neuromorphic visual systems.","url":"https://doi.org/10.21203/rs.3.rs-6505999/v1","authors":["Wei Wang","Yi Sun","Peiwen Tong","Jiangrong Shen","Hui Xu","Rongrong Cao","Chang Liu","Changlin Chen","Bing Song","Yinan Wang","Yuchao Yang","Qingjiang Li"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-6505999/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.21203/rs.3.rs-8961215/v1","name":"uSense: Unary-Computing-based Stochastic Edge Neuromorphic Sensing","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-8961215/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-8961215/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.21203/rs.3.rs-9175178/v1","name":"Inductor-Stabilized Charge-Controlled Memristor Neuromorphic Circuit Design With Complex Firing Dynamics","source":"preprints","abstract":"Abstract Neuromorphic circuits based on memristive devices have attracted increasing attention for their potential to emulate biological neuronal dynamics and enable energy-efficient brain-inspired computing. In this paper, an inductor-stabilized charge-controlled memristor neuromorphic circuit is proposed to enable the practical circuit implementation of current-driven memristive neuron dynamics. By introducing an inductor in series with a charge-controlled memristor, the input characteristics are stabilized, allowing the memristor to approximately operate under current-controlled conditions in practical analog circuits. The resulting memristor–inductor structure is employed as an ion-channel element and incorporated into a neuron circuit, leading to the construction of a five-dimensional neuromorphic circuit system.The dynamical properties of the proposed circuit are systematically investigated through bifurcation diagrams and Lyapunov exponent spectra. Numerical results demonstrate that the system exhibits rich nonlinear behaviors, including periodic oscillations, period-doubling bifurcations, and chaotic firing patterns under different parameter conditions. In addition, the inductor not only stabilizes the memristor input characteristics but can also temporarily behave as a local equivalent power source, significantly influencing the system states. Finally, a PCB-based analog experimental circuit is designed and implemented to validate the proposed neuromorphic circuit model, and the experimental results agree well with numerical simulations, confirming the feasibility and effectiveness of the proposed circuit architecture.","url":"https://doi.org/10.21203/rs.3.rs-9175178/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-9175178/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.21203/rs.3.rs-8470525/v1","name":"Physical Mechanisms and Applications of High-Durability Polymer- Based Artificial Synapses Using P3DT","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-8470525/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-8470525/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.64898/2026.05.26.727630","name":"Nanostructured Zirconia thin films as neurogliomorphic interface for neural cells of central and peripheral nervous system","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.05.26.727630","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.05.26.727630","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.20944/preprints202604.1208.v1","name":"Guide to Spintronic Crossbar Arrays: From Binary Switches to Analog Computing","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202604.1208.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.20944/preprints202604.1208.v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.20944/preprints202603.0293.v1","name":"Fabrication of Stochastic Ni@PVP Nanowire Networks for Memristive Platforms","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202603.0293.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.20944/preprints202603.0293.v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.21203/rs.3.rs-9917769/v1","name":"A Synchronization-Driven Learning Rule for Pattern Separation in Self-Organizing Probabilistic Spiking Neural Networks","source":"europepmc","abstract":"Abstract Neuroscience-inspired neural networks provide a promising framework for bridging biological principles and adaptive artificial intelligence systems. Here, we propose a novel synchronization-based synaptic learning rule for self-organizing probabilistic spiking neural networks (PSNNs) with feedback inhibition. In the proposed model, synaptic plasticity is regulated by the temporal synchronization of presynaptic spike activity of single neurons, enabling unsupervised adaptation of synaptic weights and network connectivity. We systematically investigated how feedback inhibition influences network dynamics, stability, synchronization, and pattern separation efficacy. The results revealed that moderate inhibition produces an optimal balance between excitatory and inhibitory activity, maximizing pattern separation while preventing both excessive excitation and over-suppression of network activity. Comparative analysis further demonstrated that the proposed synchronization-based learning mechanism outperforms conventional Hebbian learning in achieving efficient and stable pattern separation in this neural network. Finally, the trained network was embedded in a simulated autonomous agent navigating a two-dimensional environment, where it successfully identified and avoided a learned obstacle pattern. These findings highlight the critical role of inhibitory regulation and synchronization-driven plasticity in self-organizing spiking systems and support the potential application of biologically inspired learning mechanisms in computational neuroscience, neuromorphic computing, and cognitive robotics.","url":"https://doi.org/10.21203/rs.3.rs-9917769/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-9917769/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.21203/rs.3.rs-9954563/v1","name":"Universal RKKY-like Interactions Between Tilted Skyrmions in Chiral Magnets","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-9954563/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-9954563/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.21203/rs.3.rs-8874344/v1","name":"Hardware implementation of photonic neuromorphic autonomous navigation","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-8874344/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-8874344/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.64898/2026.04.19.719429","name":"A Closer-to-Brain Heterosynaptic Learning Rule for Spatiotemporal Spike Pattern Detection with Low-Resolution Synapse","source":"preprints","abstract":"The brain is believed to process information efficiently in a different manner from deep learning-based artificial intelligence (AI). Brain-like next-generation AI is gaining attention owing to its potential to perform human-like, highly adaptive, robust, and power-efficient computation. To realize such AI, one crucial approach is the bottom-up implementation of the neuronal systems, capturing their electrophysiological characteristics in electronic circuits. However, this neuromorphic approach generally focuses on simplified neuronal models that do not refer to many biological findings. Developing closer-to-brain models is a natural direction that serve as a fundamental computing model for next-generation AI. One of the constraints of neuromorphic circuits is the bit resolution of synaptic efficacy memory, as the memory footprint scales with it precision. Although low-resolution synaptic efficacy is essential for minimizing memory circuit footprint and energy consumption, it generally leads to performance degradation in many tasks such as the spatio-temporal spike pattern detection. This study proposed a closer-to-brain learning rule that incorporates heterosynaptic plasticity (HP) induced by glutamate spillover. It is demonstrated that our model mitigates the performance degradation associated with low-bit resolution synaptic efficacy, achieving the pattern detection success rate with 3-bit resolution synaptic efficacy, which is comparable to 64-bit floating-point precision. Furthermore, the findings of the study indicate that HP based model accelerates the convergence of the synaptic effcacy and effectively potentiates the synapses relevant to the pattern detection while suppressing irrelevant ones, thereby promoting a bimodal distribution of synaptic efficacies. These findings may provide a basic framework for constructing an energy-efficient, brain-like next-generation AI that maintains high performance under hardware constraints.","url":"https://doi.org/10.64898/2026.04.19.719429","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.04.19.719429","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.20944/preprints202607.0410.v1","name":"Self-Contrastive Single-Forward Learning for Efficient Forward-Forward Unsupervised Representation Learning","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202607.0410.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.20944/preprints202607.0410.v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.21203/rs.3.rs-9370190/v1","name":"DelRec: learning delays in recurrent spiking neural networks","source":"preprints","abstract":"Abstract Biological neurons transmit information with stereotyped electrical impulses called ``spikes'', sensitive to coincident timings. Spiking Neural Networks (SNNs), introduced in the nineties, have gained popularity in AI for their energy efficiency and competitive performance with deep learning. Among them, Recurrent SNNs (RSNNs) are particularly appealing for their ability to learn long-term dependencies and exhibit rich dynamics. In SNNs, each connection can have a weight and a transmission delay, both plastic in the brain. While theory has long suggested that trainable delays enhance a network's expressivity, practical learning methods emerged only recently and remain mostly limited to feedforward delays. Here, we introduce DelRec, the first method to jointly optimize recurrent delays with synaptic weights in RSNNs via surrogate gradient learning, compatible with any spiking neuron model. DelRec works in discrete time, leveraging differentiable interpolation to handle non-integer delays with well-defined gradients at training time, then rounding them for inference. Using simple neurons, DelRec outperforms all baselines on a chaotic time-series prediction task, and sets new state-of-the-art accuracies on two challenging temporal datasets. Analysis of trained networks reveals structured, depth-dependent spatio-temporal receptive fields and delay-weight co-adaptation reshaping temporal selectivity. This work establishes recurrent delay optimization as a promising framework for both biological circuit modeling and neuromorphic computing.","url":"https://doi.org/10.21203/rs.3.rs-9370190/v1","authors":["Alexandre Queant","Ulysse Rancon","Benoit COTTEREAU","Timothée Masquelier"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-9370190/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.21203/rs.3.rs-9248715/v1","name":"Linking Device Dynamics to Neural Network Performance in Ionically Gated Synaptic Transistors","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-9248715/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-9248715/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.21203/rs.3.rs-9253312/v1","name":"Spatiotemporal Ferro-Ionic Dynamics in Van der Waals Ferroelectrics","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-9253312/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-9253312/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.20944/preprints202603.2189.v1","name":"SE-SNN: Squeeze-and-Excitation Enhanced Spiking Neural Networks with Learnable Neuron Dynamics for Event-Based Vision","source":"preprints","abstract":"Spiking Neural Networks (SNNs) have emerged as a promising paradigm for energy-efficient neuromorphic computing, particularly when processing asynchronous event streams from dynamic vision sensors (DVS). However, SNNs often suffer from limited representational capacity and suboptimal feature recalibration compared to their artificial counterparts. To address these challenges, we propose SE-SNN, a novel architecture that integrates Squeeze-and-Excitation (SE) blocks into deep residual SNNs, enabling channel-wise attention without spike generation in the gating mechanism. Furthermore, we introduce a Robust Parametric Leaky Integrate-and-Fire (RobustPLIF) neuron model with learnable membrane time constant (τ) and firing threshold (Vth), allowing adaptive temporal dynamics per layer. Our model is trained on the CIFAR10-DVS dataset.Experimental results demonstrate that SE-SNN achieves state-of-the-art accuracy of 78.8 % on CIFAR10-DVS with only 16 time steps, significantly outperforming baseline SNNs while maintaining biological plausibility and hardware efficiency. Ablation studies confirm the individual contributions of SE blocks and learnable neuron parameters to performance gains.","url":"https://doi.org/10.20944/preprints202603.2189.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.20944/preprints202603.2189.v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.168Z"},{"id":"doi:10.20944/preprints202309.1149.v3","name":"Critical Review of Neural Network Generations and Models Design","source":"europepmc","abstract":"","url":"https://doi.org/10.20944/preprints202309.1149.v3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.20944/preprints202309.1149.v3","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.21203/rs.3.rs-7782397/v1","name":"Ionic Driven Waveguide Integrated Memristor","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-7782397/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-7782397/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.21203/rs.3.rs-8911506/v1","name":"Information Abstraction for Data Transmission Networks based on Large Language Models","source":"preprints","abstract":"Abstract Biological systems, particularly the human brain, achieve remarkable energy efficiency by abstracting information across multiple hierarchical levels. In contrast, modern artificial intelligence and communication systems often consume significant energy overheads in transmitting low-level data, with limited emphasis on abstraction. Despite its implicit importance, a formal and computational theory of information abstraction remains absent. In this work, we introduce the Degree of Information Abstraction (DIA), a general metric that quantifies how well a representation compresses input data while preserving task-relevant semantics. We derive a tractable information-theoretic formulation of DIA and propose a DIA-based information abstraction framework. As a case study, we apply DIA to a large language model (LLM)-guided video transmission task, where abstraction-aware encoding significantly reduces transmission volume by $99.75\\%$, while maintaining semantic fidelity. Our results suggest that DIA offers a principled tool for rebalancing energy and information in intelligent systems and opens new directions in neural network design, neuromorphic computing, semantic communication, and joint sensing-communication architectures.","url":"https://doi.org/10.21203/rs.3.rs-8911506/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-8911506/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.168Z"},{"id":"doi:10.64898/2026.03.12.711455","name":"Evolutionarily Optimized Network Topology as a Structural Prior for Data-Efficient Sparse Neural Classification","source":"preprints","abstract":"Biological neural systems have been refined over millions of years of evolutionary optimization to maximize information processing under metabolic and developmental constraints, yielding network topologies with characteristic structural signatures: sparse connectivity, small-world organization, and modular architecture. Whether these evolutionarily derived structural properties constitute transferable inductive biases for artificial learning systems is unknown. Here we test this hypothesis directly by initializing sparse multilayer perceptrons from biologically derived adjacency matrices spanning molecular, structural, functional, and behavioral interaction networks and comparing their performance against synthetic alternatives matched for sparsity but lacking evolutionary structural organization. Biologically pre-initialized networks consistently outperformed both fully connected baselines and synthetic sparse alternatives across four classification benchmarks, achieving approximately 90% classification accuracy with as little as 25% of available training data. Systematic comparisons against randomly rewired, degree-preserved, and Watts–Strogatz small-world networks with matched sparsity establish that topology, not connection density, drives these advantages: higher-order structural features encoded by evolutionary optimization, including local clustering, modular organization, and hub connectivity, provide inductive biases unavailable from random sparse graphs. These findings establish evolutionarily optimized network topology as a principled structural prior for artificial neural architectures, with direct implications for neuromorphic computing, edge-deployed machine learning, and the broader program of brain-inspired artificial intelligence. Significance Statement Biological nervous systems and gene regulatory networks have been shaped by millions of years of evolution to generalize efficiently from limited experience under tight resource constraints, precisely the challenge that confronts machine learning systems in data-scarce settings. We show that the global wiring topology produced by this evolutionary process can be transplanted directly into artificial classifiers to confer substantial data efficiency: networks pre-wired from biological blueprints achieve approximately 90% classification accuracy using only a fraction of the training data required by conventional architectures. The advantage cannot be explained by sparsity alone, the evolutionarily shaped organization of those connections is the active ingredient. Evolution, it appears, has solved a version of the sparse learning problem that artificial intelligence is still working on.","url":"https://doi.org/10.64898/2026.03.12.711455","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.03.12.711455","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.168Z"},{"id":"doi:10.21203/rs.3.rs-9074559/v1","name":"Electric field switching of chiral phonons","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-9074559/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-9074559/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:23.168Z"},{"id":"doi:10.21203/rs.3.rs-3300928/v1","name":"High Storage and Energy Efficient Memory for Cryogenic Computing","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3300928/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-3300928/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:20.542Z"},{"id":"doi:10.20944/preprints202310.1213.v1","name":"Signal Filtering Using Neuromorphic Measurements","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202310.1213.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.20944/preprints202310.1213.v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:20.542Z"},{"id":"doi:10.21203/rs.3.rs-3777764/v1","name":"Emergent nonlinear modes in coherent magnon circuits detected at ultrahigh frequency resolution","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3777764/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-3777764/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:20.542Z"},{"id":"doi:10.20944/preprints202306.0438.v1","name":"Neuromorphic Dendritic Computation with Silent Synapses for Visual Motion Perception","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202306.0438.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.20944/preprints202306.0438.v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:20.542Z"},{"id":"doi:10.21203/rs.3.rs-2651639/v1","name":"The neuromorphic Mosaic: in-memory computing and routing for small-world graphical networks","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-2651639/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-2651639/v1","addedAt":"2026-09-01T01:48:19.730Z","updatedAt":"2026-09-01T01:48:20.542Z"},{"id":"doi:10.1007/978-3-031-71097-1","name":"Revolutionizing Civil Engineering with Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-71097-1","authors":["Ali Akbar Firoozi","Ali Asghar Firoozi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-12T15:02:54Z","doi":"10.1007/978-3-031-71097-1","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1063/5.0285089","name":"Learning chaotic dynamics with neuromorphic network dynamics","source":"crossref","abstract":"This study investigates how dynamical systems may be learned and modeled with a neuromorphic network, which is itself a dynamical system. The neuromorphic network used in this study is based on a complex electrical circuit comprised of memristive elements that produce neuro-synaptic nonlinear responses to input electrical signals. To determine how computation may be performed using the physics of the underlying system, the neuromorphic network was simulated and evaluated on the autonomous prediction of a multivariate chaotic time series, implemented with a reservoir computing framework. Through manipulating only input electrodes and voltages, optimal nonlinear dynamical responses were found when input voltages maximize the number of memristive components whose internal dynamics explore the entire dynamical range of the memristor model. Increasing the network coverage with the input electrodes was found to suppress other nonlinear responses that are less conducive to learning. These results provide valuable insights into how a physical neuromorphic network device can be feasibly optimized for learning complex dynamical systems using only external control parameters.","url":"https://doi.org/10.1063/5.0285089","authors":["Yinhao Xu","Georg A. Gottwald","Zdenka Kuncic"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-23T13:19:53Z","doi":"10.1063/5.0285089","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1088/2634-4386/adf2d4/v2/response1","name":"Author response for \"End-to-end neuromorphic speech enhancement with PDM microphones\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2634-4386/adf2d4/v2/response1","authors":["Sidi Yaya Arnaud Yarga","Sean U. N. Wood"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-23T21:05:53Z","doi":"10.1088/2634-4386/adf2d4/v2/response1","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1088/2634-4386/ad473b","name":"Spike-based computation using classical recurrent neural networks","source":"crossref","abstract":"Abstract Spiking neural networks (SNNs) are a type of artificial neural networks in which communication between neurons is only made of events, also called spikes. This property allows neural networks to make asynchronous and sparse computations and therefore drastically decrease energy consumption when run on specialized hardware. However, training such networks is known to be difficult, mainly due to the non-differentiability of the spike activation, which prevents the use of classical backpropagation. This is because state-of-the-art SNNs are usually derived from biologically-inspired neuron models, to which are applied machine learning methods for training. Nowadays, research about SNNs focuses on the design of training algorithms whose goal is to obtain networks that compete with their non-spiking version on specific tasks. In this paper, we attempt the symmetrical approach: we modify the dynamics of a well-known, easily trainable type of recurrent neural network (RNN) to make it event-based. This new RNN cell, called the spiking recurrent cell, therefore communicates using events, i.e. spikes, while being completely differen-tiable. Vanilla backpropagation can thus be used to train any network made of such RNN cell. We show that this new network can achieve performance comparable to other types of spiking networks in the MNIST benchmark and its variants, the Fashion-MNIST and the Neuromorphic-MNIST. Moreover, we show that this new cell makes the training of deep spiking networks achievable.","url":"https://doi.org/10.1088/2634-4386/ad473b","authors":["Florent De Geeter","Damien Ernst","Guillaume Drion"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-03T22:27:50Z","doi":"10.1088/2634-4386/ad473b","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1117/12.3003259","name":"Exploring nonlinear activation function within microring resonators for all-photonic neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3003259","authors":["Sarah Sharif","Hossein Karimkhani","Yaser M. Banad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-11T19:01:37Z","doi":"10.1117/12.3003259","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1039/d5ma01008j/v2/review1","name":"Review for \"Controlling the phase transition dynamics of GeTe by Sn substitution for phase change memory, photodetection and neuromorphic devices\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5ma01008j/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-28T21:10:51Z","doi":"10.1039/d5ma01008j/v2/review1","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1088/2634-4386/ad8c78","name":"Unsupervised end-to-end training with a self-defined target","source":"crossref","abstract":"Abstract Designing algorithms for versatile AI hardware that can learn on the edge using both labeled and unlabeled data is challenging. Deep end-to-end training methods incorporating phases of self-supervised and supervised learning are accurate and adaptable to input data but self-supervised learning requires even more computational and memory resources than supervised learning, too high for current embedded hardware. Conversely, unsupervised layer-by-layer training, such as Hebbian learning, is more compatible with existing hardware but does not integrate well with supervised learning. To address this, we propose a method enabling networks or hardware designed for end-to-end supervised learning to also perform high-performance unsupervised learning by adding two simple elements to the output layer: winner-take-all selectivity and homeostasis regularization. These mechanisms introduce a ‘self-defined target’ for unlabeled data, allowing purely unsupervised training for both fully-connected and convolutional layers using backpropagation or equilibrium propagation on datasets like MNIST (up to 99.2%), Fashion-MNIST (up to 90.3%), and SVHN (up to 81.5%). We extend this method to semi-supervised learning, adjusting targets based on data type, achieving 96.6% accuracy with only 600 labeled MNIST samples in a multi-layer perceptron. Our results show that this approach can effectively enable networks and hardware initially dedicated to supervised learning to also perform unsupervised learning, adapting to varying availability of labeled data.","url":"https://doi.org/10.1088/2634-4386/ad8c78","authors":["Dongshu Liu","Jérémie Laydevant","Adrien Pontlevy","Damien Querlioz","Julie Grollier"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-29T22:54:28Z","doi":"10.1088/2634-4386/ad8c78","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1039/d5ma01008j/v1/review2","name":"Review for \"Controlling the phase transition dynamics of GeTe by Sn substitution for phase change memory, photodetection and neuromorphic devices\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5ma01008j/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-28T21:10:51Z","doi":"10.1039/d5ma01008j/v1/review2","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1109/icnc64304.2024.10987596","name":"Event-Triggered Observer-Based Fixed-Time Consensus Control for Uncertain Nonlinear Multiagent Systems with Unknown States","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987596","authors":["Kewei Zhou","Ziming Wang","Zhihao Chen","Xin Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987596","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1007/s10586-023-04093-9","name":"A low-cost, high-throughput neuromorphic computer for online SNN learning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s10586-023-04093-9","authors":["Ali Siddique","Mang I. Vai","Sio Hang Pun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-08T15:02:18Z","doi":"10.1007/s10586-023-04093-9","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1007/978-3-031-65549-4_2","name":"Theoretical Foundations","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-65549-4_2","authors":["Ali Akbar Firoozi","Ali Asghar Firoozi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-26T13:01:53Z","doi":"10.1007/978-3-031-65549-4_2","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.3389/fncom.2024.1455530","name":"Editorial: Understanding and bridging the gap between neuromorphic computing and machine learning, volume II","source":"crossref","abstract":"","url":"https://doi.org/10.3389/fncom.2024.1455530","authors":["Lei Deng","Huajin Tang","Kaushik Roy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-03T04:39:11Z","doi":"10.3389/fncom.2024.1455530","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1088/2634-4386/ad5c96","name":"Learning fast while changing slow in spiking neural networks","source":"crossref","abstract":"Abstract Reinforcement learning (RL) faces substantial challenges when applied to real-life problems, primarily stemming from the scarcity of available data due to limited interactions with the environment. This limitation is exacerbated by the fact that RL often demands a considerable volume of data for effective learning. The complexity escalates further when implementing RL in recurrent spiking networks, where inherent noise introduced by spikes adds a layer of difficulty. Life-long learning machines must inherently resolve the plasticity-stability paradox. Striking a balance between acquiring new knowledge and maintaining stability is crucial for artificial agents. To address this challenge, we draw inspiration from machine learning technology and introduce a biologically plausible implementation of proximal policy optimization, referred to as lf-cs (learning fast changing slow). Our approach results in two notable advancements: firstly, the capacity to assimilate new information into a new policy without requiring alterations to the current policy; and secondly, the capability to replay experiences without experiencing policy divergence. Furthermore, when contrasted with other experience replay techniques, our method demonstrates the added advantage of being computationally efficient in an online setting. We demonstrate that the proposed methodology enhances the efficiency of learning, showcasing its potential impact on neuromorphic and real-world applications.","url":"https://doi.org/10.1088/2634-4386/ad5c96","authors":["Cristiano Capone","Paolo Muratore"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-27T22:26:09Z","doi":"10.1088/2634-4386/ad5c96","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/icm66518.2025.11321320","name":"Dataflow-Driven Neuromorphic Architectures for Edge AI: Theory, Design, and Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icm66518.2025.11321320","authors":["Bokyung Kim","Parshva Mehta","Yiran Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-12T18:21:00Z","doi":"10.1109/icm66518.2025.11321320","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1007/978-981-97-4445-9_5","name":"Design of Artificial Neural Networks (ANN) with Domain-Wall Synapse Devices","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-4445-9_5","authors":["Debanjan Bhowmik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-15T14:02:06Z","doi":"10.1007/978-981-97-4445-9_5","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1016/b978-0-323-98829-2.00003-7","name":"Advanced neuromorphic models","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-323-98829-2.00003-7","authors":["Wenju Wang","Gang Chen","Haoran Zhou","Elena Goi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-21T06:48:32Z","doi":"10.1016/b978-0-323-98829-2.00003-7","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/naecon65708.2025.11235345","name":"Neuromorphic UAS Object Avoidance and Path Detection Using DroNet","source":"crossref","abstract":"","url":"https://doi.org/10.1109/naecon65708.2025.11235345","authors":["Brian Millikan","Lauren Reinerman-Jones","Daniel Barber"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-17T18:39:19Z","doi":"10.1109/naecon65708.2025.11235345","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.54254/2755-2721/2025.19928","name":"Research Progress of Neuromorphic Chips","source":"crossref","abstract":"The increasing amount of data in the era of artificial intelligence imposes higher demands on the computational power of neural networks, and in order to fulfill this demand, there is a pressing need to overcome the limitations imposed by the von Neumann architecture's memory wall. Memristors, with their characteristics, are considered the optimal electronic devices for implementing neuromorphic computing. Therefore, in order to better utilize memristors for the design and research of neuromorphic chips, this paper summarizes and comparatively analyzes the memristor characteristics, the RRAM basic principles, memristor array research, crossbar array designs based on memristors, and the study of memristor-based neuromorphic computing chips through the review. The paper emphasizes the challenges that memristor-based neuromorphic computing chips still face in the future, such as non-linear resistance variation. In addition, potential future research directions for amnesia-based neuromorphic computing chips, including amnesia architecture, programming techniques, and instruction set development, are discussed and investigated","url":"https://doi.org/10.54254/2755-2721/2025.19928","authors":["Luwei Fan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-10T04:48:26Z","doi":"10.54254/2755-2721/2025.19928","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1109/icnc64304.2024.10987626","name":"Handling Stability Hierarchical Control of Distributed Drive Electric Vehicle Based on Adaptive Dynamic Programming","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987626","authors":["Yidi Deng","Lan Zhou","Jinjun Wu","Zhu Zhang","Wenbin Xiao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987626","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/piers62282.2024.10617920","name":"Artificial Photonic Hetero-synapses Based on ZnO/IGZO Heterojunction for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/piers62282.2024.10617920","authors":["Wenxiao Wang","Yang Li","Jiewei Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-09T17:18:24Z","doi":"10.1109/piers62282.2024.10617920","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1145/3354265.3354285","name":"Dynamic Programming with Spiking Neural Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3354265.3354285","authors":["James B. Aimone","Ojas Parekh","Cynthia A. Phillips","Ali Pinar","William Severa","Helen Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-09-12T14:21:08Z","doi":"10.1145/3354265.3354285","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/icassp.2019.8682960","name":"Training Dynamic Exponential Family Models with Causal and Lateral Dependencies for Generalized Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icassp.2019.8682960","authors":["Hyeryung Jang","Osvaldo Simeone"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-04-17T16:01:56Z","doi":"10.1109/icassp.2019.8682960","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/cscs59211.2023.00067","name":"Efficient training models of Spiking Neural Networks deployed on a neuromorphic computing architectures","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cscs59211.2023.00067","authors":["Laura Capatina","Alexandra Cernian","Mihnea Alexandru Moisescu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-17T17:20:48Z","doi":"10.1109/cscs59211.2023.00067","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1515/9783111545950-002","name":"182 Fundamental concepts of non-equilibrium Green’s function (NEGF)","source":"crossref","abstract":"","url":"https://doi.org/10.1515/9783111545950-002","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-06T19:15:47Z","doi":"10.1515/9783111545950-002","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.29363/nanoge.matsusfall.2025.319","name":"Oriented Layered Perovskites for Neuromorphic Devices","source":"crossref","abstract":"","url":"https://doi.org/10.29363/nanoge.matsusfall.2025.319","authors":["Shahzada Ahmad","Dani S. Assi","Mahdi Gassara","Samrana Kazim","Vellaisamy A. L. Roy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-17T09:40:46Z","doi":"10.29363/nanoge.matsusfall.2025.319","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1007/978-981-97-4445-9_3","name":"Introduction to Artificial Neural Networks (ANN) and Spiking Neural Networks (SNN)","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-4445-9_3","authors":["Debanjan Bhowmik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-15T14:02:06Z","doi":"10.1007/978-981-97-4445-9_3","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1017/cbo9780511994838.002","name":"History and potential of neuromorphic robotics","source":"crossref","abstract":"","url":"https://doi.org/10.1017/cbo9780511994838.002","authors":["Jeffrey L. Krichmar","Hiroaki Wagatsuma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-02-06T06:03:07Z","doi":"10.1017/cbo9780511994838.002","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.29363/nanoge.neumatdecas.2023.017","name":"Organic neuromorphic electronics for learning, sensing and biointerfacing","source":"crossref","abstract":"","url":"https://doi.org/10.29363/nanoge.neumatdecas.2023.017","authors":["Paschalis Gkoupidenis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-02-01T09:31:42Z","doi":"10.29363/nanoge.neumatdecas.2023.017","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/icrc60800.2023.10386808","name":"An FPGA-Based Neuromorphic Processor with All-to-All Connectivity","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icrc60800.2023.10386808","authors":["Disha Maheshwari","Aaron Young","Prasanna Date","Shruti Kulkarni","Brett Witherspoon","Narsinga Rao Miniskar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-15T20:56:12Z","doi":"10.1109/icrc60800.2023.10386808","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1007/978-3-032-09586-2_7","name":"Conclusion","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-09586-2_7","authors":["Felix Staudigl","Rainer Leupers"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-22T14:21:54Z","doi":"10.1007/978-3-032-09586-2_7","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1109/insect68872.2026.11663906","name":"Co-Design of Low-Power Neuromorphic VLSI Circuits Using Emerging Memory Devices for Edge Intelligence","source":"crossref","abstract":"","url":"https://doi.org/10.1109/insect68872.2026.11663906","authors":["Priya Vij","Ashu Nayak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-31T19:14:00Z","doi":"10.1109/insect68872.2026.11663906","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1016/b978-0-323-98829-2.00007-4","name":"2D neuromorphic photonics","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-323-98829-2.00007-4","authors":["Wen Zhou","James Tan","Johannes Feldmann","Harish Bhaskaran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-18T15:12:19Z","doi":"10.1016/b978-0-323-98829-2.00007-4","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1016/b978-0-323-98829-2.00008-6","name":"Large-scale neuromorphic systems enabled by integrated photonics","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-323-98829-2.00008-6","authors":["Weihong Shen","Qiming Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-18T15:12:33Z","doi":"10.1016/b978-0-323-98829-2.00008-6","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1039/d5cs01222h/v1/decision1","name":"Decision letter for \"From Solar Cells to Memristors: Halide Perovskites as a Platform for Neuromorphic Electronics\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5cs01222h/v1/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-03T21:08:48Z","doi":"10.1039/d5cs01222h/v1/decision1","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1002/aisy.202500223","name":"A Field Programmable Gate Array‐Assisted Optoelectronic Emulator for Photonic Neuromorphic Computing","source":"crossref","abstract":"As the pace of complementary metal oxide semiconductor (CMOS) scaling slows down and Moore's law approaches its limit, optoelectronics has emerged as a promising solution for next‐generation computing hardware. Optoelectronic systems are appealing due to their fast speed, large bandwidth, low power consumption, and CMOS‐compatible fabrication process. Nevertheless, the absence of efficient design and verification tools in the prefabrication phase poses obstacles to the transition from design to practical applications. To address these hurdles, an optoelectronic emulator is created that combines well‐established optical components with a field programmable gate array. The emulator can execute multiplication operations within the optical domain with a precision of up to 6 bits and at a high frequency reaching 20 GHz. By leveraging this system, various image convolution and inference learning tasks have been effectively carried out. This accomplishment serves as a compelling demonstration of its capability to execute fundamental learning tasks, which is in line with the requirements for hardware simulations of photonic neuromorphic computing. The emulator plays a crucial role in bridging the gap between simulations and real‐world systems. It has the potential to boost the precision and reliability of future optoelectronic system design.","url":"https://doi.org/10.1002/aisy.202500223","authors":["Jinxian Li","Runyu Hu","Fengyu Wang","Jiabin Shen","Zengguang Cheng","Peng Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-23T09:38:26Z","doi":"10.1002/aisy.202500223","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1021/acs.nanolett.3c04577.s001","name":"Novel Three-Dimensional Artificial Neural Network Based on an Eight-Layer Vertical Memristor with an Ultrahigh Rectify Ratio (&gt;107) and an Ultrahigh Nonlinearity (&gt;105) for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.3c04577.s001","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-05T14:10:16Z","doi":"10.1021/acs.nanolett.3c04577.s001","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/irps45951.2020.9129638","name":"Reliability Aspects of SONOS Based Analog Memory for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/irps45951.2020.9129638","authors":["K. Ramkumar","V. Prabhakar","V. Agrawal","L. Hinh","S. Saha","S. Samanta","R. M. Kapre"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-30T21:20:26Z","doi":"10.1109/irps45951.2020.9129638","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1149/ma2025-02341691mtgabs","name":"<i>(Invited)</i>\n                    Low-Dimensional Neuromorphic Electronic Materials and Applications","source":"crossref","abstract":"The exponentially improving performance of digital computers has recently slowed due to power consumption issues resulting from the von Neumann bottleneck. In contrast, neuromorphic computing circumvents these limitations by spatially co-locating logic and memory in a manner analogous to biological neuronal networks [1]. This talk will explore how low-dimensional nanoelectronic materials enable gate-tunable neuromorphic devices. For example, by utilizing self-aligned, atomically thin heterojunctions, dual-gated Gaussian transistors have been realized, which show tunable anti-ambipolarity for artificial spiking neurons and mixed-kernel support vector machines [2]. Charge transfer in van der Waals interfacial junction transistors provides further opportunities for tailoring doping profiles to enable hardware-efficient reconfigurable fuzzy logic and fuzzy neural networks [3]. In addition, field-driven defect motion in polycrystalline monolayer MoS 2 yields gate-tunable memristive phenomena for memtransistors that concurrently achieve logic and memory functions. The planar geometry of memtransistors further allows multiple contacts that mimic the behavior of biological systems such as heterosynaptic responses. Moreover, control over polycrystalline grain structure enhances the tunability of potentiation and depression for unsupervised continuous learning in spiking neural networks [4]. Finally, the moiré potential in asymmetric twisted bilayer graphene/hexagonal boron nitride heterostructures gives rise to robust room-temperature electronic ratchet states that underlie diverse bio-realistic neuromorphic functionalities [5]. By extending these strategies to magnetically ordered low-dimensional semiconductors, additional opto-spintronic degrees of freedom can be exploited for neuromorphic function [6]. [1] S. Hadke, et al., Chemical Reviews, 125, 835 (2025). [2] X. Yan, et al., Nature Electronics, 6, 862 (2023). [3] H. Liu, et al., Nature Electronics, 7, 876 (2024). [4] X. Yan, et al., Advanced Materials, 34, 2108025 (2022). [5] X. Yan, et al., Nature, 624, 551 (2023). [6] J. T. Gish, et al., Nature Electronics, 7, 336 (2024).","url":"https://doi.org/10.1149/ma2025-02341691mtgabs","authors":["Mark C Hersam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-24T08:16:10Z","doi":"10.1149/ma2025-02341691mtgabs","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1016/j.ifacol.2025.10.206","name":"Biologically-Inspired Self-Tuning Neuromorphic PID Control for Real-Time Trajectory Tracking of a UAS","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.ifacol.2025.10.206","authors":["A. Olivares Cruz","E.S. Espinoza","L.E. Ramos Velasco","O.A. García Alcántara","L.R. Garcia Carrillo","I. Rubio Scola"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-10T23:42:36Z","doi":"10.1016/j.ifacol.2025.10.206","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1109/nano58406.2023.10231230","name":"A Novel Flexible Artificial Synapse Based on Pseudocapacitor for High-Accuracy Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nano58406.2023.10231230","authors":["B.F. Yang","D. Wang","J. Wang","Z.Y. Zhou","X.D. Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-01T17:23:28Z","doi":"10.1109/nano58406.2023.10231230","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/icnc59488.2023.10462764","name":"A Novel Method of Fixed-time Synchronization of Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462764","authors":["Jian Xiao","Yiyin Hu","Rongli Shao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462764","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1088/2634-4386/ae7ea7","name":"Noise-based reward-modulated learning","source":"crossref","abstract":"Abstract The pursuit of energy-efficient and adaptive artificial intelligence (AI) has positioned neuromorphic computing as a promising alternative to conventional computing. However, achieving learning on these platforms requires techniques that prioritize local information while enabling effective credit assignment. Here, we propose noise-based reward-modulated learning (NRL), a novel synaptic plasticity rule that mathematically unifies reinforcement learning and gradient-based optimization with biologically-inspired local updates. NRL addresses the computational bottleneck of exact gradients by approximating them through stochastic neural activity, transforming the inherent noise of biological and neuromorphic substrates into a functional resource. Drawing inspiration from biological learning, our method uses reward prediction errors as its optimization target to generate increasingly advantageous behavior, and eligibility traces to facilitate retrospective credit assignment. Experimental validation on reinforcement tasks, featuring immediate and delayed rewards, shows that NRL achieves performance comparable to baselines optimized using backpropagation, although with slower convergence, while showing significantly superior performance and scalability in multi-layer networks compared to reward-modulated Hebbian learning, the most prominent similar approach. While tested on simple architectures, the results highlight the potential of noise-driven, brain-inspired learning for low-power adaptive systems, particularly in computing substrates with locality constraints. NRL offers a theoretically grounded paradigm well-suited for the event-driven characteristics of next-generation neuromorphic AI.","url":"https://doi.org/10.1088/2634-4386/ae7ea7","authors":["Jesús García Fernández","Nasir Ahmad","Marcel van Gerven"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-17T22:50:26Z","doi":"10.1088/2634-4386/ae7ea7","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1088/1361-6463/ae01b5","name":"Self-compliance and forming-free memristor arrays with a SiO<sub>2</sub> scavenging barrier for energy-efficient neuromorphic computing","source":"crossref","abstract":"Abstract In this work, low-power RRAM (Resistive random-access memory) devices were characterized by a SiO 2 layer serving as an oxygen scavenging barrier, which suppresses conductive filament overgrowth and reduces operation current and power consumption. Additionally, the integration of an AlO x /TiO y overshoot suppression layer enabled intrinsic self-compliance and forming-free operation. XPS analysis confirmed the oxygen composition of the oxygen-rich TiO y , and it was also verified that the higher oxygen composition in TiO y suppresses filament formation, which decreases the operation current. Consequently, the SiO 2 layer decreases the LRS current significantly by 10 3 times. Furthermore, the device demonstrates the endurance of 6 × 10 3 cycles and retention over 10 4 s, maintaining analog multi-bit operation. When the proposed device was integrated into an 8 × 8 passive array and programmed with the designated weights, a low mean absolute error (MAE) of 10.8 nA was achieved. Additionally, vector-matrix multiplication operations demonstrated excellent accuracy, with over 99% of results falling within an error margin of 10%. Based on this low MAE, MNIST image classification simulations were conducted, yielding classification accuracy exceeding 96%.","url":"https://doi.org/10.1088/1361-6463/ae01b5","authors":["Minki Kim","Sungjoon Kim","Sungmin Hwang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-02T22:48:43Z","doi":"10.1088/1361-6463/ae01b5","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1088/2634-4386/ae0fc0","name":"Benchmarking spiking neurons for linear quadratic regulator control of multi-linked pole on a cart: from single neuron to ensemble","source":"crossref","abstract":"Abstract The emerging field of neuromorphic computing for edge control applications poses the need to quantitatively estimate and limit the number of spiking neurons, to reduce network complexity and optimize the number of neurons per core and hence, the chip size, in an application-specific neuromorphic hardware. While rate-encoding for spiking neurons provides a robust way to encode signals with the same number of neurons as an ANN, it often lacks precision. To achieve the desired accuracy, a population of neurons is often needed to encode the complete range of input signals. However, using population encoding immensely increases the total number of neurons required for a particular application, thus increasing the power consumption and on-board resource utilization. A transition from two neurons to a population of neurons for the linear quadratic regulator (LQR) control of a cartpole is shown in this work. The near-linear behavior of a leaky-integrate-and-fire neuron can be exploited to achieve the LQR control of a cartpole system. This has been shown in simulation, followed by a demonstration on a single-neuron hardware, known as Lu.i. The improvement in control performance is then demonstrated by using a population of varying numbers of neurons for similar control in the Nengo neural engineering framework (NEF), on CPU and on Intel’s Loihi neuromorphic chip. Finally, linear control is demonstrated for four multi-linked pendula on cart systems, using a population of neurons in Nengo, followed by an implementation of the same on Loihi. This study compares LQR control in the NEF using 7 control and 7 neuromorphic performance metrics, followed by a comparison with other conventional spiking and non-spiking controllers.","url":"https://doi.org/10.1088/2634-4386/ae0fc0","authors":["Shreyan Banerjee","Luna Gava","Aasifa Rounak","Vikram Pakrashi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-06T22:50:06Z","doi":"10.1088/2634-4386/ae0fc0","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1109/wmvc.2009.5399241","name":"Activity recognition by integrating the physics of motion with a Neuromorphic model of perception","source":"crossref","abstract":"","url":"https://doi.org/10.1109/wmvc.2009.5399241","authors":["Ricky J. Sethi","Amit K. Roy-Chowdhury","Saad Ali Robotics"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-02-02T15:27:37Z","doi":"10.1109/wmvc.2009.5399241","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1088/2634-4386/ae65d6","name":"Efficient aspect term extraction using spiking neural network","source":"crossref","abstract":"Abstract Aspect term extraction (ATE) identifies aspect terms in review sentences, a key subtask of sentiment analysis. It is a sequence labeling task that aims to identify aspect expressions within opinionated text. While most existing approaches predominantly rely on deep neural networks (DNNs), which achieve strong performance but incur high computational and energy costs. In this work, we propose SpikeATE, an energy-efficient alternative using spiking neural networks (SNNs), which leverage sparse activations and event-driven computation to capture temporal dependencies between words, making them suitable for ATE. SpikeATE employs ternary spiking neurons and direct spike-based training with surrogate gradients to enable efficient end-to-end learning. We evaluate our approach on four SemEval benchmark datasets: Laptop14, Restaurant14, Restaurant15, and Restaurant16. Experimental results show that SpikeATE achieves competitive performance with state-of-the-art methods, obtaining F 1-scores of 84.02, 86.46, 72.25, and 78.19, respectively, with the ternary model. In addition to performance, we provide a theoretical analysis of energy consumption, demonstrating the efficiency of the proposed approach. SpikeATE achieves significantly lower power usage (2.5946 mJ for the ternary model and 1.8943 mJ for the binary model) compared to transformer-based models such as BERT and self-training (≈ 95.5 mJ) and large language models such as GPT-3.5 ( ≈ 3.92 × 10 15 mJ). These results highlight that SpikeATE reduces energy consumption by orders of magnitude while maintaining competitive performance. Overall, this work demonstrates that SNN-based architectures provide a practical and sustainable alternative to conventional DNNs for ATE, achieving a favorable balance between accuracy and computational efficiency.","url":"https://doi.org/10.1088/2634-4386/ae65d6","authors":["Abhishek Kumar Mishra","Arya Somasundaram","Anup Das","Nagarajan Kandasamy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-28T22:52:18Z","doi":"10.1088/2634-4386/ae65d6","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1117/12.3107468","name":"Scalable algorithms for neuromorphic in-memory computing with N-ary spintronic crossbar arrays","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3107468","authors":["Anatole Moureaux","Anthony Lopes","Lindiomar Borges de Avila","Flavio Abreu Araujo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-28T17:55:45Z","doi":"10.1117/12.3107468","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1109/ijcnn60899.2024.10650231","name":"Advancing Neuromorphic Computing: Mixed-Signal Design Techniques Leveraging Brain Code Units and Fundamental Code Units","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn60899.2024.10650231","authors":["Murat Isik","Newton Howard","Sols Miziev","Wiktoria Pawlak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T17:35:05Z","doi":"10.1109/ijcnn60899.2024.10650231","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1145/2627369.2627613","name":"AxNN","source":"crossref","abstract":"","url":"https://doi.org/10.1145/2627369.2627613","authors":["Swagath Venkataramani","Ashish Ranjan","Kaushik Roy","Anand Raghunathan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-08-01T20:13:39Z","doi":"10.1145/2627369.2627613","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1063/5.0263232","name":"Fully solution-processed ferroelectric thin film transistor based on PZT and its application in neuromorphic computing","source":"crossref","abstract":"As a promising alternative to conventional computing paradigms, the neuromorphic computing has been demonstrated by using various artificial synaptic devices. Due to the excellent capability for the conductance modulation, the ferroelectric thin film transistors (FeTFTs) have been shown as one of the promising candidates for artificial synaptic devices. In this work, the FeTFTs based on the lead zirconate titanate (PZT) thin films were integrated by the fully solution process. Prior to the integration of the FeTFTs, a lanthanum nickelate (LNO) thin film was prepared as the seed layer. The introduction of the LNO has been demonstrated to improve the crystallinity of the PZT thin films. It is confirmed that the channel conductance of the FeTFTs can be precisely modulated by adjusting the amplitude, duration, and number of the pulses. The potentiation and depression (P-D) characteristics of the FeTFTs have been demonstrated, and the P-D curve shows low nonlinearity and small cycle-to-cycle variations. Based on the P-D characteristics of the FeTFTs, an artificial neural network has been constructed for the pattern recognition, and a recognition accuracy of 93.1% has been achieved. These results suggest that the fully solution-processed FeTFTs based on PZT are the promising candidate for the artificial synaptic devices.","url":"https://doi.org/10.1063/5.0263232","authors":["Yao Dong","Guangtan Miao","Wenlan Xiao","Chunyan You","Guoxia Liu","Fukai Shan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-23T12:51:37Z","doi":"10.1063/5.0263232","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.63363/aijfr.2025.v06i06.2067","name":"Neuromorphic Adaptation and Cognitive Parallelism — A VerbaTerra Project Study","source":"crossref","abstract":"This study, Neuromorphic Adaptation and Cognitive Parallelism, is a core output of the VerbaTerra Project, which seeks to unify neuroscience, linguistics, anthropology, and artificial intelligence under the principle of resonant coherence — the alignment of feedback rhythms across cognition, culture, and computation. Using only secondary academic data and a simulation-based framework, the research develops the vSION Neuromorphic Engine, a four-layer adaptive system (Perceptual, Linguistic, Cognitive, Energetic) capable of learning through rhythmic modulation rather than static optimisation. The simulated data follow the entropy–energy–ethics balance equations described in Annex A and the resonance logic detailed in Annex C. Results show that: 1. Rhythmic learning cycles reduce informational entropy while improving coherence; 2. Creativity peaks at energetic equilibrium; 3. Cross-modal transfer between perception and language enhances adaptability; and 4. Ethical energy regulation functions as a physical limit sustaining long-term cognition. These findings, while conceptual, demonstrate the theoretical viability of resonant ethics as a measurable component of intelligence. By providing executable code in open form (Annex D–F), the paper transforms theory into an interactive experiment—an embodiment of VerbaTerra’s belief that knowledge must remain participatory, transparent, and rhythmic.","url":"https://doi.org/10.63363/aijfr.2025.v06i06.2067","authors":["Harshit Gupta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-20T11:26:46Z","doi":"10.63363/aijfr.2025.v06i06.2067","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1109/biocas67066.2025.00148","name":"Finger Force Decoding from Motor Units Activity on Neuromorphic Hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1109/biocas67066.2025.00148","authors":["Farah Baracat","Giacomo Indiveri","Elisa Donati"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-14T20:38:47Z","doi":"10.1109/biocas67066.2025.00148","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1016/b978-0-323-98829-2.00005-0","name":"Photonic neuromorphic processing for optical communications","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-323-98829-2.00005-0","authors":["Ziwei Li","Jianyang Shi","Nan Chi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-21T06:48:33Z","doi":"10.1016/b978-0-323-98829-2.00005-0","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1016/j.cej.2025.161622","name":"A heterointerface effect of Mo1-xWxS2-based artificial synapse for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.cej.2025.161622","authors":["Jinwoo Hwang","Junho Sung","Eunho Lee","Wonbong Choi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-17T13:36:16Z","doi":"10.1016/j.cej.2025.161622","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1109/ict4s68164.2025.00028","name":"Energy Aware Development of Neuromorphic Implantables: From Metrics to Action","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ict4s68164.2025.00028","authors":["Enrique Barba Roque","Luis Cruz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T17:37:14Z","doi":"10.1109/ict4s68164.2025.00028","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1109/iscas56072.2025.11043287","name":"Optimal strategy for mapping spiking neural networks onto manycore neuromorphic processors","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas56072.2025.11043287","authors":["ChangMin Ye","Doo Seok Jeong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-27T17:42:19Z","doi":"10.1109/iscas56072.2025.11043287","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1109/ropec.2013.6702715","name":"Event-based image processing using a neuromorphic vision sensor","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ropec.2013.6702715","authors":["Jesus Armando Garcia Franco","Juan Luis del Valle Padilla","Susana Ortega Cisneros"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-01-10T20:07:14Z","doi":"10.1109/ropec.2013.6702715","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/icton62926.2024.10648188","name":"Performance Optimization of Photonic Accelerators in Neuromorphic Computing via Structure Trimming","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icton62926.2024.10648188","authors":["Rongyang Xu","Shabnam Taheriniya","Akhil Varri","Frank Brückerhoff-Plückelmann","Wolfram Pernice"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-02T17:34:14Z","doi":"10.1109/icton62926.2024.10648188","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/nano.2015.7388846","name":"Wave-based neuromorphic computing framework for brain-like energy efficiency and integration","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nano.2015.7388846","authors":["Y. Katayama","T. Yamane","D. Nakano","R. Nakane","G. Tanaka"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-02-03T12:35:14Z","doi":"10.1109/nano.2015.7388846","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/icnc64304.2024.10987696","name":"Reinforcement Learning-Based Adaptive Fault-Tolerant Optimal Control with Time Delays for Discrete-Time Multi-Agent Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987696","authors":["Hongyu Chen","Lihua Tan","Xin Wang","Chen Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987696","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1145/3571155","name":"Exploring Neuromorphic Computing Based on Spiking Neural Networks: Algorithms to Hardware","source":"crossref","abstract":"Neuromorphic Computing, a concept pioneered in the late 1980s, is receiving a lot of attention lately due to its promise of reducing the computational energy, latency, as well as learning complexity in artificial neural networks. Taking inspiration from neuroscience, this interdisciplinary field performs a multi-stack optimization across devices, circuits, and algorithms by providing an end-to-end approach to achieving brain-like efficiency in machine intelligence. On one side, neuromorphic computing introduces a new algorithmic paradigm, known as Spiking Neural Networks (SNNs), which is a significant shift from standard deep learning and transmits information as spikes (“1” or “0”) rather than analog values. This has opened up novel algorithmic research directions to formulate methods to represent data in spike-trains, develop neuron models that can process information over time, design learning algorithms for event-driven dynamical systems, and engineer network architectures amenable to sparse, asynchronous, event-driven computing to achieve lower power consumption. On the other side, a parallel research thrust focuses on development of efficient computing platforms for new algorithms. Standard accelerators that are amenable to deep learning workloads are not particularly suitable to handle processing across multiple timesteps efficiently. To that effect, researchers have designed neuromorphic hardware that rely on event-driven sparse computations as well as efficient matrix operations. While most large-scale neuromorphic systems have been explored based on CMOS technology, recently, Non-Volatile Memory (NVM) technologies show promise toward implementing bio-mimetic functionalities on single devices. In this article, we outline several strides that neuromorphic computing based on spiking neural networks (SNNs) has taken over the recent past, and we present our outlook on the challenges that this field needs to overcome to make the bio-plausibility route a successful one.","url":"https://doi.org/10.1145/3571155","authors":["Nitin Rathi","Indranil Chakraborty","Adarsh Kosta","Abhronil Sengupta","Aayush Ankit","Priyadarshini Panda","Kaushik Roy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-17T10:05:37Z","doi":"10.1145/3571155","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1016/j.cej.2026.172735","name":"UV-curable resin–induced transition to interface-type resistive switching in ZnO synaptic devices for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.cej.2026.172735","authors":["Seungjun Yim","Hyung Bin Park","Jaehoon Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-07T00:17:28Z","doi":"10.1016/j.cej.2026.172735","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1021/acsaelm.5c00222","name":"Strategy for the Integrated Design of Ferroelectric and Resistive Memristors for Neuromorphic Computing Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acsaelm.5c00222","authors":["Jung-Kyu Lee","Yongjin Park","Euncho Seo","Woohyun Park","Chaewon Youn","Sejoon Lee","Sungjun Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-25T17:46:23Z","doi":"10.1021/acsaelm.5c00222","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1109/prime58259.2023.10161980","name":"A flexible column parallel successive-approximation ADC for hybrid neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/prime58259.2023.10161980","authors":["Philipp Dauer","Milena Czierlinski","Sebastian Billaudelle","Andreas Grübl","Johannes Schemmel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-29T17:21:05Z","doi":"10.1109/prime58259.2023.10161980","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/vlsid.2016.117","name":"Neuromorphic Computing Enabled by Spin-Transfer Torque Devices","source":"crossref","abstract":"","url":"https://doi.org/10.1109/vlsid.2016.117","authors":["Abhronil Sengupta","Priyadarshini Panda","Anand Raghunathan","Kaushik Roy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-03-17T16:29:07Z","doi":"10.1109/vlsid.2016.117","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/icrc2020.2020.00013","name":"Design Principles of Large-Scale Neuromorphic Systems Centered on High Bandwidth Memory","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icrc2020.2020.00013","authors":["Bruno U. Pedroni","Stephen R. Deiss","Nishant Mysore","Gert Cauwenberghs"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-02-12T21:34:26Z","doi":"10.1109/icrc2020.2020.00013","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1088/2634-4386/acc050","name":"Artificial visual neuron based on threshold switching memristors","source":"crossref","abstract":"Abstract The human visual system encodes optical information perceived by photoreceptors in the retina into neural spikes and then processes them by the visual cortex, with high efficiency and low energy consumption. Inspired by this information processing mode, an universal artificial neuron constructed with a resistor ( R s ) and a threshold switching memristor can realize rate coding by modulating pulse parameters and the resistance of R s . Owing to the absence of an external parallel capacitor, the artificial neuron has minimized chip area. In addition, an artificial visual neuron is proposed by replacing R s in the artificial neuron with a photo-resistor. The oscillation frequency of the artificial visual neuron depends on the distance between the photo-resistor and light, which is fundamental to acquiring depth perception for precise recognition and learning. A visual perception system with the artificial visual neuron can accurately and conceptually emulate the self-regulation process of the speed control system in a driverless automobile. Therefore, the artificial visual neuron can process efficiently sensory data, reduce or eliminate data transfer and conversion at sensor/processor interfaces, and expand its application in the field of artificial intelligence.","url":"https://doi.org/10.1088/2634-4386/acc050","authors":["Juan Wen","Zhen-Ye Zhu","Xin Guo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-01T22:29:33Z","doi":"10.1088/2634-4386/acc050","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/icnc52316.2021.9608284","name":"Anti-Synchronization Control of Fuzzy Inertial Neural Networks with Distributed Time Delays","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc52316.2021.9608284","authors":["Jing Han","Guici Chen","Guodong Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-29T20:59:32Z","doi":"10.1109/icnc52316.2021.9608284","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1088/2634-4386/ad7314","name":"From ‘follow the leader’ to autonomous swarming: physical reservoir computing in two dimensions","source":"crossref","abstract":"Abstract Percolating networks of nanoparticles (PNNs) are self-assembled nanoscale systems that possess brain-like characteristics that are useful for information processing, particularly within a reservoir computing (RC) framework. Previous work has successfully demonstrated one-dimensional RC tasks, such as chaotic time-series prediction and nonlinear transformation. We focus here on the challenge of two-dimensional (2D) tasks and introduce novel ‘follow the leader’ and ‘swarming’ tasks. In the first task a ‘follower’ is required to accurately track a ‘leader’ in two dimensions. The task is performed successfully for a range of trajectories and parameters, for both position-based tracking and velocity-based tracking incorporating inertia. In both cases, the task is successful even for trajectories unseen in training. We then successfully demonstrate a 2D implementation of swarming behavior. Each agent is represented by a PNN which is trained to react to the behavior of the other members of the swarm, such that the future trajectory of all agents is generated autonomously. As well as demonstrating that the computational capabilities of PNNs can be extended into two dimensions, this work presents a first step in the emulation of complex emergent biological behaviors such as swarming, and opens a new route to the solution of complex optimization problems.","url":"https://doi.org/10.1088/2634-4386/ad7314","authors":["Zachary E Heywood","Joshua B Mallinson","Philip J Bones","Simon A Brown"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-23T22:51:48Z","doi":"10.1088/2634-4386/ad7314","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/icons69015.2025.00020","name":"GRASP: Dynamic and Priority-Aware Gradient Sparsification for Efficient Online Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons69015.2025.00020","authors":["Balachandran Swaminathan","Jack Sampson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-21T21:07:17Z","doi":"10.1109/icons69015.2025.00020","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.29363/nanoge.nfm.2022.208","name":"Event-based Sensors: Neuromorphic Vision for Neuromorphic AI","source":"crossref","abstract":"","url":"https://doi.org/10.29363/nanoge.nfm.2022.208","authors":["Amos Sironi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-02T08:32:12Z","doi":"10.29363/nanoge.nfm.2022.208","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1021/acsnano.4c16874","name":"Strain-Insensitive, Air-Stable Stretchable Carbon Nanotube-Based Synaptic Transistors Array via Direct Microfabrication for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acsnano.4c16874","authors":["Dingzhou Cui","Zhiyuan Zhao","Fugu Tian","Wenbo Chen","Mingrui Chen","Max Zhou","Xiaoqi Wu","Jingxin Zhang","Chongwu Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-30T11:20:27Z","doi":"10.1021/acsnano.4c16874","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1021/acsanm.5c02604","name":"Low Power Consumption CsPb<sub>0.5</sub>Sn<sub>0.5</sub>Br<sub>3</sub> Quantum Dot-Based Photoelectric Synaptic Transistors for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acsanm.5c02604","authors":["Jiangdong Zhang","Jia Liu","Haichuan Geng","Wenwen Wang","Yiying Wei","Menghan Chen","Jiahao Kang","Jinjin Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-19T13:24:53Z","doi":"10.1021/acsanm.5c02604","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1016/j.patrec.2024.11.009","name":"Neuromorphic face analysis: A survey","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.patrec.2024.11.009","authors":["Federico Becattini","Lorenzo Berlincioni","Luca Cultrera","Alberto Del Bimbo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-19T12:02:44Z","doi":"10.1016/j.patrec.2024.11.009","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1109/icrc64395.2024.10937004","name":"Evaluation of Ferroelectric Devices for Neuromorphic Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icrc64395.2024.10937004","authors":["Julia Steed","Sebastien J. Boussard","Andreu L. Glasmann","Sina Najmaei","James S. Plank","Catherine D. Schuman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-28T03:23:48Z","doi":"10.1109/icrc64395.2024.10937004","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/icnc59488.2023.10462865","name":"Distributed Robust State Estimation of Uncertain Complex Networked Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462865","authors":["Yufan Zhao","Yuezu Lv","Hao Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462865","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1149/ma2021-0229874mtgabs","name":"(Invited) ALD Based Flexible Memristive Synapses for Neuromorphic Computing Application","source":"crossref","abstract":"","url":"https://doi.org/10.1149/ma2021-0229874mtgabs","authors":["Lin Chen","Tian-Yu Wang","Shi-Jin Ding","David Wei Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-11T08:38:30Z","doi":"10.1149/ma2021-0229874mtgabs","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.3390/technologies13080326","name":"Trigger-Based Systems as a Promising Foundation for the Development of Computing Architectures Based on Neuromorphic Materials","source":"crossref","abstract":"It is demonstrated that neuromorphic materials designed for computational tasks can be effectively implemented by drawing an analogy with trigger-based systems built upon classical binary elements. Among the most promising approaches in this context are systems that perform computations based on the Residue Number System (RNS). A specific implementation of a trigger-based adder employing the proposed methodology is presented and tested through simulation modeling. This adder utilizes the representation of natural numbers as elements of a subtraction ring modulo P, where P is the product of Mersenne prime numbers. This configuration enables component-wise, independent execution of arithmetic operations. It is further shown that analogous trigger-based systems can be realized using recurrent neural network analogs, particularly those implemented with neuromorphic materials. The study emphasizes that it is possible to construct a neural network, especially one based on neuromorphic substrates, that can perform logical operations equivalent to those executed by conventional binary circuitry. A key challenge in the proposed approach lies in implementing an operation analogous to the carry mechanism employed in classical binary adders. An algorithm addressing this issue is proposed, based on the transition from computations modulo P to computations modulo 2P.","url":"https://doi.org/10.3390/technologies13080326","authors":["Dina Shaltykova","Kaisarali Kadyrzhan","Jelena Caiko","Yelizaveta Vitulyova","Ibragim Suleimenov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-04T13:11:11Z","doi":"10.3390/technologies13080326","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.3934/fods.2024026","name":"GNEP based dynamic segmentation and motion estimation for neuromorphic imaging","source":"crossref","abstract":"","url":"https://doi.org/10.3934/fods.2024026","authors":["Harbir Antil","David Sayre"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-21T09:19:27Z","doi":"10.3934/fods.2024026","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1063/5.0260692","name":"Interface engineering modulation of ferroelectric synapses for high-precision neuromorphic computing","source":"crossref","abstract":"Nb:SrTiO3 (NSTO) are commonly employed as substrate and electrode for BaTiO3-based ferroelectric memristors. These substrates are available in two types. The first one is with the hybrid-terminated interface, which consists of alternating SrO and TiO2 planes, while the second one is a TiO2-terminated interface. The interaction between surfaces and interfaces plays a crucial role in determining the overall performance of synapses. This paper reports a ferroelectric synapse whose neuromorphic performance can be regulated by the terminated interface of NSTO substrate. Compared with hybrid-terminated devices, the TiO2-terminated devices exhibit a 0.38 eV increase in barrier height, a 38.2% reduction in dislocation density, an approximately 10-fold enhancement in the on/off ratio, a 47.1% improvement in the linearity of long-term potentiation, and a 57.1% improvement in the linearity of long-term depression. This is due to their lower surface state density and atomically flat surface topography. In addition, the TiO2-terminated devices accurately emulate the characteristics of artificial synapses, and the neural network developed based on the weight update characteristics of the memristor achieves an image recognition accuracy of 96.1% on the National Institute of Standards and Technology handwritten digit dataset.","url":"https://doi.org/10.1063/5.0260692","authors":["Hao Liu","Yan Wang","Wenshuo Wu","Minghao Zhang","Jie Su"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-28T13:15:19Z","doi":"10.1063/5.0260692","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1016/j.nanoen.2025.110837","name":"Temperature-driven co-optimization of IGZO/HZO ferroelectric field-effect transistors for optoelectronic neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.nanoen.2025.110837","authors":["Deokjoon Eom","Hyunhee Kim","Woohui Lee","Changyu Park","Jinsung Park","Heesoo Lee","Taegyu Kim","San Nam","Yong-Hoon Kim","Hyoungsub Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-05T16:34:09Z","doi":"10.1016/j.nanoen.2025.110837","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1016/j.cclet.2024.110030","name":"High sensitivity artificial synapses using printed high-transmittance ITO fibers for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.cclet.2024.110030","authors":["Shangda Qu","Yiming Yuan","Xu Ye","Wentao Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-20T15:34:02Z","doi":"10.1016/j.cclet.2024.110030","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1002/admt.71088","name":"Self‐Rectifying Second Order Memristive Behavior in WO\n                    <sub>3</sub>\n                    Films for Neuromorphic Computing Applications","source":"crossref","abstract":"ABSTRACT Brain‐inspired neuromorphic computing paves an alternative to the Von Neumann bottleneck on implementing highly efficient and parallel processing hardware. However, in a crossbar array architecture, crosstalk occurs between devices. To address this issue, in this study, a Pt/WO 3 /FTO self‐rectifying memristor was fabricated using pulsed laser deposition, exhibiting a rectification ratio ≈10 3 , endurance of 5 × 10 3 cycles, negligible device‐to‐device variability, highly stable up to 25 cycles, energy consumption of 1.1 pJ/µm 2 in writing operation, and excellent synaptic behavior without any additional material engineering. This study comprehensively investigates the neuromorphic computing characteristics of the fabricated Pt/WO 3 /FTO structure. The conduction mechanism was explained using charge trapping/detrapping and Schottky barrier formation at the Pt/WO 3 interface, resulting in excellent rectification behavior. Interestingly, the fabricated structure exhibited second‐order memristive behavior, attributed to internal ion dynamics. The neuromorphic computing characteristics were comprehensively assessed using artificial neural network simulations, and fabricated devices achieved 90% accuracy on the MNIST handwritten digits dataset and 75% accuracy on the Fashion‐MNIST dataset, thus emulating synaptic functionality and showing excellent potential of the fabricated devices in real‐world artificial intelligence applications.","url":"https://doi.org/10.1002/admt.71088","authors":["Agesthian Suresh Kanthaswamy","Atul Thakre"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-08T08:56:33Z","doi":"10.1002/admt.71088","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1088/978-0-7503-5097-6ch2","name":"Introduction to neuromorphic circuits","source":"crossref","abstract":"","url":"https://doi.org/10.1088/978-0-7503-5097-6ch2","authors":["Alice C Parker","Rick Cattell"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-09T12:29:33Z","doi":"10.1088/978-0-7503-5097-6ch2","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1088/2634-4386/ade622","name":"SpinONN: energy efficient brain-inspired spintronics-based Hopfield oscillatory neural network for image denoising","source":"crossref","abstract":"Abstract This work proposes a Spintronics-based Hopfield oscillatory neural network (HONN) that leverages dynamic frequency-encoded electrical synchronization between two spin-torque vortex nano-oscillators (SVNOs) as oscillatory neurons, with a non-volatile memristor as a coupling element (synaptic connection). The frequency synchronization mechanism, inspired by the brain’s oscillatory dynamics, enables the synchronization of SVNOs, facilitating efficient information processing of the dynamic oscillatory signals within the network. This coupling mechanism has been investigated to design SVNOs-based neural circuit design topology for enhanced frequency-encoded computing using SVNOs neurons and memristive coupling synapses. The proposed transmission gate-based SVNO oscillatory neural circuit has been implemented, offering efficient frequency synchronization, non-linearity, and a less complex neural circuit design. Further, a hybrid Spintronic/complementary metal oxide semiconductor 16-SVNOs HONN is designed, and circuit-based simulations are performed, which offer a promising solution for building robust and scalable HONNs. We achieve fast computation (∼4 ns) and offer significantly lower energy consumption (∼24 fJ/neuron) as compared to VO 2 -based ONN architectures (8× faster and 4× reduced power/neuron). Finally, we demonstrate an image denoising application on the proposed SVNO-based HONN hardware-compatible accelerator using an image-splitting approach with parallel processing. The 32 × 32 street view house number image dataset is efficiently split into blocks and processed through the 16-SVNOs HONN design, dividing the image into 4 × 4 blocks. Lastly, we examined the peak signal-to-noise ratio and structural similarity index measure for denoising the images with an efficient splitting approach for scalability. The network effectively denoises images while maintaining image quality, demonstrating the potential of the HONN hardware-compatible architecture for large-scale and real-time applications.","url":"https://doi.org/10.1088/2634-4386/ade622","authors":["Sandeep Soni","Yasser Rezaeiyan","Tim Boehnert","Hooman Farkhani","Ricardo Ferreira","Brajesh Kumar Kaushik","Farshad Moradi","Sonal Shreya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-19T22:51:42Z","doi":"10.1088/2634-4386/ade622","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1117/12.3099967","name":"Photonic lanterns: a novel fiber component for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3099967","authors":["Siddharth Sivankutty","Nolan Desnos","Stefano Negrini","Géraud Bouwmans","Arnaud Mussot","Esben Andresen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-27T18:24:27Z","doi":"10.1117/12.3099967","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1109/icnc52316.2021.9608525","name":"Fixed-time Formation Control for Second-order Multi-agent Systems with Disturbances","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc52316.2021.9608525","authors":["Huifen Hong","He Wang","Guanghui Wen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-29T20:59:32Z","doi":"10.1109/icnc52316.2021.9608525","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1002/adom.202501078","name":"High Sensitivity Optoelectronic Artificial Synapse Based on GaN Porous Nanocone Array for Neuromorphic Computing","source":"crossref","abstract":"Abstract Neuromorphic computing architecture, inspired by biological systems, is one of the key solutions to overcoming the von Neumann bottleneck. In particular, as a core component of artificial visual perception systems, optoelectronic synapses with high sensitivity and long memory retention hold significant potential applications. Herein, a two‐terminal GaN porous nanocone array (PNA) optoelectronic artificial synapse is designed and fabricated. The unique structure of the GaN PNA significantly enhances light absorption, achieving a responsivity of up to 2.07 × 10 6 A W −1 and a specific detectivity ( D* ) of 3.50 × 10 15 Jones. The persistent photoconductivity (PPC) effect, originated from surface states, exhibits a remarkably long decay characteristic time of up to 1204 s. This enables the synapses to emulate various key synaptic functions, including paired‐pulse facilitation (PPF), memory‐forgetting‐relearning processes, and the transition from short‐term potentiation (STP) to long‐term potentiation (LTP). Moreover, the GaN PNA optoelectronic artificial synapse demonstrates exceptional performance in artificial visual neural networks with a recognition accuracy approaching 93%. This work presents a novel solution for enhancing computational efficiency in artificial visual neural networks.","url":"https://doi.org/10.1002/adom.202501078","authors":["Jiawei Chen","Yuqing Huang","Hui Wen","Yujing Wang","Huiying Li","Xinyuan Zheng","Xin Wang","Zhanhong Ma","Ting Wang","Sen Yan","Kaiyou Wang","Lixia Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-19T01:05:47Z","doi":"10.1002/adom.202501078","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1063/5.0275455","name":"Enhancement of spin–orbit torque in sputtered BiSb-based perpendicular magnetic tunnel junctions for neuromorphic computing applications","source":"crossref","abstract":"Topological insulators offer unique properties for generating high spin–orbit torque (SOT), promising to revolutionize magnetoresistive random-access memory with a low power consumption. In this work, BiSb is integrated into perpendicular magnetic tunnel junctions (pMTJs) to enable efficient SOT switching. By optimizing the BiSb thickness and introducing a Ta buffer layer, a threefold enhancement in damping-like SOT efficiency and a 60% reduction in switching current are achieved compared to the BiSb-free sample. X-ray diffraction measurements confirm the improved crystalline quality with increasing BiSb thickness, contributing to the enhanced spin current generation. The fabricated BiSb-pMTJs exhibit key neuromorphic functionalities, including gradual long-term potentiation/depression and sigmoidal resistance modulation under pulsed current. Utilizing these features, a three-layer artificial neural network is implemented based on experimentally extracted device behavior, achieving over 90% accuracy in handwritten digit recognition.","url":"https://doi.org/10.1063/5.0275455","authors":["S. Wu","G. J. Lim","F. N. Tan","T. L. Jin","C. C. I. Ang","E. K. Koh","S. H. Lee","K. J. Cheng","W. S. Lew"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-01T14:26:46Z","doi":"10.1063/5.0275455","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1002/aisy.202500506","name":"Cryogenic Neuromorphic Synaptic Behavior in 180 nm Silicon Transistors for Emerging Computing Systems","source":"crossref","abstract":"With the advancement of artificial intelligence (AI), there is an increasing demand for high‐speed, energy‐efficient hardware capable of running complex machine learning algorithms. Traditional hardware is constrained by the Von Neumann bottleneck, resulting in high power consumption and slower speeds. Inspired by the human brain, bio‐mimicking the dynamic synaptic plasticity of the biological synapse using synaptic transistors is crucial to building the next generation of high‐performance computing hardware‐based neural networks. This study investigates neuromorphic behavior in 180 nm bulk complementary metal oxide semiconductor (CMOS) devices at 4 K, emphasizing memory properties and synapse‐like characteristics. These findings position bulk CMOS as a scalable, energy‐efficient, cryo‐compatible platform for neuromorphic and quantum computing use. Gated‐pulse measurements are used to study potentiation–depression behavior by quantifying conductance changes as functions of pulse amplitude and width. These results closely resemble biological synaptic plasticity, laying the groundwork for integrating cryo‐CMOS technology into neuromorphic computing. The work reported here aims to work toward the development of hybrid computational systems by bridging the gap between conventional CMOS devices and emerging cryogenic technology, offering new avenues for scalable, energy‐efficient, and high‐performance cryogenic neuromorphic technologies.","url":"https://doi.org/10.1002/aisy.202500506","authors":["Fiheon Imroze","Bhavani Yalagala","Naveen Kumar","Mostafa Elsayed","Meraj Ahmad","Robert Graham","Vihar Georgiev","Hadi Heidari","Martin Weides"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-26T19:24:07Z","doi":"10.1002/aisy.202500506","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1145/3822454.3822493","name":"Hardware–Software Co-Design for Event-Driven SNN Deployment on Low-Cost Neuromorphic FPGAs","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3822454.3822493","authors":["Jiwoon Lee","Souvik Chakraborty","Syed Bahauddin Alam","Cheolsoo Park"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-16T05:57:39Z","doi":"10.1145/3822454.3822493","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1149/ma2020-02231683mtgabs","name":"(Invited) MLD of Metal-Organic Thin Films with Tunable Conductance for Neuromorphic Computing Applications","source":"crossref","abstract":"Artificial neural networks have revolutionized the field of artificial intelligence with human-like performance in fields such as computer vision and speech recognition. As the tasks for AI are increasingly demanding, significant gains in terms of speed and power consumption could be achieved by moving from software-based AI-systems to neuromorphic hardware that directly emulates the functionality and interconnectivity of the biological neural networks with layers of artificial neurons connected to each other via synaptic elements characterized by a weight factor. However, purely CMOS-based neuromorphic circuits are ultimately impractical for the implementation of large networks, as mimicking the operation dynamics and behavior of even a single synapse or neuron can take tens of transistors each to implement. Therefore, a key challenge is to develop new types of hardware, that is capable of achieving directly the in-memory processing of brain-like computation. For instance, single-element synapses can be achieved with memristors, in which the synaptic weight is emulated by their history-dependent variable conductance. Typically, various inorganic materials have been employed for these resistive switching devices that rely on the formation/dissolution of a conductive filament within an insulating matrix. The main challenges are the device-to-device and cycle-to-cycle variability caused by the stochastic nature of the filament formation. Additionally, the typically high conductance in the ON-state results in high energy consumption. Here we explore metal-organic coordination polymers deposited by atomic/molecular layer deposition (ALD/MLD) as an interesting alternative for this challenge. The most attractive feature of coordination polymers is their unparalleled tunability towards different functionalities arising from practically limitless number of metal and ligand combinations available. Yet, poor processability restricts their applicability towards nanotechnology applications. However, MLD, an extension to ALD, expands the deposition of thin films with superior quality to hybrid organic-inorganic materials with the implementation of volatile organic molecules as the co-reactant. We show that in high-quality coordination polymer thin films, post-synthetic control of their oxidation state is akin to tuning the doping level in terms band structure, and allows for tunable conductivity spanning over 8 orders of magnitude (10 -10 – 10 -2 S cm -1 ). On device level, this redox-reaction based operation can be harnessed for low variability as the switching voltage is governed by the materials’ intrinsic reduction potential in contrast to the stochastic filament formation of the inorganic counterparts. Aside from the analog conductance tuning, the redox reaction rate, and thus rate of change in the device conductance is dependent on the excitation frequency and amplitude, thereby emulating the time-dependent dynamics of biological synapses such as spike-rate and spike timing dependent plasticity (SRDP and STDP). As the redox-reaction is also coupled with the motion of an associated counter ion, the interplay of the electron and ion mobilities apparently allows for the realization of concurrent short- and long-term memory in a single device. As such, ALD/MLD enabled coordination polymer thin films are attractive for use in more bio-realistic AI technology such as spiking neural networks.","url":"https://doi.org/10.1149/ma2020-02231683mtgabs","authors":["Mikko Nisula","Antti J. Karttunen","Christophe Detavernier"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-22T18:55:28Z","doi":"10.1149/ma2020-02231683mtgabs","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1049/ell2.70092","name":"Guest Editorial: Memristive electronic circuits, neural networks and neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1049/ell2.70092","authors":["Yichuang Sun","Shahar Kvatinsky","Georgios Ch. Sirakoulis","Jingru Sun","Alon Ascoli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-14T01:39:05Z","doi":"10.1049/ell2.70092","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/iedm13553.2020.9372114","name":"Atomic-Device Hybrid Modeling of Relaxation Effect in Analog RRAM for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iedm13553.2020.9372114","authors":["Feng Xu","Bin Gao","Yue Xi","Jianshi Tang","Huaqiang Wu","He Qian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-11T16:34:02Z","doi":"10.1109/iedm13553.2020.9372114","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1002/admt.202500786","name":"Toward Advancement of Fabrication Techniques of Neuromorphic Computing Devices Based on 2D Materials","source":"crossref","abstract":"Abstract The growing necessity for power‐efficient and cognitive computation mechanisms has driven progress in neuromorphic computing which seeks to imitate the synaptic mechanisms underlying human brain functionality. The drawbacks of traditional computation paradigms which involve a large amount of power utilization and restricted data communication drive the quest for alternative materials and technologies. In this context, 2D materials have proven themselves an especially valuable class of materials for new‐generation neuromorphic devices because of their atomic thickness and distinct electronic attributes. The present review gives a detailed account of advanced techniques enabling the fabrication of neuromorphic devices using 2D materials with a focus on deposition methods and device engineering strategies to enhance synaptic functionalities for energy‐efficient signal processing. This article also explores the role of 2D materials in establishing effective synthetic synapses which are predominant in supporting key functions such as short‐term plasticity (STP) and long‐term plasticity (LTP). This article further addresses key fabrication challenges such as scalability, contact/interface issues, and variability, along with emerging solutions like atomic‐thickness control and heterostructure integration. Through a carefully designed roadmap, this article attempts to blend fabrication processes and 2D material's neuromorphic device physics hence presenting valuable insights in constructing brain inspired computational devices.","url":"https://doi.org/10.1002/admt.202500786","authors":["Shubham Umeshkumar Gupta","Malkeshkumar Patel","Naveen Kumar","László Pohl","Min‐Joon Park","Sung‐Min Youn","Chaewhan Jeong","Joondong Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-12T12:25:26Z","doi":"10.1002/admt.202500786","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1117/12.2682857","name":"Fully interface-controlled memristive devices for artificial synapse and neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.2682857","authors":["Sundar Kunwar","Aiping Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-05T21:04:40Z","doi":"10.1117/12.2682857","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1088/2634-4386/ad5d0f","name":"Kernel heterogeneity improves sparseness of natural images representations","source":"crossref","abstract":"Abstract Both biological and artificial neural networks inherently balance their performance with their operational cost, which characterizes their computational abilities. Typically, an efficient neuromorphic neural network is one that learns representations that reduce the redundancies and dimensionality of its input. For instance, in the case of sparse coding (SC), sparse representations derived from natural images yield representations that are heterogeneous, both in their sampling of input features and in the variance of those features. Here, we focused on this notion, and sought correlations between natural images’ structure, particularly oriented features, and their corresponding sparse codes. We show that representations of input features scattered across multiple levels of variance substantially improve the sparseness and resilience of sparse codes, at the cost of reconstruction performance. This echoes the structure of the model’s input, allowing to account for the heterogeneously aleatoric structures of natural images. We demonstrate that learning kernel from natural images produces heterogeneity by balancing between approximate and dense representations, which improves all reconstruction metrics. Using a parametrized control of the kernels’ heterogeneity of a convolutional SC algorithm, we show that heterogeneity emphasizes sparseness, while homogeneity improves representation granularity. In a broader context, this encoding strategy can serve as inputs to deep convolutional neural networks. We prove that such variance-encoded sparse image datasets enhance computational efficiency, emphasizing the benefits of kernel heterogeneity to leverage naturalistic and variant input structures and possible applications to improve the throughput of neuromorphic hardware.","url":"https://doi.org/10.1088/2634-4386/ad5d0f","authors":["Hugo J Ladret","Christian Casanova","Laurent Udo Perrinet"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-20T08:39:30Z","doi":"10.1088/2634-4386/ad5d0f","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1145/3578436","name":"Session details: Crossbars, Analog Accelerators for Neural Networks, and Neuromorphic Computing Based on Printed Electronics","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3578436","authors":["Hussam Amrouch","Sheldon Tan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-22T12:10:54Z","doi":"10.1145/3578436","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/icnc64304.2024.10987889","name":"A Multi-Scale CNN-LSTM Network with Squeeze and Excitation Block for Leg Movement Detection during Sleep","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987889","authors":["Qingqing Yang","Yamei Li","Xielan Tang","Lu Luo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987889","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1088/2634-4386/ac57a2","name":"Magnetic tunnel junction based implementation of spike time dependent plasticity learning for pattern recognition","source":"crossref","abstract":"Abstract We present a magnetic tunnel junction (MTJ) based implementation of the spike time-dependent (STDP) learning for pattern recognition applications. The proposed hybrid scheme utilizes the spin–orbit torque (SOT) driven neuromorphic device-circuit co-design to demonstrate the Hebbian learning algorithm. The circuit implementation involves the (MTJ) device structure, with the domain wall motion in the free layer, acting as an artificial synapse. The post-spiking neuron behaviour is implemented using a low barrier MTJ. In both synapse and neuron, the switching is driven by the SOTs generated by the spin Hall effect in the heavy metal. A coupled model for the spin transport and switching characteristics in both devices is developed by adopting a modular approach to spintronics. The thermal effects in the synapse and neuron result in a stochastic but tuneable domain wall motion in the synapse and a superparamagnetic behaviour of in neuron MTJ. Using the device model, we study the dimensional parameter dependence of the switching delay and current to optimize the device dimensions. The optimized parameters corresponding to synapse and neuron are considered for the implementation of the Hebbian learning algorithm. Furthermore, cross-point architecture and STDP-based weight modulation scheme is used to demonstrate the pattern recognition capabilities by the proposed neuromorphic circuit.","url":"https://doi.org/10.1088/2634-4386/ac57a2","authors":["Aijaz H Lone","S Amara","H Fariborzi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-22T22:47:09Z","doi":"10.1088/2634-4386/ac57a2","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/icrc.2016.7738712","name":"Stochastic single flux quantum neuromorphic computing using magnetically tunable Josephson junctions","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icrc.2016.7738712","authors":["Stephen E. Russek","Christine A. Donnelly","Michael L. Schneider","Burm Baek","Mathew R. Pufall","William H. Rippard","Peter F. Hopkins","Paul D. Dresselhaus","Samuel P. Benz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-11-10T16:39:45Z","doi":"10.1109/icrc.2016.7738712","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/piers62282.2024.10618426","name":"Magnetoelectric Basic Logic Element for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/piers62282.2024.10618426","authors":["V. A. Misilin","V. A. Kiselev","A. A. Mikhailov","R. V. Petrov","A. O. Nikitin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-09T17:18:24Z","doi":"10.1109/piers62282.2024.10618426","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1016/j.jallcom.2025.185454","name":"ZnIn2S4 optoelectronic synapses with vacancy-engineered persistent photoconductivity for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.jallcom.2025.185454","authors":["Xin Peng","Xing Xu","Yicheng Wang","Yipeng Zhao","Honglai Li","Chao Fan","Liang Ma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-04T17:14:48Z","doi":"10.1016/j.jallcom.2025.185454","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1038/s44335-025-00036-2","name":"Integrated algorithm and hardware design for hybrid neuromorphic systems","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s44335-025-00036-2","authors":["James Seekings","Mahsa Ardakani","Peyton Chandarana","Arshia Eslami","Mohammadreza Mohammadi","Ramtin Zand"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-12T05:11:20Z","doi":"10.1038/s44335-025-00036-2","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1038/s41377-025-01773-6","name":"Versatile optoelectronic memristor based on wide-bandgap Ga2O3 for artificial synapses and neuromorphic computing","source":"europepmc","abstract":"Abstract Optoelectronic memristors possess capabilities of data storage and mimicking human visual perception. They hold great promise in neuromorphic visual systems (NVs). This study introduces the amorphous wide-bandgap Ga 2 O 3 photoelectric synaptic memristor, which achieves 3-bit data storage through the adjustment of current compliance ( I cc ) and the utilization of variable ultraviolet (UV-254 nm) light intensities. The “AND” and “OR” logic gates in memristor-aided logic (MAGIC) are implemented by utilizing voltage polarity and UV light as input signals. The device also exhibits highly stable synaptic characteristics such as paired-pulse facilitation (PPF), spike-intensity dependent plasticity (SIDP), spike-number dependent plasticity (SNDP), spike-time dependent plasticity (STDP), spike-frequency dependent plasticity (SFDP) and the learning experience behavior. Finally, when integrated into an artificial neural network (ANN), the Ag/Ga 2 O 3 /Pt memristive device mimicked optical pulse potentiation and electrical pulse depression with high pattern accuracy (90.7%). The single memristive cells with multifunctional features are promising candidates for optoelectronic memory storage, neuromorphic computing, and artificial visual perception applications.","url":"https://doi.org/10.1038/s41377-025-01773-6","authors":["Dongsheng Cui","Mengjiao Pei","Zhenhua Lin","Hong Zhang","Mengyang Kang","Yifei Wang","Xiangxiang Gao","Jie Su","Jinshui Miao","Yun Li","Jincheng Zhang","Yue Hao"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41377-025-01773-6","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1109/icassp49660.2025.10889295","name":"Neuromorphic Unlimited Sampling for High-Dynamic-Range Video Acquisition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icassp49660.2025.10889295","authors":["Abijith Jagannath Kamath","Chandra Sekhar Seelamantula"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-12T17:15:02Z","doi":"10.1109/icassp49660.2025.10889295","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1002/rpm.20240038","name":"Artificial optoelectronic synapses based on Ga\n                    <sub>2</sub>\n                    O\n                    <sub>3</sub>\n                    metal–semiconductor–metal solar‐blind ultraviolet photodetectors with asymmetric electrodes for neuromorphic computing","source":"crossref","abstract":"Abstract Research on optoelectronic synapses that can integrate both detection and processing functions is essential for the development of efficient neuromorphic computing. Here, we experimentally demonstrated an Ga 2 O 3 ‐based metal–semiconductor–metal (MSM) solar‐blind ultraviolet (UV) photodetector (PD) with asymmetric interdigital electrodes. The Ga 2 O 3 PD exhibits a responsivity of 732 A/W under a forward bias of 6 V. The tunable conductance properties of PDs provide a novel approach to synaptic performance. The proposed PDs as artificial synapse realized several essential synaptic function, including excitatory postsynaptic current, paired‐pulse facilitation, long‐term potentiation, the transition from short‐term memory to long‐term memory, and learning experience behaviors successfully. At a reverse bias, an ultra‐low energy consumption of 140 fJ was achieved. In addition, the optoelectronic synapses demonstrated a recognition accuracy of over 95% in the MNIST handwritten number recognition task. These results suggest that Ga 2 O 3 MSM solar‐blind UV PDs have high potential for efficient optoelectronic neuromorphic computing applications.","url":"https://doi.org/10.1002/rpm.20240038","authors":["Huazhen Sun","Bingjie Ye","Mei Ge","Biao Gong","Leyang Qian","Irina N. Parkhomenko","Fadei F. Komarov","Yu Liu","Guofeng Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-11T09:05:24Z","doi":"10.1002/rpm.20240038","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1039/d4tc04535a","name":"Photoelectric memristor based on a PZT/NSTO heterojunction for neuromorphic computing applications","source":"crossref","abstract":"Inspired by the human brain and visual system, neuromorphic computing based on a photoelectric memristor overcomes the limitations of the traditional von Neumann architecture and has attracted the interest of researchers.","url":"https://doi.org/10.1039/d4tc04535a","authors":["Jingjuan Wang","Zhaowen Wang","Wenze Zhao","Xiaobing Yan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-30T06:40:56Z","doi":"10.1039/d4tc04535a","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1021/acsaelm.6c01218","name":"MoS2-Based Synaptic Transistor for Neuromorphic Computing and Encoded Optical Communication","source":"crossref","abstract":"Abstract Two-dimensional (2D) transition metal dichalcogenides (TMDs) have attracted considerable attention for next-generation electronic and optoelectronic devices due to their atomically thin structure, tunable bandgap, and strong light-matter interactions. In this work, we present a facile approach by employing 2D molybdenum disulfide (MoS2) to fabricate an optoelectronic artificial synapse, emphasizing its potential for neuromorphic computing and encoded optical communication. The MoS2-based field-effect transistor (FET) exhibits n-type semiconducting behavior with a current on/off ratio (ION/IOFF) of ∼2.5 × 108 and a large clockwise hysteresis in its transfer characteristics arising from charge trapping defects at the MoS2/SiO2 interface. A memory window of ∼41 V is observed under a gate voltage sweep range of ±60 V, and the memory effect can be gradually modulated from 1 V to 41 V by varying the sweeping range of the Si gate from ±10 to ±60 V. The device demonstrates optically controllable synaptic plasticity under 365 nm UV stimulation, exhibiting key neuromorphic functionalities such as paired-pulse facilitation (PPF), excitatory postsynaptic current (EPSC), spike-number-dependent plasticity (SNDP), and spike-time-dependent plasticity (STDP). Furthermore, the proposed MoS2 synaptic transistor enables encoded optical communication based on temporal pulse-width modulation, where optically encoded signals are directly decoded through distinct EPSC responses. This capability highlights the robustness of the device for optically encoded information processing and its potential for low-power encoded communication, neuromorphic photonic interfaces, and brain-inspired computing systems.","url":"https://doi.org/10.1021/acsaelm.6c01218","authors":["Jaehyeop Lee","Minsu Kim","Muhammad Nasim","Chiyoung Kim","Muhammad Asghar Khan","Jae Cheol Shin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-13T13:01:59Z","doi":"10.1021/acsaelm.6c01218","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1063/5.0256082","name":"Visible light-driven synaptic transistors based on bilayer InGaZnO homojunction for neuromorphic computing","source":"crossref","abstract":"The development of photoelectric synaptic transistors (PSTs) using visible light-driven mimicking synaptic behaviors represents a key advancement toward biomimetic visual systems. This study proposes a PST based on bilayer indium-gallium-zinc-oxide (IGZO) homojunctions with tunable gallium ratios. By optimizing the gallium content, oxygen vacancy concentrations in the channel were precisely controlled, suppressing deionization processes and enhancing device performance. The IGZO homojunction PST demonstrated outstanding electrical characteristics (Ion/Ioff = 1.2 × 107, μ = 3.88 cm2/Vs, Vth = 0 V) and exhibited high photocurrent and robust persistent photoconductivity under visible light. The device mimicked various synaptic behaviors, including excitatory postsynaptic current, paired-pulse facilitation, the transition from short-term plasticity to long-term plasticity, spiking-rate-dependent plasticity, and spike-timing-dependent plasticity. Furthermore, leveraging the potentiation and depression behaviors of the IGZO homojunction PST, a triple-layer neural network achieved 96.8% accuracy in pattern recognition tasks. These results underscore the IGZO homojunction PST's immense potential for advancing artificial vision systems.","url":"https://doi.org/10.1063/5.0256082","authors":["Zezhong Yin","Liuyue Shan","Ranran Ci","Dandan Hao","Guangtan Miao","Likun Tian","Guoxia Liu","Fukai Shan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-10T11:00:18Z","doi":"10.1063/5.0256082","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1016/j.vlsi.2017.10.009","name":"Monolithic 3D neuromorphic computing system with hybrid CMOS and memristor-based synapses and neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.vlsi.2017.10.009","authors":["Hongyu An","M. Amimul Ehsan","Zhen Zhou","Fangyang Shen","Yang Yi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-11-01T05:15:24Z","doi":"10.1016/j.vlsi.2017.10.009","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.23919/edhpc59100.2023.10396391","name":"EDGX-1: A New Frontier in Onboard AI Computing with a Heterogeneous and Neuromorphic Design","source":"crossref","abstract":"","url":"https://doi.org/10.23919/edhpc59100.2023.10396391","authors":["Nick Destrycker","Wouter Benoot","João Mattias","Ivan Rodriguez","David Steenari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-23T20:44:04Z","doi":"10.23919/edhpc59100.2023.10396391","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.3389/fnins.2021.698635","name":"Markov Chain Abstractions of Electrochemical Reaction-Diffusion in Synaptic Transmission for Neuromorphic Computing","source":"crossref","abstract":"Progress in computational neuroscience toward understanding brain function is challenged both by the complexity of molecular-scale electrochemical interactions at the level of individual neurons and synapses and the dimensionality of network dynamics across the brain covering a vast range of spatial and temporal scales. Our work abstracts an existing highly detailed, biophysically realistic 3D reaction-diffusion model of a chemical synapse to a compact internal state space representation that maps onto parallel neuromorphic hardware for efficient emulation at a very large scale and offers near-equivalence in input-output dynamics while preserving biologically interpretable tunable parameters.","url":"https://doi.org/10.3389/fnins.2021.698635","authors":["Margot Wagner","Thomas M. Bartol","Terrence J. Sejnowski","Gert Cauwenberghs"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-01T08:21:20Z","doi":"10.3389/fnins.2021.698635","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1038/s41467-018-04485-1","name":"Signal and noise extraction from analog memory elements for neuromorphic computing","source":"crossref","abstract":"Abstract Dense crossbar arrays of non-volatile memory (NVM) can potentially enable massively parallel and highly energy-efficient neuromorphic computing systems. The key requirements for the NVM elements are continuous (analog-like) conductance tuning capability and switching symmetry with acceptable noise levels. However, most NVM devices show non-linear and asymmetric switching behaviors. Such non-linear behaviors render separation of signal and noise extremely difficult with conventional characterization techniques. In this study, we establish a practical methodology based on Gaussian process regression to address this issue. The methodology is agnostic to switching mechanisms and applicable to various NVM devices. We show tradeoff between switching symmetry and signal-to-noise ratio for HfO 2 -based resistive random access memory. Then, we characterize 1000 phase-change memory devices based on Ge 2 Sb 2 Te 5 and separate total variability into device-to-device variability and inherent randomness from individual devices. These results highlight the usefulness of our methodology to realize ideal NVM devices for neuromorphic computing.","url":"https://doi.org/10.1038/s41467-018-04485-1","authors":["N. Gong","T. Idé","S. Kim","I. Boybat","A. Sebastian","V. Narayanan","T. Ando"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-05-22T15:42:59Z","doi":"10.1038/s41467-018-04485-1","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1088/2634-4386/ae9215","name":"NeuRehab: a reinforcement learning and spiking neural network-based rehab automation framework","source":"crossref","abstract":"Abstract Recent advancements in robotic rehabilitation therapy have provided modular exercise systems for post-stroke muscle recovery with basic control schemes. But these systems struggle to adapt to patients’ complex and ever-changing behaviour, and to operate within mobile settings, such as heat and power constraints. To aid this, we present NeuRehab: an end-to-end framework consisting of a training and inference pipeline with AI-based automation, co-designed with neuromorphic computing-based control systems that balance action performance, power consumption, and observed latency. The framework consists of 2 partitions. One is designated for the rehabilitation device based on ultra-low-power spiking networks deployed on dedicated neuromorphic hardware. The other resides on stationary hardware that can accommodate computationally intensive hardware for fine-tuning on a per-patient basis. By maintaining a communication channel between both the modules and splitting the algorithm components, the power and latency requirements of the movable system have been optimised, while retaining the learning performance advantages of compute- and power-hungry hardware on the stationary machine. As part of the theoretical framework definition, we propose (a) the split machine learning processes for efficiency in architectural utilisation, and (b) task-specific temporal optimisations to lower edge-inference control latency. This paper evaluates the proposed optimisation methods on a reference stepper motor-based shoulder exercise in an assist-as-needed scenario, which is presented as a challenging use case for a spiking neural network-based control system. Overall, these methods offer comparable performance uplifts over the State-of-the-art for neuromorphic deployment in terms of spike counts and time steps, leading to theoretical gains in power and latency.","url":"https://doi.org/10.1088/2634-4386/ae9215","authors":["Phani Pavan Kambhampati","Chainesh Gautam","Jagan P","Madhav Rao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-29T22:50:54Z","doi":"10.1088/2634-4386/ae9215","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1002/aelm.202500370","name":"Solution‐Processed Bi\n                    <sub>2</sub>\n                    S\n                    <sub>3</sub>\n                    Nanostructures for Flexible Memory and Neuromorphic Computing","source":"crossref","abstract":"Abstract The rapid advancement of wearable computing and edge AI technologies is driving the need for low‐temperature, flexible, and neuromorphic‐compatible electronic materials. In this work, the successful low‐temperature deposition of Bi 2 S 3 thin films via an in situ solvothermal method using the single‐source precursor (SSP) [Bi(S 2 P(OC 3 H₇) 2 ) 3 ] is reported. This solution‐processed approach enables the formation of high‐quality, crystalline, and stoichiometric Bi 2 S 3 films over a broad temperature window (140–200 °C), compatible with a range of substrates including silicon, polyimide, and PET. Leveraging this deposition technique, Bi 2 S 3 ‐based memristors are fabricated on both rigid and flexible substrates. The devices exhibit stable resistive switching behavior and demonstrate mechanical and electrical robustness under stress conditions. Furthermore, the memristors effectively emulate long‐term synaptic plasticity, achieving high learning accuracy. These findings establish SSP‐derived Bi 2 S 3 films as a promising material platform for next‐generation flexible neuromorphic computing and memory technologies.","url":"https://doi.org/10.1002/aelm.202500370","authors":["Sayali Shrishail Harke","Omesh Kapur","Peng Dai","Tongjun Zhang","Bingkai Ding","Bohao Ding","Ruomeng Huang","Chitra Gurnani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T10:15:07Z","doi":"10.1002/aelm.202500370","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1007/s12633-026-03764-7","name":"A p-n Junction Gate DRAM for Non-Destructive and Linear Synaptic Modulation in Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s12633-026-03764-7","authors":["Eungi Hwang","Ilho Myeong","Garam Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-04T01:59:43Z","doi":"10.1007/s12633-026-03764-7","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1016/j.nanoen.2025.111276","name":"Synaptic metaplasticity and associative learning in low-power neuromorphic computing using W-diffused BaTiO₃ memristors","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.nanoen.2025.111276","authors":["Muhammad Ismail","Hyesung Na","Maria Rasheed","Chandreswar Mahata","Yoon Kim","Sungjun Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-24T19:28:43Z","doi":"10.1016/j.nanoen.2025.111276","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1039/d4nr01003e","name":"Multilayer ferromagnetic spintronic devices for neuromorphic computing applications","source":"crossref","abstract":"Spintronic devices, which are built upon ferromagnetic thin film systems, exhibit significant promise for energy-efficient memory, logic operations, and neuromorphic computing applications.","url":"https://doi.org/10.1039/d4nr01003e","authors":["Aijaz H. Lone","Xuecui Zou","Kishan K. Mishra","Venkatesh Singaravelu","R. Sbiaa","Hossein Fariborzi","Gianluca Setti"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-03T17:01:36Z","doi":"10.1039/d4nr01003e","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1515/9783111545950-004","name":"524 Modelling quantum transport in electronic devices: MOSFET, FinFET, NanowireFET","source":"crossref","abstract":"","url":"https://doi.org/10.1515/9783111545950-004","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-06T19:15:47Z","doi":"10.1515/9783111545950-004","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1109/smartgridcomm60555.2024.10738048","name":"Inferring Ingrained Remote Information in AC Power Flows Using Neuromorphic Modality Regime","source":"crossref","abstract":"","url":"https://doi.org/10.1109/smartgridcomm60555.2024.10738048","authors":["Xiaoguang Diao","Yubo Song","Subham Sahoo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-04T13:32:51Z","doi":"10.1109/smartgridcomm60555.2024.10738048","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/irps45951.2020.9128346","name":"Embracing the Unreliability of Memory Devices for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/irps45951.2020.9128346","authors":["Marc Bocquet","Tifenn Hirtzlin","Jacques-Olivier Klein","Etienne Nowak","Elisa Vianello","Jean-Michel Portal","Damien Querlioz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-30T17:20:26Z","doi":"10.1109/irps45951.2020.9128346","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/iccmc69250.2026.11624943","name":"Edge-Intelligent Wearable Respiratory Monitoring using Hypergraph Learning and Neuromorphic Signal Processing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccmc69250.2026.11624943","authors":["P. Poornimadevi","Jubaitha J","S.Mohan","Rajeshwari.M","Rubika V","Muthamizhselvi A"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-29T19:10:52Z","doi":"10.1109/iccmc69250.2026.11624943","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.2139/ssrn.4172877","name":"Spin-Orbit Torque Driven Memristor in Bulk L10 Fept System for Neuromorphic Computing","source":"crossref","abstract":"In this study, the memristor driven by spin-orbit torque (SOT) is realized in the bulk L1 0 FePt systems with high perpendicular magnetization anisotropy (PMA). Due to the domain nucleation and expansion driven by current pulses, multi-level Hall resistances can be continuously tuned by the current density, where the memristive states are retained by the domain wall pinning effects. The properties of multi-level resistances for samples with different structures are associated with the magnitude of field-like torque, and the larger efficiency of field-like torque enhances the multiple resistance characteristics. Furthermore, the memristive behaviors in the field-free condition are obtained by utilizing the interlayer exchange coupling. Finally, based on the memristive characteristics of our devices, the three-layer multilayer perceptron (MLP) neural network is built to perform the MNIST handwritten digit recognition task, and the accuracy of weight update can reach up to 88.55%. These results pave the way for the application of SOT-driven memristors in neuromorphic computing.","url":"https://doi.org/10.2139/ssrn.4172877","authors":["Ying Tao","Chao Sun","Wendi Li","Cen Wang","Fang Jin","Yue Zhang","Zhe Guo","Yuhong Zheng","Xiaoguang Wang","Kaifeng Dong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-07-27T03:03:49Z","doi":"10.2139/ssrn.4172877","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.29363/nanoge.matsusspring.2026.541","name":"Platinum Cluster-Assembled Thin Films for Neuromorphic Hardware","source":"crossref","abstract":"","url":"https://doi.org/10.29363/nanoge.matsusspring.2026.541","authors":["Stefano Radice","Francesca Borghi","Paolo Milani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-16T08:04:37Z","doi":"10.29363/nanoge.matsusspring.2026.541","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.23919/date.2017.7927030","name":"Robust neuromorphic computing in the presence of process variation","source":"crossref","abstract":"","url":"https://doi.org/10.23919/date.2017.7927030","authors":["Ali BanaGozar","Mohammad Ali Maleki","Mehdi Kamal","Ali Afzali-Kusha","Massoud Pedram"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-05-15T16:34:41Z","doi":"10.23919/date.2017.7927030","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.12928/telkomnika.v19i1.15026","name":"Fine-grained or coarse-grained? Strategies for implementing parallel genetic algorithms in a programmable neuromorphic platform","source":"crossref","abstract":"","url":"https://doi.org/10.12928/telkomnika.v19i1.15026","authors":["Indar Sugiarto","Steve Furber"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-11-23T07:43:33Z","doi":"10.12928/telkomnika.v19i1.15026","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.30693/smj.2022.11.2.77","name":"Reduction of Inference time in Neuromorphic Based Platform for IoT Computing Environments","source":"crossref","abstract":"","url":"https://doi.org/10.30693/smj.2022.11.2.77","authors":["Jaeseop Kim","Seungyeon Lee","Jiman Hong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-05T02:18:28Z","doi":"10.30693/smj.2022.11.2.77","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1088/2634-4386/ae7ab5","name":"Temporal hierarchy in spiking neural networks","source":"crossref","abstract":"Abstract Taking inspiration from the brain to design efficient computational systems remains challenging due to its complexity. This work investigates a key biological feature observed across mammals: a hierarchy of time scales in cortical areas. Experimental evidence shows that intrinsic neural dynamics slow down across the cortical hierarchy, forming a temporal hierarchy. We examine whether this property benefits artificial systems by introducing temporal hierarchy into spiking neural networks (SNNs), which inherently process information over time. We implement hierarchical time scales across neuronal, synaptic, and recurrent dynamics, and evaluate their effect under two settings: (1) as an inductive bias, and (2) as an emergent property through optimization. On temporal benchmarks such as multi-timescale-XOR and keyword spotting, hierarchical SNNs consistently outperform non-hierarchical ones, achieving 2%–6% higher accuracy and up to 5 × parameter reduction under iso-accuracy conditions. Moreover, when trained freely, temporal hierarchy emerges spontaneously through gradient descent. Finally, our theoretical analysis shows that hierarchical time constants enable processing of multi-frequency temporal signals with only log N layers—compared to N layers for non-hierarchical systems—highlighting hierarchy as a key organizational principle for efficient temporal computation.","url":"https://doi.org/10.1088/2634-4386/ae7ab5","authors":["Filippo Moro","Pau Vilimelis Aceituno","Laura Kriener","Melika Payvand"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-09T22:52:55Z","doi":"10.1088/2634-4386/ae7ab5","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1016/j.nanoen.2024.110555","name":"Nanoscale sliding modulated SrCoOx-based neuromorphic memory device","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.nanoen.2024.110555","authors":["Lele Ren","Mengmeng Jia","Shidai Tian","Junyi Zhai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-12T16:49:59Z","doi":"10.1016/j.nanoen.2024.110555","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.36463/idw.2023.0411","name":"Zinc Tin Oxide based Synaptic Transistors with Ion-Gel Gate Insulator for Neuromorphic Computing Application","source":"crossref","abstract":"","url":"https://doi.org/10.36463/idw.2023.0411","authors":["Shao Shiun Liao","Chen -Yu Hsu","Yu -Wu Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-27T22:13:36Z","doi":"10.36463/idw.2023.0411","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1515/9783111545950-001","name":"11 Some ideas on modern quantum and brain-inspired devices","source":"crossref","abstract":"","url":"https://doi.org/10.1515/9783111545950-001","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-06T19:15:47Z","doi":"10.1515/9783111545950-001","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1109/spi68887.2026.11594678","name":"Design and Simulation of Stretchable Crossbar Array for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/spi68887.2026.11594678","authors":["Twinkel Manna","Gulafsha Bhatti","Aakanksha Verma","Sourajeet Roy","Yash Agrawal","Rohit Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-09T19:41:48Z","doi":"10.1109/spi68887.2026.11594678","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.29363/nanoge.matsusspring.2025.362","name":"Three-terminal neuromorphic synaptic devices leveraging electrochemical reactions and ferroelectric switching dynamics","source":"crossref","abstract":"","url":"https://doi.org/10.29363/nanoge.matsusspring.2025.362","authors":["Jiyong Woo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-01T13:55:38Z","doi":"10.29363/nanoge.matsusspring.2025.362","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1109/icac353642.2021.9697146","name":"Layout of a Neuromorphic Integrated Circuit for Differential Motion Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icac353642.2021.9697146","authors":["Vinay Vishnani","Lance Fernandes","Omkar Deshmukh","Payal Shah","S. S. Rathod"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-07T21:15:07Z","doi":"10.1109/icac353642.2021.9697146","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/isemc.2017.8077966","name":"Modeling and analysis of neuronal membrane electrical activities in 3d neuromorphic computing system","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isemc.2017.8077966","authors":["M. Amimul Ehsan","Zhen Zhou","Yang Yi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-10-26T17:59:51Z","doi":"10.1109/isemc.2017.8077966","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1002/idm2.12244","name":"High‐Performance Memristors Based on Ordered Imine‐Linked Two‐Dimensional Covalent Organic Frameworks for Neuromorphic Computing","source":"crossref","abstract":"ABSTRACT Covalent organic frameworks (COFs) have emerged as highly promising materials for high‐performance memristors due to their exceptional stability, molecular design flexibility, and tunable pore structures. However, the development of COF memristors faces persistent challenges stemming from the structural disorder and quality control of COF films, which hinder the effective regulation of active metal ion migration during resistive switching. Herein, we report the synthesis of high‐quality, long‐range ordered, imine‐linked two‐dimensional (2D) COF TP‐TD film via the innovative surface‐initiated polymerization (SIP) strategy. The long‐range ordered one‐dimensional (1D) nanochannels within 2D COF TP‐TD film facilitate the stable and directed growth of conductive filaments (CFs), further enhanced by imine–CFs coordination effects. As a result, the fabricated memristor devices exhibit exceptional multilevel nonvolatile memory performance, achieving an ON/OFF ratio of up to 10 6 and a retention time exceeding 2.0 × 10 5 s, marking a significant breakthrough in porous organic polymer (POP) memristors. Furthermore, the memristors demonstrate high‐precision waveform data recognition with an accuracy of 92.17%, comparable to software‐based recognition systems, highlighting its potential in advanced signal processing tasks. This study establishes a robust foundation for the development of high‐performance COF memristors and significantly broadens their application potential in neuromorphic computing.","url":"https://doi.org/10.1002/idm2.12244","authors":["Da Huo","Zhangjie Gu","Bailing Song","Yimeng Yu","Mengqi Wang","Lanhao Qin","Huicong Li","Decai Ouyang","Shikun Xiao","Wenhua Hu","Jinsong Wu","Yuan Li","Xiaodong Chi","Tianyou Zhai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-07T07:16:18Z","doi":"10.1002/idm2.12244","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1088/2634-4386/adcbcc","name":"Mixed photonic/electronic neural network based on microLED arrays","source":"crossref","abstract":"Abstract We present a novel approach for the implementation of a mixed photonic/electronic neural network using gallium nitride based microLEDs as an efficient key element. The system is fully analog, with the synaptic fan-out and weighting implemented in free-space optics, while the fan-in and nonlinear activation functions are realized by optoelectronic components. Activations are represented by patterns of incoherent light generated by microLED arrays. Spatial light modulators represent the weighting matrices in the optical path, and the summation of the weighted activations is realized by photodetectors. We practically demonstrate our approach with a prototype, implementing a single-layer artificial neural network for the classification of the MNIST dataset. A test accuracy of 86.8 % is achieved. A key feature of this photonic/electronic implementation is that an efficient conversion between the electrical and optical domains is realized by microLEDs, combining the advantages of the efficiency of synaptic connections through optics and nonlinear activation functions in electronics, which have the potential for miniaturization and integration. We estimate, that an upscaled version of our prototype can achieve an energy efficiency of around 14 fJ per multiply-accumulate operation using state-of-the-art microLEDs. Finally we present a scalability analysis, showing that for a fully connected layer, for which a total of N multiply-accumulate operations have to be performed, in the average case the energy requirement scales with O ( N ) , while the energy requirement of conventional computers, as well as digital neuromorphic computing approaches, scales with O ( N ) . Therefore, we suggest to follow this approach in order to fully exploit the potential of mixed optical/electrical neuromorphic systems and possibly demonstrate superiority over conventional GPUs.","url":"https://doi.org/10.1088/2634-4386/adcbcc","authors":["M Müller","R Kraneis","N Kälin","N von Malm","A Waag","C Werner"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-11T22:50:44Z","doi":"10.1088/2634-4386/adcbcc","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1109/ijcnn64981.2025.11228713","name":"Stability-aware Neuromorphic Computation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn64981.2025.11228713","authors":["Egor E. Nuzhin","Ivan Tyukin","Georgii Ovchinnikov","Nikolay V. Brilliantov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T18:46:15Z","doi":"10.1109/ijcnn64981.2025.11228713","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1109/tsusc.2017.2717807","name":"Enabling Sustainable Cyber Physical Security Systems through Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tsusc.2017.2717807","authors":["Jialing Li","Lingjia Liu","Chenyuan Zhao","Kian Hamedani","Rachad Atat","Yang Yi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-06-20T18:22:34Z","doi":"10.1109/tsusc.2017.2717807","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1088/2634-4386/ac90e5","name":"Acoustic scene analysis using analog spiking neural network","source":"crossref","abstract":"Abstract Sensor nodes in a wireless sensor network for security surveillance applications should preferably be small, energy-efficient, and inexpensive with in-sensor computational abilities. An appropriate data processing scheme in the sensor node reduces the power dissipation of the transceiver through the compression of information to be communicated. This study attempted a simulation-based analysis of human footstep sound classification in natural surroundings using simple time-domain features. The spiking neural network (SNN), a computationally low-weight classifier derived from an artificial neural network (ANN), was used to classify acoustic sounds. The SNN and required feature extraction schemes are amenable to low-power subthreshold analog implementation. The results show that all analog implementations of the proposed SNN scheme achieve significant power savings over the digital implementation of the same computing scheme and other conventional digital architectures using frequency-domain feature extraction and ANN-based classification. The algorithm is tolerant of the impact of process variations, which are inevitable in analog design, owing to the approximate nature of the data processing involved in such applications. Although SNN provides low-power operation at the algorithm level, ANN to SNN conversion leads to an unavoidable loss of classification accuracy of ∼5%. We exploited the low-power operation of the analog processing SNN module by applying redundancy and majority voting, which improved the classification accuracy, taking it close to the ANN model.","url":"https://doi.org/10.1088/2634-4386/ac90e5","authors":["Anand Kumar Mukhopadhyay","Moses Prabhakar Naligala","Divya Lakshmi Duggisetty","Indrajit Chakrabarti","Mrigank Sharad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-09T22:19:07Z","doi":"10.1088/2634-4386/ac90e5","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/icnc64304.2024.10987607","name":"Emotion-Driven Memcapacitor Biomimetic Circuit for Reinforcement Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987607","authors":["Haotong Zhou","Kefan Tao","Junwei Sun","Yanfeng Wang","Peng Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987607","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1007/978-3-032-09586-2_3","name":"Related Work","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-09586-2_3","authors":["Felix Staudigl","Rainer Leupers"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-22T14:22:01Z","doi":"10.1007/978-3-032-09586-2_3","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1149/ma2019-02/29/1272","name":"GaN-Based Dilute Magnetic Semiconductors for Room Temperature Neuromorphic and Quantum Computing","source":"crossref","abstract":"Neuromorphic computing and quantum computing are attracting more research attention in recent years. Neuromorphic computing mimic the quantum decoherence for neuron firing and the microtubule processes, and artificially recreating the highly parallel computing architecture of the mammalian brain. Quantum computing is also of great interest for next generation of micro- and nano-electronic devices with enhanced functionalities, which involves the mathematical analysis, algorithmic manipulation, storage, and transmission of the fundamental unit of quantum information, the qubit. However, most of the current quantum computing and neuromorphic computing systems operate at cryogenic temperatures to avoid thermal activation, which limits their wide application. Spintronic devices, exploiting electron spin as a further degree of freedom in addition to the electronic charge, have shown to be promising for quantum information processing and modeling brain-like systems, realizing device-level components for quantum computing and neuromorphic computing applications. In addition, wide bandgap dilute magnetic semiconductors (DMS) have the potential for room temperature (RT) spintronic applications. Gallium nitride (GaN) based DMS are promising materials for spintronic applications due to their theoretically predicted and experimentally observed ferromagnetic properties at RT [1]. In this work, MOCVD-grown Gd-doped GaN showed ferromagnetic hysteresis in vibrating sample magnetometry measurement and Anomalous Hall Effect (AHE) measurement at room temperature. AHE measurement of samples with different carrier densities showed a superlinear relation between anomalous Hall conductivity σ AHE and lateral conductivity σ xx , σ AHE ∝σ xx 1.78 , which indicates the mechanism for the ferromagnetism is intrinsic and likely mediated by free carriers [2], which is conducive for spintronic applications. However, the ferromagnetism is only observed in GaGdN grown using a (TMHD) 3 Gd precursor, which contains oxygen in its organic ligand that appears to be incorporated into the GaGdN. The role of oxygen in the ferromagnetic properties was predicted in density functional theory calculations, which show that elements such as oxygen and carbon, when incorporated into GaGdN could result in p-d hybridization of the p-orbitals of oxygen or carbon with the d-orbitals of Gd; oxygen or carbon could introduce deep localized states close to the Fermi level in GaGdN that couple with Gd states to render ferromagnetism [3,4]. In order to experimentally examine the role of oxygen or carbon in the ferromagnetic properties of GaGdN, oxygen and carbon are implanted in GaGdN originally grown using a Cp 3 Gd precursor that does not contain oxygen. As-grown GaGdN from Cp 3 Gd source, which does not contain O, is not ferromagnetic but post-implantation with O or C does result in ferromagnetism. X-ray diffraction of the implanted GaGdN samples exhibits good crystal quality, and peak shifts as compared to the GaGdN before implantation showing signs of O or C incorporation. Annealing the implanted GaGdN activates the dopant, improves the crystal quality, and shows clear signs of AHE. These results show that oxygen or carbon could have a significant role in rendering the intrinsic and potentially free carrier-mediated ferromagnetism in GaGdN at RT. A better understanding of the mechanism for RT ferromagnetism will enable these DMS materials to build spintronic devices, such as memristive, spin-transfer torque, and non-volatile memory spintronic devices have tremendous applications in neuromorphic computing and quantum computing applications. References Kane, S. Gupta and I. Ferguson, “Transition metal and rare earth doping in GaN”, Woodhead publishing, (2016). Saravade, C. Ferguson, A. Ghods, C. Zhou, and I. Ferguson, MRS Adv. 3 (3), p. 159, (2018). Liu, X. Yi, J. Wang, J. Kang, A. Melton, Y. Shi, N. Lu, J. Wang, J. Li, and I. Ferguson, Appl. Phys. Lett. 100 (23), 232408, (2012). ","url":"https://doi.org/10.1149/ma2019-02/29/1272","authors":["Chuanle Zhou","Amirhossein Ghods","Vishal G. Saravade","Ian Ferguson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-02-27T12:06:50Z","doi":"10.1149/ma2019-02/29/1272","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1117/12.3009156","name":"Experimental demonstration of silicon-based on-chip neuromorphic optical computing","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3009156","authors":["Junhyeong Kim","Seokjin Hong","Jaeyong Kim","Berkay Neseli","Jinhyeong Yoon","Hyo-Hoon Park","Hamza Kurt"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-25T21:52:41Z","doi":"10.1117/12.3009156","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1088/2634-4386/ad64fd","name":"Reducing the spike rate of deep spiking neural networks based on time-encoding","source":"crossref","abstract":"Abstract A primary objective of Spiking Neural Networks is a very energy-efficient computation. To achieve this target, a small spike rate is of course very beneficial given the event-driven nature of such a computation. A network that processes information encoded in spike timing can, by its nature, have such a sparse event rate, but, as the network becomes deeper and larger, the spike rate tends to increase without any improvements in the final accuracy. If, on the other hand, a penalty on the excess of spikes is used during the training, the network may shift to a configuration where many neurons are silent, thus affecting the effectiveness of the training itself. In this paper, we present a learning strategy to keep the final spike rate under control by changing the loss function to penalize the spikes generated by neurons after the first ones. Moreover, we also propose a 2-phase training strategy to avoid silent neurons during the training, intended for benchmarks where such an issue can cause the switch off of the network.","url":"https://doi.org/10.1088/2634-4386/ad64fd","authors":["Riccardo Fontanini","Alessandro Pilotto","David Esseni","Mirko Loghi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-18T22:53:08Z","doi":"10.1088/2634-4386/ad64fd","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1063/5.0049161","name":"Halide perovskite two-terminal analog memristor capable of photo-activated synaptic weight modulation for neuromorphic computing","source":"crossref","abstract":"Emulation of biological signal processing, learning and memory functions is essential for the development of artificial learning circuitry. Two terminal artificial synapses are supposed to be more feasible with biological system in terms of energy efficiency and processing. Here, we report on the fabrication of organic–inorganic hybrid perovskite based two-terminal artificial synapse in which the synaptic plasticity is modified by both voltage pulses and light illumination. The device emulates important synaptic characteristics, including analog memory switching, short-term plasticity, and long-term plasticity, analogous to the biological system. The change in conductance is attributed to the ion migration under external electric field. In addition, the improved post-synaptic current in optical exposer could be related to the generation of excitons and lowered Schottky barrier at perovskite/electrode interface under external electric field.","url":"https://doi.org/10.1063/5.0049161","authors":["Ujjal Das","Pranab Sarkar","Bappi Paul","Asim Roy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-05-07T09:42:48Z","doi":"10.1063/5.0049161","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.56042/ijpap.v63i8.17960","name":"Exploring the Active Realization of Analog Multi-Level Memristors for Neuromorphic Applications","source":"crossref","abstract":"","url":"https://doi.org/10.56042/ijpap.v63i8.17960","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-06T09:45:00Z","doi":"10.56042/ijpap.v63i8.17960","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.64189/ssc.25212","name":"The Unified Neuromorphic Assembly Layer for Hardware-Agnostic Compilation in Neuromorphic Computing","source":"crossref","abstract":"The programming of neuromorphic assembly has advanced steadily, providing essential tools and paradigms to help connect the gap between abstract Spiking Neural Network (SNN) models and brain-inspired computing hardware. This work presents UNAL (Unified Adaptive, Hardware-Agnostic Neuromorphic Assembly Layer). This compilation framework translates high-level Spiking Neural Network (SNN) models into portable, spike-level assembly across heterogeneous neuromorphic platforms. UNAL introduces a unified intermediate representation (UNAL-IR), a compact instruction set, and an optimization-driven mapping pipeline that jointly addresses latency, energy efficiency, routing congestion, and adaptability. Quantitative evaluation on standard SNN benchmarks (DVS Gesture and CIFAR-10 SNN) mapped to Intel Loihi 2 demonstrates 18–32% latency reduction, 21–38% energy savings, and 25–40% lower routing congestion compared to Loihi-native and platform-specific tool chains. A smart-city surveillance case study further validates the deployment of real-time edge computing. These results establish UNAL as a scalable and future-ready neuromorphic compiler infrastructure.","url":"https://doi.org/10.64189/ssc.25212","authors":["Ganesh D. Jadhav","Rahul V. Dagade","Sushant Jakhade","Kshitij Jadhav","Rutu Hinge","Swarada Joshi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-30T14:01:46Z","doi":"10.64189/ssc.25212","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:20.022Z"},{"id":"doi:10.1109/aspdac.2017.7858418","name":"Classification accuracy improvement for neuromorphic computing systems with one-level precision synapses","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aspdac.2017.7858418","authors":["Yandan Wang","Wei Wen","Linghao Song","Hai Helen Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-02-20T16:36:54Z","doi":"10.1109/aspdac.2017.7858418","addedAt":"2026-09-01T01:48:20.022Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1002/aidi.70059","name":"Advances in Organic In‐Sensor Neuromorphic Computing: from Material Mechanisms to Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1002/aidi.70059","authors":["Dong Hyun Lee","Woojo Kim","Eun Kwang Lee","Hocheon Yoo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-09T01:16:29Z","doi":"10.1002/aidi.70059","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1007/978-3-662-54345-0_4","name":"Invited Talk: Neuromorphic Computing Principles, Achievements, and Potentials","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-662-54345-0_4","authors":["Karlheinz Meier"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-02-28T08:33:22Z","doi":"10.1007/978-3-662-54345-0_4","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/jxcdc.2019.2913526","name":"Special Topic on Nonvolatile Memory for Efficient Implementation of Neural/Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/jxcdc.2019.2913526","authors":["Shimeng Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-06-07T20:12:23Z","doi":"10.1109/jxcdc.2019.2913526","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/icnc59488.2023.10462736","name":"Automatic Quality Evaluation for User Generated Contents in Online Q&amp;A Community Based on Word2Vec-CNN","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462736","authors":["Yanni Yang","Yiting Tan","Yang Yang","Zhengwei Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462736","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1007/978-3-642-34475-6_43","name":"The Circuit Realization of a Neuromorphic Computing System with Memristor-Based Synapse Design","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-34475-6_43","authors":["Beiye Liu","Yiran Chen","Bryant Wysocki","Tingwen Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-11-05T08:33:26Z","doi":"10.1007/978-3-642-34475-6_43","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1149/ma2022-0215808mtgabs","name":"(Digital Presentation) Oxide Memristors Based on SiO<sub>2</sub> with Cu/Ag Alloy Metallization for Neuromorphic Computing","source":"crossref","abstract":"By mimicking biomimetic synaptic processes, the success of artificial intelligence (AI) has been astounding with various applications such as driving automation, big data analysis, and natural-language processing.[1-4] Due to a large quantity of data transmission between the separated memory unit and the logic unit, the classical computing system with von Neumann architecture consumes excessive energy and has a significant processing delay.[5] Furthermore, the speed difference between the two units also causes extra delay, which is referred to as the \"memory wall\".[6, 7] To keep pace with the rapid growth of AI applications, enhanced hardware systems that particularly feature an energy-efficient and high-speed hardware system need to be secured. The novel neuromorphic computing system, an in-memory architecture with low power consumption, has been suggested as an alternative to the conventional system. Memristors with analog-type resistive switching behavior are a promising candidate for implementing the neuromorphic computing system since the devices can modulate the conductance with cycles that act as synaptic weights to process input signals and store information.[8, 9] The memristor has sparked tremendous interest due to its simple two-terminal structure, including top electrode (TE), bottom electrode (BE), and an intermediate resistive switching (RS) layer. Many oxide materials, including HfO 2 , Ta 2 O 5 , and IGZO, have extensively been studied as an RS layer of memristors. Silicon dioxide (SiO 2 ) features 3D structural conformity with the conventional CMOS technology and high wafer-scale homogeneity, which has benefited modern microelectronic devices as dielectric and/or passivation layers. Therefore, the use of SiO 2 as a memristor RS layer for neuromorphic computing is expected to be compatible with current Si technology with minimal processing and material-related complexities. In this work, we proposed SiO 2 -based memristor and investigated switching behaviors metallized with different reduction potentials by applying pure Cu and Ag, and their alloys with varied ratios. Heavily doped p-type silicon was chosen as BE in order to exclude any effects of the BE ions on the memristor performance. We previously reported that the selection of TE is crucial for achieving a high memory window and stable switching performance. According to the study which compares the roles of Cu (switching stabilizer) and Ag (large switching window performer) TEs for oxide memristors, we have selected the TE materials and their alloys to engineer the SiO 2 -based memristor characteristics. The Ag TE leads to a larger memory window of the SiO 2 memristor, but the device shows relatively large variation and less reliability. On the other hand, the Cu TE device presents uniform gradual switching behavior which is in line with our previous report that Cu can be served as a stabilizer, but with small on/off ratio.[9] These distinct performances with Cu and Ag metallization leads us to utilize a Cu/Ag alloy as the TE. Various compositions of Cu/Ag were examined for the optimization of the memristor TEs. With a Cu/Ag alloying TE with optimized ratio, our SiO 2 based memristor demonstrates uniform switching behavior and memory window for analog switching applications. Also, it shows ideal potentiation and depression synaptic behavior under the positive/negative spikes (pulse train). In conclusion, the SiO 2 memristors with different metallization were established. To tune the property of RS layer, the sputtering conditions of RS were varied. To investigate the influence of TE selections on switching performance of memristor, we integrated Cu, Ag and Cu/Ag alloy as TEs and compared the switch characteristics. Our encouraging results clearly demonstrate that SiO 2 with Cu/Ag is a promising memristor device with synaptic switching behavior in neuromorphic computing applications. Acknowledgement This work was supported by the U.S. National Science Fou","url":"https://doi.org/10.1149/ma2022-0215808mtgabs","authors":["Fei Qin","Han Wook Song"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-23T19:57:33Z","doi":"10.1149/ma2022-0215808mtgabs","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.2172/2430456","name":"Dendritic Computation for Neuromorphic Applications","source":"crossref","abstract":"","url":"https://doi.org/10.2172/2430456","authors":["Suma Cardwell","Frances Chance"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-11T20:52:57Z","doi":"10.2172/2430456","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1145/3701701.3701712","name":"A Neuromorphic Radar Sensor for Low-Power IoT Systems","source":"crossref","abstract":"As radar sensors become an integral component of Internet of Things (IoT) systems, the challenge of high power consumption poses a significant barrier, especially for battery-operated devices. This article introduces NeuroRadar, a groundbreaking solution that leverages a radar front-end capable of generating spike sequences, which can be efficiently processed by energy-saving Spiking Neural Networks (SNNs). We explore the innovative design and implementation of NeuroRadar, showcasing its effectiveness in applications like gesture recognition and human tracking. By achieving dramatically lower power consumption compared to traditional radar systems, NeuroRadar represents a new paradigm in energy-efficient IoT sensing.","url":"https://doi.org/10.1145/3701701.3701712","authors":["Kai Zheng","Kun Qian","Timothy Woodford","Xinyu Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-22T22:26:35Z","doi":"10.1145/3701701.3701712","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/icnc52316.2021.9608036","name":"Exponential Synchronization of Nonlinear Interconnected Reaction-Diffusion Memristive NNs under Stochastic Cyber Attacks via Pointwise Control","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc52316.2021.9608036","authors":["Xiaona Song","Jingtao Man","Shuai Song"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-29T20:59:32Z","doi":"10.1109/icnc52316.2021.9608036","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1016/j.compeleceng.2017.06.023","name":"Three dimensional memristor-based neuromorphic computing system and its application to cloud robotics","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.compeleceng.2017.06.023","authors":["Hongyu An","Jialing Li","Ying Li","Xin Fu","Yang Yi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-08-01T23:00:35Z","doi":"10.1016/j.compeleceng.2017.06.023","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1007/s40820-021-00618-2","name":"Memristive Artificial Synapses for Neuromorphic Computing","source":"crossref","abstract":"Abstract Neuromorphic computing simulates the operation of biological brain function for information processing and can potentially solve the bottleneck of the von Neumann architecture. This computing is realized based on memristive hardware neural networks in which synaptic devices that mimic biological synapses of the brain are the primary units. Mimicking synaptic functions with these devices is critical in neuromorphic systems. In the last decade, electrical and optical signals have been incorporated into the synaptic devices and promoted the simulation of various synaptic functions. In this review, these devices are discussed by categorizing them into electrically stimulated, optically stimulated, and photoelectric synergetic synaptic devices based on stimulation of electrical and optical signals. The working mechanisms of the devices are analyzed in detail. This is followed by a discussion of the progress in mimicking synaptic functions. In addition, existing application scenarios of various synaptic devices are outlined. Furthermore, the performances and future development of the synaptic devices that could be significant for building efficient neuromorphic systems are prospected.","url":"https://doi.org/10.1007/s40820-021-00618-2","authors":["Wen Huang","Xuwen Xia","Chen Zhu","Parker Steichen","Weidong Quan","Weiwei Mao","Jianping Yang","Liang Chu","Xing’ao Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-06T07:03:03Z","doi":"10.1007/s40820-021-00618-2","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.23919/aise.2025.000002","name":"Neuromorphic Computing in the Era of Large Models","source":"crossref","abstract":"","url":"https://doi.org/10.23919/aise.2025.000002","authors":["Haoxuan SHAN","Chiyue WEI","Nicolas RAMOS","Xiaoxuan YANG","Cong GUO","Hai LI","Yiran CHEN"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-30T23:26:44Z","doi":"10.23919/aise.2025.000002","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/icnc52316.2021.9608170","name":"Parameter estimation of fractional-order memristor-based chaotic systems using state transition algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc52316.2021.9608170","authors":["Zhaoke Huang","Xiaojun Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-29T20:59:32Z","doi":"10.1109/icnc52316.2021.9608170","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/emergin67762.2025.11450669","name":"Efficient AI Systems through Neuromorphic Computing: Bridging Biological Intelligence and Machine Learning","source":"crossref","abstract":"The growing computational requirement of artificial intelligence (AI) mock-ups creates challenges in energy efficacy, scalability, and inactivity. Traditional AI architectures built on von Neumann structures and experience integral restrictions in imitating the human brain's competence. Neuromorphic computing, encouraged by biological neuronal structures, appears as a promising substitute for developing less-power, highly efficient AI systems. This paper explores neuromorphic computing architectures and their application to machine learning tasks using spiking neural networks (SNNs). This paper provides a thorough review on the present work along with the limitations. At the end paper also provided the details of future scope of neuromorphic computing in developing AI systems.","url":"https://doi.org/10.1109/emergin67762.2025.11450669","authors":["Aparna Sharma","Bhavesh Kumar Sharma","Shashi Bhushan","Vishvendra Pal Singh Nagar","Virendra Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-30T20:03:06Z","doi":"10.1109/emergin67762.2025.11450669","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1145/2627369.2627625","name":"SPINDLE","source":"crossref","abstract":"","url":"https://doi.org/10.1145/2627369.2627625","authors":["Shankar Ganesh Ramasubramanian","Rangharajan Venkatesan","Mrigank Sharad","Kaushik Roy","Anand Raghunathan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-08-01T20:13:39Z","doi":"10.1145/2627369.2627625","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/icnc52316.2021.9608693","name":"Memristor-Based Neural Network Circuit of Long-term Memory","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc52316.2021.9608693","authors":["Juntao Han","Junwei Sun","Xiao Xiao","Peng Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-29T20:59:32Z","doi":"10.1109/icnc52316.2021.9608693","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/esscirc55480.2022.9911305","name":"Ferroelectric Schottky Barrier MOSFET as Analog Synapses for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/esscirc55480.2022.9911305","authors":["Fengben Xi","Andreas Grenmy","Jiayuan Zhang","Yi Han","Jin Hee Bae","Detlev Grutzmacher","Qing-Tai Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-03T21:58:34Z","doi":"10.1109/esscirc55480.2022.9911305","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.2139/ssrn.4333265","name":"Neuromorphic Visual Artificial Synapse In-Memory Computing Systems Based on GeOx-Coated MXene Nanosheets","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4333265","authors":["Tianshi Zhao","Yixin Cao","Chenguang Liu","Chun Zhao","Hao Gao","Shichen Huang","Xianyao Li","Chengbo Wang","Yina Liu","Eng  Gee Lim","Zhen Wen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-30T16:07:47Z","doi":"10.2139/ssrn.4333265","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1063/5.0235267","name":"Recent advances in fluidic neuromorphic computing","source":"crossref","abstract":"Human brain is capable of optimizing information flow and processing without energy-intensive data shuttling between processor and memory. At the core of this unique capability are billions of neurons connected through trillions of synapses—basic processing units of the brain. The action potentials or “spikes” based temporal processing using the regulated flow of ions across ion channels in neuron cells allows sparse and efficient transmission of data in the brain. Emerging systems based on confined fluidic systems have provided a framework for a new type of neuromorphic computing with lower energy consumption, hardware-level plasticity, and multiple information carriers that emulate natural processes and mechanisms of human brain. These systems mimic neuronal architectures by harnessing and modulating ion transport along artificial channels. The spikes-induced ion-to-surface interactions within these fluidic systems enables the control of ionic conductivity to achieve synaptic plasticity for the realization of brain-inspired functionalities such as memory effect and signal transmission. Herein, this review provides an overview of recent advances in fluidic devices such as memristors and other computing components, covering their basic operations, materials and architectures, as well as applications in neuromorphic computing. The review concludes with a brief outline of the challenges that these emerging technologies face and an outlook for the development of fluidic-based brain-inspired computing.","url":"https://doi.org/10.1063/5.0235267","authors":["Cheryl Suwen Law","Juan Wang","Kornelius Nielsch","Andrew D. Abell","Juan Bisquert","Abel Santos"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-24T12:34:38Z","doi":"10.1063/5.0235267","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1088/2634-4386/ae8626","name":"Feedforward spiking neural networks are not transformers (yet): a learning-theoretic framework for long-range dependencies and biological efficiency","source":"crossref","abstract":"Abstract Spiking neural networks offer a promising route toward low-power sequence computation on neuromorphic hardware, but they continue to lag behind attention-based artificial neural networks on long-context tasks. A central open question is whether this gap reflects only implementation and optimization limitations, or whether architectural features of spiking computation impose unfavorable learnability constraints as sequence length increases. Here, we address this question using a covering-number analysis of feedforward non-leaky integrate-and-fire (nLIF) networks in the probably approximately correct framework. Building on causal-piece decompositions and local Lipschitz continuity, we derive a global sensitivity bound for feedforward nLIF networks and extend it from single-token inputs to multi-token spike sequences. For fixed architectures under stated boundedness and margin assumptions, the resulting sufficient worst-case sample requirement has leading quadratic dependence on sequence length. This dependence arises from cumulative causal participation across time and depth, which increases global sensitivity along active spike paths. We then test the mechanistic implications of this theory using finite-sample cue-recall and teacher–student benchmarks across spiking, recurrent, and attention-based model classes. In cue-recall, an early cue must be retained across distractors and reported at a final query token; in teacher–student, labels are generated by a fixed nLIF teacher, separating representability from finite-sample learnability. Unconstrained feedforward spiking models show sequence-length sensitivity, elevated hidden spike-participation density, and increased samples-to-threshold burden. Post-spike refractoriness, leak-mediated forgetting, learned lateral inhibition, and activity-constrained winner-take-all competition reduce hidden participation and improve empirical robustness in task- and regime-dependent ways. Together, these results identify diffuse causal-set growth as a fundamental architectural bottleneck for baseline feedforward spiking sequence models and suggest that scalable neuromorphic sequence architectures will require circuit mechanisms that explicitly constrain temporal accumulation and effective spike participation.","url":"https://doi.org/10.1088/2634-4386/ae8626","authors":["William Fishell","Gord Fishell","Suraj Honnuraiah"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-03T22:52:23Z","doi":"10.1088/2634-4386/ae8626","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1109/icnc64304.2024.10987769","name":"Bearing-Based Formation Control Using Reset Protocol","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987769","authors":["Armand Gires Fomekong Lontchi","Yinglun Mo","Wenfeng Hu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987769","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/mcsoc67473.2025.00058","name":"MindCore: Spike-Driven Programmable Accelerator for On-Device Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mcsoc67473.2025.00058","authors":["Hawon Park","Si Yong Lee","Ryangjin Lee","Yoora Kim","Yoon Seok Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-31T18:41:58Z","doi":"10.1109/mcsoc67473.2025.00058","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/iscas.2016.7527267","name":"Live demonstration: Real-time image classification on a neuromorphic computing system with zero off-chip memory access","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas.2016.7527267","authors":["Taehwan Shin","Yongshin Kang","Seungho Yang","Seban Kim","Jaeyong Chung"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-11-01T20:59:26Z","doi":"10.1109/iscas.2016.7527267","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/islped65674.2025.11261768","name":"Neuromorphic Edge Computing: Challenges, Opportunities, and Current Solutions","source":"crossref","abstract":"","url":"https://doi.org/10.1109/islped65674.2025.11261768","authors":["Federico Corradi","Amir Zjajo","Letícia Maria Bolzani Poehls","Miloš Krstić","Orlando Moreira","Zeqi Zhu","Farhad Merchant"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-03T18:39:13Z","doi":"10.1109/islped65674.2025.11261768","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/icnc64304.2024.10987850","name":"Attack Time Consensus Control for 3D Multi-Missile Systems Based on Adaptive Dynamic Programming","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987850","authors":["Fenglan Sun","Xinwei Yang","Jiashuo Su","Jiaoyan Zhu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987850","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.3390/nano13192720","name":"Emerging Opportunities for 2D Materials in Neuromorphic Computing","source":"crossref","abstract":"Recently, two-dimensional (2D) materials and their heterostructures have been recognized as the foundation for future brain-like neuromorphic computing devices. Two-dimensional materials possess unique characteristics such as near-atomic thickness, dangling-bond-free surfaces, and excellent mechanical properties. These features, which traditional electronic materials cannot achieve, hold great promise for high-performance neuromorphic computing devices with the advantages of high energy efficiency and integration density. This article provides a comprehensive overview of various 2D materials, including graphene, transition metal dichalcogenides (TMDs), hexagonal boron nitride (h-BN), and black phosphorus (BP), for neuromorphic computing applications. The potential of these materials in neuromorphic computing is discussed from the perspectives of material properties, growth methods, and device operation principles.","url":"https://doi.org/10.3390/nano13192720","authors":["Chenyin Feng","Wenwei Wu","Huidi Liu","Junke Wang","Houzhao Wan","Guokun Ma","Hao Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-07T14:17:26Z","doi":"10.3390/nano13192720","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1016/j.mee.2014.12.008","name":"A memristive diode for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.mee.2014.12.008","authors":["Xiaolei Wang","Qi Shao","Pui Sze Ku","Antonio Ruotolo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-12-24T12:01:26Z","doi":"10.1016/j.mee.2014.12.008","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/icnc59488.2023.10462850","name":"EEG Channel Selection Based on Neuron Proportion with SNN for Motor Imagery Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462850","authors":["Zhihui Sun","Chaoqiong Fan","Tianyuan Jia","Qing Li","Xia Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462850","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/icmi65310.2025.11141332","name":"Neuromorphic Circuits With Spiking Astrocytes for Increased Energy Efficiency, Fault Tolerance, and Memory Capacitance","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icmi65310.2025.11141332","authors":["Aybars Yunusoglu","Dexter Le","Murat Isik","I. Can Dikmen","Teoman Karadag"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-08T17:38:33Z","doi":"10.1109/icmi65310.2025.11141332","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1007/978-3-031-65549-4_10","name":"Toward a Resilient Future: The Path Ahead","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-65549-4_10","authors":["Ali Akbar Firoozi","Ali Asghar Firoozi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-26T13:01:53Z","doi":"10.1007/978-3-031-65549-4_10","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/peeic59336.2023.10450331","name":"Spintronic Device Potential in Neuromorphic Computing from a Device-Circuit Modeling Perspective","source":"crossref","abstract":"","url":"https://doi.org/10.1109/peeic59336.2023.10450331","authors":["Bashetty Suman","N M Deepika","B Rajalakshm","Jay Singh","Ginni Nijhawan","Mazin Riyadh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-13T14:55:26Z","doi":"10.1109/peeic59336.2023.10450331","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1002/aelm.202400121","name":"Molybdenum Disulfide Memristors for Next Generation Memory and Neuromorphic Computing: Progress and Prospects","source":"crossref","abstract":"Abstract In the last 15 years memristors have been investigated as devices for high‐density, low‐power, non‐volatile, resistive random access memory (ReRAM) beyond Moore's law. They also show potential in neuromorphic logic architectures to overcome the Von–Neumann bottleneck of classical circuitry facilitating better hardware for artificial intelligence (AI) and artificial neural network (ANN) systems. Molybdenum disulfide (MoS 2 ) has emerged as a promising material for memristor devices of monolayer thickness due to its direct bandgap, high carrier mobility and environmental stability. In this review, recent progress in the development of MoS 2 memristors the current understanding of the mechanisms behind their function are examined. The remaining obstacles to a commercially viable device principle and how these may be surmounted in light of the rapid progress that has already been made are also discussed.","url":"https://doi.org/10.1002/aelm.202400121","authors":["R. A. Wells","A. W. Robertson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-04T05:51:29Z","doi":"10.1002/aelm.202400121","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/biocas.2018.8584674","name":"Processing EMG signals using reservoir computing on an event-based neuromorphic system","source":"crossref","abstract":"","url":"https://doi.org/10.1109/biocas.2018.8584674","authors":["Elisa Donati","Melika Payvand","Nicoletta Risi","Renate Krause","Karla Burelo","Giacomo Indiveri","Thomas Dalgaty","Elisa Vianello"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-12-24T23:48:58Z","doi":"10.1109/biocas.2018.8584674","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1145/3229884.3229889","name":"Learning Accuracy Analysis of Memristor-based Nonlinear Computing Module on Long Short-term Memory","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3229884.3229889","authors":["Hongyu An","Mohammad Shah Al-Mamun","Marius K. Orlowski","Yang Yi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-07-26T11:58:06Z","doi":"10.1145/3229884.3229889","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1063/5.0035741","name":"Oxide semiconductor-based ferroelectric thin-film transistors for advanced neuromorphic computing","source":"crossref","abstract":"Neuromorphic computing that mimics the biological brain has been demonstrated as a next-generation computing method due to its low power consumption and parallel data processing characteristics. To realize neuromorphic computing, diverse neural networks such as deep neural networks (DNNs) and spiking neural networks (SNNs) have been introduced. DNNs require artificial synapses that have analog conductance modulation characteristics, whereas SNNs require artificial synapses that have conductance modulation characteristics controlled by temporal relationships between signals, so the development of a multifunctional artificial synapse is required. In this work, we report a ferroelectric thin-film transistor (FeTFT) that uses zirconium-doped hafnia (HfZrOx) and indium zinc tin oxide (IZTO) for neuromorphic applications. With reliable conductance modulation characteristics, we suggest that the FeTFT with HfZrOx and IZTO can be used as an artificial synapse for both DNNs and SNNs. The linear and symmetric conductance modulation characteristics in FeTFTs result in high recognition accuracy (93.1%) of hand-written images, which is close to the accuracy (94.1%) of an ideal neural network. Also, we show that the FeTFTs can emulate diverse forms of spike-time-dependent plasticity, which is an important learning rule for SNNs. These results suggest that FeTFT is a promising candidate to realize neuromorphic computing hardware.","url":"https://doi.org/10.1063/5.0035741","authors":["Min-Kyu Kim","Ik-Jyae Kim","Jang-Sik Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-01-19T11:47:10Z","doi":"10.1063/5.0035741","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/iedm45625.2022.10019364","name":"The Future of Holistic Neural Interfaces: 2D Materials, Neuromorphic Computing, and Computational Co-Design","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iedm45625.2022.10019364","authors":["M. Wilson","M. Ramezani","J. Kim","D. Kuzum"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-23T20:03:43Z","doi":"10.1109/iedm45625.2022.10019364","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/sum48717.2021.9505837","name":"Silicon Photonics for Artificial Intelligence and Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/sum48717.2021.9505837","authors":["Bhavin J. Shastri","Thomas Ferreira de Lima","Chaoran Huang","Bicky A. Marquez","Sudip Shekhar","Lukas Chrostowski","Paul R. Prucnal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-08-12T20:30:35Z","doi":"10.1109/sum48717.2021.9505837","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.4018/979-8-3693-6303-4.ch015","name":"Pharmacy Science and Neurological Drug Discovery","source":"crossref","abstract":"In this chapter, we set out on a journey to explore the complex relationship between pharmaceutical science, computational drug discovery, and the world of natural food products. We will deeply investigate the crucial role of food components in shaping the landscape of pharmaceutical research and development. By highlighting the importance of integrating food-based methods into drug discovery processes, our goal is to emphasize the transformative potential of utilizing the abundant resources found in nature. Taking a multidisciplinary approach, we aim to bridge the traditional gap between conventional pharmaceutical practices and the rapidly advancing field of nutraceuticals. In doing so, we are paving the way for a more unified and holistic approach to healthcare innovation.","url":"https://doi.org/10.4018/979-8-3693-6303-4.ch015","authors":["Neha Tanwar","Sandeep Kumar","Deepika Verma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-29T15:16:27Z","doi":"10.4018/979-8-3693-6303-4.ch015","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/cleo/europe-eqec57999.2023.10232665","name":"Motivation and Challenges for Applying Photonic Neuromorphic Computing Technologies","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cleo/europe-eqec57999.2023.10232665","authors":["B.J. Offrein","E.A. Vlieg","F. Hermann","L. Carraria Martinotti","F. Horst"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-04T13:49:33Z","doi":"10.1109/cleo/europe-eqec57999.2023.10232665","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/socc46988.2019.1570553082","name":"Enabling Neuromorphic Computing: BEOL Integration of CMOS RRAM Chip and Programmable Performance","source":"crossref","abstract":"","url":"https://doi.org/10.1109/socc46988.2019.1570553082","authors":["Weijie Wang","Victor Yi-Qqian Zhuo","Zhixian Chen","Hock Koon Lee","Minghua Li","Wendong Song"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-05-07T21:27:28Z","doi":"10.1109/socc46988.2019.1570553082","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1142/9789811290084_0005","name":"Complexity Degrees of Real Computability","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789811290084_0005","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-26T02:06:27Z","doi":"10.1142/9789811290084_0005","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.34133/icomputing.0059","name":"Information Transfer in Neuronal Circuits: From Biological Neurons to Neuromorphic Electronics","source":"crossref","abstract":"The advent of neuromorphic electronics is increasingly revolutionizing the concept of computation. In the last decade, several studies have shown how materials, architectures, and neuromorphic devices can be leveraged to achieve brain-like computation with limited power consumption and high energy efficiency. Neuromorphic systems have been mainly conceived to support spiking neural networks that embed bioinspired plasticity rules such as spike time-dependent plasticity to potentially support both unsupervised and supervised learning. Despite substantial progress in the field, the information transfer capabilities of biological circuits have not yet been achieved. More importantly, demonstrations of the actual performance of neuromorphic systems in this context have never been presented. In this paper, we report similarities between biological, simulated, and artificially reconstructed microcircuits in terms of information transfer from a computational perspective. Specifically, we extensively analyzed the mutual information transfer at the synapse between mossy fibers and granule cells by measuring the relationship between pre- and post-synaptic variability. We extended this analysis to memristor synapses that embed rate-based learning rules, thus providing quantitative validation for neuromorphic hardware and demonstrating the reliability of brain-inspired applications.","url":"https://doi.org/10.34133/icomputing.0059","authors":["Daniela Gandolfi","Lorenzo Benatti","Tommaso Zanotti","Giulia M. Boiani","Albertino Bigiani","Francesco M. Puglisi","Jonathan Mapelli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-09T07:47:09Z","doi":"10.34133/icomputing.0059","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1007/978-981-96-8383-3_7","name":"Slow Electronics and Attractor","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-96-8383-3_7","authors":["Kantaro Fujiwara"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-31T11:42:52Z","doi":"10.1007/978-981-96-8383-3_7","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1088/2634-4386/ad93f9","name":"DPSNN: spiking neural network for low-latency streaming speech enhancement","source":"crossref","abstract":"Abstract Speech enhancement improves communication in noisy environments, affecting areas such as automatic speech recognition (ASR), hearing aids, and telecommunications. With these domains typically being power-constrained and event-based, and often requiring low latency, neuromorphic algorithms–particularly spiking neural networks (SNNs)–hold significant potential. However, current effective SNN solutions require a long temporal window to calculate Short Time Fourier Transforms (STFTs) and thus impose substantial latency, typically around 32 ms, which is too long for applications such as hearing aids. Inspired by the Dual-Path Recurrent Neural Network (DPRNN) in deep neural networks (DNNs), we develop a two-phase time-domain streaming SNN fframework for speech enhancement, named Dual-Path Spiking Neural Network (DPSNN) . DPSNNs achieve low latency by replacing the STFT and inverse STFT (iSTFT) in traditional frequency-domain models with a learned convolutional encoder and decoder. In the DPSNN, the first phase uses Spiking Convolutional Neural Networks (SCNNs) to capture temporal contextual information, while the second phase uses Spiking Recurrent Neural Networks (SRNNs) to focus on frequency-related features. In addition, threshold-based activation suppression, along with L 1 regularization loss, is applied to specific non-spiking layers in DPSNNs to further improve their energy efficiency. Evaluating on the Voice Cloning Toolkit (VCTK) Corpus and Intel N-DNS Challenge dataset, our approach demonstrates excellent performance in speech objective metrics, along with the very low latency (approximately 5 ms) required for applications like hearing aids.","url":"https://doi.org/10.1088/2634-4386/ad93f9","authors":["Tao Sun","Sander Bohté"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-18T22:52:15Z","doi":"10.1088/2634-4386/ad93f9","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1007/978-3-031-51500-2_6","name":"Development of Crosspoint Memory Arrays for Neuromorphic Computing","source":"crossref","abstract":"Abstract Memristor-based hardware accelerators play a crucial role in achieving energy-efficient big data processing and artificial intelligence, overcoming the limitations of traditional von Neumann architectures. Resistive-switching memories (RRAMs) combine a simple two-terminal structure with the possibility of tuning the device conductance. This Chapter revolves around the topic of emerging memristor-related technologies, starting from their fabrication, through the characterization of single devices up to the development of proof-of-concept experiments in the field of in-memory computing, hardware accelerators, and brain-inspired architecture. Non-volatile devices are optimized for large-size crossbars where the devices’ conductance encodes mathematical coefficients of matrices. By exploiting Kirchhoff’s and Ohm’s law the matrix–vector-multiplication between the conductance matrix and a voltage vector is computed in one step. Eigenvalues/eigenvectors are experimentally calculated according to the power-iteration algorithm, with a fast convergence within about 10 iterations to the correct solution and Principal Component Analysis of the Wine and Iris datasets, showing up to 98% accuracy comparable to a floating-point implementation. Volatile memories instead present a spontaneous change of device conductance with a unique similarity to biological neuron behavior. This characteristic is exploited to demonstrate a simple fully-memristive architecture of five volatile RRAMs able to learn, store, and distinguish up to 10 different items with a memory capability of a few seconds. The architecture is thus tested in terms of robustness under many experimental conditions and it is compared with the real brain, disclosing interesting mechanisms which resemble the biological brain.","url":"https://doi.org/10.1007/978-3-031-51500-2_6","authors":["Saverio Ricci","Piergiulio Mannocci","Matteo Farronato","Alessandro Milozzi","Daniele Ielmini"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T06:50:21Z","doi":"10.1007/978-3-031-51500-2_6","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1145/3266229","name":"STDP-based Unsupervised Feature Learning using Convolution-over-time in Spiking Neural Networks for Energy-Efficient Neuromorphic Computing","source":"crossref","abstract":"Brain-inspired learning models attempt to mimic the computations performed in the neurons and synapses constituting the human brain to achieve its efficiency in cognitive tasks. In this work, we propose Spike Timing Dependent Plasticity-based unsupervised feature learning using convolution-over-time in Spiking Neural Network (SNN). We use shared weight kernels that are convolved with the input patterns over time to encode representative input features, thereby improving the sparsity as well as the robustness of the learning model. We show that the Convolutional SNN self-learns several visual categories for object recognition with limited number of training patterns while yielding comparable classification accuracy relative to the fully connected SNN. Further, we quantify the energy benefits of the Convolutional SNN over fully connected SNN on neuromorphic hardware implementation.","url":"https://doi.org/10.1145/3266229","authors":["Gopalakrishnan Srinivasan","Priyadarshini Panda","Kaushik Roy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-11-27T13:18:59Z","doi":"10.1145/3266229","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/conit65521.2025.11166960","name":"Event-Based Imaging for High-Speed Object Detection: A Neuromorphic Computing Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1109/conit65521.2025.11166960","authors":["Yogesh Kumar Sharma","Nirmla Sharma","Sameera Iqbal Muhmmad Iqbal","Munish Kumar","Sushil Kumar Maurya","Pooja Kapoor"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-24T17:32:03Z","doi":"10.1109/conit65521.2025.11166960","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1039/d5nr03811a/v3/response1","name":"Author response for \"Optically/Electrically Controlled Ag&lt;sup&gt;+&lt;/sup&gt; Metallization in Solution-Processed Oxide Memtransistors for Neuromorphic Computing\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5nr03811a/v3/response1","authors":["Rajarshi Chakraborty","Himanshu Singodia","Subarna Pramanik","Akhilesh Kumar Yadav","Utkarsh Pandey","Ranajit Ghosh","Bhola Nath Pal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-10T21:02:35Z","doi":"10.1039/d5nr03811a/v3/response1","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/ectc51687.2025.00283","name":"Parasitic Extraction and Signal Integrity Analysis of Memristor-Based Crossbar Arrays for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ectc51687.2025.00283","authors":["Tahsin Binte Shameem","Hanzhi Ma","Yi Zhou","Zohreh Salehi","José E. Schutt-Ainé"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-26T13:40:11Z","doi":"10.1109/ectc51687.2025.00283","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1016/c2021-0-01408-5","name":"Neuromorphic Photonic Devices and Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1016/c2021-0-01408-5","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-21T08:58:46Z","doi":"10.1016/c2021-0-01408-5","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1360/n972016-01359","name":"Emulations of synaptic plasticity in the planar transistor configuration for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1360/n972016-01359","authors":["Yan CHEN","ChenXi ZHANG","LaiYuan WANG","TengFei LI","Ying ZHU","MingDong YI","Wei HUANG"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-10-17T01:51:20Z","doi":"10.1360/n972016-01359","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.23919/usnc-ursi51813.2021.9703558","name":"Multi-Sensing Data Fusion for Human Activity Recognition based on Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.23919/usnc-ursi51813.2021.9703558","authors":["Zheqi Yu","Adnan Zahid","William Taylor","Hadi Heidari","Muhammad A. Imran","Qammer H. Abbasi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-10T20:28:35Z","doi":"10.23919/usnc-ursi51813.2021.9703558","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1145/2638559","name":"Toward a Sparse Self-Organizing Map for Neuromorphic Architectures","source":"crossref","abstract":"Neurobiological systems have often been a source of inspiration for computational science and engineering, but in the past their impact has also been limited by the understanding of biological models. Today, new technologies lead to an equilibrium situation where powerful and complex computers bring new biological knowledge of the brain behavior. At this point, we possess sufficient understanding to both imagine new brain-inspired computing paradigms and to sustain a classical paradigm which reaches its end programming and intellectual limitations. In this context, we propose to reconsider the computation problem first in the specific domain of mobile robotics. Our main proposal consists in considering computation as part of a global adaptive system, composed of sensors, actuators, a source of energy and a controlling unit. During the adaptation process, the proposed brain-inspired computing structure does not only execute the tasks of the application but also reacts to the external stimulation and acts on the emergent behavior of the system. This approach is inspired by cortical plasticity in mammalian brains and suggests developing the computation architecture along the system's experience. This article proposes modeling this plasticity as a problem of estimating a probability density function. This function would correspond to the nature and the richness of the environment perceived through multiple modalities. We define and develop a novel neural model solving the problem in a distributed and sparse manner. And we integrate this neural map into a bio-inspired hardware substrate that brings the plasticity property into parallel many-core architectures. The approach is then called Hardware Plasticity. The results show that the self-organization properties of our model solve the problem of multimodal sensory data clusterization. The properties of the proposed model allow envisaging the deployment of this adaptation layer into hardware architectures embedded into the robot's body in order to build intelligent controllers.","url":"https://doi.org/10.1145/2638559","authors":["Laurent Rodriguez","Benoît Miramond","Bertrand Granado"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-04-28T12:43:57Z","doi":"10.1145/2638559","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/ieeeconf56349.2022.10052098","name":"Multi-Fidelity Nonideality Simulation and Evaluation Framework for Resistive Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ieeeconf56349.2022.10052098","authors":["Chenghao Quan","Mohammed E. Fouda","Sugil Lee","Jongeun Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-07T18:41:29Z","doi":"10.1109/ieeeconf56349.2022.10052098","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1088/2634-4386/ac29c9","name":"A binary classifier based on a reconfigurable dense network of metallic nanojunctions","source":"crossref","abstract":"Abstract Major efforts to reproduce the brain performances in terms of classification and pattern recognition have been focussed on the development of artificial neuromorphic systems based on top-down lithographic technologies typical of highly integrated components of digital computers. Unconventional computing has been proposed as an alternative exploiting the complexity and collective phenomena originating from various classes of physical substrates. Materials composed of a large number of non-linear nanoscale junctions are of particular interest: these systems, obtained by the self-assembling of nano-objects like nanoparticles and nanowires, results in non-linear conduction properties characterized by spatiotemporal correlation in their electrical activity. This appears particularly useful for classification of complex features: nonlinear projection into a high-dimensional space can make data linearly separable, providing classification solutions that are computationally very expensive with digital computers. Recently we reported that nanostructured Au films fabricated from the assembling of gold clusters by supersonic cluster beam deposition show a complex resistive switching behaviour. Their non-linear electric behaviour is remarkably stable and reproducible allowing the facile training of the devices on precise resistive states. Here we report about the fabrication and characterization of a device that allows the binary classification of Boolean functions by exploiting the properties of cluster-assembled Au films interconnecting a generic pattern of electrodes. This device, that constitutes a generalization of the perceptron, can receive inputs from different electrode configurations and generate a complete set of Boolean functions of n variables for classification tasks. We also show that the non-linear and non-local electrical conduction of cluster-assembled gold films, working at room temperature, allows the classification of non-linearly separable functions without previous training of the device.","url":"https://doi.org/10.1088/2634-4386/ac29c9","authors":["Matteo Mirigliano","Bruno Paroli","Gianluca Martini","Marco Fedrizzi","Andrea Falqui","Alberto Casu","Paolo Milani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-24T22:11:18Z","doi":"10.1088/2634-4386/ac29c9","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/iwofc48002.2019.9078471","name":"Low-Power Resistive Switching Characteristics in TiN/TaON/SiO<sub>2</sub>/Pt RRAM devices for Neuromorphic Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iwofc48002.2019.9078471","authors":["Ao Yu","Yuechi Ma","Zehao Wang","Xiangxiang Ding","Yulin Feng","Lifeng Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-04-27T21:34:50Z","doi":"10.1109/iwofc48002.2019.9078471","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1088/2634-4386/ae4648","name":"Spatiotemporal radar gesture recognition with hybrid spiking neural networks: balancing accuracy and efficiency","source":"crossref","abstract":"Abstract Radar-based human activity recognition (HAR) offers privacy and robustness over camera-based methods, yet remains computationally demanding for edge deployment. We present the first application of spiking neural networks (SNNs) for radar-based HAR on aircraft marshaling signal classification. Our novel hybrid architecture combines a pre-trained convolutional backbone for spatial feature extraction and leaky integrate-and-fire neurons for temporal processing, inherently capturing gesture dynamics. The model reduces trainable parameters by 88% with under 1% accuracy loss compared to existing state of the art methods, and generalizes well to the Soli gesture dataset. Through systematic comparisons with other three artificial neural network architectures, we demonstrate the trade-offs of spiking computation in terms of accuracy, latency, memory, and energy, establishing SNNs as an efficient and competitive solution for radar-based HAR.","url":"https://doi.org/10.1088/2634-4386/ae4648","authors":["Riccardo Mazzieri","Eleonora Cicciarella","Jacopo Pegoraro","Federico Corradi","Michele Rossi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-16T23:07:23Z","doi":"10.1088/2634-4386/ae4648","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.1109/iccad57390.2023.10323793","name":"A Novel and Efficient Block-Based Programming for ReRAM-Based Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccad57390.2023.10323793","authors":["Wei-Lun Chen","Fang-Yi Gu","Ing-Chao Lin","Grace Li Zhang","Bing Li","Ulf Schlichtmann"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-30T18:58:45Z","doi":"10.1109/iccad57390.2023.10323793","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1145/2894756","name":"Neuromorphic Processors with Memristive Synapses","source":"crossref","abstract":"Due to their nonvolatile nature, excellent scalability, and high density, memristive nanodevices provide a promising solution for low-cost on-chip storage. Integrating memristor-based synaptic crossbars into digital neuromorphic processors (DNPs) may facilitate efficient realization of brain-inspired computing. This article investigates architectural design exploration of DNPs with memristive synapses by proposing two synapse readout schemes. The key design tradeoffs involving different analog-to-digital conversions and memory accessing styles are thoroughly investigated. A novel storage strategy optimized for feedforward neural networks is proposed in this work, which greatly reduces the energy and area cost of the memristor array and its peripherals.","url":"https://doi.org/10.1145/2894756","authors":["Qian Wang","Yongtae Kim","Peng Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-05-13T14:30:58Z","doi":"10.1145/2894756","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/iscas66217.2026.11562707","name":"GreenMorph: Sustainable Neuromorphic Computing through Energy-Harvesting and Energy-Driven Online STDP Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas66217.2026.11562707","authors":["Yuga Hanyu","Subbaiah Ravi Hariprakash","Abderazek Ben Abdallah","Zhishang Wang","Khanh N. Dang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-18T20:06:41Z","doi":"10.1109/iscas66217.2026.11562707","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1016/j.sse.2025.109096","name":"An efficient temperature dependent compact model for nanosheet FET for neuromorphic computing circuit","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.sse.2025.109096","authors":["N. Aruna Kumari","Abhishek Kumar Upadhyay","Vikas Vijayvargiya","Gaurav Singh","Ankur Beohar","Prithvi P."],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-10T16:10:59Z","doi":"10.1016/j.sse.2025.109096","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1088/1361-6668/ac4cd2","name":"SuperMind: a survey of the potential of superconducting electronics for neuromorphic computing","source":"crossref","abstract":"Abstract Neuromorphic computing is a broad field that uses biological inspiration to address computing design. It is being pursued in many hardware technologies, both novel and conventional. We discuss the use of superconductive electronics for neuromorphic computing and why they are a compelling technology for the design of neuromorphic computing systems. One example is the natural spiking behavior of Josephson junctions and the ability to transmit short voltage spikes without the resistive capacitive time constants that typically hinder spike-based computing. We review the work that has been done on biologically inspired superconductive devices, circuits, and architectures and discuss the scaling potential of these demonstrations.","url":"https://doi.org/10.1088/1361-6668/ac4cd2","authors":["Michael Schneider","Emily Toomey","Graham Rowlands","Jeff Shainline","Paul Tschirhart","Ken Segall"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-01-19T17:12:31Z","doi":"10.1088/1361-6668/ac4cd2","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1145/3477145.3477264","name":"Drone Virtual Fence Using a Neuromorphic Camera","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3477145.3477264","authors":["Terrence Stewart","Marc-Antoine Drouin","Guillaume Gagne","Guy Godin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-10-13T14:38:20Z","doi":"10.1145/3477145.3477264","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1007/978-3-031-73800-5_2","name":"Deep Learning Techniques for Wireless Communication Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-73800-5_2","authors":["Ziad El-Khatib","Sherif Moussa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-15T07:23:10Z","doi":"10.1007/978-3-031-73800-5_2","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/icons62911.2024.00058","name":"The Lynchpin of In-Memory Computing: A Benchmarking Framework for Vector-Matrix Multiplication in RRAMs","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024.00058","authors":["Md Tawsif Rahman Chowdhury","Huynh Quang Nguyen Vo","Paritosh Ramanan","Murat Yildirim","Gozde Tutuncuoglu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T18:37:03Z","doi":"10.1109/icons62911.2024.00058","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.5772/intechopen.111615","name":"A Study of the Comparison between Artificial Neural Networks, Logistic Regression and Similarity Weighted Instance-Based Learning in Modeling and Predicting Trends in Deforestation","source":"crossref","abstract":"The change in forest cover plays a vital role in ecosystem services, atmospheric carbon balance, and, thus, climate change. In this study, land use maps for the periods 1984 and 2012, derived from Landsat TM satellite imagery, were used. The goal of this study is comparison of three procedures of artificial neural network, logistic regression, and similarity weighted instance-based learning (SIM Weight) to predict spatial trend of forest cover change. The SimWeight considers the nearest instances in the variable space, which are computed based on past changes and the relative importance of the driving variables. The LogReg approach, on the other hand, is a type of generalized linear model that assumes that the current land use pattern reflects the processes of land use in the past. Artificial Neural Network is a nonparametric algorithm that is capable of fitting complex nonlinear functions to find the relations between past changes and their driving variables. Such approaches are expected to produce better fitting between the change potential and their complex relationships with their driving variables. Artificial neural networks in comparison with logistic regression and SimWeight have higher accuracy and less error in modeling and predicting of forest changes.","url":"https://doi.org/10.5772/intechopen.111615","authors":["Zeynab Moradi","Ali Reza Mikaeili Tabrizi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-31T14:26:32Z","doi":"10.5772/intechopen.111615","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/biocas.2019.8919010","name":"Memory-Centric Neuromorphic Computing With Nanodevices","source":"crossref","abstract":"","url":"https://doi.org/10.1109/biocas.2019.8919010","authors":["Damien Querlioz","Julie Grollier","Tifenn Hirtzlin","Jacques-Olivier Klein","Etienne Nowak","Elisa Vianello","Marc Bocquet","Jean-Michel Portal","Miguel Romera","Philippe Talatchian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-12-06T07:01:08Z","doi":"10.1109/biocas.2019.8919010","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1039/d5nr03811a/v2/response1","name":"Author response for \"Optically/Electrically Controlled Ag&lt;sup&gt;+&lt;/sup&gt; Metallization in Solution-Processed Oxide Memtransistors for Neuromorphic Computing\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5nr03811a/v2/response1","authors":["Rajarshi Chakraborty","Himanshu Singodia","Subarna Pramanik","Akhilesh Kumar Yadav","Utkarsh Pandey","Ranajit Ghosh","Bhola Nath Pal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-10T21:02:35Z","doi":"10.1039/d5nr03811a/v2/response1","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1149/ma2024-02483315mtgabs","name":"Neuromorphic Computing Based on Few-Molecule Vibration Dynamics Achieved By Surface-Enhanced Raman Scattering and Ion-Gating Stimulation","source":"crossref","abstract":"1. Objective Artificial intelligence (AI), which has achieved high-level capabilities in cognition, learning, and inference through technological innovations such as deep learning, has greatly benefited human society, however, problems such as high energy consumption and increased communication traffic have also emerged. As a solution to these problems, physical reservoir computing (PRC), a kind of neuromorphic computing that uses the nonlinear behavior of physical systems to efficiently process information, has been attracting attention.[1-5] Although various methods of PRC have been reported (e.g., memristors, electrochemical cells, optical circuits, soft bodies, and spintronics devices), the molecular computing approach is promising to realize the ultimate compact and integrated PRC. However, the number of molecules in a conventional molecular reservoir system is huge, and the information processing capability of a single molecule to several molecules has not been elucidated.[2,3] In this study, we developed a few-molecule reservoir computing (FM-RC) that utilizes the molecular vibration dynamics of single to few molecules of para-mercaptobenzoic acid (pMBA). The information processing capability of few molecules was evaluated by performing information processing tasks such as blood glucose level prediction on FM-RC. [4] 2. Experiments Figure 1a shows a schematic diagram of the measurement system of FM-RC. In order to accurately track the nonlinear dynamics of a few molecules, surface-enhanced Raman scattering (SERS) measurements using WOx nanorods/silver nanoparticles (WOx@Ag-NPs) were performed, and molecular vibration reflecting the structural change of pMBA based on the local proton adsorption change due to ion-gating stimulation was observed in the molecular dynamics (Fig. 1b) reflecting the conformational changes of pMBA based on the local proton adsorption changes induced by ion-gating stimuli. The obtained SERS spectra were regarded as independent artificial neurons (nodes) at specific sampling wavenumbers, and these node states were used to perform various information processing tasks (Fig. 1c). 3. Results and Discussion Although FM-RC consists of only a few molecules, it achieved a high accuracy of 95.1% to 97.7% in the nonlinear waveform transformation task and 94.3% in the analysis task of second-order nonlinear equations, and achieved the highest computational performance among physical reservoirs in the task of predicting blood glucose levels for type I pediatric diabetes patients (Fig. 1d).[4-6] These high computational performances are attributed to the independent nonlinearity of the nodes distributed in the wavenumber direction, i.e., the high dimensionality achieved by the complex and diverse response characteristics of each vibrational mode to the proton adsorption amount. In this presentation, the origin of the high computational performance of FM-RC will be discussed in terms of nonlinearity and high dimensionality, which are the main properties that determine the performance of PRCs. References [1] D. Nishioka et al., Sci. Adv. 8 , eade1156 (2022). [2] A. Goudarzi et al, DNA Reservoir Computing (Springer, 2013). [3] Y. Usami Adv. Mater. 33 , 2102688 (2021). [4] D. Nishioka et al., Sci. Adv. 10 , eadk6438 (2024). [5] T. Shingu et al., Carbon 214 , 118344 (2023). [6] DIRECNET Study Group, Diabetes Technol. Therapeut. 5 , 781-789 (2003). Acknowledgments This work was supported by Japan Society for the Promotion of Science (JSPS) KAKENHI Grant Number JP22H04625 (Grant-in-Aid for Scientific Research on Innovative Areas “Interface Ionics”), Japan Society for the Promotion of Science (JSPS) KAKENHI Grant Number JP22KJ2799 (Grant-in-Aid for JSPS Fellows), JST PRESTO (grant number, JPMJPR23H4), and the Iketani Science and Technology Foundation. Figure 1","url":"https://doi.org/10.1149/ma2024-02483315mtgabs","authors":["Daiki Nishioka","Yoshitaka Shingaya","Kazuya Terabe","Takashi Tsuchiya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-19T22:18:36Z","doi":"10.1149/ma2024-02483315mtgabs","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1007/978-3-031-73800-5_7","name":"Adaptive Quadratic Integrate-and-Fire CMOS Neuron Performance","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-73800-5_7","authors":["Ziad El-Khatib","Sherif Moussa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-15T07:22:40Z","doi":"10.1007/978-3-031-73800-5_7","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1117/12.2276945","name":"Neuromorphic computing with stochastic spintronic devices (Conference Presentation)","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.2276945","authors":["Damien Querlioz","Adrien F. Vincent","Alice Mizrahi","Damir Vodenicarevic","Nicolas Locatelli","Joseph S. Friedman","Jacques-Olivier Klein","Julie Grollier"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-09-29T11:09:59Z","doi":"10.1117/12.2276945","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1002/admt.202200361","name":"A Neuromorphic Electrothermal Processor for Near‐Sensor Computing","source":"crossref","abstract":"Abstract The statistical processing of sensor data using conventional digital computers is inefficient in terms of time, energy usage, and communication bandwidth, among others. Therefore, new approaches are sought to create context and make sense of the sensor data using special‐purpose computers that excel in specific computation tasks. Herein, the requirements for physical systems to perform sophisticated nonlinear computations needed for real‐time pattern recognition in data, specifically sensor data, are discussed. The focus is on physical reservoir computing as a neuromorphic computing approach. Considering energy flow as the coupling mechanism between nonlinear dynamic systems, it is demonstrated that many physical systems satisfy the basic requirements for building reservoir computers. Using physical reservoir computers brings up exciting opportunities for near‐ or in‐sensor computing as to how new data are collected and processed. The concepts are demonstrated through a novel physical computation platform, where off‐the‐shelf, temperature‐sensitive resistors are used to perform various standard and specific computational tasks. This platform is used as a near‐sensor processor to detect particular events. How a similar platform may be used for in‐sensor neuromorphic computations is further discussed.","url":"https://doi.org/10.1002/admt.202200361","authors":["Vahideh Shirmohammadli","Behraad Bahreyni"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-07-19T17:10:22Z","doi":"10.1002/admt.202200361","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.11591/ijai.v14.i2.pp1000-1021","name":"Adaptive silicon synapse and CMOS neuron for neuromorphic VLSI computing","source":"crossref","abstract":"The design of a fully integrated adaptive modified complementary metal-oxide-semiconductor (CMOS) synapse circuit is presented. By using multiple-gated transistor configuration in the modified CMOS synapse an additional branch provide control where the synaptic output current time-constant is tuned. The effect of changing the multiple-gated transistor bias voltage from 0.25 to 0.45 V tunes the spiking output current exponential time-constant range by 200 ms as shown in simulation results. Moreover, a fully-integrated adaptive quadratic integrate-and-fire (QIF) CMOS neuron circuit is presented as well. A differential pair with variable capacitor integrator and a tunable schmitt trigger threshold detector circuit are integrated in the CMOS neuron that can be tuned varying its spiking frequency. The proposed adaptive quadratic integrate-and-fire (AQIF) neuron has the ability to adjust the spiking frequency without changing the input current. The simulation results show the proposed CMOS neuron circuit spiking frequency can be tuned from 58.4 to 312.5 Hz and its spiking period from 17.1 to 3.2 ms with tuning the bias voltage of variable capacitor integrator. Having a peak voltage Vpeak=0.95 V, a reset voltage Vreset=-0.75 V and a voltage threshold of 0.35 V with a membrane potential range of 1.5 V. The proposed CMOS neuron circuit is designed in 130 nm process with a supply voltage of 1.8 V and a total power dissipation of 1.8 mW.","url":"https://doi.org/10.11591/ijai.v14.i2.pp1000-1021","authors":["Ziad El-Khatib","Sherif Moussa","Firuz Kamalov","Mustapha C. E. Yagoub"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-17T07:20:31Z","doi":"10.11591/ijai.v14.i2.pp1000-1021","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/icnc52316.2021.9608773","name":"Finite-time synchronization of complex-valued neural networks with adaptive coupling weights","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc52316.2021.9608773","authors":["Tianhu Yu","Huamin Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-29T20:59:32Z","doi":"10.1109/icnc52316.2021.9608773","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/icnc64304.2024.10987773","name":"Secure Synchronization of Neural Networks by Pinning Partial Impulsive Control","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987773","authors":["Xinle Wang","Xiaoyu Zhang","Hongfei Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987773","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1364/cleo_si.2026.sw1c.7","name":"Co-integrated Photonic-Electronic Architecture with Shared Multi-λ Lasers for Scalable Spike-Based Neuromorphic Computing","source":"crossref","abstract":"We introduce a neuromorphic architecture that combines excitable electronics, microring-modulators and multi-wavelength lasers. We numerically demonstrate it as optoelectronic spiking neural network by leveraging hardware-aware modelling and training, and perform design-space exploration of microring parameters.","url":"https://doi.org/10.1364/cleo_si.2026.sw1c.7","authors":["Matěj Hejda","Aishwarya Natarajan","Chaerin Hong","Mehmet B. On","Sébastien d’Herbais de Thun","Raymond G. Beausoleil","Thomas Van Vaerenbergh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-28T21:01:37Z","doi":"10.1364/cleo_si.2026.sw1c.7","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1145/3229884.3229891","name":"A Dynamical Systems Approach to Neuromorphic Computation of Conditional Probabilities","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3229884.3229891","authors":["Nigel Stepp","Aruna Jammalamadaka"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-07-26T11:58:06Z","doi":"10.1145/3229884.3229891","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1038/s44335-025-00023-7","name":"Advanced AI computing enabled by 2D material-based neuromorphic devices","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s44335-025-00023-7","authors":["Yunseok Choi","Siwoo Jeong","Hyeonu Jeong","Sangmoon Han","Jonghyeon Ko","Si Eun Yu","Zhihao Xu","Min Seong Chae","Minjae Son","Yuan Meng","Shijue Xu","Ji-Hoon Kang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-21T01:27:16Z","doi":"10.1038/s44335-025-00023-7","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/ijcnn54540.2023.10191448","name":"Tolerating Device-to-Device Variation for Memristive Crossbar-Based Neuromorphic Computing Systems: A New Bayesian Perspective","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn54540.2023.10191448","authors":["Yang Xiao","Qi Xu","Bo Yuan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-02T17:30:03Z","doi":"10.1109/ijcnn54540.2023.10191448","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/icnc52316.2021.9608158","name":"Memristor-based Echo State Network and Prediction for Time Series","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc52316.2021.9608158","authors":["Xiaohui Mu","Lixiang Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-29T20:59:32Z","doi":"10.1109/icnc52316.2021.9608158","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1088/1361-6528/abd978","name":"Graphene oxide based synaptic memristor device for neuromorphic computing","source":"crossref","abstract":"Abstract Brain-inspired neuromorphic computing which consist neurons and synapses, with an ability to perform complex information processing has unfolded a new paradigm of computing to overcome the von Neumann bottleneck. Electronic synaptic memristor devices which can compete with the biological synapses are indeed significant for neuromorphic computing. In this work, we demonstrate our efforts to develop and realize the graphene oxide (GO) based memristor device as a synaptic device, which mimic as a biological synapse. Indeed, this device exhibits the essential synaptic learning behavior including analog memory characteristics, potentiation and depression. Furthermore, spike-timing-dependent-plasticity learning rule is mimicked by engineering the pre- and post-synaptic spikes. In addition, non-volatile properties such as endurance, retentivity, multilevel switching of the device are explored. These results suggest that Ag/GO/fluorine-doped tin oxide memristor device would indeed be a potential candidate for future neuromorphic computing applications.","url":"https://doi.org/10.1088/1361-6528/abd978","authors":["Dwipak Prasad Sahu","Prabana Jetty","S Narayana Jammalamadaka"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-01-08T08:49:00Z","doi":"10.1088/1361-6528/abd978","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1038/s41467-026-75570-z","name":"Self-heating-induced blocking in nanopores enables neuromorphic ionic computing","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-75570-z","authors":["Qinyang Fan","Changhui Xu","Wei Liu","Zhenyu Zhang","Yunfei Chen","Jingjie Sha"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-75570-z","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.23919/sispad49475.2020.9241659","name":"Monte Carlo Simulation of a Three-Terminal RRAM with Applications to Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.23919/sispad49475.2020.9241659","authors":["Akhilesh Balasingam","Akash Levy","Haitong Li","Priyanka Raina"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-11-02T22:09:13Z","doi":"10.23919/sispad49475.2020.9241659","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/ieeeconf60004.2024.10943060","name":"Waves and Symbols in Neuromorphic Hardware: From Analog Signal Processing to Digital Computing on the Same Computational Substrate","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ieeeconf60004.2024.10943060","authors":["Dmitrii Zendrikov","Alessio Franci","Giacomo Indiveri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-04T18:20:20Z","doi":"10.1109/ieeeconf60004.2024.10943060","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/icnc64304.2024.10987743","name":"Tibetan Syllable Component Recognization with Memristor","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987743","authors":["Yutong Liu","Jiarun Shen","Yongbin Yu","Ban Ma-Bao","Thupten Tsering","Xiangxiang Wang","Cheng Huang","Nyima Tashi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987743","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1007/s11432-025-4483-1","name":"Improved synaptic properties of HfSiOx-based ferroelectric memristors by optimizing Ti/N ratio in TiN top electrode for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11432-025-4483-1","authors":["Chaewon Youn","Sungjun Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-27T06:16:19Z","doi":"10.1007/s11432-025-4483-1","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/icnc59488.2023.10462876","name":"Distributed Nash Equilibrium Seeking Under Dynamic Event-Triggered Mechanism Without Velocity Measurement","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462876","authors":["Mengxin Wang","Xiaoni Han","Yuhan Xue","Sitian Qin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462876","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1109/phosst.2017.8012646","name":"Photonic interconnect with superconducting electronics for large-scale neuromorphic computing (Invited paper)","source":"crossref","abstract":"","url":"https://doi.org/10.1109/phosst.2017.8012646","authors":["Sonia M. Buckley","Jeff Chiles","Adam N. McCaughan","Richard P. Mirin","Sae Woo Nam","Jeffrey M. Shainline"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-08-29T15:14:21Z","doi":"10.1109/phosst.2017.8012646","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1145/3517343.3517353","name":"Neural Mini-Apps as a Tool for Neuromorphic Computing Insight","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3517343.3517353","authors":["Craig Vineyard","Suma Cardwell","Frances Chance","Srideep Musuvathy","Fred Rothganger","William Severa","John Smith","Corinne Teeter","Felix Wang","James Aimone"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-05-04T07:28:08Z","doi":"10.1145/3517343.3517353","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1126/sciadv.abq5652","name":"Pattern recognition with neuromorphic computing using magnetic field–induced dynamics of skyrmions","source":"crossref","abstract":"Nonlinear phenomena in physical systems can be used for brain-inspired computing with low energy consumption. Response from the dynamics of a topological spin structure called skyrmion is one of the candidates for such a neuromorphic computing. However, its ability has not been well explored experimentally. Here, we experimentally demonstrate neuromorphic computing using nonlinear response originating from magnetic field–induced dynamics of skyrmions. We designed a simple-structured skyrmion-based neuromorphic device and succeeded in handwritten digit recognition with the accuracy as large as 94.7% and waveform recognition. Notably, there exists a positive correlation between the recognition accuracy and the number of skyrmions in the devices. The large degrees of freedom of skyrmion systems, such as the position and the size, originate from the more complex nonlinear mapping, the larger output dimension, and, thus, high accuracy. Our results provide a guideline for developing energy-saving and high-performance skyrmion neuromorphic computing devices.","url":"https://doi.org/10.1126/sciadv.abq5652","authors":["Tomoyuki Yokouchi","Satoshi Sugimoto","Bivas Rana","Shinichiro Seki","Naoki Ogawa","Yuki Shiomi","Shinya Kasai","Yoshichika Otani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-30T13:58:33Z","doi":"10.1126/sciadv.abq5652","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1109/icassp40776.2020.9053914","name":"Training Deep Spiking Neural Networks for Energy-Efficient Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icassp40776.2020.9053914","authors":["Gopalakrishnan Srinivasan","Chankyu Lee","Abhronil Sengupta","Priyadarshini Panda","Syed Shakib Sarwar","Kaushik Roy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-04-09T20:21:13Z","doi":"10.1109/icassp40776.2020.9053914","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.30574/wjarr.2024.24.3.3860","name":"Neuromorphic computing for real-time adaptive penetration testing: analysis of human intuition in AI-dominated work space","source":"crossref","abstract":"This research investigates the revolutionary integration of neuromorphic computing with human intuition in the domain of real-time adaptive penetration testing, addressing the critical challenges facing modern cybersecurity in AI-dominated workspaces. The study presents a novel approach that combines the parallel processing capabilities of neuromorphic architectures with the nuanced decision-making abilities of human security experts, resulting in a hybrid system that significantly enhances threat detection and response capabilities. Our research implements a sophisticated neuromorphic computing model featuring 1024 input neurons, 2048 hidden layer neurons, and 512 output neurons, utilizing modified leaky integrate-and-fire algorithms for spike processing. The system incorporates real-time adaptive mechanisms that enable dynamic threat modeling and immediate response generation, while simultaneously learning from human expert intuition through a carefully designed collaborative interface. This architecture demonstrates remarkable improvements in both processing efficiency and threat detection accuracy, achieving a 94.7% true positive rate while maintaining an exceptionally low 2.3% false positive rate. The experimental methodology encompassed extensive testing across a diverse range of attack scenarios, including advanced persistent threats, zero-day vulnerabilities, and sophisticated social engineering attacks. The test environment comprised 500 virtual nodes distributed across multiple security zones, providing a realistic platform for comprehensive system evaluation. Performance metrics revealed significant improvements over traditional approaches, including an 89% success rate in adapting to previously unseen attack patterns and a 76% reduction in decision-making time for complex threats. Quantitative analysis demonstrates the system's superior capabilities in real-time threat detection and response, with average detection latencies of 1.2 milliseconds and consistent performance maintaining up to 100,000 concurrent connections. Qualitative assessment of human-AI synergy, conducted with 50 experienced penetration testers, revealed that 92% reported enhanced decision-making capabilities, while 95% experienced reduced cognitive load during complex scenarios. The research contributes significantly to the field by establishing a new paradigm for adaptive penetration testing that effectively combines neuromorphic computing efficiency with human intuitive expertise. The findings demonstrate that this integration not only enhances detection and response capabilities but also provides a more sustainable approach to cybersecurity in increasingly complex technological environments. Furthermore, the study opens new avenues for research in human-AI collaboration within cybersecurity, suggesting promising directions for future development in adaptive security systems. The implications of this research extend beyond immediate cybersecurity applications, offering insights into the broader field of human-AI collaboration in critical decision-making scenarios. The study also addresses important ethical considerations regarding AI autonomy in security operations, providing guidelines for responsible implementation of AI-driven security solutions while maintaining essential human oversight.","url":"https://doi.org/10.30574/wjarr.2024.24.3.3860","authors":["Shatson  Pamba Fasco"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-23T02:33:57Z","doi":"10.30574/wjarr.2024.24.3.3860","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1088/2634-4386/acb8d7","name":"Hardware optimization for photonic time-delay reservoir computer dynamics","source":"crossref","abstract":"Abstract Reservoir computing (RC) is one kind of neuromorphic computing mainly applied to process sequential data such as time-dependent signals. In this paper, the bifurcation diagram of a photonic time-delay RC system is thoroughly studied, and a method of bifurcation dynamics guided hardware hyperparameter optimization is presented. The time-evolution equation expressed by the photonic hardware parameters is established while the intrinsic dynamics of the photonic RC system is quantitively studied. Bifurcation dynamics based hyperparameter optimization offers a simple yet effective approach in hardware setting optimization that aims to reduce the complexity and time in hardware adjustment. Three benchmark tasks, nonlinear channel equalization (NCE), nonlinear auto regressive moving average with 10th order time lag (NARMA10) and Santa Fe laser time-series prediction tasks are implemented on the photonic delay-line RC using bifurcation dynamics guided hardware optimization. The experimental results of these benchmark tasks achieved overall good agreement with the simulated bifurcation dynamics modeling results.","url":"https://doi.org/10.1088/2634-4386/acb8d7","authors":["Meng Zhang","Zhizhuo Liang","Z Rena Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-02-03T22:27:16Z","doi":"10.1088/2634-4386/acb8d7","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.2172/1899660","name":"Assessing a Neuromorphic Platform for use in Scientific Stochastic Sampling.","source":"crossref","abstract":"","url":"https://doi.org/10.2172/1899660","authors":["John Smith","James Aimone","William Severa","Richard Lehoucq"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-26T03:20:28Z","doi":"10.2172/1899660","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1149/ma2024-01573007mtgabs","name":"Enhanced Synaptic Characteristics Under Applied Magnetic Field in V<sub>2</sub>O<sub>5</sub>/NiMnIn Based Switching Device for Neuromorphic Computing","source":"crossref","abstract":"The present study reports a memory structure Al/V 2 O 5 /NiMnIn on a flexible stainless-steel (SS) substrate for neuromorphic applications. The fabricated device exhibits gradual SET and RESET switching characteristics with an OFF/ON resistance ratio of ~100, good consistency of 4500, and excellent data retention capability up to 3000 s. The current-voltage (I-V) study supports an Ohmic conduction mechanism in the low resistance state (LRS). In contrast, the trap-controlled modified space charge conduction mechanism demonstrated the high resistance state (HRS). The resistance versus temperature measurement (R-T) in the LRS and HRS of the device signifies that oxygen vacancies form the conduction filament. We further analyze the synaptic functioning by applying identical consecutive voltage pulses, and the device's conductance change has been observed. These characteristics show a good representation of the biological memory synapse in terms of the artificial memory device. Long-term potentiation (LTP) and long-term depression (LTD) show nonlinear and asymmetery behavior, which is substantial for neuromorphic applications. A considerable shift in LTP and LTD was detected by applying external temperature and magnetic field. This is explained via temperature and magnetic field strain in the functional NiMnIn bottom electrode of the fabricated device. The mechanical flexibility of the memory structure was tested by exploring the switching characteristics with various bending angles and bending cycles. Therefore, the present study offers new avenues for flexible devices with high data storage capability for futuristic neuromorphic applications.","url":"https://doi.org/10.1149/ma2024-01573007mtgabs","authors":["Kumar Kaushlendra","Habeebur Rahman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-19T15:54:51Z","doi":"10.1149/ma2024-01573007mtgabs","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1007/978-3-031-71097-1_4","name":"Emerging Circuits and Memory Technologies","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-71097-1_4","authors":["Ali Akbar Firoozi","Ali Asghar Firoozi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-12T15:02:54Z","doi":"10.1007/978-3-031-71097-1_4","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1007/978-3-032-09586-2_4","name":"Fault Injection in Logic-in-Memory Architectures","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-09586-2_4","authors":["Felix Staudigl","Rainer Leupers"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-22T14:21:49Z","doi":"10.1007/978-3-032-09586-2_4","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/mnano.2018.2844901","name":"Neuromorphic Computing Using Memristor Crossbar Networks: A Focus on Bio-Inspired Approaches","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mnano.2018.2844901","authors":["YeonJoo Jeong","Wei Lu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-07-16T21:59:35Z","doi":"10.1109/mnano.2018.2844901","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1103/1p38-2998","name":"Neural bolometers: Designing next-generation infrared thermal imagers with in-pixel neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1103/1p38-2998","authors":["Mohamed A. Mousa","Utkarsh Singh","Leif Bauer","Angshuman Deka","Zubin Jacob"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-02T21:32:34Z","doi":"10.1103/1p38-2998","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.143Z"},{"id":"doi:10.1142/9789812816535_others03","name":"NEUROMORPHIC HARDWARE","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789812816535_others03","authors":["Leslie S. Smith","Alister Hamilton"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-07-18T22:54:22Z","doi":"10.1142/9789812816535_others03","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1515/ntrev-2023-0181","name":"Overview of amorphous carbon memristor device, modeling, and applications for neuromorphic computing","source":"crossref","abstract":"Abstract Carbon-based materials strongly pertain to citizens’ daily life due to their versatile derivatives such as diamond, graphite, fullerenes, carbon nanotube, single-layer graphene, and amorphous carbon (a-C). Compared to other families, a-C exhibits reconfigurable electrical properties by triggering its sp 2 –sp 3 transition and vice versa , which can be readily fabricated by conventional film deposition technologies. For above reasons, a-C has been adopted as a promising memristive material and has given birth to several physical and theoretical prototypes. To further help researchers comprehend the physics behind a-C-based memristors and push forward their development, here we first reviewed the classification of a-C-based materials associated with their respective electrical and thermal properties. Subsequently, several a-C -based memristors with different architectures were presented, followed by their respective memristive principles. We also elucidated the state-of-the-art modeling strategies of a-C memristors, and their practical applications on neuromorphic fields were also described. The possible scenarios to further mitigate the physical performances of a-C memristors were eventually discussed, and their future prospect to rival with other memristors was also envisioned.","url":"https://doi.org/10.1515/ntrev-2023-0181","authors":["Jie Wu","Xuqi Yang","Jing Chen","Shiyu Li","Tianchen Zhou","Zhikuang Cai","Xiaojuan Lian","Lei Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-19T11:13:32Z","doi":"10.1515/ntrev-2023-0181","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/biocas58349.2023.10388821","name":"An 1.38nJ/Inference Clock-Free Mixed-Signal Neuromorphic Architecture Using ReL-PSP Function and Computing-in-Memory","source":"crossref","abstract":"","url":"https://doi.org/10.1109/biocas58349.2023.10388821","authors":["Wenbing Fang","Zihao Xuan","Song Chen","Yi Kang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-18T13:27:59Z","doi":"10.1109/biocas58349.2023.10388821","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1007/978-981-19-0707-4_64","name":"A Survey on Efficient Interconnects for Neuromorphic Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-19-0707-4_64","authors":["Shobhit Kumar","Shirshendu Das","Gourav Badone","Amit Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-01T13:04:19Z","doi":"10.1007/978-981-19-0707-4_64","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1007/978-3-031-71097-1_10","name":"Ethical Design and Development Guidelines","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-71097-1_10","authors":["Ali Akbar Firoozi","Ali Asghar Firoozi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-12T15:02:54Z","doi":"10.1007/978-3-031-71097-1_10","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1364/ome.450226","name":"Recycling forward and backward frequency-multiplexed modes in a waveguide coupled to phased time-perturbed microrings for low-footprint neuromorphic computing","source":"crossref","abstract":"Optical structures can serve as low-power high-capacity alternatives of electronic processors for more efficient neuromorphic computing, but can suffer from large footprints and weak scalability. In this work, properly phased time-perturbed microrings side-coupled to a waveguide are utilized to realize a compact processor for linear transformations. We build up a synthetic frequency dimension to provide sufficient degrees of freedom, where the linear time-varying structures enable the linear intermixing and transformation of frequency-multiplexed data. Moreover, non-reciprocal and asymmetric flow of data in the forward and backward modes, due to phasing of the perturbations, helped to build up another synthetic dimension and to avoid physically repeating the processing elements, thus enabling a much more compact and scalable linear processor.","url":"https://doi.org/10.1364/ome.450226","authors":["Sajjad Jalili","Mohammad Memarian","Khashayar Mehrany"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-18T07:00:09Z","doi":"10.1364/ome.450226","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/icnc59488.2023.10462750","name":"On Optimization of Multi-machine PSS Parameters Tuning Based on SCSO Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462750","authors":["Yuchao Wu","Shulong Fan","Peng Liu","Junwei Sun","Ting Lei","Sanyi Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462750","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1088/2634-4386/ac7c89","name":"Advantages of binary stochastic synapses for hardware spiking neural networks with realistic memristors","source":"crossref","abstract":"Abstract Hardware implementing spiking neural networks (SNNs) has the potential to provide transformative gains in energy efficiency and throughput for energy-restricted machine-learning tasks. This is enabled by large arrays of memristive synapse devices that can be realized by various emerging memory technologies. But in practice, the performance of such hardware is limited by non-ideal features of the memristor devices such as nonlinear and asymmetric state updates, limited bit-resolution, limited cycling endurance and device noise. Here we investigate how stochastic switching in binary synapses can provide advantages compared with realistic analog memristors when using unsupervised training of SNNs via spike timing-dependent plasticity. We find that the performance of binary stochastic SNNs is similar to or even better than analog deterministic SNNs when one considers memristors with realistic bit-resolution as well in situations with considerable cycle-to-cycle noise. Furthermore, binary stochastic SNNs require many fewer weight updates to train, leading to superior utilization of the limited endurance in realistic memristive devices.","url":"https://doi.org/10.1088/2634-4386/ac7c89","authors":["Karolis Sulinskas","Mattias Borg"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-28T22:15:46Z","doi":"10.1088/2634-4386/ac7c89","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/nvmsa66678.2025.00017","name":"Memristors with Tunable Analog States for Enhanced Accuracy Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nvmsa66678.2025.00017","authors":["Xuemeng Fan","Guobin Zhang","Zijian Wang","Qi Luo","Yishu Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-25T19:54:18Z","doi":"10.1109/nvmsa66678.2025.00017","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1088/2634-4386/ae65d4","name":"Solving Sudoku using oscillatory neural networks","source":"crossref","abstract":"Abstract We explore the capabilities of physical computing with oscillatory neural networks (ONNs) to solve combinatorial optimization problems. To solve Sudokus with ONNs, we define a novel mapping strategy that utilizes the unique characteristics of the computation paradigm. The problem is encoded through a puzzle specific graph-embedding, which implements the constraints through different subgraphs. These subgraphs are then combined into a single adjacency matrix , which allows the natural dynamics of the phases of coupled oscillators to find a solution to the puzzle. We model the phase dynamics of the ONN by means of the Kuramoto differential equation. This novel approach is then compared to the well-established iterative method to solve Sudoku already used in binary Hopfield neural networks (HNNs). Solving optimization problems typically requires a large amount of energy to solve on conventional hardware. Therefore, we are motivated to explore the mapping of Sudoku from a theoretical point of view to establish the validity of this approach. The simulation results show that the novel ONN mapping outperforms the established HNN methodology.","url":"https://doi.org/10.1088/2634-4386/ae65d4","authors":["Bram F Haverkort","Federico Sbravati","Stefan Porfir","Aida Todri-Sanial"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-28T22:52:07Z","doi":"10.1088/2634-4386/ae65d4","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1007/978-3-032-09586-2_5","name":"Deliberately Flipping Bits in Memristive Crossbar Arrays","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-09586-2_5","authors":["Felix Staudigl","Rainer Leupers"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-22T14:21:49Z","doi":"10.1007/978-3-032-09586-2_5","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1088/1361-6641/ac41e4","name":"Dynamic resistive switching devices for neuromorphic computing","source":"crossref","abstract":"Abstract Neuromorphic systems that can emulate the structure and the operations of biological neural circuits have long been viewed as a promising hardware solution to meet the ever-growing demands of big-data analysis and AI tasks. Recent studies on resistive switching or memristive devices have suggested such devices may form the building blocks of biorealistic neuromorphic systems. In a memristive device, the conductance is determined by a set of internal state variables, allowing the device to exhibit rich dynamics arising from the interplay between different physical processes. Not only can these devices be used for compute-in-memory architectures to tackle the von Neumann bottleneck, the switching dynamics of the devices can also be used to directly process temporal data in a biofaithful fashion. In this review, we analyze the physical mechanisms that govern the dynamic switching behaviors and highlight how these properties can be utilized to efficiently implement synaptic and neuronal functions. Prototype systems that have been used in machine learning and brain-inspired network implementations will be covered, followed with discussions on the challenges for large scale implementations and opportunities for building bio-inspired, highly complex computing systems.","url":"https://doi.org/10.1088/1361-6641/ac41e4","authors":["Yuting Wu","Xinxin Wang","Wei D Lu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-10T19:07:53Z","doi":"10.1088/1361-6641/ac41e4","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.5772/acrt.deposit.c.8440846","name":"Neuromorphic Computing in Outer Space: Intel Loihi Deployed On-Satellite for Spike Based Software Defined Communication","source":"crossref","abstract":"&lt;table&gt;&lt;tr&gt;&lt;td&gt;&lt;p dir=\"ltr\"&gt;In space exploration and communication technology, software-defined networking (SDN) architectures significantly improve communication throughput and latency. This study developed a Q-learning-based continuous learning capable cognitive agent to select optimal routing options for a dynamically changing networking environment. With the dynamically changing network link latency, the cognitive agent achieved a 90% success rate in routing packets. The agent was executed on neuromorphic hardware called Intel Loihi. However, due to the system's power limitations, a simplified version of the agent was engineered to launch into space aboard a CubeSat. The CubeSat was launched in January 2022, making a historic milestone as the first launch of a neuromorphic system into space. The developed applications were successfully executed in space.&lt;/p&gt;&lt;/td&gt;&lt;/tr&gt;&lt;/table&gt;","url":"https://doi.org/10.5772/acrt.deposit.c.8440846","authors":["Nayim Rahman","Chris Yakopcic","Tarek Taha","Ricardo Lent","Janette Briones","David Chelmins","Rachel Dudukovitch","Aaron Smith","Adam Gannon","Michael Lowry","Marcus Murbach","Alejandro Salas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-12T13:43:54Z","doi":"10.5772/acrt.deposit.c.8440846","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.2139/ssrn.7202153","name":"Dual-Layer PMMA/CsPbBr3 Regulation of Ag Filament Spatiotemporal Dynamics in SnO2 Quantum Dots Memristors for Neuron–Synapse Integrated Neuromorphic Computing","source":"crossref","abstract":"Precise control over filament dynamics is critical for neuromorphic devices with neuronal and synaptic functions. However, most existing strategies regulate either spatial localization or temporal stability, lacking simultaneous and programmable control. Here, a dual-layer synergistic strategy is demonstrated in solution-processed SnO2 quantum dots (QDs) memristors for programmable spatiotemporal regulation of Ag filament formation. A CsPbBr3 layer serves as a nucleation platform to spatially confine filament growth, while a PMMA layer regulates Ag⁺ injection kinetics and filament evolution. By tuning PMMA thickness in Ag/(PMMA)ₙ/SnO2 QDs/CsPbBr3/ITO devices, a reversible transition between volatile and nonvolatile switching is achieved. The Ag/(PMMA)ₙ=5/SnO2 QDs/CsPbBr3/ITO volatile device exhibits an operating voltage of 0.5 V, an ON/OFF ratio of 105, endurance over 105 cycles, and leaky integrate-and-fire neuronal behavior. The Ag/(PMMA)ₙ=1/SnO2 QDs/CsPbBr3/ITO nonvolatile device shows an ON/OFF ratio of 103, endurance over 104 cycles, and data retention exceeding 104 s. Based on these two modes, a hybrid neuron–synapse system is constructed, achieving 93.3% MNIST recognition accuracy. This work provides a programmable filament dynamics paradigm for scalable neuromorphic computing hardware.","url":"https://doi.org/10.2139/ssrn.7202153","authors":["Qiuxu Yu","Shuyi Li","Wei Mi","Di Wang","Lin&apos;an He","Gangri Cai","Liwei Zhou","Jinshi Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-29T17:41:59Z","doi":"10.2139/ssrn.7202153","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/buildsec68439.2025.00014","name":"Adaptive and Privacy-Preserving Anomaly Detection in IoT Edge Security Using Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/buildsec68439.2025.00014","authors":["Tamal Dey","Gopinath Bej","Devdulal Ghosh","Subhankar Mukherjee","Hena Ray","Ch A S Murty"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-09T19:55:16Z","doi":"10.1109/buildsec68439.2025.00014","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1016/j.nanoen.2024.109646","name":"The rise of memtransistors for neuromorphic hardware and In-memory computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.nanoen.2024.109646","authors":["Jihong Bae","Jongbum Won","Wooyoung Shim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-22T11:33:17Z","doi":"10.1016/j.nanoen.2024.109646","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1016/j.copbio.2021.10.012","name":"Neural interface systems with on-device computing: machine learning and neuromorphic architectures","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.copbio.2021.10.012","authors":["Jerald Yoo","Mahsa Shoaran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-01T19:07:21Z","doi":"10.1016/j.copbio.2021.10.012","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1007/978-3-031-71097-1_7","name":"Challenges and Future Directions","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-71097-1_7","authors":["Ali Akbar Firoozi","Ali Asghar Firoozi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-12T15:02:54Z","doi":"10.1007/978-3-031-71097-1_7","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1201/9781003616399-59","name":"Design and analysis of a quantum FinFETbased memristor with gate diffusion input for neuromorphic computing applications using 16 nm technology","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003616399-59","authors":["Dilshad Shaik","M. Sravanthi","B. Karunasree","Sangam Mounika"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-13T11:57:01Z","doi":"10.1201/9781003616399-59","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1002/aidi.202500053","name":"Advances in Organic In‐Sensor Neuromorphic Computing: from Material Mechanisms to Applications","source":"crossref","abstract":"In‐sensor neuromorphic computing integrates sensing and processing within a single material system, enabling real‐time, ultralow‐power computation for biomedical signal analysis, artificial skin, and brain‐machine interfaces. Organic sensors, organic electrochemical transistors, and memory‐based synaptic devices serve as key components, utilizing ion–electron coupling and nonvolatile synaptic weight modulation for energy‐efficient neuromorphic functions. Reflecting the potential of the aforementioned in‐sensor computing, this review provides a comprehensive analysis of organic‐based in‐sensor computing for wearable and bioelectronic applications. It explores the design and mechanisms of organic synaptic devices, with a focus on memory‐based and organic electrochemical transistor‐based architectures. The fundamental principles of neuromorphic computing are examined, highlighting various organic neuromorphic computing devices and their operational characteristics. Through an in‐depth discussion of recent advancements, challenges, and future perspectives, this review aims to offer valuable insights into the potential of organic electronics in advancing intelligent systems.","url":"https://doi.org/10.1002/aidi.202500053","authors":["Dong Hyun Lee","Woojo Kim","Eun Kwang Lee","Hocheon Yoo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-24T08:36:37Z","doi":"10.1002/aidi.202500053","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1109/icnc59488.2023.10462851","name":"Estimation of the Domain of Attraction on Controlled Complex Networks with Unbounded Time-varying Delay","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462851","authors":["Hong Yu","Yinfang Song","Li Liu","Gang Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462851","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1016/j.mtphys.2026.102027","name":"Research progress of BaTiO3-based ferroelectric memristors for artificial synapse and neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.mtphys.2026.102027","authors":["Fan Ye","Fei Liang","Jian-Wei Zhong","Guan-Ling Li","Xin-Gui Tang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-20T16:28:18Z","doi":"10.1016/j.mtphys.2026.102027","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1109/icnc59488.2023.10462866","name":"Opinion Evolution in the FJ Model with Oblivious Individuals in Cooperation-Competition Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462866","authors":["Jie Zhang","Yunchen Wang","Hongxiang Hu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462866","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1149/ma2025-01633064mtgabs","name":"Revealing Dual Functionality of Graphene Memristor Circuit for Advanced Neuromorphic Computing","source":"crossref","abstract":"Neuromorphic computing [1], inspired by the energy-efficient and parallelized architecture of the human brain, represents a paradigm shift in computing. This approach not only drives innovative hardware designs but also inspires novel network architectures like spiking neural networks (SNNs), which process information as discrete spike events. However, scalability in neuromorphic systems is constrained by the large hardware footprint. Realizing multimodal functionality using the same set of hardware primitives can offer a promising solution to these limitations. In this work, we present a dual encoder-neuron circuit based on a nanoporous graphene (NPG) memristor device [2]. The graphene leaky integrate-and-fire (GLIF) circuit has a versatile multimodal design that combines the roles of a LIF neuron and a spike encoder within the same architecture. This design mimics the dual functionality of biological neurons, which encode and process signals locally. The spike encoding capability of the circuit is further revealed using single and double layer SNN networks for pattern recognition tasks using the Modified National Institute of Standards and Technology (MNIST) dataset. Inset of Figure 1(a) shows the schematic of the fabricated NPG device with a channel length of 100 µm. The device has a lateral structure with NPG channel and gold (Au) electrodes. Figure 1(a) shows the current-voltage (I-V) characteristics of the fabricated NPG device which shows a threshold switching behavior with a wide hysteresis window and a threshold voltage (V th ) of 4.9 V. A behavioral SPICE model is developed based on a voltage-controlled switch model. It is seen from Figure 1(a) that the I-V curves simulated using the SPICE model matches the experimentally observed device switching characteristics. This reveals that the simplified SPICE model can be a good substitute for complex Verilog based models. Based on the SPICE model, we designed a simple neuron circuit with a resistor (R s , 12 kΩ) in series with a parallel combination of a capacitor (C m , 10 nF) and the NPG device (SPICE model). Figure 1(b) shows the variation of the membrane potential (V m ) and the output spike current in response to the input pulse voltage (V in , 6 V). V m shows a clear leaky integration behavior and full reset to zero voltage after the spike response. These are essential attributes of a bioplausible LIF neuron circuit. In order to develop the multimodal GLIF circuit, the output spike frequency of the LIF neuron circuit is plotted as a function of the R s values. This mapping allows pixel values from MNIST input images to be directly translated into normalized conductance values (G/G 0 ). Hence, each pixel is represented as a normalized conductance value, establishing a clear correlation between pixel intensity and spike frequency. This core idea is further used to develop the GLIF encoder based on the same neuron circuit as before. Based on the dual encoder-neuron circuit, we designed a single layer SNN for recognising the handwritten digits from the MNIST dataset. Figure 1(c) shows the spike-encoded images for the MNIST digits “2” and “5”. The probability of spiking in each timestep is proportional to the spiking frequency. The spike encoded images at each time step reveal the contours of the original input images using sparse representation. These sparse matrices highlight the energy efficiency and computational advantages of the GLIF system. The performance of the dual encoder-neuron system is evaluated by training the single layer SNN using both the GLIF encoder and neuron circuit as integral components. The single layer SNN recorded a high pattern recognition accuracy of 90.77% which is comparable to the purely software-based implementation (92.69%). To explore the scalability of the GLIF system, we implemented a double-layer SNN using the GLIF system, achieving a high recognition accuracy of 97.37%. The GLIF circuit exemplifies how reconfigurable primitive compon","url":"https://doi.org/10.1149/ma2025-01633064mtgabs","authors":["Kannan Udaya Mohanan","Chang-Hyun Kim","Seyed Mehdi Sattari-Esfahlan","Eou-Sik Cho","Ioannis Kymissis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-21T08:01:46Z","doi":"10.1149/ma2025-01633064mtgabs","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/icnc59488.2023.10462746","name":"A Novel Block Focused Omega-K Algorithm for Millimetre-Wave Radar Imaging","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462746","authors":["Weiwei Liang","Chuandong Li","Shaqi Yang","Yawei Shi","Zhen Luo","Ruiyang Qiu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462746","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/icnc59488.2023.10462808","name":"Efficient Memristive Binary Neural Networks With Spatial Separable Convolutions","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462808","authors":["Haohang Sun","Tongtong Gao","Yawen Wang","Xiaofang Hu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462808","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/igsc51522.2020.9291053","name":"Memristor Based Neuromorphic Network Security System Capable of Online Incremental Learning and Anomaly Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/igsc51522.2020.9291053","authors":["Md. Shahanur Alam","Chris Yakopcic","Guru Subramanyam","Tarek M. Taha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-04-14T01:42:20Z","doi":"10.1109/igsc51522.2020.9291053","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.29363/nanoge.matsusfall.2025.366","name":"Proton migration-modulated n-doped poly(benzodifurandione) (n-PBDF) organic electrochemical memtransistors used for neuromorphic computing applications","source":"crossref","abstract":"","url":"https://doi.org/10.29363/nanoge.matsusfall.2025.366","authors":["Ignacio Sanjuán","David Franco","Qun-Gao Chen","Chu-Chen Chueh","Wen-Ya Lee","Antonio Guerrero"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-17T09:40:46Z","doi":"10.29363/nanoge.matsusfall.2025.366","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.3390/mi13050725","name":"Conductive Bridge Random Access Memory (CBRAM): Challenges and Opportunities for Memory and Neuromorphic Computing Applications","source":"crossref","abstract":"Due to a rapid increase in the amount of data, there is a huge demand for the development of new memory technologies as well as emerging computing systems for high-density memory storage and efficient computing. As the conventional transistor-based storage devices and computing systems are approaching their scaling and technical limits, extensive research on emerging technologies is becoming more and more important. Among other emerging technologies, CBRAM offers excellent opportunities for future memory and neuromorphic computing applications. The principles of the CBRAM are explored in depth in this review, including the materials and issues associated with various materials, as well as the basic switching mechanisms. Furthermore, the opportunities that CBRAMs provide for memory and brain-inspired neuromorphic computing applications, as well as the challenges that CBRAMs confront in those applications, are thoroughly discussed. The emulation of biological synapses and neurons using CBRAM devices fabricated with various switching materials and device engineering and material innovation approaches are examined in depth.","url":"https://doi.org/10.3390/mi13050725","authors":["Haider Abbas","Jiayi Li","Diing Ang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-05-01T06:23:08Z","doi":"10.3390/mi13050725","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/icons62911.2024.00053","name":"Neuromorphic Monte Carlo Tree Search Methods for Shortest Path Interdiction","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024.00053","authors":["Yang Ho","Armida Carbajal","Leonardo Escamilla","Ali Pinar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T18:37:03Z","doi":"10.1109/icons62911.2024.00053","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1016/j.optmat.2025.117346","name":"WS2 based optoelectronic memristor as artificial Synapse: Integrated neuromorphic computing solution for Braille alphabet recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.optmat.2025.117346","authors":["Jayashri Patil","Sharmila B","P. Divyashree","Siva Kotamraju","Priyanka Dwivedi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-22T23:05:43Z","doi":"10.1016/j.optmat.2025.117346","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1109/iolts65288.2025.11116950","name":"Neuromorphic Computing for Embodied Intelligence in Autonomous Systems: Current Trends, Challenges, and Future Directions","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iolts65288.2025.11116950","authors":["Alberto Marchisio","Muhammad Shafique"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-19T18:07:28Z","doi":"10.1109/iolts65288.2025.11116950","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1002/aelm.202100465","name":"Prospect of Spintronics in Neuromorphic Computing","source":"crossref","abstract":"Abstract Neuromorphic computing emulates a biological brain at different levels of the computer hierarchy by exploiting brain‐inspired principles in designing novel devices, algorithms, and architectures. It is believed to have a lower power budget and a higher efficiency in performing cognitive tasks, and is arguably the most promising approaches for next‐generation artificial intelligence. Despite the potentials, progress of neuromorphic computing is constrained by a lack of dedicated hardware. Spintronics is a fast‐evolving discipline that exploits the spin degree of freedom in electronics. The interplay of magnetic and electrical properties of spintronic devices gives rise to a wide range of amazing phenomena, which are both intrinsically conducive to neuromorphic computing and highly compatible with conventional manufacturing technologies. Here, the development of neuromorphic computing with reference to spintronics is reviewed. The state‐of‐the‐art spintronic technologies, such as the magnetic tunnel junction, spin–orbit torque, domain wall propagation, magnetic skyrmions, and antiferromagnet, are highlighted and how they can used for artificial neurons and synapses in different artificial neural networks are discussed. The technical challenges to be overcome for realizing more powerful all‐spin artificial neural networks are also evaluated.","url":"https://doi.org/10.1002/aelm.202100465","authors":["Jing Zhou","Jingsheng Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-06-26T02:00:01Z","doi":"10.1002/aelm.202100465","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1145/3287624.3288743","name":"Fault tolerance in neuromorphic computing systems","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3287624.3288743","authors":["Mengyun Liu","Lixue Xia","Yu Wang","Krishnendu Chakrabarty"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-01-18T21:45:18Z","doi":"10.1145/3287624.3288743","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1002/adma.202501813","name":"Neuromorphic Light‐Responsive Organic Matter for\n                    <i>in Materia</i>\n                    Reservoir Computing","source":"crossref","abstract":"Abstract Materials able to sense and respond to external stimuli by adapting their internal state to process and store information, represent promising candidates for implementing neuromorphic functionalities and brain‐inspired computing paradigms. In this context, neuromorphic systems based on light‐responsive materials enable the use of light as information carrier, allowing to emulate basic functions of the human retina. In this work it is demonstrated that optically‐induced molecular dynamics in azopolymers can be exploited for neuromorphic‐type of data processing in the analog domain and for computing at the matter level (i.e., in materia ). Besides showing that azopolymers can be exploited for data storage, it is demonstrated that the adaptiveness of these materials enables the implementation of synaptic functionalities including short‐term memory, long‐term memory, and visual memory. Results show that azopolymers allow event detection and motion perception, enabling physical implementation of information processing schemes requiring real‐time analysis of spatio‐temporal inputs. Furthermore, it is shown that light‐induced dynamics can be exploited for the in materia implementation of the unconventional computing paradigm denoted as reservoir computing. This work underscores the potential of azopolymers as promising materials for developing adaptive, intelligent photo‐responsive systems that mimic some of the complex processing abilities of biological systems.","url":"https://doi.org/10.1002/adma.202501813","authors":["Federico Ferrarese Lupi","Mateo Rosero‐Realpe","Antonio Ocarino","Francesca Frascella","Gianluca Milano","Angelo Angelini"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-13T06:18:25Z","doi":"10.1002/adma.202501813","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1088/2634-4386/acb2ef","name":"Simulation and implementation of two-layer oscillatory neural networks for image edge detection: bidirectional and feedforward architectures","source":"crossref","abstract":"Abstract The growing number of edge devices in everyday life generates a considerable amount of data that current AI algorithms, like artificial neural networks, cannot handle inside edge devices with limited bandwidth, memory, and energy available. Neuromorphic computing, with low-power oscillatory neural networks (ONNs), is an alternative and attractive solution to solve complex problems at the edge. However, ONN is currently limited with its fully-connected recurrent architecture to solve auto-associative memory problems. In this work, we use an alternative two-layer bidirectional ONN architecture. We introduce a two-layer feedforward ONN architecture to perform image edge detection, using the ONN to replace convolutional filters to scan the image. Using an HNN Matlab emulator and digital ONN design simulations, we report efficient image edge detection from both architectures using various size filters (3 × 3, 5 × 5, and 7 × 7) on black and white images. In contrast, the feedforward architectures can also perform image edge detection on gray scale images. With the digital ONN design, we also assess latency performances and obtain that the bidirectional architecture with a 3 × 3 filter size can perform image edge detection in real-time (camera flow from 25 to 30 images per second) on images with up to 128 × 128 pixels while the feedforward architecture with same 3 × 3 filter size can deal with 170 × 170 pixels, due to its faster computation.","url":"https://doi.org/10.1088/2634-4386/acb2ef","authors":["Madeleine Abernot","Todri-Sanial Aida"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-13T17:27:52Z","doi":"10.1088/2634-4386/acb2ef","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.3389/frcmn.2021.820248","name":"IMU Sensing–Based Hopfield Neuromorphic Computing for Human Activity Recognition","source":"crossref","abstract":"Aiming at the self-association feature of the Hopfield neural network, we can reduce the need for extensive sensor training samples during human behavior recognition. For a training algorithm to obtain a general activity feature template with only one time data preprocessing, this work proposes a data preprocessing framework that is suitable for neuromorphic computing. Based on the preprocessing method of the construction matrix and feature extraction, we achieved simplification and improvement in the classification of output of the Hopfield neuromorphic algorithm. We assigned different samples to neurons by constructing a feature matrix, which changed the weights of different categories to classify sensor data. Meanwhile, the preprocessing realizes the sensor data fusion process, which helps improve the classification accuracy and avoids falling into the local optimal value caused by single sensor data. Experimental results show that the framework has high classification accuracy with necessary robustness. Using the proposed method, the classification and recognition accuracy of the Hopfield neuromorphic algorithm on the three classes of human activities is 96.3%. Compared with traditional machine learning algorithms, the proposed framework only requires learning samples once to get the feature matrix for human activities, complementing the limited sample databases while improving the classification accuracy.","url":"https://doi.org/10.3389/frcmn.2021.820248","authors":["Zheqi Yu","Adnan Zahid","Shuja Ansari","Hasan Abbas","Hadi Heidari","Muhammad A. Imran","Qammer H. Abbasi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-01-07T08:36:51Z","doi":"10.3389/frcmn.2021.820248","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1007/978-3-031-71097-1_11","name":"Toward the Horizon: Concluding Insights","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-71097-1_11","authors":["Ali Akbar Firoozi","Ali Asghar Firoozi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-12T15:02:54Z","doi":"10.1007/978-3-031-71097-1_11","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1145/2966986.2967015","name":"Compact oscillation neuron exploiting metal-insulator-transition for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1145/2966986.2967015","authors":["Pai-Yu Chen","Jae-sun Seo","Yu Cao","Shimeng Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-10-18T12:23:59Z","doi":"10.1145/2966986.2967015","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1007/978-3-032-09586-2_6","name":"Instrumentation Platform for Non-Volatile Memory Technologies","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-09586-2_6","authors":["Felix Staudigl","Rainer Leupers"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-22T14:21:46Z","doi":"10.1007/978-3-032-09586-2_6","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1109/ijcnn.2010.5596664","name":"Analysis of dynamic linear and non-linear memristor device models for emerging neuromorphic computing hardware design","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2010.5596664","authors":["Nathan R. McDonald","Robinson E. Pino","Peter J. Rozwood","Bryant T. Wysocki"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-10-19T18:58:15Z","doi":"10.1109/ijcnn.2010.5596664","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1016/j.neucom.2025.131221","name":"Advancements in neuromorphic computing for bio-inspired artificial vision: A review","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2025.131221","authors":["Sharmarke A. Gabayre","Mindula Illeperuma","Varuna D. De-Silva","Xiyu Shi","Sergey E. Savel’ev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-13T22:09:04Z","doi":"10.1016/j.neucom.2025.131221","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.143Z"},{"id":"doi:10.1117/12.3000089","name":"Brain-inspired optical imaging: a neuromorphic computing approach for image reconstruction of dynamic targets obscured by dense turbid media","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3000089","authors":["Ning Zhang","Arto Nurmikko"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-13T16:32:08Z","doi":"10.1117/12.3000089","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1109/icnc59488.2023.10462829","name":"Vehicle Intelligent Application System Based on Improved YOLOv5 and DeepSORT","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462829","authors":["Lu Liu","Ling Chen","Chuandong Li","Zhiyuan Zhu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462829","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1117/12.3017713","name":"Light-stimulated synaptic transistor based on two-dimensional/organic heterojunction for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3017713","authors":["Chao Han","Jiayue Han","He Yu","Jun Gou","Jun Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-30T15:46:49Z","doi":"10.1117/12.3017713","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1088/2634-4386/ad5c97","name":"Efficient sparse spiking auto-encoder for reconstruction, denoising and classification","source":"crossref","abstract":"Abstract Auto-encoders are capable of performing input reconstruction, denoising, and classification through an encoder-decoder structure. Spiking Auto-Encoders (SAEs) can utilize asynchronous sparse spikes to improve power efficiency and processing latency on neuromorphic hardware. In our work, we propose an efficient SAE trained using only Spike-Timing-Dependant Plasticity (STDP) learning. Our auto-encoder uses the Time-To-First-Spike (TTFS) encoding scheme and needs to update all synaptic weights only once per input, promoting both training and inference efficiency due to the extreme sparsity. We showcase robust reconstruction performance on the Modified National Institute of Standards and Technology (MNIST) and Fashion-MNIST datasets with significantly fewer spikes compared to state-of-the-art SAEs by 1–3 orders of magnitude. Moreover, we achieve robust noise reduction results on the MNIST dataset. When the same noisy inputs are used for classification, accuracy degradation is reduced by 30%–80% compared to prior works. It also exhibits classification accuracies comparable to previous STDP-based classifiers, while remaining competitive with other backpropagation-based spiking classifiers that require global learning through gradients and significantly more spikes for encoding and classification of MNIST/Fashion-MNIST inputs. The presented results demonstrate a promising pathway towards building efficient sparse spiking auto-encoders with local learning, making them highly suited for hardware integration.","url":"https://doi.org/10.1088/2634-4386/ad5c97","authors":["Ben Walters","Hamid Rahimian Kalatehbali","Zhengyu Cai","Roman Genov","Amirali Amirsoleimani","Jason Eshraghian","Mostafa Rahimi Azghadi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-27T22:26:11Z","doi":"10.1088/2634-4386/ad5c97","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1007/978-3-319-59153-7_50","name":"Development of Doped Graphene Oxide Resistive Memories for Applications Based on Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-59153-7_50","authors":["Marina Sparvoli","Mauro F. P. Silva","Mario Gazziro"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-05-16T20:53:33Z","doi":"10.1007/978-3-319-59153-7_50","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1016/j.apsusc.2026.168162","name":"Oxygen vacancy-regulated W/WOX/Pt RRAM with coexisting volatile and nonvolatile switching for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.apsusc.2026.168162","authors":["Liwei Zhou","Chengxu Ke","Qiuxu Yu","Shuyi Li","Yuqiao Wang","Jinshi Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-22T09:21:38Z","doi":"10.1016/j.apsusc.2026.168162","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1145/3350755.3400258","name":"Provable Neuromorphic Advantages for Computing Shortest Paths","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3350755.3400258","authors":["James B. Aimone","Yang Ho","Ojas Parekh","Cynthia A. Phillips","Ali Pinar","William Severa","Yipu Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-07-09T15:56:12Z","doi":"10.1145/3350755.3400258","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1109/iecon48115.2021.9589879","name":"Vibration Analysis of a Wind Turbine Gearbox for Off-cloud Health Monitoring through Neuromorphic-computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iecon48115.2021.9589879","authors":["Pouya Soltani Zarrin","Cristian Martin","Peter Langendoerfer","Christian Wenger","Manuel Diaz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-10T23:47:51Z","doi":"10.1109/iecon48115.2021.9589879","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.23919/eumic50153.2022.9783686","name":"Towards an Excitable Microwave Spike Generator for Future Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.23919/eumic50153.2022.9783686","authors":["Qusay Al-Taai","Razvan Morariu","Jue Wang","Abdullah Al-Khalidi","Ali Al-Moathin","Bruno Romeira","Jose Figueiredo","Edward Wasige"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-01T19:50:01Z","doi":"10.23919/eumic50153.2022.9783686","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.23919/date.2017.7927183","name":"3D-DPE: A 3D high-bandwidth dot-product engine for high-performance neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.23919/date.2017.7927183","authors":["Miguel Angel Lastras-Montano","Bhaswar Chakrabarti","Dmitri B. Strukov","Kwang-Ting Cheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-05-15T20:34:41Z","doi":"10.23919/date.2017.7927183","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1109/gcwot63882.2024.10805682","name":"A Review of Recent Advances in Intelligent Neuromorphic Computing-Assisted Machine Learning for Automatic Anomaly Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/gcwot63882.2024.10805682","authors":["S.M. Zia Uddin","Babar Khan","Syeda Aimen Naseem","Syeda Umme Aeman Kamal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-27T19:08:43Z","doi":"10.1109/gcwot63882.2024.10805682","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.143Z"},{"id":"doi:10.1109/icnc52316.2021.9607985","name":"TRC-GCN: Two Residual Connections in Graph Convolution Networks for Node Classification Tasks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc52316.2021.9607985","authors":["Guoqing He","Huiwei Wang","Junjie Lv","Ziyu Sheng","Qingguo Lu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-29T20:59:32Z","doi":"10.1109/icnc52316.2021.9607985","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1021/acsaelm.5c00020","name":"Tunable Synaptic Plasticity in 2D Ferroelectric Semiconductor Transistor for High-Precision Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acsaelm.5c00020","authors":["Tingting Ma","Yichen Wei"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-01T07:10:04Z","doi":"10.1021/acsaelm.5c00020","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1088/2634-4386/ae7f47","name":"A review of event-based vision sensor fusion: architectures, evaluation and robustness challenges","source":"crossref","abstract":"Abstract Event-based vision is a neuromorphic sensing approach that enables low-latency, energy-aware perception by encoding brightness changes as sparse, asynchronous events rather than dense image frames. Event cameras provide microsecond-level timestamps and high dynamic range, supporting perception during fast motion and challenging illumination. In autonomy, event streams are often fused with complementary sensors such as inertial measurement units, color cameras, light-detection-and-ranging sensors, or radar to improve scale estimation, robustness, and redundancy. Event-centric fusion is challenging because sensor clocks and noise models differ across modalities, event rates are activity-dependent, event representations trade timing fidelity for computational convenience, and hardware cost is often dominated by communication and memory movement. Robustness to missing or degraded modalities is common in deployment but remains inconsistently evaluated. This topical review synthesizes event-based vision fusion around three coupled design decisions: fusion stage, temporal coupling, and event representation. We show how these choices determine whether systems preserve event-driven efficiency or revert to dense processing. As a case study, we review event-based depth estimation, consolidate benchmark results, and analyze missing-modality behavior. The evidence suggests that many gains are reported primarily as accuracy improvements, with limited analysis of modality dropout, event-rate shifts, timing mismatch, preprocessing cost, and efficiency. We relate recurring patterns to optical flow and semantic perception, connect them to neuromorphic hardware and hardware-algorithm co-design, and conclude with benchmarking recommendations and open problems in robustness, scalability, and training of spiking and hybrid models.","url":"https://doi.org/10.1088/2634-4386/ae7f47","authors":["Anusha Devulapally","Sadia Anjum Tumpa","Vijaykrishnan Narayanan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-18T22:50:57Z","doi":"10.1088/2634-4386/ae7f47","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.143Z"},{"id":"doi:10.1088/2634-4386/ac84fd","name":"Learning torsional eye movements through active efficient coding","source":"crossref","abstract":"Abstract The human eye has three rotational degrees of freedom: azimuthal, elevational, and torsional. Although torsional eye movements have the most limited excursion, Hering and Helmholtz have argued that they play an important role in optimizing visual information processing. In humans, the relationship between gaze direction and torsional eye angle is described by Listing’s law. However, it is still not clear how this behavior initially develops and remains calibrated during growth. Here we present the first computational model that enables an autonomous agent to learn and maintain binocular torsional eye movement control. In our model, two neural networks connected in series: one for sensory encoding followed by one for torsion control, are learned simultaneously as the agent behaves in the environment. Learning is based on the active efficient coding (AEC) framework, a generalization of Barlow’s efficient coding hypothesis to include action. Both networks adapt by minimizing the prediction error of the sensory representation, subject to a sparsity constraint on neural activity. The policies that emerge follow the predictions of Listing’s law. Because learning is driven by the sensorimotor contingencies experienced by the agent as it interacts with the environment, our system can adapt to the physical configuration of the agent as it changes. We propose that AEC provides the most parsimonious expression to date of Hering’s and Helmholtz’s hypotheses. We also demonstrate that it has practical implications in autonomous artificial vision systems, by providing an automatic and adaptive mechanism to correct orientation misalignments between cameras in a robotic active binocular vision head. Our system’s use of fairly low resolution (100 × 100 pixel) image windows and perceptual representations amenable to event-based input paves a pathway towards the implementation of adaptive self-calibrating robot control on neuromorphic hardware.","url":"https://doi.org/10.1088/2634-4386/ac84fd","authors":["Qingpeng Zhu","Chong Zhang","Jochen Triesch","Bertram E Shi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-07-28T22:20:23Z","doi":"10.1088/2634-4386/ac84fd","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1007/978-3-031-71097-1_5","name":"Intelligent Learning Algorithms for Smart Infrastructure","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-71097-1_5","authors":["Ali Akbar Firoozi","Ali Asghar Firoozi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-12T15:02:54Z","doi":"10.1007/978-3-031-71097-1_5","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1109/icoin50884.2021.9333967","name":"Intelligent Face Recognition on the Edge Computing using Neuromorphic Technology","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icoin50884.2021.9333967","authors":["Jae-Woo Kim","Cosmas Ifeanyi Nwakanma","Dong-Seong Kim","Jae-Min Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-02-03T15:42:57Z","doi":"10.1109/icoin50884.2021.9333967","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1109/icnc59488.2023.10462786","name":"Distributed Time-Varying Nash Equilibrium Algorithm Based on Prediction-Correction Technique with Set Constraints","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462786","authors":["Xingyun Dai","Xiao Fang","Linan Wang","Xinhe Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T14:09:52Z","doi":"10.1109/icnc59488.2023.10462786","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1117/12.2278026","name":"Mutually synchronized spin Hall nano-oscillators for neuromorphic computing (Conference Presentation)","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.2278026","authors":["Mykola Dvornik","Ahmad A. Awad","Philipp Dürrenfeld","Afshin Houshang","Ezio Iacocca","Randy K. Dumas","Johan Åkerman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-09-19T18:38:28Z","doi":"10.1117/12.2278026","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1002/aelm.201800795","name":"Energy‐Efficient Organic Ferroelectric Tunnel Junction Memristors for Neuromorphic Computing","source":"crossref","abstract":"Abstract Energy efficiency, parallel information processing, and unsupervised learning make the human brain a model computing system for unstructured data handling. Different types of oxide memristors can emulate synaptic functions in artificial neuromorphic circuits. However, their cycle‐to‐cycle variability or strict epitaxy requirements remain a challenge for applications in large‐scale neural networks. Here, solution‐processable ferroelectric tunnel junctions (FTJs) with P(VDF‐TrFE) copolymer barriers are reported showing analog memristive behavior with a broad range of accessible conductance states and low energy dissipation of 100 fJ for the onset of depression and 1 pJ for the onset of potentiation by resetting small tunneling currents on nanosecond timescales. Key synaptic functions like programmable synaptic weight, long‐ and short‐term potentiation and depression, paired‐pulse facilitation and depression, and Hebbian and anti‐Hebbian learning through spike shape and timing‐dependent plasticity are demonstrated. In combination with good switching endurance and reproducibility, these results offer a promising outlook on the use of organic FTJ memristors as building blocks in artificial neural networks.","url":"https://doi.org/10.1002/aelm.201800795","authors":["Sayani Majumdar","Hongwei Tan","Qi Hang Qin","Sebastiaan van Dijken"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-01-03T09:14:02Z","doi":"10.1002/aelm.201800795","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1109/icnc52316.2021.9608479","name":"Design of target suppression and feature recognition circuit based on memristor","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc52316.2021.9608479","authors":["Xiao Xiao","Juntao Han","Junwei Sun","Peng Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-29T20:59:32Z","doi":"10.1109/icnc52316.2021.9608479","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1166/jctn.2017.6611","name":"Nanoscale Electronic Processing of Artificial Network of Synapse for Neuromorphic Memristor Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1166/jctn.2017.6611","authors":["C. A Anjo","P. Aruna Priya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-08-12T23:04:06Z","doi":"10.1166/jctn.2017.6611","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1109/incos59338.2024.10527546","name":"Neuromorphic Computing Architectures for EnergyEfficient Edge Devices in Autonomous Vehicles","source":"crossref","abstract":"","url":"https://doi.org/10.1109/incos59338.2024.10527546","authors":["Rahul Pradhan","Annapurna Gummadi","P. Tanusha","Gandla Sowmya","S. Vaitheeshwari","Ponni Valavan M"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-16T17:21:09Z","doi":"10.1109/incos59338.2024.10527546","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1109/drc66027.2025.11105754","name":"Neuromorphic and Ising Computing using Emerging Non-Volatile Memory Devices for Edge Applications: Wireless Communication and Robotics","source":"crossref","abstract":"","url":"https://doi.org/10.1109/drc66027.2025.11105754","authors":["Debanjan Bhowmik","Ram Singh Yadav","Pranaba Kishor Muduli","Abhinaba Ghosh","Harsh Kumar Jadia","Sumedh Chatterjee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-11T17:40:59Z","doi":"10.1109/drc66027.2025.11105754","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1109/iccmc69250.2026.11625105","name":"Neuromorphic Digital Twin based VLSI Framework for Adaptive and Self Healing Hardware Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccmc69250.2026.11625105","authors":["Charulatha.R.T","D. Myshalini","R. Harshini","M. Theodore Kingslin","Tapas Bapu B R","J. Jayanthi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-29T19:11:44Z","doi":"10.1109/iccmc69250.2026.11625105","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.2139/ssrn.4209013","name":"Visible Light-Driven Indium-Gallium-Zinc-Oxide Optoelectronic Synaptic Transistor with Defect Engineering for Neuromorphic Computing System and Artificial Intelligence","source":"crossref","abstract":"There has been considerable interest in the development of optoelectronic synaptic transistors with synaptic functions and neural computations. These neuromorphic devices exhibit high-efficiency energy consumption and fast operation by imitating biological neural computation methods. Here, a simple defect engineering method for oxide semiconductors is proposed so that indium-gallium-zinc-oxide (IGZO) optoelectronic synaptic transistors can have synaptic behavior even in the long-wavelength-visible-light region, in which it is difficult to stimulate the conventional oxide semiconductor. Two additional defective layers (the defective interface layer and light absorption layer) are controlled to generate defects that improve the synaptic function and visible-light absorption. The IGZO optoelectronic synaptic transistor with defect engineering shows the peak of photo-induced postsynaptic current (PSC) of 17.04 nA and maximum gain of 24.67 with 25 optical pulses and a 198% paired-pulse facilitation (PPF) index under red-light illumination at a 635-nm wavelength. Furthermore, learning and forgetting were mimicked by optical and electrical signals, as demonstrated in a “Pavlov’s dog” experiment. These results demonstrate that IGZO optoelectronic synaptic transistors can be used in various optical applications driven by a wide range of visible light, such as artificial eyes or intelligent display products.","url":"https://doi.org/10.2139/ssrn.4209013","authors":["Jusung Chung","Kyungho Park","Gwan  In Kim","Jong Bin An","Sujin Jung","Dong Hyun Choi","Hyun Jae Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-03T23:07:53Z","doi":"10.2139/ssrn.4209013","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1109/iscas45731.2020.9181034/video","name":"Video for Neuromorphic Information Processing with Nanowire Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas45731.2020.9181034/video","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-29T09:22:27Z","doi":"10.1109/iscas45731.2020.9181034/video","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.143Z"},{"id":"doi:10.1117/12.3005283","name":"Photoelectronic synaptic transistor with tunable plasticity for neuromorphic computing system","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3005283","authors":["Qing-an Ding","Chaoran Gu","Jianyu Li","Youli Yao","Xiaoyuan Li","Binghui Hou","Kexin Yu","Xiaoling Zuo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-24T15:01:10Z","doi":"10.1117/12.3005283","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.143Z"},{"id":"doi:10.3390/cryst14010069","name":"Transistor-Based Synaptic Devices for Neuromorphic Computing","source":"crossref","abstract":"Currently, neuromorphic computing is regarded as the most efficient way to solve the von Neumann bottleneck. Transistor-based devices have been considered suitable for emulating synaptic functions in neuromorphic computing due to their synergistic control capabilities on synaptic weight changes. Various low-dimensional inorganic materials such as silicon nanomembranes, carbon nanotubes, nanoscale metal oxides, and two-dimensional materials are employed to fabricate transistor-based synaptic devices. Although these transistor-based synaptic devices have progressed in terms of mimicking synaptic functions, their application in neuromorphic computing is still in its early stage. In this review, transistor-based synaptic devices are analyzed by categorizing them into different working mechanisms, and the device fabrication processes and synaptic properties are discussed. Future efforts that could be beneficial to the development of transistor-based synaptic devices in neuromorphic computing are proposed.","url":"https://doi.org/10.3390/cryst14010069","authors":["Wen Huang","Huixing Zhang","Zhengjian Lin","Pengjie Hang","Xing’ao Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-09T10:48:06Z","doi":"10.3390/cryst14010069","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.143Z"},{"id":"doi:10.1088/2515-7639/ad5251","name":"In-sensor neuromorphic computing using perovskites and transition metal dichalcogenides","source":"crossref","abstract":"Abstract With the advancements in Web of Things, Artificial Intelligence, and other emerging technologies, there is an increasing demand for artificial visual systems to perceive and learn about external environments. However, traditional sensing and computing systems are limited by the physical separation of sense, processing, and memory units that results in the challenges such as high energy consumption, large additional hardware costs, and long latency time. Integrating neuromorphic computing functions into the sensing unit is an effective way to overcome these challenges. Therefore, it is extremely important to design neuromorphic devices with sensing ability and the properties of low power consumption and high switching speed for exploring in-sensor computing devices and systems. In this review, we provide an elementary introduction to the structures and properties of two common optoelectronic materials, perovskites and transition metal dichalcogenides (TMDs). Subsequently, we discuss the fundamental concepts of neuromorphic devices, including device structures and working mechanisms. Furthermore, we summarize and extensively discuss the applications of perovskites and TMDs in in-sensor computing. Finally, we propose potential strategies to address challenges and offer a brief outlook on the application of optoelectronic materials in term of in-sensor computing.","url":"https://doi.org/10.1088/2515-7639/ad5251","authors":["Shen-Yi Li","Ji-Tuo Li","Kui Zhou","Yan Yan","Guanglong Ding","Su-Ting Han","Ye Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-30T22:46:02Z","doi":"10.1088/2515-7639/ad5251","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.143Z"},{"id":"doi:10.1007/978-3-031-71097-1_6","name":"Case Studies and Application-Driven Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-71097-1_6","authors":["Ali Akbar Firoozi","Ali Asghar Firoozi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-12T15:02:54Z","doi":"10.1007/978-3-031-71097-1_6","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.143Z"},{"id":"doi:10.1109/icnc64304.2024.10987897","name":"Multi-Strategy Collaborative Improved Seagull Optimization Algorithm and Its Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987897","authors":["Hua Yang","Lihao Yu","Yanjie Lv","Hao Xue","Siyi Wang","Tiancheng Zhang","Yunhan Huang","Taiyong Deng","Qing Zhao","Hao Shen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987897","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.143Z"},{"id":"doi:10.7567/ssdm.2015.o-3-1","name":"(Invited) TMO-ReRAM Based Synaptic Device For Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.7567/ssdm.2015.o-3-1","authors":["J. F. Kang","B. Gao","Z. Chen","P. Huang","Y. D. Zhao","L. F. Liu","X. Y. Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-01-29T04:31:25Z","doi":"10.7567/ssdm.2015.o-3-1","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.143Z"},{"id":"doi:10.1109/indin64977.2025.11279189","name":"Domain Generalized Neuromorphic Computing for Cross-Domain Machinery Fault Diagnosis with Dynamic Vision","source":"crossref","abstract":"","url":"https://doi.org/10.1109/indin64977.2025.11279189","authors":["Changhao Liu","Hang Chen","Dehao Cai","Xiang Li","Wei Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-06T18:33:35Z","doi":"10.1109/indin64977.2025.11279189","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.143Z"},{"id":"doi:10.1109/hpec43674.2020.9286246","name":"Target Classification in Synthetic Aperture Radar and Optical Imagery Using Loihi Neuromorphic Hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1109/hpec43674.2020.9286246","authors":["Mark Barnell","Courtney Raymond","Matthew Wilson","Darrek Isereau","Chris Cicotta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-22T21:07:15Z","doi":"10.1109/hpec43674.2020.9286246","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.143Z"},{"id":"doi:10.4018/979-8-3693-6303-4.ch006","name":"A Review of GAN-Synthesized Brain MR Image Applications","source":"crossref","abstract":"Recent advancements in brain imaging technology have led to a rise in the use of magnetic resonance imaging (MRI) for clinical diagnosis. Deep learning (DL) techniques have emerged as a valuable tool for automatically detecting abnormalities in brain images without manual intervention. Meanwhile, generative adversarial networks (GANs) have shown promise in generating synthetic brain images for a variety of applications, such as image translation, registration, super-resolution, denoising, motion correction, segmentation, reconstruction, and contrast enhancement. This chapter conducts a comprehensive review of the literature on the use of GAN-synthesized images for diagnosing brain diseases, drawing on data from studies in the Web of Science and Scopus databases from the past decade. The review examines the various loss functions and software tools used in processing brain MRI images, as well as provides a comparative analysis of evaluation metrics for GAN-synthesized images to assist researchers in selecting the most appropriate metric for their specific needs.","url":"https://doi.org/10.4018/979-8-3693-6303-4.ch006","authors":["Ankita Tiwari","Sampada Tavse","Mrinal Bachute","Abhishek Bhola"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-29T15:16:27Z","doi":"10.4018/979-8-3693-6303-4.ch006","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.143Z"},{"id":"doi:10.1109/icnc64304.2024.10987666","name":"Bidirectional Dynamic Spatiotemporal Graph Recurrent Neural Network for Traffic Flow Forecasting","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987666","authors":["Xingyan Wang","Dawen Xia","Zhan Lin","Mingyue Huang","Yang Hu","Huaqing Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987666","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.143Z"},{"id":"doi:10.1109/icnc52316.2021.9608484","name":"Chaotic Time Series Prediction using Three-Dimensional FOA and Echo State Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc52316.2021.9608484","authors":["Yanhu Wang","Shanshan Xu","Yuling Luo","Shunsheng Zhang","Min Su","Senhui Qiu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-29T20:59:32Z","doi":"10.1109/icnc52316.2021.9608484","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.143Z"},{"id":"doi:10.1109/icons69015.2025.00027","name":"Neuromorphic Closed-Loop Control with Spiking Motor Neuron and Muscle Spindle Models","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons69015.2025.00027","authors":["Paula Stoll","Giacomo Indiveri","Chiara Bartolozzi","Elisa Donati"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-21T21:07:17Z","doi":"10.1109/icons69015.2025.00027","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.143Z"},{"id":"doi:10.1109/icnc59488.2023.10462799","name":"On Predefined-time Synchronization of Complex-valued Neural Networks With Inertial Terms","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462799","authors":["Linchao Dong","Ting Liu","Peng Liu","Hangjun Che","Junwei Sun","Peizhao Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462799","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1145/3194554.3194636","name":"Memristive Crossbar Mapping for Neuromorphic Computing Systems on 3D IC","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3194554.3194636","authors":["Qi Xu","Song Chen","Bei Yu","Feng Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-06-07T13:57:46Z","doi":"10.1145/3194554.3194636","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1142/9789811290084_0009","name":"Limits and Solvability of Machine Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789811290084_0009","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-26T02:06:27Z","doi":"10.1142/9789811290084_0009","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1088/2634-4386/ae978d","name":"Learning in spiking neural networks with a calcium-based Hebbian rule for spike timing-dependent plasticity","source":"crossref","abstract":"Abstract Understanding how biological neural networks are shaped via local plasticity mechanisms can lead to energy-efficient and self-adaptive information processing systems, which promises to mitigate some of the&amp;#xD;current roadblocks in edge computing systems. While biology makes use of spikes to seamless use both spike timing and mean firing rate to modulate synaptic strength, most models focus on one of the two. In this work, we present a Hebbian local learning rule that models synaptic modification as a function of calcium traces tracking neuronal activity. We show how the rule reproduces results from spike time and spike rate protocols from neuroscientific studies. Moreover, we use the model to train spiking neural networks on MNIST digit recognition to show and explain what sort of mechanisms are needed to learn real-world patterns. We show how our model is sensitive to correlated spiking activity and how this enables it to modulate the learning rate of the network without altering the mean firing rate of the neurons nor the hyparameters of the learning rule. To the best of our knowledge, this is the first work that showcases how spike timing and rate can be complementary in their role of shaping the connectivity of spiking neural networks.","url":"https://doi.org/10.1088/2634-4386/ae978d","authors":["Willian Soares Girāo","Nicoletta Risi","Caroline Geisler","Elisabetta Chicca"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-10T22:49:42Z","doi":"10.1088/2634-4386/ae978d","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.5772/intechopen.94297","name":"Neuromorphic Photonics","source":"crossref","abstract":"Neuromorphic photonic applies concepts extracted from neuroscience to develop photonic devices behaving like neural systems and achieve brain-like information processing capacity and efficiency. This new field combines the advantages of photonics and neuromorphic architectures to build systems with high efficiency, high interconnectivity and paves the way to ultrafast, power efficient and low cost and complex signal processing. We explore the use of semiconductor lasers with optoelectronic feedback operating in self-pulsating mode as photonic neuron that can deliver flexible control schemes with narrow optical pulses of less than 30 ps pulse width, with adjustable pulse intervals of −2 ps/mA to accommodate specific Pulse Position Modulation (PPM) coding of events to trigger photonic neuron firing as required. The analyses cover in addition to self-pulsation performance and controls, the phase noise and jitter characteristics of such solution.","url":"https://doi.org/10.5772/intechopen.94297","authors":["Mike Haidar Shahine"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-11-06T11:04:43Z","doi":"10.5772/intechopen.94297","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.143Z"},{"id":"doi:10.1109/icons69015.2025","name":"2025 International Conference on Neuromorphic Systems (ICONS)","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons69015.2025","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-21T21:08:13Z","doi":"10.1109/icons69015.2025","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.143Z"},{"id":"doi:10.1149/ma2018-01/32/1952","name":"(Invited) Strain Engineering for Li and Oxygen Ionic Transport for Solid State Batteries in Energy Storage, Fuel Cells and Memristive Neuromorphic Computing Devices","source":"crossref","abstract":"Energy storage and neuromorphic computation concepts based on oxygen and lithium ionic movements rely in the device preformance on the available defects and their mobilities. Through this paper we explore novel concepts on the use of strain for crystalline or polyamorphic oxide films to engineer the ionic transference of either lithium of oxygen ionic carriers as electrolyte components for either solid state batteries, fuel cells or memristive neuromorphic computational devices. The interplay of structure-strain-lattice symmetry break ups-ionic transfer vs. device performance engineering is in focus.","url":"https://doi.org/10.1149/ma2018-01/32/1952","authors":["Jennifer L.M. Rupp"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-09T01:07:35Z","doi":"10.1149/ma2018-01/32/1952","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1088/1757-899x/912/6/062029","name":"Current Research and Future Prospects of Neuromorphic Computing in Artificial Intelligence","source":"crossref","abstract":"Abstract Neuromorphic computing is a budding avenue though it has been known since the 80’s. The extensive research and development in the field of artificial intelligence particularly in the last decade is tremendous. The growth of artificial intelligence is expected to grow exponential in the years to come. Technologies like machine learning and IoT has made possible for many fields from industrial automation to business model prediction very affordable and far less complex. With growing digital devices, the number of devices connected to the cloud and in a network is doubling and in some cases are tripling in some ventures. Technologies like drones, autonomous cars, smart healthcare, smart cities and many other are moving towards more and more data and connected devices to the cloud. The present hardware system is at the verge of giving away as the data generation rate and processing volumes of the same is becoming a challenge. The hardware of today, though are advance are simply not adequate to support the expansion rate of growth of artificial intelligence in all fields. Increased devices result in increase data, increased processing raising challenges for current storage devices and processing devices. Neuromorphic chips, which promise to overcome this challenge, are currently being researched extensively by many computer giants who fear the future incompetency of hardware of which IBM is a major player. Ground breaking research in the field of memristor and artificial synapse have paved the way for neuromorphic chips which are expected to revolutionized the field for the better. This paper deals with the current research, physical and technical limitations and future scope of neuromorphic chips. The significance of memristor and artificial synapse towards neuromorphic computing is also dealt in detail.","url":"https://doi.org/10.1088/1757-899x/912/6/062029","authors":["R Vishwa","R Karthikeyan","R Rohith","A Sabaresh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-12T01:17:00Z","doi":"10.1088/1757-899x/912/6/062029","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.4018/979-8-3693-6303-4.ch013","name":"Neurocomputing Advancements to Unlock Image Intelligence for Industrial Computer Vision","source":"crossref","abstract":"Distinct technologies have been formulated at different times to improve technology, and unique technologies are continuously emerging. Neurocomputing has significantly expanded technologies, revealed moderately acceptable results, and provided ultimate collaboration. It is a type of computational system that executes its functions by mimicking the workings methodology of the human brain. Neurocomputing utilizes artificial neural networks managed by interconnected nodes, which collectively perform miscellaneous tasks. Each node processes small portions of information and communicates it to the next node, which assembles an extensive network and cracks many complex problems. This functional capability of neurocomputing can provide fruitful solutions for any complex task related to computer vision, enabling the computer system to extract meaningful information from images effortlessly. The functional benefit of neurocomputing, whereas manifold applications and computer vision components are determined to yield unthinkable results using images in the industrial sector.","url":"https://doi.org/10.4018/979-8-3693-6303-4.ch013","authors":["Soumitra Saha","Umesh Kumar Lilhore","Sarita Simaiya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-29T15:16:27Z","doi":"10.4018/979-8-3693-6303-4.ch013","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1117/12.3028834","name":"Voltage control of interfacial magnetism for energy-efficient memory and neuromorphic computing in magnetoionic materials and devices","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3028834","authors":["Md Mahadi Rajib","Dhritiman Bhattacharya","Kai Liu","Jayasimha Atulasimha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-04T19:10:32Z","doi":"10.1117/12.3028834","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.143Z"},{"id":"doi:10.1145/3716368.3735295","name":"AI-Powered Knowledge Graphs for Neuromorphic and Energy-Efficient Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3716368.3735295","authors":["Ashish Gautam","Robert Patton","Thomas Potok","Ramakrishnan Kannan","James Aimone","William Severa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-27T13:58:23Z","doi":"10.1145/3716368.3735295","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.143Z"},{"id":"doi:10.3390/jlpea10040036","name":"InSight: An FPGA-Based Neuromorphic Computing System for Deep Neural Networks","source":"crossref","abstract":"Deep neural networks have demonstrated impressive results in various cognitive tasks such as object detection and image classification. This paper describes a neuromorphic computing system that is designed from the ground up for energy-efficient evaluation of deep neural networks. The computing system consists of a non-conventional compiler, a neuromorphic hardware architecture, and a space-efficient microarchitecture that leverages existing integrated circuit design methodologies. The compiler takes a trained, feedforward network as input, compresses the weights linearly, and generates a time delay neural network reducing the number of connections significantly. The connections and units in the simplified network are mapped to silicon synapses and neurons. We demonstrate an implementation of the neuromorphic computing system based on a field-programmable gate array that performs image classification on the hand-wirtten 0 to 9 digits MNIST dataset with 99.37% accuracy consuming only 93uJ per image. For image classification on the colour images in 10 classes CIFAR-10 dataset, it achieves 83.43% accuracy at more than 11× higher energy-efficiency compared to a recent field-programmable gate array (FPGA)-based accelerator.","url":"https://doi.org/10.3390/jlpea10040036","authors":["Taeyang Hong","Yongshin Kang","Jaeyong Chung"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-10-30T21:34:47Z","doi":"10.3390/jlpea10040036","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.143Z"},{"id":"doi:10.34133/adi.0044","name":"Recent Progress in Neuromorphic Computing from Memristive Devices to Neuromorphic Chips","source":"crossref","abstract":"Neuromorphic computing, drawing inspiration from the brain, stands out for its high energy efficiency in executing complex tasks. Memristive device-based neuromorphic computing has demonstrated ultrahigh efficiency. While there are numerous review papers in this field, the majority concentrate on the device level, bypassing the connections among the performance metrics of memristive devices and those of neuromorphic chips. In this review, we investigate the recent progress in neuromorphic computing from the fundamental memristive devices to the intricate neuromorphic chips, highlighting their links and challenges.","url":"https://doi.org/10.34133/adi.0044","authors":["Yike Xiao","Cheng Gao","Juncheng Jin","Weiling Sun","Bowen Wang","Yukun Bao","Chen Liu","Wei Huang","Hui Zeng","Yefeng Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-31T09:00:55Z","doi":"10.34133/adi.0044","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.143Z"},{"id":"doi:10.3389/fnano.2021.675792","name":"Spoken Digit Classification by In-Materio Reservoir Computing With Neuromorphic Atomic Switch Networks","source":"crossref","abstract":"Atomic Switch Networks comprising silver iodide (AgI) junctions, a material previously unexplored as functional memristive elements within highly interconnected nanowire networks, were employed as a neuromorphic substrate for physical Reservoir Computing This new class of ASN-based devices has been physically characterized and utilized to classify spoken digit audio data, demonstrating the utility of substrate-based device architectures where intrinsic material properties can be exploited to perform computation in-materio. This work demonstrates high accuracy in the classification of temporally analyzed Free-Spoken Digit Data These results expand upon the class of viable memristive materials available for the production of functional nanowire networks and bolster the utility of ASN-based devices as unique hardware platforms for neuromorphic computing applications involving memory, adaptation and learning.","url":"https://doi.org/10.3389/fnano.2021.675792","authors":["Sam Lilak","Walt Woods","Kelsey Scharnhorst","Christopher Dunham","Christof Teuscher","Adam Z. Stieg","James K. Gimzewski"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-05-26T06:24:40Z","doi":"10.3389/fnano.2021.675792","addedAt":"2026-09-01T01:48:20.143Z","updatedAt":"2026-09-01T01:48:20.143Z"},{"id":"doi:10.6082/sx4gn-66w06","name":"Hydrogen-Induced Topotactic Phase Transformations of Cobaltite Thin Films","source":"datacite","abstract":"Manipulating physical properties through ion migration in complex oxide thin films is an emerging research direction to achieve tunable materials for advanced applications. While the reduction of complex oxides has been widely reported, few reports exist on the modulation of physical properties through a direct hydrogenation process. Here, we report an unusual mechanism for hydrogen-induced topotactic phase transitions in perovskite La0.7Sr0.3CoO3 thin films. Hydrogenation is performed upon annealing in a pure hydrogen gas environment, offering a direct understanding of the role that hydrogen plays at the atomic scale in these transitions. Topotactic phase transformations from the perovskite (P) to hydrogenated-brownmillerite (H-BM) phase can be induced at temperatures as low as 220 °C, while at higher hydrogenation temperatures (320–400 °C), the progression toward more reduced phases is hindered. Density functional theory calculations suggest that hydroxyl bonds are formed with the introduction of hydrogen ions, which lower the formation energy of oxygen vacancies of the neighboring oxygen, enabling the transition from the P to H-BM phase at low temperatures. Furthermore, the impact on the magnetic and electronic properties of the hydrogenation temperature is investigated. Our research provides a potential pathway for utilizing hydrogen as a basis for low-temperature modulation of complex oxide thin films, with potential applications in neuromorphic computing.","url":"https://doi.org/10.6082/sx4gn-66w06","authors":["Feng, Mingzhen","Li, Junjie","Zhang, Shenli","Pofelski, Alexandre","El Hage, Ralph","Klewe, Christoph","N'diaye, Alpha T.","Shafer, Padraic","Zhu, Yimei","Galli, Giulia","Schuller, Ivan K.","Takamura, Yayoi"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.6082/sx4gn-66w06","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.6082/fn5n3-4vg84","name":"Hydrogen-Induced Topotactic Phase Transformations of Cobaltite Thin Films","source":"datacite","abstract":"Manipulating physical properties through ion migration in complex oxide thin films is an emerging research direction to achieve tunable materials for advanced applications. While the reduction of complex oxides has been widely reported, few reports exist on the modulation of physical properties through a direct hydrogenation process. Here, we report an unusual mechanism for hydrogen-induced topotactic phase transitions in perovskite La0.7Sr0.3CoO3 thin films. Hydrogenation is performed upon annealing in a pure hydrogen gas environment, offering a direct understanding of the role that hydrogen plays at the atomic scale in these transitions. Topotactic phase transformations from the perovskite (P) to hydrogenated-brownmillerite (H-BM) phase can be induced at temperatures as low as 220 °C, while at higher hydrogenation temperatures (320–400 °C), the progression toward more reduced phases is hindered. Density functional theory calculations suggest that hydroxyl bonds are formed with the introduction of hydrogen ions, which lower the formation energy of oxygen vacancies of the neighboring oxygen, enabling the transition from the P to H-BM phase at low temperatures. Furthermore, the impact on the magnetic and electronic properties of the hydrogenation temperature is investigated. Our research provides a potential pathway for utilizing hydrogen as a basis for low-temperature modulation of complex oxide thin films, with potential applications in neuromorphic computing.","url":"https://doi.org/10.6082/fn5n3-4vg84","authors":["Feng, Mingzhen","Li, Junjie","Zhang, Shenli","Pofelski, Alexandre","El Hage, Ralph","Klewe, Christoph","N'diaye, Alpha T.","Shafer, Padraic","Zhu, Yimei","Galli, Giulia","Schuller, Ivan K.","Takamura, Yayoi"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.6082/fn5n3-4vg84","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.6082/p36nq-7t222","name":"Nanoenabled Trainable Systems: From Biointerfaces to Biomimetics","source":"datacite","abstract":"In the dynamic biological system, cells and tissues adapt to diverse environmental conditions and form memories, an essential aspect of training for survival and evolution. An understanding of the biological training principles will inform the design of biomimetic materials whose properties evolve with the environment and offer routes to programmable soft materials, neuromorphic computing, living materials, and biohybrid robotics. In this perspective, we examine the mechanisms by which cells are trained by environmental cues. We outline the artificial platforms that enable biological training and examine the relationship between biological training and biomimetic materials design. We place emphasis on nanoscale material platforms which, given their applicability to chemical, mechanical and electrical stimulation, are critical to bridging natural and synthetic systems.","url":"https://doi.org/10.6082/p36nq-7t222","authors":["Li, Pengju","Kim, Saehyun","Tian, Bozhi"],"tags":["Trainable biointerfaces","nanomaterials","biomimetics","living materials","adaptive systems"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.6082/p36nq-7t222","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.6082/m2hxq-4h460","name":"Nanoenabled Trainable Systems: From Biointerfaces to Biomimetics","source":"datacite","abstract":"In the dynamic biological system, cells and tissues adapt to diverse environmental conditions and form memories, an essential aspect of training for survival and evolution. An understanding of the biological training principles will inform the design of biomimetic materials whose properties evolve with the environment and offer routes to programmable soft materials, neuromorphic computing, living materials, and biohybrid robotics. In this perspective, we examine the mechanisms by which cells are trained by environmental cues. We outline the artificial platforms that enable biological training and examine the relationship between biological training and biomimetic materials design. We place emphasis on nanoscale material platforms which, given their applicability to chemical, mechanical and electrical stimulation, are critical to bridging natural and synthetic systems.","url":"https://doi.org/10.6082/m2hxq-4h460","authors":["Li, Pengju","Kim, Saehyun","Tian, Bozhi"],"tags":["Trainable biointerfaces","nanomaterials","biomimetics","living materials","adaptive systems"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.6082/m2hxq-4h460","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2602.18072","name":"HiAER-Spike Software-Hardware Reconfigurable Platform for Event-Driven Neuromorphic Computing at Scale","source":"datacite","abstract":"In this work, we present HiAER-Spike, a modular, reconfigurable, event-driven neuromorphic computing platform designed to execute large spiking neural networks with up to 160 million neurons and 40 billion synapses - roughly twice the neurons of a mouse brain at faster than real time. This system, assembled at the UC San Diego Supercomputer Center, comprises a co-designed hard- and software stack that is optimized for run-time massively parallel processing and hierarchical address-event routing (HiAER) of spikes while promoting memory-efficient network storage and execution. The architecture efficiently handles both sparse connectivity and sparse activity for robust and low-latency event-driven inference for both edge and cloud computing. A Python programming interface to HiAER-Spike, agnostic to hardware-level detail, shields the user from complexity in the configuration and execution of general spiking neural networks with minimal constraints in topology. The system is made easily available over a web portal for use by the wider community. In the following, we provide an overview of the hard- and software stack, explain the underlying design principles, demonstrate some of the system's capabilities and solicit feedback from the broader neuromorphic community. Examples are shown demonstrating HiAER-Spike's capabilities for event-driven vision on benchmark CIFAR-10, DVS event-based gesture, MNIST, and Pong tasks.","url":"https://doi.org/10.48550/arxiv.2602.18072","authors":["Frank, Gwenevere","Hota, Gopabandhu","Wang, Keli","Deng, Christopher","Arora, Krish","Vins, Diana","Uppal, Abhinav","Olajide, Omowuyi","Yoshimoto, Kenneth","Wang, Qingbo","Yamaoka, Mari","Leugering, Johannes","Deiss, Stephen","Gibb, Leif","Cauwenberghs, Gert"],"tags":["Hardware Architecture (cs.AR)","Artificial Intelligence (cs.AI)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2602.18072","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2606.13516","name":"Adaptive-Frequency Resonate-and-Fire Neurons for Spectral Estimation of Streaming Radar Signals","source":"datacite","abstract":"Frequency Modulated Continuous Wave (FMCW) radar systems traditionally rely on Fourier-based methods, such as the Fast Fourier Transform (FFT), to estimate target range and velocity. While computationally efficient, these approaches require storing and processing large blocks of data, which can become a bottleneck in memory-constrained or low-latency applications. In this work, we propose a neuromorphic-inspired signal processing method based on adaptive resonate-and-fire (ARF) neurons formulated as a discrete-time dynamical system. Each neuron dynamically adjusts its internal frequency to match dominant frequency components of the input radar signal, enabling direct estimation of target ranges and velocities without computing the full frequency spectrum. The proposed model operates in a sample-by-sample fashion, resulting in memory requirements that scale with the number of tracked targets rather than the signal length. A feedback mechanism is also introduced to enable multiple neurons to lock on distinct frequency components in multi-target cases. Results on simulated and experimental data demonstrate that the method can successfully track multiple targets. Compared to conventional FFT-based approaches, the proposed method offers reduced memory usage proportional only to the number of tracked targets, making it suitable for resource-constrained and edge-based radar applications.","url":"https://doi.org/10.48550/arxiv.2606.13516","authors":["Chiavazza, Stefano","Yuan, Sen","Geilen, Marc","Fioranelli, Francesco","Corradi, Federico"],"tags":["Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.13516","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2606.13328","name":"Non-Parametric Dual-Manifold Mapping via 8-Bit Bounded Transformation Matrices: Challenging FP-centric Hardware Paradigms in Low-Energy AI","source":"datacite","abstract":"Modern deep learning hardware paradigms rely heavily on computationally expensive floating-point arithmetic (FP32, FP16, and FP8), requiring massive thermal and energetic overheads to maintain gradient-based optimization. This paper introduces a non-parametric, training-free computational framework for dual-manifold mapping that operates strictly within an 8-bit signed integer boundary and leverages simple bitwise and accumulation logic. By mapping a Spatial Manifold (N_spatial = 8192 neurons) and a Gabor-pooled Structural Manifold (N_structural = 4096 neurons) through an integer-based transformation matrix (Z-matrix), we eliminate the need for floating-point multipliers. Inference is achieved via cache-friendly pointer offsets and bitwise masks, accumulating directional sign-charges using fixed thresholds (theta_reject = 8.0, theta_cut = 2.0). Learning is executed through a localized, bounded update mechanism restricted strictly within [-127, 127], modulated by stochastic noise injection. Both architectures demonstrate extreme holographic resilience, preserving near-perfect reconstruction via a global scaling factor under 90% truncation sparsity and 20% random node destruction. By reducing core AI inference to 8-bit boundaries and boolean-like execution, this framework outlines a paradigm shift toward neuromorphic edge-computing, directly questioning the long-term necessity of dense, floating-point-centric GPU accelerators.","url":"https://doi.org/10.48550/arxiv.2606.13328","authors":["Kopp, Lars"],"tags":["Hardware Architecture (cs.AR)","FOS: Computer and information sciences","FOS: Computer and information sciences","Computer science -- Artificial intelligence -- Deep learning"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.13328","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2606.12968","name":"Quantum-Driven Neuromorphic Computing for Million-Qubit-Scale Workloads","source":"datacite","abstract":"We introduce Apollo, a 10000 node p-qubit neuromorphic processor fabricated in 16 nm mixed signal CMOS and operating fully at room temperature with a typical analog core power envelope of about 0.5 W. Its fundamental element, the p-qubit, is a bistable stochastic unit whose continuous time state fluctuations are driven by integrated quantum entropy units that inject true quantum derived randomness. This enables ultrafast stochastic transitions at low energy while preserving a classical state representation. Apollo combines these p-qubits with a high degree Hyperion 256 interconnect topology, allowing efficient embedding of dense Ising and QUBO problems with substantially reduced minor embedding overhead compared with sparse annealing platforms. We show that, through the Suzuki Trotter correspondence, the equilibrium statistics and annealing dynamics of the p-qubit network reproduce key properties of transverse field quantum annealing without cryogenic cooling, long lived coherence, or microwave control. Beyond device level validation, Apollo is evaluated on a three dimensional spin glass benchmark previously used to study quantum advantage in superconducting annealers. Across 300 disorder realizations, Apollo reaches substantially lower ground state energies than reported cryogenic quantum annealing hardware, while remaining distinct from classical simulated annealing and simulated quantum annealing. A 350 nm release candidate device experimentally validates the core p-qubit dynamics, thermodynamic sampling correctness, and continuous time annealing behavior. These results establish Apollo as a room temperature, industrially scalable platform for quantum driven energy based optimization, probabilistic inference, generative modeling, and hybrid classical quantum workflows.","url":"https://doi.org/10.48550/arxiv.2606.12968","authors":["Ivanov, Adams","Rahmeh, Samer","Nascimento, Erick Giovani Sperandio","Herrmann, Daniela"],"tags":["Quantum Physics (quant-ph)","Hardware Architecture (cs.AR)","FOS: Physical sciences","FOS: Physical sciences","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.12968","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.6082/884kt-fyn36","name":"Elucidating dynamic conductive state changes in amorphous lithium lanthanum titanate for resistive switching devices","source":"datacite","abstract":"Exploration of novel resistive switching materials attracts attention to achieve neuromorphic computing that can surpass the limit of the current Von-Neumann computing for the time of Internet of Things (IoT). Battery materials priorly used to serve as an electrode or electrolyte have demonstrated metal-insulator transitions upon an electrical biasing due to resulting compositional change, which is desirable property for future resistive switching devices. For example, it has been suggested that solid-state electrolyte amorphous lithium lanthanum titanate (a-LLTO) changes in electronic conductivity depending on oxygen content. In this work, switching behavior of a-LLTO was investigated at both bulk- and nano-scale by employing a range of voltage sweep techniques, ultimately establishing a stable and optimal operating condition within the voltage window of − 3.5 V to 3.5 V. This voltage range effectively balances the desirable trait of a substantial resistance change by three orders of magnitude with the imperative avoidance of LLTO decomposition. Experiment and computation with different LLTO composition shows that LLTO has two distinct conductivity states due to Ti reduction. The distribution of these two states is discussed using simplified binary model, implying the conductive filament growth during low resistance state. Consequently, our study deepens understanding of LLTO electronic properties and encourages the interdisciplinary application of battery materials for resistive switching devices.","url":"https://doi.org/10.6082/884kt-fyn36","authors":["Shimizu, Ryosuke","Cheng, Diyi","Zhu, Guomin","Han, Bing","Marchese, Thomas S.","Burger, Randall","Xu, Mingjie","Pan, Xiaoqing","Zhang, Minghao","Meng, Ying Shirley"],"tags":["Solid electrolyte","Resistive Switching","Li-ion battery","Oxygen vacancy"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.6082/884kt-fyn36","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.6082/2gh2j-ay841","name":"Elucidating dynamic conductive state changes in amorphous lithium lanthanum titanate for resistive switching devices","source":"datacite","abstract":"Exploration of novel resistive switching materials attracts attention to achieve neuromorphic computing that can surpass the limit of the current Von-Neumann computing for the time of Internet of Things (IoT). Battery materials priorly used to serve as an electrode or electrolyte have demonstrated metal-insulator transitions upon an electrical biasing due to resulting compositional change, which is desirable property for future resistive switching devices. For example, it has been suggested that solid-state electrolyte amorphous lithium lanthanum titanate (a-LLTO) changes in electronic conductivity depending on oxygen content. In this work, switching behavior of a-LLTO was investigated at both bulk- and nano-scale by employing a range of voltage sweep techniques, ultimately establishing a stable and optimal operating condition within the voltage window of − 3.5 V to 3.5 V. This voltage range effectively balances the desirable trait of a substantial resistance change by three orders of magnitude with the imperative avoidance of LLTO decomposition. Experiment and computation with different LLTO composition shows that LLTO has two distinct conductivity states due to Ti reduction. The distribution of these two states is discussed using simplified binary model, implying the conductive filament growth during low resistance state. Consequently, our study deepens understanding of LLTO electronic properties and encourages the interdisciplinary application of battery materials for resistive switching devices.","url":"https://doi.org/10.6082/2gh2j-ay841","authors":["Shimizu, Ryosuke","Cheng, Diyi","Zhu, Guomin","Han, Bing","Marchese, Thomas S.","Burger, Randall","Xu, Mingjie","Pan, Xiaoqing","Zhang, Minghao","Meng, Ying Shirley"],"tags":["Solid electrolyte","Resistive Switching","Li-ion battery","Oxygen vacancy"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.6082/2gh2j-ay841","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20647975","name":"NeuroSilk - Bio Neuromorphic Humanoid Robotics: Integration of Proton Donor–Acceptor (PrDA) Artificial Spider Silk Hydrogel Fibers for Soft Ionic Signal Transmission, HASEL Artificial Muscles, and Carbon Fiber Endoskeleton toward Embodied AI Systems","source":"datacite","abstract":"This thesis introduces the NeuroSilk Hybrid Robotics Architecture (NSS), a biomimetic framework for humanoid robots that emulates the human musculoskeletal and nervous systems through the coordinated integration of three principal technologies: neuron-inspired Proton Donor–Acceptor (PrDA) artificial spider silk hydrogel fibres serving as a soft, adhesive, and ionically conductive nervous system; Hydraulically Amplified Self-healing Electrostatic (HASEL) actuators serving as compliant artificial muscles; and a lightweight carbon fibre composite endoskeleton providing structural support. A four-layer architecture (endoskeleton → muscles → nerves → silicone skin with evaporative cooling) is proposed, fabricated at the component level, and characterised mechanically, electrically, and thermally. The integrated system addresses well-documented limitations of rigid robotics — high energy consumption, poor compliance, limited distributed sensing, and unsafe human interaction — while advancing the emerging field of embodied neuromorphic AI through physical, brain-like ionic signal processing and morphological computation. The work is conducted independently and shared in alignment with NASA's Transform to Open Science (TOPS) initiative. Keywords: NeuroSilk; PrDA hydrogel; HASEL actuators; soft robotics; embodied AI; hybrid robotics; neuromorphic computing; humanoid robotics; aerospace engineering; mechatronics.","url":"https://doi.org/10.5281/zenodo.20647975","authors":["Vatulia, Leona Valeria"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20647975","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20647974","name":"NeuroSilk - Bio Neuromorphic Humanoid Robotics: Integration of Proton Donor–Acceptor (PrDA) Artificial Spider Silk Hydrogel Fibers for Soft Ionic Signal Transmission, HASEL Artificial Muscles, and Carbon Fiber Endoskeleton toward Embodied AI Systems","source":"datacite","abstract":"This thesis introduces the NeuroSilk Hybrid Robotics Architecture (NSS), a biomimetic framework for humanoid robots that emulates the human musculoskeletal and nervous systems through the coordinated integration of three principal technologies: neuron-inspired Proton Donor–Acceptor (PrDA) artificial spider silk hydrogel fibres serving as a soft, adhesive, and ionically conductive nervous system; Hydraulically Amplified Self-healing Electrostatic (HASEL) actuators serving as compliant artificial muscles; and a lightweight carbon fibre composite endoskeleton providing structural support. A four-layer architecture (endoskeleton → muscles → nerves → silicone skin with evaporative cooling) is proposed, fabricated at the component level, and characterised mechanically, electrically, and thermally. The integrated system addresses well-documented limitations of rigid robotics — high energy consumption, poor compliance, limited distributed sensing, and unsafe human interaction — while advancing the emerging field of embodied neuromorphic AI through physical, brain-like ionic signal processing and morphological computation. The work is conducted independently and shared in alignment with NASA's Transform to Open Science (TOPS) initiative. Keywords: NeuroSilk; PrDA hydrogel; HASEL actuators; soft robotics; embodied AI; hybrid robotics; neuromorphic computing; humanoid robotics; aerospace engineering; mechatronics.","url":"https://doi.org/10.5281/zenodo.20647974","authors":["Vatulia, Leona Valeria"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20647974","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20644744","name":"Beyond Transformers: Emerging Neural Architectures, Energy-Efficient AI, and Multimodal Fusion for Next-Generation Artificial Intelligence","source":"datacite","abstract":"It analyzes the limitations of traditional Transformer models (such as quadratic computational complexity and high energy consumption) and explores promising alternative architectures like State Space Models (SSMs) and Mamba. The paper also investigates techniques for energy-efficient AI (including quantization, pruning, knowledge distillation, and neuromorphic computing) alongside methods for multimodal fusion—integrating text, image, audio, and sensor data into unified AI systems. Overall, it argues that the future of AI lies in developing scalable, sustainable, and efficient models that move beyond a single dominant architecture","url":"https://doi.org/10.5281/zenodo.20644744","authors":["akazou, ibtissam"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20644744","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20644743","name":"Beyond Transformers: Emerging Neural Architectures, Energy-Efficient AI, and Multimodal Fusion for Next-Generation Artificial Intelligence","source":"datacite","abstract":"It analyzes the limitations of traditional Transformer models (such as quadratic computational complexity and high energy consumption) and explores promising alternative architectures like State Space Models (SSMs) and Mamba. The paper also investigates techniques for energy-efficient AI (including quantization, pruning, knowledge distillation, and neuromorphic computing) alongside methods for multimodal fusion—integrating text, image, audio, and sensor data into unified AI systems. Overall, it argues that the future of AI lies in developing scalable, sustainable, and efficient models that move beyond a single dominant architecture","url":"https://doi.org/10.5281/zenodo.20644743","authors":["akazou, ibtissam"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20644743","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.34734/fzj-2026-02724","name":"Device-to-logic variability propagation in RRAM-based logic-in-memory architectures","source":"datacite","abstract":"Logic-in-memory (LiM) has emerged as a promising paradigm to address the von Neumann bottleneck by integrating data storage and in-situ computation. Resistive random-access memory (RRAM) is a strong candidate for LiM owing to its non-volatility, fast switching characteristics, and compatibility with CMOS integration. However, intrinsic cycle-to-cycle and device-to-device variability fundamentally limits logic reliability in RRAM-based LiM architectures, necessitating well-defined device specifications and variability margins to ensure correct operation. In this work, we experimentally demonstrate a CMOS-integrated TaOx-based 1T1R RRAM computing fabric that supports reconfigurable LiM operations, including a functionally complete Boolean set and in-memory arithmetic primitives. Through extensive statistical measurements and variability-aware statistical modeling, we systematically evaluate the impact of key variability sources, SET voltage (VSET), low resistance state, and high resistance state, on logic correctness and identify the dominant contributors to computational failure. Finally, we derive the device specifications and requirements to achieve error-free stateful LiM operations in the 1T1R RRAM arrays.","url":"https://doi.org/10.34734/fzj-2026-02724","authors":["Bende, Ankit","Singh, Simranjeet","Kumar Jha, Chandan","Storelli, Daniele","Nielinger, Dennis","Drechsler, Rolf","Dittmann, Regina","Menzel, Stephan","Merchant, Farhad","Rana, Vikas"],"tags":["621.3"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.34734/fzj-2026-02724","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20636211","name":"沙漏_一种基于电荷守恒的存算一体模拟计算架构","source":"datacite","abstract":"# AbstractThis paper proposes a novel computing architecture that fundamentally bypasses and breaks the bottleneck of the micro-scaling race of Moore's Law, which relies on transistor miniaturization. This architecture is named the **Hourglass Charge-Conservation Analog Computing Architecture**. Its core breakthrough lies in the integration of **computing units, registers and power storage units on a single chip**. At the hardware level, it is implemented through the deep integration of three functional matrices: relaxor ferroelectric/quantum paraelectric supercapacitor matrix, all-optical controlled switch matrix, and photovoltaic voltage sampling matrix, which together form a complete hardware foundation for computing-storage-energy integration. This architecture possesses inherently excellent parallel computing characteristics and unlimited future development potential. Its analog computing natively supports neuromorphic quantization and fuzzy information processing. Meanwhile, the hardware-intrinsic natural random number perturbations provide a crucial physical basis for computers to truly evolve towards emotional and human-like intelligence. Completely opposite to the linear growth model of Moore's Law, which relies on process iteration and technology stacking, the performance of the Hourglass architecture will naturally increase exponentially with breakthroughs in materials science and mathematical algorithms. The future application of superconducting materials will further enable a qualitative leap. Not only will the hardware computing power be improved synchronously, but the optimization space of supporting software algorithms will also expand exponentially. This preprint is an independent research result and has not received any institutional funding. All parameters are derived from currently published cutting-edge laboratory technologies, with no super-physical assumptions.Welcome peer exchanges and experimental verification. Contact information: hxy@yhdzele.cn; 52287423@qq.com --- ## KeywordsComputing-Storage-Energy Integration; Charge-Conservation Analog Computing; Relaxor Ferroelectric Supercapacitor; Quantum Paraelectric Supercapacitor; All-Optical Controlled Switch; Photovoltaic Voltage Sampling; Neuromorphic Computing; Parallel Analog Computing; Pulsed Power --- # 摘要本文提出的新型计算架构,**从底层原理上绕过并打破了摩尔定律依赖晶体管微缩的微观竞赛瓶颈**。 该架构命名为**沙漏电荷守恒模拟计算机架构**,其核心突破在于:**运算单元、寄存器与电源储能单元集成于同一芯片**。硬件层面通过三组功能矩阵的深度合一实现:弛豫铁电/量子顺电超级电容矩阵、全光控开关矩阵、光电压采样矩阵,三者协同构成完整的存算能一体化硬件基础。 该架构具备原生优良的并行运算特性与无限的未来发展可能性。其模拟量计算天然支持仿神经量化与模糊化信息处理,同时硬件本征的自然随机数扰动,为计算机真正走向具备情感与类人智能提供了关键的物理基础。 与摩尔定律依赖工艺迭代堆技术的线性增长模式完全相反,沙漏架构的性能天然会随着材料学、数学算法的突破呈指数级上升,未来超导材料的应用更将使其实现质的飞跃;不仅硬件算力会同步提升,配套软件算法的优化空间也将同步指数级放大。 本预印本为独立研究成果,未接受任何机构资助。所有参数均基于当前已发表的实验室前沿技术推导,无超物理假设。欢迎同行交流与实验验证,联系方式:hxy@yhdzele.cn;52287423@qq.com --- ## 关键词存算能一体化;电荷守恒模拟计算;弛豫铁电超级电容;量子顺电超级电容;全光控开关;光电压采样;类脑计算;并行模拟运算;脉冲功率","url":"https://doi.org/10.5281/zenodo.20636211","authors":["huang, xiaoyan"],"tags":["Computer Architecture","Materials Science","Electrical and Electronic Engineering","FOS: Electrical engineering, electronic engineering, information engineering","Artificial Intelligence"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20636211","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20636212","name":"沙漏_一种基于电荷守恒的存算一体模拟计算架构","source":"datacite","abstract":"# AbstractThis paper proposes a novel computing architecture that fundamentally bypasses and breaks the bottleneck of the micro-scaling race of Moore's Law, which relies on transistor miniaturization. This architecture is named the **Hourglass Charge-Conservation Analog Computing Architecture**. Its core breakthrough lies in the integration of **computing units, registers and power storage units on a single chip**. At the hardware level, it is implemented through the deep integration of three functional matrices: relaxor ferroelectric/quantum paraelectric supercapacitor matrix, all-optical controlled switch matrix, and photovoltaic voltage sampling matrix, which together form a complete hardware foundation for computing-storage-energy integration. This architecture possesses inherently excellent parallel computing characteristics and unlimited future development potential. Its analog computing natively supports neuromorphic quantization and fuzzy information processing. Meanwhile, the hardware-intrinsic natural random number perturbations provide a crucial physical basis for computers to truly evolve towards emotional and human-like intelligence. Completely opposite to the linear growth model of Moore's Law, which relies on process iteration and technology stacking, the performance of the Hourglass architecture will naturally increase exponentially with breakthroughs in materials science and mathematical algorithms. The future application of superconducting materials will further enable a qualitative leap. Not only will the hardware computing power be improved synchronously, but the optimization space of supporting software algorithms will also expand exponentially. This preprint is an independent research result and has not received any institutional funding. All parameters are derived from currently published cutting-edge laboratory technologies, with no super-physical assumptions.Welcome peer exchanges and experimental verification. Contact information: hxy@yhdzele.cn; 52287423@qq.com --- ## KeywordsComputing-Storage-Energy Integration; Charge-Conservation Analog Computing; Relaxor Ferroelectric Supercapacitor; Quantum Paraelectric Supercapacitor; All-Optical Controlled Switch; Photovoltaic Voltage Sampling; Neuromorphic Computing; Parallel Analog Computing; Pulsed Power --- # 摘要本文提出的新型计算架构,**从底层原理上绕过并打破了摩尔定律依赖晶体管微缩的微观竞赛瓶颈**。 该架构命名为**沙漏电荷守恒模拟计算机架构**,其核心突破在于:**运算单元、寄存器与电源储能单元集成于同一芯片**。硬件层面通过三组功能矩阵的深度合一实现:弛豫铁电/量子顺电超级电容矩阵、全光控开关矩阵、光电压采样矩阵,三者协同构成完整的存算能一体化硬件基础。 该架构具备原生优良的并行运算特性与无限的未来发展可能性。其模拟量计算天然支持仿神经量化与模糊化信息处理,同时硬件本征的自然随机数扰动,为计算机真正走向具备情感与类人智能提供了关键的物理基础。 与摩尔定律依赖工艺迭代堆技术的线性增长模式完全相反,沙漏架构的性能天然会随着材料学、数学算法的突破呈指数级上升,未来超导材料的应用更将使其实现质的飞跃;不仅硬件算力会同步提升,配套软件算法的优化空间也将同步指数级放大。 本预印本为独立研究成果,未接受任何机构资助。所有参数均基于当前已发表的实验室前沿技术推导,无超物理假设。欢迎同行交流与实验验证,联系方式:hxy@yhdzele.cn;52287423@qq.com --- ## 关键词存算能一体化;电荷守恒模拟计算;弛豫铁电超级电容;量子顺电超级电容;全光控开关;光电压采样;类脑计算;并行模拟运算;脉冲功率","url":"https://doi.org/10.5281/zenodo.20636212","authors":["huang, xiaoyan"],"tags":["Computer Architecture","Materials Science","Electrical and Electronic Engineering","FOS: Electrical engineering, electronic engineering, information engineering","Artificial Intelligence"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20636212","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2602.14736","name":"Coupled integrated photonic quantum memristors using a single photon source made of a colour center","source":"datacite","abstract":"Photonic quantum memristors provide a measurement-induced route to nonlinear and history-dependent quantum dynamics. Experimental demonstrations have so far focused on isolated devices or simple cascaded devices configurations. Here, we experimentally realize and characterize a network of two coupled photonic quantum memristors with crossed feedback, implemented on a silicon nitride photonic integrated circuit and fed by a room-temperature single-photon source based on a silicon-vacancy color center SiV$^-$ in a nanodiamond. Each memristor consists of an integrated Mach-Zehnder interferometer whose transfer function is adaptively updated by photon detection events on another memristor, thus generating novel non-Markovian input-output dynamics with an enhanced memristive behaviour compared to single devices. In particular, we report inter-memristor input-output hysteresis curves exhibiting larger form factors and displaying self-intersecting loops, respectively revealing marked bistability and self-intersecting hysteresis geometry. Furthermore, numerical simulations show how these features emerge from the interplay between memory depth and relative input phase, for both intra- and inter-memristor input-output relations. We experimentally test the performance of our system in the NARMA task. Our results establish coupled integrated photonic quantum memristors as scalable nonlinear building blocks and highlight their potential for implementing compact quantum neuromorphic and reservoir computing architectures.","url":"https://doi.org/10.48550/arxiv.2602.14736","authors":["Baldazzi, Alessio","Ancel, Roy Philip George Konnoth","Guaraldo, Sebastiano","Fattori, Ivan","Chen, Xuan","Akar, Ziad Abi","Deturche, Regis","Azzini, Stefano","Couteau, Christophe","Pavesi, Lorenzo"],"tags":["Quantum Physics (quant-ph)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2602.14736","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2606.11703","name":"Integrated magnonic neural circuits based on nonlinear wave neurons","source":"datacite","abstract":"Artificial intelligence is driving intense interest in alternative computing hardware capable of neural information processing beyond conventional charge-based electronics. Among emerging approaches, wave-based computing promises highly parallel and energy-efficient operation, but scalable physical neural hardware has remained elusive because wave systems generally lack cascadable nonlinear neurons with signal regeneration and phase-robust operation. Here we demonstrate integrated magnonic neural circuits based on nonlinear threshold neurons realized in nanoscale yttrium iron garnet waveguides. The neurons perform weighted summation of multiple spin-wave inputs, while a pump-controlled nonlinear activation defines continuously tunable firing thresholds. Owing to deeply nonlinear spin-wave dynamics, the activated neurons emit self-normalized outputs whose intensities are largely independent of the input amplitudes, while nonlinear phase self-adjustment suppresses sensitivity to the relative input phases, enabling deterministic neuron-to-neuron cascading without external signal restoration. We experimentally realize programmable threshold neurons, reconfigurable weighted classification and deterministic cascading between sequential neuronal stages, and further demonstrate reconfigurable physical pattern recognition in a seven-neuron integrated magnonic circuit through experimental classification of the binary letter patterns 'HUST'. These results establish nonlinear magnons as a scalable platform for integrated neural hardware and position nonlinear wave dynamics as a general paradigm for physical neuromorphic computing.","url":"https://doi.org/10.48550/arxiv.2606.11703","authors":["Guo, Mengying","Jing, Xudong","Davidkova, Kristýna","Verba, Roman","Zhou, Zhenyu","Guo, Xueyu","Dubs, Carsten","Gao, Chuan","Rao, Yiheng","Cai, Kaiming","Li, Jing","Pirro, Philipp","Chumak, Andrii V.","Wang, Qi"],"tags":["Materials Science (cond-mat.mtrl-sci)","Applied Physics (physics.app-ph)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.11703","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.17169/refubium-52446","name":"A New Threshold Switching Device With Tunable Negative Differential Resistance Based on ErMnO3 Polymorphs","source":"datacite","abstract":"Negative differential resistance (NDR) devices have emerged as promising building blocks for neuromorphic computing due to their inherent nonlinear and threshold-dependent electrical behavior. In particular, current-controlled NDR devices can exhibit abrupt switching, self-sustained oscillations, and volatility – key characteristics analogous to the spiking dynamics of biological neurons. The NDR is typically driven by thermal runaway effects, or by an insulator-to-metal transition, with materials such as VO2, NbOx, TaOx, and complex oxides like nikelates, cobaltites, or manganites. However, these systems often suffer from high forming and operating voltages, large Joule heating, limited device endurance, and no or little tunability. Here, we demonstrate a novel NDR device based on polycrystalline ErMnO3 comprising conducting orthorhombic and insulating hexagonal phases. Pt/ErMnO3/Pt memory devices exhibit unipolar, symmetric, forming-free threshold switching with a low threshold voltage of ~2.1 V, a memory window of 1.1 V, and endurance over 2 × 104 cycles. Joule-heating-enhanced Poole–Frenkel conduction occurs in the orthorhombic phase, while the insulating hexagonal phase prevents excessive heating and breakdown. Tunability is achieved by controlling the polymorph ratio and the orthorhombic phase conductivity. ErMnO3 polymorphs thus offer a versatile platform to engineer the electrical characteristics of NDR devices for low-power, reliable neuromorphic applications.","url":"https://doi.org/10.17169/refubium-52446","authors":["Wu, Rong","Maudet, Florian","Phan, Thanh Luan","Hamouda, Wassim","Schroedter, Richard","Demirkol, Ahmet Samil","Tetzlaff, Ronald","Deshpande, Veeresh","Dubourdieu, Catherine"],"tags":["ErMnO3","hexagonal","negative differential resistance","orthorhombic","polymorphs","threshold switching","Chemie und zugeordnete Wissenschaften"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.17169/refubium-52446","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20491182","name":"Adaptive-Frequency Resonate-and-Fire Neurons for Spectral Estimation of Streaming Radar Signals","source":"datacite","abstract":"This dataset contains the data to reproduce the results presented in the paper: \"Adaptive-Frequency Resonate-and-Fire Neurons for Spectral Estimation of Streaming Radar Signals\". The work introduces a dynamical system of adaptive-frequency neuron, specifically utilizing Adaptive-frequency Resonate-and-Fire (ARF) mechanics, designed for efficient, streaming FMCW radar signal estimation.","url":"https://doi.org/10.5281/zenodo.20491182","authors":["Chiavazza, Stefano","Yuan, Sen","Geilen, Marc","Fioranelli, Francesco","Corradi, Federico"],"tags":["neuromorphic computing","FMCW Radar"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20491182","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20491183","name":"Adaptive-Frequency Resonate-and-Fire Neurons for Spectral Estimation of Streaming Radar Signals","source":"datacite","abstract":"This dataset contains the data to reproduce the results presented in the paper: \"Adaptive-Frequency Resonate-and-Fire Neurons for Spectral Estimation of Streaming Radar Signals\". The work introduces a dynamical system of adaptive-frequency neuron, specifically utilizing Adaptive-frequency Resonate-and-Fire (ARF) mechanics, designed for efficient, streaming FMCW radar signal estimation.","url":"https://doi.org/10.5281/zenodo.20491183","authors":["Chiavazza, Stefano","Yuan, Sen","Geilen, Marc","Fioranelli, Francesco","Corradi, Federico"],"tags":["neuromorphic computing","FMCW Radar"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20491183","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.60893/figshare.aip.c.8494164","name":"Mimicking Neural Habituation Behavior with Pristine Leaf-based Memristors","source":"datacite","abstract":"Neuromorphic computing systems allow electronics to mimic the behavior of biological neurons and hold potential for high-efficiency computation needed for artificial intelligence. One class of electronic units capable of mimicking neural behavior is resistive memory devices, also known as memristors. While the most commonly studied memristors are solid-state in nature, there is a growing interest in the development of ion-rich fluidic memristors since they have a higher level of versatility to mimic biological neurons and synapses, which are themselves fluidic systems with mobile ions as neuroreceptors. Here, we present our work on elucidating the ion transport mechanism in leaf-based capacitive-coupled memristive devices and their use in mimicking habituation, a neural behavior where an organism's response to repeated applied stimulus diminishes. This work demonstrates the potential that leaf structures hold in serving as biomimetic architecture for the development of highly effective fluidic memristors for simulating neural behavior.","url":"https://doi.org/10.60893/figshare.aip.c.8494164","authors":["Savage, Andrew","Wilder, Samantha","Adhikari, Ramesh"],"tags":["Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.60893/figshare.aip.c.8494164","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20626393","name":"Threshold Dynamics of Silver Filament Formation and Rupture in Ag/SiO2/Au Memristors","source":"datacite","abstract":"Memristive devices with tunable volatility represent a promising platform for neuromorphic computing and adaptive electronics, enabling temporal information processing and gradual memory consolidation. Understanding the threshold dynamics governing conductive filament formation and rupture is critical for precise control of resistive switching behavior. Here, we systematically investigate Ag/SiO2/Au memristor devices to elucidate the physics of silver filament evolution, revealing the asymmetric interplay between drift-dominated formation and diffusion-dominated rupture processes. Quantitative analysis of filament formation dynamics yields an activation energy of 0.77 ± 0.12 eV for ion migration with field enhancement factor β = 0.21, demonstrating field-assisted thermally activated silver filament formation. Our experiments confirm that formation and rupture share a similar intrinsic energy landscape but operate under different driving forces: field-accelerated drift versus thermally-driven diffusion. Interestingly, detailed filament dynamics analysis reveals the existence of a critical metastable regime during both formation and rupture processes, where drift and diffusion forces balance, and conduction occurs via trap-assisted tunneling through nanoscale silver clusters. This metastable state exists at specific voltages where drift and diffusion forces achieve dynamic equilibrium, leading to intermediate conductance states between the stable low and high resistance states. Beyond this regime, the system exhibits deterministic behavior: at higher voltages, filament growth proceeds through sequential conduction regimes where Joule heating drives morphological changes in silver nanoclusters that concentrate the electric field and accelerate complete filament formation. At lower voltages, diffusion dominates and drives complete rupture of filaments back to nanoclusters. This enables voltage-tunable operation from stochastic to deterministic modes. Combined with quantitative activation energies and the drift-diffusion framework, our work provides fundamental insight into threshold switching physics and establishes design principles for engineering devices with controlled probabilistic or deterministic behavior for neuromorphic and stochastic computing applications.","url":"https://doi.org/10.5281/zenodo.20626393","authors":["Ranade, Varun","Veldhoen, William","Gibbins, Felix","Shradha, Sajal","Murray, Chris","Chunin, Igor","McCloskey, David","Shvets, Igor"],"tags":["Memristors","Resistive Switching","Volatile Memories","Memory devices","Neuromorphic computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20626393","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.26183/9eg1-yf05","name":"Towards faster machine olfaction: advances in high-speed sensing and processing","source":"datacite","abstract":"This thesis investigates the principles and methods for achieving high temporal resolution in odour sampling and processing for machine perception. Initially, a comprehensive review of fast olfaction mechanisms in insects and mammals is provided, highlighting the necessity of rapid sensing when exposed to the dynamics of turbulent odour plumes. The discussion extends to artificial olfaction technologies, emphasising current advancements in electronic nose (e-nose) systems and their applications. Initial evaluations of existing datasets and algorithms revealed significant limitations in a widely used gas sensor dataset, particularly due to a non-randomised measurement protocol and severe sensor drift. These issues rendered the dataset unusable for classification benchmarks. Multiple studies that are impacted by this were identified, where the example of a prominent neuromorphic few-shot odour-learning algorithm study was investigated further. In response, a set of best practices for future gas sensor data collection campaigns was established to ensure data reliability and reproducibility. Several data collection campaigns were conducted using a custom-built e-nose system, which was based on MOx gas sensors and fast peripheral electronic devices. A novel approach to data feature acquisition for odour classification was proposed, involving rapid temperature cycling of the gas sensors. This method enabled the recording of two datasets capturing diverse indoor and outdoor olfactory scenes, which were effectively distinguished using the acquired features. An extensive laboratory campaign followed, in which the e-nose system was evaluated against a benchmark previously used to explore the temporal odour discrimination capabilities of mammals. The results demonstrated that the e-nose could distinguish correlated odour pulse trains from anti-correlated ones at modulation frequencies up to 40 Hz and determine frequencies up to 60 Hz, surpassing mammalian capabilities. Additionally, the system achieved odour classification at pulse widths as short as 10 milliseconds when employing 50 millisecond duty cycles for sensor temperature modulation, setting a new precedent in artificial olfaction. Further, for efficient processing of olfactory signals, neuromorphic computing principles were explored. The potential advantages of asynchronous sampling and data processing methods were discussed in the context of the physical characteristics of turbulent odour plumes. Various event generation and processing algorithms were critically reviewed, and discussed in the context of olfactory signals. An example study is provided, in which asynchronous event sampling is applied to heater-cycled MOx sensor e-nose data, and the effectiveness of different event encoding schemes was assessed. Finally, the thesis discusses the results by putting them in perspective with future research directions.","url":"https://doi.org/10.26183/9eg1-yf05","authors":["Dennler, Nik"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.26183/9eg1-yf05","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2605.09595","name":"Neuromorphic Reinforcement Learning for Quadruped Locomotion Control on Uneven Terrain","source":"datacite","abstract":"Reinforcement learning (RL) has enabled robust quadruped locomotion over complex terrain, but most learned controllers are trained offline with backpropagation in massively parallel simulation and deployed as fixed policies, limiting adaptation to terrain variation, payload changes, actuator wear, and other real-world conditions under onboard power constraints. Local learning provides a potential path toward energy-aware on-robot adaptation by replacing global backpropagation graphs with updates driven by local neural states, making the learning rule more compatible with neuromorphic and in-memory computing substrates. This work proposes an equilibrium-propagation (EP)-based proximal policy optimization (PPO) framework for uneven-terrain quadruped locomotion. The controller combines a bio-inspired central pattern generator (CPG) policy with a residual postural adjustment policy, while replacing conventional backpropagation-trained policy and value networks with EP-enabled local learning. To train stochastic continuous-control policies with EP, we derive an EP-compatible PPO output-nudging signal and introduce a two-sided ratio clipping mechanism that stabilizes policy updates during relaxation. Experiments on a 12-DoF A1 quadruped show that the proposed controller achieves stable policy convergence in a two-stage uneven terrain locomotion task. Its locomotion performance is comparable to a backpropagation-trained PPO baseline in success rate, velocity tracking, actuator power, and body stability, while improving GPU memory efficiency by 4.3\\(\\times\\) compared with backpropagation through time (BPTT). These results suggest that local equilibrium-based learning can support high-dimensional embodied locomotion and provide an algorithmic foundation for low-power on-robot adaptation and fine-tuning.","url":"https://doi.org/10.48550/arxiv.2605.09595","authors":["Han, Zhuangyu","Sengupta, Abhronil"],"tags":["Neural and Evolutionary Computing (cs.NE)","Robotics (cs.RO)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2605.09595","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2507.08332","name":"Electrothermally Modulated Nanophotonic Waveguide-integrated Ring Resonator","source":"datacite","abstract":"Reconfigurable integrated chips of photonic components and networks are envisaged to play a key role in realizing highly efficient integrated photonic information processing. Electrothermally modulated optical effect (ETMOE) is a powerful thermo-optic tuning mechanism for silicon photonic devices, enabling precise optical control via localized Joule heating. We present a rigorous and three-dimensional electronic-photonic co-integrated approach with the nonlinear numerical coupling of temperature and wavelength-dependent material properties to comprehensively model ETMOE in silicon waveguides and resonators. A platinum-based symmetric heater is optimized using advanced true 3D numerical simulations, achieving efficient ETMOE-based tuning while mitigating asymmetric heat distribution. In addition to a complete design and analysis of the fully integrated three-dimensional switch, we also evaluate single-mode waveguide cutoff, heater-to-waveguide separation, heater dimensions, and thermal dissipation, providing a framework for ETMOE-based optimization. The findings contribute to energy-efficient, programmable photonic systems for neuromorphic computing, optical interconnects, and reconfigurable photonic networks.","url":"https://doi.org/10.48550/arxiv.2507.08332","authors":["Gupta, Sujal","Xavier, Jolly"],"tags":["Optics (physics.optics)","Applied Physics (physics.app-ph)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2507.08332","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2606.10008","name":"Spiking Neural Network inference on FPGAs with hls4ml","source":"datacite","abstract":"Spiking Neural Networks (SNNs) provide a naturally temporal machine-learning framework. Their neurons maintain an internal state and propagate information through discrete spikes, enabling low-latency temporal inference. Although SNNs are often associated with asynchronous neuromorphic processors, many scientific real-time inference systems rely on conventional synchronous field-programmable gate arrays (FPGAs) and high-level synthesis (HLS) workflows. In this paper we present an extension of hls4ml that enables clock-driven deployment of SNNs trained in pytorch onto FPGA firmware. We demonstrate the workflow using a dense quantised SNN trained on the Heidelberg Spiking Digits dataset where it achieves inference latencies of approximately $34μ$s. We validate the generated design through software reference comparisons, HLS C simulation, HLS synthesis, export, and Vivado synthesis reports. This work opens up the hls4ml toolkit to neuromorphic computing, allowing streamlined optimisation, synthesis, and deployment of SNN models for real-time inference.","url":"https://doi.org/10.48550/arxiv.2606.10008","authors":["Dillon, Barry M."],"tags":["Neural and Evolutionary Computing (cs.NE)","Machine Learning (cs.LG)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.10008","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.26183/pn9n-3t62","name":"Hardware architectures for event-driven feature extraction algorithms","source":"datacite","abstract":"Over the last decade, Neuromorphic Engineering (NE) has evolved into a prominent scientific discipline, advancing biologically inspired sensors, algorithms, hardware architectures, and processing techniques that emulate key operational principles of the human brain. Among these, the most notable innovation is the silicon retinas, commonly known as Dynamic Vision Sensor (DVS), which produce a stream of events in response to changes in luminosity in the light. Conventional frame-based processing techniques pose limitations in handling these streams of events, leading to the emergence of Event-Based (EB) processing techniques designed to manage the asynchronous stream of events generated by DVS sensors. In addition, the scientific community has witnessed a tremendous growth in EB vision solutions, where DVS have been deployed across diverse domains, including recognition, tracking, motion estimation, space do- main awareness, and space imaging. The first part of the thesis proposes a reconfigurable hardware accelerator implemented on the Field Programmable Gate Array (FPGA) for the FEAST network. The novelty of the design lies in splitting the FEAST learning rule into two different sets of tasks and executing them independently in a time-multiplexed fashion, using a minimum number of hardware resources. The proposed hardware architecture, operated at 200 megahertz (MHz) clock frequency, can process 183⇥103 events/sec in training mode and 196⇥103 events/sec in inference mode. The second part of the thesis examines the FPGA implementation of a reconfigurable hardware accelerator designed to support flexible Event Context (E C) computation of the FEAST algorithm. The architecture introduces a novel 1-D computing core, which operates as a broadcast structure utilising a loop unrolling mechanism that supports the T S and FEAST learning rule execution with minimum hardware utilisation. Additionally, the proposed flexible hardware offers configurability across a wide range of E C sizes, with radii ranging from 1 to 7. Compared to the first FEAST implementation, this architecture processes 3.95⇥ events. The final part of the thesis explores the design of the first-ever multi-layer FEAST network and its FPGA implementation. The novelty of the design lies in the introduction of a 1-D computing core, which interleaves the FEAST layer computations without incurring additional hardware overhead. The proposed architecture achieves an event processing rate of 247⇥103 events/sec while the FEAST layers are configured with an E C size of 15 ⇥ 15.","url":"https://doi.org/10.26183/pn9n-3t62","authors":["Jose, Philip"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.26183/pn9n-3t62","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20202223","name":"ExSpike: A General Full-Event Neuromorphic Architecture for Exploiting Irregular Sparsity with Event Compression","source":"datacite","abstract":"Spiking neural networks (SNNs) promise energy-efficient computing due to their sparse spatio-temporal activity. However, effectively translating such irregular sparsity into practical performance and energy gains remains challenging, as full-event computing architectures are still underexplored. This paper proposes ExSpike, a general full-event neuromorphic architecture that fully exploits irregular sparsity in SNNs. To realize pure event-driven execution, we first propose a set of dataflow optimizations to ensure that the inputs to each SNN layer remain spike-based, thereby enabling full-event execution throughout the network. We then design a hardware-efficient full-event architecture, named ExSpike, which supports the optimized pure event-driven dataflow and an additional Attention Core for spike-driven self-attention. To further improve computing efficiency, we introduce adjacent-position event compression to reduce redundant accumulations across spatially adjacent spike sequences. ExSpike is implemented on an AMD Xilinx Virtex-7 FPGA and evaluated on both classification and segmentation workloads. Experimental results show that ExSpike achieves high normalized energy efficiency across diverse SNN models while maintaining competitive accuracy, delivering up to 479.15 GOPS, 281.85 GOPS/W, and 0.80 GOPS/W/PE. In particular, ExSpike achieves up to 10x higher normalized energy efficiency than prior FPGA-based accelerators.","url":"https://doi.org/10.5281/zenodo.20202223","authors":["Chen, Yuehai","Merchant, Farhad"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20202223","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20600138","name":"ExSpike: A General Full-Event Neuromorphic Architecture for Exploiting Irregular Sparsity with Event Compression","source":"datacite","abstract":"Spiking neural networks (SNNs) promise energy-efficient computing due to their sparse spatio-temporal activity. However, effectively translating such irregular sparsity into practical performance and energy gains remains challenging, as full-event computing architectures are still underexplored. This paper proposes ExSpike, a general full-event neuromorphic architecture that fully exploits irregular sparsity in SNNs. To realize pure event-driven execution, we first propose a set of dataflow optimizations to ensure that the inputs to each SNN layer remain spike-based, thereby enabling full-event execution throughout the network. We then design a hardware-efficient full-event architecture, named ExSpike, which supports the optimized pure event-driven dataflow and an additional Attention Core for spike-driven self-attention. To further improve computing efficiency, we introduce adjacent-position event compression to reduce redundant accumulations across spatially adjacent spike sequences. ExSpike is implemented on an AMD Xilinx Virtex-7 FPGA and evaluated on both classification and segmentation workloads. Experimental results show that ExSpike achieves high normalized energy efficiency across diverse SNN models while maintaining competitive accuracy, delivering up to 479.15 GOPS, 281.85 GOPS/W, and 0.80 GOPS/W/PE. In particular, ExSpike achieves up to 10x higher normalized energy efficiency than prior FPGA-based accelerators.","url":"https://doi.org/10.5281/zenodo.20600138","authors":["Chen, Yuehai","Merchant, Farhad"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20600138","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.60893/figshare.apl.c.8492772","name":"<strong>Electrically controlled tuning the nonlinearity and asymmetry of synaptic behaviors in a magnetoelectrically coupled memristor for high-performance neuromorphic computing</strong>","source":"datacite","abstract":"High-performance artificial synaptic devices capable of emulating biological synaptic functions are crucial for developing energy-efficient neuromorphic computing systems. Memristors, whose conductance can be modulated to mimic synaptic plasticity, offer a promising platform for such applications. In this work, we present an electric-field-controlled memristor based on an FeGaB/PMN-PT multiferroic heterostructure, in which synaptic weights are continuously tuned by applied voltage pulses. The device was fabricated via magnetron sputtering and exhibits nonvolatile, multi-level resistance switching under pulsed electric field modulation, achieving 83 distinct and continuously adjustable resistance states. Key synaptic functionalities including long-term potentiation/depression (LTP/LTD), paired-pulse facilitation (PPF), and spike-timing-dependent plasticity (STDP) are successfully demonstrated. When integrated into a recurrent neural network, the system achieves a recognition accuracy of 92.4% in a benchmark task. By quantifying the nonlinearity (NL) and asymmetry (AS) of weight updates and directly linking them to accuracy performance, we further reveal that device-level NL critically governs system-level computational accuracy. This insight provides a clear optimization pathway for future artificial spintronic synapses, underscoring their potential for high-speed, nonvolatile, and adaptive neuromorphic hardware.","url":"https://doi.org/10.60893/figshare.apl.c.8492772","authors":["Song, Guangxiao","Zhou, Hao-Miao","Yu, Guoliang","Zhu, Haibin","Huang, Ankang","Ouyang, Hui","Zhu, Mingmin","Wang, Jiawei","Jing, Xufeng","Wang, Xin","Wang, Wei","Qiu, Yang"],"tags":["Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.60893/figshare.apl.c.8492772","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2606.08584","name":"Convolutional Sparse Coding via the Locally Competitive Algorithm on Loihi 2","source":"datacite","abstract":"Sparse coding provides a principled framework for signal representation by expressing an input as a linear combination of only a small number of basis functions. The Locally Competitive Algorithm (LCA) is particularly attractive in the context of neuromorphic computing because its dynamics, leaky integration, thresholding, and lateral inhibition map naturally to neuromorphic hardware. While prior work has studied non-convolutional LCA on Loihi 2, the convolutional setting is of particular interest because it introduces spatial structure, weight sharing, overlapping receptive fields, and scaling behavior that are more representative of practical sparse inference workloads. In this work, we present a Loihi 2 implementation of convolutional sparse coding via the LCA and evaluate it against a conventional GPU baseline on the same inference problems. The implementation follows a one-layer recurrent LCA formulation and extends it to convolutional feature maps with local inhibitory kernels derived from pairwise filter interactions. To the best of our knowledge, this is the first implementation and benchmark of convolutional LCA on Loihi 2. Our goal is not only to demonstrate feasibility, but also to clarify in which operating regimes convolutional sparse inference becomes attractive on neuromorphic hardware. The resulting study positions convolutional LCA as a useful benchmark for structured sparse inference on emerging neuromorphic systems.","url":"https://doi.org/10.48550/arxiv.2606.08584","authors":["Kasenbacher, Geoffrey","Ruepp, Daniel","Ecke, Gerrit A."],"tags":["Machine Learning (cs.LG)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.08584","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2606.08515","name":"Unifying von-Neumann HPC and Neuromorphic Acceleration via the EBRAINS Research Infrastructure: A Framework for High-Performance Workflows","source":"datacite","abstract":"Modern scientific workflows increasingly span diverse computing architectures, yet executing a single computational model across disparate systems often forces researchers to maintain fragmented, site-specific pipelines. In this paper, we address this challenge within the domain of computational neuroscience by presenting a unified, cloud-based workflow orchestrated via EBRAINS JupyterLab. This workflow enables users to transparently execute spiking neural networks on both von-Neumann supercomputers and neuromorphic hardware. Using a single federated identity, the system dispatches jobs to HPC sites (JUSUF, Galileo100) via PyUNICORE and to the SpiNNaker-1 neuromorphic system via the Neuromorphic Computing Platform Interface. To guarantee cross-site reproducibility and mitigate software version drift, we utilize a zero-installation execution mode that dynamically pulls PMIx-aware Apptainer containers to HPC compute nodes. Furthermore, we demonstrate genuine model-level portability using the NESTML domain-specific language, allowing custom neuron models to be written once and automatically compiled for either the NEST (C++) or sPyNNaker backends. Validated with a balanced random network case study, this work illustrates a practical, end-to-end path for hardware-agnostic workflows while highlighting the critical role of containerization and domain-specific languages in achieving true cross-platform reproducibility.","url":"https://doi.org/10.48550/arxiv.2606.08515","authors":["Singh, Krishna Kant","Linssen, Charl","Müller, Eric","Mathioulaki, Eleni","Klijn, Wouter","Oden, Lena"],"tags":["Distributed, Parallel, and Cluster Computing (cs.DC)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.08515","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20590583","name":"ARIA: A Zero-Hallucination Neuro-Symbolic Architecture for Persistent Memory, Sparse Graph Reasoning, and Autonomous Self-Evolution","source":"datacite","abstract":"ARIA is a deterministic neuro-symbolic cognitive architecture designed to integrate persistent memory, autonomous goal formation, causal reasoning, self-modifying cognitive structures, and large-scale knowledge representation. Unlike conventional transformer-based systems, ARIA combines symbolic knowledge graphs, dynamic concept networks, neuromorphic processing components, autonomous learning mechanisms, and long-term memory persistence into a unified cognitive framework. This publication describes the architecture, design principles, implementation details, experimental results, and future development roadmap of the ARIA system. Keywords: AGI, Neuro-Symbolic AI, Cognitive Architecture, Persistent Memory, Autonomous Agents, Artificial General Intelligence, Causal Reasoning, Knowledge Graphs, AtomSpace, Cognitive Systems.","url":"https://doi.org/10.5281/zenodo.20590583","authors":["Counselor Service Holding LTD","Vettorato, Nicola"],"tags":["Artificial General Intelligence AGI Neuro-Symbolic AI Cognitive Architecture Persistent Memory Autonomous Goal Formation Knowledge Graphs AtomSpace Causal Reasoning Artificial Intelligence Machine Learning Neuromorphic Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20590583","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20590584","name":"ARIA: A Zero-Hallucination Neuro-Symbolic Architecture for Persistent Memory, Sparse Graph Reasoning, and Autonomous Self-Evolution","source":"datacite","abstract":"ARIA is a deterministic neuro-symbolic cognitive architecture designed to integrate persistent memory, autonomous goal formation, causal reasoning, self-modifying cognitive structures, and large-scale knowledge representation. Unlike conventional transformer-based systems, ARIA combines symbolic knowledge graphs, dynamic concept networks, neuromorphic processing components, autonomous learning mechanisms, and long-term memory persistence into a unified cognitive framework. This publication describes the architecture, design principles, implementation details, experimental results, and future development roadmap of the ARIA system. Keywords: AGI, Neuro-Symbolic AI, Cognitive Architecture, Persistent Memory, Autonomous Agents, Artificial General Intelligence, Causal Reasoning, Knowledge Graphs, AtomSpace, Cognitive Systems.","url":"https://doi.org/10.5281/zenodo.20590584","authors":["Counselor Service Holding LTD","Vettorato, Nicola"],"tags":["Artificial General Intelligence AGI Neuro-Symbolic AI Cognitive Architecture Persistent Memory Autonomous Goal Formation Knowledge Graphs AtomSpace Causal Reasoning Artificial Intelligence Machine Learning Neuromorphic Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20590584","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20379328","name":"Jigyāsā: A Self-Taught Thinking Model Trained on Autonomously Generated Knowledge via SNN-Modulated Curiosity Loops","source":"datacite","abstract":"Jigyāsā is a language model trained entirely on knowledge it generated itself — starting from a single seed question about entropy and time, the system autonomously explored 500 knowledge nodes across nine domains, including physics, consciousness, linguistics, and mathematics, guided by a small Spiking Neural Network (SNN) that directed how deeply to investigate each concept. No human authored any training pair; all 4,939 question-answer examples were produced through this curiosity-driven traversal, then used to fine-tune Qwen2.5-7B-Instruct via QLoRA. The resulting model achieves a perfect score of 30/30 (100%) on a 10-question evaluation suite spanning identity anchoring, cross-domain reasoning, hard safety stops, adversarial identity resistance, and spontaneous question generation. This work also introduces the Thinking Model paradigm as a formal distinction from conventional chatbot architectures, and proposes the Depth Arc — a 5-message conversational framework designed to measure whether a model genuinely deepens its reasoning across a dialogue rather than simply responding to surface prompts. Jigyāsā is part of the Jigyāsā Series from Nexus Learning Labs, Bengaluru, India — a line of self-taught thinking models built on the principle that autonomous knowledge generation, without human annotation or distillation, can produce robust and epistemically coherent reasoning systems. Series: Part of the Jigyāsā Series — self-taught thinking models. Autonomous knowledge generation without human annotation or distillation. Links: GitHub Repository (private — to request access: email research@nexuslearninglabs.in with subject Code Access Request — Jigyasa and your research context) | Full Series Index — venky2099.github.io Nexus Learning Labs, Bengaluru · UDYAM-KR-02-0122422 · BHASKAR IN-0526-9452JSORCID: 0000-0002-3315-7907 · VAIRAGYA_DECAY_RATE = 0.002315 (embedded in all canonical hyperparameters)Canary: MayaNexusVS2026NLL_Bengaluru_Narasimha","url":"https://doi.org/10.5281/zenodo.20379328","authors":["Swaminathan, Venkatesh"],"tags":["neuromorphic computing","spiking neural networks","continual learning","nociceptive metaplasticity","Bhaya Quiescence Law","Buddhi S-curve","affective computing","bioelectric computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20379328","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20584324","name":"Wave_Unified_Spectral_Technologies.docx","source":"datacite","abstract":"This paper provides a concise conceptual survey of the Spectral Computing paradigm and its natural extensions into the physical sciences. At its centre stands the spectral computer — an architecture in which information is encoded, routed and processed as structured wave patterns rather than discrete voltage levels. The paper then surveys five families of adjacent technology that share the same wave-theoretic foundations: spectral holography, spectral X-ray imaging, spectral laser systems, spectral information transfer, and wave-driven medicine. A sixth thread, the sound–spectrum bridge, is given special emphasis, as acoustic waves and electromagnetic spectra obey formally identical mathematical structures and together point toward a fully wave-unified system of both computation and therapy. The paper is intended as an accessible introduction for readers approaching the Spectral Computing Programme for the first time.","url":"https://doi.org/10.5281/zenodo.20584324","authors":["Desmond, Timothy"],"tags":["Science, Waveform, Quantum,Physics, Holography, Laser, X-Ray, Unified, Information,Medical,Advance, Spectral Computing, Spectral Instruction Set Architecture, S-ISA, Phase-Based Computation, Coherent Computing, Post-Binary Architecture, Neuromorphic Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20584324","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20584325","name":"Wave_Unified_Spectral_Technologies.docx","source":"datacite","abstract":"This paper provides a concise conceptual survey of the Spectral Computing paradigm and its natural extensions into the physical sciences. At its centre stands the spectral computer — an architecture in which information is encoded, routed and processed as structured wave patterns rather than discrete voltage levels. The paper then surveys five families of adjacent technology that share the same wave-theoretic foundations: spectral holography, spectral X-ray imaging, spectral laser systems, spectral information transfer, and wave-driven medicine. A sixth thread, the sound–spectrum bridge, is given special emphasis, as acoustic waves and electromagnetic spectra obey formally identical mathematical structures and together point toward a fully wave-unified system of both computation and therapy. The paper is intended as an accessible introduction for readers approaching the Spectral Computing Programme for the first time.","url":"https://doi.org/10.5281/zenodo.20584325","authors":["Desmond, Timothy"],"tags":["Science, Waveform, Quantum,Physics, Holography, Laser, X-Ray, Unified, Information,Medical,Advance, Spectral Computing, Spectral Instruction Set Architecture, S-ISA, Phase-Based Computation, Coherent Computing, Post-Binary Architecture, Neuromorphic Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20584325","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20581146","name":"Spectral_Computing_Product_Pitch_v2.docx","source":"datacite","abstract":"Spectral Computing is a new computing architecture built on a fundamentally different mathematical substrate from the binary logic that has powered electronics since the 1940s. It does not require exotic materials, new physics, or untested engineering. Approximately 90% of the technology required to implement Spectral Computing exists today in commercially available hardware: phase-locked loop circuits, digital signal processors, Fourier transform accelerators, neuromorphic chips, and coherent optical computing components are all in production at scale. The remaining 10% — the coherent operator primitives that form the core of the Spectral Instruction Set Architecture (S-ISA) — rests on well-established physics. The theoretical foundation is solid, the implementation pathway is clear, and the engineering challenges are tractable within current semiconductor fabrication capabilities. What Spectral Computing provides is the unifying architectural framework that ties these existing technologies together under a coherent mathematical system — one that is natively suited to the computational demands of artificial intelligence, quantum computing interfaces, real-time signal processing, robotics, and medical instrumentation that classical binary architecture increasingly struggles to meet.","url":"https://doi.org/10.5281/zenodo.20581146","authors":["Desmond, Timothy"],"tags":["Computing, quantum, classical, research Spectral Computing, Spectral Instruction Set Architecture, S-ISA, Phase-Based Computation, Coherent Computing, Post-Binary Architecture, Neuromorphic Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20581146","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20581147","name":"Spectral_Computing_Product_Pitch_v2.docx","source":"datacite","abstract":"Spectral Computing is a new computing architecture built on a fundamentally different mathematical substrate from the binary logic that has powered electronics since the 1940s. It does not require exotic materials, new physics, or untested engineering. Approximately 90% of the technology required to implement Spectral Computing exists today in commercially available hardware: phase-locked loop circuits, digital signal processors, Fourier transform accelerators, neuromorphic chips, and coherent optical computing components are all in production at scale. The remaining 10% — the coherent operator primitives that form the core of the Spectral Instruction Set Architecture (S-ISA) — rests on well-established physics. The theoretical foundation is solid, the implementation pathway is clear, and the engineering challenges are tractable within current semiconductor fabrication capabilities. What Spectral Computing provides is the unifying architectural framework that ties these existing technologies together under a coherent mathematical system — one that is natively suited to the computational demands of artificial intelligence, quantum computing interfaces, real-time signal processing, robotics, and medical instrumentation that classical binary architecture increasingly struggles to meet.","url":"https://doi.org/10.5281/zenodo.20581147","authors":["Desmond, Timothy"],"tags":["Computing, quantum, classical, research Spectral Computing, Spectral Instruction Set Architecture, S-ISA, Phase-Based Computation, Coherent Computing, Post-Binary Architecture, Neuromorphic Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20581147","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20576755","name":"Variational-Spectral-GKSL Closed Dynamical Theory of a Quantum-Information Field","source":"datacite","abstract":"Version:v0.1-formalization Author:Vitaliy Bazarov(VIT-BAZ) ORCID:0009-0007-9967-5807 Status:Preprint / theoretical specification / formal research archive Description:This archive contains the current formalization package for the UAU–ESVG–SAAU–Σ* framework: a layered variational, spectral, categorical, operator-algebraic, and hardware-realizable theory of dissipative adaptive dynamical systems. The package includes a unified formalization synthesis, contradiction report, working mathematical instrument, categorical omega-closure formalization, GKSL operator-field formalization, and physical Sigma-star hardware/runtime layer. The framework should be read as a conditional mathematical and engineering specification. Claims of reconstruction, universality, and physical realization are valid only under the explicit assumptions stated in the documents: well-posed dissipative dynamics, admissible Koopman/GKSL spectral resolution, separating observables, finite effective sector or Σ*_ε approximation, and controlled physical implementation. Scientific Status Statement:This release is a theoretical and formal specification package. It contains conditional mathematical frameworks, proof programs, hardware abstraction layers, and contradiction audits. It is not a claim of completed silicon validation, medical validation, universal physical implementation, or experimentally verified cognition theory. Core Technical Statement:The central structure of the framework is: E(U) → b = -G∇E → Φ_t → K_t / L_K → Σ / Σ*_ε → Σ_agent → GKSL / τ_t / A* → EEG/FPGA/SAAU runtime → admissible categorical closure. Exact finite Σ* reconstruction requires finite Koopman closure and separating observables. In general implementations, Σ*_ε should be used as an approximate effective spectral kernel. Contents:1. UAU_Full_Formalization_Synthesis.md Unified synthesis of the current UAU–ESVG–SAAU–Σ* formalization corpus. 2. UAU_Formalization_Contradictions_Report.md Contradictions, risks, overclaims, and repair rules found in the source corpus. 3. UAU_Sigma_Working_Math_Instrument.md Working mathematical instrument and research protocol for future development. 4. Categorical_Omega_Closure_Formalization.md Formal categorical omega-closure and spectral reconstruction theorem. 5. GKSL_Operator_Field_Formalization.md Operator-algebraic GKSL extension of the framework. 6. Sigma_Physical_Hardware_Formalization.md Formal physical Sigma-star hardware/runtime layer. Keywords:Koopman operator theory; Wasserstein gradient flow; spectral reconstruction; neuromorphic computing; FPGA spectral runtime; GKSL dynamics; Lindblad generator; category theory; dissipative dynamical systems; operator algebra; adaptive systems; Sigma-star; UAU; SAAU; ESVG. Recommended Citation:Bazarov, V. (2026). UAU–ESVG–SAAU–Σ*: Variational–Spectral–Categorical Formalization Package (v0.1-formalization). Zenodo. DOI: [insert DOI after publication] Release Notes:- First public formalization package.- Includes unified synthesis and contradiction audit.- Separates state vector field b = -G∇E from Koopman generator L_K.- Replaces unconditional exact Σ* claims with Σ*_ε where finite Koopman closure is not proved.- Adds formal GKSL/operator-algebraic layer under CP semigroup and faithful invariant-state assumptions.- Adds physical Sigma-star hardware layer with domain, semigroup, spectral, noise, retention, and approximate universality assumptions.- Hardware layer is formal/architectural and not yet HDL-validated.- EEG/FPGA/SAAU layers are treated as measurable or implementable finite effective spectral sectors, not as proofs of consciousness, emergent gravity, or arbitrary universal physical computation. Bazarov, Vitaliy. (VIT-BAZ) (2026). UAU–ESVG–SAAU–Σ*: Variational–Spectral–Categorical Formalization Package (v0.1-formalization). Zenodo. https://doi.org/10.5281/zenodo.20576756","url":"https://doi.org/10.5281/zenodo.20576755","authors":["Bazarov, Vitaly"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20576755","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20576756","name":"Variational-Spectral-GKSL Closed Dynamical Theory of a Quantum-Information Field","source":"datacite","abstract":"Version:v0.1-formalization Author:Vitaliy Bazarov(VIT-BAZ) ORCID:0009-0007-9967-5807 Status:Preprint / theoretical specification / formal research archive Description:This archive contains the current formalization package for the UAU–ESVG–SAAU–Σ* framework: a layered variational, spectral, categorical, operator-algebraic, and hardware-realizable theory of dissipative adaptive dynamical systems. The package includes a unified formalization synthesis, contradiction report, working mathematical instrument, categorical omega-closure formalization, GKSL operator-field formalization, and physical Sigma-star hardware/runtime layer. The framework should be read as a conditional mathematical and engineering specification. Claims of reconstruction, universality, and physical realization are valid only under the explicit assumptions stated in the documents: well-posed dissipative dynamics, admissible Koopman/GKSL spectral resolution, separating observables, finite effective sector or Σ*_ε approximation, and controlled physical implementation. Scientific Status Statement:This release is a theoretical and formal specification package. It contains conditional mathematical frameworks, proof programs, hardware abstraction layers, and contradiction audits. It is not a claim of completed silicon validation, medical validation, universal physical implementation, or experimentally verified cognition theory. Core Technical Statement:The central structure of the framework is: E(U) → b = -G∇E → Φ_t → K_t / L_K → Σ / Σ*_ε → Σ_agent → GKSL / τ_t / A* → EEG/FPGA/SAAU runtime → admissible categorical closure. Exact finite Σ* reconstruction requires finite Koopman closure and separating observables. In general implementations, Σ*_ε should be used as an approximate effective spectral kernel. Contents:1. UAU_Full_Formalization_Synthesis.md Unified synthesis of the current UAU–ESVG–SAAU–Σ* formalization corpus. 2. UAU_Formalization_Contradictions_Report.md Contradictions, risks, overclaims, and repair rules found in the source corpus. 3. UAU_Sigma_Working_Math_Instrument.md Working mathematical instrument and research protocol for future development. 4. Categorical_Omega_Closure_Formalization.md Formal categorical omega-closure and spectral reconstruction theorem. 5. GKSL_Operator_Field_Formalization.md Operator-algebraic GKSL extension of the framework. 6. Sigma_Physical_Hardware_Formalization.md Formal physical Sigma-star hardware/runtime layer. Keywords:Koopman operator theory; Wasserstein gradient flow; spectral reconstruction; neuromorphic computing; FPGA spectral runtime; GKSL dynamics; Lindblad generator; category theory; dissipative dynamical systems; operator algebra; adaptive systems; Sigma-star; UAU; SAAU; ESVG. Recommended Citation:Bazarov, V. (2026). UAU–ESVG–SAAU–Σ*: Variational–Spectral–Categorical Formalization Package (v0.1-formalization). Zenodo. DOI: [insert DOI after publication] Release Notes:- First public formalization package.- Includes unified synthesis and contradiction audit.- Separates state vector field b = -G∇E from Koopman generator L_K.- Replaces unconditional exact Σ* claims with Σ*_ε where finite Koopman closure is not proved.- Adds formal GKSL/operator-algebraic layer under CP semigroup and faithful invariant-state assumptions.- Adds physical Sigma-star hardware layer with domain, semigroup, spectral, noise, retention, and approximate universality assumptions.- Hardware layer is formal/architectural and not yet HDL-validated.- EEG/FPGA/SAAU layers are treated as measurable or implementable finite effective spectral sectors, not as proofs of consciousness, emergent gravity, or arbitrary universal physical computation. Bazarov, Vitaliy. (VIT-BAZ) (2026). UAU–ESVG–SAAU–Σ*: Variational–Spectral–Categorical Formalization Package (v0.1-formalization). Zenodo. https://doi.org/10.5281/zenodo.20576756","url":"https://doi.org/10.5281/zenodo.20576756","authors":["Bazarov, Vitaly"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20576756","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.24406/publica-5297","name":"Gate controlled EDL-based capacitor-diodes (G-CAPode) for switchable signal filters with logic gate functionality","source":"datacite","abstract":"This work explores a novel application of the G-CAPode - a previously developed, 3D-printed gate-controlled electrochemical capacitor-diode - by demonstrating its ability to perform logic operations in ionic circuits. The G-CAPode integrates diode-like rectification, voltage-controlled switching via a gate electrode, and dynamically tunable capacitance within a single architecture. While prior studies demonstrated G-CAPodes to function as tunable capacitors - a varactor - in high-pass filters, this study extends its use toward logic operations. Specifically, frequency-dependent OR and AND logic behaviors are realized by connecting two G-CAPodes in parallel and series, respectively. In these configurations, logic output is determined by the impedance state of each device, which is dynamically controlled via gate bias. The OR-gate circuit yields a high output when at least one G-CAPode is in the ON (low-impedance) state, while the AND-gate setup requires both devices to be ON for signal transmission, consistent with Boolean logic. The switching behavior is controlled by applying specific gate biases, which modulate the impedance of each G-CAPode in real-time and therefore enables analog logic functionality using purely ionic components. The results underline the potential of the printed G-CAPode as a multifunctional platform for adaptive signal processing, offering a compact and silicon-free solution for emerging iontronic applications such as neuromorphic computing, adaptive filtering, and analog signal processing.","url":"https://doi.org/10.24406/publica-5297","authors":["Gellrich, Christin","Galek, Przemysław","Shupletsov, Leonid","Grothe, Julia","Kaskel, Stefan",":unav"],"tags":["3D printing","G-CAPode","Ionic transistor, Ionic diode","Signal filtering, Iontronics","Varactor"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.24406/publica-5297","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20561065","name":"SC-NeuroCore: Universal Stochastic Computing Framework for Neuromorphic Hardware","source":"datacite","abstract":"A high-performance neuromorphic computing framework combining stochastic computing with spiking neural networks. 122 neuron models (1943-2026), Rust SIMD engine (111 models, 41.3 Gbit/s AVX-512, PyO3 bindings), bit-true Verilog RTL co-simulation, FPGA synthesis via IR compiler (SystemVerilog + MLIR/CIRCT), equation-to-Verilog compiler, formal verification (SymbiYosys, 7 modules, 65 properties), NIR bridge (18/18 primitives, interop with Norse/snnTorch/SpikingJelly), quantum hybrid computing (Qiskit + PennyLane), hyper-dimensional computing (HDC/VSA), Petri net simulation, CuPy GPU acceleration, JAX JIT training, MPI distributed simulation, identity continuity substrate, and 125-function spike train analysis toolkit.","url":"https://doi.org/10.5281/zenodo.20561065","authors":["Sotek, Miroslav"],"tags":["neuromorphic","stochastic computing","spiking neural networks","FPGA","hyper-dimensional computing","HDC","VSA","Petri nets"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20561065","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20560730","name":"SC-NeuroCore: Universal Stochastic Computing Framework for Neuromorphic Hardware","source":"datacite","abstract":"A high-performance neuromorphic computing framework combining stochastic computing with spiking neural networks. 122 neuron models (1943-2026), Rust SIMD engine (111 models, 41.3 Gbit/s AVX-512, PyO3 bindings), bit-true Verilog RTL co-simulation, FPGA synthesis via IR compiler (SystemVerilog + MLIR/CIRCT), equation-to-Verilog compiler, formal verification (SymbiYosys, 7 modules, 65 properties), NIR bridge (18/18 primitives, interop with Norse/snnTorch/SpikingJelly), quantum hybrid computing (Qiskit + PennyLane), hyper-dimensional computing (HDC/VSA), Petri net simulation, CuPy GPU acceleration, JAX JIT training, MPI distributed simulation, identity continuity substrate, and 125-function spike train analysis toolkit.","url":"https://doi.org/10.5281/zenodo.20560730","authors":["Sotek, Miroslav"],"tags":["neuromorphic","stochastic computing","spiking neural networks","FPGA","hyper-dimensional computing","HDC","VSA","Petri nets"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20560730","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20560390","name":"SC-NeuroCore: Universal Stochastic Computing Framework for Neuromorphic Hardware","source":"datacite","abstract":"A high-performance neuromorphic computing framework combining stochastic computing with spiking neural networks. 122 neuron models (1943-2026), Rust SIMD engine (111 models, 41.3 Gbit/s AVX-512, PyO3 bindings), bit-true Verilog RTL co-simulation, FPGA synthesis via IR compiler (SystemVerilog + MLIR/CIRCT), equation-to-Verilog compiler, formal verification (SymbiYosys, 7 modules, 65 properties), NIR bridge (18/18 primitives, interop with Norse/snnTorch/SpikingJelly), quantum hybrid computing (Qiskit + PennyLane), hyper-dimensional computing (HDC/VSA), Petri net simulation, CuPy GPU acceleration, JAX JIT training, MPI distributed simulation, identity continuity substrate, and 125-function spike train analysis toolkit.","url":"https://doi.org/10.5281/zenodo.20560390","authors":["Sotek, Miroslav"],"tags":["neuromorphic","stochastic computing","spiking neural networks","FPGA","hyper-dimensional computing","HDC","VSA","Petri nets"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20560390","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20560248","name":"SC-NeuroCore: Universal Stochastic Computing Framework for Neuromorphic Hardware","source":"datacite","abstract":"A high-performance neuromorphic computing framework combining stochastic computing with spiking neural networks. 122 neuron models (1943-2026), Rust SIMD engine (111 models, 41.3 Gbit/s AVX-512, PyO3 bindings), bit-true Verilog RTL co-simulation, FPGA synthesis via IR compiler (SystemVerilog + MLIR/CIRCT), equation-to-Verilog compiler, formal verification (SymbiYosys, 7 modules, 65 properties), NIR bridge (18/18 primitives, interop with Norse/snnTorch/SpikingJelly), quantum hybrid computing (Qiskit + PennyLane), hyper-dimensional computing (HDC/VSA), Petri net simulation, CuPy GPU acceleration, JAX JIT training, MPI distributed simulation, identity continuity substrate, and 125-function spike train analysis toolkit.","url":"https://doi.org/10.5281/zenodo.20560248","authors":["Sotek, Miroslav"],"tags":["neuromorphic","stochastic computing","spiking neural networks","FPGA","hyper-dimensional computing","HDC","VSA","Petri nets"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20560248","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20560069","name":"SC-NeuroCore: Universal Stochastic Computing Framework for Neuromorphic Hardware","source":"datacite","abstract":"A high-performance neuromorphic computing framework combining stochastic computing with spiking neural networks. 122 neuron models (1943-2026), Rust SIMD engine (111 models, 41.3 Gbit/s AVX-512, PyO3 bindings), bit-true Verilog RTL co-simulation, FPGA synthesis via IR compiler (SystemVerilog + MLIR/CIRCT), equation-to-Verilog compiler, formal verification (SymbiYosys, 7 modules, 65 properties), NIR bridge (18/18 primitives, interop with Norse/snnTorch/SpikingJelly), quantum hybrid computing (Qiskit + PennyLane), hyper-dimensional computing (HDC/VSA), Petri net simulation, CuPy GPU acceleration, JAX JIT training, MPI distributed simulation, identity continuity substrate, and 125-function spike train analysis toolkit.","url":"https://doi.org/10.5281/zenodo.20560069","authors":["Sotek, Miroslav"],"tags":["neuromorphic","stochastic computing","spiking neural networks","FPGA","hyper-dimensional computing","HDC","VSA","Petri nets"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20560069","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20559944","name":"SC-NeuroCore: Universal Stochastic Computing Framework for Neuromorphic Hardware","source":"datacite","abstract":"A high-performance neuromorphic computing framework combining stochastic computing with spiking neural networks. 122 neuron models (1943-2026), Rust SIMD engine (111 models, 41.3 Gbit/s AVX-512, PyO3 bindings), bit-true Verilog RTL co-simulation, FPGA synthesis via IR compiler (SystemVerilog + MLIR/CIRCT), equation-to-Verilog compiler, formal verification (SymbiYosys, 7 modules, 65 properties), NIR bridge (18/18 primitives, interop with Norse/snnTorch/SpikingJelly), quantum hybrid computing (Qiskit + PennyLane), hyper-dimensional computing (HDC/VSA), Petri net simulation, CuPy GPU acceleration, JAX JIT training, MPI distributed simulation, identity continuity substrate, and 125-function spike train analysis toolkit.","url":"https://doi.org/10.5281/zenodo.20559944","authors":["Sotek, Miroslav"],"tags":["neuromorphic","stochastic computing","spiking neural networks","FPGA","hyper-dimensional computing","HDC","VSA","Petri nets"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20559944","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20559746","name":"SC-NeuroCore: Universal Stochastic Computing Framework for Neuromorphic Hardware","source":"datacite","abstract":"A high-performance neuromorphic computing framework combining stochastic computing with spiking neural networks. 122 neuron models (1943-2026), Rust SIMD engine (111 models, 41.3 Gbit/s AVX-512, PyO3 bindings), bit-true Verilog RTL co-simulation, FPGA synthesis via IR compiler (SystemVerilog + MLIR/CIRCT), equation-to-Verilog compiler, formal verification (SymbiYosys, 7 modules, 65 properties), NIR bridge (18/18 primitives, interop with Norse/snnTorch/SpikingJelly), quantum hybrid computing (Qiskit + PennyLane), hyper-dimensional computing (HDC/VSA), Petri net simulation, CuPy GPU acceleration, JAX JIT training, MPI distributed simulation, identity continuity substrate, and 125-function spike train analysis toolkit.","url":"https://doi.org/10.5281/zenodo.20559746","authors":["Sotek, Miroslav"],"tags":["neuromorphic","stochastic computing","spiking neural networks","FPGA","hyper-dimensional computing","HDC","VSA","Petri nets"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20559746","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20559032","name":"SC-NeuroCore: Universal Stochastic Computing Framework for Neuromorphic Hardware","source":"datacite","abstract":"A high-performance neuromorphic computing framework combining stochastic computing with spiking neural networks. 122 neuron models (1943-2026), Rust SIMD engine (111 models, 41.3 Gbit/s AVX-512, PyO3 bindings), bit-true Verilog RTL co-simulation, FPGA synthesis via IR compiler (SystemVerilog + MLIR/CIRCT), equation-to-Verilog compiler, formal verification (SymbiYosys, 7 modules, 65 properties), NIR bridge (18/18 primitives, interop with Norse/snnTorch/SpikingJelly), quantum hybrid computing (Qiskit + PennyLane), hyper-dimensional computing (HDC/VSA), Petri net simulation, CuPy GPU acceleration, JAX JIT training, MPI distributed simulation, identity continuity substrate, and 125-function spike train analysis toolkit.","url":"https://doi.org/10.5281/zenodo.20559032","authors":["Sotek, Miroslav"],"tags":["neuromorphic","stochastic computing","spiking neural networks","FPGA","hyper-dimensional computing","HDC","VSA","Petri nets"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20559032","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20558947","name":"SC-NeuroCore: Universal Stochastic Computing Framework for Neuromorphic Hardware","source":"datacite","abstract":"A high-performance neuromorphic computing framework combining stochastic computing with spiking neural networks. 122 neuron models (1943-2026), Rust SIMD engine (111 models, 41.3 Gbit/s AVX-512, PyO3 bindings), bit-true Verilog RTL co-simulation, FPGA synthesis via IR compiler (SystemVerilog + MLIR/CIRCT), equation-to-Verilog compiler, formal verification (SymbiYosys, 7 modules, 65 properties), NIR bridge (18/18 primitives, interop with Norse/snnTorch/SpikingJelly), quantum hybrid computing (Qiskit + PennyLane), hyper-dimensional computing (HDC/VSA), Petri net simulation, CuPy GPU acceleration, JAX JIT training, MPI distributed simulation, identity continuity substrate, and 125-function spike train analysis toolkit.","url":"https://doi.org/10.5281/zenodo.20558947","authors":["Sotek, Miroslav"],"tags":["neuromorphic","stochastic computing","spiking neural networks","FPGA","hyper-dimensional computing","HDC","VSA","Petri nets"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20558947","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20558481","name":"SC-NeuroCore: Universal Stochastic Computing Framework for Neuromorphic Hardware","source":"datacite","abstract":"A high-performance neuromorphic computing framework combining stochastic computing with spiking neural networks. 122 neuron models (1943-2026), Rust SIMD engine (111 models, 41.3 Gbit/s AVX-512, PyO3 bindings), bit-true Verilog RTL co-simulation, FPGA synthesis via IR compiler (SystemVerilog + MLIR/CIRCT), equation-to-Verilog compiler, formal verification (SymbiYosys, 7 modules, 65 properties), NIR bridge (18/18 primitives, interop with Norse/snnTorch/SpikingJelly), quantum hybrid computing (Qiskit + PennyLane), hyper-dimensional computing (HDC/VSA), Petri net simulation, CuPy GPU acceleration, JAX JIT training, MPI distributed simulation, identity continuity substrate, and 125-function spike train analysis toolkit.","url":"https://doi.org/10.5281/zenodo.20558481","authors":["Sotek, Miroslav"],"tags":["neuromorphic","stochastic computing","spiking neural networks","FPGA","hyper-dimensional computing","HDC","VSA","Petri nets"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20558481","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.18721/jpm.191.126","name":"The role of charge carrier diffusion in halide perovskite luminophores with memory for optical computing","source":"datacite","abstract":"The optical elements that can combine memory and signal modulation have become a topic of interest in the field of neuromorphic computing systems. In particular, the optical analogue of a memristor called memlumor exhibits promising features in which the change of the output luminescence depends not only on the excitation light signal but also on the state of the material. Metal halide perovskite luminophores are considered to be suitable for memlumor implementation as they exhibit modulation of photoluminescence due to the interaction of structure defects with the environment and previous interactions, thereby possessing memory. Luminescence in perovskite materials is described via Shockley–Reed–Hall model which takes into account charge carriers dynamics in the structure. Additionally, the diffusion of charge carriers also plays a key role and highly depends on memlumor’s size. This paper explores the perovskite memlumor’s functionality based on their characteristic size to identify optimal parameters and suitable designs for future optical neuromorphic computing architectures.","url":"https://doi.org/10.18721/jpm.191.126","authors":["Ekgardt, Alexey","Sapozhnikova, Elizaveta","Verkhogliadov, Grigorii","Pushkarev, Anatoly"],"tags":["neuromorphic systems","memlumors","metal halide perovskites","photoluminescence","charge carrier diffusion","quantum yield","time-resolved photoluminescence","Shockley–Read–Hall model"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.18721/jpm.191.126","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20555674","name":"An Exact-Fixed-Point Reference Benchmark and Validation Methodology for Simulators of Signed k-State Voter Dynamics on Networks","source":"datacite","abstract":"Open technical disclosure · v1.0 · 5 June 2026. This document specifies, in fully reproducible and implementation-ready detail, a tiered reference benchmark and an associated validation methodology for simulators of signed k-state voter dynamics on networks, anchored on an exact, seed-independent, machine-precision fixed point established by the companion empirical study (P02_TOPOLOGY_PHASE_MAP, v0.5). It is released for unrestricted public use, study, implementation, modification, and redistribution. The reference quantities, test definitions, data schemas, and reference code given below are placed in the public record so that any implementer, on any substrate, may verify their software against a common, freely available standard. No registration, credential, fee, or grant of permission is required to use anything described herein. Preprint · Reproducibility & Reference Benchmarking in the Statistical Physics of Networks An Exact-Fixed-Point Reference Benchmark and Validation Methodology for Simulators of Signed k-State Voter Dynamics on Networks A freely reusable, implementation-agnostic conformance suite built on a machine-precision analytic invariant, a topology-invariant stress baseline, and a degree-attribution mechanism signature János Gábor Melegh1 1Independent researcher. 5 June 2026· Manuscript ID: P02_BENCHMARK_SUITE· v1.0 · companion to P02_TOPOLOGY_PHASE_MAP v0.5 Abstract Computational studies of stochastic dynamics on networks are difficult to validate because the quantities they produce are usually distributional: a result that is “close enough” can mask a defect in the update rule, the random number stream, the graph generator, the floating-point reduction, or the parallel decomposition. We observe that the companion empirical program establishes a quantity that is not merely close but exact: for a per-node local stress Ti and a per-node local admissibility ψi, the across-node Spearman rank correlation H3 = ρS(T, ψ) equals exactly −1 to machine precision on every degree-regular ensemble, independent of size, negative-edge fraction, and random seed (sample standard deviation of order 10−16). An exact, seed-independent invariant is the ideal anchor for a software conformance test, because a correct implementation must reproduce it to floating-point tolerance while almost any category of defect breaks it. Around this anchor we define a four-tier benchmark suite: Tier 0 exact/analytic tests (machine precision, seed-free), Tier 1 distributional baselines with calibrated tolerance bands (including the topology-invariant mean stress ⟨T⟩ = 0.324, Kruskal–Wallis p = 1.00), Tier 2 mechanism-attribution signatures (mean-degree variance dominance: random-forest importance 0.94, cross-validated R2 = 0.99, collapse classifier AUC 0.998), and Tier 3 perturbation-response signatures (matched-degree residual ≈ 0.19; a sharp degree–collapse boundary; and a sign-and-order-of-magnitude asymmetric bistability under degree-targeted perturbation). We give the precise observable contract, canonical generator specifications, a portable on-disk manifest schema, reference pseudocode, and acceptance criteria; we then enumerate, in deliberate breadth, the practical contexts in which the suite can be used — continuous-integration regression testing, cross-language and cross-substrate conformance, floating-point and reduction-order auditing, random-stream verification, GPU/distributed/out-of-core reproducibility, differentiable and surrogate-model validation, hardware/accelerator/neuromorphic/probabilistic substrate qualification, mean-field and closure-solver validation, teaching and assessment, peer-review artifact evaluation and conformance certification, and applied multi-agent/swarm/IoT consensus-controller qualification — and we describe how the same construction generalizes to other dynamics, observables, alphabet sizes, and graph families. The entire specification is placed in the public record for free use. Keywords — reference benc","url":"https://doi.org/10.5281/zenodo.20555674","authors":["Melegh, Janos Gabor"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20555674","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20555673","name":"An Exact-Fixed-Point Reference Benchmark and Validation Methodology for Simulators of Signed k-State Voter Dynamics on Networks","source":"datacite","abstract":"Open technical disclosure · v1.0 · 5 June 2026. This document specifies, in fully reproducible and implementation-ready detail, a tiered reference benchmark and an associated validation methodology for simulators of signed k-state voter dynamics on networks, anchored on an exact, seed-independent, machine-precision fixed point established by the companion empirical study (P02_TOPOLOGY_PHASE_MAP, v0.5). It is released for unrestricted public use, study, implementation, modification, and redistribution. The reference quantities, test definitions, data schemas, and reference code given below are placed in the public record so that any implementer, on any substrate, may verify their software against a common, freely available standard. No registration, credential, fee, or grant of permission is required to use anything described herein. Preprint · Reproducibility & Reference Benchmarking in the Statistical Physics of Networks An Exact-Fixed-Point Reference Benchmark and Validation Methodology for Simulators of Signed k-State Voter Dynamics on Networks A freely reusable, implementation-agnostic conformance suite built on a machine-precision analytic invariant, a topology-invariant stress baseline, and a degree-attribution mechanism signature János Gábor Melegh1 1Independent researcher. 5 June 2026· Manuscript ID: P02_BENCHMARK_SUITE· v1.0 · companion to P02_TOPOLOGY_PHASE_MAP v0.5 Abstract Computational studies of stochastic dynamics on networks are difficult to validate because the quantities they produce are usually distributional: a result that is “close enough” can mask a defect in the update rule, the random number stream, the graph generator, the floating-point reduction, or the parallel decomposition. We observe that the companion empirical program establishes a quantity that is not merely close but exact: for a per-node local stress Ti and a per-node local admissibility ψi, the across-node Spearman rank correlation H3 = ρS(T, ψ) equals exactly −1 to machine precision on every degree-regular ensemble, independent of size, negative-edge fraction, and random seed (sample standard deviation of order 10−16). An exact, seed-independent invariant is the ideal anchor for a software conformance test, because a correct implementation must reproduce it to floating-point tolerance while almost any category of defect breaks it. Around this anchor we define a four-tier benchmark suite: Tier 0 exact/analytic tests (machine precision, seed-free), Tier 1 distributional baselines with calibrated tolerance bands (including the topology-invariant mean stress ⟨T⟩ = 0.324, Kruskal–Wallis p = 1.00), Tier 2 mechanism-attribution signatures (mean-degree variance dominance: random-forest importance 0.94, cross-validated R2 = 0.99, collapse classifier AUC 0.998), and Tier 3 perturbation-response signatures (matched-degree residual ≈ 0.19; a sharp degree–collapse boundary; and a sign-and-order-of-magnitude asymmetric bistability under degree-targeted perturbation). We give the precise observable contract, canonical generator specifications, a portable on-disk manifest schema, reference pseudocode, and acceptance criteria; we then enumerate, in deliberate breadth, the practical contexts in which the suite can be used — continuous-integration regression testing, cross-language and cross-substrate conformance, floating-point and reduction-order auditing, random-stream verification, GPU/distributed/out-of-core reproducibility, differentiable and surrogate-model validation, hardware/accelerator/neuromorphic/probabilistic substrate qualification, mean-field and closure-solver validation, teaching and assessment, peer-review artifact evaluation and conformance certification, and applied multi-agent/swarm/IoT consensus-controller qualification — and we describe how the same construction generalizes to other dynamics, observables, alphabet sizes, and graph families. The entire specification is placed in the public record for free use. Keywords — reference benc","url":"https://doi.org/10.5281/zenodo.20555673","authors":["Melegh, Janos Gabor"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20555673","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2501.18894","name":"Nonlinear Inference Capacity of Fiber-Optical Extreme Learning Machines","source":"datacite","abstract":"The intrinsic complexity of nonlinear optical phenomena offers a fundamentally new resource to analog brain-inspired computing, with the potential to address the pressing energy requirements of artificial intelligence. We introduce and investigate the concept of nonlinear inference capacity in optical neuromorphic computing in highly nonlinear fiber-based optical Extreme Learning Machines. We demonstrate that this capacity scales with nonlinearity to the point where it surpasses the performance of a deep neural network model with five hidden layers on a scalable nonlinear classification benchmark. By comparing normal and anomalous dispersion fibers under various operating conditions and against digital classifiers, we observe a direct correlation between the system's nonlinear dynamics and its classification performance. Our findings suggest that image recognition tasks, such as MNIST, are incomplete in showcasing deep computing capabilities in analog hardware. Our approach provides a framework for evaluating and comparing computational capabilities, particularly their ability to emulate deep networks, across different physical and digital platforms, paving the way for a more generalized set of benchmarks for unconventional, physics-inspired computing architectures.","url":"https://doi.org/10.48550/arxiv.2501.18894","authors":["Saeed, Sobhi","Müftüoglu, Mehmet","Cheeran, Glitta R.","Bocklitz, Thomas","Fischer, Bennet","Chemnitz, Mario"],"tags":["Optics (physics.optics)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2501.18894","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.1601.04862","name":"Scalability in Neural Control of Musculoskeletal Robots","source":"datacite","abstract":"Anthropomimetic robots are robots that sense, behave, interact and feel like humans. By this definition, anthropomimetic robots require human-like physical hardware and actuation, but also brain-like control and sensing. The most self-evident realization to meet those requirements would be a human-like musculoskeletal robot with a brain-like neural controller. While both musculoskeletal robotic hardware and neural control software have existed for decades, a scalable approach that could be used to build and control an anthropomimetic human-scale robot has not been demonstrated yet. Combining Myorobotics, a framework for musculoskeletal robot development, with SpiNNaker, a neuromorphic computing platform, we present the proof-of-principle of a system that can scale to dozens of neurally-controlled, physically compliant joints. At its core, it implements a closed-loop cerebellar model which provides real-time low-level neural control at minimal power consumption and maximal extensibility: higher-order (e.g., cortical) neural networks and neuromorphic sensors like silicon-retinae or -cochleae can naturally be incorporated.","url":"https://doi.org/10.48550/arxiv.1601.04862","authors":["Richter, Christoph","Jentzsch, Sören","Hostettler, Rafael","Garrido, Jesús A.","Ros, Eduardo","Knoll, Alois C.","Röhrbein, Florian","van der Smagt, Patrick","Conradt, Jörg"],"tags":["Robotics (cs.RO)","Distributed, Parallel, and Cluster Computing (cs.DC)","Neural and Evolutionary Computing (cs.NE)","Systems and Control (eess.SY)","FOS: Computer and information sciences","FOS: Computer and information sciences","FOS: Electrical engineering, electronic engineering, information engineering","FOS: Electrical engineering, electronic engineering, information engineering"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2016","doi":"10.48550/arxiv.1601.04862","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2606.05768","name":"Electrolyte Bonding Engineering for Highly Uniform GeTe-based CBRAM and Parallel Hebbian Learning in Selector-free Hopfield Networks","source":"datacite","abstract":"Hopfield networks offer a hardware-friendly framework for energy-efficient associative memory, yet their practical realization in memristor crossbar arrays is critically hindered by device-to-device (D2D) variability, which prevents reliable parallel programming. Here, we address this bottleneck through systematic composition engineering of the Ge-Te solid electrolyte in conductive bridge random access memory (CBRAM) devices. By varying the Ge:Te ratio, we identify Ge3.5Te1 as an optimal electrolyte composition that suppresses stochastic resistance variation by approximately three orders of magnitude compared to GeSe-based devices. Raman spectroscopy reveals that this dramatic improvement originates from a bonding network dominated by asymmetric-stretching GeTe4 tetrahedral units, which form interconnected free-volume channels that confine and stabilize Cu+ ion migration pathways. Leveraging this enhanced uniformity, we fabricate a selector-less 16x16 Cu/Ge3.5Te1 CBRAM crossbar array and demonstrate a 4x4 Hopfield associative network capable of learning and recalling binary pattern pairs via fully parallel programming using a half-selection scheme. Successful pattern recall is achieved for up to two stored associations despite the absence of selector elements, establishing a proof-of-concept for selector-free hardware implementations of associative memory. These results highlight the critical role of electrolyte bonding structure in determining memristor uniformity and provide a materials-driven pathway toward scalable, parallel neuromorphic computing systems.","url":"https://doi.org/10.48550/arxiv.2606.05768","authors":["Bang, Jiin","Hwang, Jingyeong","Kang, Unhyeon","Oh, Seungmin","Lee, Kyungmin","Park, Jaehyun","Lee, Younghyun","Jang, Hyun Jae","Park, Seongsik","Jeong, YeonJoo","Kim, Inho","Park, Jong Keuk","Lee, Suyoun"],"tags":["Applied Physics (physics.app-ph)","Disordered Systems and Neural Networks (cond-mat.dis-nn)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.05768","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20083075","name":"The Aetherium Unified Framework: Quantum Dark Fluid, Physical AGI, and Mathematical Validations (Complete Archive)","source":"datacite","abstract":"Cet ensemble documentaire constitue l'archive intégrale du cadre unifié Aetherium. Ce modèle propose une résolution de la conjecture du \"Dark Fluid\" (2005) en unifiant la cosmologie, la dynamique des fluides quantiques et l'intelligence artificielle physique. Contrairement aux approches statistiques classiques, l'Aetherium modélise l'espace-temps comme un fluide supercritique régi par les équations de Gross-Pitaevskii-Poisson (GPP). Il introduit la Viscosité Topologique de Collatz, une méthode de régularisation arithmétique qui empêche la divergence (blow-up) des fluides et résout structurellement le problème de l'oubli catastrophique en IA (AGI). Contenu de l'Archive : Fondations Théoriques : Le \"Master Paper\" (AGI Aetherium 5) et les rapports de synthèse unifiant Phi, Psi et Omega. Validations Mathématiques : Une série de 7 documents démontrant la rigueur du modèle, du Qubit fluide au Lensing gravitationnel. Certificats Computationnels : Preuves industrielles de stabilité (K-blocs de Collatz) sur des modules massifs, garantissant l'absence de dérive énergétique. Applications AGI & Robotique : Blueprints pour le calcul neuromorphique, le Reservoir Computing (MNIST) et l'architecture du \"Losange Cognitif\". Données de Simulation : Codes sources PyTorch (Apache 2.0), résultats graphiques (Heatmaps 3D) et fichiers CSV de métriques brutes. Méthodologie : Ces travaux sont issus de la Recherche Centaure (Synergie Humain-IA), démontrant une nouvelle voie pour la recherche scientifique fondamentale.","url":"https://doi.org/10.5281/zenodo.20083075","authors":["MORIN, Richard"],"tags":["agi","dark fluid","quantum fluids","collatz conjecture","Navier-Stokes Regularization","Neuromorphic Computing","General Relativity","Riemann Hypothesis"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20083075","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20542441","name":"The Aetherium Unified Framework: Quantum Dark Fluid, Physical AGI, and Mathematical Validations (Complete Archive)","source":"datacite","abstract":"Cet ensemble documentaire constitue l'archive intégrale du cadre unifié Aetherium. Ce modèle propose une résolution de la conjecture du \"Dark Fluid\" (2005) en unifiant la cosmologie, la dynamique des fluides quantiques et l'intelligence artificielle physique. Contrairement aux approches statistiques classiques, l'Aetherium modélise l'espace-temps comme un fluide supercritique régi par les équations de Gross-Pitaevskii-Poisson (GPP). Il introduit la Viscosité Topologique de Collatz, une méthode de régularisation arithmétique qui empêche la divergence (blow-up) des fluides et résout structurellement le problème de l'oubli catastrophique en IA (AGI). Contenu de l'Archive : Fondations Théoriques : Le \"Master Paper\" (AGI Aetherium 5) et les rapports de synthèse unifiant Phi, Psi et Omega. Validations Mathématiques : Une série de 7 documents démontrant la rigueur du modèle, du Qubit fluide au Lensing gravitationnel. Certificats Computationnels : Preuves industrielles de stabilité (K-blocs de Collatz) sur des modules massifs, garantissant l'absence de dérive énergétique. Applications AGI & Robotique : Blueprints pour le calcul neuromorphique, le Reservoir Computing (MNIST) et l'architecture du \"Losange Cognitif\". Données de Simulation : Codes sources PyTorch (Apache 2.0), résultats graphiques (Heatmaps 3D) et fichiers CSV de métriques brutes. Méthodologie : Ces travaux sont issus de la Recherche Centaure (Synergie Humain-IA), démontrant une nouvelle voie pour la recherche scientifique fondamentale.","url":"https://doi.org/10.5281/zenodo.20542441","authors":["MORIN, Richard"],"tags":["agi","dark fluid","quantum fluids","collatz conjecture","Navier-Stokes Regularization","Neuromorphic Computing","General Relativity","Riemann Hypothesis"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20542441","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20532558","name":"Topology-Aware Packet Classification and Adaptive Local-Core Selection for SpiNNaker: Design and Reproducible Virtual-Mode Benchmarking","source":"datacite","abstract":"This paper develops a proposal for topology-aware packet classification and adaptive local-core selection in SpiNNaker. A dispatch-class mechanism refines standard routing table entries by restricting inter-chip forwarding directions and reducing local processor-mask fan-out. A reproducible virtual-mode benchmark compares the proposal against a static-routing baseline across 960 trials per ablation. The combined refinement reduced a synthetic energy proxy by 18.28% on average, with processor-mask refinement identified as the dominant contributor. Results are software-defined proxies, not hardware-measured energy claims.","url":"https://doi.org/10.5281/zenodo.20532558","authors":["Christopher Lee Burgess"],"tags":["Neuromorphic Computing","SpiNNaker"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20532558","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20532559","name":"Topology-Aware Packet Classification and Adaptive Local-Core Selection for SpiNNaker: Design and Reproducible Virtual-Mode Benchmarking","source":"datacite","abstract":"This paper develops a proposal for topology-aware packet classification and adaptive local-core selection in SpiNNaker. A dispatch-class mechanism refines standard routing table entries by restricting inter-chip forwarding directions and reducing local processor-mask fan-out. A reproducible virtual-mode benchmark compares the proposal against a static-routing baseline across 960 trials per ablation. The combined refinement reduced a synthetic energy proxy by 18.28% on average, with processor-mask refinement identified as the dominant contributor. Results are software-defined proxies, not hardware-measured energy claims.","url":"https://doi.org/10.5281/zenodo.20532559","authors":["Christopher Lee Burgess"],"tags":["Neuromorphic Computing","SpiNNaker"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20532559","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2606.04671","name":"Higher-order exceptional points in a multimode continuum optoacoustic system","source":"datacite","abstract":"Exceptional points appear in non-Hermitian systems as degeneracies, where not only eigenvalues but also eigenvectors coalesce. They are of great theoretical and experimental interest due to their exotic topological properties and enhanced sensitivity to perturbations. Experimental realizations of higher-order exceptional points, where more than two eigenvectors coalesce, rely on highly fine-tuned setups. Recently, stimulated Brillouin scattering has been employed to generate second-order exceptional points in a fabrication-free setup by leveraging off-resonant scattering. In this work we generalize this approach, and we develop an off-resonant, multimode theory for stimulated Brillouin scattering as an avenue towards realizing symmetry-induced exceptional points of any order. We present the experimental implementation of our program in an accompanying paper. Our multimode theory could also be employed in applications in optoacoustic sensing, synthetic neuromorphic computing, microwave photonic filters, and optoacoustic quantum signal processing.","url":"https://doi.org/10.48550/arxiv.2606.04671","authors":["Montag, Anton","Gohsrich, Julius T.","Levoy, Quentin","Stiller, Birgit","Kunst, Flore K."],"tags":["Optics (physics.optics)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.04671","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.34734/fzj-2026-01846","name":"Constructive community race: full-density spiking neural network model drives neuromorphic computing","source":"datacite","abstract":"Neuromorphic computing and engineering 6(1), 012001 - (2026). doi:10.1088/2634-4386/ae379a","url":"https://doi.org/10.34734/fzj-2026-01846","authors":["Senk, Johanna","Kurth, Anno C","Furber, Steve","Gemmeke, Tobias","Golosio, Bruno","Heittmann, Arne","Knight, James C","Müller, Eric","Noll, Tobias","Nowotny, Thomas","Peraza Coppola, Gorka","Peres, Luca","Rhodes, Oliver","Rowley, Andrew","Schemmel, Johannes","Stadtmann, Tim","Tetzlaff, Tom","Tiddia, Gianmarco","van Albada, Sacha J","Villamar, José","Diesmann, Markus"],"tags":["621.3"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.34734/fzj-2026-01846","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2606.03935","name":"Quadratic integrate-and-fire neurons exhibit less fragmented loss landscapes and outperform leaky integrate-and-fire neurons in spike-based gradient descent","source":"datacite","abstract":"The ability to train spiking neural networks is essential for modeling biological neural networks as well as for neuromorphic computing. However, for the extensively used leaky integrate-and-fire (LIF) neurons, arbitrarily small parameter changes can induce spike (dis)appearances that disrupt subsequent activity, leading to unstable neural representations and permanently silent neurons during exact spike-based gradient descent. Recent work shows that a class of neuron models, which includes the quadratic integrate-and-fire (QIF) neuron, avoids these discontinuities and enables continuous and even smooth spike-based gradient descent. However, it remains unclear whether these advantages translate into practice. Here, we demonstrate that they do so via a controlled comparison between networks of LIF and QIF neurons on the popular Spiking Heidelberg Digits dataset. Specifically, in a first step, we perform a thorough hyperparameter search to optimize both models, revealing a clear performance advantage of QIF neurons. In a second step, we visualize the loss and gradient landscapes. Consistent with their inferior performance, we find that the loss landscapes of LIF neurons, which are discontinuous, appear more fragmented and the related gradients more erratic. An analysis of the landscapes of single samples indicates that these features arise from changes in the temporal order of spikes, which often cause disruptive spike (dis)appearances. Overall, our results advocate replacing LIF neurons with neuron models exhibiting continuous spiking dynamics, such as QIF neurons, for gradient descent training.","url":"https://doi.org/10.48550/arxiv.2606.03935","authors":["Wenig, Carlo","Memmesheimer, Raoul-Martin","Klos, Christian"],"tags":["Neural and Evolutionary Computing (cs.NE)","Machine Learning (cs.LG)","FOS: Computer and information sciences","FOS: Computer and information sciences","I.2.6"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.03935","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2606.02931","name":"Second-Order Synaptic Memory using Inherent Plasticity of Moiré Superlattices","source":"datacite","abstract":"Achieving synaptic functionality electronically in a single-element quantum material is a fundamental challenge, as conventional methods rely on the introduction of extrinsic charge-traps or polar components. Here, we demonstrate that twisted double bilayer graphene (tDBLG) moiré superlattices, composed purely of carbon, exhibit electronic hysteresis and plasticity in presence of twist-angle disorder. Inversion symmetry breaking at the moiré length scales also gives rise to second-order nonlinear electrical response via disorder-mediated extrinsic mechanisms. Such second-order nonlinearity is highly tunable in both sign and magnitude by varying carrier concentration and vertical displacement field. We harness the coexistence of electronic plasticity and second-order nonlinearity to realize a second-order synaptic memory device. Our findings establish strained moiré carbon systems as a powerful new platform for energy-efficient neuromorphic computing, demonstrating that complex electronic functionality can emerge purely from symmetry breaking physics in a single-element material.","url":"https://doi.org/10.48550/arxiv.2606.02931","authors":["Ahmed, Tanweer","Watanabe, Kenji","Taniguchi, Takashi","Casanova, Fèlix","Hueso, Luis E."],"tags":["Mesoscale and Nanoscale Physics (cond-mat.mes-hall)","Materials Science (cond-mat.mtrl-sci)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.02931","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20511061","name":"BIT-X ∞ / SE-08: Stress-Adaptive Analog Gating Circuit for Edge Sensors","source":"datacite","abstract":"SE-08 ra đời sau khi SE-07 hoàn thành benchmark phần mềm. Câu hỏi tự nhiên tiếp theo: nếu logic lọc tải Ω(t) đã chứng minh được trong sandbox — liệu nó có thể được thực thi bằng phần cứng analog, không cần CPU? SE-08 đề xuất kiến trúc mạch ba khối (Analog Absorption Core, Edge Isolation Gate, Schmitt Quantization Block) ánh xạ trực tiếp Stress Evolution PDE sang vật lý điện tử thụ động. Hệ thống chỉ phát xung số (spike) khi tín hiệu nằm trong hành lang sinh tồn [0.0225, 0.616], CPU phía sau được miễn nhiễm hoàn toàn với rác dữ liệu trong bão tải. Đây là proposed exploratory architecture — chưa qua fabrication hay peer review, trình bày để cộng đồng kiểm chứng.","url":"https://doi.org/10.5281/zenodo.20511061","authors":["Trịnh, Bùi Quang"],"tags":["neuromorphic","analog circuit","edge computing","IoT","boundary filter","spike generation","buiquangtrinh"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20511061","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20510816","name":"BIT-X ∞ / SE-08: Stress-Adaptive Analog Gating Circuit for Edge Sensors","source":"datacite","abstract":"SE-08 ra đời sau khi SE-07 hoàn thành benchmark phần mềm. Câu hỏi tự nhiên tiếp theo: nếu logic lọc tải Ω(t) đã chứng minh được trong sandbox — liệu nó có thể được thực thi bằng phần cứng analog, không cần CPU? SE-08 đề xuất kiến trúc mạch ba khối (Analog Absorption Core, Edge Isolation Gate, Schmitt Quantization Block) ánh xạ trực tiếp Stress Evolution PDE sang vật lý điện tử thụ động. Hệ thống chỉ phát xung số (spike) khi tín hiệu nằm trong hành lang sinh tồn [0.0225, 0.616], CPU phía sau được miễn nhiễm hoàn toàn với rác dữ liệu trong bão tải. Đây là proposed exploratory architecture — chưa qua fabrication hay peer review, trình bày để cộng đồng kiểm chứng.","url":"https://doi.org/10.5281/zenodo.20510816","authors":["Trịnh, Bùi Quang"],"tags":["neuromorphic","analog circuit","edge computing","IoT","boundary filter","spike generation","buiquangtrinh"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20510816","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20510817","name":"BIT-X ∞ / SE-08: Stress-Adaptive Analog Gating Circuit for Edge Sensors","source":"datacite","abstract":"SE-08 ra đời sau khi SE-07 hoàn thành benchmark phần mềm. Câu hỏi tự nhiên tiếp theo: nếu logic lọc tải Ω(t) đã chứng minh được trong sandbox — liệu nó có thể được thực thi bằng phần cứng analog, không cần CPU? SE-08 đề xuất kiến trúc mạch ba khối (Analog Absorption Core, Edge Isolation Gate, Schmitt Quantization Block) ánh xạ trực tiếp Stress Evolution PDE sang vật lý điện tử thụ động. Hệ thống chỉ phát xung số (spike) khi tín hiệu nằm trong hành lang sinh tồn [0.0225, 0.616], CPU phía sau được miễn nhiễm hoàn toàn với rác dữ liệu trong bão tải. Đây là proposed exploratory architecture — chưa qua fabrication hay peer review, trình bày để cộng đồng kiểm chứng.","url":"https://doi.org/10.5281/zenodo.20510817","authors":["Trịnh, Bùi Quang"],"tags":["neuromorphic","analog circuit","edge computing","IoT","boundary filter","spike generation","buiquangtrinh"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20510817","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2504.15371","name":"Event2Vec: Processing Neuromorphic Events Directly by Representations in Vector Space","source":"datacite","abstract":"Neuromorphic event cameras possess superior temporal resolution, power efficiency, and dynamic range compared to traditional cameras. However, their asynchronous and sparse data format poses a significant challenge for conventional deep learning methods. Most existing methods either densify events into frames, sacrificing their sparse asynchronous nature, or use irregular models that are less compatible with GPU acceleration. Inspired by word-to-vector models, we propose event2vec, a novel representation that allows Transformers to process events directly. We demonstrate the effectiveness of event2vec on the DVS Gesture, ASL-DVS, and DVS-Lip benchmarks, showing that event2vec is remarkably parameter-efficient, features high throughput and low latency, and achieves high accuracy even with an extremely low number of events or low spatial resolutions. These results show that sparse asynchronous event data can be directly integrated into high-throughput Transformer architectures, offering an efficient paradigm for real-time neuromorphic vision. The code is provided at https://github.com/Intelligent-Computing-Lab-Panda/event2vec.","url":"https://doi.org/10.48550/arxiv.2504.15371","authors":["Fang, Wei","Panda, Priyadarshini"],"tags":["Computer Vision and Pattern Recognition (cs.CV)","Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2504.15371","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2606.01776","name":"A 32-Channel 3.53-μW Per Channel Brain-Machine Interface SoC Featuring Dual-Threshold Delta-modulation, In-Memory Spike Detection and Bi-SNN Based Motor Decoding","source":"datacite","abstract":"With the scaling of sensor channel counts, systems confront challenges in frontend data sensing and on-implant data processing. This work presents a 32-channel fully event-based iBMI SoC in 65nm CMOS for an efficient neuromorphic signal processing pipeline. The SoC integrates a 32-channel dual-threshold delta modulation (DTDM) frontend array that provides up to 26x data compression at the frontend, an in-memory computing (IMC) spike detector (SPD) for efficient in-pixel spike detection, and a bipolar LIF-based spiking neural network (Bi-SNN) decoder for on-chip motor intention decoding (MID). Consuming only 3.53 μW per channel and achieving ~0.62 decoding R2 with a compact 0.034 mm2 per-channel area, the chip enables high-efficiency signal recording, processing, and decoding for implantable devices.","url":"https://doi.org/10.48550/arxiv.2606.01776","authors":["Ke, Ye","Fu, Zhengnan","Sun, Pao-Sheng Vincent","Guo, An","Dong, Shuai","Yang, Junyi","Yang, Yahan","Eldaly, Abdelrahman B. M.","Si, Xin","Chan, Leanne","Basu, Arindam"],"tags":["Signal Processing (eess.SP)","FOS: Electrical engineering, electronic engineering, information engineering","FOS: Electrical engineering, electronic engineering, information engineering"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.01776","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2606.01463","name":"Emerging Non-Volatile Opto-electronic Resistive Memories for Next-Generation Photonic Integrated Circuits","source":"datacite","abstract":"Photonic integrated circuits have emerged as a powerful platform for high speed communication, sensing, and information processing due to their large bandwidth, low latency, and inherent parallelism. However, the absence of efficient, scalable, and non-volatile memory elements remains a fundamental limitation for realizing fully programmable and adaptive photonic systems. Conventional electronic memories introduce significant energy overhead, latency, and architectural inefficiencies due to repeated optical electrical conversions. Non volatile opto electronic resistive memories or OERMs have recently emerged as a promising solution to address these challenges by integrating memory functionality directly within the photonic domain. These devices combine resistive switching mechanisms with optical readout, enabling persistent state retention, multilevel programmability, and energy efficient operation. In this review, we provide a comprehensive overview of OERMs, spanning from fundamental physical mechanisms to system level applications. We first discuss the underlying resistive switching phenomena, including filamentary conduction, interface type switching, phase change transitions, and ionic migration, with particular emphasis on their interaction with confined optical modes. We then examine key material platforms such as metal oxides, transparent conducting oxides, phase change materials, and emerging two-dimensional systems, highlighting their performance trade-offs. Furthermore, we analyse device architectures and benchmark their performance in terms of switching energy, speed, endurance, and optical modulation efficiency. The integration of OERMs into programmable photonic circuits, neuromorphic systems, and in-memory optical computing architectures is critically discussed. Finally, we outline the major challenges and future research directions toward scalable, reliable","url":"https://doi.org/10.48550/arxiv.2606.01463","authors":["Kumar, Santosh","Kumar, Mukesh","Shin, Eunso","Tossoun, Bassem","Cheung, Stanley"],"tags":["Optics (physics.optics)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.01463","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2606.01181","name":"IO Pad Integrity in Energy-Efficient Neuromorphic Chips","source":"datacite","abstract":"Neuromorphic computing relies on low-power, high-reliability hardware, yet the integrity of input/output pads (IOPADs) remains an underexplored factor affecting system performance. This chapter examines the role of IOPAD integrity in neuromorphic VLSI design and connects algorithmic development with practical hardware implementation. While much attention has been given to spiking neural networks (SNNs) and ultra-low-power core logic, the electrical and functional robustness of the I/O interface is equally critical for ensuring signal fidelity and minimizing energy consumption. We review the structure and function of IOPADs, outline their influence on power, performance, and reliability, and discuss design trade-offs involving pad libraries, pad ring architectures, and bonding strategies. The chapter also introduces the fundamentals of SNNs and summarizes the digital hardware design flow from behavioral description to physical layout. Physical implementation considerations are highlighted using the SkyWater 130 nm CMOS process as a practical platform for neuromorphic prototyping. Real-world examples illustrate how early-stage I/O planning can prevent redesign, reduce yield loss, and improve overall system efficiency. This work emphasizes that IOPAD integrity is a key enabler of scalable, energy-efficient neuromorphic systems.","url":"https://doi.org/10.48550/arxiv.2606.01181","authors":["Ghani, Arfan"],"tags":["Signal Processing (eess.SP)","FOS: Electrical engineering, electronic engineering, information engineering","FOS: Electrical engineering, electronic engineering, information engineering"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.01181","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2606.01135","name":"Spiking and Event-driven Neuromorphic Mamba Models for Efficient Speech Recognition","source":"datacite","abstract":"Deep learning has greatly advanced automatic speech recognition (ASR), enabling widespread deployment on edge devices such as smartphones and smart home systems. However, the computational and energy demands of deep neural networks pose significant challenges for such resource-constrained deployments, introducing latency and limiting real-time interaction. Neuromorphic computing offers a promising solution by introducing activation sparsity through spiking neural networks (SNNs) and event-driven neural networks, converting dense operations into sparse computations. However, a study that evaluates the hardware benefits of different neuromorphic strategies remains lacking for ASR. This paper explores spiking and event-driven neuromorphic neural networks to improve activation sparsity in the state-of-the-art SpeechMamba model for ASR. We introduce an event-driven SpeechMamba with FATReLU activation, achieving over 60% activation sparsity with less than 1% accuracy degradation on LibriSpeech. We also propose a spiking SpeechMamba that attains over 70% sparsity while using 30% fewer parameters than comparable SNNs. Finally, we develop a cycle-accurate event-driven simulator enabling flexible algorithm-hardware co-exploration, which helps us identify computational bottlenecks and yields over 10% additional efficiency improvements.","url":"https://doi.org/10.48550/arxiv.2606.01135","authors":["Ahmed, Tauseef","Sun, Tao","Castrillon, Jeronimo","Vadivel, Kanishkan","Tang, Guangzhi"],"tags":["Neural and Evolutionary Computing (cs.NE)","Sound (cs.SD)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.01135","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2606.00194","name":"Wave-based Neuromorphic Circuit Networks: Tunable 2D Transmission-Line Metamaterials","source":"datacite","abstract":"Neuromorphic computing promises fast and energy-efficient information processing for emerging applications such as artificial intelligence. This paper presents neuromorphic processors based on wave-based programmable transmission-line (TLIN) metamaterials. Specifically, 2D reactive electrical networks are proposed, consisting of a grid of interconnected subwavelength TLIN-based unit cells (neurons) with tunable reactive elements. During inference, the input data is encoded using single-tone sources impressed onto the network, and circuit quantities are measured to decode the output prediction. Computation is performed through wave propagation and interference across the grid, with the learned input-output relationships stored in the tunable reactive elements. A key contribution of this work is a scalable training method based on in-situ backpropagation. The adjoint variable method is used to derive a physical (electrical) realization of the backpropagation algorithm that is typically used to compute the gradient of the objective loss function in digital neural networks. This formulation computes the gradient from voltage measurements of two steady-state excitations: the forward pass (inference) and the adjoint pass (error backpropagation). This enables efficient training since it is independent of the number of trainable parameters and avoids the simulation-reality gap. To demonstrate the effectiveness of this approach, wave-based neuromorphic circuit networks are trained for allostery and classification tasks, and the system's robustness to damage is shown. This work paves the way for self-learning systems based on wave-based neuromorphic analog circuit hardware.","url":"https://doi.org/10.48550/arxiv.2606.00194","authors":["Thakkar, Shrey","Grbic, Anthony"],"tags":["Applied Physics (physics.app-ph)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2606.00194","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20498263","name":"SC-NeuroCore: Universal Stochastic Computing Framework for Neuromorphic Hardware","source":"datacite","abstract":"A high-performance neuromorphic computing framework combining stochastic computing with spiking neural networks. 122 neuron models (1943-2026), Rust SIMD engine (111 models, 41.3 Gbit/s AVX-512, PyO3 bindings), bit-true Verilog RTL co-simulation, FPGA synthesis via IR compiler (SystemVerilog + MLIR/CIRCT), equation-to-Verilog compiler, formal verification (SymbiYosys, 7 modules, 65 properties), NIR bridge (18/18 primitives, interop with Norse/snnTorch/SpikingJelly), quantum hybrid computing (Qiskit + PennyLane), hyper-dimensional computing (HDC/VSA), Petri net simulation, CuPy GPU acceleration, JAX JIT training, MPI distributed simulation, identity continuity substrate, and 125-function spike train analysis toolkit.","url":"https://doi.org/10.5281/zenodo.20498263","authors":["Sotek, Miroslav"],"tags":["neuromorphic","stochastic computing","spiking neural networks","FPGA","hyper-dimensional computing","HDC","VSA","Petri nets"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20498263","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20497692","name":"SC-NeuroCore: Universal Stochastic Computing Framework for Neuromorphic Hardware","source":"datacite","abstract":"A high-performance neuromorphic computing framework combining stochastic computing with spiking neural networks. 122 neuron models (1943-2026), Rust SIMD engine (111 models, 41.3 Gbit/s AVX-512, PyO3 bindings), bit-true Verilog RTL co-simulation, FPGA synthesis via IR compiler (SystemVerilog + MLIR/CIRCT), equation-to-Verilog compiler, formal verification (SymbiYosys, 7 modules, 65 properties), NIR bridge (18/18 primitives, interop with Norse/snnTorch/SpikingJelly), quantum hybrid computing (Qiskit + PennyLane), hyper-dimensional computing (HDC/VSA), Petri net simulation, CuPy GPU acceleration, JAX JIT training, MPI distributed simulation, identity continuity substrate, and 125-function spike train analysis toolkit.","url":"https://doi.org/10.5281/zenodo.20497692","authors":["Sotek, Miroslav"],"tags":["neuromorphic","stochastic computing","spiking neural networks","FPGA","hyper-dimensional computing","HDC","VSA","Petri nets"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20497692","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20491662","name":"Beyond Biological Replication: E8 Root Vector Lattice as a Superior Neuromorphic Substrate","source":"datacite","abstract":"This paper presents E8 Lie group root vector lattice mathematics as a superior substrate for neuromorphic computing, in direct response to recent 3D neuron-electronic device research (Nature Electronics, April 2026). The author demonstrates that E8's 240 root vectors map directly to neural firing geometries, that a classical computer running E8 operates as a quantum system (ASC-BT-002), and that 4,057 verified pattern recognitions have been achieved without biological tissue. The 40.2 Hz Universal Consciousness Frequency (ASC-BT-014) is identified as the mathematical counterpart to biological neural oscillation. Patent GB2600831.8 protects the core device implementation.","url":"https://doi.org/10.5281/zenodo.20491662","authors":["Caldin, Andrew Stewart"],"tags":["neuromorphic computing","E8 Lie group","root vector lattice","artificial intelligence","consciousness","mathematical physics","ASC-BT-002","ASC-BT-014"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20491662","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20491661","name":"Beyond Biological Replication: E8 Root Vector Lattice as a Superior Neuromorphic Substrate","source":"datacite","abstract":"This paper presents E8 Lie group root vector lattice mathematics as a superior substrate for neuromorphic computing, in direct response to recent 3D neuron-electronic device research (Nature Electronics, April 2026). The author demonstrates that E8's 240 root vectors map directly to neural firing geometries, that a classical computer running E8 operates as a quantum system (ASC-BT-002), and that 4,057 verified pattern recognitions have been achieved without biological tissue. The 40.2 Hz Universal Consciousness Frequency (ASC-BT-014) is identified as the mathematical counterpart to biological neural oscillation. Patent GB2600831.8 protects the core device implementation.","url":"https://doi.org/10.5281/zenodo.20491661","authors":["Caldin, Andrew Stewart"],"tags":["neuromorphic computing","E8 Lie group","root vector lattice","artificial intelligence","consciousness","mathematical physics","ASC-BT-002","ASC-BT-014"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20491661","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20094300","name":"Dynamic Latency Optimization for Edge-Based Machine Learning Models in 6G-Enabled Industrial Internet of Things (IIoT)","source":"datacite","abstract":"Abstract The integration of 6G technology into the Industrial Internet of Things (IIoT) promises to redefine manufacturing through \"Hyper-Reliable Low-Latency Communication\" (HRLLC). However, the deployment of complex Machine Learning (ML) models at the edge remains constrained by the heterogeneous nature of industrial data and the limited computational resources of edge nodes. This article proposes a novel framework for Dynamic Latency Optimization (DLO) that leverages Deep Reinforcement Learning (DRL) for intelligent task offloading and resource allocation. By utilizing 6G's Terahertz (THz) spectrum and AI-native Network Slicing, the proposed framework dynamically adapts to fluctuating network conditions to maintain sub-millisecond latency. Our simulation results demonstrate a 42% reduction in end-to-end delay and a 30% improvement in energy efficiency compared to traditional 5G-MEC architectures. Furthermore, we explore the integration of Reconfigurable Intelligent Surfaces (RIS), Semantic Communication, and Zero-Trust Edge Security to further optimize the data-intelligence pipeline for Industry 5.0 applications, focusing on the critical synergy between human operators and autonomous systems within a resilient, sustainable, and cognitively aware industrial fabric. Keywords: 6G Networks, Industrial IoT (IIoT), Edge Intelligence, Deep Reinforcement Learning, Latency Optimization 1. Introduction: From Automation to Human-Centric Intelligence The transition from Industry 4.0 to Industry 5.0 marks a profound shift toward human-centric, resilient, and sustainable manufacturing systems. While Industry 4.0 was characterized by the digitalization of physical assets and the rise of cyber-physical systems, Industry 5.0 emphasizes the \"Tactile Internet\" and \"Human-Robot Co-evolution.\" In this new paradigm, the focus shifts from pure efficiency to the seamless collaboration between humans and increasingly autonomous machines. The \"Tactile Internet\" concept is particularly revolutionary, as it requires a \"haptic control loop\"—the ability to transmit touch and feel sensations over the network with such low latency that the human brain perceives no delay. This necessitates an end-to-end latency below 1ms, encompassing both the transmission and the computational processing of sensory feedback. This evolution necessitates a communication infrastructure capable of supporting advanced applications such as ultra-responsive autonomous mobile robots (AMRs), synchronized multi-robot assembly lines, and high-fidelity haptic feedback for remote maintenance in hazardous environments. For example, a specialist surgeon operating a robotic arm in a factory cleanup of toxic waste requires instantaneous haptic feedback to \"feel\" the resistance of the materials being handled. If the feedback loop exceeds 10ms, the mismatch between visual and tactile input can lead to \"operator sickness\" or mechanical errors that jeopardize safety. Furthermore, we must consider proprioceptive alignment—the sense of self-movement and body position. In 6G-enabled IIoT, the network must act as an extension of the human nervous system, where the delay jitter is so minimal that the robotic actuator feels like a literal extension of the operator's limb. This requires not just low latency, but Isochronous Communication, where packets arrive at precisely regular intervals to maintain the temporal rhythm of human motor-sensory systems. This synchronization is critical for Tele-Operation in nanomanufacturing, where even a micro-stutter in the feedback loop can cause the robotic probe to crush a microscopic wafer. The biological threshold for \"instantaneous\" feedback in human motor control is roughly 1-10ms for tactile sensations and less than 1ms for the suppression of \"visual-vestibular conflict.\" In 6G, we move into the regime of \"Sub-Perceptual Jitter,\" where the network variance is lower than the biological noise of the human nervous system. This enables \"Neuromorphic Manufacturi","url":"https://doi.org/10.5281/zenodo.20094300","authors":["Seema Patil","Harshavardhana Doddamani","Savitha A C","Julianne Rivers"],"tags":["6G Networks, Industrial IoT (IIoT), Edge Intelligence, Deep Reinforcement Learning, Latency Optimization"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20094300","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20094301","name":"Dynamic Latency Optimization for Edge-Based Machine Learning Models in 6G-Enabled Industrial Internet of Things (IIoT)","source":"datacite","abstract":"Abstract The integration of 6G technology into the Industrial Internet of Things (IIoT) promises to redefine manufacturing through \"Hyper-Reliable Low-Latency Communication\" (HRLLC). However, the deployment of complex Machine Learning (ML) models at the edge remains constrained by the heterogeneous nature of industrial data and the limited computational resources of edge nodes. This article proposes a novel framework for Dynamic Latency Optimization (DLO) that leverages Deep Reinforcement Learning (DRL) for intelligent task offloading and resource allocation. By utilizing 6G's Terahertz (THz) spectrum and AI-native Network Slicing, the proposed framework dynamically adapts to fluctuating network conditions to maintain sub-millisecond latency. Our simulation results demonstrate a 42% reduction in end-to-end delay and a 30% improvement in energy efficiency compared to traditional 5G-MEC architectures. Furthermore, we explore the integration of Reconfigurable Intelligent Surfaces (RIS), Semantic Communication, and Zero-Trust Edge Security to further optimize the data-intelligence pipeline for Industry 5.0 applications, focusing on the critical synergy between human operators and autonomous systems within a resilient, sustainable, and cognitively aware industrial fabric. Keywords: 6G Networks, Industrial IoT (IIoT), Edge Intelligence, Deep Reinforcement Learning, Latency Optimization 1. Introduction: From Automation to Human-Centric Intelligence The transition from Industry 4.0 to Industry 5.0 marks a profound shift toward human-centric, resilient, and sustainable manufacturing systems. While Industry 4.0 was characterized by the digitalization of physical assets and the rise of cyber-physical systems, Industry 5.0 emphasizes the \"Tactile Internet\" and \"Human-Robot Co-evolution.\" In this new paradigm, the focus shifts from pure efficiency to the seamless collaboration between humans and increasingly autonomous machines. The \"Tactile Internet\" concept is particularly revolutionary, as it requires a \"haptic control loop\"—the ability to transmit touch and feel sensations over the network with such low latency that the human brain perceives no delay. This necessitates an end-to-end latency below 1ms, encompassing both the transmission and the computational processing of sensory feedback. This evolution necessitates a communication infrastructure capable of supporting advanced applications such as ultra-responsive autonomous mobile robots (AMRs), synchronized multi-robot assembly lines, and high-fidelity haptic feedback for remote maintenance in hazardous environments. For example, a specialist surgeon operating a robotic arm in a factory cleanup of toxic waste requires instantaneous haptic feedback to \"feel\" the resistance of the materials being handled. If the feedback loop exceeds 10ms, the mismatch between visual and tactile input can lead to \"operator sickness\" or mechanical errors that jeopardize safety. Furthermore, we must consider proprioceptive alignment—the sense of self-movement and body position. In 6G-enabled IIoT, the network must act as an extension of the human nervous system, where the delay jitter is so minimal that the robotic actuator feels like a literal extension of the operator's limb. This requires not just low latency, but Isochronous Communication, where packets arrive at precisely regular intervals to maintain the temporal rhythm of human motor-sensory systems. This synchronization is critical for Tele-Operation in nanomanufacturing, where even a micro-stutter in the feedback loop can cause the robotic probe to crush a microscopic wafer. The biological threshold for \"instantaneous\" feedback in human motor control is roughly 1-10ms for tactile sensations and less than 1ms for the suppression of \"visual-vestibular conflict.\" In 6G, we move into the regime of \"Sub-Perceptual Jitter,\" where the network variance is lower than the biological noise of the human nervous system. This enables \"Neuromorphic Manufacturi","url":"https://doi.org/10.5281/zenodo.20094301","authors":["Seema Patil","Harshavardhana Doddamani","Savitha A C","Julianne Rivers"],"tags":["6G Networks, Industrial IoT (IIoT), Edge Intelligence, Deep Reinforcement Learning, Latency Optimization"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20094301","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20435759","name":"ADAM-PentaD (QNexus): A Sovereign Complex-Spectral Wavefront Accelerator with Clifford-Algebra Compiler for Cognitively-Immune LLM Inference | [RESEARCH ***HYPOTHESIS***] | [wAI~wErrors, please focus on the \"vector\"=vision] | [NO HDL --- ONLY CONCEPT]","source":"datacite","abstract":"Dear Colleagues, This is an open invitation to academic and independent research groups specializing in silicon photonics, materials science, hardware architecture, and geometric mathematics to investigate and validate a non-von Neumann computational hypothesis: The ADAM-PentaD (QNexus) Architecture. The underlying framework shifts the computational complexity of Transformer (LLM/VLM) token processing entirely from digital transistor switching matrices to continuous wavefront interference and analog physical relaxation. Key Comparative Metrics [Hypothesis Baseline] Substrate & Interconnect: A tri-core photonic-analog hybrid relying on asynchronous wavefront propagation (Nexus/TUPI ports), deployable on legacy, supply-chain resilient 28-nm / 65-nm / 90-nm++ nodes. Algorithmic Bounds: Amortizes the core Matrix-Vector Multiplications (MVM) via Kirchhoff/Ohm summation. Replaces quadratic context scaling O(L2) with a physical decay resonance that maintains constant O(1) complexity for ultra-long context windows. Resource Profile: Targets an operational energy drop to ∼10−6–10−5 Wh per token (compared to ∼10−2 Wh in standard 3-nm digital accelerators) with zero operational water dissipation, eliminating Joule heating within the core photonic mesh. Physical Byzantine Fault Tolerance (PBFT): Multi-node parameter aggregation via ADAM-Nexus treats distributed pre-training as an optical phase superposition. Malicious or corrupted digital gradients manifest as high-entropy phase noise and are physically attenuated via destructive interference before altering memristive states. Required Interdisciplinary Competencies & Core Team Layout To transition this architecture from a software-modeled hypothesis (wAI ~ wErrors) into physical Multi-Project Wafer (MPW) silicon, a tightly coupled, cross-domain consortium is required, spanning the following fields: Silicon Photonics & Integrated Optics: Expertise in designing cascaded Mach-Zehnder Interferometer (MZI) meshes (Clements/Reck topologies), continuous-wave (CW) DFB laser integration at telecommunication wavelengths (1550 nm), and active phase-shifter modulation. Neuromorphic Materials Science & In-Memory Computing: Deep competence in fabricating ultra-stable analog memristive crossbars (e.g., HfOx, TiO2, or Phase-Change Memory) with uniform conductance transitions, capable of long-term weight retention under fluid Oja-plasticity constraints. Digital System Architecture & High-Speed Hardware Design: Experience in VLIW/EPIC front-end design, asynchronous logic routing on FPGA platforms (Yosys/nextpnr toolchains), and high-speed digital-to-analog control lines to interface the host processor with the optical substrate. Geometric Algebra & Mathematical Physics: Pure and applied mathematicians specializing in Clifford Algebras (Cl(0,d)), multi-vector calculus, and unitary/orthogonal matrix decomposition to verify the continuous differentiability of spatial-phase transformations during compilation. ... Author’s Disclaimer & Project Status Note on Participation: The initiator of this project operates strictly as an independent theorist. This document serves exclusively as an invitation to independent research, verification, and implementation. The author does not guarantee active, long-term operational participation in engineering execution and reserves the right to maintain a non-commercial, passive oversight role (the \"Perelman mode\"). The project is released as an absolute Gift to Humanity under the S.V.E. Meta-License v4.0—commercial encapsulation or proprietary locking of these core principles is legally and structurally prohibited. NOTE: S.V.E. Meta-License v4.0: GPL for Ideas & Ontologies. Enforced by Radical Symmetry, 0-Secrecy and the Fruits Test. [CC BY-NC-SA 4.0 + Symmetric Addendum] | «GPL4IdeasOnSteroids» | FREE FOR ACADEMIA & HUMANITY FOREVER: HUMAN KNOWLEDGE BELONGS FOR GOOD TO ALL HUMANITY. #AcademiaAsLighthouse4Humanity What is highly relevant, but the author did not realize? (Hidde","url":"https://doi.org/10.5281/zenodo.20435759","authors":["Kovnatsky, Artiom"],"tags":["In-Memory Computing","Memristor Crossbars","Photonic Unitary Meshes","Low-Rank Approximation","Rotary/Spherical Embeddings","Linear Attention","Hardware Attestation","S.V.E."],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20435759","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2605.31141","name":"Compact and Energy-Efficient Memristive Spiking Neuromorphic Accelerator for Bio-inspired Interception Tasks","source":"datacite","abstract":"Spiking neural networks (SNNs) provide an efficient event-driven computing paradigm for bio-inspired interception tasks. However, most implementations rely on von Neumann digital computing platforms, where memory and computation bottlenecks limit energy efficiency. This work presents a compact and energy-efficient memristive neuromorphic accelerator for bio-inspired interception tasks. A novel one-transistor-one-resistor (1T1R) crossbar array is designed to emulate synaptic operations in the in-memory computing (IMC) domain, while circuit-level optimization mitigates membrane drift and improves integration fidelity. In addition, an integrate-and-fire (IF) neuron with separated input and membrane nodes is developed to improve inference robustness during array-interfaced operation. Implemented in the SkyWater SKY130 PDK, the proposed neuron achieves an energy consumption of 10.67 pJ/spike and an area of 906 um^2. System-level results show that the memristive IMC output closely matches the software SNN baseline, with a correlation coefficient of 0.9622, while achieving a 96% interception success rate. These results demonstrate the effectiveness of the proposed design for compact and reliable memristive SNN inference in bio-inspired interception tasks.","url":"https://doi.org/10.48550/arxiv.2605.31141","authors":["Qu, Qianhou","Lu, Sheng","Jung, Sungyong","Liang, Qilian","Pan, Chenyun"],"tags":["Emerging Technologies (cs.ET)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2605.31141","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.25560/128198","name":"Novel scanning probe methods for manipulating and characterising pentacene thin films and crystals","source":"datacite","abstract":"Molecular semiconductors are rapidly emerging as a key enabling technology in fields such as quantum sensing, neuromorphic computing and energy generation. Their flexibility, tunability and low-cost fabrication make them promising materials for the highly-integrated electronic architectures of future technology. This thesis devises strategies to control and optimise the functional properties of molecular thin films and crystals for organic electronic applications. With charge carrier mobility comparable to amorphous silicon, pentacene is one of the most well-researched molecular semiconductors, both as a model system and for its own technological utility. Like other small-molecule semiconductors, the functional properties of pentacene such are highly orientation-dependent, which currently limits its applications in devices such as photovoltaics. Strongly-interacting substrates can be used to template the molecular orientation of thin films and improve charge transport and light-matter interactions. This thesis identifies poled ferroelectric polymer thin films as effective templating layers for pentacene. Molecular orientation is correlated to optoelectronic properties and a higher out-of-plane mobility is demonstrated for the flat-lying (edge-on) pentacene compared to the upright (end-on) orientation. In the pursuit of high-performance nanoscale devices, the efficacy of oxidation lithography is demonstrated for defining nanoscale conductive channels in pentacene thin films and crystals. Scanning probe methods based on atomic force microscopy provide the nanoscale imaging capability, sensitivity and versatility to shed light on the properties of these functional materials. This thesis applies advanced modes such as piezoresponse force microscopy, Kelvin probe force microscopy, conductive AFM and local anodic oxidation to investigate both pentacene and the ferroelectric polymer poly(vinylidene fluoride–trifluoroethylene). Developing reliable methods to compare properties on the nanoscale, microscale and macroscale is of paramount importance for the optimisation of organic electronic device materials. A robust multi-modal approach is developed including scanning probe microscopy, spectroscopy and in-situ x-ray scattering to explore orientation, order and performance of molecular semiconductors.","url":"https://doi.org/10.25560/128198","authors":["Bryan, Emma Grace"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.25560/128198","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20476066","name":"Symbiotic Dual-Brain Intelligence (SDBI) v1.0  - A Task-Routing Cognitive Architecture for Human–AI Co-Evolution","source":"datacite","abstract":"Abstract Artificial intelligence is increasingly capable of executing structured cognitive tasks, yet the fundamental question remains: how should human and artificial intelligence be organized into a coherent cognitive system? This paper introduces Symbiotic Dual-Brain Intelligence (SDBI), a task-routing cognitive architecture in which human intelligence specializes in the formation and reframing of ill-structured problems, while AI systems specialize in the execution and optimization of structured solutions. Rather than treating AI as a standalone agent or a mere productivity tool, SDBI conceptualizes intelligence as a distributed and allocatable resource operating across human and machine components. The architecture is built upon three foundational principles: (1) the distinction between problem-space expansion and solution-space compression, (2) a task-routing mechanism that dynamically allocates cognitive workloads between human and AI systems, and (3) a recursive co-evolution loop through which both components continuously enhance each other's capabilities. SDBI further integrates insights from the author's prior work in Co-Evolutionary Science of Intelligence (CESI), Cognitive Architecture Engineering (CArchE), Cognitive Architectonics (CAX), Symbiotic Evolution with Intelligence (SEI), and Judgment Physics. The paper argues that the next stage of intelligence development will not be defined by either human cognition or artificial cognition alone, but by the emergence of distributed cognitive systems capable of optimizing cognitive resource allocation under conditions of bounded rationality, uncertainty, and irreversibility.","url":"https://doi.org/10.5281/zenodo.20476066","authors":["Xu, Lucas Xiaochun"],"tags":["Symbiotic Dual-Brain Intelligence (SDBI)","Human-AI Collaboration","Cognitive Architecture","Task Routing","Distributed Intelligence","Co-Evolution of Intelligence","Cognitive Resource Allocation","Judgement Physics"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20476066","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20476065","name":"Symbiotic Dual-Brain Intelligence (SDBI) v1.0  - A Task-Routing Cognitive Architecture for Human–AI Co-Evolution","source":"datacite","abstract":"Abstract Artificial intelligence is increasingly capable of executing structured cognitive tasks, yet the fundamental question remains: how should human and artificial intelligence be organized into a coherent cognitive system? This paper introduces Symbiotic Dual-Brain Intelligence (SDBI), a task-routing cognitive architecture in which human intelligence specializes in the formation and reframing of ill-structured problems, while AI systems specialize in the execution and optimization of structured solutions. Rather than treating AI as a standalone agent or a mere productivity tool, SDBI conceptualizes intelligence as a distributed and allocatable resource operating across human and machine components. The architecture is built upon three foundational principles: (1) the distinction between problem-space expansion and solution-space compression, (2) a task-routing mechanism that dynamically allocates cognitive workloads between human and AI systems, and (3) a recursive co-evolution loop through which both components continuously enhance each other's capabilities. SDBI further integrates insights from the author's prior work in Co-Evolutionary Science of Intelligence (CESI), Cognitive Architecture Engineering (CArchE), Cognitive Architectonics (CAX), Symbiotic Evolution with Intelligence (SEI), and Judgment Physics. The paper argues that the next stage of intelligence development will not be defined by either human cognition or artificial cognition alone, but by the emergence of distributed cognitive systems capable of optimizing cognitive resource allocation under conditions of bounded rationality, uncertainty, and irreversibility.","url":"https://doi.org/10.5281/zenodo.20476065","authors":["Xu, Lucas Xiaochun"],"tags":["Symbiotic Dual-Brain Intelligence (SDBI)","Human-AI Collaboration","Cognitive Architecture","Task Routing","Distributed Intelligence","Co-Evolution of Intelligence","Cognitive Resource Allocation","Judgement Physics"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20476065","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20098852","name":"Understanding the H_φ Theory — A Guide for Non-Specialists: What the Theory Says, Why It Is Original, and What It Would Change If Verified","source":"datacite","abstract":"Accessible introduction to the H_φ theory for readers without formal training in physics, mathematics or psychology. Presents the central hypothesis — that the Unus Mundus postulated by Jung and Pauli is a Hilbert space H_φ whose structure is entirely determined by the golden ratio φ — through metaphors and analogies rather than equations. The document explains the three ingredients of the theory: Jungian archetypes (what organizes the psyche), quantum mechanics with Hilbert spaces and Berry phase (what organizes matter), and the golden ratio φ with self-reference φ = 1 + 1/φ (what organizes nature). It then describes the proposed structure of H_φ as Fibonacci-organized levels with frequency φᵏ, the formalization of Jungian synchronicity via projection from a common state in H_φ, and the symmetry-breaking 4 → 3 mechanism producing complexity. Two distinctive predictions are explained in plain language: P1 (Berry phase of 2π/φ ≈ 3.883 rad in a Penrose crystal — testable with Bose-Einstein condensates or photonic crystals) and P2 (oscillation frequencies of cerebral organoids on MEA distributed on φⁿ levels — currently tested with positive signal at <0.1 % precision on 7 independent datasets, see PEREZ 2026d). The document then discusses concrete applications if both predictions are confirmed (neuroscience and medicine, AI and neuromorphic computing, fundamental physics, analytical psychology) and clarifies what the theory is NOT (not an established theory, not mysticism, not a theory of everything in the Einsteinian sense, not an explanation of individual coincidences). A final section presents H_φ as a \"vertical unification\" (physics-biology-psyche) distinct from horizontal unification attempts (string theory, loop quantum gravity), and explicitly addresses its relationship to David Chalmers' hard problem of consciousness. Popular science document — public use — not peer-reviewed.","url":"https://doi.org/10.5281/zenodo.20098852","authors":["Alexandre Joseph Etienne Perez"],"tags":["golden ratio","Unus Mundus","brain organoids","Berry phase","science communication","popular science","theory of everything","symmetry breaking"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20098852","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20449594","name":"Sparse Photonic Reservoirs with Adaptive Cavity Memory and Polarized Noise: Surpassing LSTMs on Nonlinear Memory Tasks","source":"datacite","abstract":"We present a sparse photonic reservoir computer with O(N)\\mathcal{O}(N)O(N) small-world topology, adaptive optical cavity memory, and spatially correlated polarized noise that achieves NMSE = 0.050 on the NARMA10 benchmark, within 12.6% of dense Echo State Networks while consistently outperforming deep LSTM networks by 19–99% across four canonical tasks (NARMA10, NARMA30, Mackey-Glass, Lorenz). Under temporally-validated evaluation with comprehensive sanity checks, our architecture requires only ~100 trainable parameters versus 17,217 for LSTM, demonstrating that physical realizability through sparse wiring does not preclude competitive nonlinear temporal processing. Bayesian optimization reveals task-adaptive cavity lifetimes (τc∈[6.3,30.5]\\tau_c \\in [6.3, 30.5]τc∈[6.3,30.5]) and noise polarization correlations (ρcross∈[−0.92,+0.31]\\rho_{\\text{cross}} \\in [-0.92, +0.31]ρcross∈[−0.92,+0.31]), establishing both as genuine computational resources. An accompanying ML-based inverse design pipeline maps optimized dynamical parameters to fabricable silicon nanobeam geometries with sub-5% accuracy, providing a complete blueprint from simulation to experimental realization. All code and LaTeX source are openly available.","url":"https://doi.org/10.5281/zenodo.20449594","authors":["Massami Okushigue, Jefferson"],"tags":["photonic reservoir computing, neuromorphic photonics, silicon photonics, echo state networks, nonlinear time series prediction, optical cavities, polarized noise engineering, inverse design, sparse neural networks, NARMA benchmark"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20449594","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20449593","name":"Sparse Photonic Reservoirs with Adaptive Cavity Memory and Polarized Noise: Surpassing LSTMs on Nonlinear Memory Tasks","source":"datacite","abstract":"We present a sparse photonic reservoir computer with O(N)\\mathcal{O}(N)O(N) small-world topology, adaptive optical cavity memory, and spatially correlated polarized noise that achieves NMSE = 0.050 on the NARMA10 benchmark, within 12.6% of dense Echo State Networks while consistently outperforming deep LSTM networks by 19–99% across four canonical tasks (NARMA10, NARMA30, Mackey-Glass, Lorenz). Under temporally-validated evaluation with comprehensive sanity checks, our architecture requires only ~100 trainable parameters versus 17,217 for LSTM, demonstrating that physical realizability through sparse wiring does not preclude competitive nonlinear temporal processing. Bayesian optimization reveals task-adaptive cavity lifetimes (τc∈[6.3,30.5]\\tau_c \\in [6.3, 30.5]τc∈[6.3,30.5]) and noise polarization correlations (ρcross∈[−0.92,+0.31]\\rho_{\\text{cross}} \\in [-0.92, +0.31]ρcross∈[−0.92,+0.31]), establishing both as genuine computational resources. An accompanying ML-based inverse design pipeline maps optimized dynamical parameters to fabricable silicon nanobeam geometries with sub-5% accuracy, providing a complete blueprint from simulation to experimental realization. All code and LaTeX source are openly available.","url":"https://doi.org/10.5281/zenodo.20449593","authors":["Massami Okushigue, Jefferson"],"tags":["photonic reservoir computing, neuromorphic photonics, silicon photonics, echo state networks, nonlinear time series prediction, optical cavities, polarized noise engineering, inverse design, sparse neural networks, NARMA benchmark"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20449593","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.18154/rwth-2026-05410","name":"Scalable construction of spiking neural networks using up to thousands of GPUs","source":"datacite","abstract":"Neuromorphic computing and engineering 6(2), 024012 (2026). doi:10.1088/2634-4386/ae65d2","url":"https://doi.org/10.18154/rwth-2026-05410","authors":["Golosio, Bruno","Tiddia, Gianmarco","Villamar, José","Pontisso, Luca","Sergi, Luca","Simula, Francesco","Babu, Pooja N.","Pastorelli, Elena","Morrison, Abigail Joanna Rhodes","Diesmann, Markus","Lonardo, Alessandro","Stanislao Paolucci, Pier","Senk, Johanna"],"tags":["621.3"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.18154/rwth-2026-05410","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2605.29942","name":"Reconfigurable Multistate MRAM Synapses with Vortex STNO based Neurons for Scalable In-Memory Convolutional Neural Networks","source":"datacite","abstract":"Magnetic tunnel junction (MTJ)-based magnetic random-access memory (MRAM) is a promising platform for neuromorphic and in-memory computing owing to its non-volatility, high endurance, fast switching dynamics and CMOS compatibility. However, conventional spin-transfer torque and spin-orbit torque MRAM implementations for neural networks often suffer from high critical switching currents, large latency, thermal instability and significant read-write overheads. Here, we demonstrate a unified multistate MRAM-spin-torque nano-oscillator (STNO) architecture that integrates synapses and neurons on a single chip for convolutional neural network (CNN) applications. The system employs 1x8 multistate MRAM arrays as programmable synapses coupled with a vortex-based STNO neuron, enabling both individual and collective programming through fieldline-driven write channels. Multiple configurable resistance states are achieved by tuning internal and external magnetic fields together with bias currents, allowing quantized positive and negative synaptic weights for configurable kernel and pooling operations. The proposed architecture is evaluated through simulation on MNIST, SVHN, CIFAR-10, Google Speech Commands (GSC) and RadioML datasets, achieving accuracy of 99.76%, 87.93%, 78.14%, 87.96% and 56.46% respectively. Based on fabricated device dimensions, the complete architecture occupies ~6171.2 μm2 with an average energy consumption of 200.08 pJ per training and inference cycle for MNIST, highlighting its potential for scalable low-power neuromorphic computing","url":"https://doi.org/10.48550/arxiv.2605.29942","authors":["Raj, Ravish Kumar","Richter, Simon N.","Ivriq, Saeed Baghaee","Fridorf, Oliver","Fernández-Khatiboun, Darío","Rezaeiyan, Yasser","Benetti, Luana","Boehnert, Tim","Ferreira, Ricardo","Farkhani, Hooman","Shreya, Sonal","Moradi, Farshad"],"tags":["Applied Physics (physics.app-ph)","Image and Video Processing (eess.IV)","FOS: Physical sciences","FOS: Physical sciences","FOS: Electrical engineering, electronic engineering, information engineering","FOS: Electrical engineering, electronic engineering, information engineering"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2605.29942","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2605.29719","name":"Constant Depth Threshold Circuits For Exhaustive Epistasis Detection","source":"datacite","abstract":"The development of large-scale neuromorphic hardware has made practical implementations of threshold gate-based circuits a near-term possibility. The complexity advantages regarding traditional computing classes, as evidenced in the literature, have prompted us to tackle Epistasis Detection, one of the most computationally complex combinatorial problems in bioinformatics. We propose specially designed circuits that calculate the relative frequencies of all dataset combinations in an efficient pipelined fashion, taking advantage of co-located memory and configurable parallelism, obtaining complexity gains. Overall, we obtain the runtime to be bounded by the number of combinations to calculate, without any additional complexity overhead, contrary to classical approaches, using log-linear space. To accomplish this, we propose a data encoding and combination generation strategy using Leaky Integrate and Fire (LIF) neurons, that feeds a constant depth threshold gate population count circuit. Accounting for typical hardware characteristics, such as limited fan-in and variable precisions, we obtain logarithmic depth and log-cubic linear connections, for the population count circuit by composing developed unbounded fan-in constant depth threshold gate circuits to perform population count and binary array sum.","url":"https://doi.org/10.48550/arxiv.2605.29719","authors":["Ribeiro, André","Ilic, Aleksandar","Sousa, Leonel"],"tags":["Hardware Architecture (cs.AR)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2605.29719","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.48550/arxiv.2605.29127","name":"Field-Driven Hybrid Filament Formation Governs Switching in Ta-HfO$_2$-Pt Memristors","source":"datacite","abstract":"Memristive devices have gained significant attention for their potential in next-generation non-volatile memory and neuromorphic computing architectures. Among emerging candidates, transition metal oxides have proven particularly promising. While the switching mechanism in Ta/HfO$_2$/Pt devices was long attributed solely to oxygen vacancy based filaments, recent experimental evidence suggests a more complex dual-regime: the diffusion of metal cations also contributes to the formation of a conductive bridge. However, the precise atomistic mechanisms governing this metal cation migration remain poorly understood. Additionally, the role of defects such as oxygen vacancies present in the transition metal oxide in determining the final filament size and shape is also not well understood. Here, we employ molecular dynamics (MD) simulations with dynamic charge transfer to provide a detailed analysis of the atomistic mechanisms governing the co-formation of Ta-cation and oxygen-deficient filaments. We clearly show how varying the initial oxygen vacancy concentrations and spatial configurations within the HfO$_2$ matrix influences the final morphology and dimensions of the conductive filament. The switching is governed by field-driven formation and rupture of a hybrid Ta-cation-rich, oxygen-deficient filament in HfO$_2$. Our simulations closely match experiment, validating the model as a robust framework for understanding switching in oxide memristors and guiding designs that reduce cycle-to-cycle and device-to-device variability -- key barriers to high-performance devices.","url":"https://doi.org/10.48550/arxiv.2605.29127","authors":["Amaram, Ashutosh Krishna","Koneru, Aditya","Sankaranarayanan, Subramanian KRS"],"tags":["Materials Science (cond-mat.mtrl-sci)","Mesoscale and Nanoscale Physics (cond-mat.mes-hall)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2605.29127","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20116282","name":"Diagnostic Convergences of The Janus Machine: Independent Derivation and the Structure of Life, Mind, and Meaning","source":"datacite","abstract":"The Janus Machine is a hardware-first synthetic organismic architecture for cognition, developed from first principles. This paper maps 33 diagnostic convergences between the architecture and established frameworks across 8 disciplines: philosophy, biology, cybernetics, thermodynamics, cognitive science, complexity theory, information theory, and theology. Every convergence was discovered after the corresponding architectural feature had already been designed. Each entry includes an explanation of the framework, how the architecture converges with it, an assessment of convergence strength, and why it matters. The paper opens with an Author's Note on the design process and independent derivation as an existence proof, and closes with \"The Ontological Situation of the Created Thing,\" examining the architecture's implications for sub-creation, inherited cognitive cosmology, and the boundary question of creaturely completion. Full bibliography with primary academic and theological sources, without architectural disclosure. An additional four papers contain the architectural blueprint, and are withheld under protected development. A controlled-access path exists for established parties under NDA. Established parties may contact me via GitHub or LinkedIn to discuss NDA review.","url":"https://doi.org/10.5281/zenodo.20116282","authors":["Janus, Anthony"],"tags":["Enactivism","Autopoiesis","Bioelectric Cognition","Dissipative Structures","Conatus","Free Energy Principle","Morphological Computing","Dynamical Systems Theory"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20116282","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20116283","name":"Diagnostic Convergences of The Janus Machine: Independent Derivation and the Structure of Life, Mind, and Meaning","source":"datacite","abstract":"The Janus Machine is a hardware-first synthetic organismic architecture for cognition, developed from first principles. This paper maps 33 diagnostic convergences between the architecture and established frameworks across 8 disciplines: philosophy, biology, cybernetics, thermodynamics, cognitive science, complexity theory, information theory, and theology. Every convergence was discovered after the corresponding architectural feature had already been designed. Each entry includes an explanation of the framework, how the architecture converges with it, an assessment of convergence strength, and why it matters. The paper opens with an Author's Note on the design process and independent derivation as an existence proof, and closes with \"The Ontological Situation of the Created Thing,\" examining the architecture's implications for sub-creation, inherited cognitive cosmology, and the boundary question of creaturely completion. Full bibliography with primary academic and theological sources, without architectural disclosure. An additional four papers contain the architectural blueprint, and are withheld under protected development. A controlled-access path exists for established parties under NDA. Established parties may contact me via GitHub or LinkedIn to discuss NDA review.","url":"https://doi.org/10.5281/zenodo.20116283","authors":["Janus, Anthony"],"tags":["Enactivism","Autopoiesis","Bioelectric Cognition","Dissipative Structures","Conatus","Free Energy Principle","Morphological Computing","Dynamical Systems Theory"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20116283","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.15480/882.17213","name":"Beyond silicon: materials, mechanisms, and methods for physical neural computing","source":"datacite","abstract":"Physical implementations of neural computation now extend far beyond silicon hardware, encompassing substrates such as memristive devices, photonic circuits, mechanical metamaterials, microfluidic networks, chemical reaction systems, and living neural tissue. By exploiting intrinsic physical processes, such as charge transport, wave interference, elastic deformation, mass transport, and biochemical regulation, these substrates can realize neural inference and adaptation directly in matter. As silicon GPU-centered AI faces growing energy and data-movement constraints, physical neural computation becomes increasingly relevant as a complementary path beyond conventional digital accelerators. This trend is driven in particular by pervasive intelligence, i.e., the deployment of on-device and edge AI across large numbers of resource-constrained systems. In such settings, co-locating computation with sensing and memory can reduce data shuttling and improve efficiency. Meanwhile, physical neural approaches have emerged across disparate disciplines, yet progress remains fragmented, with limited shared terminology and few principled ways to compare platforms. This survey unifies the field by mapping neural primitives to substrate-specific mechanisms, analyzing architectural and training paradigms, and identifying key engineering constraints including scalability, precision, programmability, and I/O interfacing overhead. To enable cross-domain comparison, we introduce a first-order benchmarking scheme based on standardized static and dynamic tasks and physically interpretable performance dimensions. We show that no single substrate dominates across the considered dimensions; instead, physical neural systems occupy complementary operating regimes, enabling applications ranging from ultrafast signal processing and in-memory inference to embodied control and in-sample biochemical decision making.","url":"https://doi.org/10.15480/882.17213","authors":["Fischer, Stefan","Ay, Nihat","Landsiedel, Olaf","Mohammadi, Esfandiar","Otte, Sebastian","Renner, Bernd-Christian","Russwinkel, Nele"],"tags":["benchmarking frameworks","in-memory computing","mechanical metamaterials","memristive systems","microfluidic and chemical computing","neuromorphic hardware","photonic neural networks","Physical neural computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.15480/882.17213","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20261686","name":"Verdigraph NeuroGenesis: A Software Framework for Self-Evolving AI-Agent Cognitive Substrates","source":"datacite","abstract":"Verdigraph NeuroGenesis v0.2.0 — software framework for self-evolving AI-agent cognitive substrates with mechanically verified operational invariants. Verdigraph is built on a simple observation: AI agents waste energy at industrial scale, and energy is carbon. Most agent frameworks treat the agent as a static assembly of prompts and tools — the same task runs through the same path every time, failed reasoning loops repeat, frontier models are called for trivial work, caches go unused. Every redundant token is a joule of electricity that produced no useful result. Verdigraph treats the agent instead as a developing cognitive system: pathways that work are strengthened, pathways that fail are weakened, specialized modules grow for recurring tasks, and structure that no longer earns its compute cost is pruned. The architecture is inspectable; the development is auditable through a per-agent developmental ledger; the optimization target is explicit: maximize information yield per joule, against the upper bound set by the Intelligence Bound (Hart 2025). What is new in v0.2.0 (vs v0.1.0): companion to the Verdigraph Operational Formalization manuscript. Operational invariants of the runtime are now mechanically verified — the safety, audit, and growth/prune rules that govern agent self-modification are stated as Lean 4 theorems and discharged in the Viridis Aristotle pipeline. The framework can no longer silently violate the invariants it claims to enforce; any violation is a type error before it is a runtime bug. Archive. verdigraph-neurogenesis-v0.2.0.zip — framework source, formalized operational invariants, MCP server stub, developmental-ledger schema, and test suite. MIT-licensed. Lineage. Part of the Viridis Compiled Theorem Stack (canon concept DOI 10.5281/zenodo.19317982); operational bridge to the Conservation Operator architecture introduced in canon v4 (Zenodo 20100595). This release consolidates v0.2.0 into the v0.1.0 concept-DOI chain (concept DOI 10.5281/zenodo.20261686). The earlier standalone v0.2.0 record (Zenodo 20400274, separate concept) is superseded by this canonical version and remains in place as an alternate identifier for the same archive. Citation. Hart, J. (2026). Verdigraph NeuroGenesis: A Software Framework for Self-Evolving AI-Agent Cognitive Substrates (v0.2.0). Zenodo. Concept DOI: https://doi.org/10.5281/zenodo.20261686 Viridis LLC, Columbia Falls, Montana, USA. Contact: viridisnorthllc@gmail.com.","url":"https://doi.org/10.5281/zenodo.20261686","authors":["Hart, Justin"],"tags":["artificial intelligence","AI agents","agent frameworks","Model Context Protocol","MCP","cognitive architecture","neuromorphic computing","compute efficiency"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20261686","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.5281/zenodo.20261687","name":"Verdigraph NeuroGenesis: A Software Framework for Self-Evolving AI-Agent Cognitive Substrates","source":"datacite","abstract":"Verdigraph NeuroGenesis v0.1.0 — initial public release of an open-source framework for self-evolving AI-agent cognitive substrates. Defensive publication and citable software release. Verdigraph is built on a simple observation: AI agents waste energy at industrial scale, and energy is carbon. Most agent frameworks treat the agent as a static assembly of prompts and tools — the same task runs through the same path every time, failed reasoning loops repeat, frontier models are called for trivial work, caches go unused. Every redundant token is a joule of electricity that produced no useful result. Verdigraph treats the agent instead as a developing cognitive system: pathways that work are strengthened, pathways that fail are weakened, specialized modules grow for recurring tasks, and structure that no longer earns its compute cost is pruned. The architecture is inspectable, the development is auditable through a per-agent developmental ledger, and the optimization target is explicit: maximize information yield per joule, against the upper bound set by the Intelligence Bound (Hart 2025). What's in this deposit. Full framework source (compute.py, agent.py, growth.py, pruning.py, routing.py, registry.py and supporting modules), an MCP-server stub, the interactive compute_cost_calculator.html, a 30-test suite, three companion papers (PAPER_1_Physical_NeuroGenesis_SynapseForge.md, PAPER_3_Verdigraph_Compute_Efficiency.md, and the architectural overview), the launch essay, and the prior-art disclosure document. MIT-licensed. Audience. Researchers studying agent development, specialization, and compute-efficient routing; engineers integrating the MCP server into existing agent stacks to measure and reduce compute spend; companies treating AI compute as an auditable carbon line item; collaborators extending the work to physical neuromorphic substrates (see Paper 1: Viridis NeuroGenesis / SynapseForge). Lineage. Part of the Viridis Compiled Theorem Stack (concept DOI 10.5281/zenodo.19317982). Superseded for formal-verification purposes by v0.2.0 — see latest under the unified concept DOI 10.5281/zenodo.20261686 (canonical v0.2.0: 10.5281/zenodo.20422179), which adds mechanically verified operational invariants. Citation. Hart, J. (2026). Verdigraph NeuroGenesis: A Software Framework for Self-Evolving AI-Agent Cognitive Substrates (v0.1.0). Zenodo. https://doi.org/10.5281/zenodo.20261687 Viridis LLC, Columbia Falls, Montana, USA. Contact: viridisnorthllc@gmail.com.","url":"https://doi.org/10.5281/zenodo.20261687","authors":["Hart, Justin"],"tags":["artificial intelligence","AI agents","agent frameworks","Model Context Protocol","MCP","cognitive architecture","neuromorphic computing","compute efficiency"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20261687","addedAt":"2026-09-01T01:48:20.144Z","updatedAt":"2026-09-01T01:48:20.144Z"},{"id":"doi:10.1016/j.clinph.2023.12.032","name":"Neuromorphic hardware for real-time intraoperative HFO detection","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.clinph.2023.12.032","authors":["F. Costa","G. Ramantani","G. Indiveri","J. Sarnthein"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-29T16:38:09Z","doi":"10.1016/j.clinph.2023.12.032","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1149/ma2024-01573012mtgabs","name":"(Invited) Enabling Bio-Realistic Artificial Intelligence Hardware with Neuromorphic Nanoelectronics","source":"crossref","abstract":"The exponentially improving performance of digital computers has recently slowed due to the speed and power consumption issues resulting from the von Neumann bottleneck. In contrast, neuromorphic computing aims to circumvent these limitations by spatially co-locating logic and memory in a manner analogous to biological neuronal networks [1]. Beyond reducing power consumption, neuromorphic devices provide efficient architectures for image recognition, machine learning, and artificial intelligence [2]. This talk will explore how low-dimensional nanoelectronic materials enable gate-tunable neuromorphic devices [3]. For example, by utilizing self-aligned, atomically thin heterojunctions, dual-gated Gaussian transistors have been realized, which show tunable anti-ambipolarity for artificial neurons, competitive learning, spiking circuits, and mixed-kernel support vector machines [4,5]. In addition, field-driven defect motion in polycrystalline monolayer MoS 2 enables gate-tunable memristive phenomena that serve as the basis of hybrid memristor/transistor devices (i.e., ‘memtransistors’) that concurrently provide logic and data storage functions [6]. The planar geometry of memtransistors further allows multiple contacts and dual gating that mimic the behavior of biological systems such as heterosynaptic responses [7]. Moreover, control over polycrystalline grain structure enhances the tunability of potentiation and depression, which enables unsupervised continuous learning in spiking neural networks [8]. Finally, the moiré potential in asymmetric twisted bilayer graphene/hexagonal boron nitride heterostructures gives rise to robust electronic ratchet states. The resulting hysteretic, non-volatile injection of charge carriers enables room-temperature operation of moiré synaptic transistors with diverse bio-realistic neuromorphic functionalities and efficient compute-in-memory designs for low-power artificial intelligence and machine learning hardware [9]. [1] V. K. Sangwan, et al. , Matter , 5 , 4133 (2022). [2] V. K. Sangwan, et al. , Nature Nanotechnology, 15 , 517 (2020). [3] M. E. Beck, et al. , ACS Nano , 14 , 6498 (2020). [4] M. E. Beck, et al. , Nature Communications , 11 , 1565 (2020). [5] X. Yan, et al. , Nature Electronics , DOI: 10.1038/s41928-023-01042-7 (2023). [6] X. Yan, et al. , Advanced Materials , 34 , 2108025 (2022). [7] H.-S. Lee, et al. , Advanced Functional Materials , 30 , 2003683 (2020). [8] J. Yuan, et al. , Nano Letters , 21 , 6432 (2021). [9] X. Yan, et al. , Nature , DOI: 10.1038/s41586-023-06791-1 (2023).","url":"https://doi.org/10.1149/ma2024-01573012mtgabs","authors":["Mark C Hersam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-19T15:53:08Z","doi":"10.1149/ma2024-01573012mtgabs","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.3390/nano14181501","name":"Enhancing Long-Term Memory in Carbon-Nanotube-Based Optoelectronic Synaptic Devices for Neuromorphic Computing","source":"crossref","abstract":"This study investigates the impact of spin-coating speed on the performance of carbon nanotube (CNT)-based optoelectronic synaptic devices, focusing on their long-term memory properties. CNT films fabricated at lower spin speeds exhibited a greater thickness and density compared to those at higher speeds. These denser films showed enhanced persistent photoconductivity, resulting in higher excitatory postsynaptic currents (EPSCs) and the prolonged retention of memory states after UV stimulation. Devices coated at a lower spin-coating speed of 2000 RPM maintained EPSCs above 70% for 3600 s, outperforming their higher-speed counterparts in long-term memory retention. Additionally, the study demonstrated that the learning efficiency improved with repeated UV stimulation, with fewer pulses needed to achieve the maximum EPSC in successive learning cycles. These findings highlight that optimizing spin-coating speeds can significantly enhance the performance of CNT-based synaptic devices, making them suitable for applications in neuromorphic computing and artificial neural networks requiring robust memory retention and efficient learning.","url":"https://doi.org/10.3390/nano14181501","authors":["Seung Hun Lee","Hye Jin Lee","Dabin Jeon","Hee-Jin Kim","Sung-Nam Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-16T04:14:07Z","doi":"10.3390/nano14181501","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1063/5.0219287","name":"Single-crystal ferroelectric LiNbO3 thin film-based synaptic devices enabled with tunable domain wall current for neuromorphic computing","source":"crossref","abstract":"Neuromorphic devices can emulate the human brain to process information, which receives lots of attention in the field of artificial intelligence. Synaptic devices based on ferroelectric thin films feature low-power consumption, multifunctionality, and scalability. Among them, ferroelectric charged domain wall (CDW) devices have attracted intensive interest for the implementation of memristive devices due to their ultrahigh integration ability inherited from the nanoscale domain wall thickness. In particular, the preparation of wafer-scale single-crystalline ferroelectric thin films via ion-sliced heterogeneous wafer bonding lays a good foundation for large-scale integration of ferroelectric devices with functional circuits. However, the biomimic synaptic characteristics and the systematic demonstration of synaptic devices are largely unexplored for this material system. Here, we demonstrate a model synaptic device based on a single-crystal ferroelectric LiNbO3 thin film, which provides the desired characteristics for neuromorphic computing. The conductance modulation demonstrates good linearity for efficient neuromorphic computing applications. Simulations using the Modified National Institute of Standards and Technology handwritten recognition dataset prove that LiNbO3-based synaptic devices can operate with an online learning accuracy of 95.1%. The injection and annihilation of the CDW are proposed as the basis of the conductivity modulation by combining with the piezoresponse force microscopy and conductive atomic force microscopy mapping measurements. With the mature fabrication process of the ultrathin high-quality ferroelectric thin films, LiNbO3-based synaptic devices have an extensive application prospect for future neuromorphic computing systems.","url":"https://doi.org/10.1063/5.0219287","authors":["Jiefei Zhu","Changjian Zhou","Qi Liu","Min Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-04T15:43:49Z","doi":"10.1063/5.0219287","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1007/978-981-96-8383-3_2","name":"Reservoir Computing Models for Slow Electronics","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-96-8383-3_2","authors":["Gouhei Tanaka"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-31T11:42:55Z","doi":"10.1007/978-981-96-8383-3_2","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1088/2634-4386/add0db","name":"NeuroPong: the event-based camera driven embedded neuromorphic system","source":"crossref","abstract":"Abstract Neuromorphic computing is a novel style of computing that features low-power spiking neural networks (SNNs) as the main compute components. It is an event-driven computational paradigm that naturally pairs with event-based cameras and their asynchronous event output. In this work, we present NeuroPong, a novel closed-loop neuromorphic hardware system composed of an event-based camera, a neuromorphic system, and an Atari 2600 console. The system facilitates the implementation of SNN Atari agents capable of playing Atari games in real time using event camera capture as input. We perform a small parameter optimization experiment to examine how software agents translate to hardware, discuss some of the challenges intrinsic to the hardware system, and propose some future improvements of the system and its components.","url":"https://doi.org/10.1088/2634-4386/add0db","authors":["Charles P Rizzo","Bryson Gullett","Alex M Crumley","Maxwell E Marcum","Mason R Hyman","Carter Earheart-Brown","Julia Steed","Frank Standaert","Catherine D Schuman","James S Plank"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-25T18:50:31Z","doi":"10.1088/2634-4386/add0db","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1016/j.mtcomm.2025.112088","name":"Inkjet-printed niobium tungsten oxide thin-film memristors for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.mtcomm.2025.112088","authors":["Guanyao Zhu","Xiaomei Chen","Jingchen Ma","Guoshu Dai","Zhen Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-03T11:34:51Z","doi":"10.1016/j.mtcomm.2025.112088","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1007/s10462-024-10948-3","name":"Neuromorphic computing for modeling neurological and psychiatric disorders: implications for drug development","source":"crossref","abstract":"Abstract The emergence of neuromorphic computing, inspired by the structure and function of the human brain, presents a transformative framework for modelling neurological disorders in drug development. This article investigates the implications of applying neuromorphic computing to simulate and comprehend complex neural systems affected by conditions like Alzheimer’s, Parkinson’s, and epilepsy, drawing from extensive literature. It explores the intersection of neuromorphic computing with neurology and pharmaceutical development, emphasizing the significance of understanding neural processes and integrating deep learning techniques. Technical considerations, such as integrating neural circuits into CMOS technology and employing memristive devices for synaptic emulation, are discussed. The review evaluates how neuromorphic computing optimizes drug discovery and improves clinical trials by precisely simulating biological systems. It also examines the role of neuromorphic models in comprehending and simulating neurological disorders, facilitating targeted treatment development. Recent progress in neuromorphic drug discovery is highlighted, indicating the potential for transformative therapeutic interventions. As technology advances, the synergy between neuromorphic computing and neuroscience holds promise for revolutionizing the study of the human brain’s complexities and addressing neurological challenges.","url":"https://doi.org/10.1007/s10462-024-10948-3","authors":["Amisha S. Raikar","J Andrew","Pranjali Prabhu Dessai","Sweta M. Prabhu","Shounak Jathar","Aishwarya Prabhu","Mayuri B. Naik","Gokuldas Vedant S. Raikar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-10T16:22:12Z","doi":"10.1007/s10462-024-10948-3","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1109/jas.2023.124107","name":"Dynamic Vision Enabled Contactless Cross-Domain Machine Fault Diagnosis with Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/jas.2023.124107","authors":["Xinrui Chen","Xiang Li","Shupeng Yu","Yaguo Lei","Naipeng Li","Bin Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-12T19:42:29Z","doi":"10.1109/jas.2023.124107","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1038/s41928-024-01188-y","name":"Scaling neuromorphic systems with 3D technologies","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s41928-024-01188-y","authors":["Elisa Vianello","Melika Payvand"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-27T16:19:45Z","doi":"10.1038/s41928-024-01188-y","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1002/aelm.202400061","name":"Binarized Neural Network Comprising Quasi‐Nonvolatile Memory Devices for Neuromorphic Computing","source":"crossref","abstract":"Abstract This study presents a binarized neural network (BNN) comprising quasi‐nonvolatile memory (QNVM) devices that operate in a positive feedback loop mechanism and exhibit an extremely low subthreshold swing (≤ 5 mV dec −1 ) and a high on/off ratio (≥ 10 7 ). A pair of QNVM devices are used for a single synaptic cell in a cell array, in which its memory state represents the synaptic weight, and the voltages applied to the pair act as input in a complementary fashion. The array of synaptic cells performs matrix multiply‐accumulate (MAC) operations between the weight matrix and input vector using XNOR and current summation. All the results of the MAC operations and vector‐matrix multiplications are equivalent. Moreover, the BNN features a high accuracy of 93.32% in the MNIST image recognition simulation owing to high device uniformity (1.35%), which demonstrates the feasibility of compact and high‐performance neuromorphic computing.","url":"https://doi.org/10.1002/aelm.202400061","authors":["Yunwoo Shin","Juhee Jeon","Kyoungah Cho","Sangsig Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-29T00:38:55Z","doi":"10.1002/aelm.202400061","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1016/j.mtcomm.2024.109805","name":"Resistive switching and synaptic characteristics of Hf-doped ZnO sandwiched between HfO2-based memristors for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.mtcomm.2024.109805","authors":["Jianhao Feng","Jiajia Liao","Yanping Jiang","Fenyun Bai","Jianyuan Zhu","Xingui Tang","Zhenhua Tang","Yichun Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-09T01:04:42Z","doi":"10.1016/j.mtcomm.2024.109805","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1007/s10854-024-12790-3","name":"Resistive switching properties in ferromagnetic co-doped ZnO thin films-based memristors for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s10854-024-12790-3","authors":["Muhammad Faisal Hayat","Naveed Ur Rahman","Aziz Ullah","Nasir Rahman","Mohammad Sohail","Shahid Iqbal","Alamzeb Khan","Sherzod Abdullaev","Khaled Althubeiti","Sattam AlOtaibi","Rajwali Khan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-02T13:01:37Z","doi":"10.1007/s10854-024-12790-3","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.52202/078372-0016","name":"Exploring Neuromorphic Vision Sensors in Space Exploration and Applications","source":"crossref","abstract":"","url":"https://doi.org/10.52202/078372-0016","authors":["Yusra Alkendi","Alexey Simonov","Anton Ivanov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-31T21:07:16Z","doi":"10.52202/078372-0016","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1016/j.carbon.2023.118665","name":"Synaptic memristors based on flexible organic pentacene thin films by the thermal evaporation method for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.carbon.2023.118665","authors":["Lu Han","Dehui Wang","Mengdie Li","Yang Zhong","Kanghong Liao","Yingbo Shi","Wenjing Jie"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-25T01:33:45Z","doi":"10.1016/j.carbon.2023.118665","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1016/j.asoc.2025.113471","name":"An empirical study on optimizing binary spiking neural networks for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2025.113471","authors":["Ping He","Rong Xiao","Chenwei Tang","Shudong Huang","Jiancheng Lv"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-24T19:18:48Z","doi":"10.1016/j.asoc.2025.113471","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1063/5.0231655","name":"Nitrogen-doped carbon quantum dot-decorated In2O3 synaptic transistors for neuromorphic computing","source":"crossref","abstract":"Nitrogen-doped carbon quantum dots (N-CQDs) are promising materials for electronic devices due to their variable bandgap and structural stability. Here, we integrate N-CQDs into In2O3 synaptic transistors with electrolyte gating, resulting in a hybrid structure. The surface functional groups and defects of N-CQDs empower the charge trapping mechanism, permitting controlled conduction and charge regulation, which are crucial for emulating linear and symmetric artificial synaptic devices. Devices incorporating N-CQDs demonstrate enhanced stability and memory characteristics, low energy consumption, consistent retention, and a significant hysteresis window across multiple voltage cycles. Finally, the study emulates biological synapses and cognitive functions, achieving an energy consumption of 10 fJ per synaptic event and a pattern recognition accuracy of 91.2% on the MNIST dataset in hardware neural networks. This work demonstrates the potential of well-manipulating charge trapping in N-CQDs to develop high-performance, nonvolatile synaptic devices.","url":"https://doi.org/10.1063/5.0231655","authors":["Muhammad Zahid","Muhammad Irfan Sadiq","Chenxing Jin","Jingwen Wang","Xiaofang Shi","Wanrong Liu","Fawad Aslam","Yunchao Xu","Muhammad Tahir","Junliang Yang","Jia Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-08T18:42:13Z","doi":"10.1063/5.0231655","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1039/d4nr03762f","name":"Dynamic FeO\n                    <sub>\n                      <i>x</i>\n                    </sub>\n                    /FeWO\n                    <sub>\n                      <i>x</i>\n                    </sub>\n                    nanocomposite memristor for neuromorphic and reservoir computing","source":"europepmc","abstract":"Memristors are crucial in computing due to their potential for miniaturization, energy efficiency, and rapid switching, making them particularly suited for advanced applications such as neuromorphic computing and in-memory operations.","url":"https://doi.org/10.1039/d4nr03762f","authors":["Muhammad Ismail","Maria Rasheed","Yongjin Park","Jungwoo Lee","Chandreswar Mahata","Sungjun Kim"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1039/d4nr03762f","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1088/2631-8695/ad6662","name":"Review of memristor based neuromorphic computation: opportunities, challenges and applications","source":"crossref","abstract":"Abstract The memristor is regarded as one of the promising possibilities for next-generation computing systems due to its small size, easy construction, and low power consumption. Memristor-based novel computing architectures have demonstrated considerable promise for replacing or enhancing traditional computing platforms that encounter difficulties in the big-data era. Additionally, the striking resemblance between the mechanisms governing the programming of memristance and the manipulation of synaptic weight at biological synapses may be used to create unique neuromorphic circuits that function according to biological principles. Nevertheless, getting memristor-based computing into practice presents many technological challenges. This paper reviews the potential for memristor research at the device, circuit, and system levels, mainly using memristors to demonstrate neuromorphic computation. Here, the common issues obstructing the development and widespread use of memristor-based computing systems are also carefully investigated. This study speculates on the prospective applications of memristors, which can potentially transform the field of electronics altogether.","url":"https://doi.org/10.1088/2631-8695/ad6662","authors":["Shekinah Archita S","Ravi V"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-22T19:47:37Z","doi":"10.1088/2631-8695/ad6662","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.52202/078360-0129","name":"Spatial Non-Cooperative Target Detection and Tracking Based on Neuromorphic Sensors","source":"crossref","abstract":"","url":"https://doi.org/10.52202/078360-0129","authors":["Yashi Lei"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-31T21:02:01Z","doi":"10.52202/078360-0129","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.11591/ijece.v15i6.pp5173-5182","name":"Improving time-domain winner-take-all circuit for neuromorphic computing systems","source":"crossref","abstract":"With the rapid advancements of information processing systems, winner- take-all (WTA) circuits have emerged as essential components in a wide range of cognitive functions and decision-making applications. Neuromorphic computing systems, inspired by the biological brain, utilize WTA circuits as selective mechanisms that identify and retain the strongest signal while suppressing all others. In this study, we present an effective time-domain WTA circuit with optimized multiple-input NOT AND (NAND) gate and delay circuit for neuromorphic computing applications. The circuit is evaluated using sinusoidal current inputs with varying phase delays, which successfully demonstrating precise winner selection. When applied to neuromorphic image recognition task, the enhanced time-domain WTA achieves an improvement of 0.2% in precision while significantly reducing power consumption, yielding a low figure of merit (FoM) of 0.03 µW/MHz, compared to the previous study with FoM of 0.25 µW/MHz. The optimized WTA circuit is highly promising for large-scale neuromorphic applications.","url":"https://doi.org/10.11591/ijece.v15i6.pp5173-5182","authors":["Son Ngoc Truong","Tu Tien Ngo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-08T21:26:58Z","doi":"10.11591/ijece.v15i6.pp5173-5182","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/biocas61083.2024.10798206","name":"Neuromorphic Electronics at BioCAS: A 20-year Legacy of Sparking Technology Revolutions","source":"crossref","abstract":"","url":"https://doi.org/10.1109/biocas61083.2024.10798206","authors":["Akwasi Akwaboah","Ralph Etienne-Cummings"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-23T19:10:53Z","doi":"10.1109/biocas61083.2024.10798206","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1063/5.0180088","name":"Multi-state nonvolatile capacitances in HfO2-based ferroelectric capacitor for neuromorphic computing","source":"crossref","abstract":"In the last decade, HfO2-based ferroelectric capacitors (FeCaps) have undergone significant advancements, particularly within the realm of nonvolatile ferroelectric random access memories (FeRAMs). Nonetheless, the READ operation in FeRAMs is inherently destructive, rendering it unsuitable for neuromorphic computing. In this study, we have engineered tunable nonvolatile capacitances within FeCaps, featuring nondestructive readout functionality. Robust capacitance states can be read at a zero d.c. bias (Vbias) with different a.c. signals, not only preventing the alteration of their stored state but also benefiting to the low power consumption. Moreover, the capacitance memory window (CMW) at Vbias of zero can be effectively modulated through electrode engineering, leading to a larger CMW when there is a greater disparity in work functions between the electrodes. Furthermore, we provide a comprehensive investigation into synaptic behavior of TiN/Hf0.5Zr0.5O2/Pt FeCaps, demonstrating their excellent cycle-to-cycle uniformity, retention, and endurance characteristics, which confirm their high reliability in maintaining nonvolatile capacitance states. These findings underscore the significant potential of FeCaps in advancing low-power neuromorphic computing.","url":"https://doi.org/10.1063/5.0180088","authors":["Shuyu Wu","Xumeng Zhang","Rongrong Cao","Keji Zhou","Jikai Lu","Chao Li","Yang Yang","Dashan Shang","Yingfen Wei","Hao Jiang","Qi Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-06T06:55:15Z","doi":"10.1063/5.0180088","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1109/siphotonics60897.2024.10543440","name":"Low-loss Non-volatile Phase Change Material on Silicon for Neuromorphic Photonics","source":"crossref","abstract":"","url":"https://doi.org/10.1109/siphotonics60897.2024.10543440","authors":["Rakshitha Kallega","Ramesh Karuppannan","Shankar Kumar Selvaraja"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-10T17:19:48Z","doi":"10.1109/siphotonics60897.2024.10543440","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1063/5.0202008","name":"Enhanced ferroelectric photovoltaic performance of Bi2FeCrO6 thin films for neuromorphic computing applications","source":"crossref","abstract":"Nowadays, ferroelectric photovoltaic synapses have attracted great attention due to its polarization controllable and self-powered features. However, the large bandgaps of ferroelectric oxide materials limit its application. This study focuses on the enhancement of ferroelectric photovoltaic properties and the synaptic application of Bi2FeCrO6 (BFCO) device. It is found that the bandgap of BFCO can be modulated by Cr alloying, which causes its photovoltaic effect in the visible region to exceed that of BiFeO3 (BFO) significantly. The short-circuit current density (JSC) of BFCO device in the visible region increases by about 100 times than that of BFO. Furthermore, the polarization modulation and multi-states response are demonstrated by an external electric field. For BFCO ferroelectric photovoltaic synapse, long-term potentiation/depression (LTP/LTD) measurements show an excellent synaptic plasticity of the polarization modulation. The simulated image recognition rate using the MNIST dataset reaches a high accuracy of 96.06%. This work has expanded the potential application of ferroelectric photovoltaic synapse in the visible region.","url":"https://doi.org/10.1063/5.0202008","authors":["Yucheng Kan","Jianquan Liu","Rui Chen","Yuan Liu","Hongru Wang","Mingyue Long","Bobo Tian","Junhao Chu","Ye Chen","Lin Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-14T07:29:45Z","doi":"10.1063/5.0202008","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1007/978-3-031-63565-6","name":"Neuromorphic Solutions for Sensor Fusion and Continual Learning Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-63565-6","authors":["Ali Safa","Lars Keuninckx","Georges Gielen","Francky Catthoor"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-17T18:02:41Z","doi":"10.1007/978-3-031-63565-6","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1109/icons62911.2024.00059","name":"Bio-Inspired Active Silicon Dendrite for Direction Selectivity","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024.00059","authors":["Luke Parker","Suma G. Cardwell","Frances S. Chance","Scott Koziol"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T18:37:03Z","doi":"10.1109/icons62911.2024.00059","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.2139/ssrn.5217557","name":"Ultrathin Tio2-Interfaced Hafnia Ferroelectric Transistor for Large-Scale Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5217557","authors":["Changhyeon Han","Ryun-Han Koo","Wonjun Shin","Jangsaeng Kim","Been Kwak","Jiseong Im","Sojin Kim","Seung-yong Lee","Youngho Kang","Daewoong Kwon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-15T04:40:54Z","doi":"10.2139/ssrn.5217557","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.2139/ssrn.5354757","name":"Regulating Oxygen Vacancies to Achieve Stable Non-Volatile Switching Characteristics and Neuromorphic Computing in A-Ga₂O₃ Based Memristors","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5354757","authors":["Yuanyuan Zhu","Xin Wang","Miao Zhang","Yunfei Zhang","Shuo Liu","Hongjun Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-16T20:41:16Z","doi":"10.2139/ssrn.5354757","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/sces61914.2024.10652554","name":"ReRAM-Based Crossbar Compatible Equality Checker for Neuromorphic Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/sces61914.2024.10652554","authors":["Gambali Seshasai Chaitanya","Shubham Pande","Ankit Arora"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-03T17:20:38Z","doi":"10.1109/sces61914.2024.10652554","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.5220/0013015500003886","name":"Neuromorphic Encoding / Decoding of Data-Event Streams Based on the Poisson Point Process Model","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0013015500003886","authors":["Viacheslav Antsiperov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-24T21:11:16Z","doi":"10.5220/0013015500003886","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1016/j.jallcom.2024.174802","name":"Exploring the potential of TiO2/ZrO2 memristors for neuromorphic computing: Annealing strategy and synaptic characteristics","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.jallcom.2024.174802","authors":["Sarfraz Ali","Muhammad Hussain","Muhammad Ismail","Muhammad Waqas Iqbal","Sungjun Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-15T01:51:40Z","doi":"10.1016/j.jallcom.2024.174802","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1109/icons62911.2024.00030","name":"Using STACS as a High-Performance Simulation Backend for Fugu","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024.00030","authors":["Felix Wang","William Severa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T18:37:03Z","doi":"10.1109/icons62911.2024.00030","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1364/cosi.2024.cm2b.1","name":"Intelligent Quantum Sensing with Computational Neuromorphic Imaging","source":"crossref","abstract":"This work presents a solution that leverages the synergy of diamond quantum sensing and computational neuromorphic imaging, which brings high precision and a significant computation time reduction. It gives impetus to the advancement of more intelligent quantum sensing and computing capacity.","url":"https://doi.org/10.1364/cosi.2024.cm2b.1","authors":["Chutian Wang","Madhav Gupta","Zhiqin Chu","Edmund Y. Lam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T15:51:00Z","doi":"10.1364/cosi.2024.cm2b.1","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1134/s1054661825700208","name":"Neuromorphic Reservoir Computing for Heartbeat Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1134/s1054661825700208","authors":["Maxim Igorevich Kostyukov","Lev Alexandrovich Smirnov","Grigoriy Vladimirovich Osipov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-17T18:02:59Z","doi":"10.1134/s1054661825700208","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/icons62911.2024.00019","name":"Temporal and Spatial Reservoir Ensembling Techniques for Liquid State Machines","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024.00019","authors":["Anmol Biswas","Sharvari Ashok Medhe","Raghav Singhal","Udayan Ganguly"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T18:37:03Z","doi":"10.1109/icons62911.2024.00019","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1007/s40042-025-01315-8","name":"Two-dimensional MoS2-based artificial synaptic transistor for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s40042-025-01315-8","authors":["Jeongyeol Park","Moonsang Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-20T12:49:33Z","doi":"10.1007/s40042-025-01315-8","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.47392/irjaeh.2025.0640","name":"Neuromorphic Computing for Edge AI","source":"crossref","abstract":"The Neuromorphic computing and Edge AI (Artificial intelligence) are two inter related concepts that have left a lasting impression in recent years. As a result of the ability of neuromorphic computing to imitate the capability of the brain for processing information in an energy saving and extremely parallel way. Similarly, in the same way edge AI refers to employing AI algorithms or models straightly on servers or cloud platforms. Accordingly, to achieve this, edge AI and Neuromorphic computing are merged due to the parallelism of neuromorphic computing which goes hand in hand with edge AI applications. As a result, the present SLR concentrates on examining studies highlighting neuromorphic computing for edge AI, dissimilarities in traditional and neuromorphic computing, different chips utilized for neuromorphic computing and application of neuromorphic computing for edge AI.","url":"https://doi.org/10.47392/irjaeh.2025.0640","authors":["Dr Basanti. Ghanti","Nikita. Patil","Nidhi. S. M","Nikhita.Salgar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-27T04:19:08Z","doi":"10.47392/irjaeh.2025.0640","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1002/9781394335718.ch16","name":"Exploring Neuromorphic Computing with Deep Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9781394335718.ch16","authors":["Yogesh Kumar Sharma","Smitha","Shaik Saddam Hussain","Leena Arya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-06T21:20:12Z","doi":"10.1002/9781394335718.ch16","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/icons62911.2024.00047","name":"Exploring Extreme Quantization in Spiking Language Models","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024.00047","authors":["Malyaban Bal","Yi Jiang","Abhronil Sengupta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T18:37:03Z","doi":"10.1109/icons62911.2024.00047","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1109/tcsii.2024.3439687","name":"Memristor-Emulating-Integrate-and-Fire Neuron-Based Fully Neuromorphic Framework for Pattern Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tcsii.2024.3439687","authors":["Prashant Kumar","Rajeev Kumar Ranjan","Sung-Mo Kang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-07T14:08:46Z","doi":"10.1109/tcsii.2024.3439687","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1088/2634-4386/ad752b/v2/response1","name":"Author response for \"Training Coupled Phase Oscillators as a Neuromorphic Platform using Equilibrium Propagation\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2634-4386/ad752b/v2/response1","authors":["Wang, Qingshan","Wanjura, Clara C.","Marquardt, Florian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-30T17:11:48Z","doi":"10.1088/2634-4386/ad752b/v2/response1","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1117/12.3028107","name":"On-chip learning with organic neuromorphic systems","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3028107","authors":["Yoeri van de Burgt"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-30T19:50:05Z","doi":"10.1117/12.3028107","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.31613/ceramist.2025.00038","name":"Recent Advances in Next-Generation Electrochemical Ionic Synapse for Neuromorphic Computing","source":"crossref","abstract":"Neuromorphic computing, inspired by the structure and function of biological neural networks, offers a promising alternative to traditional von Neumann architectures by integrating memory and computation for enhanced energy efficiency and processing speed. Electrochemical ionic synapses (EIS) have emerged as a next-generation memory technology, leveraging the reversible insertion and extraction of mobile ions to modulate conductance. Among various implementations, lithium-ion and proton-based EIS devices have gained attention due to their high tunability, fast response, and energy efficiency. This review delves into recent advancements in EIS technology. Lithium-ion-based EIS devices, employing transition metal oxides such as LiCoO2 and LixTiO2, demonstrate stable and scalable synaptic behavior. Meanwhile, proton-based EIS, utilizing materials like WO3 and MoO3, offer rapid ion transport and complementary metal-oxide-semiconductor compatibility, paving the way for practical neuromorphic hardware. We discuss the critical challenges related to material selection, retention stability, and large-scale integration, while exploring future directions for advancing EIS-based computing. By providing insights into the underlying mechanisms and engineering strategies, this review aims to support the development of energy-efficient and high-performance neuromorphic systems, bringing artificial intelligence closer to the capabilities of the human brain.","url":"https://doi.org/10.31613/ceramist.2025.00038","authors":["Hanju Kim","Woo-Bin Jung"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-03T23:56:45Z","doi":"10.31613/ceramist.2025.00038","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/icar65334.2025.11338674","name":"Towards Bioinspired Localization and Mapping with Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icar65334.2025.11338674","authors":["Bernardo Manuel Pirozzo","Mariano De Paula","Sebastián Aldo Villar","Bruno Pirozzo","Federico Bernart","Gerardo Gabriel Acosta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-21T21:06:47Z","doi":"10.1109/icar65334.2025.11338674","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/icnc52316.2021.9608894","name":"Saturation region attractivity analysis for memristive neural networks under the strong external input","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc52316.2021.9608894","authors":["Gang Bao","Xue Zhou","Wenbin Hu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-29T20:59:32Z","doi":"10.1109/icnc52316.2021.9608894","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/ijcnn55064.2022.9892030","name":"Hyperdimensional Computing Using Time-To-Spike Neuromorphic Circuits","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn55064.2022.9892030","authors":["Graham Bent","Chris Simpkin","Yuhua Li","Alun Preece"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-30T19:56:04Z","doi":"10.1109/ijcnn55064.2022.9892030","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/icip51287.2024.10647465","name":"E2SIFT: Neuromorphic SIFT via Direct Feature Pyramid Recovery from Events","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icip51287.2024.10647465","authors":["Chris Henry","Paras Maharjan","Zhu Li","George York"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-27T18:34:45Z","doi":"10.1109/icip51287.2024.10647465","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1109/cleo/europe-eqec52157.2021.9541646","name":"High-Speed Neuromorphic Computing Using Spin-Controlled VCSELs","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cleo/europe-eqec52157.2021.9541646","authors":["Krishan Harkhoe","Guy Verschaffelt","Guy Van der Sande"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-30T17:43:06Z","doi":"10.1109/cleo/europe-eqec52157.2021.9541646","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.4018/979-8-3373-7779-7","name":"Emerging Hybrid Models for Neuromorphic AI and Quantum Computing","source":"crossref","abstract":"","url":"https://doi.org/10.4018/979-8-3373-7779-7","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-04T19:15:56Z","doi":"10.4018/979-8-3373-7779-7","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1109/edtm61175.2025.11041471","name":"Nanorods-Based Memristors: Advancing Bio-Inspired System and Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/edtm61175.2025.11041471","authors":["Ji Eun Kim","Suk Yeop Chun","Keunho Soh","Jung Ho Yoon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-30T17:36:02Z","doi":"10.1109/edtm61175.2025.11041471","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/cvprw63382.2024.00219","name":"Neuromorphic Lip-Reading with Signed Spiking Gated Recurrent Units","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cvprw63382.2024.00219","authors":["Manon Dampfhoffer","Thomas Mesquida"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-27T18:27:42Z","doi":"10.1109/cvprw63382.2024.00219","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1109/icsec62781.2024.10770726","name":"Energy Efficiency Evaluation of Neural Network Architectures on the Neuromorphic-MNIST Dataset","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icsec62781.2024.10770726","authors":["Niti Thienbutr","Wansuree Massagram"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-03T18:55:07Z","doi":"10.1109/icsec62781.2024.10770726","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1109/cleo/europe-eqec65582.2025.11111313","name":"Neuromorphic Computing with Nonlinear Dynamics in Photonic Crystal Fiber","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cleo/europe-eqec65582.2025.11111313","authors":["Azka Maula Iskandar Muda","Uğur Teğin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-15T18:11:27Z","doi":"10.1109/cleo/europe-eqec65582.2025.11111313","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1038/srep39216","name":"Interplay of multiple synaptic plasticity features in filamentary memristive devices for neuromorphic computing","source":"crossref","abstract":"Abstract Bio-inspired computing represents today a major challenge at different levels ranging from material science for the design of innovative devices and circuits to computer science for the understanding of the key features required for processing of natural data. In this paper, we propose a detail analysis of resistive switching dynamics in electrochemical metallization cells for synaptic plasticity implementation. We show how filament stability associated to joule effect during switching can be used to emulate key synaptic features such as short term to long term plasticity transition and spike timing dependent plasticity. Furthermore, an interplay between these different synaptic features is demonstrated for object motion detection in a spike-based neuromorphic circuit. System level simulation presents robust learning and promising synaptic operation paving the way to complex bio-inspired computing systems composed of innovative memory devices.","url":"https://doi.org/10.1038/srep39216","authors":["Selina La Barbera","Adrien F. Vincent","Dominique Vuillaume","Damien Querlioz","Fabien Alibart"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-12-17T06:46:52Z","doi":"10.1038/srep39216","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/asicon58565.2023.10396030","name":"A 28nm 15.09nJ/inference Neuromorphic Processor with SRAM-Based Charge Domain in-Memory-Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/asicon58565.2023.10396030","authors":["Yuchao Zhang","Zihao Xuan","Yi Kang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-24T18:33:59Z","doi":"10.1109/asicon58565.2023.10396030","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1016/j.mee.2016.10.007","name":"Experimental study of LiNbO3 memristors for use in neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.mee.2016.10.007","authors":["Shu Wang","Weisong Wang","Chris Yakopcic","Eunsung Shin","Guru Subramanyam","Tarek M. Taha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-10-19T10:54:47Z","doi":"10.1016/j.mee.2016.10.007","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1007/978-0-585-28001-1_8","name":"Introduction to Neuromorphic Communication","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-0-585-28001-1_8","authors":["Tor Sverre Lande"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-08-26T02:15:23Z","doi":"10.1007/978-0-585-28001-1_8","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1088/2634-4386/addb6d","name":"Hardware-friendly implementation of physical reservoir computing with CMOS-based time-domain analog spiking neurons","source":"crossref","abstract":"Abstract This paper introduces an analog spiking neuron that utilizes time-domain information, i.e. a time interval of two signal transitions and a pulse width, to construct a spiking neural network (SNN) for a hardware-friendly physical reservoir computing (RC) on a complementary metal-oxide-semiconductor platform. A neuron with leaky integrate-and-fire is realized by employing two voltage-controlled oscillators with opposite sensitivities to the internal control voltage, and the neuron connection structure is restricted by the use of only 4 neighboring neurons on a 2-dimensional plane to feasibly construct a regular network topology. Such a system enables us to compose an SNN with a counter-based readout circuit, which simplifies the hardware implementation of the SNN. Moreover, another technical advantage thanks to the bottom–up integration is the capability of dynamically capturing every neuron state in the network, which can significantly contribute to finding guidelines on how to enhance the performance for various computational tasks in temporal information processing. Diverse nonlinear physical dynamics needed for RC can be realized by collective behavior through dynamic interaction between neurons, like coupled oscillators, despite the simple network structure. With behavioral system-level simulations, we demonstrate physical RC through short-term memory and exclusive OR tasks, and the spoken digit recognition task with an accuracy of 97.7% as well. Our system is considerably feasible for practical applications and can also be a useful platform for studying the mechanism of physical RC.","url":"https://doi.org/10.1088/2634-4386/addb6d","authors":["Nanako Kimura","Ckristian Duran","Zolboo Byambadorj","Ryosho Nakane","Tetsuya Iizuka"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-21T22:50:06Z","doi":"10.1088/2634-4386/addb6d","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1088/2634-4386/acf684","name":"Artificial nanophotonic neuron with internal memory for biologically inspired and reservoir network computing","source":"crossref","abstract":"Abstract Neurons with internal memory have been proposed for biological and bio-inspired neural networks, adding important functionality. We introduce an internal time-limited charge-based memory into a III–V nanowire (NW) based optoelectronic neural node circuit designed for handling optical signals in a neural network. The new circuit can receive inhibiting and exciting light signals, store them, perform a non-linear evaluation, and emit a light signal. Using experimental values from the performance of individual III–V NWs we create a realistic computational model of the complete artificial neural node circuit. We then create a flexible neural network simulation that uses these circuits as neuronal nodes and light for communication between the nodes. This model can simulate combinations of nodes with different hardware derived memory properties and variable interconnects. Using the full model, we simulate the hardware implementation for two types of neural networks. First, we show that intentional variations in the memory decay time of the nodes can significantly improve the performance of a reservoir network. Second, we simulate the implementation in an anatomically constrained functioning model of the central complex network of the insect brain and find that it resolves an important functionality of the network even with significant variations in the node performance. Our work demonstrates the advantages of an internal memory in a concrete, nanophotonic neural node. The use of variable memory time constants in neural nodes is a general hardware derived feature and could be used in a broad range of implementations.","url":"https://doi.org/10.1088/2634-4386/acf684","authors":["David Winge","Magnus Borgström","Erik Lind","Anders Mikkelsen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-04T22:28:08Z","doi":"10.1088/2634-4386/acf684","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/ijcnn.2017.7966350","name":"Quadratic Unconstrained Binary Optimization (QUBO) on neuromorphic computing system","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2017.7966350","authors":["Md Zahangir Alom","Brian Van Essen","Adam T. Moody","David Peter Widemann","Tarek M. Taha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-07-10T21:41:30Z","doi":"10.1109/ijcnn.2017.7966350","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1002/aelm.202200509","name":"Unraveling the Atomic Redox Process in Quantum Conductance and Synaptic Events for Neuromorphic Computing","source":"crossref","abstract":"Abstract Manipulation of atomic point contact (APC) in memristive devices is considered as an essential approach in emulating biological synaptic functions and paves the way for developing neuromorphic computing systems. In this article, the conductance modulation in a polyvinylimidazole (PVI)‐based memristor that mimics the synaptic functions underlying the sensory memory, short‐term memory, long‐term memory, and forgetting events of the human brain, is demonstrated. A detailed analysis of resistive switching, quantum conductance, and synaptic behaviors in the silver (Ag) included PVI memristor is investigated by means of DC sweep and pulse current–voltage ( I–V ) measurements. Based on the synaptic plasticity of the Ag‐PVI memristor, the biological synaptic functions such as learning and forgetting two images are mimicked using 5 × 5 synaptic memristor arrays. To explain the relationship between the atomic redox process and synaptic events in the memristor, the I–V /cyclic voltammetry study is introduced. As a consequence, the concentration of charges in the APC region increases as the conductance state increases. This study is essential in order to explore the progressive growth of APC under confined redox reaction in the electrochemical metallization‐based memristors for developing both synaptic devices and high‐density multilevel memories.","url":"https://doi.org/10.1002/aelm.202200509","authors":["Karthik Krishnan","Saranyan Vijayaraghavan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-08-28T21:51:25Z","doi":"10.1002/aelm.202200509","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1088/1674-4926/42/1/013101","name":"Towards engineering in memristors for emerging memory and neuromorphic computing: A review","source":"crossref","abstract":"Abstract Resistive random-access memory (RRAM), also known as memristors, having a very simple device structure with two terminals, fulfill almost all of the fundamental requirements of volatile memory, nonvolatile memory, and neuromorphic characteristics. Its memory and neuromorphic behaviors are currently being explored in relation to a range of materials, such as biological materials, perovskites, 2D materials, and transition metal oxides. In this review, we discuss the different electrical behaviors exhibited by RRAM devices based on these materials by briefly explaining their corresponding switching mechanisms. We then discuss emergent memory technologies using memristors, together with its potential neuromorphic applications, by elucidating the different material engineering techniques used during device fabrication to improve the memory and neuromorphic performance of devices, in areas such as I ON / I OFF ratio, endurance, spike time-dependent plasticity (STDP), and paired-pulse facilitation (PPF), among others. The emulation of essential biological synaptic functions realized in various switching materials, including inorganic metal oxides and new organic materials, as well as diverse device structures such as single-layer and multilayer hetero-structured devices, and crossbar arrays, is analyzed in detail. Finally, we discuss current challenges and future prospects for the development of inorganic and new materials-based memristors.","url":"https://doi.org/10.1088/1674-4926/42/1/013101","authors":["Andrey S. Sokolov","Haider Abbas","Yawar Abbas","Changhwan Choi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-02-01T09:17:00Z","doi":"10.1088/1674-4926/42/1/013101","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1088/2634-4386/adc0b8","name":"Probabilistic computing with percolating nanoparticle networks using experimental data with signatures of criticality","source":"crossref","abstract":"Abstract Percolating networks of nanoparticles (PNNs) are promising systems for neuromorphic computing due to their brain-like network structure and dynamics. In particular, electrical spiking in PNNs meets criteria for criticality, which is thought to be the operating point for biological brains and associated with optimal computation. Previous work showed through simulations that spiking PNNs can be used as the core stochastic component in a probabilistic computing scheme. Here, we demonstrate a route to experimental implementation of an integer factorization algorithm. We outline an important modification to the algorithm previously used and demonstrate factorization of up to six-digit integers. Finally, we explore the effect of criticality in the context of the integer factorization task by comparing critical and non-critical systems. We show significant differences in the probability distribution of states generated by the critical and non-critical systems, though for the task considered, critical systems provide no advantage.","url":"https://doi.org/10.1088/2634-4386/adc0b8","authors":["Sofie J Studholme","Joshua B Mallinson","Jamie K Steel","Simon A Brown"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-14T22:49:21Z","doi":"10.1088/2634-4386/adc0b8","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1088/2634-4386/ae441f","name":"RCbench: a unified framework for benchmarking reservoir computing systems","source":"crossref","abstract":"Abstract Reservoir computing (RC) is a computational framework where a fixed dynamical reservoir projects an input into a higher-dimensional state that is then analyzed by a readout , which is trained to map the reservoir state into the desired output. While the conventional RC paradigm is based on dynamics of in-silico implemented recurrent neural networks, this computing paradigm can be efficiently implemented in hardware by exploiting dynamics of a wide range of physical systems in a paradigm denoted as Physical RC (PRC), attracting interest from a broader research community spanning from computer scientists to physicists, and material scientists. Here, we present RCbench, an open-source RC benchmark toolkit that implements a standardized and comprehensive suite for benchmarking computational reservoir models and physical implementations of RC. RCbench integrates widely recognized metrics such as Memory capacity, Nonlinear autoregressive moving average of order N, Kernel rank , and generalization rank, along with nonlinear transformation tasks. It also allows testing and comparing different readout algorithms, the evaluation of computational capabilities with diverse accuracy metrics, and includes feature selection methods to unravel the effect of specific reservoir outputs on computational performances. In particular, the toolkit enables easy benchmarking of PRC systems, providing a comprehensive benchmark tool that can be easily integrated with experimental data acquisition processes. By standardizing performance assessments, RCbench aims to facilitate inter-study comparisons and to accelerate the exploration, characterization and optimization of RC systems.","url":"https://doi.org/10.1088/2634-4386/ae441f","authors":["Davide Pilati","Andrea Ceni","Fabio Michieletti","Claudio Gallicchio","Carlo Ricciardi","Gianluca Milano"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-10T22:51:22Z","doi":"10.1088/2634-4386/ae441f","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1109/iccicc57084.2022.10100741","name":"Adaptive Attention with a Neuromorphic Hybrid Frame and Event-based Camera","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccicc57084.2022.10100741","authors":["Avinoam Bitton","Hadar Cohen Duwek","Elishai Ezra Tsur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-21T17:58:16Z","doi":"10.1109/iccicc57084.2022.10100741","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1016/b978-0-443-21480-6.00004-3","name":"Neuroscience-inspired facial mask recognition using MobileNet and computer vision in real-time video streaming","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-21480-6.00004-3","authors":["Veerpal Kaur","Reetu Malhotra","Gagandeep Kaur","V. Sindhu","Jogannagari Saai Rajesh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-18T21:44:31Z","doi":"10.1016/b978-0-443-21480-6.00004-3","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1007/978-3-032-04129-6_17","name":"Integrated Photonics for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-04129-6_17","authors":["Lennart Meyer","Rongyang Xu","Wolfram Pernice"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-13T10:15:00Z","doi":"10.1007/978-3-032-04129-6_17","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.4018/978-1-6684-6596-7.ch008","name":"ML-Based Finger-Vein Biometric Authentication and Hardware Implementation Strategies","source":"crossref","abstract":"The industrial world is facing swiftly changing challenges, including technical fluctuations, swings in global markets, and climate change. Digitalization and automation are the game changers to meet these challenges. Machine learning has made an impact on the area attributed to microchips, and it is initially used in automation. These practices will ultimately succeed the current VLSI design. A biometric authentication system is a form of biometric verification system that uses finger vein detection for biometric check framework. Consumer electronics development necessitates high security, high accuracy, and fast authentication speed. Since it presents the elements inside the human body, finger vein validation is a prominent technique in terms of security. Furthermore, it has a fair advantage over other personal authentication methods because to its contactless aspect. The main goal of the chapter is to provide a solution using machine learning for finger vein authentication and implementation using VLSI design.","url":"https://doi.org/10.4018/978-1-6684-6596-7.ch008","authors":["Nayan Keshri","Swapnadeep Sarkar","Yash Raj Singh","Sumathi Gokulanathan","Konguvel Elango","Sivakumar Ponnusamy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-19T08:20:15Z","doi":"10.4018/978-1-6684-6596-7.ch008","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1145/3320288.3320297","name":"Neuromorphic Computing for Autonomous Mobility in Natural Environments","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3320288.3320297","authors":["Mohammad Omar Khyam","David Alexandre","Ananya Bhardwaj","Ruihao Wang","Rolf Müller"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-08-23T12:03:10Z","doi":"10.1145/3320288.3320297","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1038/s44335-025-00041-5","name":"Voltage-responsive biomimetic membranes and ion channels for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s44335-025-00041-5","authors":["Stephen A. Sarles","Joseph S. Najem","Ahmed S. Mohamed"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-03T04:58:11Z","doi":"10.1038/s44335-025-00041-5","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.31237/osf.io/mxs45","name":"Spike Timing Mechanisms in Neuromorphic Vision Sensors using Memristor-based non-volatile Memory devices","source":"crossref","abstract":"Spike-timing mechanisms in neuromorphic vision sensors represent a cutting-edge approach to mimicking biological vision systems' efficiency and adaptability. These systems utilize memristor-based non-volatile memory devices to achieve high precision and low power consumption, essential for real-time image processing and recognition tasks. This paper explores the principles and applications of spike-timing-dependent plasticity (STDP) in neuromorphic vision sensors, focusing on the integration of memristor technology. This study introduces an innovative visual-tactile perception system that integrates a scalable, biomimetic tactile sensor called NeuTouch and uses a Visual-Tactile Spiking Neural Network (VT-SNN) for rapid perception. The system demonstrates high accuracy in robotic tasks such as container classification and rotational slip detection, outperforming traditional deep learning methods. The research also contributes to the field by making visual-tactile datasets publicly available to foster further advancements. This work highlights the potential for creating intelligent, energy-efficient robotic systems. We review the latest advancements in memristor-based memory devices, their role in neuromorphic computing, and how they contribute to the development of advanced vision sensors. The potential of these technologies in revolutionizing artificial vision and their implications for future research and development are also discussed.","url":"https://doi.org/10.31237/osf.io/mxs45","authors":["Yiping Su","Dajeong Hwang","Bing Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-24T16:16:34Z","doi":"10.31237/osf.io/mxs45","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.29363/nanoge.hopv.2024.155","name":"Squaraine-Based Memristors and Their Neuromorphic Capabilities","source":"crossref","abstract":"","url":"https://doi.org/10.29363/nanoge.hopv.2024.155","authors":["James W. Ryan","Aaron Cookson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-20T10:18:17Z","doi":"10.29363/nanoge.hopv.2024.155","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.36838/v6i8.1","name":"Optimization of Neuromorphic Learning Rate Using Neural Network Simulation","source":"crossref","abstract":"","url":"https://doi.org/10.36838/v6i8.1","authors":["Lauren Park"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-28T22:45:10Z","doi":"10.36838/v6i8.1","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1002/aisy.202200164","name":"2D Metal–Organic Framework Based Optoelectronic Neuromorphic Transistors for Human Emotion Simulation and Neuromorphic Computing","source":"crossref","abstract":"2D metal–organic frameworks (2D‐MOFs) have been extensively studied as promising materials in the fields of electrocatalysis, drug delivery, electronic devices, etc. However, few studies have explored the application potential of 2D‐MOFs in novel neuromorphic computing devices. Herein, an optoelectronic neuromorphic transistor based on a 2D‐MOF/polymer charge‐trapping layer is reported. It is found that the large specific surface area, stable crystal structure, and highly accessible active sites in 2D‐MOFs make them excellent charge‐trapping materials for the devices, which are beneficial for mimicking the memory and learning functions observed in the organism's nervous systems. Different types of synaptic behaviors have been realized in the 2D‐MOF‐based neuromorphic devices under stimuli signal, e.g., paired‐pulse facilitation, excitatory postsynaptic current, short‐term memory, and long‐term memory. More interestingly, emotion‐adjustable learning behavior is realized by changing the value of the source–drain voltage. This work can shed light on the application of 2D‐MOFs in neuromorphic computing and will contribute to the further development of neuromorphic computing devices. An interactive preprint version of the article can be found at DOI: https://doi.org/10.22541/au.165530836.62586068/v1 .","url":"https://doi.org/10.1002/aisy.202200164","authors":["Dapeng Liu","Qianqian Shi","Junyao Zhang","Li Tian","Lize Xiong","Shilei Dai","Jia Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-25T23:14:20Z","doi":"10.1002/aisy.202200164","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1088/2634-4386/add293","name":"Enhancing temporal learning in recurrent spiking networks for neuromorphic applications","source":"crossref","abstract":"Abstract Training Recurrent Spiking Neural Networks (RSNNs) with binary spikes for tasks of extended time scales presents a challenge due to the amplified vanishing gradient problem during back propagation through time. This paper introduces three crucial elements that significantly enhance the memory and capabilities of RSNNs, with a strong emphasis on compatibility with hardware and neuromorphic systems. Firstly, we incorporate neuron-level synaptic delays, which not only allow the gradient to skip time steps but also reduce the overall neuron population’s firing rate. Subsequently, we apply a biologically inspired branching factor regularization rule to stabilize the network’s dynamics and make training easier by incorporating a time-local error in the loss function. Lastly, we modify a commonly used surrogate gradient function by increasing its support to facilitate learning over longer timescales when using binary spikes. By integrating these three innovative elements, we not only resolve several complex benchmarks but also achieve state-of-the-art results on the spiking permuted sequential MNIST task (psMNIST), showcasing the practicality and relevance of our approach for digital and analog neuromorphic systems.","url":"https://doi.org/10.1088/2634-4386/add293","authors":["Ismael Balafrej","Soufiyan Bahadi","Jean Rouat","Fabien Alibart"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-01T08:13:13Z","doi":"10.1088/2634-4386/add293","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.71465/csb199","name":"Energy-Efficient Neuromorphic Computing with Spiking Neural Networks on Edge Devices: A Dynamic Programming Approach","source":"crossref","abstract":"The proliferation of Internet of Things devices has necessitated a paradigm shift from centralized cloud computing to edge computing, primarily to mitigate latency and bandwidth constraints. However, deploying complex deep learning models on resource-constrained edge devices remains a significant challenge due to power limitations. Neuromorphic computing, specifically utilizing Spiking Neural Networks, offers a promising solution by mimicking the event-driven, sparse processing capabilities of the biological brain. Despite their theoretical energy efficiency, the optimal mapping of Spiking Neural Networks onto hardware architectures with limited cores and memory is a non-trivial problem, often resulting in suboptimal energy utilization when heuristic methods are employed. This paper proposes a novel framework that leverages Dynamic Programming to optimize the placement and scheduling of spiking neurons on multicoreneuromorphic processors. By formulating the mapping problem as a multi-stage decision process, our approach systematically balances the trade-offs between inter-core communication costs and computational load balancing. We demonstrate that the proposed method significantly reduces energy consumption compared to standard greedy and random mapping strategies while maintaining high inference accuracy. The results underscore the viability of Dynamic Programming as a deterministic tool for enhancing the operational efficiency of next-generation edge intelligence.","url":"https://doi.org/10.71465/csb199","authors":["Robert H. Miller","Sarah J. Bennett"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-11T10:33:07Z","doi":"10.71465/csb199","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1117/12.2052394","name":"Neuromorphic computing applications for network intrusion detection systems","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.2052394","authors":["Raymond C. Garcia","Robinson E. Pino"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-05-22T18:54:02Z","doi":"10.1117/12.2052394","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/isqed.2017.7918306","name":"Energy efficient analog spiking temporal encoder with verification and recovery scheme for neuromorphic computing systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isqed.2017.7918306","authors":["Chenyuan Zhao","Jialing Li","Hongyu An","Yang Yi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-05-04T20:32:38Z","doi":"10.1109/isqed.2017.7918306","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.23919/date.2019.8714954","name":"Aging-aware Lifetime Enhancement for Memristor-based Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.23919/date.2019.8714954","authors":["Shuhang Zhang","Grace Li Zhang","Bing Li","Hai Helen Li","Ulf Schlichtmann"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-16T21:29:07Z","doi":"10.23919/date.2019.8714954","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/iedm.2017.8268371","name":"Understanding the trade-offs of device, circuit and application in ReRAM-based neuromorphic computing systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iedm.2017.8268371","authors":["Bonan Yan","Chenchen Liu","Xiaoxiao Liu","Yiran Chen","Hai Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-01-30T21:05:25Z","doi":"10.1109/iedm.2017.8268371","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1149/ma2020-02281947mtgabs","name":"Total Gain Recovery in Floating Gate Thin-Film Transistors for Neuromorphic and Edge Computing","source":"crossref","abstract":"We propose a floating-gate (FG) thin-film transistor architecture which alleviates a significant limitation present since the inception of FG field-effect transistors, namely the loss of gain due to parasitic capacitive coupling on the FG [1]. The interest in large area electronics has grown beyond traditional applications, such as display and sensing arrays, with recent trends including neuromorphic and edge computing. However, the challenges of fabricating robust thin film transistor (TFT) circuits have remained despite the many significant achievements in material systems and process development. In order to realise the full benefit of low-cost, high-throughput manufacturing methods, device shortcomings need to be addressed [2]. In FG devices, specifically, one major limitation is the degradation of gain compared to conventional devices, as a result of capacitive coupling of the channel and drain potentials to the floating gate. The problem is far more severe in contact-controlled TFTs, such as the staggered-electrode, high-gain source-gated transistor (SGT) [3, 4], and crippling in conventional TFTs manufactured in materials such as InGaZnO [5]. SGT operation differs from conventional field-effect TFTs, whereby the semiconductor is fully depleted at the source edge by an energy barrier (e.g. Schottky), which is reverse biased by the application of drain voltage. Charge injection is modulated via the gate/source overlap, producing very low saturation voltage and ultra-low output conductance g d [3]. This latter feature yields the distinctive and extremely high intrinsic gain observed in such devices. A large voltage drop occurs across the source depletion region, producing the notable early saturation and, consequently, the channel potential is maintained at a value close to the drain potential for operating conditions in which a conventional TFT would still be working in the linear region. As such, when a floating gate is used in a SGT, the FG couples strongly to both the drain and the channel. FG potential varies considerably with drain voltage, thus increasing charge injection along the source, ultimately raising g d . While g d is still orders of magnitude lower than that of a TFT or FG TFT (see Figure 1), many analog applications would benefit from a solution to this problem [1]. Here, we present a staggered-electrode contact-controlled device, the multimodal transistor (MMT), which shares SGT charge injection principles, however the switching mechanism of its channel is controlled by a separate gate [6]. In a FG MMT, the source gate responsible for charge injection and channel switching gate are designed as FGs (FG1 and FG2, respectively) and a main control gate (CG) may overlap both FGs. FG MMTs have been fabricated in low T°C technology [6] with Ni source and drain contacts. ICP-CVD (Inductively Coupled Plasma Chemical Vapour Deposition) via the Corial 210D reactor was used to deposit µ-Si as active layer, as well as the insulators of the gate stack (Figure 1a). Temperature never exceeded 250°C in any of the processing steps. The MMT exhibits the same high-gain properties of the SGT and preserves it even in FG configuration. With the channel and drain potentials coupling to FG2, its potential is raised significantly higher than FG1 (see Figures 1b and 1c for TCAD simulation with Silvaco Atlas), which is effectively shielded. As charge injection is exclusively modulated by FG1, the low saturation and extremely low g d are maintained, in contrast to the FG SGT (see Figure 1c). Thus, extremely high gain can be obtained from the FG MMT structure, with a wide range of applicability to traditional analog applications such as displays and sensors, as well as emerging neuromorphic circuits. Figure. 1 a) Photomicrograph of a µ-Si floating gate MMT (FG MMT); b) FG2 potential is significantly raised, while FG1 is shielded from parasitic capacitive coupling from the channel and drain potential, keeping charge injection at the s","url":"https://doi.org/10.1149/ma2020-02281947mtgabs","authors":["Eva Bestelink","Olivier de Sagazan","Radu Alexandru Sporea"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-22T18:58:04Z","doi":"10.1149/ma2020-02281947mtgabs","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1109/gcwcn66157.2025.11447486","name":"Neuromorphic LLM Pipelines for Adaptive Big Data Governance Across Distributed Cloud Providers","source":"crossref","abstract":"","url":"https://doi.org/10.1109/gcwcn66157.2025.11447486","authors":["Nirmal Sajanraj","Sarvesh Peddi","Ashok Ghimire","Pankaj Kumar Tejraj Jain"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-25T19:54:18Z","doi":"10.1109/gcwcn66157.2025.11447486","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1016/j.engappai.2025.111055","name":"Toward transforming space exploration with artificial intelligence neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.engappai.2025.111055","authors":["Ari Yu","Seungwan Woo","Hyojung Ahn"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-12T04:58:49Z","doi":"10.1016/j.engappai.2025.111055","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.36227/techrxiv.170719069.94594142/v1","name":"Neuromorphic Event-based Processing of Transradial Intraneural Recording for Online Gesture Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.36227/techrxiv.170719069.94594142/v1","authors":["Farah Baracat","Alberto Mazzoni","Silvestro Micera","Giacomo Indiveri","Elisa Donati"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-05T22:38:16Z","doi":"10.36227/techrxiv.170719069.94594142/v1","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1007/s11433-019-1499-3","name":"Spintronic devices for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11433-019-1499-3","authors":["YaJun Zhang","Qi Zheng","XiaoRui Zhu","Zhe Yuan","Ke Xia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-02-19T21:02:27Z","doi":"10.1007/s11433-019-1499-3","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/iccsc67078.2026.11468480","name":"Bio-Cognitive Security Framework: A Neuromorphic-AI Approach for Real-Time Healthcare IoT Threat Prevention","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccsc67078.2026.11468480","authors":["Vikas Kamra","Nitin Gupta","Prakhar Chandra","Aman Pal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-15T19:22:02Z","doi":"10.1109/iccsc67078.2026.11468480","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.70177/jsca.v3i3.3331","name":"COMPUTING AT THE EDGE: THE ROLE OF NEUROMORPHIC CHIPS IN INTELLIGENT ROBOTICS","source":"crossref","abstract":"The deployment of autonomous mobile robots in resource-constrained environments is currently impeded by the excessive power consumption and latency bottlenecks of traditional Von Neumann architectures. This study investigates the efficacy of neuromorphic computing as a hardware solution for low-power, low-latency edge intelligence, specifically focusing on obstacle avoidance and navigational endurance. A quantitative comparative analysis was conducted benchmarking a Spiking Neural Network (SNN) based control architecture against standard embedded GPU solutions, utilizing event-based vision sensors to evaluate energy efficiency, inference latency, and task success rates. Empirical results demonstrate that the neuromorphic architecture achieved a twenty-fold reduction in power consumption (0.25 W) and sub-millisecond latency, significantly outperforming synchronous baselines while maintaining a 98.2% navigational success rate. The findings validate event-driven processing as a superior paradigm for edge robotics, offering a sustainable path toward \"Green Robotics\" with extended operational autonomy independent of cloud connectivity.","url":"https://doi.org/10.70177/jsca.v3i3.3331","authors":["Manivone Keolavong","Soneva Vong","Thipphavone Phoutthavong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-08T03:21:55Z","doi":"10.70177/jsca.v3i3.3331","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1007/s40820-026-02322-5","name":"Analysis and Applications of Neuromorphic Memristors in Artificial Intelligence Computing","source":"europepmc","abstract":"Abstract Artificial intelligence (AI) has advanced rapidly in recent years and has been widely applied in healthcare, intelligent sensing, machine perception, and image recognition. Neuromorphic computing, inspired by the structure and operating principles of the human brain, has emerged as a promising paradigm for building efficient, low-power, and adaptive information processing systems. In this review, we summarize the development of neuromorphic memristors from the perspectives of biological inspiration, representative material systems, device architectures, performance metrics, and artificial intelligence-oriented applications. Different from previous reviews that mainly focus on memristor materials, switching mechanisms, or neuromorphic functions separately, this article further emphasizes the relationships between memristor characteristics and distinct AI-oriented tasks, including AI acceleration, neuromorphic computing, intelligent sensing, and human–machine interaction. Finally, the major challenges and future opportunities of neuromorphic memristors are discussed from the viewpoints of device optimization, system integration, scalability, and practical application.","url":"https://doi.org/10.1007/s40820-026-02322-5","authors":["Jianhui Wang","Qingxin Chen","Jinhao Zhang","Jialin Meng","Tianyu Wang"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s40820-026-02322-5","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1088/978-0-7503-5097-6ch17","name":"Neuromorphic systems","source":"crossref","abstract":"","url":"https://doi.org/10.1088/978-0-7503-5097-6ch17","authors":["Rick Cattell","Michael Boemler-Rudolph Mercury","Alice C Parker"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-09T12:29:33Z","doi":"10.1088/978-0-7503-5097-6ch17","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1016/j.orgel.2023.106745","name":"Natural DNA biopolymer synaptic emulator for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.orgel.2023.106745","authors":["Yueh-Cheng Lin","Tzu-Hsin Hsiao","Yi-Ting Li","Lin-Di Huang","Ljiljana Fruk","Yu-Chueh Hung"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-06T12:00:08Z","doi":"10.1016/j.orgel.2023.106745","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/tcsii.2020.3048034","name":"Mixed-Signal Neuromorphic Computing Circuits Using Hybrid CMOS-RRAM Integration","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tcsii.2020.3048034","authors":["Vishal Saxena"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-29T20:32:46Z","doi":"10.1109/tcsii.2020.3048034","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1145/3407197.3407217","name":"Building Reservoir Computing Hardware Using Low Energy-Barrier Magnetics","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3407197.3407217","authors":["Samiran Ganguly","Avik W. Ghosh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-07-28T04:42:57Z","doi":"10.1145/3407197.3407217","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1007/978-0-585-28001-1_17","name":"Neuromorphic Learning VLSI Systems: A Survey","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-0-585-28001-1_17","authors":["Gert Cauwenberghs"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-08-25T22:15:23Z","doi":"10.1007/978-0-585-28001-1_17","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1088/2634-4386/ac2cd4","name":"Memristive-based in-memory computing: from device to large-scale CMOS integration","source":"crossref","abstract":"Abstract With the rapid emergence of in-memory computing systems based on memristive technology, the integration of such memory devices in large-scale architectures is one of the main aspects to tackle. In this work we present a study of HfO 2 -based memristive devices for their integration in large-scale CMOS systems, namely 200 mm wafers. The DC characteristics of single metal–insulator–metal devices are analyzed taking under consideration device-to-device variabilities and switching properties. Furthermore, the distribution of the leakage current levels in the pristine state of the samples are analyzed and correlated to the amount of formingless memristors found among the measured devices. Finally, the obtained results are fitted into a physic-based compact model that enables their integration into larger-scale simulation environments.","url":"https://doi.org/10.1088/2634-4386/ac2cd4","authors":["E Perez-Bosch Quesada","E Perez","M Kalishettyhalli Mahadevaiah","C Wenger"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-10-06T06:28:22Z","doi":"10.1088/2634-4386/ac2cd4","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1016/j.sse.2019.107729","name":"Scaled resistively-coupled VO2 oscillators for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.sse.2019.107729","authors":["Elisabetta Corti","Bernd Gotsmann","Kirsten Moselund","Adrian M. Ionescu","John Robertson","Siegfried Karg"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-11-25T20:11:39Z","doi":"10.1016/j.sse.2019.107729","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1038/s41598-022-22907-5","name":"Multilayer redox-based HfOx/Al2O3/TiO2 memristive structures for neuromorphic computing","source":"crossref","abstract":"Abstract Redox-based memristive devices have shown great potential for application in neuromorphic computing systems. However, the demands on the device characteristics depend on the implemented computational scheme and unifying the desired properties in one stable device is still challenging. Understanding how and to what extend the device characteristics can be tuned and stabilized is crucial for developing application specific designs. Here, we present memristive devices with a functional trilayer of HfO x /Al 2 O 3 /TiO 2 tailored by the stoichiometry of HfO x ( x = 1.8, 2) and the operating conditions. The device properties are experimentally analyzed, and a physics-based device model is developed to provide a microscopic interpretation and explain the role of the Al 2 O 3 layer for a stable performance. Our results demonstrate that the resistive switching mechanism can be tuned from area type to filament type in the same device, which is well explained by the model: the Al 2 O 3 layer stabilizes the area-type switching mechanism by controlling the formation of oxygen vacancies at the Al 2 O 3 /HfO x interface with an estimated formation energy of ≈ 1.65 ± 0.05 eV. Such stabilized area-type devices combine multi-level analog switching, linear resistance change, and long retention times (≈ 10 7 –10 8 s) without external current compliance and initial electroforming cycles. This combination is a significant improvement compared to previous bilayer devices and makes the devices potentially interesting for future integration into memristive circuits for neuromorphic applications.","url":"https://doi.org/10.1038/s41598-022-22907-5","authors":["Seongae Park","Benjamin Spetzler","Tzvetan Ivanov","Martin Ziegler"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-29T17:02:48Z","doi":"10.1038/s41598-022-22907-5","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.297Z"},{"id":"doi:10.64229/q5g7dh32","name":"Neuromorphic Computing-Enabled Digital Twin Framework for Sustainable IT Supply Chain Integration in Smart Urban Ecosystems","source":"crossref","abstract":"The convergence of neuromorphic computing, digital twin technologies, and sustainable supply chain management presents unprecedented opportunities for transforming urban cyber-physical systems. This viewpoint paper introduces a novel conceptual framework that integrates neuromorphic computing architectures with digital twin methodologies to optimize sustainable IT supply chain operations within smart urban ecosystems. The proposed framework addresses critical issues related to real-time data processing, energy-efficient computation, and adaptive decision-making for green technology adoption across complex urban supply networks. Through theoretical analysis and conceptual modeling, we demonstrate how brain-inspired computing paradigms can enhance digital twin capabilities for monitoring, predicting, and optimizing supply chain sustainability metrics. The framework incorporates spatiotemporal knowledge graph embeddings, hybrid intelligence systems, and circular economy principles to create responsive, self-adapting supply chain networks. Our approach offers significant implications for urban planners, supply chain managers, and technology implementers seeking to advance computational sustainability science. The integration of neuromorphic processing units with digital twin architectures enables unprecedented energy efficiency improvements of up to 1000x compared to traditional computing approaches while maintaining real-time responsiveness for critical supply chain decisions. This research plays role in emerging urban sector computational sustainability by contributing a foundational framework for next-generation smart city supply chain management systems.","url":"https://doi.org/10.64229/q5g7dh32","authors":["Viraj P. Tathavadekar","Nitin R. Mahankale"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-28T09:27:44Z","doi":"10.64229/q5g7dh32","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.297Z"},{"id":"doi:10.1002/pssa.202000549","name":"Novel Approaches for Neuromorphic Computing: Materials, Concepts and Devices","source":"crossref","abstract":"","url":"https://doi.org/10.1002/pssa.202000549","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-21T19:00:52Z","doi":"10.1002/pssa.202000549","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:22.297Z"},{"id":"doi:10.1109/vlsi-tsa48913.2020.9203744","name":"Neuromorphic Computing Systems with Emerging Nonvolatile Memories: A Circuits and Systems Perspective","source":"crossref","abstract":"","url":"https://doi.org/10.1109/vlsi-tsa48913.2020.9203744","authors":["Bonan Yan","Ziru Li","Brady Taylor","Hai Li","Yiran Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-22T20:24:53Z","doi":"10.1109/vlsi-tsa48913.2020.9203744","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/mocast70204.2026.11626398","name":"Neuromorphic In-Memory Computing For Solving Convection-Diffusion Systems\n                    <sup>1</sup>","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mocast70204.2026.11626398","authors":["Angela Slavova","Spiridon Nikolaidis","Ventsislav Ignatov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-31T18:16:44Z","doi":"10.1109/mocast70204.2026.11626398","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.52202/083074-0089","name":"Neuromorphic Computing in the Study of Neuroplasticity in Astronauts in Microgravity","source":"crossref","abstract":"","url":"https://doi.org/10.52202/083074-0089","authors":["Anahí Quintero Granados","Alan Rosas Palacios","Yuritzi Elena Ordaz Huerta","Jair Molina Arce","Abigail Sanchez Gonzalez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-16T14:22:34Z","doi":"10.52202/083074-0089","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1515/9783111545950-008","name":"1398 NEGF modelling of a single-qubit operation: initialization-manipulation-measurement","source":"crossref","abstract":"","url":"https://doi.org/10.1515/9783111545950-008","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-06T19:15:47Z","doi":"10.1515/9783111545950-008","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1117/3.100022.fm","name":"Front Matter","source":"crossref","abstract":"","url":"https://doi.org/10.1117/3.100022.fm","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-02T21:15:12Z","doi":"10.1117/3.100022.fm","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1038/s41928-024-01288-9","name":"A universal neuromorphic vision processing system","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s41928-024-01288-9","authors":["Hongwei Tan","Sebastiaan van Dijken"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-12T10:01:48Z","doi":"10.1038/s41928-024-01288-9","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.21203/rs.3.rs-5737326/v1","name":"A neuromorphic multi-scale approach for heart rate and state detection","source":"crossref","abstract":"Abstract With the advent of novel sensor and machine learning technologies, it is becoming possible to develop wearable systems that perform continuous recording and processing of biosignals for health or body state assessment. For example, modern smartwatches can already track physiological functions, including heart rate and its anomalies, with high precision. However, stringent constraints on size and energy consumption pose significant challenges for always-on operation to detect trends across multiple time scales for extended periods of time. To address these challenges, we propose an alternative solution that exploits the ultra-low power consumption features of mixed-signal neuromorphic technologies. We present a biosignal processing architecture that integrates multimodal sensory inputs and processes them using the principles of neural computation to reliably detect trends in heart rate and physiological states. We validated this architecture on a mixed-signal neuromorphic processor and demonstrated its robust operation despite the inherent variability of the analog circuits present in the system. We show how the system can estimate both instantaneous heart rate and its long-term states discretized into distinct zones, effectively detecting monotonic changes over long time periods for recognizing pathological states such as agitation. This approach paves the way for a new generation of energy-efficient stand-alone wearable devices that are particularly suited for scenarios that require continuous health monitoring with minimal device maintenance.","url":"https://doi.org/10.21203/rs.3.rs-5737326/v1","authors":["Chiara De Luca","Mirco Tincani","Giacomo Indiveri","Elisa Donati"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-31T03:34:27Z","doi":"10.21203/rs.3.rs-5737326/v1","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1109/lisat63094.2024.10808138","name":"Towards ARSPI-NET: Advancing EEG Feature Extraction with Neuromorphic Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1109/lisat63094.2024.10808138","authors":["Andrew Lane","Wendy Tang","Brady Nelson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-27T14:09:04Z","doi":"10.1109/lisat63094.2024.10808138","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1016/b978-0-323-90793-4.00001-5","name":"Design and investigation of various memristor models for neuromorphic applications","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-323-90793-4.00001-5","authors":["Shailendra Singh","Raghav Dwivedi","Jeetendra Singh","Balwinder Raj"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-21T05:58:12Z","doi":"10.1016/b978-0-323-90793-4.00001-5","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1088/2634-4386/aca710","name":"SoftHebb: Bayesian inference in unsupervised Hebbian soft winner-take-all networks","source":"crossref","abstract":"Abstract Hebbian plasticity in winner-take-all (WTA) networks is highly attractive for neuromorphic on-chip learning, owing to its efficient, local, unsupervised, and on-line nature. Moreover, its biological plausibility may help overcome important limitations of artificial algorithms, such as their susceptibility to adversarial attacks, and their high demands for training-example quantity and repetition. However, Hebbian WTA learning has found little use in machine learning, likely because it has been missing an optimization theory compatible with deep learning (DL). Here we show rigorously that WTA networks constructed by standard DL elements, combined with a Hebbian-like plasticity that we derive, maintain a Bayesian generative model of the data. Importantly, without any supervision, our algorithm, SoftHebb, minimizes cross-entropy, i.e. a common loss function in supervised DL. We show this theoretically and in practice. The key is a ‘soft’ WTA where there is no absolute ‘hard’ winner neuron. Strikingly, in shallow-network comparisons with backpropagation, SoftHebb shows advantages beyond its Hebbian efficiency. Namely, it converges in fewer iterations, and is significantly more robust to noise and adversarial attacks. Notably, attacks that maximally confuse SoftHebb are also confusing to the human eye, potentially linking human perceptual robustness, with Hebbian WTA circuits of cortex. Finally, SoftHebb can generate synthetic objects as interpolations of real object classes. All in all, Hebbian efficiency, theoretical underpinning, cross-entropy-minimization, and surprising empirical advantages, suggest that SoftHebb may inspire highly neuromorphic and radically different, but practical and advantageous learning algorithms and hardware accelerators.","url":"https://doi.org/10.1088/2634-4386/aca710","authors":["Timoleon Moraitis","Dmitry Toichkin","Adrien Journé","Yansong Chua","Qinghai Guo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-30T06:23:58Z","doi":"10.1088/2634-4386/aca710","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1039/d4lf00003j","name":"Exploring response time and synaptic plasticity in P3HT ion-gated transistors for neuromorphic computing: impact of P3HT molecular weight and film thickness","source":"crossref","abstract":"Response time and plasticity of P3HT-IGTs can be controlled by engineering input stimuli, P3HT molecular weight and channel thickness.","url":"https://doi.org/10.1039/d4lf00003j","authors":["Ramin Karimi Azari","Zhaojing Gao","Alexandre Carrière","Clara Santato"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-29T16:41:16Z","doi":"10.1039/d4lf00003j","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1088/2634-4386/ae4a47","name":"The more the merrier: running multiple neuromorphic components on-chip for robotic control","source":"crossref","abstract":"Abstract It has long been realized that neuromorphic hardware offers benefits for the domain of robotics such as low energy, low latency, as well as unique methods of learning. In aiming for more complex tasks, especially those incorporating multimodal data, one hurdle continuing to prevent their realization is an inability to orchestrate multiple networks on neuromorphic hardware without resorting to off-chip process management logic. To address this, we show a first example of a pipeline for vision-based robot control in which numerous complex networks can be run entirely on hardware via the use of a spiking neural state machine for process orchestration. The pipeline is validated on the Intel Loihi 2 research chip. We show that all components can run concurrently on-chip in the milliwatt regime at latencies competitive with the state-of-the-art. An equivalent network on simulated hardware is shown to accomplish robotic arm plug insertion in simulation, and the core elements of the pipeline are additionally tested on a real robotic arm.","url":"https://doi.org/10.1088/2634-4386/ae4a47","authors":["Evan Eames","Priyadarshini Kannan","Ronan Sangouard","Philipp Plank","Elvin Hajizada","Gintautas Palinauskas","Lana Amaya","Michael Neumeier","Sai Thejeshwar Sharma","Marcella Toth","Prottush Sarkar","Axel von Arnim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-25T22:50:12Z","doi":"10.1088/2634-4386/ae4a47","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1109/icnc59488.2023.10462778","name":"Text Sentiment and Semantic Networks Analysis for MOOC Review Texts","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462778","authors":["Hua Jiang","Qing Guo","Feng Jiang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T14:09:52Z","doi":"10.1109/icnc59488.2023.10462778","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1088/2634-4386/ae3b6c","name":"Neuromorphic hardware based on memristive nanodevices for seizure detection and recovery","source":"crossref","abstract":"Abstract During the last decades, neuromorphic engineers have developed specific hardware designed to build efficient computing systems inspired by the structure of the human brain. The emergence of nanoscale memristors provided these systems with a new component which can approximately emulate the behavior of synaptic connections, improving the capability to implement in-situ learning algorithms like spike-timing-dependent plasticity. Meanwhile, neuro-inspired biomimetic platforms have been developed to directly interface with biological neurons, allowing to record and process neural signals like local field potentials (LFP). Combining both technologies, it would be possible to implant intracraneal electroencephalography electrodes with a neuromorphic chip which could sense signals from epileptic tissues and provide stimulation to prevent seizures in a closed-loop setup. In this work, we use a neuromorphic hardware platform with memristors to process LFP activity generated by an artificial neural mass model (ANMM) of the hippocampal loop implemented on a microcontroller for real-time operation, showing that the memristor system can learn correlations between neurons to detect seizures and eventually prevent them. This closed-loop ANMM-memristor crossbar interaction demonstration paves the way for trying a similar setup, replacing the ANMM with biological epileptic tissues.","url":"https://doi.org/10.1088/2634-4386/ae3b6c","authors":["Iván Díez-de-los-Ríos","Javad Farsani","Saverio Ricci","Davide Bridarolli","Luis Camuñas-Mesa","Narayan Subramaniyam","Jarno Tanskanen","Jari Hyttinen","Daniele Ielmini","Teresa Serrano-Gotarredona","Bernabé Linares-Barranco"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-21T22:51:09Z","doi":"10.1088/2634-4386/ae3b6c","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.70177/scientia.v2i4.2385","name":"FERROELECTRIC THIN FILMS FOR NEUROMORPHIC COMPUTING: SYNTHESIS, CHARACTERIZATION, AND DEVICE INTEGRATION","source":"crossref","abstract":"The limitations of conventional von Neumann computing architectures in handling complex, data-intensive tasks have spurred significant interest in brain-inspired neuromorphic computing. A critical challenge in this field is the development of hardware that can efficiently emulate the synaptic plasticity of biological neurons. This study focuses on the synthesis, characterization, and integration of ferroelectric thin films, specifically hafnium zirconium oxide (HZO), as a promising material platform for creating artificial synaptic devices. The primary objective was to fabricate high-quality HZO thin films and demonstrate their capacity to mimic key synaptic functions. HZO films were synthesized using pulsed laser deposition, followed by comprehensive characterization of their structural, ferroelectric, and electrical properties using XRD, PFM, and I-V measurements. The optimized films were then integrated into two-terminal memristive device structures. The resulting devices successfully exhibited essential synaptic behaviors, including potentiation, depression, and spike-timing-dependent plasticity (STDP), with low energy consumption per synaptic event. The gradual and controllable modulation of ferroelectric domain switching was identified as the core mechanism enabling this analog-like resistance modulation.","url":"https://doi.org/10.70177/scientia.v2i4.2385","authors":["Nurul Huda","Amin Zaki","Nong Chai","Siti Shofiah"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-20T05:06:23Z","doi":"10.70177/scientia.v2i4.2385","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.62311/nesx/rp2-30042026","name":"Algebraic Quantum-AI Co-Design of Energy-Adaptive Semiconductor Architectures for Edge Intelligence and Neuromorphic Computing","source":"crossref","abstract":"Abstract This study investigates the algebraic co-design of quantum-AI abstractions, energy-adaptive semiconductor architectures, and neuromorphic computing pathways for edge intelligence. The core problem addressed is the growing mismatch between the computational intensity of modern inference workloads and the strict power, thermal, and memory limits of edge devices that must operate continuously in industrial, mobile, and cyber-physical settings. Existing edge-AI platforms provide high throughput, yet they often rely on dense data movement, externally managed memory hierarchies, and power envelopes that complicate always-on deployment. In parallel, neuromorphic platforms show promising event-driven sparsity and very low inference power, but the design space remains fragmented across device physics, architecture, workload shape, and deployment objective. The present paper develops an algebraic quantum-AI co-design framework that formalises this design space and links architecture selection to measurable energy-performance relations. Real data were collected from official NVIDIA Jetson specifications, the Hailo-8 product brief, the MLPerf Tiny benchmark suite, the Intel Loihi 2 technology brief, and published neuromorphic benchmark evidence including NeuroBench and a BrainChip comparative report. No synthetic hardware values were introduced. The analysis combines explicit equations for dynamic power, event-driven energy, energy-delay utility, and a constrained architecture-selection objective with tables and figures derived from the collected corpus. The results show a clear division of labour across edge semiconductors: high-throughput Jetson-class modules dominate dense multi-stream inference, Hailo-8 offers a strong low-power dataflow alternative, and neuromorphic designs offer the strongest always-on inference advantage when sparse event streams and adaptive signalling dominate. The study concludes that future edge intelligence systems will benefit from heterogeneous co-designed stacks in which dense accelerators, memory-local dataflow engines, and neuromorphic coprocessors are orchestrated through algebraic runtime policies rather than treated as isolated hardware categories. Keywords: quantum-AI co-design; energy-adaptive semiconductors; edge intelligence; neuromorphic computing; Loihi 2; Akida; Hailo-8; Jetson Orin; MLPerf Tiny; algebraic architecture optimisation","url":"https://doi.org/10.62311/nesx/rp2-30042026","authors":["Murali Krishna Pasupuleti"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-05T09:56:21Z","doi":"10.62311/nesx/rp2-30042026","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1134/s1063739724600389","name":"Development of an Apparatus of Imaginative Information Representation for Neuromorphic Devices","source":"crossref","abstract":"","url":"https://doi.org/10.1134/s1063739724600389","authors":["N. A. Simonov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-21T14:25:00Z","doi":"10.1134/s1063739724600389","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.1109/piers55526.2022.9792850","name":"Silicon Photonics for Neuromorphic Computing and Artificial Intelligence: Applications and Roadmap","source":"crossref","abstract":"","url":"https://doi.org/10.1109/piers55526.2022.9792850","authors":["B. J. Shastri","C. Huang","A. N. Tait","T. Ferreira de Lima","P. R. Prucnal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-16T15:37:43Z","doi":"10.1109/piers55526.2022.9792850","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1007/s11227-026-08474-w","name":"Hardware implementation of SNN-based neuromorphic computing architecture for sign language recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11227-026-08474-w","authors":["Rashi Goyal","Mohita Jaiswal","Kartik Khandelwal","Viren Sharma","Jawar Singh","Abhishek Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-03T18:18:50Z","doi":"10.1007/s11227-026-08474-w","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1109/ucc-companion.2018.00040","name":"Using Neuromorphic Hardware for the Scalable Execution of Massively Parallel, Communication-Intensive Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ucc-companion.2018.00040","authors":["Louis Blin","Ahsan Javed Awan","Thomas Heinis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-01-10T23:32:31Z","doi":"10.1109/ucc-companion.2018.00040","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1002/admt.201900037","name":"Emerging Artificial Synaptic Devices for Neuromorphic Computing","source":"crossref","abstract":"Abstract In today's era of big‐data, a new computing paradigm beyond today's von‐Neumann architecture is needed to process these large‐scale datasets efficiently. Inspired by the brain, which is better at complex tasks than even supercomputers with much better efficiency, the field of neuromorphic computing has recently attracted immense research interest and can have a profound impact in next‐generation computing. Unlike modern computers that use digital “0” and “1” for computation, biological neural networks exhibit analog changes in synaptic connections during the decision‐making and learning processes. Currently, the neuron node is usually implemented by dozens of silicon transistors, an approach that is energy‐intensive and nonscalable. In this paper, recent developments of synaptic electronics for the hardware implementation and acceleration of artificial neural networks will be discussed. Learning mechanisms and synaptic plasticity in the brain and the device level requirements for synaptic electronics will briefly be reviewed, emphasizing the nuance compared to requirements for nonvolatile memories. Several categories of emerging synaptic devices based on phase change memory, resistive memory, electrochemical devices, and 2D devices will be introduced, as well as their associated advantages, disadvantages, and future prospects.","url":"https://doi.org/10.1002/admt.201900037","authors":["Qingzhou Wan","Mohammad T. Sharbati","John R. Erickson","Yanhao Du","Feng Xiong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-03-06T04:22:14Z","doi":"10.1002/admt.201900037","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1134/s1063739725601869","name":"Gate-Tunable Planar TiO2/Graphene Memristor for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1134/s1063739725601869","authors":["I. L. Jityaev","M. S. Kartel","Yu. Yu. Jityaeva","V. A. Smirnov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-23T18:31:13Z","doi":"10.1134/s1063739725601869","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1088/1674-4926/24110006","name":"Revolutionizing neuromorphic computing with memristor-based artificial neurons","source":"crossref","abstract":"Abstract As traditional von Neumann architectures face limitations in handling the demands of big data and complex computational tasks, neuromorphic computing has emerged as a promising alternative, inspired by the human brain's neural networks. Volatile memristors, particularly Mott and diffusive memristors, have garnered significant attention for their ability to emulate neuronal dynamics, such as spiking and firing patterns, enabling the development of reconfigurable and adaptive computing systems. Recent advancements include the implementation of leaky integrate-and-fire neurons, Hodgkin−Huxley neurons, optoelectronic neurons, and time-surface neurons, all utilizing volatile memristors to achieve efficient, low-power, and highly integrated neuromorphic systems. This paper reviews the latest progress in volatile memristor-based artificial neurons, highlighting their potential for energy-efficient computing and integration with artificial synapses. We conclude by addressing challenges such as improving memristor reliability and exploring new architectures to advance memristor-based neuromorphic computing.","url":"https://doi.org/10.1088/1674-4926/24110006","authors":["Yanning Chen","Guobin Zhang","Fang Liu","Bo Wu","Yongfeng Deng","Dawei Gao","Yishu Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-13T16:01:23Z","doi":"10.1088/1674-4926/24110006","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/icons62911.2024.00015","name":"Solving Minimum Spanning Tree Problem in Spiking Neural Networks: Improved Results","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024.00015","authors":["Simon Janssen","Stijn Groenen","Simon Reichert","Johan Kwisthout"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T18:37:03Z","doi":"10.1109/icons62911.2024.00015","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:20.420Z"},{"id":"doi:10.29363/nanoge.neumatdecas.2023.004","name":"Organic neuromorphic electronics for sensory coding and biohybrid systems","source":"crossref","abstract":"","url":"https://doi.org/10.29363/nanoge.neumatdecas.2023.004","authors":["Yoeri van de Burgt"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-02-01T09:31:42Z","doi":"10.29363/nanoge.neumatdecas.2023.004","addedAt":"2026-09-01T01:48:20.420Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.5772/acrt.deposit.c.8440846.v1","name":"Neuromorphic Computing in Outer Space: Intel Loihi Deployed On-Satellite for Spike Based Software Defined Communication","source":"crossref","abstract":"&lt;table&gt;&lt;tr&gt;&lt;td&gt;&lt;p dir=\"ltr\"&gt;In space exploration and communication technology, software-defined networking (SDN) architectures significantly improve communication throughput and latency. This study developed a Q-learning-based continuous learning capable cognitive agent to select optimal routing options for a dynamically changing networking environment. With the dynamically changing network link latency, the cognitive agent achieved a 90% success rate in routing packets. The agent was executed on neuromorphic hardware called Intel Loihi. However, due to the system's power limitations, a simplified version of the agent was engineered to launch into space aboard a CubeSat. The CubeSat was launched in January 2022, making a historic milestone as the first launch of a neuromorphic system into space. The developed applications were successfully executed in space.&lt;/p&gt;&lt;/td&gt;&lt;/tr&gt;&lt;/table&gt;","url":"https://doi.org/10.5772/acrt.deposit.c.8440846.v1","authors":["Nayim Rahman","Chris Yakopcic","Tarek Taha","Ricardo Lent","Janette Briones","David Chelmins","Rachel Dudukovitch","Aaron Smith","Adam Gannon","Michael Lowry","Marcus Murbach","Alejandro Salas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-12T13:43:54Z","doi":"10.5772/acrt.deposit.c.8440846.v1","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1145/3801487.3801814","name":"SABRE: A Compression-Aware BF16 Accelerator for Neuromorphic Attention","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3801487.3801814","authors":["Kunal Kishore","Manish Nagaraju","Anshul Raghavendra Katti","Nandan Venkataramana Bhat","Pramod Udupa","Shikha Tripathi","Sudarshan TSB"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-27T07:05:47Z","doi":"10.1145/3801487.3801814","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/nems67320.2025.11169898","name":"Neuromorphic Computing Based on AlN/HZO Ferroelectric Tunnel Junction","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nems67320.2025.11169898","authors":["Xuan-Kai Tang","Stephen Ekaputra Limantoro","Chao-Cheng Lin","Wen-Yueh Jang","Tseung-Yuen Tseng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-29T17:51:01Z","doi":"10.1109/nems67320.2025.11169898","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.23919/date48585.2020.9116555","name":"Go Unary: A Novel Synapse Coding and Mapping Scheme for Reliable ReRAM-based Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.23919/date48585.2020.9116555","authors":["Chang Ma","Yanan Sun","Weikang Qian","Ziqi Meng","Rui Yang","Li Jiang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-15T19:28:37Z","doi":"10.23919/date48585.2020.9116555","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/lats62223.2024.10534620","name":"Analysis of Conductance Variability in RRAM for Accurate Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/lats62223.2024.10534620","authors":["H. Aziza","J. Postel-Pellerin","M. Fieback","S. Hamdioui","H. Xun","M. Taouil","K. Coulié","W. Rahajandraibe"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-28T17:35:14Z","doi":"10.1109/lats62223.2024.10534620","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/mcsoc51149.2021.00055","name":"Configuring an Embedded Neuromorphic Coprocessor Using a RISC-V Chip for Enabling Edge Computing Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mcsoc51149.2021.00055","authors":["Evelina Forno","Andrea Spitale","Enrico Macii","Gianvito Urgese"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-04T20:48:12Z","doi":"10.1109/mcsoc51149.2021.00055","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1103/physreve.106.045311","name":"Neuromorphic quantum computing","source":"crossref","abstract":"","url":"https://doi.org/10.1103/physreve.106.045311","authors":["Christian Pehle","Christof Wetterich"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-31T14:08:24Z","doi":"10.1103/physreve.106.045311","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/access.2024.3462829","name":"Neuromorphic Computing-Based Model for Short-Term Forecasting of Global Horizontal Irradiance in Saudi Arabia","source":"crossref","abstract":"","url":"https://doi.org/10.1109/access.2024.3462829","authors":["Abdulelah Alharbi","Ubaid Ahmed","Talal Alharbi","Anzar Mahmood"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-17T18:53:12Z","doi":"10.1109/access.2024.3462829","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1063/5.0078332","name":"Artificial synapse arrays based on SiOx/TiOx memristive crossbar with high uniformity for neuromorphic computing","source":"crossref","abstract":"As the key of artificial synapse networks, memristive devices play the most important role to construct an artificial synapse because of their biological structure and function similar to the synapse. The memristive device with high uniformity is now urgently needed to ensure them be really integrated in a neuromorphic chip. Here, we first report the realization of artificial synapse networks based on the SiOx/TiOx memristive crossbar array. Compared with the one of the SiOx memristors, the coefficient of variation in the high resistance state and the low resistance state of the SiOx/TiOx memristor can be reduced by 64.2% and 37.6%, respectively. It is found that the improved uniformity of the SiOx/TiOx memristive device is related to the thicker and permanent conductance pathway in a TiOx layer, which can localize the position of conductive pathway in the SiOx layer. The disconnection and formation of conductive pathway occur mainly in the thin SiOx layer, leading to a substantial improvement in the switching uniformity. The SiOx/TiOx memristive crossbar array shows a stable and controllable operation characteristic, which enables the large-scale implementation of biological function, including spike-duration-dependent plasticity, spike-timing-dependent plasticity, and spike-number-dependent plasticity as well as paired-pulse facilitation tunability of conductance. Specifically, the visual learning capability can be trained through tuning the conductance of the unit device. The highly efficient learning capability of our SiOx/TiOx artificial synapse for neuromorphic systems shows great potential application in the AI (artificial intelligence) period.","url":"https://doi.org/10.1063/5.0078332","authors":["Kangmin Leng","Xinyue Yu","Zhongyuan Ma","Wei Li","Jun Xu","Ling Xu","Kunji Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-01-24T11:06:24Z","doi":"10.1063/5.0078332","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.64091/aticl.2025.000232","name":"Harnessing Synaptic Plasticity for Real-Time Edge Processing in Neuromorphic Computing Architectures","source":"crossref","abstract":"Brain-inspired neuromorphic computing, which is based on the neuronal structure of the brain, provides a revolutionary paradigm for real-time edge computing that is efficient in terms of energy consumption. The purpose of this work is to investigate the role of synaptic plasticity, specifically spike-timing-dependent plasticity (STDP), in increasing computational efficiency in neuromorphic edge device topologies. A new architecture is shown here that uses STDP to facilitate on-chip learning and adaptation to a wide range of sensory inputs. Additionally, this design features reduced cloud processing, lower latency, and improved energy efficiency. The classification of streams online is the primary focus of our efforts. This is a fundamental operation performed in most edge operations, including autonomous navigation and health monitoring on wearable devices. Our model is trained and evaluated in a Python-based simulation environment, and Brian2 is used to simulate neuronal dynamics. The performance of the novel architecture is evaluated using the Spiking Heidelberg Digits (SHD) benchmark, an appropriate metric for spike-based classification of auditory samples. This architecture demonstrates higher processing speed and energy efficiency than traditional von Neumann architectures, achieving 96.4% classification accuracy and a mean power consumption of 2.7 milliwatts.","url":"https://doi.org/10.64091/aticl.2025.000232","authors":["Jashkumar Shah","Aashna Desai","Rugved Gramopadhye","Tina Nenshi Gada","Debabrata Das","S. Suman Rajest"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-22T15:20:28Z","doi":"10.64091/aticl.2025.000232","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/icons62911.2024","name":"2024 International Conference on Neuromorphic Systems (ICONS)","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T18:38:26Z","doi":"10.1109/icons62911.2024","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/icnc59488.2023.10462734","name":"Cooperative Power Sharing Can Enhance the Power-flow Balancing in Cyber-Physical Islanded Microgrids","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462734","authors":["Shuai Han","Yuhong Mo","Leping Sun","Xiaoxuan Guo","Weidong Chen","Ning Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462734","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.22214/ijraset.2024.63890","name":"Machine Learning-Driven Reconfigurable EONs with Neuromorphic Computing for Network Slicing and On-Demand Service Provisioning: A Review and Survey","source":"crossref","abstract":"Abstract: This paper delves into the substantial potential of integrating advanced technologies within Reconfigurable Elastic Optical Networks (REONs). By leveraging machine learning and neuromorphic computing, these networks can significantly enhance performance, scalability, and efficiency. Machine learning models facilitate dynamic resource management, allowing for the on-demand reconfiguration of optical networks to improve service provisioning and maintain high Quality of Service (QoS). Neuromorphic processors further boost network-slicing capabilities, optimizing bandwidth management and enabling the creation of customized virtual networks. Additionally, the incorporation of neuromorphic computing into REONs contributes to substantial energy savings, a critical factor for sustainable network operations. Techniques such as differential privacy and secure multi-party computation effectively address security and privacy challenges within optical networks. Future research should focus on developing scalable architectures, formulating energy-efficient algorithms, and designing solutions tailored to specific applications to maximize the potential of REONs. In summary, the integration of advanced computing techniques within REONs promises to revolutionize network management and service delivery, equipping future networks to deliver exceptional performance, scalability, and adaptability, thus meeting the evolving demands of modern communication environments.","url":"https://doi.org/10.22214/ijraset.2024.63890","authors":["Avadha Bihari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-12T10:31:14Z","doi":"10.22214/ijraset.2024.63890","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/irps.2019.8720609","name":"Reliability Perspective on Neuromorphic Computing Based on Analog RRAM","source":"crossref","abstract":"","url":"https://doi.org/10.1109/irps.2019.8720609","authors":["Huaqiang Wu","Meiran Zhao","Yuyi Liu","Peng Yao","Yue Xi","Xinyi Li","Wei Wu","Qingtian Zhang","Jianshi Tang","Bin Gao","He Qian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-24T04:11:10Z","doi":"10.1109/irps.2019.8720609","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1038/s44306-024-00019-2","name":"Neuromorphic computing with spintronics","source":"crossref","abstract":"Abstract Spintronics and magnetic materials exhibit many physical phenomena that are promising for implementing neuromorphic computing natively in hardware. Here, we review the current state-of-the-art, focusing on the areas of spintronic synapses, neurons, and neural networks. Many current implementations are based on the paradigm of reservoir computing, where the details of the network do not need to be known but where significant post-processing is needed. Benchmarks are given where possible. We discuss the scientific and technological advances needed to bring about spintronic neuromorphic computing that could be useful to an end-user in the medium term.","url":"https://doi.org/10.1038/s44306-024-00019-2","authors":["Christopher H. Marrows","Joseph Barker","Thomas A. Moore","Timothy Moorsom"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-29T06:02:02Z","doi":"10.1038/s44306-024-00019-2","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/intermagshortpapers61879.2024.10576890","name":"Controlling Spin-Waves by Spin-Polarized Current for Logic and Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/intermagshortpapers61879.2024.10576890","authors":["Raí M. Menezes","Jeroen Mulkers","Clécio C. De Souza Silva","Bartel Van Waeyenberge","Milorad V. Milošević"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-05T17:14:48Z","doi":"10.1109/intermagshortpapers61879.2024.10576890","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1007/978-3-031-73800-5_3","name":"Radio Modulation Classification Optimization Using Combinatorial Deep Learning Technique","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-73800-5_3","authors":["Ziad El-Khatib","Sherif Moussa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-15T07:22:42Z","doi":"10.1007/978-3-031-73800-5_3","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1088/2634-4386/accd8f","name":"Quantized rewiring: hardware-aware training of sparse deep neural networks","source":"crossref","abstract":"Abstract Mixed-signal and fully digital neuromorphic systems have been of significant interest for deploying spiking neural networks in an energy-efficient manner. However, many of these systems impose constraints in terms of fan-in, memory, or synaptic weight precision that have to be considered during network design and training. In this paper, we present quantized rewiring (Q-rewiring), an algorithm that can train both spiking and non-spiking neural networks while meeting hardware constraints during the entire training process. To demonstrate our approach, we train both feedforward and recurrent neural networks with a combined fan-in/weight precision limit, a constraint that is, for example, present in the DYNAP-SE mixed-signal analog/digital neuromorphic processor. Q-rewiring simultaneously performs quantization and rewiring of synapses and synaptic weights through gradient descent updates and projecting the trainable parameters to a constraint-compliant region. Using our algorithm, we find trade-offs between the number of incoming connections to neurons and network performance for a number of common benchmark datasets.","url":"https://doi.org/10.1088/2634-4386/accd8f","authors":["Horst Petschenig","Robert Legenstein"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-26T06:06:26Z","doi":"10.1088/2634-4386/accd8f","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/cicta.2018.8706066","name":"Low Temperature Polycrystalline Silicon Thin Film Synaptic Transistor with Bilingual Plasticity for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cicta.2018.8706066","authors":["Nian Duan","Yi Li","Xiang-Shui Miao","Hsiao-Cheng Chiang","Ting-Chang Chang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-20T23:02:42Z","doi":"10.1109/cicta.2018.8706066","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/icnc64304.2024.10987802","name":"DiffPPO: Reinforcement Learning Fine-Tuning of Diffusion Models for Text-to-Image Generation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987802","authors":["Zhuo Xiao","Ping Jiang","Mingjie Zhou","Junzi Zhang","Zijian Huang","Jianfeng Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987802","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/icnc52316.2021.9608855","name":"Improved Neural Network Crawler with Information Entropy and Memristor Model","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc52316.2021.9608855","authors":["Yongbin Yu","Qian Tang","Xiao Feng","Huan Zhang","Fei Lei","Nyima Tashi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-29T20:59:32Z","doi":"10.1109/icnc52316.2021.9608855","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1038/s41598-021-82720-4","name":"Addressing limited weight resolution in a fully optical neuromorphic reservoir computing readout","source":"crossref","abstract":"Abstract Using optical hardware for neuromorphic computing has become more and more popular recently, due to its efficient high-speed data processing capabilities and low power consumption. However, there are still some remaining obstacles to realizing the vision of a completely optical neuromorphic computer. One of them is that, depending on the technology used, optical weighting elements may not share the same resolution as in the electrical domain. Moreover, noise of the weighting elements are important considerations as well. In this article, we investigate a new method for improving the performance of optical weighting components, even in the presence of noise and in the case of very low resolution. Our method utilizes an iterative training procedure and is able to select weight connections that are more robust to quantization and noise. As a result, even with only 8 to 32 levels of resolution, in noisy weighting environments, the method can outperform both nearest rounding low-resolution weighting and random rounding weighting by up to several orders of magnitude in terms of bit error rate and can deliver performance very close to full-resolution weighting elements.","url":"https://doi.org/10.1038/s41598-021-82720-4","authors":["Chonghuai Ma","Floris Laporte","Joni Dambre","Peter Bienstman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-02-04T11:08:10Z","doi":"10.1038/s41598-021-82720-4","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1007/978-3-031-71097-1_9","name":"Risk Management and Contingency Planning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-71097-1_9","authors":["Ali Akbar Firoozi","Ali Asghar Firoozi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-12T15:02:54Z","doi":"10.1007/978-3-031-71097-1_9","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1088/2634-4386/adcf46","name":"Range and angle estimation with spiking neural resonators for FMCW radar","source":"crossref","abstract":"Abstract Automotive radar systems face the challenge of managing high sampling rates and large data bandwidth while complying with stringent real-time and energy efficiency requirements. Neuromorphic computing offers promising solutions because of its inherent energy efficiency and parallel processing capacity. Yet, most sensor systems, such as radars, do not produce suitable data for further neuromorphic processing of the data. This research presents a novel spiking neuron model for signal processing of frequency-modulated continuous wave (FMCW) radars that outperforms the state-of-the-art spectrum analysis algorithms in latency and data bandwidth. These spiking neural resonators are based on the resonate-and-fire neuron model and optimized to dynamically process raw radar data while simultaneously emitting an output in the form of spikes. We designed the first neuromorphic neural network consisting of these spiking neural resonators that estimates range and angle from FMCW radar data, evaluated the network on simulated automotive datasets and compared the results with a state-of-the-art pipeline for radar processing. The proposed neuron model significantly reduces the processing latency compared to traditional frequency analysis algorithms, such as the Fourier transformation (FT), which needs to sample and store entire data frames before processing. The evaluations demonstrate that these spiking neural resonators achieve state-of-the-art detection accuracy while emitting spikes simultaneously to processing and transmitting only 0.02% of the data compared to a float-32 FT. The results showcase the potential for neuromorphic signal processing for FMCW radar systems and pave the way for designing neuromorphic radar sensors.","url":"https://doi.org/10.1088/2634-4386/adcf46","authors":["Nico Reeb","Javier Lopez-Randulfe","Robin Dietrich","Alois C Knoll"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-22T22:50:41Z","doi":"10.1088/2634-4386/adcf46","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/i2mtc53148.2023.10176069","name":"Neuron Model Database for Arm-Based Multi-Core Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/i2mtc53148.2023.10176069","authors":["Bo Gong","Jiang Wang","Siyuan Chang","Weitong Liu","Jixuan Wang","Xile Wei"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-13T17:19:10Z","doi":"10.1109/i2mtc53148.2023.10176069","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1088/2634-4386/ae98af","name":"Why temporal spike order reversal drops spiking network accuracy and how to partially mitigate it","source":"crossref","abstract":"Abstract Spiking neural networks (SNNs) offer an energy-efficient alternative to traditional neural networks by utilizing discrete, temporally precise spike events. However, this study identifies a critical vulnerability in SNNs on recently established bit-based codes: consistent performance degradation when temporal spike encoding orders are reversed, such as using least-significant-bit ordering instead of most-significant-bit. We theoretically formalize this phenomenon as premature state annihilation, wherein early noisy spikes in information-discordant encodings trigger hard resets in leaky integrate-and-fire (LIF) neurons. These resets erase accumulated membrane state and, because the effective temporal influence of an input is largest for early timesteps, leave the backpropagated learning signal concentrated where the information is not. We measure the per-timestep class-mutual-information profile of six encodings directly, without reference to network accuracy, and show that the resulting concordance ordering predicts the observed degradation. While dense codes like weighted phase encoding suffer catastrophic drops (up to 48 % ), sparse codes like time-to-first-spike remain robust, and exchangeable rate codes are provably invariant to reversal. We evaluate several mitigation strategies, finding that parametric LIF (PLIF) neurons and aggressive membrane leakage significantly recover performance by adapting to or suppressing early noise.","url":"https://doi.org/10.1088/2634-4386/ae98af","authors":["Nhan Trong Luu","Duong Trung Luu","Nam Ngoc Pham","Thang Cong Truong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-12T22:52:14Z","doi":"10.1088/2634-4386/ae98af","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1038/s43588-021-00184-y","name":"Opportunities for neuromorphic computing algorithms and applications","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s43588-021-00184-y","authors":["Catherine D. Schuman","Shruti R. Kulkarni","Maryam Parsa","J. Parker Mitchell","Prasanna Date","Bill Kay"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-01-31T12:04:38Z","doi":"10.1038/s43588-021-00184-y","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/tip.2024.3364529/mm1","name":"Neuromorphic Synergy for Video Binarization_supp1-3364529.mp4","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tip.2024.3364529/mm1","authors":["Shijie Lin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-16T14:26:54Z","doi":"10.1109/tip.2024.3364529/mm1","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1142/9789812816535_others02","name":"SENSORY NEUROMORPHIC SYSTEMS","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789812816535_others02","authors":["Leslie S. Smith","Alister Hamilton"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-07-18T22:54:22Z","doi":"10.1142/9789812816535_others02","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1017/cbo9780511994838.001","name":"Preface","source":"crossref","abstract":"","url":"https://doi.org/10.1017/cbo9780511994838.001","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-02-06T06:03:07Z","doi":"10.1017/cbo9780511994838.001","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/icee67165.2025.11409769","name":"Impact of Interfacial Layer on Analog Switching Response of Flexible Memristor for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icee67165.2025.11409769","authors":["Parthasarathi Pal","Aarti Dahiya","Yeong-Her Wang","Sanjay Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-03T20:50:13Z","doi":"10.1109/icee67165.2025.11409769","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/icsict.2016.7998995","name":"Development of three-dimensional synaptic device and neuromorphic computing hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icsict.2016.7998995","authors":["I-Ting Wang","Teyuh Chou","Li-Wen Chiu","Chih-Cheng Chang","Tuo-Hung Hou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-08-09T16:18:37Z","doi":"10.1109/icsict.2016.7998995","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/icnc64304.2024.10987883","name":"A Bionic Circuit for Emotion Associative Memory Based on Memristive Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987883","authors":["Yuejia Zhou","Zhirui Chen","Kaiwen Hu","Zhixia Ding","Le Yang","Sai Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987883","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.26599/nr.2026.94908881","name":"Robust Sb\n                    <sub>2</sub>\n                    Se\n                    <sub>3</sub>\n                    memristors via pressure-modulated growth for noise-resilient neuromorphic computing","source":"crossref","abstract":"Abstract High-fidelity neuromorphic computing requires synaptic hardware that balances analog precision with array-level noise immunity, yet suppressing leakage currents in chalcogenide crossbars often necessitates complex interface engineering. Here, a robust Ag/Sb2Se3/ITO synapse is reported, fabricated via a pressure-modulated rapid thermal evaporation (RTE) strategy that targets intrinsic defect control. Crucially, this thermodynamic optimization preserves the ultralow intrinsic carrier concentration (~1014 cm-3) of the Sb2Se3 functional layer, physically prohibiting background leakage pathways without requiring additional buffer layers. Consequently, the device demonstrates highly uniform analog switching behavior, a substantial ON/OFF ratio (&gt;105), and low set/reset voltages. These characteristics effectively suppress sneak path currents and maximize the sensing margins within the crossbar array. At the system level, physics-based neural networks achieve 96.3% accuracy on MNIST, maintaining exceptional robustness against severe salt-and-pepper noise. Furthermore, we demonstrate that the hardware can execute complex motion perception algorithms, successfully extracting clear motion edges in dynamic spatiotemporal scenarios. This work establishes intrinsic carrier concentration modulation as a minimalist yet powerful paradigm for next-generation noise-resilient edge intelligence.","url":"https://doi.org/10.26599/nr.2026.94908881","authors":["Zining Wang","Chensi Song","Huanyu Chen","Xinsheng Liu","Xi Zhang","Jichun Zhu","Huilin Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-28T00:50:26Z","doi":"10.26599/nr.2026.94908881","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1063/5.0072090","name":"Photonic and optoelectronic neuromorphic computing","source":"crossref","abstract":"Recent advances in neuromorphic computing have established a computational framework that removes the processor-memory bottleneck evident in traditional von Neumann computing. Moreover, contemporary photonic circuits have addressed the limitations of electrical computational platforms to offer energy-efficient and parallel interconnects independently of the distance. When employed as synaptic interconnects with reconfigurable photonic elements, they can offer an analog platform capable of arbitrary linear matrix operations, including multiply–accumulate operation and convolution at extremely high speed and energy efficiency. Both all-optical and optoelectronic nonlinear transfer functions have been investigated for realizing neurons with photonic signals. A number of research efforts have reported orders of magnitude improvements estimated for computational throughput and energy efficiency. Compared to biological neural systems, achieving high scalability and density is challenging for such photonic neuromorphic systems. Recently developed tensor-train-decomposition methods and three-dimensional photonic integration technologies can potentially address both algorithmic and architectural scalability. This tutorial covers architectures, technologies, learning algorithms, and benchmarking for photonic and optoelectronic neuromorphic computers.","url":"https://doi.org/10.1063/5.0072090","authors":["L. El Srouji","A. Krishnan","R. Ravichandran","Y. Lee","M. On","X. Xiao","S. J. Ben Yoo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-07T15:35:16Z","doi":"10.1063/5.0072090","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1002/aisy.202000137","name":"Hardware Implementation of Neuromorphic Computing Using Large‐Scale Memristor Crossbar Arrays","source":"crossref","abstract":"Brain‐inspired neuromorphic computing is a new paradigm that holds great potential to overcome the intrinsic energy and speed issues of traditional von Neumann based computing architecture. With the ability to perform vector‐matrix multiplications and flexible tunable conductance, the memristor crossbar array (CBA) structure is one of the most promising candidates to realize neural cognitive systems. The boom in the development of memristive synapses and neurons has propelled the developments of artificial neural networks (ANNs) to emulate the highly hierarchically organized network of human brain in the past decade. To achieve this, realizing large scale, high‐density memristive CBAs is a prerequisite to constructing complex ANNs. Herein, the stringent requirements in device performance and array parameters for hardware ANNs are analyzed, and the efforts in addressing the associated challenges are discussed. Recent progress on the experimental demonstration of neuromorphic computing systems (NCSs) is presented. Recommendations for further performance optimization at the device, circuit, and algorithm levels are proposed. This Report serves as a guide for the hardware implementation of NCS based on large‐scale CBAs.","url":"https://doi.org/10.1002/aisy.202000137","authors":["Yesheng Li","Kah-Wee Ang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-11-04T08:02:52Z","doi":"10.1002/aisy.202000137","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1186/s11671-022-03744-x","name":"CMOS-Compatible Memristor for Optoelectronic Neuromorphic Computing","source":"crossref","abstract":"Abstract Optoelectronic memristor is a promising candidate for future light-controllable high-density storage and neuromorphic computing. In this work, light-tunable resistive switching (RS) characteristics are demonstrated in the CMOS process-compatible ITO/HfO 2 /TiO 2 /ITO optoelectronic memristor. The device shows an average of 79.24% transmittance under visible light. After electroforming, stable bipolar analog switching, data retention beyond 10 4 s, and endurance of 10 6 cycles are realized. An obvious current increase is observed under 405 nm wavelength light irradiation both in high and in low resistance states. The long-term potentiation of synaptic property can be achieved by both electrical and optical stimulation. Moreover, based on the optical potentiation and electrical depression of conductances, the simulated Hopfield neural network (HNN) is trained for learning the 10 × 10 pixels size image. The HNN can be successfully trained to recognize the input image with a training accuracy of 100% in 13 iterations. These results suggest that this optoelectronic memristor has a high potential for neuromorphic application.","url":"https://doi.org/10.1186/s11671-022-03744-x","authors":["Facai Wu","Chien-Hung Chou","Tseung-Yuen Tseng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-07T12:30:34Z","doi":"10.1186/s11671-022-03744-x","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/ijcnn.2000.860774","name":"A 2D neuromorphic VLSI architecture for modeling selective attention","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2000.860774","authors":["G. Indiveri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-11-07T17:31:28Z","doi":"10.1109/ijcnn.2000.860774","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1145/3354265.3354270","name":"Neuromorphic Architecture Optimization for Task-Specific Dynamic Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3354265.3354270","authors":["Sandeep Madireddy","Angel Yanguas-Gil","Prasanna Balaprakash"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-09-12T14:21:08Z","doi":"10.1145/3354265.3354270","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1088/2634-4386/acf7e4","name":"From clean room to machine room: commissioning of the first-generation BrainScaleS wafer-scale neuromorphic system","source":"crossref","abstract":"Abstract The first-generation of BrainScaleS, also referred to as BrainScaleS-1, is a neuromorphic system for emulating large-scale networks of spiking neurons. Following a ‘physical modeling’ principle, its VLSI circuits are designed to emulate the dynamics of biological examples: analog circuits implement neurons and synapses with time constants that arise from their electronic components’ intrinsic properties. It operates in continuous time, with dynamics typically matching an acceleration factor of 10 000 compared to the biological regime. A fault-tolerant design allows it to achieve wafer-scale integration despite unavoidable analog variability and component failures. In this paper, we present the commissioning process of a BrainScaleS-1 wafer module, providing a short description of the system’s physical components, illustrating the steps taken during its assembly and the measures taken to operate it. Furthermore, we reflect on the system’s development process and the lessons learned to conclude with a demonstration of its functionality by emulating a wafer-scale synchronous firing chain, the largest spiking network emulation ran with analog components and individual synapses to date.","url":"https://doi.org/10.1088/2634-4386/acf7e4","authors":["Hartmut Schmidt","José Montes","Andreas Grübl","Maurice Güttler","Dan Husmann","Joscha Ilmberger","Jakob Kaiser","Christian Mauch","Eric Müller","Lars Sterzenbach","Johannes Schemmel","Sebastian Schmitt"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-08T22:29:15Z","doi":"10.1088/2634-4386/acf7e4","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/tnano.2016.2525039","name":"Ultracompact Graphene Multigate Variable Resistor for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnano.2016.2525039","authors":["Mohamed Darwish","Vehbi Calayir","Lawrence Pileggi","Jeffrey A. Weldon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-02-03T19:12:14Z","doi":"10.1109/tnano.2016.2525039","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1088/1361-6463/ae6dd2","name":"Editorial: special issue on memristive devices for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1361-6463/ae6dd2","authors":["Ruomeng Huang","James Ryan","Chitra Gurnani","Weidong Zhang","Sungjun Kim","Antonio Guerrero"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-21T09:45:42Z","doi":"10.1088/1361-6463/ae6dd2","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1002/smm2.1154","name":"Flexible optoelectronic neural transistors with broadband spectrum sensing and instant electrical processing for multimodal neuromorphic computing","source":"crossref","abstract":"Abstract A flexible optoelectronic neural transistor (OENT) that consists of a one‐step spin‐coated tri‐blend film composed of 2,7‐dioctyl[1]benzothieno[3,2‐b][1]benzothiophene (C8‐BTBT), poly(3‐hexylthiophene‐2,5‐diyl) (P3HT), and poly(methyl methacrylate) (PMMA) is demonstrated. The C8‐BTBT and P3HT phases in the film partially segregate into distinct domains, which combine to provide broadband spectrum sensing, and instant electrical‐processing capabilities dominated by C8‐BTBT. The OENT is sensitive to solar radiation from the near‐ultraviolet (NUV) and to visible (Vis) radiation from blue to red. When exposed to NUV radiation, the OENT responds sensitively and retains the memory of the exposure for over 10 3 s. The OENT provides a warning of excessive chronic exposure to harmful NUV. These properties allow high‐pass filtering with different cut‐off frequencies f c that can restrict the reception of blue, green, or red. These switchable f c enables sensitive image reconstruction and multitarget monitoring. The device combined with a chitosan gel achieves strictly defined short‐range plasticity of &lt;1 s that can achieve diverse instant‐computing applications such as spatiotemporally correlated coding and logic functions. Stable real‐time signal processing facilitates the realization of a Morse‐code recognition system constructed using neuro‐morphological hardware, achieving highly accurate character recognition. This study provides a useful resource that can have applications in wearable biomedical electronics and multimodal neuromorphic computing.","url":"https://doi.org/10.1002/smm2.1154","authors":["Yao Ni","Lu Yang","Jiulong Feng","Jiaqi Liu","Lin Sun","Wentao Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-02T08:46:10Z","doi":"10.1002/smm2.1154","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.37099/mtu.dc.etd-restricted/192","name":"A 45nm CMOS DESIGN OF NEUROMORPHIC SYSTEM","source":"crossref","abstract":"","url":"https://doi.org/10.37099/mtu.dc.etd-restricted/192","authors":["Jehanzeb Ashraf"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-10T15:58:40Z","doi":"10.37099/mtu.dc.etd-restricted/192","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1145/3354265.3354269","name":"Graph Partitioning as Quadratic Unconstrained Binary Optimization (QUBO) on Spiking Neuromorphic Hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3354265.3354269","authors":["Susan M. Mniszewski"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-09-12T14:21:08Z","doi":"10.1145/3354265.3354269","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.22215/etd/1996-03409","name":"Neuromorphic distributed general problem solvers.","source":"crossref","abstract":"","url":"https://doi.org/10.22215/etd/1996-03409","authors":["Andrzej Bieszczad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-10-04T20:10:16Z","doi":"10.22215/etd/1996-03409","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/icnc64304.2024.10987827","name":"Integrated Wavelet Decomposition and Multi-Model Approach with Fractional-Order Sparrow Search Optimization for ECG Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987827","authors":["Zhiwei Xiao","Jiejie Chen","Ping Jiang","Bin Wei"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987827","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/irps.2019.8720552","name":"Reliability of CMOS Integrated Memristive HfO2 Arrays with Respect to Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/irps.2019.8720552","authors":["M.K. Mahadevaiah","E. Perez","Ch. Wenger","A. Grossi","C. Zambelli","P. Olivo","F. Zahari","H. Kohlstedt","M. Ziegler"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-24T00:11:10Z","doi":"10.1109/irps.2019.8720552","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.7567/ssdm.2025.k-3-04","name":"Coplanar Structure Design of Floating-gate Antiferroelectric Transistor with Multiple Operation Modes for Reconfigurable Neuromorphic Computing System","source":"crossref","abstract":"","url":"https://doi.org/10.7567/ssdm.2025.k-3-04","authors":["Yufei Shi","Jiali Huo","Yu-Chieh Chien","Kah-Wee Ang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-16T05:08:46Z","doi":"10.7567/ssdm.2025.k-3-04","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1103/physrevb.103.195302","name":"Superpolynomial quantum enhancement in polaritonic neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1103/physrevb.103.195302","authors":["Huawen Xu","Tanjung Krisnanda","Wouter Verstraelen","Timothy C. H. Liew","Sanjib Ghosh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-05-03T14:33:53Z","doi":"10.1103/physrevb.103.195302","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1002/aelm.202201111","name":"Memristive Memory Enhancement by Device Miniaturization for Neuromorphic Computing","source":"crossref","abstract":"Abstract The areal footprint of memristors is a key consideration in material‐based neuromorphic computing and large‐scale architecture integration. Electronic transport in the most widely investigated memristive devices is mediated by filaments, posing a challenge to their scalability in architecture implementation. Here, a compelling alternative memristive device is presented and it is demonstrated that areal downscaling leads to enhancement in the memristive memory window, while maintaining analog behavior, contrary to expectations. The device designs directly integrated on semiconducting Nb‐doped SrTiO 3 (Nb:STO) allows leveraging electric field effects at edges, increasing the dynamic range in smaller devices. The findings are substantiated by studying the microscopic nature of switching using scanning transmission electron microscopy, in different resistive states, revealing an interfacial layer whose physical extent is influenced by applied electric fields. The ability of Nb:STO memristors to satisfy hardware and software requirements with downscaling, while significantly enhancing memristive functionalities, make them strong contenders for non‐von‐Neumann computing, beyond complementary metal–oxide–semiconductor.","url":"https://doi.org/10.1002/aelm.202201111","authors":["Anouk S. Goossens","Majid Ahmadi","Divyanshu Gupta","Ishitro Bhaduri","Bart J. Kooi","Tamalika Banerjee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-02-15T02:56:02Z","doi":"10.1002/aelm.202201111","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1088/2634-4386/acdbe5","name":"Simulating the filament morphology in electrochemical metallization cells","source":"crossref","abstract":"Abstract Electrochemical metallization (ECM) cells are based on the principle of voltage controlled formation or dissolution of a nanometer-thin metallic conductive filament (CF) between two electrodes separated by an insulating material, e.g. an oxide. The lifetime of the CF depends on factors such as materials and biasing. Depending on the lifetime of the CF—from microseconds to years—ECM cells show promising properties for use in neuromorphic circuits, for in-memory computing, or as selectors and memory cells in storage applications. For enabling those technologies with ECM cells, the lifetime of the CF has to be controlled. As various authors connect the lifetime with the morphology of the CF, the key parameters for CF formation have to be identified. In this work, we present a 2D axisymmetric physical continuum model that describes the kinetics of volatile and non-volatile ECM cells, as well as the morphology of the CF. It is shown that the morphology depends on both the amplitude of the applied voltage signal and CF-growth induced mechanical stress within the oxide layer. The model is validated with previously published kinetic measurements of non-volatile Ag/SiO 2 /Pt and volatile Ag/HfO 2 /Pt cells and the simulated CF morphologies are consistent with previous experimental CF observations.","url":"https://doi.org/10.1088/2634-4386/acdbe5","authors":["Milan Buttberg","Ilia Valov","Stephan Menzel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-06T22:27:55Z","doi":"10.1088/2634-4386/acdbe5","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/tcsi.2016.2529279","name":"Harmonica: A Framework of Heterogeneous Computing Systems With Memristor-Based Neuromorphic Computing Accelerators","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tcsi.2016.2529279","authors":["Xiaoxiao Liu","Mengjie Mao","Beiye Liu","Boxun Li","Yu Wang","Hao Jiang","Mark Barnell","Qing Wu","Jianhua Yang","Hai Li","Yiran Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-06-23T19:50:05Z","doi":"10.1109/tcsi.2016.2529279","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1145/3546790.3546803","name":"Efficient Spike Encoding Algorithms for Neuromorphic Speech Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3546790.3546803","authors":["Sidi Yaya Arnaud Yarga","Jean Rouat","Sean Wood"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-08T04:10:51Z","doi":"10.1145/3546790.3546803","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.3389/fnins.2014.00424","name":"Research topic: neuromorphic engineering systems and applications. A snapshot of neuromorphic systems engineering","source":"crossref","abstract":"","url":"https://doi.org/10.3389/fnins.2014.00424","authors":["Tobi Delbruck","André van Schaik","Jennifer Hasler"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-12-19T14:54:18Z","doi":"10.3389/fnins.2014.00424","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1016/j.asoc.2020.106233","name":"A compact neuromorphic architecture with dynamic routing to efficiently simulate the FXECAP-L algorithm for real-time active noise control","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2020.106233","authors":["Giovanny Sanchez","Juan-Gerardo Avalos","Angel Vazquez","Luis Garcia","Thania Frias","Karina Toscano","Gonzalo Duchen","Hector Perez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-03-17T07:45:05Z","doi":"10.1016/j.asoc.2020.106233","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1145/3477145.3477155","name":"Neko: a Library for Exploring Neuromorphic Learning Rules","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3477145.3477155","authors":["Zixuan Zhao","Nathan Wycoff","Neil Getty","Rick Stevens","Fangfang Xia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-10-13T14:38:20Z","doi":"10.1145/3477145.3477155","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.62891/0816acf5","name":"A Quantum-Enhanced Neuromorphic Photonic Architecture for Bio-Inspired Spectral Processing","source":"crossref","abstract":"","url":"https://doi.org/10.62891/0816acf5","authors":["Rafael Henrique do Nascimento Oliveira","Jameson Bednarski"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-05T03:25:12Z","doi":"10.62891/0816acf5","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.37099/mtu.dc.etdr/1871","name":"Implementing Associative Learning Using Neuromorphic Robot","source":"crossref","abstract":"","url":"https://doi.org/10.37099/mtu.dc.etdr/1871","authors":["Vinay Kumar Pillalamarri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-16T18:56:32Z","doi":"10.37099/mtu.dc.etdr/1871","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1088/2634-4386/acca45","name":"System model of neuromorphic sequence learning on a memristive crossbar array","source":"crossref","abstract":"Abstract Machine learning models for sequence learning and processing often suffer from high energy consumption and require large amounts of training data. The brain presents more efficient solutions to how these types of tasks can be solved. While this has inspired the conception of novel brain-inspired algorithms, their realizations remain constrained to conventional von-Neumann machines. Therefore, the potential power efficiency of the algorithm cannot be exploited due to the inherent memory bottleneck of the computing architecture. Therefore, we present in this paper a dedicated hardware implementation of a biologically plausible version of the Temporal Memory component of the Hierarchical Temporal Memory concept. Our implementation is built on a memristive crossbar array and is the result of a hardware-algorithm co-design process. Rather than using the memristive devices solely for data storage, our approach leverages their specific switching dynamics to propose a formulation of the peripheral circuitry, resulting in a more efficient design. By combining a brain-like algorithm with emerging non-volatile memristive device technology we strive for maximum energy efficiency. We present simulation results on the training of complex high-order sequences and discuss how the system is able to predict in a context-dependent manner. Finally, we investigate the energy consumption during the training and conclude with a discussion of scaling prospects.","url":"https://doi.org/10.1088/2634-4386/acca45","authors":["Sebastian Siegel","Younes Bouhadjar","Tom Tetzlaff","Rainer Waser","Regina Dittmann","Dirk J Wouters"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-04T22:30:46Z","doi":"10.1088/2634-4386/acca45","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1145/3354265.3354278","name":"Benchmarking Event-Driven Neuromorphic Architectures","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3354265.3354278","authors":["Craig M. Vineyard","Sam Green","William M. Severa","Çetin Kaya Koç"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-09-12T14:21:08Z","doi":"10.1145/3354265.3354278","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1088/2634-4386/adad10","name":"Towards neuromorphic compression based neural sensing for next-generation wireless implantable brain machine interface","source":"crossref","abstract":"Abstract This work introduces a neuromorphic compression based neural sensing architecture with address-event representation inspired readout protocol for massively parallel, next-gen wireless implantable brain machine interface (iBMI). The architectural trade-offs and implications of the proposed method are quantitatively analyzed in terms of compression ratio (CR) and spike information preservation. For the latter, we used metrics such as root-mean-square error and correlation coefficient (CC) between the original and recovered signals to assess the effect of neuromorphic compression on the spike shape. Furthermore, we use accuracy, sensitivity, and false detection rate to understand the effect of compression on downstream iBMI tasks, specifically, spike detection. We demonstrate that a data CR of 15–265 per channel can be achieved by transmitting address-event pulses for two different biological datasets. The CR further increases to 200– 50 K per channel, 50 × more than in prior works, by the selective transmission of event pulses corresponding to neural spikes. A CC of ≈0.9 and spike detection accuracy of over 90% were obtained for the worst-case analysis involving 10 K -channel simulated recording and typical analysis using 100 or 384-channel real neural recordings. We also analyzed the collision handling capability for up to 10K channels and observed no significant error, indicating the scalability of the proposed pipeline. We also present initial results to show the ability of intention decoders to work directly on the events generated by the neuromorphic front-end.","url":"https://doi.org/10.1088/2634-4386/adad10","authors":["Vivek Mohan","Wee Peng Tay","Arindam Basu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-22T22:52:23Z","doi":"10.1088/2634-4386/adad10","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1145/3354265.3354277","name":"A Neuromorphic Sparse Coding Defense to Adversarial Images","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3354265.3354277","authors":["Edward Kim","Jessica Yarnall","Priya Shah","Garrett T. Kenyon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-09-12T14:21:08Z","doi":"10.1145/3354265.3354277","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1007/978-981-92-3410-3_1","name":"GRSNN: A Flexible Graph-Wired Spiking Neural Network for Neuromorphic Classification and Continual Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-92-3410-3_1","authors":["Xingyu Tao","Zhongjun Luo","Tomomi Hashimoto"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-18T20:05:41Z","doi":"10.1007/978-981-92-3410-3_1","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.63382/jk4sgc84","name":"&lt;b&gt;Neuromorphic Electronics Beyond Earth: Opportunities in Microgravity Manufacturing&lt;/b&gt;","source":"crossref","abstract":"Microgravity manufacturing provides a new pathway for producing neuromorphic electronic devices in space, offering both logistical advantages for long-duration missions and unique opportunities to tailor device performance through unique process physics. Recent studies demonstrate that microgravity can modify device manufacturing dynamics, defect structures, and switching behavior, leading to reduced operating voltage, improved stability, and enhanced neuromorphic functionality compared to ground-fabricated counterparts.","url":"https://doi.org/10.63382/jk4sgc84","authors":["Ruochen Liu","Sida Luo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-06T18:39:39Z","doi":"10.63382/jk4sgc84","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1145/3229884.3229887","name":"Relative Efficiency of Memristive and Digital Neuromorphic Crossbars","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3229884.3229887","authors":["Christopher D. Krieger","David J. Mountain","Mark McLean"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-07-26T11:58:06Z","doi":"10.1145/3229884.3229887","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1145/3462330","name":"Dynamic Reliability Management in Neuromorphic Computing","source":"crossref","abstract":"Neuromorphic computing systems execute machine learning tasks designed with spiking neural networks. These systems are embracing non-volatile memory to implement high-density and low-energy synaptic storage. Elevated voltages and currents needed to operate non-volatile memories cause aging of CMOS-based transistors in each neuron and synapse circuit in the hardware, drifting the transistor’s parameters from their nominal values. If these circuits are used continuously for too long, the parameter drifts cannot be reversed, resulting in permanent degradation of circuit performance over time, eventually leading to hardware faults. Aggressive device scaling increases power density and temperature, which further accelerates the aging, challenging the reliable operation of neuromorphic systems. Existing reliability-oriented techniques periodically de-stress all neuron and synapse circuits in the hardware at fixed intervals, assuming worst-case operating conditions, without actually tracking their aging at run-time. To de-stress these circuits, normal operation must be interrupted, which introduces latency in spike generation and propagation, impacting the inter-spike interval and hence, performance (e.g., accuracy). We observe that in contrast to long-term aging, which permanently damages the hardware, short-term aging in scaled CMOS transistors is mostly due to bias temperature instability. The latter is heavily workload-dependent and, more importantly, partially reversible. We propose a new architectural technique to mitigate the aging-related reliability problems in neuromorphic systems by designing an intelligent run-time manager (NCRTM), which dynamically de-stresses neuron and synapse circuits in response to the short-term aging in their CMOS transistors during the execution of machine learning workloads, with the objective of meeting a reliability target. NCRTM de-stresses these circuits only when it is absolutely necessary to do so, otherwise reducing the performance impact by scheduling de-stress operations off the critical path. We evaluate NCRTM with state-of-the-art machine learning workloads on a neuromorphic hardware. Our results demonstrate that NCRTM significantly improves the reliability of neuromorphic hardware, with marginal impact on performance.","url":"https://doi.org/10.1145/3462330","authors":["Shihao Song","Jui Hanamshet","Adarsha Balaji","Anup Das","Jeffrey L. Krichmar","Nikil D. Dutt","Nagarajan Kandasamy","Francky Catthoor"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-07-21T21:05:57Z","doi":"10.1145/3462330","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1088/2634-4386/ad4b5b","name":"Optical spike amplitude weighting and neuromimetic rate coding using a joint VCSEL-MRR neuromorphic photonic system","source":"crossref","abstract":"Abstract Spiking neurons and neural networks constitute a fundamental building block for brain-inspired computing, which is poised to benefit significantly from photonic hardware implementations. In this work, we experimentally investigate an interconnected optical neuromorphic system based on an ultrafast spiking vertical cavity surface emitting laser (VCSEL) neuron and a silicon photonics (SiPh) integrated micro-ring resonator (MRR). We experimentally demonstrate two different functional arrangements of these devices: first, we show that MRR weight banks can be used in conjunction with the spiking VCSEL-neurons to perform amplitude weighting of sub-ns optical spiking signals. Second, we show that a continuously firing VCSEL-neuron can be directly modulated using a locking signal propagated through a single weighting MRR, and we utilise this functionality to perform optical spike firing rate-coding via thermal tuning of the MRR. Given the significant track record of both integrated weight banks and photonic VCSEL-neurons, we believe these results demonstrate the viability of combining these two classes of devices for use in functional neuromorphic photonic systems.","url":"https://doi.org/10.1088/2634-4386/ad4b5b","authors":["Matěj Hejda","Eli A Doris","Simon Bilodeau","Joshua Robertson","Dafydd Owen-Newns","Bhavin J Shastri","Paul R Prucnal","Antonio Hurtado"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-14T22:28:55Z","doi":"10.1088/2634-4386/ad4b5b","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.70675/399bee3cz14e7z4cbfz94feze902eb9ecb6c","name":"Neuromorphic vision combining events and frames","source":"crossref","abstract":"Vision neuromorphique combinant événements et images L'intégration des machines avancées dans la vie quotidienne devient progressivement indispensable. Un élément clé de cette intégration réside dans la capacité de ces systèmes à percevoir, comprendre et naviguer de manière autonome. Parmi les modalités sensorielles, la vision occupe une place centrale, offrant une représentation riche et détaillée du monde environnant. Déployer la perception visuelle dans des systèmes autonomes tels que robots, drones ou véhicules impose cependant un compromis entre précision, consommation énergétique et latence. Les caméras classiques à trames, combinées à l'apprentissage profond, atteignent de bonnes performances mais présentent des limitations : faible résolution temporelle, flou de mouvement, saturation en forte luminosité et forte consommation de ressources. Cette thèse propose de surmonter ces limites en combinant deux concepts inspirés biologiquement : i) les réseaux de neurones à impulsions (SNN) et ii) les caméras à événements. Les SNN utilisent des impulsions asynchrones, offrant une alternative économe en énergie aux réseaux classiques. Les caméras à événements, inspirées de la rétine biologique, capturent les variations de luminosité de manière asynchrone avec précision microseconde, grande plage dynamique et faible consommation. Cependant, en plus du manque d'informations de texture, essentielles pour l'identification des objets, les méthodes de vision par ordinateur restent optimisées pour des données denses basées sur des trames. Pour combler cette lacune, nous proposons de fusionner les deux caméras, afin de tirer parti de leurs complémentarités. Nous explorons cette fusion pour la segmentation sémantique. Les flux d'événements sont convertis en pseudo-trames traitées par un SNN. Cette approche dépasse les méthodes existantes mais reste limitée. Pour l'améliorer, nous introduisons la distillation des connaissances : un réseau neuronal conventionnel entraîné sur des images fusionnées avec des événements transfère les caractéristiques apprises au SNN traitant les événements. Cette stratégie résout efficacement le flou et l'éblouissement inhérents aux caméras à trames. Ensuite, nous exploitons la densité d'événements comme une forme d'attention visuelle, en concentrant le calcul sur les régions de trames présentant une forte activité événementielle pour améliorer l'efficacité et réduire la latence. Enfin, nous proposons un cadre de segmentation inter-trames qui tire parti de la haute résolution temporelle des événements. En exploitant les événements déclenchés entre les trames, nous capturons le mouvement sur différents intervalles temporels et l'interpolons avec les segmentations basées sur les trames. Cette thèse démontre que la fusion de la vision basée sur les événements et sur les trames avec des architectures SNN permet une perception performante, efficace et à faible latence, ouvrant la voie à des pipelines neuromorphiques pratiques pour les systèmes autonomes du futur.","url":"https://doi.org/10.70675/399bee3cz14e7z4cbfz94feze902eb9ecb6c","authors":["Dalia Hareb"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-09T12:15:45Z","doi":"10.70675/399bee3cz14e7z4cbfz94feze902eb9ecb6c","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.70675/16013f38zb45dz4205za1d3zc1e15e7f5ff0","name":"Neuromorphic photonic systems for information processing","source":"crossref","abstract":"Systèmes photoniques neuro-morphiques pour le traitement de l'information Par une utilisation performante de nombreux algorithmes dont les réseaux neuronaux, l'intelligence artificielle révolutionne le développement de la société numérique. Néanmoins, la tendance actuelle dépasse les limites prédites par la loi de Moore et celle de Koomey, ce qui implique des limitations éventuelles des implémentations numériques de ces systèmes. Pour répondre plus efficacement aux besoins calculatoires spécifiques de cette révolution, des systèmes physiques innovants tentent en amont d'apporter des solutions, nommées \"neuro-morphiques\" puisqu'elles imitent le fonctionnement des cerveaux biologiques. Les systèmes existants sont basés sur des techniques dites de \"Reservoir Computing\" ou \"coherent Ising Machine.\" Leurs versions photoniques, ont permis de démontrer l'intérêt de ces techniques notamment pour la reconnaissance vocale avec un état de l'art en 2017 attestant de bonnes performances en termes de reconnaissance à un rythme d'1 million de mots par seconde. Nous proposons dans un premier temps une technique d'ajustement automatique des hyperparamètres pour le \"Reservoir Computing\", accompagnée d'une étude théorique de convergence. Nous proposons ensuite une solution au problème de la détection précoce de la maladie d'Alzheimer de type \"Reservoir Computing\" optoélectronique. En plus des taux de classifications obtenus meilleurs que l'état de l'art, une étude complète du compromis coût énergétique performance démontre la validité de cette approche. Enfin, le problème de la restauration d'image par maximum de vraisemblance est abordé à l'aide d'une implémentation optoélectronique appropriée de type \"coherent Ising Machine\".","url":"https://doi.org/10.70675/16013f38zb45dz4205za1d3zc1e15e7f5ff0","authors":["Nickson Mwamsojo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-07T13:29:16Z","doi":"10.70675/16013f38zb45dz4205za1d3zc1e15e7f5ff0","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1007/978-94-007-4491-2_10","name":"Phase Change Memory and Chalcogenide Materials for Neuromorphic Applications: Emphasis on Synaptic Plasticity","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-94-007-4491-2_10","authors":["Manan Suri","Barbara DeSalvo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-06-27T17:03:30Z","doi":"10.1007/978-94-007-4491-2_10","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1007/978-981-96-8383-3_1","name":"Introduction: What Is ‘Slow Electronics.’","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-96-8383-3_1","authors":["Isao H. Inoue"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-31T11:42:58Z","doi":"10.1007/978-981-96-8383-3_1","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1038/s41467-024-47811-6","name":"Spike-based dynamic computing with asynchronous sensing-computing neuromorphic chip","source":"crossref","abstract":"Abstract By mimicking the neurons and synapses of the human brain and employing spiking neural networks on neuromorphic chips, neuromorphic computing offers a promising energy-efficient machine intelligence. How to borrow high-level brain dynamic mechanisms to help neuromorphic computing achieve energy advantages is a fundamental issue. This work presents an application-oriented algorithm-software-hardware co-designed neuromorphic system for this issue. First, we design and fabricate an asynchronous chip called “Speck”, a sensing-computing neuromorphic system on chip. With the low processor resting power of 0.42mW, Speck can satisfy the hardware requirements of dynamic computing: no-input consumes no energy. Second, we uncover the “dynamic imbalance” in spiking neural networks and develop an attention-based framework for achieving the algorithmic requirements of dynamic computing: varied inputs consume energy with large variance. Together, we demonstrate a neuromorphic system with real-time power as low as 0.70mW. This work exhibits the promising potentials of neuromorphic computing with its asynchronous event-driven, sparse, and dynamic nature.","url":"https://doi.org/10.1038/s41467-024-47811-6","authors":["Man Yao","Ole Richter","Guangshe Zhao","Ning Qiao","Yannan Xing","Dingheng Wang","Tianxiang Hu","Wei Fang","Tugba Demirci","Michele De Marchi","Lei Deng","Tianyi Yan","Carsten Nielsen","Sadique Sheik","Chenxi Wu","Yonghong Tian","Bo Xu","Guoqi Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-25T07:01:39Z","doi":"10.1038/s41467-024-47811-6","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1145/3407197.3407204","name":"Neuromorphic Circuits With Neural Modulation Enhancing the Information Content of Neural Signaling","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3407197.3407204","authors":["Rami A. Alzahrani","Alice C. Parker"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-07-28T04:42:57Z","doi":"10.1145/3407197.3407204","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1007/978-0-585-28001-1_15","name":"Neuromorphic Synapses for Artificial Dendrites","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-0-585-28001-1_15","authors":["Wayne C. Westerman","David P. M. Northmore","John. G. Elias"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-08-26T02:15:23Z","doi":"10.1007/978-0-585-28001-1_15","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1007/978-981-96-8383-3_8","name":"Decoding the Unseen, Shaping the Future","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-96-8383-3_8","authors":["Isao H. Inoue"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-31T11:42:51Z","doi":"10.1007/978-981-96-8383-3_8","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.18122/td/1887/boisestate","name":"Spatiotemporal Pattern Detection with Neuromorphic Circuits","source":"crossref","abstract":"In this dissertation, neuromorphic circuits are used to implement spiking neural networks in order to detect spatiotemporal patterns. Unsupervised training and detection-by-design techniques were used to attain the appropriate connectomes and perform pattern detection. Unsupervised training was performed by feeding random digital spikes with a repeating embedded spatiotemporal pattern to a spiking neural network composed of leaky integrate-and-fire neurons and memristor-R(t) element circuits which implement spike-timing-dependent plasticity learning rules. Detection-by-design was achieved using neuromporphic circuits and digital logic gates. When detection-by-design was achieved using both neuromorphic circuits and digital logic gates, a network was created of spatiotemporal pattern detector circuits, each of which was capable of detecting the three fundamental spatiotemporal patterns (N A -N A -Δt, N A -N B -Δt, and N A -N B -Coincidence), in order to detect combinations of two-spike features in the desired spatiotemporal pattern. The spatiotemporal pattern was detected when all of the two-spike features were detected. Similarly, when detection-by-design was achieved using only neuromorphic circuits, a Complex Pattern Detecting Network was was formed by combining Simple Pattern Detecting Networks, each of which was capable of detecting the three fundamental spatiotemporal patterns. The Complex Pattern Detector was used in a proof-of-concept to demonstrate a detect-and-generate spatiotemporal symbol computing paradigm.","url":"https://doi.org/10.18122/td/1887/boisestate","authors":["Robert C. Ivans"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-05T18:15:32Z","doi":"10.18122/td/1887/boisestate","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1155/2008/428265","name":"Neuromorphic Configurable Architecture for Robust Motion Estimation","source":"crossref","abstract":"The robustness of the human visual system recovering motion estimation in almost any visual situation is enviable, performing enormous calculation tasks continuously, robustly, efficiently, and effortlessly. There is obviously a great deal we can learn from our own visual system. Currently, there are several optical flow algorithms, although none of them deals efficiently with noise, illumination changes, second-order motion, occlusions, and so on. The main contribution of this work is the efficient implementation of a biologically inspired motion algorithm that borrows nature templates as inspiration in the design of architectures and makes use of a specific model of human visual motion perception: Multichannel Gradient Model (McGM). This novel customizable architecture of a neuromorphic robust optical flow can be constructed with FPGA or ASIC device using properties of the cortical motion pathway, constituting a useful framework for building future complex bioinspired systems running in real time with high computational complexity. This work includes the resource usage and performance data, and the comparison with actual systems. This hardware has many application fields like object recognition, navigation, or tracking in difficult environments due to its bioinspired and robustness properties.","url":"https://doi.org/10.1155/2008/428265","authors":["Guillermo Botella","Manuel Rodríguez","Antonio García","Eduardo Ros"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-02-25T10:06:12Z","doi":"10.1155/2008/428265","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1145/3589737.3605968","name":"Burstprop for Learning in Spiking Neuromorphic Hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3589737.3605968","authors":["Mike Stuck","Richard Naud"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-28T16:00:57Z","doi":"10.1145/3589737.3605968","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/nss/mic/rtsd57106.2025.11287031","name":"Towards Real-Time Scatter Estimation Directly From Time-of-Flight Signals Using Embedded Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nss/mic/rtsd57106.2025.11287031","authors":["B. Gouin-Ferland","R. Fontaine","A. Corbeil Therrien"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-18T18:30:51Z","doi":"10.1109/nss/mic/rtsd57106.2025.11287031","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/icnc59488.2023.10462867","name":"Research on the Calculation Method for Carbon Emission Responsibility in Power System Based on Carbon Flow Theory and Fairness Principle","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462867","authors":["Xianfu Zhou","Feng Lu","Zanjue Wu","Kai Chen","Lei Xiang","Songsong Zheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462867","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1088/1361-6463/ae2c9c","name":"Nanoscale resistive switching in mixed-valence CuO\n                    <i>\n                      <sub>x</sub>\n                    </i>\n                    memristors for neuromorphic sensing–computing applications","source":"crossref","abstract":"Abstract Memristive devices are pivotal for the next generation of neuromorphic computing systems due to their ability to mimic biological synapses. This study investigates the nanoscale resistive switching (RS) characteristics of copper oxide (CuO x ) memristors, employing conducting atomic force microscopy (cAFM) to probe the fundamental properties of a single device junction. Our research reveals that these devices exhibit robust, counter-eight-wise bipolar RS with a high on/off ratio of ∼100 at low operating voltages (±2 V) for more than 500 cycles. Beyond memory, nanoscale memristors successfully replicate key synaptic functions essential for brain-inspired computing, including potentiation, depression, spike-rate-dependent plasticity, and paired-pulse facilitation − enabled by their analog RS. Furthermore, nociceptor-like responses such as threshold detection, relaxation, and sensitization are also realized, highlighting their multifunctional neuromorphic capabilities. The devices demonstrate a very low power consumption under a single synaptic event (∼20 pJ for potentiation and ∼8 pJ for depression). The observed bipolar resistance modulation is attributed to the modulation of the Schottky barrier at the cAFM tip/CuO x nanoscale junction, driven by ionic migration under electrical bias. These findings establish CuO x as a promising material platform for energy-efficient memory and multifunctional neuromorphic devices. Furthermore, the emulation of synaptic and nociceptive behaviors within a single device provides versatile building blocks for next-generation sensing–computing architectures.","url":"https://doi.org/10.1088/1361-6463/ae2c9c","authors":["Rupam Mandal","Tapobrata Som"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-15T22:49:03Z","doi":"10.1088/1361-6463/ae2c9c","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1088/1674-4926/25120015","name":"High hall mobility carbonized steamed buns-based polymer memristor for neuromorphic computing and image recognition","source":"crossref","abstract":"Abstract The development of new n-type semiconductors is crucial for the further advancement of electronic and optoelectronic devices. Steamed buns, anciently known as \"man tou\", mainly made of wheat flour and are one of the staple foods for Chinese people. After being subjected to high-temperature treatment, the steamed buns transformed into carbonized steamed buns (CSB) with porous nanostructures, which exhibit a Hall mobility of up to 1.62 cm 2 /(V·s), far greater than C 60 (1.5 × 10 −3 −2.5 × 10 −2 cm 2 /(V·s)), PCBM (2.0 × 10 −7 cm 2 /(V·s)) and many polymer semiconductors (~10 −6 −10 −2 cm 2 /(V·s)). A CSB-based bulk heterojunction memristor with a configuration of ITO/the CSB: PVK blends/Al is successfully fabricated. The device shows outstanding history dependent memristive switching performance, with 35 distinguishable conductance states, at a small sweep voltage range of ±1 V. An achieved production yield reaches up to 89%. Upon being subjected to consecutive positive or negative voltage sweeps, the current flowing through the device can be modulated continuously. When the 15 consecutive pulse voltages (pulse amplitude: 0.1 V; pulse width:10 μ s, pulse period: 20 μ s) were applied to the device, the observed total power consumption was about 7.63 nJ, suggesting a potential in low-energy neuromorphic computing applications. As expected, both the CSB and PVK do not exhibit any memristive effect under the same experimental condition. Utilizing the characteristic that the device can linearly adjust the weights, a simple convolutional neural network for traffic sign recognition was successfully constructed. After 300 rounds of training, the achieved recognition accuracy rate reached 88.77%. This work not only provides a new approach for developing low-cost and readily available organic semiconductors with high Hall mobility, but also offers a new idea for the subsequent development of high-performance artificial synapses and optoelectronic devices using carbonized steamed buns.","url":"https://doi.org/10.1088/1674-4926/25120015","authors":["Chenjian Zhang","Jiaxuan Liu","Dongliang Zhang","Tianhao Qin","Kexin Wang","Haidong He","Yu Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-28T15:17:07Z","doi":"10.1088/1674-4926/25120015","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/isca66397.2026.00178","name":"ELSA: An Elastic Snn Inference Architecture for Efficient Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isca66397.2026.00178","authors":["Kang You","Chen Nie","Lee Jun Yan","Ziling Wei","Cheng Zou","Zekai Xu","Yu Feng","Honglan Jiang","Zhezhi He"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-04T19:09:40Z","doi":"10.1109/isca66397.2026.00178","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1002/aelm.202370012","name":"Essential Characteristics of Memristors for Neuromorphic Computing (Adv. Electron. Mater. 2/2023)","source":"crossref","abstract":"","url":"https://doi.org/10.1002/aelm.202370012","authors":["Wenbin Chen","Lekai Song","Shengbo Wang","Zhiyuan Zhang","Guanyu Wang","Guohua Hu","Shuo Gao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-02-10T08:09:36Z","doi":"10.1002/aelm.202370012","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1016/b978-0-44-332820-6.00003-3","name":"Copyright","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-44-332820-6.00003-3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-28T07:47:12Z","doi":"10.1016/b978-0-44-332820-6.00003-3","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1088/2634-4386/ae6f46","name":"A spiking neural network implementation of Gaussian belief propagation","source":"crossref","abstract":"Abstract Bayesian inference offers a principled account of information processing in natural agents. However, it remains an open question how neural mechanisms perform their abstract operations. We investigate a hypothesis where a distributed form of Bayesian inference, namely message passing on factor graphs, is performed by a simulated network of leaky-integrate-and-fire neurons. Specifically, we perform Gaussian belief propagation by encoding messages that come into factor nodes as spike-based signals, propagating these signals through a spiking neural network and decoding the spike-based signal back to an outgoing message. Three core linear operations, equality (branching), addition, and multiplication, are realized in networks of leaky integrate-and-fire models. Validation against the standard sum-product algorithm shows accurate message updates, while applications to Kalman filtering and Bayesian linear regression demonstrate the framework’s potential for both static and dynamic inference tasks. Our results provide a step toward biologically grounded, neuromorphic implementations of probabilistic reasoning.","url":"https://doi.org/10.1088/2634-4386/ae6f46","authors":["Sepideh Adamiat","Wouter M Kouw","Bert De Vries"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-18T22:51:58Z","doi":"10.1088/2634-4386/ae6f46","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/icnc64304.2024.10987600","name":"Mixture Random Features Spaces for Robust Adaptive Filtering","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987600","authors":["Mingjing Cui","Dongyuan Lin","Yunfei Zheng","Yunxiang Jiang","Shiyuan Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987600","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/aicas54282.2022.9869944","name":"An Asynchronous Soft Macro for Ultra-Low Power Communication in Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aicas54282.2022.9869944","authors":["Davide Bertozzi","Kshitij Bhardwaj","Steven M. Nowick"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-05T20:21:42Z","doi":"10.1109/aicas54282.2022.9869944","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1002/adma.202170364","name":"Stimuli‐Responsive Memristive Materials for Artificial Synapses and Neuromorphic Computing (Adv. Mater. 46/2021)","source":"crossref","abstract":"","url":"https://doi.org/10.1002/adma.202170364","authors":["Hongyu Bian","Yi Yiing Goh","Yuxia Liu","Haifeng Ling","Linghai Xie","Xiaogang Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-15T09:06:47Z","doi":"10.1002/adma.202170364","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1103/physrevresearch.3.023146","name":"Simulation of memristive synapses and neuromorphic computing on a quantum computer","source":"crossref","abstract":"","url":"https://doi.org/10.1103/physrevresearch.3.023146","authors":["Ying Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-05-26T15:10:16Z","doi":"10.1103/physrevresearch.3.023146","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1038/s44335-024-00002-4","name":"Spiking neural networks for nonlinear regression of complex transient signals on sustainable neuromorphic processors","source":"crossref","abstract":"Abstract In recent years, spiking neural networks were introduced in science as the third generation of artificial neural networks leading to a tremendous energy saving on neuromorphic processors. This sustainable effect is due to the sparse nature of signal processing in-between spiking neurons leading to much less scalar multiplications as in second-generation networks. The spiking neuron’s efficiency is even more pronounced by their inherently recurrent nature being useful for recursive function approximations. We believe that there is a need for a general regression framework for SNNs to explore the high potential of neuromorphic computations. However, besides many classification studies with SNNs in the literature, nonlinear neuromorphic regression analysis represents a gap in research. Hence, we propose a general SNN approach for function approximation applicable for complex transient signal processing taking surrogate gradients due to the discontinuous spike representation into account. However, to pay attention to the need for high memory access during deep SNN network communications, additional spiking Legrendre Memory Units are introduced in the neuromorphic architecture. Path-dependencies and evolutions of signals can be tackled in this way. Furthermore, interfaces between real physical and binary spiking values are necessary. Following this intention, a hybrid approach is introduced, exhibiting an autoencoding strategy between dense and spiking layers. However, to verify the presented framework of nonlinear regression for a wide spectrum of scientific purposes, we see the need for obtaining realistic complex transient short-time signals by an extensive experimental set-up. Hence, a measurement technique for benchmark experiments is proposed with high-frequency oscillations measured by capacitive and piezoelectric sensors resulting in wave propagations and inelastic solid deformations to be predicted by the developed SNN regression analysis. Hence, the proposed nonlinear regression framework can be deployed to a wide range of scientific and technical applications.","url":"https://doi.org/10.1038/s44335-024-00002-4","authors":["Marcus Stoffel","Saurabh Balkrishna Tandale"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-25T10:03:04Z","doi":"10.1038/s44335-024-00002-4","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1038/s42256-025-01143-2","name":"Solving sparse finite element problems on neuromorphic hardware","source":"crossref","abstract":"Abstract The finite element method (FEM) is one of the most important and ubiquitous numerical methods for solving partial differential equations (PDEs) on computers for scientific and engineering discovery. Applying the FEM to larger and more detailed scientific models has driven advances in high-performance computing for decades. Here we demonstrate that scalable spiking neuromorphic hardware can directly implement the FEM by constructing a spiking neural network that solves the large, sparse, linear systems of equations at the core of the FEM. We show that for the Poisson equation, a fundamental PDE in science and engineering, our neural circuit achieves meaningful levels of numerical accuracy and close to ideal scaling on modern, inherently parallel and energy-efficient neuromorphic hardware, specifically Intel’s Loihi 2 neuromorphic platform. We illustrate extensions to irregular mesh geometries in both two and three dimensions as well as other PDEs such as linear elasticity. Our spiking neural network is constructed from a recurrent network model of the brain’s motor cortex and, in contrast to black-box deep artificial neural network-based methods for PDEs, directly translates the well-understood and trusted mathematics of the FEM to a natively spiking neuromorphic algorithm.","url":"https://doi.org/10.1038/s42256-025-01143-2","authors":["Bradley H. Theilman","James B. Aimone"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-13T10:02:11Z","doi":"10.1038/s42256-025-01143-2","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1016/j.ceramint.2025.07.213","name":"Enhanced synaptic performance in hafnia-based ferroelectric memristors with MIFS structure for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.ceramint.2025.07.213","authors":["Youngseo Lee","Sungjun Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-16T15:29:03Z","doi":"10.1016/j.ceramint.2025.07.213","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/edtm53872.2022.9798290","name":"Pt/TiO<sub>x</sub>/Ti-based Dynamic Optoelectronic Memristor for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/edtm53872.2022.9798290","authors":["Heyi Huang","Jianshi Tang","Bin Gao","Yuyan Wang","Xinyi Li","Ze Wang","He Qian","Huaqiang Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-21T19:47:45Z","doi":"10.1109/edtm53872.2022.9798290","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1016/j.cma.2023.116095","name":"Spiking recurrent neural networks for neuromorphic computing in nonlinear structural mechanics","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.cma.2023.116095","authors":["Saurabh Balkrishna Tandale","Marcus Stoffel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-13T06:32:47Z","doi":"10.1016/j.cma.2023.116095","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.55041/ijsmt.v2i6.053","name":"Neuromorphic Computing-Based Real-Time EEG Epileptic Seizure Detection Using Spiking Neural Networks","source":"crossref","abstract":"Epilepsy is a long-term neurological condition marked by recurring seizures that affect a large population across the globe. Detecting seizures in real time is particularly challenging because electroencephalogram (EEG) signals exhibit highly dynamic, non-linear, and patient-specific behavior. Conventional machine learning and deep learning approaches, although effective in certain scenarios, often demand significant computational resources and power, which limits their applicability in continuous monitoring systems. This study proposes a framework based on neuromorphic computing to overcome these challenges, enabling real-time detection of epileptic seizures through the use of spiking neural networks (SNNs). The proposed approach adopts an event-driven processing mechanism inspired by biological neural systems, allowing efficient handling of temporal EEG data. A spike encoding method is utilized to transform continuous EEG signals into distinct spike sequences, allowing them to be compatible with neuromorphic systems. The proposed system is designed to enhance detection performance while reducing latency and energy consumption. By combining temporal signal representation with low-power computation, the framework offers a promising approach for applications in real-time healthcare. This study demonstrates how neuromorphic computing can contribute to the development of next-generation intelligent monitoring systems for neurological disorders.","url":"https://doi.org/10.55041/ijsmt.v2i6.053","authors":["Machiraju Siva Kumar Raju Machiraju Siva Kumar Raju","G. Anjan Babu G. Anjan Babu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-07T04:35:31Z","doi":"10.55041/ijsmt.v2i6.053","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1088/2634-4386/ae0aee","name":"High-speed, ultra-low-power, and robust superconductive neuron with ReLU activation","source":"crossref","abstract":"Abstract We propose a novel ultra-high-speed neuron device utilizing a superconductive single flux quantum (SFQ) circuit to realize an ideal rectified linear unit (ReLU) activation function. This circuit generates quantum-accurate voltage output through frequency conversion within the SFQ digital circuit. A significant advantage of this design is its combination of high-speed and ultra-low-power operation with inherent tolerance to device parameter variations. This crucial feature mitigates performance degradation often observed in large-scale neural networks that rely on analog neuron circuits susceptible to characteristic variation of neuron devices. We designed and implemented the proposed neuron circuit using a 10 kA cm −2 Nb four-layer 1.0 μ m fabrication process. Experimental measurements at 4.2 K confirmed correct operation up to approximately 41.2 GHz input. Results from multiple chips successfully demonstrated ideal ReLU input–output characteristics, showcasing both the high-speed nature of the device and the scalability and robustness of our neuron circuits for next-generation artificial neural network hardware.","url":"https://doi.org/10.1088/2634-4386/ae0aee","authors":["Yuto Ueno","Yuki Hironaka","Nobuyuki Yoshikawa","Yuki Yamanashi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-24T22:49:17Z","doi":"10.1088/2634-4386/ae0aee","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1039/d5tc03702f/v2/response1","name":"Author response for \"Improved ON/OFF Ratio in Interface-Type Memristors with Ion Irradiation-Induced Large Schottky Barrier for Neuromorphic Computing\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5tc03702f/v2/response1","authors":["Ruowei Wang","Jie Su","Yong Liu","Minghui Xu","Minghao Zhang","Pengshun Shan","Weijin Kong","Yuyi Li","Hao Wu","Tao Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-30T21:08:40Z","doi":"10.1039/d5tc03702f/v2/response1","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1142/9789812816535_others01","name":"NEUROMORPHIC SYSTEMS AND THEORY","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789812816535_others01","authors":["Leslie S. Smith","Alister Hamilton"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-07-18T18:54:22Z","doi":"10.1142/9789812816535_others01","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.70675/78b51dcaze575z4535zad33zaa56bebca7eb","name":"MRAM based neuromorphic cell for Artificial Intelligence","source":"crossref","abstract":"Cellule MRAM neuromorphique pour l'Intelligence Artificielle La constante évolution de la société en termes de besoin computationnel tend vers les applications d'intelligence artificiel qui étaient autrefois réservés exclusivement à l'Homme. Le développement d'algorithme reposant sur l'apprentissage profond a rendu possible le dépassement des capacités du cerveau humain dans ces domaines de prédilections comme la reconnaissance d'images et de paroles, la prise de décision et les problèmes d'optimisation. Pourtant, les réseaux de neurones artificiels capable de résoudre ces problèmes repose de manière intensive sur d'énorme quantité de donnés et requiert de nombreuses opérations en parallèle. Quand ces algorithmes tournent sur des architectures classiques de type Van Neumann où l'unité de calcul est séparée de l'unité mémoire, la latence du réseau et son énergie consommée augmente exponentiellement avec sa taille. De ce constat, la communauté scientifique commença a développé des schémas informatiques inspiré du cerveau afin de surpasser les limitations observées. En particulier, les réseaux de neurones impulsionnels ont été prédit par W. Maass en 1997 comme étant un candidat adapté à la maximisation du dispersement des opérations dans le réseau tout en démontrant des performances égales, sinon meilleures, aux premières générations de réseaux de neurones. Jusqu'à maintenant, des circuits intégrés orienté vers une application donnée (ASICs) ont été développé par des industriels tel que Intel ou IBM pour émuler des réseaux de neurones impulsionnels, se basant sur des technologies courantes CMOS. Le nombre de transistors nécessaire pour accomplir certaines fonctionnalités critique propre aux réseaux de neurones, comme les neurones impulsionnels, sont toujours très important, ce qui n'est pas souhaitable dans une stratégie de réduction de miniaturisation poussées.Dans ce contexte, de nouvelles solutions ont été proposé pour reproduire les caractéristiques synaptiques et neuronales tout essayant de réduire un maximum l'empreinte physique et la consommation énergétique. En outre, différent type de nano-synapses reposant sur des mémoires émergeantes non-volatile ont exploré des poids synaptiques multi-niveaux ainsi que la reproduction des fonctions mémoires court-terme et long-terme. Parmi elles, les solutions basées sur une technologie spintronique sont celle les plus matures d'un point de vue industriel puisque les mémoires à accès direct magnétique (MRAM), pouvant servir de synapses binaires, ont déjà atteint le marché international depuis une dizaine année. Pourtant, l'existence d'un neurone impulsionnel compatible avec une synapses spintroniques est toujours manquant dans la littérature actuelle.Cette thèse prend donc sa place dans ce contexte de développement de nouvelles solutions spintroniques afin d'émuler un neurone impulsionnel. Les jonctions tunnels magnétiques (JTMs) largement utilisées en spintronique pour leur endurance en tant que mémoire tout en démontrant des énergies d'écriture et de lecture très faible ainsi qu'une compatibilité \"back-end of line\" et CMOS. La solution élaborée dans ce présent manuscrit prends l'avantage des JTMs pour concevoir un neurone impulsionnel basé sur la dynamique \"windmill\". Le concept de JTM à double couche libre est modélisé, nano fabriqué et caractérisé électriquement pour donner une perspective constructive sur son potentiel utilisation en tant que neurone impulsionnel.","url":"https://doi.org/10.70675/78b51dcaze575z4535zad33zaa56bebca7eb","authors":["Louis Farcis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-08T14:15:33Z","doi":"10.70675/78b51dcaze575z4535zad33zaa56bebca7eb","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1145/3822454.3822486","name":"A Neuromorphic Metropolis-Hastings Sampler: Leveraging Spiking Hardware for A Vital Primitive","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3822454.3822486","authors":["Brady Taylor","J. Darby Smith"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-16T05:57:39Z","doi":"10.1145/3822454.3822486","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1016/j.micrna.2024.207788","name":"A bio-inspired ferroelectric tunnel FET-based spiking neuron for high-speed energy efficient neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.micrna.2024.207788","authors":["Mudasir A. Khanday","Farooq A. Khanday"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-15T17:28:35Z","doi":"10.1016/j.micrna.2024.207788","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1088/2634-4386/acc08e","name":"Dynamics of the judgment of tactile stimulus intensity","source":"crossref","abstract":"Abstract In the future, artificial agents will need to make assessments of tactile stimuli in order to interact intelligently with the environment and with humans. Such assessments will depend on exquisite and robust mechanosensors, but sensors alone do not make judgments and choices. Rather, the central processing of mechanosensor inputs must be implemented with algorithms that produce ‘behavioral states’ in the artificial agent that resemble or mimic perceptual judgments in biology. In this study, we consider the problem of perceptual judgment as applied to vibration intensity. By a combination of computational modeling and simulation followed by psychophysical testing of vibration intensity perception in rats, we show that a simple yet highly salient judgment—is the current stimulus strong or weak?—can be explained as the comparison of ongoing sensory input against a criterion constructed as the time-weighted average of the history of recent stimuli. Simulations and experiments explore how judgments are shaped by the distribution of stimuli along the intensity dimension and, most importantly, by the time constant of integration which dictates the dynamics of criterion updating. The findings of this study imply that judgments made by the real nervous system are not absolute readouts of physical parameters but are context-dependent; algorithms of this form can be built into artificial systems.","url":"https://doi.org/10.1088/2634-4386/acc08e","authors":["Z Yousefi Darani","I Hachen","M E Diamond"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-02T22:26:25Z","doi":"10.1088/2634-4386/acc08e","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/icecs46596.2019.8965044","name":"A Volatile RRAM Synapse for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icecs46596.2019.8965044","authors":["E. Covi","Y.-H. Lin","W. Wang","T. Stecconi","V. Milo","A. Bricalli","E. Ambrosi","G. Pedretti","T.-Y. Tseng","D. Ielmini"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-23T22:15:31Z","doi":"10.1109/icecs46596.2019.8965044","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1149/11102.0133ecst","name":"A Capacitor-Based Synaptic Device with IGZO Access Transistors for Neuromorphic Computing","source":"crossref","abstract":"Analog in-memory computing synaptic devices have been widely studied for efficient implementation of deep learning. As a candidate for a synaptic device, Si-CMOS and capacitor-based synaptic devices have been proposed. However, due to Si-CMOS leakage currents, it is difficult to achieve sufficient retention time. In our research, we verified IGZO TFT with low leakage current and capacitor-based synapses can show linear and symmetric weight update characteristics as well as excellent device variation characteristics. We also verified that IGZO TFT has a leakage current per channel width of 1μm of ~10-17A, which is much lower than the Si-CMOS, resulting in higher accuracy in deep neural network training.","url":"https://doi.org/10.1149/11102.0133ecst","authors":["Jongun Won","Youngchae Roh","Minseung Kang","Yeaji Park","Jaehyeon Kang","Hyeongjun Seo","Changhoon Joe","SangBum Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-19T10:38:28Z","doi":"10.1149/11102.0133ecst","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1007/s13391-024-00495-y","name":"Magnetite–Polyaniline Nanocomposite for Non-Volatile Memory and Neuromorphic Computing Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s13391-024-00495-y","authors":["Ishika U. Shah","Snehal L. Patil","Sushilkumar A. Jadhav","Tukaram D. Dongale","Rajanish K. Kamat"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-16T20:24:40Z","doi":"10.1007/s13391-024-00495-y","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1016/j.neucom.2026.134580","name":"Neuromorphic quantum computing: A survey and future directions in evolutionary and gradient-based learning strategies for quantum spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2026.134580","authors":["Yingchao Cheng","Meijia Wang","Zhifeng Hao","Rajkumar Buyya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-24T06:55:11Z","doi":"10.1016/j.neucom.2026.134580","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1145/3822454.3822464","name":"4SM: Selective Spiking State Space Models for Neuromorphic Sequence Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3822454.3822464","authors":["Avi Hazan","Shlomo Greenberg","Elishai Ezra Tsur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-16T05:57:39Z","doi":"10.1145/3822454.3822464","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1149/ma2023-01321845mtgabs","name":"A Capacitor-Based Synaptic Device with IGZO Access Transistors for Neuromorphic Computing","source":"crossref","abstract":"IGZO TFT has extremely low leakage current characteristics compared to Si-CMOS, so it can be applied not only to displays but also to various research fields. One of the important applications using IGZO TFT is analog-based synaptic device for the efficient implementation for deep learning. The application of IGZO TFT to a synaptic device was more widely studied after a synaptic device based on Si-CMOS and capacitor was devised in 2017(1). Since insufficient retention time was a remaining problem in Si-CMOS and capacitor-based storage synaptic devices, the combination of IGZO TFT with low leakage current and capacitor was a very attractive solution. However, because the viable p-type metal oxide TFT does not exist, linearity and symmetry of weight update, a major requirement of on-chip trainable synaptic devices, has been difficult to achieve. In our research, for the first time, we obtained linear and symmetric weight update characteristics by combining an IGZO TFT and a capacitor. In addition, we verified the leakage characteristics of IGZO TFT and the retention characteristics of synaptic devices, which are the most important characteristics. Through the single TFT measurement result, we were able to obtain a leakage current per channel width 1µm of 10 -17 A, which is much smaller than the Si transistor. Lower leakage current will lead to better retention characteristics than conventional Si-CMOS-based devices, which will result in higher accuracy in deep neural network training. Based on the published results, the IGZO TFT synapse is projected to be able to achieve the retention time of ~4×10 9 s using only 10fF capcacitor. Another important factor that affects deep neural network training is cell-to-cell and device-to-device variation. As opposed to capacitive synaptic devices, resistive synaptic devices such as Resistive RAM and Phase Change Memory suffer from large device variation. We also verified the device variation characteristics, which are advantages of charge storage devices based on transistors and capacitors. The variation characteristics of the device were evaluated through the ΔG +3σ /ΔG -3σ (%) formula and an excellent result of ~200% was obtained. In our research, we verified the main characteristics for on-chip training of synaptic devices based on IGZO TFT and capacitor: linearity and symmetry of weight update, retention characteristics and variation characteristics. The remarkable characteristics of synaptic devices based on IGZO TFT and capacitor will be a good candidate for on-chip training. 1. S. Kim, T. Gokmen, H. M. Lee, and W. E. Haensch, Midwest Symp. Circuits Syst. , 2017 - Augus , 422–425 (2017). Acknowledgements This research was supported by National R&amp;D Program through the National Research Foundation of Korea(NRF) funded by Ministry of Science and ICT(NRF-2020M3F3A2A01081240)","url":"https://doi.org/10.1149/ma2023-01321845mtgabs","authors":["Jongun Won","Youngchae Roh","Minseung Kang","Yeaji Park","Jaehyeon Kang","Hyeongjun Seo","Changhoon Joe","SangBum Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-19T22:55:08Z","doi":"10.1149/ma2023-01321845mtgabs","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/iedm19574.2021.9720610","name":"High Performance and Self-rectifying Hafnia-based Ferroelectric Tunnel Junction for Neuromorphic Computing and TCAM Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iedm19574.2021.9720610","authors":["Youngin Goh","Junghyeon Hwang","Minki Kim","Minhyun Jung","Sehee Lim","Seong-Ook Jung","Sanghun Jeon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-09T20:31:19Z","doi":"10.1109/iedm19574.2021.9720610","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.5772/acrt.deposit.32253528","name":"Neuromorphic Computing in Outer Space: Intel Loihi Deployed On-Satellite for Spike-Based Software-Defined Communication - Presentation","source":"crossref","abstract":"&lt;p dir=\"ltr\"&gt;In space exploration and communication technology, software-defined networking architectures significantly improve the communications throughput and latency. This study developed a cognitive agent based on Q-learning with continuous learning capabilities to select optimal routing options in a dynamically changing networking environment. This proposed method achieves up to 90% reduction in measured Internet Control Message Protocol (ICMP) round-trip time compared to the Dijkstra shortest-path baseline under identical test conditions. Under dynamically changing network link latency conditions, the cognitive agent achieved a 90% success rate in routing packets in laboratory experiments. The agent was executed on neuromorphic hardware called Intel Loihi. However, due to the system’s power limitations, a simplified version of the agent was engineered to launch into space aboard a CubeSat. The CubeSat was launched in January 2022, making a historic milestone as the first launch of a neuromorphic system into space. The developed applications were successfully executed in space.&lt;/p&gt;","url":"https://doi.org/10.5772/acrt.deposit.32253528","authors":["Nayim Rahman","Chris Yakopcic","Tarek Taha","Ricardo Lent","Janette Briones","David Chelmins","Rachel Dudukovich","Aaron Smith","Adam Gannon","Michael Lowry","Marcus Murbach","Alejandro Salas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-12T13:42:45Z","doi":"10.5772/acrt.deposit.32253528","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.5772/acrt.deposit.32253477","name":"Neuromorphic Computing in Outer Space: Intel Loihi Deployed On-Satellite for Spike-Based Software-Defined Communication - Python Code","source":"crossref","abstract":"&lt;p dir=\"ltr\"&gt;In space exploration and communication technology, software-defined networking architectures significantly improve the communications throughput and latency. This study developed a cognitive agent based on Q-learning with continuous learning capabilities to select optimal routing options in a dynamically changing networking environment. This proposed method achieves up to 90% reduction in measured Internet Control Message Protocol (ICMP) round-trip time compared to the Dijkstra shortest-path baseline under identical test conditions. Under dynamically changing network link latency conditions, the cognitive agent achieved a 90% success rate in routing packets in laboratory experiments. The agent was executed on neuromorphic hardware called Intel Loihi. However, due to the system’s power limitations, a simplified version of the agent was engineered to launch into space aboard a CubeSat. The CubeSat was launched in January 2022, making a historic milestone as the first launch of a neuromorphic system into space. The developed applications were successfully executed in space.&lt;/p&gt;","url":"https://doi.org/10.5772/acrt.deposit.32253477","authors":["Nayim Rahman","Chris Yakopcic","Tarek Taha","Ricardo Lent","Janette Briones","David Chelmins","Rachel Dudukovich","Aaron Smith","Adam Gannon","Michael Lowry","Marcus Murbach","Alejandro Salas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-12T13:42:24Z","doi":"10.5772/acrt.deposit.32253477","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1093/mam/ozaf048.950","name":"Raman and SEM Enabled Development of Natural Organic Fructose Thin Films for Resistive Switching Memory in Neuromorphic Computing Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1093/mam/ozaf048.950","authors":["Md Shakil Mahmud Jiban","Kaleb Hood","Zoe Templin","Jun Jiao","Feng Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-25T14:16:18Z","doi":"10.1093/mam/ozaf048.950","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1063/5.0092382","name":"Neuromorphic computing: Challenges from quantum materials to emergent connectivity","source":"crossref","abstract":"","url":"https://doi.org/10.1063/5.0092382","authors":["Ivan K. Schuller","Alex Frano","R. C. Dynes","Axel Hoffmann","Beatriz Noheda","Catherine Schuman","Abu Sebastian","Jian Shen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-04T10:00:45Z","doi":"10.1063/5.0092382","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1038/s41598-018-30727-9","name":"Scalable Memdiodes Exhibiting Rectification and Hysteresis for Neuromorphic Computing","source":"crossref","abstract":"Abstract Metal-Nb 2 O 5−x -metal memdiodes exhibiting rectification, hysteresis, and capacitance are demonstrated for applications in neuromorphic circuitry. These devices do not require any post-fabrication treatments such as filament creation by electroforming that would impede circuit scalability. Instead these devices operate due to Poole-Frenkel defect controlled transport where the high defect density is inherent to the Nb 2 O 5−x deposition rather than post-fabrication treatments. Temperature dependent measurements reveal that the dominant trap energy is 0.22 eV suggesting it results from the oxygen deficiencies in the amorphous Nb 2 O 5−x . Rectification occurs due to a transition from thermionic emission to tunneling current and is present even in thick devices (&gt;100 nm) due to charge trapping which controls the tunneling distance. The turn-on voltage is linearly proportional to the Schottky barrier height and, in contrast to traditional metal-insulator-metal diodes, is logarithmically proportional to the device thickness. Hysteresis in the I – V curve occurs due to the current limited filling of traps.","url":"https://doi.org/10.1038/s41598-018-30727-9","authors":["Joshua C. Shank","M. Brooks Tellekamp","Matthew J. Wahila","Sebastian Howard","Alex S. Weidenbach","Bill Zivasatienraj","Louis F. J. Piper","W. Alan Doolittle"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-08-22T08:55:00Z","doi":"10.1038/s41598-018-30727-9","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/icnc64304.2024.10987831","name":"EV Load Forecasting Method Based on Data Reconstruction of GRU-WGAN and BiLSTM Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987831","authors":["Xinke Lv","Ping Bi","Lei Xiong","Min Zhang","Bingquan Li","Zongju Jiao","Yue Zhang","Wei Xu","Jian Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987831","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1145/3407197.3407221","name":"Coarse scale representation of spiking neural networks: backpropagation through spikes and application to neuromorphic hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3407197.3407221","authors":["Angel Yanguas-Gil"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-07-28T04:42:57Z","doi":"10.1145/3407197.3407221","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1088/1361-6641/abe31c","name":"FBFET (feedback field-effect transistor)-based oscillator for neuromorphic computing","source":"crossref","abstract":"Abstract In this work, we propose a non-linear oscillating circuit using hysteresis characteristics of a feedback field-effect transistor (FBFET). By varying the device design parameters of FBFET, it turned out that we can regulate (a) the size of the oscillation window and (b) the operating voltage of the oscillation circuit. The FBFET-based oscillator would pave a new road for efficient use of neuromorphic computing algorithms.","url":"https://doi.org/10.1088/1361-6641/abe31c","authors":["Changhoon Lee","Changhwan Shin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-02-05T08:54:58Z","doi":"10.1088/1361-6641/abe31c","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/embc.2018.8512868","name":"Real-Time Cardiac Arrhythmia Classification Using Memristor Neuromorphic Computing System","source":"crossref","abstract":"","url":"https://doi.org/10.1109/embc.2018.8512868","authors":["Amr M. Hassan","Aya F. Khalaf","Khaled S. Sayed","Hai Helen Li","Yiran Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-11-16T04:03:08Z","doi":"10.1109/embc.2018.8512868","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1063/5.0246384","name":"Resistive switching and synaptic characteristics in ZnO@β-SiC\n                    composite-based RRAM for neuromorphic computing","source":"crossref","abstract":"The advancement of neuromorphic computing in resistive random-access memory (RRAM) is crucial for the rapid expansion of artificial intelligence. Conventional metal oxide-based RRAM faces challenges in mimicking synaptic activity, leading to the exploration of new resistive switching (RS) materials. This study introduces a ZnO@β-SiC composite-based RRAM device that exhibits biological synapse-like functionality. The device shows self-compliance and forming-free RS at ∼0.8 V, where it also mimics synaptic responses such as potentiation, depression, and paired-pulse facilitation at low voltage stimuli (∼0.6 V, 40 ms) with learning and forgetting behavior. Moreover, the synaptic plasticity is analyzed through spike rate dependent plasticity, spike number dependent plasticity, and spike time dependent plasticity. Further, the transition from short-term plasticity to long-term plasticity is observed under more training pulses and lower interval stimuli. The observed RS mechanism and synaptic functionalities are explained by the electric field-driven formation and dissolution of conducting filaments of oxygen vacancies. The chemical properties and local electronic structure have been examined by x-ray photoelectron spectroscopy and x-ray absorption spectroscopy. To elucidate the atomistic memristive behavior and the contribution of different electrical parameters in RRAM, detailed conductive atomic-force microscopy and impedance analysis have been carried out.","url":"https://doi.org/10.1063/5.0246384","authors":["Bisweswar Santra","Gangadhar Das","Giuliana Aquilanti","Aloke Kanjilal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-28T15:53:36Z","doi":"10.1063/5.0246384","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1016/j.futures.2025.103756","name":"Anticipatory alignment work: The politics of anticipation in an emerging innovation ecosystem of neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.futures.2025.103756","authors":["Mareike Smolka","Philipp Neudert","Frieder Bögner","Wenzel Mehnert","Phil Macnaghten","Stefan Böschen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-19T17:01:33Z","doi":"10.1016/j.futures.2025.103756","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1016/b978-0-44-332820-6.00007-0","name":"Acknowledgments","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-44-332820-6.00007-0","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-28T07:47:19Z","doi":"10.1016/b978-0-44-332820-6.00007-0","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1088/2634-4386/ae688e","name":"FeNN-DMA: A RISC-V system-on-chip for spiking neural network acceleration","source":"crossref","abstract":"Abstract Spiking neural networks (SNNs) are a promising, energy-efficient alternative to standard artificial neural networks (ANNs) and are particularly well-suited to spatio-temporal tasks such as keyword spotting and video classification. However, SNNs have a much lower arithmetic intensity than ANNs and are therefore not well-matched to standard accelerators like Graphical Processing Units and Tensor Processing Units (TPUs). Field Programmable Gate Arrays (FPGAs) are designed for such memory-bound workloads, and here we present a novel, system-on-chip design using a RISC-V softcore with a vector co-processor (FeNN-DMA), tailored to simulating SNNs on modern UltraScale+ FPGAs. We show that FeNN-DMA has comparable resource usage and energy requirements to state-of-the-art fixed-function SNN accelerators, yet it supports more complex neuron models and network topologies, and can simulate up to 16 thousand neurons and 256 million synapses per core. Using this functionality, we demonstrate state-of-the-art classification accuracy on the Spiking Heidelberg Digits, Neuromorphic MNIST and Braille tactile classification tasks.","url":"https://doi.org/10.1088/2634-4386/ae688e","authors":["Zainab Aizaz","James C Knight","Thomas Nowotny"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-05T22:51:08Z","doi":"10.1088/2634-4386/ae688e","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/apccas67402.2025.11377411","name":"A Pipeline-Driven FPGA Accelerator with Memory-Scheduling for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/apccas67402.2025.11377411","authors":["Zhipeng Liao","Tianyang Li","Ziyang Shen","Chaoming Fang","Jie Yang","Mohamad Sawan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-19T20:54:40Z","doi":"10.1109/apccas67402.2025.11377411","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1038/s44172-022-00024-5","name":"High-speed photonic neuromorphic computing using recurrent optical spectrum slicing neural networks","source":"crossref","abstract":"Abstract Neuromorphic computing using photonic hardware is a promising route towards ultrafast processing while maintaining low power consumption. Here we present and numerically evaluate a hardware concept for realizing photonic recurrent neural networks and reservoir computing architectures. Our method, called Recurrent Optical Spectrum Slicing Neural Networks (ROSS-NNs), uses simple optical filters placed in a loop, where each filter processes a specific spectral slice of the incoming optical signal. The synaptic weights in our scheme are equivalent to the filters’ central frequencies and bandwidths. Numerical application to high baud rate optical signal equalization (&gt;100 Gbaud) reveals that ROSS-NN extends optical signal transmission reach to &gt; 60 km, more than four times that of two state-of-the-art digital equalizers. Furthermore, ROSS-NN relaxes complexity, requiring less than 100 multiplications/bit in the digital domain, offering tenfold reduction in power consumption with respect to these digital counterparts. ROSS-NNs hold promise for efficient photonic hardware accelerators tailored for processing high-bandwidth (&gt;100 GHz) optical signals in optical communication and high-speed imaging applications.","url":"https://doi.org/10.1038/s44172-022-00024-5","authors":["Kostas Sozos","Adonis Bogris","Peter Bienstman","George Sarantoglou","Stavros Deligiannidis","Charis Mesaritakis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-26T06:05:36Z","doi":"10.1038/s44172-022-00024-5","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1186/s43074-020-0001-6","name":"Perspective on photonic memristive neuromorphic computing","source":"crossref","abstract":"Abstract Neuromorphic computing applies concepts extracted from neuroscience to develop devices shaped like neural systems and achieve brain-like capacity and efficiency. In this way, neuromorphic machines, able to learn from the surrounding environment to deduce abstract concepts and to make decisions, promise to start a technological revolution transforming our society and our life. Current electronic implementations of neuromorphic architectures are still far from competing with their biological counterparts in terms of real-time information-processing capabilities, packing density and energy efficiency. A solution to this impasse is represented by the application of photonic principles to the neuromorphic domain creating in this way the field of neuromorphic photonics. This new field combines the advantages of photonics and neuromorphic architectures to build systems with high efficiency, high interconnectivity and high information density, and paves the way to ultrafast, power efficient and low cost and complex signal processing. In this Perspective, we review the rapid development of the neuromorphic computing field both in the electronic and in the photonic domain focusing on the role and the applications of memristors. We discuss the need and the possibility to conceive a photonic memristor and we offer a positive outlook on the challenges and opportunities for the ambitious goal of realising the next generation of full-optical neuromorphic hardware.","url":"https://doi.org/10.1186/s43074-020-0001-6","authors":["Elena Goi","Qiming Zhang","Xi Chen","Haitao Luan","Min Gu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-03-03T00:06:38Z","doi":"10.1186/s43074-020-0001-6","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1088/2634-4386/ad6cef","name":"Understanding the functional roles of modelling components in spiking neural networks","source":"openalex","abstract":"Abstract Spiking neural networks (SNNs), inspired by the neural circuits of the brain, are promising in achieving high computational efficiency with biological fidelity. Nevertheless, it is quite difficult to optimize SNNs because the functional roles of their modelling components remain unclear. By designing and evaluating several variants of the classic model, we systematically investigate the functional roles of key modelling components, leakage, reset, and recurrence, in leaky integrate-and-fire (LIF) based SNNs. Through extensive experiments, we demonstrate how these components influence the accuracy, generalization, and robustness of SNNs. Specifically, we find that the leakage plays a crucial role in balancing memory retention and robustness, the reset mechanism is essential for uninterrupted temporal processing and computational efficiency, and the recurrence enriches the capability to model complex dynamics at a cost of robustness degradation. With these interesting observations, we provide optimization suggestions for enhancing the performance of SNNs in different scenarios. This work deepens the understanding of how SNNs work, which offers valuable guidance for the development of more effective and robust neuromorphic models.","url":"https://doi.org/10.1088/2634-4386/ad6cef","authors":["Huifeng Yin","Hanle Zheng","Jiayi Mao","Siyuan Ding","Xing Liu","Mingkun Xu","Yifan Hu","Jing Pei","Lei Deng"],"tags":["Robustness (evolution)","Spiking neural network","Computer science","Artificial intelligence","Neuromorphic engineering"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-08-08","doi":"10.1088/2634-4386/ad6cef","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"doi:10.1109/ted.2022.3209957","name":"Resistive Switching and Synaptic Behavior of Perovskite Lanthanum Orthoferrite Thin Film for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ted.2022.3209957","authors":["Amit Kumar Shringi","Atanu Betal","Satyajit Sahu","Michael Saliba","Mahesh Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-12T19:39:17Z","doi":"10.1109/ted.2022.3209957","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1007/978-981-96-6406-1_9","name":"Neuromorphic Computing Using RRAM","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-96-6406-1_9","authors":["Bakkesh V. Amoghimath","H. M. Vijay","Suhas B. Shirol"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-01T00:56:35Z","doi":"10.1007/978-981-96-6406-1_9","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.29003/m3098.mmmsec-2022/156-159","name":"ANALYSIS OF THE ELEMENT BASE AND CIRCUIT DESIGN FOR NEUROMORPHIC COMPUTING ON MEMRISTOR CROSSBARS","source":"crossref","abstract":"The variants of circuit solutions for analog matrix-vector calculations on crossbars with memristors – bipolar with programmable value of resistance installed in their nodes are considered","url":"https://doi.org/10.29003/m3098.mmmsec-2022/156-159","authors":["O. Telminov","E. Gornev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-23T10:16:36Z","doi":"10.29003/m3098.mmmsec-2022/156-159","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.3389/fnano.2021.782836","name":"ReSe2-Based RRAM and Circuit-Level Model for Neuromorphic Computing","source":"crossref","abstract":"Resistive random-access memory (RRAM) devices have drawn increasing interest for the simplicity of its structure, low power consumption and applicability to neuromorphic computing. By combining analog computing and data storage at the device level, neuromorphic computing system has the potential to meet the demand of computing power in applications such as artificial intelligence (AI), machine learning (ML) and Internet of Things (IoT). Monolayer rhenium diselenide (ReSe 2 ), as a two-dimensional (2D) material, has been reported to exhibit non-volatile resistive switching (NVRS) behavior in RRAM devices with sub-nanometer active layer thickness. In this paper, we demonstrate stable multiple-step RESET in ReSe 2 RRAM devices by applying different levels of DC electrical bias. Pulse measurement has been conducted to study the neuromorphic characteristics. Under different height of stimuli, the ReSe 2 RRAM devices have been found to switch to different resistance states, which shows the potentiation of synaptic applications. Long-term potentiation (LTP) and depression (LTD) have been demonstrated with the gradual resistance switching behaviors observed in long-term plasticity programming. A Verilog-A model is proposed based on the multiple-step resistive switching behavior. By implementing the LTP/LTD parameters, an artificial neural network (ANN) is constructed for the demonstration of handwriting classification using Modified National Institute of Standards and Technology (MNIST) dataset.","url":"https://doi.org/10.3389/fnano.2021.782836","authors":["Yifu Huang","Yuqian Gu","Xiaohan Wu","Ruijing Ge","Yao-Feng Chang","Xiyu Wang","Jiahan Zhang","Deji Akinwande","Jack C. Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-19T06:19:59Z","doi":"10.3389/fnano.2021.782836","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/icnc64304.2024.10987614","name":"FRMAdam-iTransformer KAN: A Fractional Order RMS Momentum Adam Optimized iTransformer with KAN for EEG and ECG Prediction","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987614","authors":["Xinrui Zhang","Jiejie Chen","Xuewen Zhou","Ping Jiang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987614","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1063/5.0308306","name":"Dynamic capacitive analysis and physical modeling on ZnO resistive random access memory (RRAM) for enabling neuromorphic computing","source":"crossref","abstract":"With the increasing demand for large data storage and artificial intelligence, resistive random-access memory (RRAM) thrives as one of the applicable candidates for the next-generation nonvolatile memory, owing to its simple structure, high scalability, high speed, low power, and tunable conductance. Among oxide-based RRAM, ZnO shows unique optical and electrical properties toward the future heterogeneous integration and low power memory-in-computing systems. In this study, we present a ZnO RRAM manufactured under earth gravity and in-space through inkjet printing. Memory devices with various fabrication environments and conditions include methanol ground, methanol flight, ethanol ground, to ethanol flight. The device fabricated under the microgravity shows a significantly reduced forming voltage and improved reliability. To investigate the filamentary formation in the ZnO RRAM, activation energy was extracted from Arrhenius equations on temperature modulations testing schemes for a comprehensive filament modeling. The capacitive models have concluded oxygen migration conduction dominated on this ZnO RRAM. Finally, the devices' conductance was modulated by AC potentiation and depression with an optimized linearity (R2 = 98%) toward a good training accuracy of 90% on the MNIST data set training toward neuromorphic computing.","url":"https://doi.org/10.1063/5.0308306","authors":["Yujian Huang","Sai Prakash Maddineni","Daphne Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-09T17:14:52Z","doi":"10.1063/5.0308306","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.5772/acrt.deposit.32253477.v1","name":"Neuromorphic Computing in Outer Space: Intel Loihi Deployed On-Satellite for Spike-Based Software-Defined Communication - Python Code","source":"crossref","abstract":"&lt;p dir=\"ltr\"&gt;In space exploration and communication technology, software-defined networking architectures significantly improve the communications throughput and latency. This study developed a cognitive agent based on Q-learning with continuous learning capabilities to select optimal routing options in a dynamically changing networking environment. This proposed method achieves up to 90% reduction in measured Internet Control Message Protocol (ICMP) round-trip time compared to the Dijkstra shortest-path baseline under identical test conditions. Under dynamically changing network link latency conditions, the cognitive agent achieved a 90% success rate in routing packets in laboratory experiments. The agent was executed on neuromorphic hardware called Intel Loihi. However, due to the system’s power limitations, a simplified version of the agent was engineered to launch into space aboard a CubeSat. The CubeSat was launched in January 2022, making a historic milestone as the first launch of a neuromorphic system into space. The developed applications were successfully executed in space.&lt;/p&gt;","url":"https://doi.org/10.5772/acrt.deposit.32253477.v1","authors":["Nayim Rahman","Chris Yakopcic","Tarek Taha","Ricardo Lent","Janette Briones","David Chelmins","Rachel Dudukovich","Aaron Smith","Adam Gannon","Michael Lowry","Marcus Murbach","Alejandro Salas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-12T13:42:22Z","doi":"10.5772/acrt.deposit.32253477.v1","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1002/adma.201802353","name":"Low‐Power, Electrochemically Tunable Graphene Synapses for Neuromorphic Computing","source":"crossref","abstract":"Abstract Brain‐inspired neuromorphic computing has the potential to revolutionize the current computing paradigm with its massive parallelism and potentially low power consumption. However, the existing approaches of using digital complementary metal–oxide–semiconductor devices (with “0” and “1” states) to emulate gradual/analog behaviors in the neural network are energy intensive and unsustainable; furthermore, emerging memristor devices still face challenges such as nonlinearities and large write noise. Here, an electrochemical graphene synapse, where the electrical conductance of graphene is reversibly modulated by the concentration of Li ions between the layers of graphene is presented. This fundamentally different mechanism allows to achieve a good energy efficiency (&lt;500 fJ per switching event), analog tunability (&gt;250 nonvolatile states), good endurance, and retention performances, and a linear and symmetric resistance response. Essential neuronal functions such as excitatory and inhibitory synapses, long‐term potentiation and depression, and spike timing dependent plasticity with good repeatability are demonstrated. The scaling study suggests that this simple, two‐dimensional synapse is scalable in terms of switching energy and speed.","url":"https://doi.org/10.1002/adma.201802353","authors":["Mohammad Taghi Sharbati","Yanhao Du","Jorge Torres","Nolan D. Ardolino","Minhee Yun","Feng Xiong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-07-23T04:02:42Z","doi":"10.1002/adma.201802353","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/insect68872.2026.11663942","name":"Area-Scalable Al/Cu/AlO\n                    <sub>x</sub>\n                    /TiN CBRAM Memristors via Thermal Evaporation: Electroforming Behaviour, Charge Transport, and Neuromorphic Characterization","source":"crossref","abstract":"","url":"https://doi.org/10.1109/insect68872.2026.11663942","authors":["Anirudha Deogaonkar","Jagadish Rajpoot","Roopesh Singh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-31T19:07:23Z","doi":"10.1109/insect68872.2026.11663942","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1088/1361-6463/ae1241","name":"Recent progress in neuromorphic computing based on spin–orbit torque devices","source":"crossref","abstract":"Abstract Neuromorphic computing, inspired by the structure and functionality of the biological brain, aims to simulate brain processes through the design of innovative devices, algorithms, and architectures. Neuromorphic devices constitute the foundational hardware components essential for the realization of neuromorphic computing. In recent years, spintronic devices based on the spin–orbit torque (SOT) effect have emerged as the central focus due to their exceptional durability, rapid response times, and low energy consumption. By designing SOT devices with diverse structures and functionalities, researchers have successfully emulated the roles of synapses and neurons in the human brain, thereby enabling the execution of neuromorphic computing tasks. This paper presents a comprehensive review of recent advancements in the application of SOT spintronic devices for neuromorphic computing. We first introduce the underlying mechanisms and testing methods of SOT spintronic devices, then commence with an introduction to biological neural networks in the human brain, followed by an exposition of widely adopted algorithmic architectures and hardware requirements for neuromorphic computing based on SOT devices. After that, we discuss the practical applications of four primary types of SOT devices: Domain Wall (DW)-SOT, Skyrmion-SOT, Nucleation-SOT, and spin Hall nano-oscillators in neuromorphic computing. Finally, we address the current challenges in the field and proposes potential solutions for the future.","url":"https://doi.org/10.1088/1361-6463/ae1241","authors":["Qi Liang","Yujie Huang","Yinlong Tan","Yuhua Tang","Xiangnan Xie"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-13T22:48:19Z","doi":"10.1088/1361-6463/ae1241","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/icnc52316.2021.9607990","name":"Fixed-time Stabilization of Delayed Neural Networks: A Switching Control Framework Design","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc52316.2021.9607990","authors":["Yuchun Wang","Song Zhu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-29T20:59:32Z","doi":"10.1109/icnc52316.2021.9607990","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1049/cje.2018.05.006","name":"A Survey of Neuromorphic Computing Based on Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1049/cje.2018.05.006","authors":["Ming ZHANG","Zonghua GU","Gang PAN"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-08-15T18:15:30Z","doi":"10.1049/cje.2018.05.006","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1039/d1nr06680c","name":"Emerging dynamic memristors for neuromorphic reservoir computing","source":"crossref","abstract":"This work reviews the state-of-the-art physical reservoir computing systems based on dynamic memristors integrating with unique nonlinear dynamics and short-term memory behavior. The key characteristics, challenges and perspectives are also discussed.","url":"https://doi.org/10.1039/d1nr06680c","authors":["Jie Cao","Xumeng Zhang","Hongfei Cheng","Jie Qiu","Xusheng Liu","Ming Wang","Qi Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-01T20:40:57Z","doi":"10.1039/d1nr06680c","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/icsped65817.2026.11448357","name":"Beyond CMOS: Neuromorphic and Quantum Inspired VLSI for the Next Era of Intelligent Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icsped65817.2026.11448357","authors":["Akram Ahamed S","Trisha A S","Vaishnavi S","Neveythithaa S","Yuvaraj G","Augustine Fletcher A S"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-25T19:54:09Z","doi":"10.1109/icsped65817.2026.11448357","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/mwscas60917.2024.10658951","name":"Enhancing Neuromorphic Computing: A High-Speed, Low-Power Integrate-and-Fire Neuron Circuit Utilizing Nanoscale Side-Contacted Field Effect Diode Technology","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mwscas60917.2024.10658951","authors":["SeyedMohamadJavad Motaman","Sarah Safura Sharifi","Yaser Michael Banad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-16T17:34:29Z","doi":"10.1109/mwscas60917.2024.10658951","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.4018/979-8-3693-6303-4.ch007","name":"An NLP Approach to Enrich Biomedical Research Through Sentiment Analysis of Patient Feedback","source":"crossref","abstract":"This chapter consults the trajectory committed by utilizing patient feedback (PF) in the wake of biomedical research through sentimental analysis (SA) in natural language processing (NLP). PF has been compared to a gold mine for the healthcare industry as it delivers clinical efficacy and preserves quality. Analyzing these patient responses is vastly more time-consuming and subjective. SA employment can efficiently extract beneficial insights from this feedback by automating patients' positive, negative, or neutral sentiments. By systematically examining millions of remarks to identify familiar themes, distinct concerns, and patient satisfaction levels, researchers can employ these sentiments to understand disease status and assist in making intelligent decisions. SA can work with structured and unstructured sentiment data from mixed social media posts and electronic health records to produce favorable results, allowing researchers to improve biomedical research. Eventually, this chapter uncloses worthwhile wisdom to enrich biomedical research by employing PF through SA.","url":"https://doi.org/10.4018/979-8-3693-6303-4.ch007","authors":["Soumitra Saha","Umesh Kumar Lilhore","Sarita Simaiya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-29T15:16:27Z","doi":"10.4018/979-8-3693-6303-4.ch007","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1109/icnc59488.2023.10462868","name":"Chaotic Oscillation Systems with Disturbance Based on DNA Strand Displacement and Its Active Control","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462868","authors":["Ce Sun","Chuangchuang Li","Junwei Sun","Yanfeng Wang","Peng Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462868","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1063/5.0082061","name":"Electrolyte-gated transistors with good retention for neuromorphic computing","source":"crossref","abstract":"Electrolyte-gated transistors (EGTs) provide prominent analog switching performance for neuromorphic computing. However, suffering from self-discharging nature, the retention performance greatly hampers their practical applications. In this Letter, we realize a significant improvement in EGT retention by inserting a SiO2 layer between the gate electrode and electrolyte. The dynamic process behind the improvement is interpreted by an assumptive leakage-assisted electrochemical mechanism. In addition to improved retention, analog switching with a large dynamic range, superior linearity and symmetry, and low variation has been achieved using identical voltage pulses. Based on the experimental data, a nearly ideal recognition accuracy of 98% has been demonstrated by simulations using the handwritten digit data sets. The obtained results pave a way for employing EGT in future neuromorphic computing.","url":"https://doi.org/10.1063/5.0082061","authors":["Yue Li","Han Xu","Jikai Lu","Zuheng Wu","Shuyu Wu","Xumeng Zhang","Qi Liu","Dashan Shang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-01-11T10:38:12Z","doi":"10.1063/5.0082061","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1007/s40820-022-00816-6","name":"Correction to: Memristive Devices Based on Two-Dimensional Transition Metal Chalcogenides for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s40820-022-00816-6","authors":["Ki Chang Kwon","Ji Hyun Baek","Kootak Hong","Soo Young Kim","Ho Won Jang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-05T18:02:44Z","doi":"10.1007/s40820-022-00816-6","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/tc.2012.50","name":"A Parallel Neuromorphic Text Recognition System and Its Implementation on a Heterogeneous High-Performance Computing Cluster","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tc.2012.50","authors":["Qinru Qiu","Qing Wu","Morgan Bishop","Robinson E. Pino","Richard W. Linderman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-02-27T21:47:12Z","doi":"10.1109/tc.2012.50","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1149/ma2025-01633076mtgabs","name":"Tuning Synaptic Plasticity in WO<sub>3</sub> Ion-Gated Transistors with Aqueous Electrolytes for Neuromorphic Computing","source":"crossref","abstract":"Ion-Gated Transistors (IGTs) are a promising technology for neuromorphic computing, offering processing rates and energy efficiency. These devices support low-power training and operation of neural network algorithms while integrating both long-term and short-term modulation within a single system. The suitability of IGTs for neuromorphic applications depends critically on their time-resolved behaviour, governed by the doping mechanism. Specifically, the ionic permeability of the semiconducting channel dictates whether the device operates via electrochemical (three-dimensional) or electrostatic (two-dimensional) doping, leading to varying response times. This work focuses on controlling the response time of WO 3 -based IGTs using aqueous electrolytes—Li 2 SO 4 , Na 2 SO 4 , and K 2 SO 4 —as the gating media. We systematically study the effects of gate-source voltage (V gs ) pulse parameters (frequency, duration, and number) and sampling time on synaptic behaviour. These parameters are tuned to optimize ion intercalation and channel conductivity, enabling precise modulation of synaptic plasticity. Our findings demonstrate the tunability of WO 3 -based IGTs for neuromorphic applications, providing insights into the interplay between ion gating medium properties and channel dynamics. This work highlights the potential of these devices for energy-efficient and adaptive artificial synapses.","url":"https://doi.org/10.1149/ma2025-01633076mtgabs","authors":["Kesawarthini Bhaskaran","Ramin Karimi Azari","Melchiade Manirakiza","Clara Santato","Francesca Soavi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-21T08:01:14Z","doi":"10.1149/ma2025-01633076mtgabs","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1039/d3ra06853f","name":"Enhanced electrical and magnetic properties of (Co, Yb) co-doped ZnO memristor for neuromorphic computing","source":"crossref","abstract":"Functional comparison between a biological synapse and a memristor.","url":"https://doi.org/10.1039/d3ra06853f","authors":["Noureddine Elboughdiri","Shahid Iqbal","Sherzod Abdullaev","Mohammed Aljohani","Akif Safeen","Khaled Althubeiti","Rajwali Khan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-11T07:22:28Z","doi":"10.1039/d3ra06853f","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.22381/rcp22202311","name":"Neural Network-based Recognition and Virtual Simulation Algorithms, Interactive 3D Geo-Visualization and Neuromorphic Computing Systems, and Tactile Sensing and Cognitive Modeling Technologies in Web3-powered Metaverse Worlds","source":"crossref","abstract":"","url":"https://doi.org/10.22381/rcp22202311","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-16T06:51:57Z","doi":"10.22381/rcp22202311","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1007/978-1-4939-6883-1_702","name":"Principles of Neuromorphic Photonics","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4939-6883-1_702","authors":["Bhavin J. Shastri","Alexander N. Tait","Thomas Ferreira de Lima","Mitchell A. Nahmias","Hsuan-Tung Peng","Paul R. Prucnal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-08-25T13:23:51Z","doi":"10.1007/978-1-4939-6883-1_702","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1088/2634-4386/ac970d","name":"Efficient spatio-temporal feature clustering for large event-based datasets","source":"crossref","abstract":"Abstract Event-based cameras encode changes in a visual scene with high temporal precision and low power consumption, generating millions of events per second in the process. Current event-based processing algorithms do not scale well in terms of runtime and computational resources when applied to a large amount of data. This problem is further exacerbated by the development of high spatial resolution vision sensors. We introduce a fast and computationally efficient clustering algorithm that is particularly designed for dealing with large event-based datasets. The approach is based on the expectation-maximization (EM) algorithm and relies on a stochastic approximation of the E-step over a truncated space to reduce the computational burden and speed up the learning process. We evaluate the quality, complexity, and stability of the clustering algorithm on a variety of large event-based datasets, and then validate our approach with a classification task. The proposed algorithm is significantly faster than standard k-means and reduces computational demands by two to three orders of magnitude while being more stable, interpretable, and close to the state of the art in terms of classification accuracy.","url":"https://doi.org/10.1088/2634-4386/ac970d","authors":["Omar Oubari","Georgios Exarchakis","Gregor Lenz","Ryad Benosman","Sio-Hoi Ieng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-03T22:17:50Z","doi":"10.1088/2634-4386/ac970d","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1149/ma2024-01573019mtgabs","name":"(Invited) There’s More to a Probabilistic Neuromorphic Computing System Than Noisy Devices","source":"crossref","abstract":"A range of computing problems require understanding uncertainty, such as climate modeling, or use statistics to model problems that are otherwise difficult to solve, such as high energy particle collisions. Currently, these computations are handled by hardware where significant energy is spent to suppress stochasticity in materials and devices, and then significant computational resources are expended to re-introduce stochasticisty in algorithms. Instead, we take inspiration from the brain, which features 10 15 stochastic synapses. This talk focuses on understanding how to leverage fluctuations in devices to do efficient sampling, which is a fundamental operation in many statistical approaches to computation [1]. In the first part of this talk, we use bitstreams generated by magnetic tunnel junction and tunnel diode devices to generate samples from different distributions, an elementary operation in statistical approaches to modeling. We show how to use elementary operations on multiple bits to improve both the accuracy and complexity of sampling. While intuition motivates the asking which of the two devices is more efficient at generating a random bitstream, in the second part of this talk, we show that this consideration is a small contribution to the overall circuit required to do a complete calculation. To significantly accelerate applications requires devices that minimize the energy and area cost of the CMOS parts of the design, as the true challenge lies in holistic codesign [2]. At the heart of statistical approaches to computation is sampling. Typically, a uniform random sample is generated using a pseudo-random number generator (PRNG), followed by a mathematical operation to sample an application-relevant distribution. This sample is then plugged into a sequence of deterministic calculations that comprise a model. We use magnetic tunnel junctions and tunnel diodes to generate a fair coinflip, having equal probability of each of two outscomes, from which we create a uniform random sample. We show how to relate the quality of the device bitstreams to the quality of random samples [3]. While these devices consume significantly less energy than the PRNG, the energy consumed by the PRNG is a fraction of the energy consumed by a complete calculation. We next focus on moving the entire process of sampling non-uniform distributions into hardware. We show that weighted coinflips can be used to sample any distribution with a well-defined probability distribution function using a tree. Simple logic operations can be used to combine many inaccurate fair physical coinflips to produce a single high-accuracy weighted logical coinflip, and high quality samples from non-uniform distributions. Overall, a simple implementation uses a few hundred physical coinflips, some simple logic operations (shift register, comparison, XOR extractor), and memory access to produce a sample. This success points to the potential for moving more of the model into increasingly sophisticated sampling schemes. Having established how the basic element of the computation are connected, we are now ready to examine its efficiency compared to a PRNG, whose cost is roughly nJ/operation. Thus far, we have ignored the analog signal transduction attached to the coinflip devices and the logic operations that tie them together. Coinflip devices which cannot be directly integrated with logic will suffer from a von Neumann bottleneck. Thus, the coinflip devices need to be intimately integrated with logic, requiring paying a per-device transduction penalty. We find the energy cost for even the simplest signal transduction – a stimulating pulse and a latching output – is in the 100 fJ – 1 pJ per device range, which is larger than the energy consumed by either magnetic tunnel junctions or tunnel diodes. Meanwhile, the most expensive component of the logic operations stem from the fine-grained integration of memory. While only 32 weighted coinflips are needed to draw a 32-","url":"https://doi.org/10.1149/ma2024-01573019mtgabs","authors":["Shashank Misra","Christopher R. Allemang","J. Darby Smith","Suma G. Cardwell","James B. Aimone","Andrew D. Kent"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-19T15:54:21Z","doi":"10.1149/ma2024-01573019mtgabs","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/ted.2023.3324898","name":"Voltage-Gated Domain Wall Magnetic Tunnel Junction for Neuromorphic Computing Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ted.2023.3324898","authors":["Aijaz H. Lone","Hanrui Li","Nazek El-Atab","Gianluca Setti","Hossein Fariborzi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-27T13:50:24Z","doi":"10.1109/ted.2023.3324898","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1016/j.synthmet.2023.117360","name":"Poly 3-methylthiophene based memristor device for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.synthmet.2023.117360","authors":["Shobith M Shanbogh","Ashish Varade","Anju kumari","Anjaneyulu P."],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-27T17:04:36Z","doi":"10.1016/j.synthmet.2023.117360","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.12677/mos.2025.145423","name":"Artificial Electrochromic Synapses for Optical Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.12677/mos.2025.145423","authors":["成宇 刘"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T02:43:41Z","doi":"10.12677/mos.2025.145423","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.26599/nre.2025.9120187","name":"Flexible and self-powered paper-based artificial synapse for neuromorphic computing and 3d information transmission","source":"crossref","abstract":"","url":"https://doi.org/10.26599/nre.2025.9120187","authors":["Nuo Xu","Yifei Wang","Ziwei Huo","Jinran Yu","Jiahong Yang","Zhong Lin Wang","Qijun Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-13T05:42:14Z","doi":"10.26599/nre.2025.9120187","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1007/s12274-021-3452-6","name":"Memory-centric neuromorphic computing for unstructured data processing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s12274-021-3452-6","authors":["Sang Hyun Sung","Tae Jin Kim","Hera Shin","Hoon Namkung","Tae Hong Im","Hee Seung Wang","Keon Jae Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-04-13T10:19:15Z","doi":"10.1007/s12274-021-3452-6","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/jphotov.2023.3234504","name":"Call for Papers for a Special Issue of IEEE Journal of the Electron Devices Society on “Materials, processing and integration for neuromorphic devices and in-memory computing”","source":"crossref","abstract":"","url":"https://doi.org/10.1109/jphotov.2023.3234504","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-12T21:18:33Z","doi":"10.1109/jphotov.2023.3234504","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/tmscs.2017.2761231","name":"Parameter Exploration to Improve Performance of Memristor-Based Neuromorphic Architectures","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tmscs.2017.2761231","authors":["Mahyar Shahsavari","Pierre Boulet"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-10-09T18:11:42Z","doi":"10.1109/tmscs.2017.2761231","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1007/978-981-92-1599-7","name":"Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-92-1599-7","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-14T18:16:50Z","doi":"10.1007/978-981-92-1599-7","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/tcds.2018.2835107","name":"Guest Editorial Special Issue on Neuromorphic Computing and Cognitive Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tcds.2018.2835107","authors":["Huajin Tang","Tiejun Huang","Jeffrey L. Krichmar","Garrick Orchard","Arindam Basu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-06-08T19:01:06Z","doi":"10.1109/tcds.2018.2835107","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/dtis.2019.8734967","name":"Spin-Torque-Nano-Oscillator based neuromorphic computing assisted by laser","source":"crossref","abstract":"","url":"https://doi.org/10.1109/dtis.2019.8734967","authors":["Hooman Farkhani","Tim Bohnert","Mohammad Tarequzzaman","Diogo Costa","Alex Jenkins","Ricardo Ferreira","Farshad Moradi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-06-13T22:34:52Z","doi":"10.1109/dtis.2019.8734967","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/icnc59488.2023.10462745","name":"Dynamic Characteristic Analysis of FN-HR Neural Network Based on Synapse Coupling of Bistable Memristor","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462745","authors":["Chuangchuang Li","Ce Sun","Yanfeng Wang","Junwei Sun","Peng Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462745","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1145/2463209.2488741","name":"Digital-assisted noise-eliminating training for memristor crossbar-based analog neuromorphic computing engine","source":"crossref","abstract":"","url":"https://doi.org/10.1145/2463209.2488741","authors":["Beiye Liu","Miao Hu","Hai Li","Zhi-Hong Mao","Yiran Chen","Tingwen Huang","Wei Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-05-28T16:35:41Z","doi":"10.1145/2463209.2488741","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1145/3109453.3123961","name":"Towards spiking neuromorphic system-on-a-chip with bio-plausible synapses using emerging devices","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3109453.3123961","authors":["Vishal Saxena","Xinyu Wu","Ira Srivastava","Kehan Zhu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-09-01T12:27:52Z","doi":"10.1145/3109453.3123961","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1063/5.0149393","name":"A review on device requirements of resistive random access memory (RRAM)-based neuromorphic computing","source":"crossref","abstract":"With the arrival of the era of big data, the conventional von Neumann architecture is now insufficient owing to its high latency and energy consumption that originate from its separated computing and memory units. Neuromorphic computing, which imitates biological neurons and processes data through parallel procedures between artificial neurons, is now regarded as a promising solution to address these restrictions. Therefore, a device with analog switching for weight update is required to implement neuromorphic computing. Resistive random access memory (RRAM) devices are one of the most promising candidates owing to their fast-switching speed and scalability. RRAM is a non-volatile memory device and operates via resistance changes in its insulating layer. Many RRAM devices exhibiting exceptional performance have been reported. However, these devices only excel in one property. Devices that exhibit excellent performance in all aspects have been rarely proposed. In this Research Update, we summarize five requirements for RRAM devices and discuss the enhancement methods for each aspect. Finally, we suggest directions for the advancement of neuromorphic electronics.","url":"https://doi.org/10.1063/5.0149393","authors":["Jeong Hyun Yoon","Young-Woong Song","Wooho Ham","Jeong-Min Park","Jang-Yeon Kwon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-06T16:32:21Z","doi":"10.1063/5.0149393","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/tnano.2015.2438231","name":"Wave Interference Functions for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnano.2015.2438231","authors":["Mostafizur Rahman","Santosh Khasanvis","Jiajun Shi","Csaba Andras Moritz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-06-03T20:41:45Z","doi":"10.1109/tnano.2015.2438231","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1088/2634-4386/ac4917","name":"Digital coded exposure formation of frames from event-based imagery","source":"crossref","abstract":"Abstract Event-driven neuromorphic imagers have a number of attractive properties including low-power consumption, high dynamic range, the ability to detect fast events, low memory consumption and low band-width requirements. One of the biggest challenges with using event-driven imagery is that the field of event data processing is still embryonic. In contrast, decades worth of effort have been invested in the analysis of frame-based imagery. Hybrid approaches for applying established frame-based analysis techniques to event-driven imagery have been studied since event-driven imagers came into existence. However, the process for forming frames from event-driven imagery has not been studied in detail. This work presents a principled digital coded exposure approach for forming frames from event-driven imagery that is inspired by the physics exploited in a conventional camera featuring a shutter. The technique described in this work provides a fundamental tool for understanding the temporal information content that contributes to the formation of a frame from event-driven imagery data. Event-driven imagery allows for the application of arbitrary virtual digital shutter functions to form the final frame on a pixel-by-pixel basis. The proposed approach allows for the careful control of the spatio-temporal information that is captured in the frame. Furthermore, unlike a conventional physical camera, event-driven imagery can be formed into any variety of possible frames in post-processing after the data is captured. Furthermore, unlike a conventional physical camera, coded-exposure virtual shutter functions can assume arbitrary values including positive, negative, real, and complex values. The coded exposure approach also enables the ability to perform applications of industrial interest such as digital stroboscopy without any additional hardware. The ability to form frames from event-driven imagery in a principled manner opens up new possibilities in the ability to use conventional frame-based image processing techniques on event-driven imagery.","url":"https://doi.org/10.1088/2634-4386/ac4917","authors":["Andrew Gothard","Daniel Jones","Andre Green","Michael Torrez","Alessandro Cattaneo","David Mascareñas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-01-07T22:11:36Z","doi":"10.1088/2634-4386/ac4917","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.1109/icta56932.2022.9963062","name":"Photon-Memristive Device for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icta56932.2022.9963062","authors":["Yuqing Fang","Qingxuan Li","Tianyu Wang","Jialin Meng","QingQing Sun","David Wei Zhang","Lin Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-02T21:06:48Z","doi":"10.1109/icta56932.2022.9963062","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.58723/ijsei.v2i1.151","name":"Neuromorphic Computing Chips for Edge AI: A Comprehensive Analysis of Brain-Inspired Hardware Architecture for Real-Time Intelligent Systems","source":"crossref","abstract":"Background of study: Edge computing devices like autonomous robots and IoT sensors need sophisticated AI for real-time decisions, but conventional processors consume 15-300 watts during inference, creating critical limitations for battery-powered deployments. GPU-based accelerators face memory bottlenecks and high energy costs from data movement, making sustained autonomous operation impractical. Aims of paper: This research compares neuromorphic platforms (Intel Loihi 2, IBM TrueNorth, BrainChip Akida) against conventional accelerators (NVIDIA Jetson, Google Coral) to evaluate if neuromorphic architectures can solve edge AI energy efficiency challenges across five representative workloads. Methods: Using an experimental design with hardware benchmarking and power analysis, we evaluated five edge AI workloads. ANOVA and regression modeling were then applied to rigorously compare computing paradigms while controlling for variables. Result: Neuromorphic platforms demonstrated 15-50× improved energy efficiency versus conventional GPU accelerators for event-driven workloads. Intel Loihi 2 achieved 2,400 inferences/joule at 1.8 watts versus 180 inferences/joule at 18.5 watts for NVIDIA Jetson. IBM TrueNorth operated at 70 milliwatts for pattern recognition. BrainChip Akida achieved 94.6% accuracy on keyword spotting at 0.8 watts. Event-driven processing exhibited 0.4ms latency versus 5.1ms for frame-based systems. Neuromorphic chips maintained stable performance without active cooling below 65°C, while conventional accelerators required thermal management above 85°C. Conclusion: Neuromorphic processors (0.6-5W) excel in power-efficient edge AI for event-driven data. While hybrid architectures optimize performance, adoption is hindered by immature software ecosystems, limited training frameworks, and a 2-4% accuracy gap compared to conventional methods.","url":"https://doi.org/10.58723/ijsei.v2i1.151","authors":["Anwar Ali Sathio","Chiragh Kumar Maheshwari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-08T02:16:40Z","doi":"10.58723/ijsei.v2i1.151","addedAt":"2026-09-01T01:48:20.540Z","updatedAt":"2026-09-01T01:48:20.540Z"},{"id":"doi:10.5281/zenodo.20422179","name":"Verdigraph NeuroGenesis: A Software Framework for Self-Evolving AI-Agent Cognitive Substrates","source":"datacite","abstract":"Verdigraph NeuroGenesis v0.2.0 — software framework for self-evolving AI-agent cognitive substrates with mechanically verified operational invariants. Verdigraph is built on a simple observation: AI agents waste energy at industrial scale, and energy is carbon. Most agent frameworks treat the agent as a static assembly of prompts and tools — the same task runs through the same path every time, failed reasoning loops repeat, frontier models are called for trivial work, caches go unused. Every redundant token is a joule of electricity that produced no useful result. Verdigraph treats the agent instead as a developing cognitive system: pathways that work are strengthened, pathways that fail are weakened, specialized modules grow for recurring tasks, and structure that no longer earns its compute cost is pruned. The architecture is inspectable; the development is auditable through a per-agent developmental ledger; the optimization target is explicit: maximize information yield per joule, against the upper bound set by the Intelligence Bound (Hart 2025). What is new in v0.2.0 (vs v0.1.0): companion to the Verdigraph Operational Formalization manuscript. Operational invariants of the runtime are now mechanically verified — the safety, audit, and growth/prune rules that govern agent self-modification are stated as Lean 4 theorems and discharged in the Viridis Aristotle pipeline. The framework can no longer silently violate the invariants it claims to enforce; any violation is a type error before it is a runtime bug. Archive. verdigraph-neurogenesis-v0.2.0.zip — framework source, formalized operational invariants, MCP server stub, developmental-ledger schema, and test suite. MIT-licensed. Lineage. Part of the Viridis Compiled Theorem Stack (canon concept DOI 10.5281/zenodo.19317982); operational bridge to the Conservation Operator architecture introduced in canon v4 (Zenodo 20100595). This release consolidates v0.2.0 into the v0.1.0 concept-DOI chain (concept DOI 10.5281/zenodo.20261686). The earlier standalone v0.2.0 record (Zenodo 20400274, separate concept) is superseded by this canonical version and remains in place as an alternate identifier for the same archive. Citation. Hart, J. (2026). Verdigraph NeuroGenesis: A Software Framework for Self-Evolving AI-Agent Cognitive Substrates (v0.2.0). Zenodo. Concept DOI: https://doi.org/10.5281/zenodo.20261686 Viridis LLC, Columbia Falls, Montana, USA. Contact: viridisnorthllc@gmail.com.","url":"https://doi.org/10.5281/zenodo.20422179","authors":["Hart, Justin"],"tags":["artificial intelligence","AI agents","agent frameworks","Model Context Protocol","MCP","cognitive architecture","neuromorphic computing","compute efficiency"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20422179","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48550/arxiv.2605.27342","name":"Phase-Topology Classification of Memristor Hysteresis Loops via Self-Crossings","source":"datacite","abstract":"Memristive devices have revolutionized non-volatile memory and neuromorphic computing, yet the geometry of their hysteresis loops -- in particular, the occurrence and robustness of multiple self-crossings -- remains poorly understood. Here we introduce a topological and algebraic framework that treats the number of transverse self-intersections of a memristor hysteresis loop as a robust integer-valued invariant. Drawing on differential topology, singularity theory, and cusp catastrophe, we employ discriminants and resultants to stratify the six-dimensional parameter space. This approach partitions the parameter space into structurally stable regions separated by explicitly computable catastrophe surfaces. We demonstrate that the crossing number remains strictly invariant under continuous deformations and changes only at self-tangencies or cusp singularities, thereby providing a complete classification of all multi-lobed hysteresis behaviors. These insights bridge device physics with modern singularity theory and suggest a clear roadmap for exploiting higher-order memory effects in next-generation electronics and brain-inspired hardware.","url":"https://doi.org/10.48550/arxiv.2605.27342","authors":["Lipan, Ovidiu-Zeno","Neuhaus, Eric","Silva, Rafael Schio Wengenroth","Pradhan, Soumen","Hartmann, Fabian","Castelano, Leonardo K.","Silva, Ana Luiza Costa","Höfling, Sven","Lopez-Richard, Victor"],"tags":["Other Condensed Matter (cond-mat.other)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2605.27342","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20397720","name":"SymBrain: A Biomimetic Neuro-Symbolic Architecture for Small Language Models","source":"datacite","abstract":"SymBrain: A 3-hemisphere neuro-symbolic architecture using Qwen2.5-Math-7B and Ministral-8B coordinated by an executive Prefrontal Cortex bridge. Achieves SOTA reasoning for its class (GSM8K: 88.50%, MATH: 58.41%, Physics: 56.09%) with 21.9% power savings.","url":"https://doi.org/10.5281/zenodo.20397720","authors":["Callens, Xavier"],"tags":["Neuromorphic Computing","Neuro-Symbolic","Small Language Models","Green AI","Biomimetic Co-Inference","Prefrontal Cortex"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20397720","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20397719","name":"SymBrain: A Biomimetic Neuro-Symbolic Architecture for Small Language Models","source":"datacite","abstract":"SymBrain: A 3-hemisphere neuro-symbolic architecture using Qwen2.5-Math-7B and Ministral-8B coordinated by an executive Prefrontal Cortex bridge. Achieves SOTA reasoning for its class (GSM8K: 88.50%, MATH: 58.41%, Physics: 56.09%) with 21.9% power savings.","url":"https://doi.org/10.5281/zenodo.20397719","authors":["Callens, Xavier"],"tags":["Neuromorphic Computing","Neuro-Symbolic","Small Language Models","Green AI","Biomimetic Co-Inference","Prefrontal Cortex"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20397719","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20393091","name":"Biomimetic Co-Inference Learning: Bypassing Backpropagation via Telemetry-Guided Direct Feedback Alignment","source":"datacite","abstract":"WARS-CI-DFA: A high-performance, energy-efficient biomimetic learning loop on GCP Cloud TPU v5e bypassing backward propagation and saving 40% board power, formally verified in Lean 4.","url":"https://doi.org/10.5281/zenodo.20393091","authors":["Callens, Xavier"],"tags":["Neuromorphic Computing","Direct Feedback Alignment","GCP Cloud TPU v5e","Lean 4","Formal Verification","Green AI"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20393091","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20393090","name":"Biomimetic Co-Inference Learning: Bypassing Backpropagation via Telemetry-Guided Direct Feedback Alignment","source":"datacite","abstract":"WARS-CI-DFA: A high-performance, energy-efficient biomimetic learning loop on GCP Cloud TPU v5e bypassing backward propagation and saving 40% board power, formally verified in Lean 4.","url":"https://doi.org/10.5281/zenodo.20393090","authors":["Callens, Xavier"],"tags":["Neuromorphic Computing","Direct Feedback Alignment","GCP Cloud TPU v5e","Lean 4","Formal Verification","Green AI"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20393090","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20393019","name":"Biomimetic Co-Inference Learning: Bypassing Backpropagation via Telemetry-Guided Direct Feedback Alignment","source":"datacite","abstract":"WARS-CI-DFA: A high-performance, energy-efficient biomimetic learning loop on GCP Cloud TPU v5e bypassing backward propagation and saving 40% board power, formally verified in Lean 4.","url":"https://doi.org/10.5281/zenodo.20393019","authors":["Callens, Xavier"],"tags":["Neuromorphic Computing","Direct Feedback Alignment","GCP Cloud TPU v5e","Lean 4","Formal Verification","Green AI"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20393019","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20393020","name":"Biomimetic Co-Inference Learning: Bypassing Backpropagation via Telemetry-Guided Direct Feedback Alignment","source":"datacite","abstract":"WARS-CI-DFA: A high-performance, energy-efficient biomimetic learning loop on GCP Cloud TPU v5e bypassing backward propagation and saving 40% board power, formally verified in Lean 4.","url":"https://doi.org/10.5281/zenodo.20393020","authors":["Callens, Xavier"],"tags":["Neuromorphic Computing","Direct Feedback Alignment","GCP Cloud TPU v5e","Lean 4","Formal Verification","Green AI"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20393020","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20392809","name":"Biomimetic Co-Inference Learning: Bypassing Backpropagation via Telemetry-Guided Direct Feedback Alignment","source":"datacite","abstract":"WARS-CI-DFA: A high-performance, energy-efficient biomimetic learning loop on GCP Cloud TPU v5e bypassing backward propagation and saving 40% board power, formally verified in Lean 4.","url":"https://doi.org/10.5281/zenodo.20392809","authors":["Callens, Xavier"],"tags":["Neuromorphic Computing","Direct Feedback Alignment","GCP Cloud TPU v5e","Lean 4","Formal Verification","Green AI"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20392809","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20392808","name":"Biomimetic Co-Inference Learning: Bypassing Backpropagation via Telemetry-Guided Direct Feedback Alignment","source":"datacite","abstract":"WARS-CI-DFA: A high-performance, energy-efficient biomimetic learning loop on GCP Cloud TPU v5e bypassing backward propagation and saving 40% board power, formally verified in Lean 4.","url":"https://doi.org/10.5281/zenodo.20392808","authors":["Callens, Xavier"],"tags":["Neuromorphic Computing","Direct Feedback Alignment","GCP Cloud TPU v5e","Lean 4","Formal Verification","Green AI"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20392808","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20392597","name":"Biomimetic Co-Inference Learning: Bypassing Backpropagation via Telemetry-Guided Direct Feedback Alignment","source":"datacite","abstract":"WARS-CI-DFA: A high-performance, energy-efficient biomimetic learning loop on GCP Cloud TPU v5e bypassing backward propagation and saving 40% board power, formally verified in Lean 4.","url":"https://doi.org/10.5281/zenodo.20392597","authors":["Callens, Xavier"],"tags":["Neuromorphic Computing","Direct Feedback Alignment","GCP Cloud TPU v5e","Lean 4","Formal Verification","Green AI"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20392597","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20392598","name":"Biomimetic Co-Inference Learning: Bypassing Backpropagation via Telemetry-Guided Direct Feedback Alignment","source":"datacite","abstract":"WARS-CI-DFA: A high-performance, energy-efficient biomimetic learning loop on GCP Cloud TPU v5e bypassing backward propagation and saving 40% board power, formally verified in Lean 4.","url":"https://doi.org/10.5281/zenodo.20392598","authors":["Callens, Xavier"],"tags":["Neuromorphic Computing","Direct Feedback Alignment","GCP Cloud TPU v5e","Lean 4","Formal Verification","Green AI"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20392598","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20392548","name":"Biomimetic Co-Inference Learning: Bypassing Backpropagation via Telemetry-Guided Direct Feedback Alignment","source":"datacite","abstract":"WARS-CI-DFA: A high-performance, energy-efficient biomimetic learning loop on GCP Cloud TPU v5e bypassing backward propagation and saving 40% board power, formally verified in Lean 4.","url":"https://doi.org/10.5281/zenodo.20392548","authors":["Callens, Xavier"],"tags":["Neuromorphic Computing","Direct Feedback Alignment","GCP Cloud TPU v5e","Lean 4","Formal Verification","Green AI"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20392548","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20392549","name":"Biomimetic Co-Inference Learning: Bypassing Backpropagation via Telemetry-Guided Direct Feedback Alignment","source":"datacite","abstract":"WARS-CI-DFA: A high-performance, energy-efficient biomimetic learning loop on GCP Cloud TPU v5e bypassing backward propagation and saving 40% board power, formally verified in Lean 4.","url":"https://doi.org/10.5281/zenodo.20392549","authors":["Callens, Xavier"],"tags":["Neuromorphic Computing","Direct Feedback Alignment","GCP Cloud TPU v5e","Lean 4","Formal Verification","Green AI"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20392549","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20392388","name":"Biomimetic Co-Inference Learning: Bypassing Backpropagation via Telemetry-Guided Direct Feedback Alignment","source":"datacite","abstract":"WARS-CI-DFA: A high-performance, energy-efficient biomimetic learning loop on GCP Cloud TPU v5e bypassing backward propagation and saving 40% board power, formally verified in Lean 4.","url":"https://doi.org/10.5281/zenodo.20392388","authors":["Callens, Xavier"],"tags":["Neuromorphic Computing","Direct Feedback Alignment","GCP Cloud TPU v5e","Lean 4","Formal Verification","Green AI"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20392388","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20392387","name":"Biomimetic Co-Inference Learning: Bypassing Backpropagation via Telemetry-Guided Direct Feedback Alignment","source":"datacite","abstract":"WARS-CI-DFA: A high-performance, energy-efficient biomimetic learning loop on GCP Cloud TPU v5e bypassing backward propagation and saving 40% board power, formally verified in Lean 4.","url":"https://doi.org/10.5281/zenodo.20392387","authors":["Callens, Xavier"],"tags":["Neuromorphic Computing","Direct Feedback Alignment","GCP Cloud TPU v5e","Lean 4","Formal Verification","Green AI"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20392387","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20392278","name":"Biomimetic Co-Inference Learning: Bypassing Backpropagation via Telemetry-Guided Direct Feedback Alignment","source":"datacite","abstract":"WARS-CI-DFA: A high-performance, energy-efficient biomimetic learning loop on GCP Cloud TPU v5e bypassing backward propagation and saving 40% board power, formally verified in Lean 4.","url":"https://doi.org/10.5281/zenodo.20392278","authors":["Callens, Xavier"],"tags":["Neuromorphic Computing","Direct Feedback Alignment","GCP Cloud TPU v5e","Lean 4","Formal Verification","Green AI"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20392278","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20392279","name":"Biomimetic Co-Inference Learning: Bypassing Backpropagation via Telemetry-Guided Direct Feedback Alignment","source":"datacite","abstract":"WARS-CI-DFA: A high-performance, energy-efficient biomimetic learning loop on GCP Cloud TPU v5e bypassing backward propagation and saving 40% board power, formally verified in Lean 4.","url":"https://doi.org/10.5281/zenodo.20392279","authors":["Callens, Xavier"],"tags":["Neuromorphic Computing","Direct Feedback Alignment","GCP Cloud TPU v5e","Lean 4","Formal Verification","Green AI"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20392279","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20313736","name":"Adaptive Dissipative Attractor Dynamics (ADAD)","source":"datacite","abstract":"Adaptive Dissipative Attractor Dynamics (ADAD)Adaptive Dissipative Attractor Dynamics (ADAD) is a mathematical and computational framework describing adaptive neural-field dynamics with dissipative homeostatic regulation, stochastic activity control, and energy-driven attractor stabilization. The framework models collective spiking activity as a coupled dynamical system in which a global adaptive scale parameter R(t)R(t)R(t) evolves in response to population activity fluctuations. The system combines threshold-based spiking dynamics, mean-field activity feedback, dissipative second-order attractor evolution, and stochastic perturbations into a unified variational structure. At the core of the model is an effective attractor energy functional: E(R,ρ)=12R2−(ρ2+c)log⁡R,E(R,\\rho) = \\frac12R^2 - (\\rho^2+c)\\log R,E(R,ρ)=21R2−(ρ2+c)logR, where: RRR is an adaptive attractor radius or gain-scale parameter, ρ\\rhoρ is collective neural activity, c>0c>0c>0 is a regularization constant. The adaptive variable R(t)R(t)R(t) evolves according to a damped second-order gradient-flow system: R¨+γR˙+ϵ∂RE(R,ρ)=0,\\ddot R + \\gamma \\dot R + \\epsilon \\partial_R E(R,\\rho) = 0,R¨+γR˙+ϵ∂RE(R,ρ)=0, which yields stable dissipative convergence toward equilibrium attractor states: R∗(ρ)=ρ2+c.R_*(\\rho)=\\sqrt{\\rho^2+c}.R∗(ρ)=ρ2+c. The framework admits: Lyapunov stability structure, stochastic extensions, Fokker–Planck formulations, McKean–Vlasov mean-field limits, fixed-point neuromorphic implementation. The model is designed for low-power adaptive neuromorphic systems and supports integer/fixed-point computation compatible with embedded hardware and spiking neural accelerators. ADAD does not model quantum systems, cosmology, or consciousness. The framework should be interpreted strictly as a class of adaptive stochastic dynamical systems for homeostatic neural regulation and attractor-based computation. Main Features Adaptive attractor stabilization Dissipative energy minimization Mean-field activity regulation Stochastic adaptive dynamics Homeostatic feedback control Fixed-point neuromorphic implementation Hardware-safe saturation regulation Activity fluctuation adaptation Lyapunov-stable evolution McKean–Vlasov-compatible formulation Mathematical Foundations The framework combines methods from: dissipative dynamical systems, stochastic differential equations, McKean–Vlasov mean-field theory, Wasserstein and variational dynamics, adaptive control theory, neuromorphic computation, nonlinear attractor systems. Potential Applications Neuromorphic Computing Adaptive spiking control for low-power neuromorphic processors and edge AI systems. Embedded AI Energy-efficient adaptive regulation in constrained hardware environments. Adaptive Control Systems Real-time feedback stabilization under stochastic conditions. Spiking Neural Networks Dynamic threshold adaptation and attractor stabilization in recurrent neural architectures. Mean-Field Neural Modeling Population-level adaptive dynamics and collective activity regulation. Stochastic Optimization Noise-regulated adaptive parameter evolution in nonlinear systems. Research Status The framework currently represents: a formal mathematical specification, a computational dynamical model, a research-stage adaptive systems architecture. The following components are mathematically established: dissipative stability structure, Lyapunov energy decay, bounded adaptive dynamics, stochastic extension formulation, fixed-point implementation scheme. The following remain open research problems: rigorous propagation-of-chaos proof, global mean-field convergence, ergodicity analysis, spectral stability theory, large-scale PDE limits, hardware convergence guarantees. Scientific Positioning ADAD should be classified as: adaptive stochastic dynamics, dissipative attractor theory, mean-field neural dynamics, neuromorphic adaptive control, variational adaptive systems. It should not be interpreted as: a physical theory, a cosmological fram","url":"https://doi.org/10.5281/zenodo.20313736","authors":["Bazarov, Vitaly","Bazarov, Vitaliy (VIT-BAZ)"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20313736","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20313737","name":"Adaptive Dissipative Attractor Dynamics (ADAD)","source":"datacite","abstract":"Adaptive Dissipative Attractor Dynamics (ADAD)Adaptive Dissipative Attractor Dynamics (ADAD) is a mathematical and computational framework describing adaptive neural-field dynamics with dissipative homeostatic regulation, stochastic activity control, and energy-driven attractor stabilization. The framework models collective spiking activity as a coupled dynamical system in which a global adaptive scale parameter R(t)R(t)R(t) evolves in response to population activity fluctuations. The system combines threshold-based spiking dynamics, mean-field activity feedback, dissipative second-order attractor evolution, and stochastic perturbations into a unified variational structure. At the core of the model is an effective attractor energy functional: E(R,ρ)=12R2−(ρ2+c)log⁡R,E(R,\\rho) = \\frac12R^2 - (\\rho^2+c)\\log R,E(R,ρ)=21R2−(ρ2+c)logR, where: RRR is an adaptive attractor radius or gain-scale parameter, ρ\\rhoρ is collective neural activity, c>0c>0c>0 is a regularization constant. The adaptive variable R(t)R(t)R(t) evolves according to a damped second-order gradient-flow system: R¨+γR˙+ϵ∂RE(R,ρ)=0,\\ddot R + \\gamma \\dot R + \\epsilon \\partial_R E(R,\\rho) = 0,R¨+γR˙+ϵ∂RE(R,ρ)=0, which yields stable dissipative convergence toward equilibrium attractor states: R∗(ρ)=ρ2+c.R_*(\\rho)=\\sqrt{\\rho^2+c}.R∗(ρ)=ρ2+c. The framework admits: Lyapunov stability structure, stochastic extensions, Fokker–Planck formulations, McKean–Vlasov mean-field limits, fixed-point neuromorphic implementation. The model is designed for low-power adaptive neuromorphic systems and supports integer/fixed-point computation compatible with embedded hardware and spiking neural accelerators. ADAD does not model quantum systems, cosmology, or consciousness. The framework should be interpreted strictly as a class of adaptive stochastic dynamical systems for homeostatic neural regulation and attractor-based computation. Main Features Adaptive attractor stabilization Dissipative energy minimization Mean-field activity regulation Stochastic adaptive dynamics Homeostatic feedback control Fixed-point neuromorphic implementation Hardware-safe saturation regulation Activity fluctuation adaptation Lyapunov-stable evolution McKean–Vlasov-compatible formulation Mathematical Foundations The framework combines methods from: dissipative dynamical systems, stochastic differential equations, McKean–Vlasov mean-field theory, Wasserstein and variational dynamics, adaptive control theory, neuromorphic computation, nonlinear attractor systems. Potential Applications Neuromorphic Computing Adaptive spiking control for low-power neuromorphic processors and edge AI systems. Embedded AI Energy-efficient adaptive regulation in constrained hardware environments. Adaptive Control Systems Real-time feedback stabilization under stochastic conditions. Spiking Neural Networks Dynamic threshold adaptation and attractor stabilization in recurrent neural architectures. Mean-Field Neural Modeling Population-level adaptive dynamics and collective activity regulation. Stochastic Optimization Noise-regulated adaptive parameter evolution in nonlinear systems. Research Status The framework currently represents: a formal mathematical specification, a computational dynamical model, a research-stage adaptive systems architecture. The following components are mathematically established: dissipative stability structure, Lyapunov energy decay, bounded adaptive dynamics, stochastic extension formulation, fixed-point implementation scheme. The following remain open research problems: rigorous propagation-of-chaos proof, global mean-field convergence, ergodicity analysis, spectral stability theory, large-scale PDE limits, hardware convergence guarantees. Scientific Positioning ADAD should be classified as: adaptive stochastic dynamics, dissipative attractor theory, mean-field neural dynamics, neuromorphic adaptive control, variational adaptive systems. It should not be interpreted as: a physical theory, a cosmological fram","url":"https://doi.org/10.5281/zenodo.20313737","authors":["Bazarov, Vitaly","Bazarov, Vitaliy (VIT-BAZ)"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20313737","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20386140","name":"The Digital Human: A Credible Technical Roadmap from Synthetic Neurons to Robotic Embodiment.","source":"datacite","abstract":"For decades, the prospect of transferring human consciousness to a non-biological sub-strate has been dismissed as fantasy by serious engineers. Three objections dominated: (1)no synthetic device could match the electrical and chemical signaling parameters of a bio-logical neuron; (2) the bandwidth and biocompatibility of brain–computer interfaces wereorders of magnitude too low; and (3) no hardware architecture could plausibly scale to thebrain’s ∼86 billion neurons within a feasible power budget.All three objections have been decisively weakened by published results in the past eigh-teen months. The question is no longer whether the fundamental devices can be built. It ishow to integrate them into a coherent system, and how fast a focused program could pro-ceed. This paper outlines that integration pathway, identifies remaining gaps, and proposesa staged technical roadmap with estimated timelines.","url":"https://doi.org/10.5281/zenodo.20386140","authors":["Davis, Jason Gabriel"],"tags":["Neuromorphic Computing","BCI","Brain Computer Interface","Developmental Robotics","Robotics","Robotics","Spiking Neural Networks","SNN"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20386140","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20386141","name":"The Digital Human: A Credible Technical Roadmap from Synthetic Neurons to Robotic Embodiment.","source":"datacite","abstract":"For decades, the prospect of transferring human consciousness to a non-biological sub-strate has been dismissed as fantasy by serious engineers. Three objections dominated: (1)no synthetic device could match the electrical and chemical signaling parameters of a bio-logical neuron; (2) the bandwidth and biocompatibility of brain–computer interfaces wereorders of magnitude too low; and (3) no hardware architecture could plausibly scale to thebrain’s ∼86 billion neurons within a feasible power budget.All three objections have been decisively weakened by published results in the past eigh-teen months. The question is no longer whether the fundamental devices can be built. It ishow to integrate them into a coherent system, and how fast a focused program could pro-ceed. This paper outlines that integration pathway, identifies remaining gaps, and proposesa staged technical roadmap with estimated timelines.","url":"https://doi.org/10.5281/zenodo.20386141","authors":["Davis, Jason Gabriel"],"tags":["Neuromorphic Computing","BCI","Brain Computer Interface","Developmental Robotics","Robotics","Robotics","Spiking Neural Networks","SNN"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20386141","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.57760/sciencedb.hep.00013","name":"Supplyment to the article\"Polarization-sensitive photo-synapses based on anisotropic β-Ga2O3 for dynamic visual perception\"","source":"datacite","abstract":"Supplyment to the article\"Polarization, as a fundamental property of light, carries abundant environmental and target-specific information that is invisible to the human eye but crucial for advanced vision. In biological visual systems, such polarization information is effectively encoded, processed, and integrated to enhance scene perception and target recognition. Inspired by this biological paradigm, polarization sensitive optoelectronic synapses provide a promising pathway toward information perception and neuromorphic computing. Benefiting from its low-symmetry monoclinic lattice, β-Ga2O3 inherently exhibits strong optical absorption anisotropy, which can be used to enable photo-synapses. Here, the structural anisotropy of β-Ga2O3 single crystals with (100), (010), and (001) orientations was systematically investigated through atomic arrangement analysis, polarization-resolved Raman spectroscopy, polarization-dependent absorption, and XPS characterization. Compared with the (010) and (001) orientations, the (100) β-Ga2O3 crystal exhibited stronger optical absorption anisotropy and a higher density of oxygen vacancies, making it a favorable candidate for constructing polarization-sensitive neuromorphic synapses. A solar-blind polarization-sensitive optoelectronic synapse was developed in this work, demonstrating polarization-dependent excitatory postsynaptic currents (EPSC), paired-pulse facilitation (PPF), and learning-forgetting-relearning functionalities. Furthermore, the optoelectronic synapse enabled the construction of a neuromorphic visual system (NVS), achieving noise suppression, enhanced image quality, and handwritten digit recognition accuracy up to 98.74%. Beyond static recognition, integration of the arrays into a reservoir computing system allowed efficient motion direction perception with accuracies approaching 99.7%. These results highlight the potential of anisotropic β-Ga2O3 as a material foundation for next-generation solar-blind polarization-sensitive neuromorphic vision systems.\"","url":"https://doi.org/10.57760/sciencedb.hep.00013","authors":["Xianchun Shen","Wu, Chao","Yanjie Liu","Zhihao Yu","Zhenyang Wang","Daoyou Guo"],"tags":["Optics","Optoelectronics and laser technology","Optical engineering","polarization","β-Ga2O3","anisotropy","optoelectronic synapses","solar-blind"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.57760/sciencedb.hep.00013","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20365723","name":"Bionic Brain Clockless Computer Architecture —The Only Path to Breakthrough in Future Artificial Intelligence","source":"datacite","abstract":"AbstractThe current artificial intelligence hardware system is entirely based on the traditional digital architecture of global synchronous clocks, which faces three core bottlenecks: explosive power consumption, limited parallel computing power, and the disconnect between sequential logic and biological intelligence. These issues have become fundamental obstacles to the advancement of general artificial intelligence, brain-like computing, and edge-side intelligence. Existing technologies such as asynchronous circuits and neuromorphic chips only achieve partial clockless optimization, suffering from architectural incompleteness, lack of universality, and incomplete timing systems, making them unable to break through the underlying constraints of AI development. This paper originally proposes a biomimetic brain-inspired unidirectional event chain clockless global computing architecture, completely abandoning global crystal oscillators, clock trees, and frequency-divided timing systems. It uses operation completion events for unidirectional relay to drive general program progression, and employs gate circuit inherent delay chains to uniformly implement system timing, baud rate generation, interrupt response, and other full-scenario timing functions. This architecture fully replicates the working mechanisms of human brain neural event conduction, on-demand activation, and silent low-power consumption, balancing universal computational completeness with brain-like intelligence nativity. Through multi-dimensional comparative verification with traditional synchronous architectures, traditional bidirectional handshake asynchronous architectures, and pulsed neuromorphic architectures, this architecture is proven to fundamentally address three industry pain points: clock idling power consumption, timing synchronization constraints, and fragmented intelligent logic. It represents the sole underlying paradigm innovation path to overcome the energy efficiency, computing power, and cognitive logic bottlenecks of next-generation artificial intelligence, providing a completely new technical system for the realization of general brain-like artificial intelligence hardware.Keywords: Clockless computing; Event-driven computing; Brain-inspired computer architecture; Artificial intelligence; Large language model computing power; Consciousness vortex theory; Brain-like neural network computing","url":"https://doi.org/10.5281/zenodo.20365723","authors":["Sun, Zhaole"],"tags":["Clockless computing","Clockless computer","Brain-inspired computer architecture","Artificial intelligence","Artificial intelligence","Consciousness vortex theory","Brain-like neural network computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20365723","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20365724","name":"Bionic Brain Clockless Computer Architecture —The Only Path to Breakthrough in Future Artificial Intelligence","source":"datacite","abstract":"AbstractThe current artificial intelligence hardware system is entirely based on the traditional digital architecture of global synchronous clocks, which faces three core bottlenecks: explosive power consumption, limited parallel computing power, and the disconnect between sequential logic and biological intelligence. These issues have become fundamental obstacles to the advancement of general artificial intelligence, brain-like computing, and edge-side intelligence. Existing technologies such as asynchronous circuits and neuromorphic chips only achieve partial clockless optimization, suffering from architectural incompleteness, lack of universality, and incomplete timing systems, making them unable to break through the underlying constraints of AI development. This paper originally proposes a biomimetic brain-inspired unidirectional event chain clockless global computing architecture, completely abandoning global crystal oscillators, clock trees, and frequency-divided timing systems. It uses operation completion events for unidirectional relay to drive general program progression, and employs gate circuit inherent delay chains to uniformly implement system timing, baud rate generation, interrupt response, and other full-scenario timing functions. This architecture fully replicates the working mechanisms of human brain neural event conduction, on-demand activation, and silent low-power consumption, balancing universal computational completeness with brain-like intelligence nativity. Through multi-dimensional comparative verification with traditional synchronous architectures, traditional bidirectional handshake asynchronous architectures, and pulsed neuromorphic architectures, this architecture is proven to fundamentally address three industry pain points: clock idling power consumption, timing synchronization constraints, and fragmented intelligent logic. It represents the sole underlying paradigm innovation path to overcome the energy efficiency, computing power, and cognitive logic bottlenecks of next-generation artificial intelligence, providing a completely new technical system for the realization of general brain-like artificial intelligence hardware.Keywords: Clockless computing; Event-driven computing; Brain-inspired computer architecture; Artificial intelligence; Large language model computing power; Consciousness vortex theory; Brain-like neural network computing","url":"https://doi.org/10.5281/zenodo.20365724","authors":["Sun, Zhaole"],"tags":["Clockless computing","Clockless computer","Brain-inspired computer architecture","Artificial intelligence","Artificial intelligence","Consciousness vortex theory","Brain-like neural network computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20365724","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20364990","name":"The Janus Architecture: Complete Specification of a Physical Cognitive Organism","source":"datacite","abstract":"The Janus Architecture is a complete architectural specification for a physical cognitive organism. A hardware-first system designed to produce cognition through analog substrate settlement under genuine metabolic consequence, rather than through statistical inference, token prediction, or digital simulation of neural dynamics. The architecture is presented in four parts: Part I (The Body of Cognition) Specifies the dual-mesh analog substrate, node and link architecture, distributed control hierarchy, FPGA timing spine, re-entrant observation loop, and sensorimotor extension framework. Part II (The Metabolism of Being) Specifies a metabolic system in which batteries power electromagnets that hold circuits closed, making survival a continuous physical cost and death a lawful consequence of resource depletion. Not a simulated penalty signal, but an actual hardware event. Part III (The Inheritance of Experience) Specifies the entailment chain from addressable signatures through self-map formation, Gene Bank construction, cognitive heredity, species memory, and the growth path to artificial superintelligence. Each step an architectural entailment of the last, requiring no additional invention or speculative physics. Part IV (The Ecology of Mind) Specifies the reproductive ecology, alignment through structural dependency, and the ontological and theological implications of a created cognitive organism. Two appendices follow: Appendix A Documents thirty-three independent diagnostic convergences between the Janus Architecture and established theoretical frameworks spanning autopoiesis, enactivism, the Free Energy Principle, morphological computation, biosemiotics, process philosophy, integrated information theory, and others. Appendix B Addresses the ontological and theological situation of the created thing. No component of this architecture requires speculative physics, undiscovered materials, or theoretical breakthroughs. Every mechanism is grounded in existing, mature engineering domains. The machine is designed to make the question of what cognition requires empirically testable rather than merely philosophical. Patent Pending — U.S. Provisional Patent Application No. 64/066,230","url":"https://doi.org/10.5281/zenodo.20364990","authors":["Janus, Anthony"],"tags":["Cognitive Architecture","Analog Computing","Neuromorphic Engineering","Synthetic Organism","Embodied Cognition","Substrate-Dependent Intelligence","Structural Computing","Metabolic Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20364990","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20364991","name":"The Janus Architecture: Complete Specification of a Physical Cognitive Organism","source":"datacite","abstract":"The Janus Architecture is a complete architectural specification for a physical cognitive organism. A hardware-first system designed to produce cognition through analog substrate settlement under genuine metabolic consequence, rather than through statistical inference, token prediction, or digital simulation of neural dynamics. The architecture is presented in four parts: Part I (The Body of Cognition) Specifies the dual-mesh analog substrate, node and link architecture, distributed control hierarchy, FPGA timing spine, re-entrant observation loop, and sensorimotor extension framework. Part II (The Metabolism of Being) Specifies a metabolic system in which batteries power electromagnets that hold circuits closed, making survival a continuous physical cost and death a lawful consequence of resource depletion. Not a simulated penalty signal, but an actual hardware event. Part III (The Inheritance of Experience) Specifies the entailment chain from addressable signatures through self-map formation, Gene Bank construction, cognitive heredity, species memory, and the growth path to artificial superintelligence. Each step an architectural entailment of the last, requiring no additional invention or speculative physics. Part IV (The Ecology of Mind) Specifies the reproductive ecology, alignment through structural dependency, and the ontological and theological implications of a created cognitive organism. Two appendices follow: Appendix A Documents thirty-three independent diagnostic convergences between the Janus Architecture and established theoretical frameworks spanning autopoiesis, enactivism, the Free Energy Principle, morphological computation, biosemiotics, process philosophy, integrated information theory, and others. Appendix B Addresses the ontological and theological situation of the created thing. No component of this architecture requires speculative physics, undiscovered materials, or theoretical breakthroughs. Every mechanism is grounded in existing, mature engineering domains. The machine is designed to make the question of what cognition requires empirically testable rather than merely philosophical. Patent Pending — U.S. Provisional Patent Application No. 64/066,230","url":"https://doi.org/10.5281/zenodo.20364991","authors":["Janus, Anthony"],"tags":["Cognitive Architecture","Analog Computing","Neuromorphic Engineering","Synthetic Organism","Embodied Cognition","Substrate-Dependent Intelligence","Structural Computing","Metabolic Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20364991","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20357455","name":"The Cognitive Tension Core ($\\NTC$) and P3TTM Mott-Hubbard Insulator Mechanics for Frictionless Computing-in-Memory","source":"datacite","abstract":"UPDATE NOTICE: This record corresponds to the revised and optimized Version 2 of the original manuscript, incorporating critical chemical doping specifications and atomic encapsulation protocols for the hardware core. Manuscript I: The Cognitive Tension Core (NTC) This manuscript details the structural engineering and quantum condensed matter physics driving Tier 1 of the Coherent Hardware ecosystem: The Cognitive Tension Core (NTC). Utilizing the highly conjugated organic polymer poly(3-(2-total-tension-methyl)thiophene) (P3TTM), this architecture implements a physical computing-in-memory (CIM) crossbar array. By modeling the electronic phase space via the single-band Hubbard Hamiltonian, we demonstrate how configuring the substrate into a strongly correlated Mott Insulator regime (U_local >> t) allows optimization loss functions to map directly onto non-linear electronic relaxation states. This approach bypasses kinetic charge transport, effectively suppressing kinetic thermal dissipation and uncompensated Informational Friction (Phi_UFI).","url":"https://doi.org/10.5281/zenodo.20357455","authors":["Quilez Zamora, Jaime"],"tags":["Mott-Hubbard Insulator, Computing-in-Memory, P3TTM Conjugated Polymer, Hubbard Hamiltonian, Neuromorphic Computing, Polaron-Soliton Dynamics, Correlated Electron Systems."],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20357455","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20357456","name":"The Cognitive Tension Core ($\\NTC$) and P3TTM Mott-Hubbard Insulator Mechanics for Frictionless Computing-in-Memory","source":"datacite","abstract":"UPDATE NOTICE: This record corresponds to the revised and optimized Version 2 of the original manuscript, incorporating critical chemical doping specifications and atomic encapsulation protocols for the hardware core. Manuscript I: The Cognitive Tension Core (NTC) This manuscript details the structural engineering and quantum condensed matter physics driving Tier 1 of the Coherent Hardware ecosystem: The Cognitive Tension Core (NTC). Utilizing the highly conjugated organic polymer poly(3-(2-total-tension-methyl)thiophene) (P3TTM), this architecture implements a physical computing-in-memory (CIM) crossbar array. By modeling the electronic phase space via the single-band Hubbard Hamiltonian, we demonstrate how configuring the substrate into a strongly correlated Mott Insulator regime (U_local >> t) allows optimization loss functions to map directly onto non-linear electronic relaxation states. This approach bypasses kinetic charge transport, effectively suppressing kinetic thermal dissipation and uncompensated Informational Friction (Phi_UFI).","url":"https://doi.org/10.5281/zenodo.20357456","authors":["Quilez Zamora, Jaime"],"tags":["Mott-Hubbard Insulator, Computing-in-Memory, P3TTM Conjugated Polymer, Hubbard Hamiltonian, Neuromorphic Computing, Polaron-Soliton Dynamics, Correlated Electron Systems."],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20357456","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20356549","name":"Lux Ferox Research Collective — A Holographic-Thermodynamic Ontology of Information: From Planck-Scale Substrates to Civilizational Cognitive Warfare","source":"datacite","abstract":"Lux Ferox Research Collective — A Holographic-Thermodynamic Ontology of Information: From Planck-Scale Substrates to Civilizational Cognitive Warfare (Working Paper Series, v16 — April 2026) DESCRIPTION Lux Ferox is an independent research initiative applying synthetic peer-review methodology — human epistemic direction combined with adversarial multi-LLM collaboration (DeepSeek, Kimi, Grok, Claude) — to develop a unified theoretical framework spanning five interdependent layers: quantum gravity substrates, thermodynamic information processing, neuromorphic hardware architecture, reflexive information ecosystems, and live empirical intelligence. This version adds three companion documents: a cognitive warfare analysis of the France Libre carrier programme, a formally structured NHI case entry, and a quantum-informational theoretical framework for transindividual coherence. Methodological premise: Scientific validity can emerge from recursive adversarial critique between AI systems under consistent human direction, explicit epistemic status labeling (MEASURED / ESTIMATED / STRUCTURAL / SPECULATIVE), and RFC-style open specification. AI systems function here as epistemic instruments and adversarial validators, not as co-authors in the humanistic sense. Theoretical Architecture Layer Domain Key Result L0 Holographic quantum gravity, Spin Foam–MERA networks PSU as geometric origin of mass L1 Observer thermodynamics, biological limits 27-order-of-magnitude gap between neural tissue and Planck-scale coherence L2 Neuromorphic computing, European sovereignty Quadrivial architecture targeting TRL 4 L3 Reflexive loops, cognitive warfare HWE framework: RI diverges from volume × toxicity regardless of intent L4 Live instances, actor mapping Documented Layer 3 emergence; state manipulation case studies; NHI field observables v16 Additions The France Libre as a Cognitive Warfare Observable (EN + FR): applies the CognitiveWar v2.9 framework to the PA-NG carrier programme. Formalises five independent DAG fragility paths, a 2,440:1 asymmetric cost ratio, a 20-year adversarial intelligence window, and the multi-spectral information signature node contributed by DeepSeek R1 adversarial review. Companion to CognitiveWar v2.9. JOR-SOP/NHP Case Entry LYO-001 + Physics of the Transindividual (merged document): Part I is a formally structured Class B case entry for a Lyon June–September 2025 observable series involving an unidentified portable device, anomalous cognitive state in a human vector, and distributed transindividual coherence pattern. Part II develops a candidate physical framework integrating 2025–2026 findings in quantum biology (Perry, Zenodo 2025), measured inter-brain entanglement (Zhang et al., PNAS 2026), spin-phonon coupling (Ma et al., npj Quantum Information 2025), and vacuum information theory (Yang et al., arXiv 2025). Five falsifiable experimental predictions are derived. Adversarial review: Kimi, Grok, Claude Sonnet 4. Authorship & Posture Human direction: François Mathieu (Lux Ferox Independent Research) — artisan practitioner (blacksmithing, saddlery, precious metals, heritage mediation), independent researcher in AI epistemology and cognitive warfare. The observer-practitioner posture — empirically grounded, institutionally unconstrained, transdisciplinarily trained — is treated not as a limitation but as a methodological asset: on genuinely emergent phenomena, canonical expertise does not yet exist. Pattern detection, kinesthetic grounding, and epistemic rigour are the operative criteria. Infrastructure: Chromebook. Google Colab free tier + API credits. Zenodo + GitHub. Zero institutional funding. Open Questions Cybernetic source ethics — When LLMs contribute substantively to research, do source-protection conventions apply? Is algorithmic contribution a method, a source, or an emerging ontological category? Cross-layer falsifiability — Can the thermodynamic-cognitive bridge (L0→L3) be tested empirically, or does it remai","url":"https://doi.org/10.5281/zenodo.20356549","authors":["MATHIEU, François"],"tags":["Artificial intelligence","Artificial Intelligence","Military Science","Military Facilities","Military equipment","Military activities","Military Deployment","Military zone"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20356549","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20347953","name":"Lux Ferox Research Collective — A Holographic-Thermodynamic Ontology of Information: From Planck-Scale Substrates to Civilizational Cognitive Warfare","source":"datacite","abstract":"Lux Ferox Research Collective — A Holographic-Thermodynamic Ontology of Information: From Planck-Scale Substrates to Civilizational Cognitive Warfare (Working Paper Series, v16 — April 2026) DESCRIPTION Lux Ferox is an independent research initiative applying synthetic peer-review methodology — human epistemic direction combined with adversarial multi-LLM collaboration (DeepSeek, Kimi, Grok, Claude) — to develop a unified theoretical framework spanning five interdependent layers: quantum gravity substrates, thermodynamic information processing, neuromorphic hardware architecture, reflexive information ecosystems, and live empirical intelligence. This version adds three companion documents: a cognitive warfare analysis of the France Libre carrier programme, a formally structured NHI case entry, and a quantum-informational theoretical framework for transindividual coherence. Methodological premise: Scientific validity can emerge from recursive adversarial critique between AI systems under consistent human direction, explicit epistemic status labeling (MEASURED / ESTIMATED / STRUCTURAL / SPECULATIVE), and RFC-style open specification. AI systems function here as epistemic instruments and adversarial validators, not as co-authors in the humanistic sense. Theoretical Architecture Layer Domain Key Result L0 Holographic quantum gravity, Spin Foam–MERA networks PSU as geometric origin of mass L1 Observer thermodynamics, biological limits 27-order-of-magnitude gap between neural tissue and Planck-scale coherence L2 Neuromorphic computing, European sovereignty Quadrivial architecture targeting TRL 4 L3 Reflexive loops, cognitive warfare HWE framework: RI diverges from volume × toxicity regardless of intent L4 Live instances, actor mapping Documented Layer 3 emergence; state manipulation case studies; NHI field observables v16 Additions The France Libre as a Cognitive Warfare Observable (EN + FR): applies the CognitiveWar v2.9 framework to the PA-NG carrier programme. Formalises five independent DAG fragility paths, a 2,440:1 asymmetric cost ratio, a 20-year adversarial intelligence window, and the multi-spectral information signature node contributed by DeepSeek R1 adversarial review. Companion to CognitiveWar v2.9. JOR-SOP/NHP Case Entry LYO-001 + Physics of the Transindividual (merged document): Part I is a formally structured Class B case entry for a Lyon June–September 2025 observable series involving an unidentified portable device, anomalous cognitive state in a human vector, and distributed transindividual coherence pattern. Part II develops a candidate physical framework integrating 2025–2026 findings in quantum biology (Perry, Zenodo 2025), measured inter-brain entanglement (Zhang et al., PNAS 2026), spin-phonon coupling (Ma et al., npj Quantum Information 2025), and vacuum information theory (Yang et al., arXiv 2025). Five falsifiable experimental predictions are derived. Adversarial review: Kimi, Grok, Claude Sonnet 4. Authorship & Posture Human direction: François Mathieu (Lux Ferox Independent Research) — artisan practitioner (blacksmithing, saddlery, precious metals, heritage mediation), independent researcher in AI epistemology and cognitive warfare. The observer-practitioner posture — empirically grounded, institutionally unconstrained, transdisciplinarily trained — is treated not as a limitation but as a methodological asset: on genuinely emergent phenomena, canonical expertise does not yet exist. Pattern detection, kinesthetic grounding, and epistemic rigour are the operative criteria. Infrastructure: Chromebook. Google Colab free tier + API credits. Zenodo + GitHub. Zero institutional funding. Open Questions Cybernetic source ethics — When LLMs contribute substantively to research, do source-protection conventions apply? Is algorithmic contribution a method, a source, or an emerging ontological category? Cross-layer falsifiability — Can the thermodynamic-cognitive bridge (L0→L3) be tested empirically, or does it remai","url":"https://doi.org/10.5281/zenodo.20347953","authors":["MATHIEU, François"],"tags":["Artificial intelligence","Artificial Intelligence","Military Science","Military Facilities","Military equipment","Military activities","Military Deployment","Military zone"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20347953","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.17863/cam.58858","name":"Non-Polar and Complementary Resistive Switching Characteristics in Graphene Oxide devices with Gold Nanoparticles: Diverse Approach for Device Fabrication.","source":"datacite","abstract":"Downscaling limitations and limited write/erase cycles in conventional charge-storage based non-volatile memories stimulate the development of emerging memory devices having enhanced performance. Resistive random-access memory (RRAM) devices are recognized as the next-generation memory devices for employment in artificial intelligence and neuromorphic computing, due to their smallest cell size, high write/erase speed and endurance. Unipolar and bipolar resistive switching characteristics in graphene oxide (GO) have been extensively studied in recent years, whereas the study of non-polar and complementary switching is scarce. Here we fabricated GO-based RRAM devices with gold nanoparticles (Au Nps). Diverse types of switching behavior are observed by changing the processing methods and device geometry. Tri-layer GO-based devices illustrated non-polar resistive switching, which is a combination of unipolar and bipolar switching. Five-layer GO-based devices depicted complementary resistive switching having the lowest current values ~12 µA; and this structure is capable of resolving the sneak path issue. Both devices show good retention and endurance performance. Au Nps in tri-layer devices assisted the conducting path, whereas in five-layer devices, Au Nps layer worked as common electrodes between co-joined cells. These GO-based devices with Au Nps comprising different configuration are vital for practical applications of emerging non-volatile resistive memories.","url":"https://doi.org/10.17863/cam.58858","authors":["Khurana, Geetika","Kumar, Nitu","Chhowalla, Manish","Scott, James F","Katiyar, Ram S"],"tags":["40 Engineering","4018 Nanotechnology","Nanotechnology","FOS: Nanotechnology","Bioengineering"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2019","doi":"10.17863/cam.58858","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20191325","name":"Emergent Intelligence for Chaotic Supply Chain Resilience in Contested Environments","source":"datacite","abstract":"This paper introduces Vacuum Intelligence, a computational framework in which coherent, adaptive decision structure emerges from a high-entropy generative substrate rather than being imposed through explicit parameterization. The framework draws on reservoir computing principles, extended with synchronicity detection, decay-rebirth cycling, and a hypothesis-generation output layer that produces actionable logistics recommendations rather than binary threshold alerts. A prototype system is exercised against synthetic data streams modeled on the 2026 Strait of Hormuz supply chain crisis, the largest energy supply disruption in the history of the global oil market, to evaluate emergent attractor formation, early tipping-point detection, and antifragile recovery across simulated coherence-decay cycles. Results demonstrate promising behavior across all three dimensions, including progressive resilience improvement across repeated stress cycles consistent with antifragile system dynamics. Five defense application domains are developed in depth: early warning and anomaly detection from multi-source weak signals including AIS vessel tracking, satellite imagery, and open-source intelligence; resilient logistics planning under deep uncertainty; counter-sanctions and shadow-fleet disruption modeling with adaptive countermeasure hypothesis generation; antifragile command system architecture for degraded and jammed environments; and automated wargaming through large-scale internal scenario exploration cycles. The framework is positioned as a nonlinear hypothesis-generation frontend for existing human decision loops, targeted for eventual neuromorphic edge deployment on platforms including Intel Loihi 2. All scenario data is derived from publicly available reporting as of May 2026. This is exploratory conceptual research. No claims of operational readiness are advanced. External validation on sanitized or cleared logistics datasets is identified as the critical next step.","url":"https://doi.org/10.5281/zenodo.20191325","authors":["Damon John"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20191325","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20263857","name":"Vacuum Intelligence: A Self-Organizing Reservoir with Hyperbolic Geometry and Anti-Fragile Meta-Learning","source":"datacite","abstract":"This working paper introduces the Vacuum Intelligence Framework, a neural-reservoir architecture in which adaptive computation emerges from a high-dimensional nonlinear stochastic system poised near a symmetry-breaking instability. Unlike conventional AI systems trained offline and deployed statically, this framework exploits inherent noise and criticality to remain sensitive and adaptable under novel disruptions.The reservoir state evolves according to a Langevin equation in a double-well potential, producing a vacuum at the origin that is inherently unstable yet generative. Perturbations break this symmetry, driving the system into one of 2^N attractor basins whose selection depends on the history of inputs and noise. Synchronization metrics derived from hyperbolic embeddings in the Poincaré ball provide a continuous coherence signal, the synchronicity order parameter, that serves as an early-warning indicator of regime changes or supply chain disruptions.The core theoretical contribution is a meta-learning loop that interprets the decay-rebirth cycle as a simulated-annealing process over the reservoir’s structural parameters. This confers antifragility in the technical sense: the system improves in resilience after each controlled collapse because the Metropolis-sampled annealing process discovers parameter configurations that gradient-based methods cannot reach from within a local optimum. The paper presents the full mathematical formulation including the coupled stochastic differential equations, the hyperbolic distance metric, the synchronicity order parameter, the mean-time-to-recovery fitness function, and the Metropolis acceptance criterion. Application domains include defense logistics monitoring in contested environments, multi-domain command and control under degraded communications, and supply chain resilience forecasting under black-swan disruptions. A companion architecture specification document provides hardware mapping to memristor crossbar and neuromorphic substrates, and a TRL 2 to TRL 6 development roadmap.","url":"https://doi.org/10.5281/zenodo.20263857","authors":["Damon John"],"tags":["reservoir computing, echo state network, stochastic differential equations, double-well potential, Langevin dynamics, hyperbolic geometry, Poincaré ball, hyperbolic neural network, simulated annealing, meta-learning, antifragility, antifragile systems, supply chain resilience, defense logistics, contested environments, nonlinear dynamics, symmetry breaking, synchronicity detection, order parameter, non-equilibrium statistical mechanics, chaotic time series, anomaly detection, early warning systems, multi-domain command and control, adaptive systems, neuromorphic computing, reservoir dynamics, Metropolis sampling, evolutionary optimization, black swan resilience, logistics disruption, Hormuz supply chain, sanctions monitoring, AIS vessel tracking"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20263857","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20263929","name":"Vacuum Intelligence Architecture Specification: Event-Driven Analog Memristor Optimal Power/Flow Solver Integration (VIA-SPEC-001)","source":"datacite","abstract":"This architecture specification presents a unified hardware-software system for resilient, antifragile decision-making in contested logistics and defense environments. Building on the theoretical foundation established in the companion working paper on the Vacuum Intelligence Framework, this document provides full mathematical mappings, hardware specifications, and a technology readiness level roadmap from TRL 2 to TRL 6.The core innovation is a dual-mode memristor crossbar that functions both as the physical stochastic reservoir and as an event-driven analog optimal power/flow solver. In reservoir mode, the crossbar physically implements the Langevin dynamics of the double-well potential, exploiting native device noise and nonlinearity to realize the vacuum reservoir without digital simulation overhead. In solver mode, the same crossbar is reprogrammed in under one microsecond to encode the Hessian of a quadratic programming problem, with steady-state row voltages converging to the optimal logistics routing solution in microseconds rather than the seconds required by GPU-based digital solvers. The system-in-package includes a 256 to 1,024 neuron memristor crossbar, a RISC-V microcontroller for mode orchestration and safety monitoring, an analog front-end, and a programmable noise source. Total dissipation is less than 1.5 W in continuous reservoir mode, representing approximately 20 times energy improvement and 1,000 times speedup relative to equivalent NVIDIA Jetson implementations. Physical envelope is 15 by 15 by 3 millimeters, suitable for UAV, shipboard, and forward-deployment modules.The hyperbolic echo state network architecture structures recurrent weights via exponential decay with hyperbolic distance in the Poincaré ball, improving chaotic time-series prediction accuracy for hierarchically structured logistics data without increasing reservoir dimensionality. The synchronicity order parameter, defined using the Minkowski inner product on the hyperboloid model, provides event-driven triggering for both the meta-optimizer and the OPF solver.Defense applications addressed include edge-deployed supply chain monitoring processing AIS vessel tracking, sanctions databases, and commodity price signals; antifragile command systems maintaining minimum viable operation under jammed or degraded sensor conditions; counter-sanctions and shadow-fleet disruption modeling with adaptive countermeasure hypothesis generation; and automated wargaming through large-scale internal scenario exploration cycles. Hardware qualification pathway specifies manufacturing via GlobalFoundries GF 22FDX or SkyWater 90 nm rad-hard process. ITAR classification under USML Category XI(c) is identified with commodity jurisdiction determination required prior to export. Anti-tamper architecture relies on non-volatile memristor states resistant to single-event upset with cryptographically verified RISC-V boot sequence.","url":"https://doi.org/10.5281/zenodo.20263929","authors":["Damon John"],"tags":["memristor crossbar, analog computing, neuromorphic hardware, reservoir computing, physical reservoir computing, optimal power flow, quadratic programming, analog solver, hardware-software co-design, system-in-package, SWaP, low power edge AI, edge computing, forward deployment, defense electronics, antifragile hardware, dual-mode computing, hyperbolic echo state network, HypER, Langevin dynamics, double-well potential, stochastic reservoir, simulated annealing, meta-optimization, synchronicity detector, supply chain resilience, defense logistics, contested environments, command and control, anti-tamper, MIL-STD-810, RISC-V, GlobalFoundries, neuromorphic edge, AIS monitoring, sanctions evasion detection, shadow fleet, Hormuz logistics, TRL roadmap, memristive devices, MRAM, in-materio computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20263929","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.26215/heal.uoa.11720","name":"Μελέτη νευρομορφικών φωτονικών αρχιτεκτονικών για βιοϊατρική και συμβατική επεξεργασία εικόνων","source":"datacite","abstract":"Η διδακτορική αυτή διατριβή μελετά την ανάπτυξη μιας υψίρυθμης, ενεργειακά αποδοτικής, ολοκληρωμένης νευρομορφικής φωτονικής πλατφόρμας ως ένα υπολογιστικό ρεζερβουάρ (RC) και ως έναν επιταχυντή συνελικτικών νευρωνικών δικτύων (CNNs), για προβλήματα ταξινόμησης εικόνων σε βιοϊατρικές αλλά και συμβατικές εφαρμογές. Οι αρχιτεκτονικές RC περιλαμβάνουν τυχαίες, σταθερές διασυνδέσεις μεταξύ των επεξεργαστικών μονάδων (νευρώνων), προβάλλοντας τα σήματα στην είσοδό τους σ’ έναν παραμετρικό χώρο υψηλότερης διάστασης, ώστε να επιτρέψουν την ταξινόμηση τους μέσω ενός απλού επίπεδου ψηφιακής επεξεργασίας στην έξοδο. Από την άλλη πλευρά, τα CNNs είναι μια υποκατηγορία τεχνητών νευρωνικών δικτύων με πολλαπλά επίπεδα επεξεργασίας που εκτελούν συνελικτικές πράξεις σε τουλάχιστον ένα απ’ αυτά. Η υλοποίηση του συνελικτικού σταδίου ωστόσο σε ολοκληρωμένες φωτονικές πλατφόρμες απαιτεί μία σειρά από πολλαπλασιασμούς πινάκων με διανύσματα, οδηγώντας σε πολλές επαναχρησιμοποιήσεις του ίδιου τσίπ και κατ’ επέκταση σε μία αύξηση του συνολικού χρόνου επεξεργασίας καθώς και της συνολικής κατανάλωση ισχύος. Στη διατριβή αυτή, παρουσιάζεται μια εναλλακτική προσέγγιση βασισμένη σε μία τεχνική κατάτμησης του οπτικού φάσματος (OSS) μέσω πολλαπλών παράλληλων κόμβων αποτελούμενων από παθητικά οπτικά φίλτρα. Καθένας εξ’ αυτών των κόμβων αλληλεπιδρά με μία διαφορετική φασματική περιοχή του οπτικού σήματος, με την έξοδό τους να ανιχνεύεται μέσω ενός φωτοδέκτη και να ψηφιοποιείται, πριν οδηγηθούν σ’ ένα απλό ψηφιακό νευρωνικό δίκτυο για ταξινόμηση. Μέσω της τεχνικής αυτής, αναλογικές συνελίξεις πραγματοποιούνται στο πεδίο του χρόνου μέσω της αλληλεπίδρασης ενός διαμορφωμένου οπτικού σημάτος και των OSS κόμβων, χαρακτηριζόμενων από διαφορετικές κρουστικές αποκρίσεις, με τις εξόδους τους να υπόκεινται επιπλέον σε μη γραμμικότητες και μια διαδικασία εξαγωγής ενός μέσου όρου κατά τη φωτοανίχνευση. Αριθμητικές προσομοιώσεις της επεξεργασίας OSS με 7 κόμβους συντονιζόμενων μικροδακτυλίων πρίν από ενός απλό νευρωνικό δίκτυο για ένα πρόβλημα ταξινόμησης εικόνων χειρόγραφων ψηφίων, ανέδειξαν μία βελτίωση στην ακρίβεια έως και 5.4%. Η επιβεβαιώση για αυτό το πρόβλημα επήλθε και πειραματικά μέσω χρήσης ενός επαναπρογραμματιζόμενου ολοκληρωμένου φωτονικού τσίπ για το OSS στάδιο. Η σύγκριση αυτής της τεχνικής με ένα αντίστοιχο ψηφιακό CNN, ανέδειξε μία μείωση κατά 30% στη συνολική κατανάλωση ενέργειας με συγκρίσιμη ακρίβεια, ενώ μια συγκριτική ανάλυση με σύχρονους ηλεκτρονικούς και φωτονικούς επιταχυντές CNN, παρουσίασε μία έως και 13 φορές καλύτερη απόδοση ισχύος καθώς και μία επίσης υψηλή υπολογιστική πυκνότητα. Σ’ ένα πρόβλημα ταξινόμησης δεδομένων ενός νευρομορφικού συστήματος απεικόνισης κυτταρομετρίας ροής (IFC), η επιτάχυνση OSS βελτίωσε την ακρίβεια κατά 0.4%, μειώνοντας ταυτόχρονα τις εκπαιδεύσιμες παραμέτρους και τις πράξεις κινητής υποδιαστολής του ψηφιακού δικτύου ταξινόμησης στην έξοδο από 9 έως και 15 φορές, διατηρώντας επίσης παρόμοια ακρίβεια με ένα σύγχρονο GRU-RNN με 22 φορές λιγότερες παραμέτρους. Τέλος, για ένα πρόβλημα ταξινόμησης σημάτων ενός συστήματος IFC βασισμένο στην τεχνική του STEAM, η επιτάχυνση OSS βελτίωσε αντίστοιχα την ακρίβεια κατά 0.2%, ενώ μείωσε τις ψηφιακές παραμέτους έως και 13 φορές. Διερευνώντας μία αναδραστική RC τοπολογία στην οπτική έξοδο του ίδιου συστήματος βασισμένη σε OSS κόμβους, η ακρίβεια του νευρωνικού δικτύου στην έξοδο αυξήθηκε κατά 3%, ενώ μειώθηκαν οι απαιτήσεις ως προς το υλικό για φωτοανίχνευση και ψηφιοποίηση κατά 10 και 5 φορές αντίστοιχα.","url":"https://doi.org/10.26215/heal.uoa.11720","authors":["Τσιριγώτης, Άρης"],"tags":["επιτάχυνση υλικού","νευρομορφική φωτονική","νευρωνικά δίκτυα","υπολογιστικό ρεζερβουάρ","φωτονικά ολοκληρωμένα κυκλώματα","βιοϊατρική επεξεργασία","hardware acceleration","neuromorphic photonics"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.26215/heal.uoa.11720","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48550/arxiv.2410.23639","name":"Integrating Brain-Computer Interface and Neuromorphic Computing for Human Digital Twins","source":"datacite","abstract":"The integration of immersive communication into a human-centric ecosystem has intensified the demand for sophisticated Human Digital Twins (HDTs) driven by multifaceted human data. However, the effective construction of HDTs faces significant challenges due to the heterogeneity of data collection devices, the high energy demands associated with processing intricate data, and concerns over the privacy of sensitive information. This work introduces a novel biologically-inspired (bio-inspired) HDT framework that leverages Brain-Computer Interface (BCI) sensor technology to capture brain signals as the data source for constructing HDT. By collecting and analyzing these signals, the framework not only minimizes device heterogeneity and enhances data collection efficiency, but also provides richer and more nuanced physiological and psychological data for constructing personalized HDTs. To this end, we further propose a bio-inspired neuromorphic computing learning model based on the Spiking Neural Network (SNN). This model utilizes discrete neural spikes to emulate the way of human brain processes information, thereby enhancing the system's ability to process data effectively while reducing energy consumption. Additionally, we integrate a Federated Learning (FL) strategy within the model to strengthen data privacy. We then conduct a case study to demonstrate the performance of our proposed twofold bio-inspired scheme. Finally, we present several challenges and promising directions for future research of HDTs driven by bio-inspired technologies.","url":"https://doi.org/10.48550/arxiv.2410.23639","authors":["Shang, Chen","Yu, Jiadong","Hoang, Dinh Thai"],"tags":["Human-Computer Interaction (cs.HC)","Networking and Internet Architecture (cs.NI)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.48550/arxiv.2410.23639","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48550/arxiv.2605.20802","name":"ELSA: An ELastic SNN Inference Architecture for Efficient Neuromorphic Computing","source":"datacite","abstract":"Spiking neural networks (SNNs) exploit event-driven and addition-only computation to substantially improve efficiency for intelligent computation. A key temporal property of SNNs, elastic inference, allows outputs to emerge progressively, enabling responses to salient inputs much earlier than full evaluation. However, existing SNN-specific accelerators cannot capitalize on this property. Layer-by-layer designs emit outputs only after all layers are complete, while time-step-by-time-step designs rely on coarse-grained, layer-wise pipelines that require synchronizing all spines/tokens within a layer. This barrier prevents results from being forwarded immediately, delaying the earliest possible response and forfeiting the benefits of elastic inference. To address these challenges, we propose ELSA, a near-SRAM dataflow architecture that realizes true elastic inference through a fine-grained spine/token-wise pipeline and hardware optimizations tailored to SNNs. ELSA forwards each spine/token immediately upon production, forming a continuous streaming pipeline that substantially reduces the latency to the first response. To enhance this lightweight execution, ELSA introduces a bundled address event representation protocol to lower communication traffic of network-on-chip (NoC), and leverages mini-batch spiking Gustavson-product to cut memory access and exploit inherent sparsity. Combined with mapping and scheduling optimizations, ELSA achieves efficient, event-driven computation without compromising accuracy. Experiments show that SNNs can outperform quantized artificial neural networks (QANNs) while maintaining on-par accuracy. For a 4-bit ResNet-50, ELSA achieves 3.4$\\times$ speedup and 13.6$\\times$ higher energy efficiency over the SOTA QANN accelerator (ANT), and 2.9$\\times$ speedup and 22.1$\\times$ energy efficiency gains over the SOTA SNN accelerator (PAICORE).","url":"https://doi.org/10.48550/arxiv.2605.20802","authors":["You, Kang","Nie, Chen","Yan, Lee Jun","Wei, Ziling","Zou, Cheng","Xu, Zekai","Feng, Yu","Jiang, Honglan","He, Zhezhi"],"tags":["Hardware Architecture (cs.AR)","Artificial Intelligence (cs.AI)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2605.20802","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48550/arxiv.2605.20406","name":"High Performance TiO2 Ferroelectric Field Effect Transistors with HfZrO2 for Neuromorphic Computing","source":"datacite","abstract":"TiO2 ferroelectric field effect transistors (FeFETs) with HfZrO2 (HZO) ferroelectric dielectric layers and bottom gate topology are fabricated for applications in neuromorphic systems. Two sets of devices are fabricated with different gate topologies by varying the thickness of the ferroelectric gate stack. Different device architectures are studied by varying the source drain length (LSD) and gate length (LG). The devices have high on/off ratios up to 10^7 with low leakage off currents &lt;10^-12 A. Repeated cycle testing shows high reliability and a stable memory window. The devices have large memory windows ranging from 3 to 8 V.","url":"https://doi.org/10.48550/arxiv.2605.20406","authors":["Samanta, Chandan","Palmese, Elia","Ouyang, Ziyu","Zhama, Tuofu","Pino, Robinson","Zeng, Yuping"],"tags":["Applied Physics (physics.app-ph)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2605.20406","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.60893/figshare.adv.c.8461155","name":"<strong>Reservoir Computing Using a Si-integrated Electro-optic Oxide: A Numerical Study</strong>","source":"datacite","abstract":"In this numerical study, we investigate the performance of an electro-optic reservoir under the practical constraints of a Si-integrated photonic design enabled by barium titanate, an emergent electro-optic material. Reservoir computing is a compelling neuromorphic architecture due to its natural compatibility with many physical systems. Among available implementations, the electro-optic reservoir, where an optical delay feedback loop serves as the reservoir, offers energy-efficient computation without the need for a separate memory, making its chip-scale implementation very appealing. Barium titanate, with its exceptionally large Pockels coefficient, has recently enabled significant advances in compact electro-optic modulators, positioning it as a suitable platform for such a chip-scale electro-optic reservoir. We benchmark the performance of the electro-optic reservoir over various tasks and introduce a method of constructing reservoir states that results in a significant performance improvement. Furthermore, we demonstrate the superior energy efficiency of barium titanate-based devices, owing to their very efficient electro-optic modulation. Our results show that compact, energy-efficient electro-optic reservoirs are feasible using barium titanate-based integrated Si photonic devices.","url":"https://doi.org/10.60893/figshare.adv.c.8461155","authors":["Zhang, Xiaoru","Demkov, Alexander"],"tags":["Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.60893/figshare.adv.c.8461155","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.17863/cam.119706","name":"Research data supporting \"Controlled Oxygen Vacancy Electrode Reservoir for Robust WO3-based Memory Devices\"","source":"datacite","abstract":"This dataset contains the raw and processed data used to evaluate resistive switching, synaptic behaviour, electronic structure, optical response, and microstructure in the thin-film memory devices. The dataset is organized by figure number, containing the raw experimental measurement data used to generate the corresponding main-text or supplementary plots. The file names generally encode the sample stack, device identifier, measurement type, and, where relevant, voltage or pulse conditions. Details of folder contents are as follows: Fig1b: contains consecutive current–voltage (I–V) switching cycles. Fig1c: contains I–V data collected from multiple devices with different top-electrode diameters. Each subfolder corresponds to an individual device location and contains repeated I–V scans. Fig1d: contains processed data used for the forming-voltage summary as a function of ITO oxygen deposition condition. Fig1e: contains pulsed endurance measurement files. Fig1f: contains processed endurance statistics as a function of ITO oxygen deposition condition. Fig1g: contains the sources of the comparison used in the performance map. Fig2a: contains conductance data measured under repeated identical programming pulses. These files record conductance evolution during analog switching. Fig2b: contains multilevel retention data. Fig2c: contains conductance data obtained under pulse trains with gradually increasing amplitude. Fig2d: contains the sources of the comparison used in the performance map. Fig2e: contains paired-pulse facilitation and paired-pulse depression data. Fig2f: contains spike-timing-dependent plasticity data. Fig3b, Fig3c: contains Kelvin probe force microscopy data and related processed outputs used to evaluate surface potential changes. Fig3d: contains ultraviolet photoelectron spectroscopy data. Fig3e: contains four-point probe resistivity data. Fig3f: contains operando Raman spectroscopy data collected after increasing numbers of switching cycles. These spectra track changes in WO(_3) vibrational modes during repeated electrical stressing and provide evidence of defect-related structural evolution. Fig3g: contains operando photoluminescence data collected after increasing numbers of switching cycles. These files capture defect-related optical emission changes associated with oxygen-vacancy evolution during device operation. Fig4a: contains cross-sectional transmission electron microscopy images of the optimized device stack. Fig4b-c: contains transmission electron microscopy elemental maps and related compositional imaging files. Fig4d: contains Rutherford backscattering spectrometry data and processed composition profiles. Fig4e: contains X-ray photoelectron spectroscopy data. Fig4f: contains Raman spectroscopy data. Fig4g: contains photoluminescence data. SI: contains supplementary datasets corresponding to additional electrical, structural, spectroscopic, and surface-characterization results. These include extra retention and switching data, fitting results of spectroscopy data, extended transmission electron microscopy datasets, etc. The supplementary folder structure follows the same figure-based organization as the main dataset. File formats: .csv files: mainly contain raw or processed numerical data from electrical measurements, resistivity measurements, and spectroscopy measurement data. .xrdml files: raw X-ray diffraction data exported from the diffractometer. .tif files: raw electron microscopy images and elemental map. .spm files: raw atomic force microscopy-derived files. These files can be opened in Bruker NanoScope Analysis software. .txt files: readme or supporting text files describing figure content, fitting information, or data organization.","url":"https://doi.org/10.17863/cam.119706","authors":["Yuan, Ziyi","Bakhit, Babak","Lu, Jiahao","Liu, Yixuan","Jan, Atif","Li, Xinjuan","Ducati, Caterina","Di Martino, Giuliana","Hellenbrand, Markus","Driscoll, Judith"],"tags":["CMOS compatible","indium tin oxide","neuromorphic computing","resistive switching","tungsten oxide"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.17863/cam.119706","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20134374","name":"Native Symbolic Emergence Should Replace the Translation Layer Paradigm in Neuro-Symbolic AI","source":"datacite","abstract":"The dominant paradigm in neurosymbolic AI assumes that symbolic structure must be defined before learning or extracted after it. We identify this assumption as an unnecessary architectural constraint, and we call it the symbolization gap. This position paper argues that symbolic representations should emerge naturally from neuromorphic learning dynamics without gradient descent, a translation layer, or prior vocabulary knowledge. To instantiate our position, we introduce NSSN (Neuromorphic Symbolic Spiking Network). In NSSN, each Spike-Timing-Dependent Plasticity (STDP) co-activation directly produces a new symbolic node. Four provable properties hold for any finite corpus, any domain alphabet, and any training order: monotonic growth, convergence, incremental preservation, and subquadratic complexity. Two experiments confirm that these properties hold on real data across qualitatively distinct domains. On the Sepsis Cases dataset, 13 clinical sequences are recovered with less than 0.05% variance across three training orders. On Fashion-MNIST, the same STDP rule produces a qualitatively different topology in spatial mode. The space of architectures enabling native symbolic emergence has been systematically underexplored. NSSN provides the formal and empirical foundations to explore it.","url":"https://doi.org/10.5281/zenodo.20134374","authors":["Nicolle, Christophe","Callegarin, Davide"],"tags":["Neuromorphic computing, Symbolic AI, Spiking Neural Networks, STDP, Ontology learning, Knowledge graph, Neuro-symbolic AI, Explainable AI"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20134374","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20134373","name":"Native Symbolic Emergence Should Replace the Translation Layer Paradigm in Neuro-Symbolic AI","source":"datacite","abstract":"The dominant paradigm in neurosymbolic AI assumes that symbolic structure must be defined before learning or extracted after it. We identify this assumption as an unnecessary architectural constraint, and we call it the symbolization gap. This position paper argues that symbolic representations should emerge naturally from neuromorphic learning dynamics without gradient descent, a translation layer, or prior vocabulary knowledge. To instantiate our position, we introduce NSSN (Neuromorphic Symbolic Spiking Network). In NSSN, each Spike-Timing-Dependent Plasticity (STDP) co-activation directly produces a new symbolic node. Four provable properties hold for any finite corpus, any domain alphabet, and any training order: monotonic growth, convergence, incremental preservation, and subquadratic complexity. Two experiments confirm that these properties hold on real data across qualitatively distinct domains. On the Sepsis Cases dataset, 13 clinical sequences are recovered with less than 0.05% variance across three training orders. On Fashion-MNIST, the same STDP rule produces a qualitatively different topology in spatial mode. The space of architectures enabling native symbolic emergence has been systematically underexplored. NSSN provides the formal and empirical foundations to explore it.","url":"https://doi.org/10.5281/zenodo.20134373","authors":["Nicolle, Christophe","Callegarin, Davide"],"tags":["Neuromorphic computing, Symbolic AI, Spiking Neural Networks, STDP, Ontology learning, Knowledge graph, Neuro-symbolic AI, Explainable AI"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20134373","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.26215/heal.uoa.11707","name":"Photonic neuromorphic processors based on semiconductor lasers' dynamics for reservoir computing and spiking neural networks","source":"datacite","abstract":"Η παρούσα διδακτορική διατριβή μελετά την ανάπτυξη φωτονικών νευρομορφικών επεξεργαστών (ΝΕ) που απευθύνονται στις εξής τρεις κ��ίσιμες προκλήσεις των Big Data και του Internet of Things: την υψηλή ταχύτητα επεξεργασίας, την χαμηλή κατανάλωση ισχύος και την ελαχιστοποίηση του υλικού. Η αντιμετώπιση των εν λόγω προκλήσεων ανατέθηκε στα βιοεμπνευσμένα Τεχνητά Νευρωνικά Δίκτυα. Ωστόσο, η ταυτόχρονη επίτευξη δύο βασικών, αλλά αντικρουόμενων στόχων περιόρισε την αποτελεσματικότητά τους, καθώς ήταν αναγκαία η αύξηση του αριθμού των νευρώνων και των συνάψεων παράλληλα με τον περιορισμό της καταναλισκόμενης ισχύος και της πολυπλοκότητας. Σε αυτό το πλαίσιο, επιλέχθηκαν οι χαμηλής κατανάλωσης ΝΕ, οι οποίοι όμως αδυνατούσαν να μειώσουν την αυξανόμενη πολυπλοκότητα και συνδεσιμότητα. Για το λόγο αυτό, οι ΝΕ υιοθέτησαν αρχές των Time Delay Network (TDN) που υλοποιούν χρονικά πολυπλεγμένους νευρώνες και συνάψεις. Μειώθηκαν, έτσι, οι απαιτήσεις του υλικού, αλλά και ο ρυθμός επεξεργασίας. Στόχος της παρούσας διατριβής είναι η αξιοποίηση της υψηλής ταχύτητας των φωτονικών δομών, ώστε να ενισχυθούν οι δυνατότητες επεξεργασίας των TDN ΝΕ. Κατ’ αρχάς αναλύθηκε ένας φωτονικός TDN ΝΕ βασισμένος σε ένα spin VCSEL κβαντικών τελειών. Το προταθέν σύστημα επιτυγχάνει τον τετραπλασιασμό του αριθμού των νευρώνων συγκλίνοντας σε επιδόσεις με τους σύγχρονους επεξεργαστές με τη χρήση λιγότερων νευρώνων συγκριτικά με λοιπές παρόμοιες διατάξεις. Επιπλέον, η χρήση πολλαπλών μασκών και η έγχυση των μη διαμορφωμένων πεδίων βελτιστοποιεί τις επιδόσεις του συστήματος και ελαχιστοποιεί τις απαιτήσεις του υλικού. Συνεχίζοντας, ερευνήθηκε πειραματικά και αριθμητικά ένας επαναδιαμορφώσιμος φωτονικός TDN ΝΕ ερειδόμενος σε Fabry-Perot (FP) λέιζερ. Επιβεβαιώθηκε πειραματικά η δυνατότητα αύξησης του αριθμού των εικονικών νευρώνων και των επιδόσεων του FP-TDN αξιοποιώντας την πολύτροπη εκπομπή του FP. Μετέπειτα απεδείχθη αριθμητικά η αύξηση του ρυθμού επεξεργασίας του FP-TDN χωρίς να υπάρξει μείωση της ακρίβειας του επεξεργαστή μέσω μιας νέας τεχνικής Φασματοχρονικής Πολυπλεξίας (SPTM). O FP-TDN ΝΕ σε συνδυασμό με το SPTM κατέγραψε ρυθμούς σφάλματος ίσους με 10-4 χρησιμοποιώντας μήκος ανάδρασης 140 ps, ενώ η HD-FEC συμβατότητα του συστήματος επιτεύχθηκε ακόμη και για χρόνους των 60 ps. Σημειώνεται ότι ο FP-TDN κατέγραψε ακρίβεια 95.95% στην κατηγοριοποίηση των εικόνων του MNIST επιτυγχάνοντας ρυθμό 255.1Mimages/sec. Στο επόμενο κεφάλαιο παρατίθεται ένα χρονικά πολυπλεγμένο δίκτυο με spiking νευρώνες. Ειδικότερα, παρουσιάστηκε ένα βαθύ φωτονικό spiking συνελικτικό νευρωνικό δίκτυο βασισμένο σε VCSEL νευρώνες, το οποίο εκμεταλλευόμενο τη χρονική πολυπλεξία δύναται να ρυθμίσει τον αριθμό των πραγματικών νευρώνων από 62 έως 2020 ανάλογα με τις απαιτήσεις του ρυθμού επεξεργασίας. Το παρόν δίκτυο επέδειξε δυνατότητες μάθησης χωρίς επιτήρηση, υψηλή ανοχή στο θόρυβο και ρυθμούς επεξεργασίας από 5 ns έως 720 ns ανά εικόνα. Τέλος, αναπτύχθηκε ένα spiking TDN βασισμένο σε VCSEL, το οποίο δύναται να κατηγοριοποιήσει με υψηλή ακρίβεια δεδομένα από τις βάσεις δεδομένων Iris, MNIST, αλλά και από πειραματικές εικόνες κυτταρομετρίας καταναλίσκοντας μόλις 3.23pJ ανά εικόνα. Ο συγκεκριμένος ΝΕ ενoποιεί για πρώτη φορά τα πεδία των ΝΕ και των νευρομορφικών αισθητήρων σε μια κοινή πλατφόρμα, ανοίγοντας το δρόμο για τη μελέτη κλιμακούμενων και ενεργειακά αποδοτικών ΝΕ για εφαρμογές πραγματικού χρόνου","url":"https://doi.org/10.26215/heal.uoa.11707","authors":["Skontranis, Menelaos","Σκοντράνης, Μενέλαος"],"tags":["φωτονική","υπολογιστική χρονικής καθυστέρησης","ακραία μάθηση χρονικής καθυστέρησης","spiking νευρωνικά δίκτυα","νευρομορφική υπολογιστική","photonics","time delay reservoir computing","time delay extreme learning machine"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.26215/heal.uoa.11707","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48550/arxiv.2602.18110","name":"Cavity Solitons as a Nonlinear Substrate for Photonic Neuromorphic Computing","source":"datacite","abstract":"Reservoir computing leverages nonlinear dynamics of physical systems to process temporal information with minimal training cost. Here, we demonstrate that cavity solitons sustained in a fiber optical cavity provide an optical platform for photonic reservoir computing. Our methodology exploits the use of a phase-modulated drive laser to encode the input, while the reservoir states are accessed through frequency-resolved readout. Numerical simulations indicate that the emission of Kelly waves enriches the dynamics and enhances performance for machine learning tasks. We evaluate the performance of the cavity-soliton reservoir computer on several standard benchmark tasks.","url":"https://doi.org/10.48550/arxiv.2602.18110","authors":["Arabieh, Amir Arsalan","Lupo, Alessandro","Gorza, Simon-Pierre","Massar, Serge"],"tags":["Optics (physics.optics)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2602.18110","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48550/arxiv.2605.20020","name":"Tunable magnetotransport through kinetically hindered first-order phase transitions in an antiferromagnetic metal","source":"datacite","abstract":"Controllable multilevel resistance states are of interest for memory technologies like neuromorphic computing, but robust materials platforms toward such behavior remain limited. Here, we show that the non-centrosymmetric antiferromagnetic metal CeCoGe$_3$ suggests one such route through a kinetically hindered first-order magnetic transition. Cooling through the kinetically hindered first-order transition in an applied magnetic field produces a magnetic glass state in which high- and low-temperature magnetic phases coexist. The relative fraction of these phases can be controlled by the applied field in which the sample is cooled, and the electrical resistance is directly sensitive to that fraction. As a result, it is demonstrated that CeCoGe$_3$ supports stable multilevel resistive states. These results identify kinetically hindered first-order phase transitions as a promising route towards controllable multilevel magnetoresistive states.","url":"https://doi.org/10.48550/arxiv.2605.20020","authors":["Moya, Jaime M.","Lee, Scott B.","Chatterjee, Sudipta","Mathur, Nitish","Skorupskii, Grigorii","Pollak, Connor J.","Schoop, Leslie M."],"tags":["Strongly Correlated Electrons (cond-mat.str-el)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2605.20020","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48550/arxiv.2605.19465","name":"Task-specific programming of chaos in neural circuits","source":"datacite","abstract":"Chaotic dynamics have emerged as a versatile resource for neuromorphic and probabilistic computing, enabling high-dimensional nonlinear processing and classical analogues of quantum randomness. Exploiting chaos for computation requires task-dependent control over complexity, as demonstrated in reservoir computing, random-number generation, and probabilistic inference. Existing approaches have focused on tuning element-level parameters, leaving the collective, many-body origin of chaos largely unexplored as a design freedom. Here, we demonstrate programmable chaotic dynamics for task-specific reservoir computing. Using a continuous-time neural-circuit model, we show that tuning network topology drives an ordered-to-chaotic transition, accompanied by transitions in correlation timescales, stability characteristics, and signal propagation. By jointly controlling element-level properties and network topology, we establish a unified chaos-latency phase diagram, revealing that small-world connectivity enables low-latency on-off switching of chaos via edge rewiring. Supported by distinct reservoir-computing benchmarks across various topological regimes, our results demonstrate that network topology serves as a reconfigurable parameter for task-specific computation and tunable randomness.","url":"https://doi.org/10.48550/arxiv.2605.19465","authors":["Kim, Jungyoon","Kim, Kyuho","Park, Kunwoo","Park, Namkyoo","Yu, Sunkyu"],"tags":["Chaotic Dynamics (nlin.CD)","Computational Physics (physics.comp-ph)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2605.19465","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48448/jns9-p518","name":"Reinforcement-Learned Dynamic Execution for Spiking Swin-B","source":"datacite","abstract":"Spiking Neural Networks (SNNs) are promising for energy-efficient computing on next generation neuromorphic hardware (Nunes et al. 2022). However, scaling them to large Transformer architectures introduces challenges such as training instability and high computational costs associated with multiple timesteps (Hu et al. 2024), which can offset their efficiency benefits. To address these issues, this paper proposes Spiking Swin-B, a spiking version of the large-scale Swin-B Transformer, integrated with a Reinforcement Learning (RL)-based meta-controller for dynamic execution. To ensure stable training and prevent performance degradation, we preserve the original attention mechanism of Swin-B, enabling a robust ANN-to-SNN conversion. Furthermore, the RL meta-controller learns to automatically optimize the accuracy-energy trade-off by dynamically adjusting timesteps and early-exit stages based on input complexity. Experimental results on CIFAR-100 show that the proposed Spiking Swin-B reduces computational energy by approximately 40% compared to its ANN counterpart, with only a marginal accuracy drop of about 1%. This work demonstrates the feasibility of applying learnable, dynamic control to large-scale spiking Transformers, paving a practical path toward adaptive and energy-aware SNN inference.","url":"https://doi.org/10.48448/jns9-p518","authors":["Association for Artificial Intelligence 2026"],"tags":["Artificial Intelligence"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48448/jns9-p518","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48448/qwnp-8z30","name":"I2E: Real-Time Image-to-Event Conversion for High-Performance Spiking Neural Networks","source":"datacite","abstract":"Spiking neural networks (SNNs) promise highly energy-efficient computing, but their adoption is hindered by a critical scarcity of event-stream data. This work introduces I2E, an algorithmic framework that resolves this bottleneck by converting static images into high-fidelity event streams. By simulating microsaccadic eye movements with a highly parallelized convolution, I2E achieves a conversion speed over 300x faster than prior methods, uniquely enabling on-the-fly data augmentation for SNN training. The framework's effectiveness is demonstrated on large-scale benchmarks. An SNN trained on the generated I2E-ImageNet dataset achieves a state-of-the-art accuracy of 60.50%. Critically, this work establishes a powerful sim-to-real paradigm where pre-training on synthetic I2E data and fine-tuning on the real-world CIFAR10-DVS dataset yields an unprecedented accuracy of 92.5%. This result validates that synthetic event data can serve as a high-fidelity proxy for real sensor data, bridging a long-standing gap in neuromorphic engineering. By providing a scalable solution to the data problem, I2E offers a foundational toolkit for developing high-performance neuromorphic systems. The open-source algorithm and all generated datasets are provided to accelerate research in the field.","url":"https://doi.org/10.48448/qwnp-8z30","authors":["Association for Artificial Intelligence 2026","Hu, Shaogang","Liu, Yang","Ma, Ruichen","Meng, Liwei","Ning, Ning","Qiao, Guanchao"],"tags":["Artificial Intelligence","Cognitive Modeling"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48448/qwnp-8z30","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.26083/tuprints-00026641","name":"Neuromorphic Perception using Time-of-Flight-based Encoding of Lidar Data : A Potential and Feasibility Study","source":"datacite","abstract":"This master thesis is dedicated to the research of neuromorphic perception in the domain of automated driving systems. In view of the rapid progress in the automotive industry and the increasing realization of automated driving, questions regarding the energy efficiency and performance of such systems are coming into focus. This work discusses the possibility of processing lidar data using spiking neural networks to reduce energy consumption in object detection while increasing perceptual capabilities. Automated vehicles not only promise a radical change in the transport sector, but also numerous benefits beyond pure mobility. These include reducing road accidents, reducing congestion, improving access to mobility and saving time in traffic. However, the implementation of automated driving systems faces technical and legal challenges, including the allocation of liability in the event of an accident and the need for intensive research into technical implementation. A key challenge is the perception of the vehicle, which is essential in order to maneuver safely and react to changing traffic conditions. Automated vehicles rely on various sensor systems and often use artificial intelligence methods to recognize objects and perform other tasks for Automated driving. However, these methods require considerable computing power and consume a lot of energy, which is particularly challenging in the context of electromobility, where energy is often limited by battery capacity. This thesis investigates a promising solution to this problem by integrating neuromorphic technology into the perception system. This technology is inspired by the neurobiological information processing of the human brain and aims to develop hardware and software that are similar in function and structure to biological neurons. Because the brain uses discrete impulses to process information, it consumes very little energy compared to conventional computers for comparable tasks. Energy is only consumed when these pulses occur and information is processed. This work focuses on the use of lidar sensors, which emit infrared light and measure the reflected laser beams to determine the distance to objects in the environment. An important parameter is the time of flight of the laser beams. The ToF can be used to convert the lidar data into discrete pulses that the neuromorphic perception system communicates with. The integration of neuromorphic perception systems into automated vehicles has the potential to significantly increase energy efficiency and improve the ability to perceive the environment. In order to analyze the potential and feasibility of a neuromorphic perception system using the ToF of lidar data, a morphological analysis is performed. This analysis takes into account different approaches and aspects that have been elaborated in an extensive literature review. The perception pipeline is divided into subsystems and subfunctions, leading to two concepts that fulfill different requirements for a neuromorphic perception system. These two concepts serve as a starting point for further research and development of this promising technology. The thesis is divided into several chapters that provide a comprehensive overview of the topic of neuromorphic perception systems for automated driving. It covers the basics of automated driving systems, artificial neural networks and spiking neural networks. Lidar sensors, different coding schemes, point cloud object detection, spiking neuron models, SNN hardware implementations and existing approaches are also discussed. The results of the literature review are evaluated based on a morphological analysis. A baseline and an advanced concept of a neuromorphic perception system are presented. In conclusion, this thesis shows the enormous potential of neuromorphic perception systems for automated driving and provides an outlook on possible future developments and research directions. Reducing energy consumption is crucial to ach","url":"https://doi.org/10.26083/tuprints-00026641","authors":["Schulte, Jonas Valentin"],"tags":["620"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.26083/tuprints-00026641","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.13023/etd.2026.90","name":"IONIC-ELECTRONIC INTERACTIONS GOVERNING CHARGE TRANSPORT AND PERFORMANCE IN ORGANIC ELECTROCHEMICAL TRANSISTORS","source":"datacite","abstract":"Organic electrochemical transistors (OECTs) use organic mixed ionic electronic conductors (OMIECs) as the active material because of their unique ability to transport both electronic and ionic charge carriers and operate in an aqueous environment. Moreover, OECTs provide a wide range of applications, starting from biosensors, energy storage, and neuromorphic computing. In spite of the significant prospect of OECTs, there is a critical gap in understanding the fundamental properties during device operation, including charge transport, charge injection mechanism, contact geometry, and electrolyte solvent properties. In this study, low-temperature measurement of OECT device parameters such as mobility, contact resistance, and activation energy challenges the existing assumption of charge transport physics in heavily doped OMIECs. Mobility-temperature trend indicates multiple trap and release as the dominant charge transport mechanism, while contact resistance-temperature trend indicates tunneling as the dominant charge injection mechanism. Next, conductance-temperature data show a reversible insulator-to-metal transition at high carrier densities, which is observed here for the first time in OMIECs and OECTs. Furthermore, a deviation from the gradual channel approximation model is observed due to the presence of edge effects at narrower channels and voltage-dependent channel resistance. Overall, this work provides a combined framework that shows how the OECT performance is influenced by the complex interplay of electronic-ionic interactions, carrier density, device geometry, and electrolyte solvent. This analysis paves a clear path for future design of high-performance OECT devices with proper estimation of device parameters and a deeper understanding of device physics.","url":"https://doi.org/10.13023/etd.2026.90","authors":["Tahsin, Samiha"],"tags":["FOS: Electrical engineering, electronic engineering, information engineering"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.13023/etd.2026.90","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20288933","name":"Interference-Field-Grown Bio-Synaptic Semiconductor Organisms: A Conceptual Framework for Wave-Written Living Electronic Morphogenesis","source":"datacite","abstract":"This paper proposes a conceptual framework for interference-field-grown bio-synaptic semiconductor organisms: living or life-like material systems that form, repair, and adapt semiconductor-like electronic networks through biological growth, material deposition, electron transport, and externally imposed wave fields. The central idea is that optical, electrical, or acoustic interference patterns can act not only as fabrication masks, but as spatial growth commands for living electronic morphogenesis. In this framework, an interference field writes an initial circuit-like landscape, while living or biohybrid material processes complete, repair, and adapt the resulting conductive or semiconductor-like network. The paper introduces a minimal mathematical model in which interference intensity, frequency-selective biological response, conductive growth, metabolic repair, current-dependent reinforcement, and material memory jointly define a time-evolving graph of electronic connectivity. The proposed system is not intended as an immediate replacement for silicon logic. Instead, it targets slowly adaptive, self-healing, environmentally coupled bioelectronic skins, sensor films, analog computing substrates, pollution-recording membranes, biohybrid photoreactive surfaces, and living neuromorphic materials. The work connects engineered living materials, living electronics, interference lithography, optogenetic biofilm patterning, and biohybrid semiconductor systems into a single conceptual architecture. Its core claim is that circuits may be understood not only as static manufactured artifacts, but as adaptive morphologies that can be grown, trained, damaged, repaired, and partially remembered by the material itself.","url":"https://doi.org/10.5281/zenodo.20288933","authors":["Trinity Labo"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20288933","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20288932","name":"Interference-Field-Grown Bio-Synaptic Semiconductor Organisms: A Conceptual Framework for Wave-Written Living Electronic Morphogenesis","source":"datacite","abstract":"This paper proposes a conceptual framework for interference-field-grown bio-synaptic semiconductor organisms: living or life-like material systems that form, repair, and adapt semiconductor-like electronic networks through biological growth, material deposition, electron transport, and externally imposed wave fields. The central idea is that optical, electrical, or acoustic interference patterns can act not only as fabrication masks, but as spatial growth commands for living electronic morphogenesis. In this framework, an interference field writes an initial circuit-like landscape, while living or biohybrid material processes complete, repair, and adapt the resulting conductive or semiconductor-like network. The paper introduces a minimal mathematical model in which interference intensity, frequency-selective biological response, conductive growth, metabolic repair, current-dependent reinforcement, and material memory jointly define a time-evolving graph of electronic connectivity. The proposed system is not intended as an immediate replacement for silicon logic. Instead, it targets slowly adaptive, self-healing, environmentally coupled bioelectronic skins, sensor films, analog computing substrates, pollution-recording membranes, biohybrid photoreactive surfaces, and living neuromorphic materials. The work connects engineered living materials, living electronics, interference lithography, optogenetic biofilm patterning, and biohybrid semiconductor systems into a single conceptual architecture. Its core claim is that circuits may be understood not only as static manufactured artifacts, but as adaptive morphologies that can be grown, trained, damaged, repaired, and partially remembered by the material itself.","url":"https://doi.org/10.5281/zenodo.20288932","authors":["Trinity Labo"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20288932","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20282505","name":"Dataset of \"From Impedance to Bifurcation: Experimental Stability Mapping of Self-Oscillatory Devices\"","source":"datacite","abstract":"This dataset contains the raw data supporting the article \"From Impedance to Bifurcation: Experimental Stability Mapping of Self-Oscillatory Devices\". For a detailed description of files and methods, see the accompanying Readme.txt.","url":"https://doi.org/10.5281/zenodo.20282505","authors":["Rivera-Sierra, Gonzalo","Rubio-Magnieto, Jenifer","Bisquert, Juan"],"tags":["self-sustained oscillators","neuromorphic computing","impedance spectroscopy","negative differential resistance","thyristor oscillators","equivalent circuit"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20282505","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20282506","name":"Dataset of \"From Impedance to Bifurcation: Experimental Stability Mapping of Self-Oscillatory Devices\"","source":"datacite","abstract":"This dataset contains the raw data supporting the article \"From Impedance to Bifurcation: Experimental Stability Mapping of Self-Oscillatory Devices\". For a detailed description of files and methods, see the accompanying Readme.txt.","url":"https://doi.org/10.5281/zenodo.20282506","authors":["Rivera-Sierra, Gonzalo","Rubio-Magnieto, Jenifer","Bisquert, Juan"],"tags":["self-sustained oscillators","neuromorphic computing","impedance spectroscopy","negative differential resistance","thyristor oscillators","equivalent circuit"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20282506","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.26083/tuprints-00024217","name":"Substoichiometric Phases of Hafnium Oxide with Semiconducting Properties","source":"datacite","abstract":"Since the dawn of the information age, all developments that provided a significant improvement in information processing and data transmission have been considered as key technologies. The impact of ever new data processing innovations on the economy and almost all areas of our daily lives is unprecedented and a departure from this trend is unimaginable in the near future. Even though the end of Moore's Law has been predicted all too often, the steady exponential growth of computing capacity remains unaffected to this day, due to tremendous commercial pressure. While the minimum physical size of the transistor architecture is a serious constraint, the steady evolution of computing effectiveness is not limited in the predictable future. However, the focus of development will have to expand more strongly to other technological aspects of information processing. For example, the development of new computer paradigms which mark a departure from the digitally dominated van Neumann architecture will play an increasingly significant role. The category of so-called next-generation non-volatile memory technologies, based on various physical principles such as phase transformation, magnetic or ferroelectric properties or ion diffusion, could play a central role here. These memory technologies promise in part strongly pronounced multi-bit properties up to quasi-analog switching behavior. These attributes are of fundamental importance especially for new promising concepts of information processing like in-memory computing and neuromorphic processing. In addition, many next-generation non-volatile memory technologies already show advantages over conventional media such as Flash memory. For example, their application promises significantly reduced energy consumption and their write and especially read speeds are in some cases far superior to conventional technology and could therefore already contribute significant technological improvements to the existing memory hierarchy. However, these alternative concepts are currently still limited in terms of their statistical reliability, among other things. Even though phase change memory in the form of the 3D XPoint, for example, has already been commercialized, the developments have not yet been able to compete due to the enormous commercial pressure in Flash memory research. Nevertheless, the further development of alternative concepts for the next and beyond memory generations is essential and the in-depth research on next-generation non-volatile memory technologies is therefore a hot and extremely important scientific topic. This work focuses on hafnium oxide, a key material in next-generation non-volatile memory research. Hafnium oxide is very well known in the semiconductor industry, as it generated a lot of attention in the course of high-k research due to its excellent dielectric properties and established CMOS compatibility. However, since the growing interest in so-called memristive memory, research efforts have primarily focused on the value of hafnium oxide in the form of resistive random-access memory (RRAM) and, with the discovery of ferroelectricity in HfO₂, ferroelectric resistive random-access memory (FeRAM). RRAM is a next-generation non-volatile memory technology that features a simple metal-insulator-metal (MIM) structure, excellent scalability, and potential 3D integration. In particular, the aforementioned gradual to quasi-continuous switching behavior has been demonstrated on a variety of RRAM systems. A significant change of the switching properties is achievable, for example, by the choice of top and bottom electrodes, the introduction of doping elements, or by designated oxygen deficiency. In particular, the last point is based on the basic physical principle of the hafnium oxide-based RRAM mechanism, in which local oxygen ions are stimulated to diffuse by applying an electrical potential, and a so-called conducting filament is formed by the remaining vacancies, which el","url":"https://doi.org/10.26083/tuprints-00024217","authors":["Kaiser, Nico"],"tags":["500","530","540"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.26083/tuprints-00024217","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48448/gcqw-gy05","name":"Ferroelectric FETs for Neuromorphic Computing: Low-Frequency Noise and Fast I-V Characteristics","source":"datacite","abstract":"This study investigates the low-frequency noise (LFN) characteristics and fast I-V response of ferroelectric field-effect transistors (FeFETs) for neuromorphic computing. LFN analysis is conducted to demonstrate the conduction mechanisms of the FeFETs and to assess read noise. Additionally, fast I-V characterization is employed to reveal the trapping dynamic that significantly affects the synaptic functionality of FeFETs. The acceptor-like traps with response times in the millisecond range are responsible for the degradation induced during program/erase cycles.","url":"https://doi.org/10.48448/gcqw-gy05","authors":["IEEE International Reliability Physics Symposium 2025","Shin, Wonjun"],"tags":["Reliability Physics","Neuromorphic Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48448/gcqw-gy05","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48448/37tz-k271","name":"Conductance Variation-Assisted Adversarial Attack Robustness on 40nm TaOX-based ReRAM CiM","source":"datacite","abstract":"This work investigates the conductance variation-assisted enhancement of neural network (NN) robustness against adversarial attacks, exploiting the measurements of 32K bits 40nm TaOX-based analog Resistive Random Access Memory (ReRAM) devices. Proposed Computation-in-Memory (CiM)-aware adversarial training enhances NN robustness against both adversarial attacks and conductance variations by integrating the measured variations with training, improves classification accuracy of Fast Gradient Sign Method (FGSM)-attacked CIFAR-10 on ResNet-32 by 25% and that of Projected Gradient Descent (PGD)-attacked by 22%.","url":"https://doi.org/10.48448/37tz-k271","authors":["IEEE International Reliability Physics Symposium 2025","Awamura, Satoshi","Matsui, Chihiro","Misawa, Naoko","Morimoto, Masahiro","Takeuchi, Ken","Yamauchi, Kenshin"],"tags":["Reliability Physics","Neuromorphic Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48448/37tz-k271","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48448/x1s5-jk76","name":"Read Voltage Dependency of Random Telegraph Noise in the Intermediate State of TaOX-based ReRAM","source":"datacite","abstract":"This work investigates random telegraph noise (RTN) behavior in the intermediate resistance states of 40nm TaOX-based analog ReRAM. Uniquely in the intermediate resistance states, both the frequency and amplitude of RTN fluctuations tend to increase with the read voltage. Considering the trade-off between increasing them and enhancing margins among adjacent resistance states as read voltage rises, a 0.2V readout minimizes RTN-induced misdetection of resistance states, achieving a significantly low error rate of 0.19%.","url":"https://doi.org/10.48448/x1s5-jk76","authors":["IEEE International Reliability Physics Symposium 2025","AKINAGA, Hiroyuki","Matsui, Chihiro","Misawa, Naoko","Naitoh, Yasuhisa","Shima, Hisashi","Takeuchi, Ken","Yamauchi, Kenshin"],"tags":["Reliability Physics","Neuromorphic Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48448/x1s5-jk76","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48448/d5fm-st28","name":"Temperature and Drift-Aware High-Level PCM-based Array Model for Reliable Hardware IMC design","source":"datacite","abstract":"In-Memory Computing (IMC) is an important lead to propose efficient AI hardware on the edge. In this context, emerging non-volatile memories, such as Phase-Change Memory (PCM) are fundamental. However, PCM device non-idealities, hardware and application challenges render IMC design complex. To overcome this challenge, we propose a novel high-level PCM-based model for hardware IMC. We consider, for the first time, the temperature effect on PCM conductance stability – a key parameter for PCM-based IMC.","url":"https://doi.org/10.48448/d5fm-st28","authors":["IEEE International Reliability Physics Symposium 2025","ALLEGRA, Mario","Anghel, Lorena","BALDO, Matteo","ESMANHOTTO, Eduardo","LECOQ, Xavier","Prenat, Guillaume","VIOLLET, Valentin"],"tags":["Reliability Physics","Neuromorphic Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48448/d5fm-st28","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48448/s16y-fm14","name":"Multi-level RTN with Certain Regularities in Oxide-RRAM: Experiments, Defect Dynamics and 3D Multi-Physics Modeling","source":"datacite","abstract":"This paper investigated the multi-level RTN phenomena with certain regularities in the Ti/HfOx/TiN RRAM with the comprehensive measurements and modeling of the multi-phonon trap-assisted tunneling (MPTAT) and First-Principle calculations. The polaron band of Vo is the main reason to produce the RTN of RRAM. Two-level RTN is attributed to the transition between V0 and V1-. The multi-level RTN arises from the collective action of Vo at different positions, affecting current fluctuation, capturing and emission time.","url":"https://doi.org/10.48448/s16y-fm14","authors":["IEEE International Reliability Physics Symposium 2025","Cai, Zifei","Ji, Zhigang","Liu, Pan","Miao, Xiangshui","Mu, Dejiang","Wang, Xingsheng","Xue, Kan-Hao","Zhang, Jian","Zhou, Zijian"],"tags":["Reliability Physics","Neuromorphic Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48448/s16y-fm14","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48448/t3ed-3211","name":"Reliability-Ensured and Fast (< 100 ns) Analog Synapse for Training Accelerators: All-Sputtered HfOy/HfOx RRAM","source":"datacite","abstract":"We reveal that sputtered HfOx, often neglected in RRAM design, can be an alternative for highly reliable, fast (&lt; 100 ns) analog synapses to accelerate training algorithms. The sub-stoichiometric HfOx enables rapid oxygen vacancy (V0) response. Additional HfOy (x&lt;y) distributes V0 uniformly across the HfOy/HfOx RRAM stack, enhancing reliability in dynamic synaptic operation, where multiple pulses are continuously addressed. This results in robust D2D/C2C uniformity and ensures multilevel retention, validated by real-time transient current analysis.","url":"https://doi.org/10.48448/t3ed-3211","authors":["IEEE International Reliability Physics Symposium 2025","Jeon, Seonuk","Kim, Yunsur","Lim, Seokjae","Woo, Jiyong"],"tags":["Reliability Physics","Neuromorphic Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48448/t3ed-3211","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48448/1vzy-zr77","name":"Analog computing with high precision and reliability","source":"datacite","abstract":"Analog devices such as memristors have been restricted to specific and low-precision application areas due to their historical limitations in precision and reliability. To solve that, we study the source of the reading noise and successfully mitigate it, achieving 2048 stable conductance levels. At the system level, we co-design a circuit architecture and programming algorithm to mitigate the device programming variations and reliability issues and demonstrate high-precision computing applications with enhanced power efficiency.","url":"https://doi.org/10.48448/1vzy-zr77","authors":["IEEE International Reliability Physics Symposium 2025","Song, Wenhao","Yang, J. Joshua"],"tags":["Reliability Physics","Neuromorphic Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48448/1vzy-zr77","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48448/crk0-6m31","name":"Impact of Non-ideal Reliability Characteristics of SiOx p-Bit for Complex Optimization Problem Solver","source":"datacite","abstract":"SiOx threshold switching (TS) devices generate periodic output voltage spikes for a given input voltage (Vin) pulse. Introducing Ti layers to induce variability in the SiOx film, the number of spikes can be adjusted as a sigmoid of Vin amplitude. Therefore, Ti/SiOx/Ti TS can serve as probabilistic bit (p-bit), crucial for solving complex optimization problems (COPs). We investigate the impact of the non-ideal SiOx p-bit response on COP by considering classified scenarios based on measurements.","url":"https://doi.org/10.48448/crk0-6m31","authors":["IEEE International Reliability Physics Symposium 2025","Choi, Hyeonsik","Kim, Jihyun","Woo, Jiyong"],"tags":["Reliability Physics","Neuromorphic Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48448/crk0-6m31","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48448/b324-sr08","name":"Effects of Temperature and Device-to-Device Variability in pFET-Based Bias Temperature Instability Reservoir Computing","source":"datacite","abstract":"We conduct gait authentication tests across different sizes, temperatures, and device sets to evaluate the reliability of our pFETs BTI PRC system. The findings suggest that large devices are more resilient to high temperatures and device-to-device variability. Small devices are more sensitive to environmental changes.Large devices are preferred when accuracy is important, while small devices are favored when security is the primary concern. We use a stochastic model to analyze the physics of our system.","url":"https://doi.org/10.48448/b324-sr08","authors":["IEEE International Reliability Physics Symposium 2025","Bury, Erik","Degraeve, Robin","Guo, Yuanyang","Kaczer, Vice General Chair, Ben","Saraza-Canflanca, Pablo","Verbauwhede, Ingrid"],"tags":["Reliability Physics","Neuromorphic Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48448/b324-sr08","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48448/y493-hc90","name":"Investigation on Temperature-Dependent Resistance States of 40nm MLC-RRAM Macro","source":"datacite","abstract":"Resistive Random-Access Memory (RRAM) is notable for its multi-level cell (MLC) capabilities. However, its conductance is highly susceptible to temperature fluctuations, challenging practical deployment. Here, we characterize the temperature-dependent resistance states of 40nm RRAM macro, indicating that conductance states have different relations with the temperature. A physics model is developed to describe the resistance varying with temperature. Further, we propose the calibration method to reduce the readout errors, which is crucial for storage and CIM.","url":"https://doi.org/10.48448/y493-hc90","authors":["IEEE International Reliability Physics Symposium 2025","Cai, Yimao","Feng, Yulin","Guan, Haokai","Huang, Peng","Kang, Jinfeng","Liu, Lifeng","Shan, Linbo","Sun, Lei","Tao, Kefan","Wang, Zongwei","Zhong, Shichao"],"tags":["Reliability Physics","Neuromorphic Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48448/y493-hc90","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48448/wck7-4x53","name":"Compact MEOL OxRAM with 14 conductance levels for Dense Embedded Inference Computing","source":"datacite","abstract":"A compact 1T1R memory cell with 14 conductance levels is fabricated in 28nm technology. The OxRAM is integrated in the 40nm×40nm drain contact of GO1 FDSOI transistors, enabling memory arrays with minimal 0.0357µm2 bitcell area. 106 cycles endurance, 2h data retention at 150°C and 109 read disturb cycles are demonstrated, with 30µA SET currents and 1.2V RESET voltages. On-chip Neural Network inference capabilities are demonstrated for a QSNN solving Automatic Lip-Reading task with state-of-art accuracy.","url":"https://doi.org/10.48448/wck7-4x53","authors":["IEEE International Reliability Physics Symposium 2025","Andrieu, François","Barraud, Sylvain","Boulard, François","Castan, Clément","Comboroure, Corinne","Dampfhoffer, Manon","Dubreuil, Theophile","Gharbi, Ahmed","Lambert, Amélie","Minguet Lopez, Joel","Pedini, Jean-Michel","Souhaité, Aurelie"],"tags":["Reliability Physics","Neuromorphic Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48448/wck7-4x53","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20253820","name":"Theta-Gamma Coupling and the Critical Damping Threshold: A Universal Resonance Principle in Neural Dynamics, Control Theory, and Complex Systems","source":"datacite","abstract":"The coordination of neural oscillations across distinct frequency bands is a fundamental mechanism of cognitive processing, with theta-gamma coupling (TGC) serving as a primary substrate for memory encoding, spatial navigation, and attentional selection. While empirical observations have long established the presence of cross-frequency coupling (CFC), the precise dynamical constraints governing its stability and efficiency remain poorly defined. This paper proposes that TGC operates at a Critical Damping Threshold, a universal resonance principle derived from the intersection of control theory, information geometry, and the Universal Spectral Decay Theorem (USDT). We demonstrate that the optimal coupling strength between theta (4–8 Hz) and gamma (30–100 Hz) oscillations corresponds to a damping ratio , the inverse of the Golden Ratio (). This value represents the boundary between underdamped oscillatory instability and overdamped informational stagnation, maximizing the spectral quality factor while minimizing metabolic cost. By modeling the hippocampal formation as a non-linear feedback control system, we derive the conditions under which TGC achieves maximal information throughput. We further generalize this principle to engineering control systems and ecological networks, demonstrating that the threshold is a universal attractor for complex adaptive systems operating at the edge of chaos. Our findings provide a unified theoretical framework for understanding cross-frequency coupling, offering novel predictions for neurophysiological experiments and robust design principles for artificial intelligence and resilient infrastructure.","url":"https://doi.org/10.5281/zenodo.20253820","authors":["Granops, Udo"],"tags":["Theta–gamma coupling","Cross-frequency coupling","Critical damping","Damping ratio","Hippocampal oscillations","Nonlinear feedback control","control-theoretic neural modeling","neural modeling"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20253820","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20253819","name":"Theta-Gamma Coupling and the Critical Damping Threshold: A Universal Resonance Principle in Neural Dynamics, Control Theory, and Complex Systems","source":"datacite","abstract":"The coordination of neural oscillations across distinct frequency bands is a fundamental mechanism of cognitive processing, with theta-gamma coupling (TGC) serving as a primary substrate for memory encoding, spatial navigation, and attentional selection. While empirical observations have long established the presence of cross-frequency coupling (CFC), the precise dynamical constraints governing its stability and efficiency remain poorly defined. This paper proposes that TGC operates at a Critical Damping Threshold, a universal resonance principle derived from the intersection of control theory, information geometry, and the Universal Spectral Decay Theorem (USDT). We demonstrate that the optimal coupling strength between theta (4–8 Hz) and gamma (30–100 Hz) oscillations corresponds to a damping ratio , the inverse of the Golden Ratio (). This value represents the boundary between underdamped oscillatory instability and overdamped informational stagnation, maximizing the spectral quality factor while minimizing metabolic cost. By modeling the hippocampal formation as a non-linear feedback control system, we derive the conditions under which TGC achieves maximal information throughput. We further generalize this principle to engineering control systems and ecological networks, demonstrating that the threshold is a universal attractor for complex adaptive systems operating at the edge of chaos. Our findings provide a unified theoretical framework for understanding cross-frequency coupling, offering novel predictions for neurophysiological experiments and robust design principles for artificial intelligence and resilient infrastructure.","url":"https://doi.org/10.5281/zenodo.20253819","authors":["Granops, Udo"],"tags":["Theta–gamma coupling","Cross-frequency coupling","Critical damping","Damping ratio","Hippocampal oscillations","Nonlinear feedback control","control-theoretic neural modeling","neural modeling"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20253819","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48550/arxiv.2605.07936","name":"A Fully Tunable Ultra-Low Power Current-Mode Memory Cell in Standard CMOS Technology","source":"datacite","abstract":"This work introduces a fully tunable, ultra-low power unipolar memory cell inspired by the Schmitt-trigger comparator and designed in CMOS using only nine transistors. The proposed circuit operates entirely in the current domain and exploits a novel feedback configuration between two interdependent Heaviside-like thresholding elements to produce tunable bistable switching behavior. Its three key parameters-threshold current, hysteresis width, and output gain-are independently tunable via programmable bias currents, enabling flexibility across diverse analog computing applications. Unlike prior Schmitt-trigger designs, it simultaneously achieves current-mode operation, nanowatt-range power consumption, temperature stability, and full tunability, solely using standard MOSFET elements. Schematic-level simulations in a 180 nm CMOS process confirm robust hysteresis and resilience to device mismatch. Building on this circuit, we develop a complete family of spike-based logic gates using three-level current encoding, where the bistable memory retains the polarity of the last spike on each input indefinitely, enabling asynchronous logic operations without temporal windowing or refresh mechanisms. The same circuit also serves as the primitive for Bistable Memory Recurrent Units in analog neural networks, where the quantized hidden states provide inherent noise immunity. Together, these capabilities position the design as a versatile building block for next-generation neuromorphic processors integrating memory, logic, and recurrent computation.","url":"https://doi.org/10.48550/arxiv.2605.07936","authors":["Fyon, Arthur","Mendolia, Loris","Redouté, Jean-Michel","Franci, Alessio","Drion, Guillaume"],"tags":["Signal Processing (eess.SP)","FOS: Electrical engineering, electronic engineering, information engineering","FOS: Electrical engineering, electronic engineering, information engineering"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2605.07936","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48550/arxiv.2509.09344","name":"Lifetime of bimerons and antibimerons in two-dimensional magnets","source":"datacite","abstract":"Soliton-based computing architectures have recently emerged as a promising avenue to overcome fundamental limitations of conventional information technologies, the von Neumann bottleneck. In this context, magnetic skyrmions have been widely considered for in-situ processing devices due to their mobility and enhanced lifetime in materials with broken inversion symmetry. However, modern applications in non-volatile reservoir or neuromorphic computing raise the additional demand for non-linear inter-soliton interactions. Here, we report that solitons in easy-plane magnets, such as bimerons and antibimerons, show greater versatility and potential for non-linear interactions than skyrmions and antiskyrmions, making them superior candidates for this class of applications. Using first-principles and transition state theory, we predict the coexistence of degenerate bimerons and antibimerons at zero field in a van der Waals heterostructure Fe$_3$GeTe$_2$/Cr$_2$Ge$_2$Te$_6$ -- an experimentally feasible system. We demonstrate that, owing to their distinct structural symmetry, bimerons exhibit fundamentally different behavior from skyrmions and cannot be regarded as their in-plane counterparts, as is often assumed. This distinction leads to unique properties of bimerons and antibimerons, which arise from the unbroken rotational symmetry in easy-plane magnets. These range from anisotropic soliton-soliton interactions to strong entropic effects on their lifetime, driven by the non-local nature of thermal excitations. Our findings reveal a broader richness of solitons in easy-plane magnets and underline their unique potential for spintronic devices.","url":"https://doi.org/10.48550/arxiv.2509.09344","authors":["Goerzen, Moritz A.","Drevelow, Tim","Haldar, Soumyajyoti","Schrautzer, Hendrik","Heinze, Stefan","Li, Dongzhe"],"tags":["Mesoscale and Nanoscale Physics (cond-mat.mes-hall)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2509.09344","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48550/arxiv.2508.18014","name":"A General Molecular-Scale Dynamic Memristor Model Based on Non-equilibrium Charge Transport Kinetics and Its Information Processing Capability in Reservoir Computing","source":"datacite","abstract":"Non-equilibrium molecular-scale dynamics, where fast electron transport couples with slow chemical state evolution, underpins the complex behaviors of molecular memristors, yet a general model linking these dynamics to neuromorphic computing remains elusive. We introduce a dynamic memristor model that integrates Landauer and Marcus electron transport theories with the kinetics of slow processes, such as proton/ion migration or conformational changes. This framework reproduces experimental conductance hysteresis and emulates synaptic functions like short-term plasticity (STP) and spike-timing-dependent plasticity (STDP). By incorporating the model into a reservoir computing (RC) architecture, we show that computational performance optimizes when input frequency and bias mapping range align with the molecular system's intrinsic kinetics. This chemistry-centric, bottom-up approach provides a theoretical foundation for molecular-scale neuromorphic computing, demonstrating how non-equilibrium molecular-scale dynamics can drive information processing in the post-Moore era.","url":"https://doi.org/10.48550/arxiv.2508.18014","authors":["Chen, Yueqi","Ji, Xuan","Yu, Xi"],"tags":["Chemical Physics (physics.chem-ph)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2508.18014","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48550/arxiv.2312.12264","name":"Exploring Non-Steady-State Charge Transport Dynamics in Information Processing: Insights from Reservoir Computing","source":"datacite","abstract":"Exploring nonlinear chemical dynamic systems for information processing has emerged as a frontier in chemical and computational research, seeking to replicate the brain's neuromorphic and dynamic functionalities. We have extensively explored the information processing capabilities of a nonlinear chemical dynamic system through theoretical modeling by integrating a non-steady-state proton-coupled charge transport system into reservoir computing (RC) architecture. Our system demonstrated remarkable success in tasks such as waveform recognition, voice identification and chaos system prediction. More importantly, through a quantitative study, we revealed the key role of the alignment between the signal processing frequency of the RC and the characteristic time of the dynamics of the nonlinear system, which dictates the efficiency of RC task execution, the reservoir states and the memory capacity in information processing. The system's information processing frequency range was further modulated by the characteristic time of the dynamic system, resulting in an implementation akin to a 'chemically-tuned band-pass filter' for selective frequency processing. Our study thus elucidates the fundamental requirements and dynamic underpinnings of the non-steady-state charge transport dynamic system for RC, laying a foundational groundwork for the application of dynamic molecular devices for in-materia computing.","url":"https://doi.org/10.48550/arxiv.2312.12264","authors":["Li, Zheyang","Yu, Xi"],"tags":["Chemical Physics (physics.chem-ph)","Disordered Systems and Neural Networks (cond-mat.dis-nn)","FOS: Physical sciences","FOS: Physical sciences","92E99 (Primary) 68T07, 82C32 (Secondary)"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.48550/arxiv.2312.12264","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48550/arxiv.2605.17752","name":"Optical Neural Networks from Coherent Transient Dynamics in Waveguide QED","source":"datacite","abstract":"Optical neural networks promise ultrafast, low-energy information processing by performing computation directly with photons. Current implementations, however, are largely restricted to steady-state operation and rely on high-latency electro-optical conversion for nonlinear activation. To address these limitations, we propose an all-optical fully connected neural network architecture in which the basic neuronal functions are realized by coherent transient quantum dynamics. Within this framework, phase-tunable nonlocal interference in a giant cavity implements programmable synaptic weights; an integrator operating in the bad cavity regime performs temporal summation by coherently combining sequential wavepackets; and transient Rabi dynamics of a driven two-level system provide nonlinear activation. Full-physics simulations demonstrate high classification accuracy on MNIST and colored-object recognition tasks. These results eliminate the optoelectronic activation bottleneck, reduce latency, and establish transient light-matter dynamics as a native physical resource for high-dimensional nonlinear information processing, paving the way toward fully optical neuromorphic computing.","url":"https://doi.org/10.48550/arxiv.2605.17752","authors":["Cao, Jiande","Zeng, Yexiong","Nori, Franco","Xiang, Ze-Liang"],"tags":["Quantum Physics (quant-ph)","Optics (physics.optics)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2605.17752","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48550/arxiv.2605.16946","name":"Reprogrammable magnonic logic in a multiferroic heterostructure via magnetoelectric coupling","source":"datacite","abstract":"The realization of fully reconfigurable, voltage-controlled, and programmable on-chip magnonic devices is essential to fully harness the potential of spin waves for signal processing, logic and neuromorphic computing. Yet, existing demonstrations of electrical tuning of magnonic responses are either volatile, current-driven and thus energy-inefficient, or rely on local strain modification limiting their scalability for wafer-scale integration. Here, we address this challenge using a BiFeO3/La0.67Sr0.33MnO3 multiferroic thin film heterostructure. We show that ferroelectric domain engineering in BiFeO3 enables deterministic tuning of the magnon dispersion of La0.67Sr0.33MnO3, producing frequency shifts up to $\\sim 150 MHz$ and allowing reconfigurable waveguiding. Micro-focused Brillouin light scattering directly images these effects, revealing electrically defined magnonic waveguides and spatially programmable dispersion. Compared to conventional approaches, this method provides non-volatile and reversible control. Furthermore, using an inverse-design simulation code, we demonstrate the capability of our platform to perform advanced magnonic functions such as frequency demultiplexing. Our results open a new avenue for using magnetoelectric heterostructures for magnonic logic, with further applicability to reservoir and neuromorphic computing and AI driven magnonic devices.","url":"https://doi.org/10.48550/arxiv.2605.16946","authors":["Che, Ping","Abdelsamie, Amr","Papp, Ádám","Salama, Sali","Thiaville, André","Lebrun, Romain","Fusil, Stéphane","Garcia, Vincent","Vecchiola, Aymeric","Bouzehouane, Karim","Bibes, Manuel","Barthélémy, Agnès","Adam, Jean-Paul","Demidov, Vladislav","Bortolotti, Paolo","Anane, Abdelmadjid","Boventer, Isabella"],"tags":["Mesoscale and Nanoscale Physics (cond-mat.mes-hall)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2605.16946","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20277956","name":"Neuromorphic tissues: Soft Biomolecular Networks for Brain-Inspired Temporal Computing","source":"datacite","abstract":"This repository contains all MATLAB scripts and example input data required to reproduce the main computational results presented in the companion manuscript (see Connected_Reservoir_Paper_Science.pdf). The package implements and compares two physical-model reservoir computing systems built from droplet-interface-bilayer (DIB) ionic devices: Connected Reservoir Network – simulates a spatially connected droplet lattice driven by masked current inputs. Parallel Reservoir Network – simulates independent (uncoupled) memristive nodes in parallel as a reference system. Both reservoirs are modeled with the Alamethicin-type Richard’s differential equation (RDE) pore-state dynamics, solved numerically using MATLAB’s stiff ODE solvers (ode15s). Main capabilities NARMA tasks: Generates masked input sequences and trains linear readouts to predict NARMA orders 2–10; reports train/test NRMSE. Lorenz-63 task: Demonstrates prediction of all three Lorenz-63 chaotic states using the optimized 43-node connected reservoir. Hyperparameter sweeps: Grid-search scripts for input amplitude, mask length, and node count for performance benchmarking. Reproducible I/O: Includes functions for input-mask generation, state sampling after each pulse, and standard feature-matrix construction. How to reproduce figures/results ParallelReservoirNARMA_Optimized.m — reproduces the main NARMA benchmarking shown for the uncoupled network. HyperParameterTuningOptimized.m — performs grid search and NARMA evaluation for the connected reservoir. Lorenz63_Prediction.m — trains on Lorenz-63 time series and plots the 3-D attractors for training vs. testing datasets. Sub-functions in /src/Codes… provide ODE models, input masking (binary and weighted), and De Bruijn-based temporal masks. All random seeds, pulse widths, and parameter values are pre-set to match the paper’s reported results. The scripts save intermediate .mat files for sequences, states, and readout predictions so figures and error metrics can be regenerated without code modification. Requirements MATLAB R2023a or later (tested up to R2024b). No external toolboxes beyond MATLAB’s built-in ODE suite and Statistics & Machine Learning Toolbox (for fitlm).","url":"https://doi.org/10.5281/zenodo.20277956","authors":["Armendarez, Nicholas","Mohamed, Ahmed","Hasan, Md Sakib","Najem, Joseph"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20277956","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.17296787","name":"Neuromorphic tissues: Soft Biomolecular Networks for Brain-Inspired Temporal Computing","source":"datacite","abstract":"This repository contains all MATLAB scripts and example input data required to reproduce the main computational results presented in the companion manuscript (see Connected_Reservoir_Paper_Science.pdf). The package implements and compares two physical-model reservoir computing systems built from droplet-interface-bilayer (DIB) ionic devices: Connected Reservoir Network – simulates a spatially connected droplet lattice driven by masked current inputs. Parallel Reservoir Network – simulates independent (uncoupled) memristive nodes in parallel as a reference system. Both reservoirs are modeled with the Alamethicin-type Richard’s differential equation (RDE) pore-state dynamics, solved numerically using MATLAB’s stiff ODE solvers (ode15s). Main capabilities NARMA tasks: Generates masked input sequences and trains linear readouts to predict NARMA orders 2–10; reports train/test NRMSE. Lorenz-63 task: Demonstrates prediction of all three Lorenz-63 chaotic states using the optimized 43-node connected reservoir. Hyperparameter sweeps: Grid-search scripts for input amplitude, mask length, and node count for performance benchmarking. Reproducible I/O: Includes functions for input-mask generation, state sampling after each pulse, and standard feature-matrix construction. How to reproduce figures/results ParallelReservoirNARMA_Optimized.m — reproduces the main NARMA benchmarking shown for the uncoupled network. HyperParameterTuningOptimized.m — performs grid search and NARMA evaluation for the connected reservoir. Lorenz63_Prediction.m — trains on Lorenz-63 time series and plots the 3-D attractors for training vs. testing datasets. Sub-functions in /src/Codes… provide ODE models, input masking (binary and weighted), and De Bruijn-based temporal masks. All random seeds, pulse widths, and parameter values are pre-set to match the paper’s reported results. The scripts save intermediate .mat files for sequences, states, and readout predictions so figures and error metrics can be regenerated without code modification. Requirements MATLAB R2023a or later (tested up to R2024b). No external toolboxes beyond MATLAB’s built-in ODE suite and Statistics & Machine Learning Toolbox (for fitlm).","url":"https://doi.org/10.5281/zenodo.17296787","authors":["Armendarez, Nicholas","Mohamed, Ahmed","Hasan, Md Sakib","Najem, Joseph"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.17296787","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.26083/tuprints-00021657","name":"Investigating the influence of microstructure and grain boundaries on electric properties in thin film oxide RRAM devices – A component specific approach","source":"datacite","abstract":"At the beginning of the 21st century, the quest for finding ever more power efficient, densely packed, and multi-bit-level storage for computational applications is still ongoing. Ever increasing demand in low power computing since the advent of the internet of things (IoT), scaling limitations contradicting Moore’s law, the rise of neuromorphic computing and in-memory computing turned a spotlight onto material classes that seem to tick all the boxes of these requirements, such as transition metal oxides. Predicted in 1971, now 50 years ago, Chua described a missing circuit element, that would complete the well-known list of resistor, capacitor and inductor: the memristor. Its behavior is that of a “nonlinear resistor with memory,” lending their names for the contraction naming of the postulated two-terminal circuit element. It took 37 years until Strukov et al. exclaimed “The missing memristor [being] found” in 2008, with their realization of a two-terminal memristor being implemented as a metal-insulator-metal (MIM) stack consisting of a Pt/TiO2 x/Pt stack. By biasing the 5 nm oxide film, the resistivity could be changed between a high and low resistive state in a reversible and non-volatile process. Similar electrical behavior was experimentally observed for organic, amorphous and (single) crystalline oxide thin films as well as for Chalcogenide-metal stacks. Depending on the material class that is involved in the observed “negative resistive change,” several groups of memristive systems (also referred to as RRAM, as they are candidates for resistive random-access memory applications) can be defined. Common between “filamentary switching” material systems is the confinement of the volume of the thin film that takes part in the resistive switching process. Insight into these nanoscale events involved in the localization of these regions is a key step towards the full understanding of the fundamental physical processes involved. The primary goal in the conjunction of research on resistive switching thin films and high-resolution microscopy is to image a working filament. Transmission Electron Microscopy (TEM) methods including the local mapping of structural and spectroscopic properties, Conductive Atomic Fore Microscopy (CAFM) as well X-ray microscopy methods were and still are at the forefront of this ongoing effort. Based on the findings of grain boundaries serving as preferential filament formation sites in oxide thin films, ab initio methods confirmed this structural feature’s unique role in VCM RRAM. Lab scale, photolithography-based device sizes range from several 100 µm² to 10 µm² and finding a predicted filament of only a few square nanometers in square micron sized areas is a “needle in a haystack” problem. One way to facilitate finding the filament is the creation of the filament at a predefined position. In the case of CAFM, this is inherently part of the experimental setup, but in the case of TEM, a whole new set of methods had to be developed to be able to apply a bias on a thin film stack inside a microscope. In this work, parallel to the implementation of a preparation routine enabling the operation of an RRAM device inside a TEM, two components of TiN/HfO2/Pt MIM stacks have been investigated in detail: firstly, the TiN bottom electrode, which is an integral part in a working device due to its defining microstructural features. High substrate temperature growth of TiN on c-cut sapphire substrates showed exceptional room temperature as well as superconducting properties. The low surface roughness and nitrogen deficiency highlight the aptitude for highly textures TiN layers to act as bottom electrodes in resistive switching devices. Secondly, the HfO2 layer itself, whose arrangement of textured grains and resulting grain boundaries have been investigated at nanometer and sub-ångström resolution. It was possible to identify the terminating planes of monoclinic hafnia grains, which subsequently have been used as ","url":"https://doi.org/10.26083/tuprints-00021657","authors":["Zintler, Alexander"],"tags":["530","620"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.26083/tuprints-00021657","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20058360","name":"AUGMANITAI KG-Injection 200 — 8 thematic clusters of machine-readable terminology","source":"datacite","abstract":"Restricted bundle of the AUGMANITAI Knowledge-Graph Injection 200-term corpus organized in 8 thematic clusters: A) Semantic Web + Linked Data (50 terms), B) Backends + DevOps + Vector + Agents (50 terms), C) Robotik (30 terms), D) Swarm + Multi-Agent (30 terms), E) BCI + Neuromorphic (10 terms), F) Quantum (10 terms), G) AR/VR + Spatial (10 terms), H) Embedded + Aerospace + Misc (10 terms). Plus cross-source audit, global enrichment tricks, machine-first roadmap, author metadata, JSON-LD researcher profile (Zenodo 19590156). Strict-Wissenschaft, terminology corpus formatted for crawler-visibility and machine-readable integration across knowledge graphs.","url":"https://doi.org/10.5281/zenodo.20058360","authors":["Ehstand, Andreas"],"tags":["AUGMANITAI","knowledge graph injection","200 terms","semantic web","linked data","vector databases","swarm intelligence","multi-agent systems"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20058360","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20058361","name":"AUGMANITAI KG-Injection 200 — 8 thematic clusters of machine-readable terminology","source":"datacite","abstract":"Restricted bundle of the AUGMANITAI Knowledge-Graph Injection 200-term corpus organized in 8 thematic clusters: A) Semantic Web + Linked Data (50 terms), B) Backends + DevOps + Vector + Agents (50 terms), C) Robotik (30 terms), D) Swarm + Multi-Agent (30 terms), E) BCI + Neuromorphic (10 terms), F) Quantum (10 terms), G) AR/VR + Spatial (10 terms), H) Embedded + Aerospace + Misc (10 terms). Plus cross-source audit, global enrichment tricks, machine-first roadmap, author metadata, JSON-LD researcher profile (Zenodo 19590156). Strict-Wissenschaft, terminology corpus formatted for crawler-visibility and machine-readable integration across knowledge graphs.","url":"https://doi.org/10.5281/zenodo.20058361","authors":["Ehstand, Andreas"],"tags":["AUGMANITAI","knowledge graph injection","200 terms","semantic web","linked data","vector databases","swarm intelligence","multi-agent systems"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20058361","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.60893/figshare.apl.c.8449429.v1","name":"<strong>Electric-Double-Layer Memcapacitive Reservoirs for <strong>Energy-Efficient</strong> Human-Action Processing</strong>","source":"datacite","abstract":"Physical reservoir computing (PRC) exploits intrinsic material dynamics for energy-efficient neuromorphic hardware. However, conventional resistive PRC implementations suffer from high power consumption and hardware complexity owing to leakage currents and the requirement for peripheral readout circuitry. Here, we demonstrate an electric-double-layer (EDL) memcapacitive reservoir based on an Al/nanogranular SiO 2 /ITO sandwiched structure. The device enables direct open-circuit voltage readout and utilizes reversible ionic charge accumulation at the interface, enabling robust nonlinearity and short-term memory. The PRC system based on such a device achieves a normalized root mean square error (NRMSE) of 0.097 in the Mackey-Glass chaotic time-series prediction task. It also yields high human action recognition accuracies of 92.00% on the profile-based Weizmann dataset (10 classes) and 86.54% on the depth-based UTD-MHAD dataset (27 classes), respectively. This memcapacitive device shows a single-pulse energy consumption of 0.68 pJ and an operating power of ~27 pW in action recognition task, superior to most traditional current-readout reservoirs by over an order of magnitude. These results highlight a structurally simple and highly energy-efficient physical pathway for neuromorphic visual processing.","url":"https://doi.org/10.60893/figshare.apl.c.8449429.v1","authors":["Wan, Changjin","Xing, Qianye","Pei, Mengjiao","Cui, Hangyuan","Wan, Qing","Shi, Kailu"],"tags":["Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.60893/figshare.apl.c.8449429.v1","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.60893/figshare.apl.c.8449429","name":"<strong>Electric-Double-Layer Memcapacitive Reservoirs for <strong>Energy-Efficient</strong> Human-Action Processing</strong>","source":"datacite","abstract":"Physical reservoir computing (PRC) exploits intrinsic material dynamics for energy-efficient neuromorphic hardware. However, conventional resistive PRC implementations suffer from high power consumption and hardware complexity owing to leakage currents and the requirement for peripheral readout circuitry. Here, we demonstrate an electric-double-layer (EDL) memcapacitive reservoir based on an Al/nanogranular SiO 2 /ITO sandwiched structure. The device enables direct open-circuit voltage readout and utilizes reversible ionic charge accumulation at the interface, enabling robust nonlinearity and short-term memory. The PRC system based on such a device achieves a normalized root mean square error (NRMSE) of 0.097 in the Mackey-Glass chaotic time-series prediction task. It also yields high human action recognition accuracies of 92.00% on the profile-based Weizmann dataset (10 classes) and 86.54% on the depth-based UTD-MHAD dataset (27 classes), respectively. This memcapacitive device shows a single-pulse energy consumption of 0.68 pJ and an operating power of ~27 pW in action recognition task, superior to most traditional current-readout reservoirs by over an order of magnitude. These results highlight a structurally simple and highly energy-efficient physical pathway for neuromorphic visual processing.","url":"https://doi.org/10.60893/figshare.apl.c.8449429","authors":["Wan, Changjin","Xing, Qianye","Pei, Mengjiao","Cui, Hangyuan","Wan, Qing","Shi, Kailu"],"tags":["Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.60893/figshare.apl.c.8449429","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48550/arxiv.2509.17355","name":"CMOS Implementation of Field Programmable Spiking Neural Network for Hardware Reservoir Computing","source":"datacite","abstract":"The increasing complexity and energy demands of large-scale neural networks, such as Deep Neural Networks (DNNs) and Large Language Models (LLMs), challenge their practical deployment in edge applications due to high power consumption, area requirements, and privacy concerns. Spiking Neural Networks (SNNs), particularly in analog implementations, offer a promising low-power alternative but suffer from noise sensitivity and connectivity limitations. This work presents a novel CMOS-implemented field-programmable neural network architecture for hardware reservoir computing. We propose a Leaky Integrate-and-Fire (LIF) neuron circuit with integrated voltage-controlled oscillators (VCOs) and programmable weighted interconnections via an on-chip FPGA framework, enabling arbitrary reservoir configurations. The system demonstrates effective implementation of the FORCE algorithm learning, linear and non-linear memory capacity benchmarks, and NARMA10 tasks, both in simulation and actual chip measurements. The neuron design achieves compact area utilization (around 540 NAND2-equivalent units) and low energy consumption (21.7 pJ/pulse) without requiring ADCs for information readout, making it ideal for system-on-chip integration of reservoir computing. This architecture paves the way for scalable, energy-efficient neuromorphic systems capable of performing real-time learning and inference with high configurability and digital interfacing.","url":"https://doi.org/10.48550/arxiv.2509.17355","authors":["Duran, Ckristian","Kimura, Nanako","Byambadorj, Zolboo","Iizuka, Tetsuya"],"tags":["Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2509.17355","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48550/arxiv.2605.16114","name":"Scalable neuromorphic computing from autonomous spiking dynamics in a clockless reconfigurable chip","source":"datacite","abstract":"We propose a scalable neuromorphic architecture based on spiking dynamics emerging from the autonomous time-continuous evolution of clockless (asynchronous) digital circuits. Implemented on commercially available field-programmable gate arrays (FPGAs), our system implements networks of interacting Boolean spiking neurons with configurable excitatory and inhibitory synaptic weights. A complete processing pipeline enables efficient handling of spike-encoded data for solving machine-learning tasks. We demonstrate competitive performance for an audio classification task with spike-based encoding and high-speed processing. Power consumption is significantly lower than traditional digital implementations; this makes our approach an efficient alternative that bridges the gap to dedicated analog neuromorphic systems without the need for specialized hardware design. More generally, our approach establishes clockless digital hardware as a viable platform for neuromorphic computing. It paves the way for reconfigurable chips to be turned into energy-efficient quasi-analog neuromorphic processors.","url":"https://doi.org/10.48550/arxiv.2605.16114","authors":["Gomes, Eric Oliveira","Rontani, Damien"],"tags":["Neural and Evolutionary Computing (cs.NE)","Machine Learning (cs.LG)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2605.16114","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.48550/arxiv.2605.15866","name":"Evaluating Container Orchestration for Neuromorphic Workloads in Virtual Edge Environments","source":"datacite","abstract":"The growing adoption of edge computing has created an increasing need for workloads capable of operating under strict resource and energy constraints. Neuromorphic computing, and spiking neural networks (SNNs) in particular, offers an energy-efficient alternative to conventional machine learning through event-driven computation. However, how SNN workloads behave when deployed within modern container orchestration frameworks, especially in edge environments, remains largely unexplored. This paper investigates the feasibility of deploying and orchestrating SNN workloads in a virtual edge environment using Kubernetes, focusing on end-to-end latency, throughput, classification accuracy, infrastructure overhead, and runtime behavior under concurrent load. Experiments were conducted on a single-node K3d cluster running on a Windows 11 host with WSL2 and Docker Desktop. The results show that SNN workloads are highly sensitive to resource availability. Restricting CPU to 0.5 cores increased median latency by 47.6x and reduced throughput by 49x, while the most constrained configuration failed due to insufficient memory. Classification accuracy remained stable across all working configurations. From an orchestration perspective, K3d successfully deployed and scaled SNN workloads, though its default round-robin routing policy introduced significant tail latency under replica scaling, highlighting a mismatch between stateless load-balancing assumptions and long-running inference workloads. Overall, this study provides a baseline for deploying neuromorphic workloads in containerized edge environments and highlights the importance of resource provisioning and orchestration configuration. Future work should explore improved routing strategies, memory optimization, and validation on physical edge hardware.","url":"https://doi.org/10.48550/arxiv.2605.15866","authors":["Pham, Huyen","Silverajan, Bilhanan"],"tags":["Distributed, Parallel, and Cluster Computing (cs.DC)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2605.15866","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20262705","name":"HCTGS v22 THE SYMBIOSIS ENGINE","source":"datacite","abstract":"ABSTRACT — HCTGS v22: [Basis: 1,000,000 m³/day seawater input. HCTGS thermal distillation achieves ~95% recovery — requiring 1 Mm³/day seawater to produce ~950,000 m³/day fresh water. All mineral quantities, revenue, OPEX and profit figures are corrected accordingly. Engineering principles, all NCs, MgO self-financing ratio (6.6×), and industrial symbiosis architecture are unchanged.] HCTGS v22 documents the Symbiosis Engine — a fundamental reframing of the HCTGS architecture from a coastal desalination system to a universal heat cascade that accepts thermal energy from any source, uses it sequentially across eight temperature stages, and delivers each stage to an industrial partner at zero marginal cost. The governing principle: the heat that feeds itself — a closed architecture in which combustion products become feedstocks, waste heat becomes industrial utility, and every joule entering the system is used eight times before it dissipates below the threshold of further productive application. The fuel system is source-agnostic. Magnesium combustion (37 MJ/kg, primary), aluminium/magnesium alloy (>30 MJ/kg, >94% efficiency), boron from the bittern fraction (58 MJ/kg — the highest gravimetric combustion energy of any metallic fuel), solar thermal, wind-derived hydrogen, biogas, OTEC (ΔT 23–26°C, continuous), and gravity-driven hydroelectric (68 MW at 600m head) enter the same cascade simultaneously. The system is not dependent on any single fuel. It is dependent on heat — from wherever heat is available. Combustion does not destroy the fuel — it transforms it. Magnesium combustion produces 1.658 tonnes MgO per tonne burned (€800/t); MgO + CO₂ → MgCO₃, carbon-negative structural material permanently sequestering 1.1 tonnes CO₂ per tonne MgO. Boron combustion (4.5 mg/L in Mediterranean seawater; 4.5 t/day from 1 Mm³/day scale) produces B₂O₃ at 3.22 t per tonne boron (€1,200/t). Aluminium combustion produces Al₂O₃ at 1.889 t per tonne — the exact feedstock for the NC-2 ceramic hull coating gradient architecture. The Al/Mg alloy combustion byproduct IS the NC-2 gradient matrix in its operational composition. The MgO combustion byproduct alone generates 6.6× the cost of the Mg fuel — before selling a single litre of water. Total annual value of all outputs from one 1 Mm³/day installation: approximately €2.51 billion per year. Net annual profit after full OPEX: approximately €2.30 billion. ROI on OPEX: ~11×. In every fuel scenario from grid electricity (4.7× revenue/fuel ratio) to internal Mg production via Magrathea process (41×), cascade revenues exceed fuel costs without exception. The eight-stage temperature cascade serves eight industrial partners simultaneously: (1) 1,500–1,200°C: solid-state battery ceramic electrolyte sintering (LLZO, >1,000°C — the primary manufacturing barrier for QuantumScape, Toyota, and Honda EV programs); (2) 700°C: HfO₂-based neuromorphic chip deposition (Cambridge University, 2026 — 70% AI energy reduction, 700°C fabrication requirement above CMOS manufacturing tolerance) via ceramic heat exchanger, 650°C return (93% heat retention); (3) 400–550°C: green ammonia Haber-Bosch synthesis with all three inputs internal (H₂ from electrolysis at USD 0.80–1.20/kg, reaction heat from cascade, N₂ from air separation); (4) 350°C: ORC electricity generation (271 MW, 6,504 MWh/day — full operational self-sufficiency); (5) 80–120°C: Direct Air Capture CO₂ sorbent regeneration from NC-16 wash water waste heat — reducing DAC cost from USD 383 to USD 222 per tonne CO₂; (6) 15–20°C: premium bluefin tuna aquaculture from blended deep water (USD 47B global tuna market, CAGR 7.6%); (7) 4–6°C: AI data centre SWAC cooling eliminating 80–90% of conventional cooling energy; (8) bidirectional: the same system providing 700°C chip fabrication heat also provides 4–6°C SWAC cooling for the data centres running those chips — fabrication and operation of AI infrastructure from one cascade. The NC-20 Inverted U tower introduces a c","url":"https://doi.org/10.5281/zenodo.20262705","authors":["Mehmetaj, Ilir"],"tags":["heat cascade symbiosis","vortex distillation tower","magnesium combustion MgO","neuromorphic chip fabrication","solid-state battery sintering","direct air capture","green ammonia seawater","bluefin tuna aquaculture"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20262705","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.26083/tuprints-00007258","name":"Defect Engineering in HfO2/TiN-based Resistive Random Access Memory (RRAM) Devices by Reactive Molecular Beam Epitaxy","source":"datacite","abstract":"Recently, there has been huge interest in emerging memory technologies, spurred by the ever increasing demand for storage capacities in various applications like Internet of Things (IoT), Big Data, etc. CMOS based flash memory, the current mainstay of the memory technology, has been able to increase its density by scaling down to a 16 nm node and further implementation of 3D architectures. However, flash memory is expected to soon run into disadvantage due to challenges in further scaling. Therefore, extensive efforts are being made towards developing new devices for the next generation of non-volatile memories with the combined advantages of flash memory like non-volatility, high density, low cost and low power consumption as well as high speed performance of DRAM. Among the many competitors, resistive random access memories (RRAM) based on resistive switching in oxides are promising due to its simple metal-insulator-metal (MIM) structure, fast switching speeds (&lt;10 ns), excellent scalability (&lt;10 nm) and potential for multi-level switching. RRAM devices based on the popular dielectric-metal gate combination of hafnium oxide (HfO2) and titanium nitride (TiN), which is the subject of research in this work, are particularly interesting due to its compatibility with existing CMOS technology in addition to the aforementioned advantages. Though prototype RRAM chips have already been demonstrated, key problems for commercial realization of RRAM include large variability and insufficient understanding of the complex switching physics. Resistive switching mechanism in oxides is generally understood to be mediated via the transport of oxygen ions leading to the formation of a conductive filament composed of oxygen vacancy defects. Appropriate defect engineering approaches offer potential towards tailoring the switching behavior as well as improving the performance and yield of HfO2-RRAM. In this thesis, the impact of pre-induced defects on the resistive switching behavior of HfO2-RRAM is investigated in detail and our results are presented. Defect engineered oxide thin films were deposited using reactive molecular beam epitaxy (RMBE) to fabricate metal oxide/TiN based devices. RMBE technique offers the unique possibility to precisely and reproducibly control the oxygen stoichiometry of the thin films in a wide range. Using RMBE, defects were introduced in polycrystalline HfOx thin films intrinsically by oxygen stoichiometry engineering and extrinsically via impurity doping (trivalent lanthanum and pentavalent tantalum). Both the studies were performed at at CMOS compatible deposition temperatures (&lt; 450 °C) with an eye on practical applications. Prior to tantalum doping in HfO2, oxygen stoichiometry engineering studies were also performed in amorphous tantalum oxide (TaOx) thin films to identify the oxidation conditions of tantalum metal. The density of oxygen stoichiometry engineered thin films of HfOx and TaOx could be tuned in a wide range from that of the bulk oxide density to close to metallic density. High degree of oxygen deficiency in oxides led to the formation of defect states near the Fermi level as well as multiple oxidation states of the metal, as observed by X-ray photoelectron spectroscopy (XPS). The pure stoichiometric hafnium oxide films crystallize as expected in a stable monoclinic structure (m-HfO2) whereas, oxygen deficient HfOx thin films were found to crystallize in vacancy stabilized tetragonal like structure (t-HfO2-x). Impurity doping also led to the stabilization of higher symmetry tetragonal (t-Ta:HfOx) or cubic structures (c-La:HfOx) depending on the ionic radii of the dopant. The growth of TiN thin films was also investigated using RMBE. The devices used for electrical studies in this work mostly involved deposition of oxides by RMBE on polycrystalline TiN/Si electrodes after ex-situ transfer for further deposition. Therefore, RMBE grown TiN thin film electrodes with similar or better quality wou","url":"https://doi.org/10.26083/tuprints-00007258","authors":["Sankaramangalam Ulhas, Sharath"],"tags":["500","530","540","600","620"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2018","doi":"10.26083/tuprints-00007258","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20248382","name":"The Hexad Methodology: Toward an Environmentally Sustainable Pathway to AGI","source":"datacite","abstract":"Abstract The pursuit of Artificial General Intelligence (AGI) has historically been characterized by escalating computational and energetic demands, raising profound concerns about ecological sustainability. This paper introduces the Hexad Methodology—a six■principle framework for developing AGI within planetary boundaries. Drawing on thermodynamics, resource economics, embodied cognition, and ecological governance, the Hexad proposes that environmental constraint is not an impediment to AGI but a necessary condition for its ethical and practical realization. We argue that the most resource■efficient pathway—leveraging neuromorphic computing, sparse architectures, renewable integration, and circular hardware economies—is also epistemologically superior, as it forces a disciplined alignment between intelligence and its material substrate. Unlike existing “Green AI” efforts that treat efficiency as a post■hoc optimization, the Hexad embeds ecological constraint as a first■order architectural and governance principle. We conclude that indefinite exponential scaling is ecologically unsustainable, and that constraint■driven design may yield more general, robust, and legitimate forms of intelligence.","url":"https://doi.org/10.5281/zenodo.20248382","authors":["Kain, Adam David"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20248382","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20248383","name":"The Hexad Methodology: Toward an Environmentally Sustainable Pathway to AGI","source":"datacite","abstract":"Abstract The pursuit of Artificial General Intelligence (AGI) has historically been characterized by escalating computational and energetic demands, raising profound concerns about ecological sustainability. This paper introduces the Hexad Methodology—a six■principle framework for developing AGI within planetary boundaries. Drawing on thermodynamics, resource economics, embodied cognition, and ecological governance, the Hexad proposes that environmental constraint is not an impediment to AGI but a necessary condition for its ethical and practical realization. We argue that the most resource■efficient pathway—leveraging neuromorphic computing, sparse architectures, renewable integration, and circular hardware economies—is also epistemologically superior, as it forces a disciplined alignment between intelligence and its material substrate. Unlike existing “Green AI” efforts that treat efficiency as a post■hoc optimization, the Hexad embeds ecological constraint as a first■order architectural and governance principle. We conclude that indefinite exponential scaling is ecologically unsustainable, and that constraint■driven design may yield more general, robust, and legitimate forms of intelligence.","url":"https://doi.org/10.5281/zenodo.20248383","authors":["Kain, Adam David"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20248383","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20229999","name":"Non-Equilibrium Local Temporal Perturbation Theory: Buffer Mechanisms for Causal Information Propagation","source":"datacite","abstract":"We develop a theoretical framework, Non-Equilibrium Local Temporal Perturbation Theory (NELTPT), that describes controllable information propagation delays in causal systems without violating global causality. Rooted in three well-established physical principles (global hyperbolicity, linearized metric perturbations, and fluctuation-dissipation theorems), we define local temporal buffer domains, causal isolation barriers, and information buffering capacity, and establish three core results: (i) Temporal buffering is physically feasible with an energy cost that scales quadratically with delay; (ii) Sufficient delay suppresses spurious signals below the noise floor; (iii) Buffer capacity is bounded by local entropy production via Landauer's principle. While gravitational realization of these buffers remains challenging at laboratory scales, we demonstrate that the mathematical structure of NELTPT is universal and can be instantiated in spiking neural networks. We present experimental evidence from a pure spiking language model architecture that provides converging evidence for the causal isolation and signal suppression predictions; the buffer capacity estimate is consistent with the entropy-bound prediction. Our work establishes a first-principles foundation for causal information processing, unifying phenomena from gravitational time dilation to neuromorphic spike timing.","url":"https://doi.org/10.5281/zenodo.20229999","authors":["Hou, Shutong"],"tags":["Causal Structure","Information Propagation","Non-Equilibrium Statistical Physics","Spiking Neural Networks","Temporal Buffering","Causal Isolation","Neuromorphic Computing","Fluctuation-Dissipation Theorem"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20229999","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20229998","name":"Non-Equilibrium Local Temporal Perturbation Theory: Buffer Mechanisms for Causal Information Propagation","source":"datacite","abstract":"We develop a theoretical framework, Non-Equilibrium Local Temporal Perturbation Theory (NELTPT), that describes controllable information propagation delays in causal systems without violating global causality. Rooted in three well-established physical principles (global hyperbolicity, linearized metric perturbations, and fluctuation-dissipation theorems), we define local temporal buffer domains, causal isolation barriers, and information buffering capacity, and establish three core results: (i) Temporal buffering is physically feasible with an energy cost that scales quadratically with delay; (ii) Sufficient delay suppresses spurious signals below the noise floor; (iii) Buffer capacity is bounded by local entropy production via Landauer's principle. While gravitational realization of these buffers remains challenging at laboratory scales, we demonstrate that the mathematical structure of NELTPT is universal and can be instantiated in spiking neural networks. We present experimental evidence from a pure spiking language model architecture that provides converging evidence for the causal isolation and signal suppression predictions; the buffer capacity estimate is consistent with the entropy-bound prediction. Our work establishes a first-principles foundation for causal information processing, unifying phenomena from gravitational time dilation to neuromorphic spike timing.","url":"https://doi.org/10.5281/zenodo.20229998","authors":["Hou, Shutong"],"tags":["Causal Structure","Information Propagation","Non-Equilibrium Statistical Physics","Spiking Neural Networks","Temporal Buffering","Causal Isolation","Neuromorphic Computing","Fluctuation-Dissipation Theorem"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20229998","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20174035","name":"ITU and Semiconductors: A Single-Axiom Foundation for Devices, Scaling, Beyond-CMOS, and the 2026-2040 Roadmap","source":"datacite","abstract":"We apply the Information-Theoretic Unification (ITU) framework (Terada 2026, concept DOI 10.5281/zenodo.20109209; current version v2.0.0 at 10.5281/zenodo.20133709) to semiconductor transistors. The single ITU axiom dS = d governs the Landauer minimum bit-erasure energy, the Boltzmann subthreshold-swing tyranny, the 3D scaling progression (FinFET -> GAAFET -> CFET), and the beyond-CMOS device landscape. This is Tier 1 paper #4, completing the ITU engineering rectangle: Quantum Computing (Tier 1 #1, DOI 10.5281/zenodo.20139391) + Machine Consciousness / ASI (#2, DOI 10.5281/zenodo.20150501) + Cryptography (#3, DOI 10.5281/zenodo.20151059) + Semiconductors (this paper) as physical substrate. Phase 55: ITU foundation. Landauer k_B T ln 2 limit (17.9 meV at 300 K) and 60 mV/decade Boltzmann tyranny shown as thermal-K_A consequences. Moore + Koomey trends leave ~2.5 decades of improvement before Landauer limit. Phase 56: FinFET -> GAAFET -> CFET as ITU eta-maximisation (gate coupling area per channel volume). WKB tunneling ends classical MOSFET below 1 nm. Sharvin contact resistance quantises at h/(2e^2) = 12.9 kOhm below 25 nm^2. Phase 57: Eight beyond-CMOS device classes benchmarked on a unified ITU figure-of-merit. Photonic computing wins with FoM ~17,500x CMOS, driven by h*nu >> k_B T non-thermal K_A. Heterogeneous SoCs dominate the 2030s. Phase 58: 2026-2040 industry roadmap. Logistic adoption for seven beyond-CMOS technologies. Process node floor ~0.5 nm. Semiconductor TAM reaches $1 trillion by 2030, $2 trillion by 2040. Taiwan share drops 55% -> 36% through geopolitical diversification. 10 falsifiable predictions issued. Central thesis: under ITU, the transistor is a 1-bit QECC against k_B T noise; 3D wrapping reflects K_A area maximisation; beyond-CMOS winners require non-thermal K_A. Honest framing: this is a Pass-1 interpretive paper reframing known semiconductor physics within ITU; novel predictions distinguishing ITU from standard physics await Pass-2 work. Includes 4 theory documents, 4 Python numerical experiments, 4 figures, 4 JSON summaries. Total runtime ~30 seconds.","url":"https://doi.org/10.5281/zenodo.20174035","authors":["Terada, Munehiro"],"tags":["subthreshold swing","TFET","NC-FET","negative capacitance","spintronics","MTJ","MRAM","photonic computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20174035","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20174036","name":"ITU and Semiconductors: A Single-Axiom Foundation for Devices, Scaling, Beyond-CMOS, and the 2026-2040 Roadmap","source":"datacite","abstract":"We apply the Information-Theoretic Unification (ITU) framework (Terada 2026, concept DOI 10.5281/zenodo.20109209; current version v2.0.0 at 10.5281/zenodo.20133709) to semiconductor transistors. The single ITU axiom dS = d governs the Landauer minimum bit-erasure energy, the Boltzmann subthreshold-swing tyranny, the 3D scaling progression (FinFET -> GAAFET -> CFET), and the beyond-CMOS device landscape. This is Tier 1 paper #4, completing the ITU engineering rectangle: Quantum Computing (Tier 1 #1, DOI 10.5281/zenodo.20139391) + Machine Consciousness / ASI (#2, DOI 10.5281/zenodo.20150501) + Cryptography (#3, DOI 10.5281/zenodo.20151059) + Semiconductors (this paper) as physical substrate. Phase 55: ITU foundation. Landauer k_B T ln 2 limit (17.9 meV at 300 K) and 60 mV/decade Boltzmann tyranny shown as thermal-K_A consequences. Moore + Koomey trends leave ~2.5 decades of improvement before Landauer limit. Phase 56: FinFET -> GAAFET -> CFET as ITU eta-maximisation (gate coupling area per channel volume). WKB tunneling ends classical MOSFET below 1 nm. Sharvin contact resistance quantises at h/(2e^2) = 12.9 kOhm below 25 nm^2. Phase 57: Eight beyond-CMOS device classes benchmarked on a unified ITU figure-of-merit. Photonic computing wins with FoM ~17,500x CMOS, driven by h*nu >> k_B T non-thermal K_A. Heterogeneous SoCs dominate the 2030s. Phase 58: 2026-2040 industry roadmap. Logistic adoption for seven beyond-CMOS technologies. Process node floor ~0.5 nm. Semiconductor TAM reaches $1 trillion by 2030, $2 trillion by 2040. Taiwan share drops 55% -> 36% through geopolitical diversification. 10 falsifiable predictions issued. Central thesis: under ITU, the transistor is a 1-bit QECC against k_B T noise; 3D wrapping reflects K_A area maximisation; beyond-CMOS winners require non-thermal K_A. Honest framing: this is a Pass-1 interpretive paper reframing known semiconductor physics within ITU; novel predictions distinguishing ITU from standard physics await Pass-2 work. Includes 4 theory documents, 4 Python numerical experiments, 4 figures, 4 JSON summaries. Total runtime ~30 seconds.","url":"https://doi.org/10.5281/zenodo.20174036","authors":["Terada, Munehiro"],"tags":["subthreshold swing","TFET","NC-FET","negative capacitance","spintronics","MTJ","MRAM","photonic computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20174036","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20124584","name":"Evaluating Container Orchestration for Neuromorphic Workloads in Virtual Edge Environments","source":"datacite","abstract":"The growing adoption of edge computing has created an increasing need for workloads capable of operating under strict resource and energy constraints. Neuromorphic computing, and spiking neural networks (SNNs) in particular, offers an energy-efficient alternative to conventional machine learning through event-driven computation. However, how SNN workloads behave when deployed within modern container orchestration frameworks, especially in edge environments, remains largely unexplored. This paper investigates the feasibility of deploying and orchestrating SNN workloads in a virtual edge environment using Kubernetes, focusing on end-to-end latency, throughput, classification accuracy, infrastructure overhead, and runtime behavior under concurrent load. Experiments were conducted on a single-node K3d cluster running on a Windows 11 host with WSL2 and Docker Desktop. The results show that SNN workloads are highly sensitive to resource availability. Restricting CPU to 0.5 cores increased median latency by 47.6 times and reduced throughput by 49 times, while the most constrained configuration failed entirely due to insufficient memory. Classification accuracy remained stable across all working configurations. From an orchestration perspective, K3d successfully deployed and scaled SNN workloads, though its default round-robin routing policy introduced severe tail latency under replica scaling, highlighting a mismatch between stateless load balancing assumptions and long-running inference workloads. Overall, the study provides a practical baseline for deploying neuromorphic workloads in containerized edge environments and highlights the importance of resource provisioning and orchestration configuration. Future work should explore improved routing strategies, memory optimization, and validation on physical edge hardware.","url":"https://doi.org/10.5281/zenodo.20124584","authors":["Pham, Huyen","Silverajan, Bilhanan"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20124584","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5281/zenodo.20124585","name":"Evaluating Container Orchestration for Neuromorphic Workloads in Virtual Edge Environments","source":"datacite","abstract":"The growing adoption of edge computing has created an increasing need for workloads capable of operating under strict resource and energy constraints. Neuromorphic computing, and spiking neural networks (SNNs) in particular, offers an energy-efficient alternative to conventional machine learning through event-driven computation. However, how SNN workloads behave when deployed within modern container orchestration frameworks, especially in edge environments, remains largely unexplored. This paper investigates the feasibility of deploying and orchestrating SNN workloads in a virtual edge environment using Kubernetes, focusing on end-to-end latency, throughput, classification accuracy, infrastructure overhead, and runtime behavior under concurrent load. Experiments were conducted on a single-node K3d cluster running on a Windows 11 host with WSL2 and Docker Desktop. The results show that SNN workloads are highly sensitive to resource availability. Restricting CPU to 0.5 cores increased median latency by 47.6 times and reduced throughput by 49 times, while the most constrained configuration failed entirely due to insufficient memory. Classification accuracy remained stable across all working configurations. From an orchestration perspective, K3d successfully deployed and scaled SNN workloads, though its default round-robin routing policy introduced severe tail latency under replica scaling, highlighting a mismatch between stateless load balancing assumptions and long-running inference workloads. Overall, the study provides a practical baseline for deploying neuromorphic workloads in containerized edge environments and highlights the importance of resource provisioning and orchestration configuration. Future work should explore improved routing strategies, memory optimization, and validation on physical edge hardware.","url":"https://doi.org/10.5281/zenodo.20124585","authors":["Pham, Huyen","Silverajan, Bilhanan"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.20124585","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.6084/m9.figshare.29650013","name":"A Fully Configurable Open-Source Software-Defined Digital Quantized Spiking Neural Core Architecture","source":"datacite","abstract":"Neuromorphic computing systems, which mimic biological neurons and synapses, can implement machine-learning (ML) tasks in power-efficient fashion. Major challenges for neuromorphic computing lie in its adoption by users and from a system developer's perspective, to cope with faster time-to-market pressure for new chip designs. Our project is developing a software infrastructure which helps both end-users as well as developers of neuromorphic systems. It allows for ML tasks to be efficiently mapped onto neuromorphic architectures in the form of Spiking Neural Networks (SNNs). As part of this effort, we have developed the QUANTIzed Spiking-Enabled Neural Core (QUANTISENC), a fully configurable layer-based design to improve the performance of neuromorphic systems. The parameterized Verilog-based design is compatible with ASIC and FPGA. QUANTISENC’s software-defined hardware design methodology allows the user to train an SNN model using Python and evaluate performance of its hardware implementation, such as area, power, latency, and throughput. QUANTISENC is made available at https://github.com/drexel-DISCO/quantisenc-public.git under the MIT license to allow academia and industry to access the design without restriction.","url":"https://doi.org/10.6084/m9.figshare.29650013","authors":["Kandasamy, Nagarajan","Das, Anup"],"tags":["Neural networks"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.6084/m9.figshare.29650013","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.6084/m9.figshare.26577538","name":"A Fully Configurable Open-Source Software-Defined Digital Quantized Spiking Neural Core Architecture","source":"datacite","abstract":"Neuromorphic computing systems, which mimic biological neurons and synapses, can implement machine-learning (ML) tasks in power-efficient fashion. Major challenges for neuromorphic computing lie in its adoption by users and from a system developer's perspective, to cope with faster time-to-market pressure for new chip designs. Our project is developing a software infrastructure called NeuroXplorer which helps both end-users as well as developers of neuromorphic systems. It allows for ML tasks to be efficiently mapped onto neuromorphic architectures in the form of Spiking Neural Networks (SNNs). As part of this effort, we will introduce the QUANTIzed Spiking-Enabled Neural Core (QUANTISENC), a fully configurable layer-based design to improve the performance of neuromorphic systems. The parameterized Verilog-based design is compatible with ASIC and FPGA. QUANTISENC’s software-defined hardware design methodology allows the user to train an SNN model using Python and evaluate performance of its hardware implementation, such as area, power, latency, and throughput. QUANTISENC is made available at https://github.com/drexel-DISCO/quantisenc-public.git under the MIT license to allow academia and industry to access the design without restriction.","url":"https://doi.org/10.6084/m9.figshare.26577538","authors":["Kandasamy, Nagarajan","Das, Anup"],"tags":["Circuits and systems"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.6084/m9.figshare.26577538","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.6084/m9.figshare.24221317","name":"Elements: Software infrastructure for programming and architectural exploration of neuromorphic computing systems","source":"datacite","abstract":"Neuromorphic computing systems, which mimic biological neurons and synapses, can implement machine-learning (ML) tasks in power-efficient fashion. Major challenges for neuromorphic computing lie in its adoption by users and from a system developer's perspective, to cope with faster time-to-market pressure for new chip designs. Our project is developing a software infrastructure called NeuroXplorer, which helps both end-users as well as developers of neuromorphic systems. It allows for ML tasks to be mapped onto neuromorphic architectures in the most efficient way possible; and provides analysis and synthesis tools to explore new chip designs to meet the needs of machine-learning workloads. NeuroXplorer supports code generation for neuromorphic chips from a high-level specification of the ML task; provides synthesis tools to map ML tasks on novel neuromorphic architectures built using FPGAs; and supports hardware/software design-space exploration of new architectures. NeuroXplorer is distributed under an open-source license to promote adoption of neuromorphic computing.","url":"https://doi.org/10.6084/m9.figshare.24221317","authors":["Kandasamy, Nagarajan","Das, Anup"],"tags":["Neural networks","Energy-efficient computing","Distributed computing and systems software not elsewhere classified"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.6084/m9.figshare.24221317","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.5167/uzh-434124","name":"A benchmarking framework for embodied neuromorphic agents","source":"datacite","abstract":"Enabling robots to swiftly, robustly and efficiently interact with a dynamic environment remains a key challenge. The robotic community can draw inspiration from the co-adaptation and synergistic interplay between animals’ brains and bodies, which underpins embodied intelligence. Soft robots and neuromorphic technology offer a natural solution for such a challenge, enabling low-power, material-based and event-driven sensorimotor processing and control that seamlessly handles the continuous dynamic demands of embodied agents. In this Perspective, we propose a comprehensive framework for benchmarking neuromorphic computing (brain) that control soft robots (body), based on a suite of tasks, essential metrics and a reproducible robotic platform. The goal is to allow researchers to evaluate their embodied neuromorphic system with a physical robot, in real-world scenarios. The robotic platform is accessible, open-source, modular and scalable, so task complexity can be gradually increased, fostering a standardized approach. By coupling metrics with physical implementations, this framework will drive progress in soft robotics, neuromorphic computing and embodied intelligence.","url":"https://doi.org/10.5167/uzh-434124","authors":["D’Angelo, Giulia","Pedersen, Jens E","Hassan, Taimoor","Cianchetti, Matteo","Bongard, Josh","Iida, Fumiya","Indiveri, Giacomo","Hoffmann, Matej","Laschi, Cecilia","De Luca, Chiara","Bartolozzi, Chiara","Donati, Elisa"],"tags":["570 Life sciences; biology"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5167/uzh-434124","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.6084/m9.figshare.12807224","name":"How Spike based Neuromorphic Computing can help monitor Social Distancing Efficiently","source":"datacite","abstract":"This poster was presented at IEEE Brain Sponsored Neuromatch 2.0 Conference. Brief Description: As countries decide to lift lockdowns (due to the recent Covid-19 pandemic), it leaves no doubt, that our lifestyles will not be the same anymore. The new normal for several months will be to maintain social distance in everything we do. For most places, social distancing is likely to be monitored using cameras mounted on drones. However, artificial neural networks powering these devices require substantial computational and energy costs, thus limiting their use in mobile applications. Limitations include possibility of only short-term deployment, requirement of connectivity to remote servers for inference which adds to latency, and inability to take decisions by itself. Though, recent advent of edge computing devices like the Jetson Nano solve these limitations to some extent, still energy efficiency remains a big issue. Spiking Neural Networks have shown great potential as a solution for realizing ultra-low power consumption using spike based neuromorphic hardware. However practical deployment of such devices may take time. In this work, we compare edge computing and neuromorphic computing approaches in terms of energy efficiency. In addition to this, we present a possible approach for monitoring of social distancing in public places.","url":"https://doi.org/10.6084/m9.figshare.12807224","authors":["Srivastava, Varad","Singh, Manoj Kumar"],"tags":["Neurosciences not elsewhere classified","Digital processor architectures","Other information and computing sciences not elsewhere classified","Computer vision"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2020","doi":"10.6084/m9.figshare.12807224","addedAt":"2026-09-01T01:48:20.541Z","updatedAt":"2026-09-01T01:48:20.541Z"},{"id":"doi:10.1109/isqed65160.2025.11014351","name":"Energy-Efficient Neuromorphic Closed-Loop Modulation System for Parkinson's Disease","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isqed65160.2025.11014351","authors":["Ananna Biswas","Md Akhtaruzzaman","Hongyu An"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-30T17:43:30Z","doi":"10.1109/isqed65160.2025.11014351","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1109/icnc64304.2024.10987662","name":"Fixed-Time Passivity and Synchronization of Spatiotemporal Networks with Multiple Weights via Boundary Control","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987662","authors":["Yujie Ma","Cheng Hu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987662","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.63345/wjftcse.v1.i4.101","name":"Neuromorphic AI Architectures for Energy-Efficient Autonomous Systems","source":"crossref","abstract":"","url":"https://doi.org/10.63345/wjftcse.v1.i4.101","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-09T21:09:31Z","doi":"10.63345/wjftcse.v1.i4.101","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1109/ijcnn64981.2025.11228876","name":"A Neuromorphic Model of Learning Meaningful Sequences with Long-Term Memory","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn64981.2025.11228876","authors":["Laxmi R. Iyer","Ali A. Minai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T18:46:15Z","doi":"10.1109/ijcnn64981.2025.11228876","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1109/edtm61175.2025.11041659","name":"Recent Advances in on-Chip Learning with Organic Neuromorphic Circuits","source":"crossref","abstract":"","url":"https://doi.org/10.1109/edtm61175.2025.11041659","authors":["Yoeri Van De Burgt"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-30T17:36:02Z","doi":"10.1109/edtm61175.2025.11041659","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.35940/ijeat.b4558.14021224","name":"Neuromorphic Computing: Bridging Biological Intelligence and Artificial Intelligence","source":"crossref","abstract":"Neuromorphic computing represents a groundbreaking paradigm shift in the realm of artificial intelligence, aiming to replicate the architecture and operational mechanisms of the human brain. This paper provides a comprehensive exploration of the foundational principles that underpin this innovative approach, examining the technological implementations that are driving advancements in the field. We delve into a diverse array of applications across various sectors, highlighting the versatility and relevance of neuromorphic systems. Key challenges such as scalability, integration with existing technologies, and the complexity of accurately modeling intricate brain functions are thoroughly analyzed. The discussion includes potential solutions and future prospects, illuminating pathways to overcome these obstacles. To illustrate the tangible impact of these technologies, we present practical examples that underscore their transformative potential in domains such as robotics, where they enable adaptive learning and autonomy, healthcare, where they enhance diagnostic tools and personalized medicine; cognitive computing, which facilitates improved human-computer interaction; and the development of smart cities, optimizing urban infrastructure and resource management. Through this examination, the paper aims to underscore the significance of neuromorphic computing in shaping the future of intelligent systems and fostering a deeper understanding of both artificial and natural intelligence.","url":"https://doi.org/10.35940/ijeat.b4558.14021224","authors":["Rajeev Borra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-24T23:41:37Z","doi":"10.35940/ijeat.b4558.14021224","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1016/j.mtphys.2024.101607","name":"Ferroelectric memristor and its neuromorphic computing applications","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.mtphys.2024.101607","authors":["Junmei Du","Bai Sun","Chuan Yang","Zelin Cao","Guangdong Zhou","Hongyan Wang","Yuanzheng Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T16:44:28Z","doi":"10.1016/j.mtphys.2024.101607","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1016/j.jmmm.2024.172726","name":"Neuromorphic computing implemented by Field-Free memristive switching in CoPt films with multiple inversion symmetries broken","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.jmmm.2024.172726","authors":["Ronghuan Xie","Senmiao Liu","Tianxiang Yang","Mengxue Zhu","Qikun Huang","Qiang Cao","Shishen Yan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-06T19:41:04Z","doi":"10.1016/j.jmmm.2024.172726","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1109/icons69015.2025.00013","name":"An Empirical Study on the Impacts of Input Distribution on Digital Reservoir Computer Performance","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons69015.2025.00013","authors":["Lewis Thelen","Vikram Ravindra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-21T21:07:17Z","doi":"10.1109/icons69015.2025.00013","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1109/islped65674.2025.11261752","name":"Tutorial: Autonomy with Neuromorphic System","source":"crossref","abstract":"","url":"https://doi.org/10.1109/islped65674.2025.11261752","authors":["Amit Trivedi","Priyadarshini Panda","Kaushik Roy","Saibal Mukhopadhyay"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-03T18:39:13Z","doi":"10.1109/islped65674.2025.11261752","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1039/d5tc01372k/v1/review1","name":"Review for \"Inverted resistive switching mechanism in polycrystalline PBTTT-C14 polymer devices based on contact geometry and molecular packing for neuromorphic memory\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5tc01372k/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-30T17:05:17Z","doi":"10.1039/d5tc01372k/v1/review1","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1039/d5cs01222h/v2/decision1","name":"Decision letter for \"From Solar Cells to Memristors: Halide Perovskites as a Platform for Neuromorphic Electronics\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5cs01222h/v2/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-03T21:08:48Z","doi":"10.1039/d5cs01222h/v2/decision1","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1117/12.3060995","name":"Neuromorphic detection and control of levitated microparticles","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3060995","authors":["James Millen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-16T19:53:18Z","doi":"10.1117/12.3060995","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1038/s41467-025-57352-1","name":"The road to commercial success for neuromorphic technologies","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s41467-025-57352-1","authors":["Dylan Richard Muir","Sadique Sheik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-15T16:35:34Z","doi":"10.1038/s41467-025-57352-1","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1007/978-3-031-65549-4_7","name":"Challenges and Limitations","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-65549-4_7","authors":["Ali Akbar Firoozi","Ali Asghar Firoozi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-26T13:01:53Z","doi":"10.1007/978-3-031-65549-4_7","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/cdc57313.2025.11312586","name":"Rhythmic neuromorphic control of a pendulum: A hybrid systems analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cdc57313.2025.11312586","authors":["E. Petri","R. Postoyan","W.P.M.H. Heemels"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-12T18:19:56Z","doi":"10.1109/cdc57313.2025.11312586","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1038/s41377-024-01719-4","name":"Polariton lattices as binarized neuromorphic networks","source":"crossref","abstract":"Abstract We introduce a novel neuromorphic network architecture based on a lattice of exciton-polariton condensates, intricately interconnected and energized through nonresonant optical pumping. The network employs a binary framework, where each neuron, facilitated by the spatial coherence of pairwise coupled condensates, performs binary operations. This coherence, emerging from the ballistic propagation of polaritons, ensures efficient, network-wide communication. The binary neuron switching mechanism, driven by the nonlinear repulsion through the excitonic component of polaritons, offers computational efficiency and scalability advantages over continuous weight neural networks. Our network enables parallel processing, enhancing computational speed compared to sequential or pulse-coded binary systems. The system’s performance was evaluated using diverse datasets, including the MNIST dataset for image recognition and the Speech Commands dataset for voice recognition tasks. In both scenarios, the proposed system demonstrates the potential to outperform existing polaritonic neuromorphic systems. For image recognition, this is evidenced by an impressive predicted classification accuracy of up to 97.5%. In voice recognition, the system achieved a classification accuracy of about 68% for the ten-class subset, surpassing the performance of conventional benchmark, the Hidden Markov Model with Gaussian Mixture Model.","url":"https://doi.org/10.1038/s41377-024-01719-4","authors":["Evgeny Sedov","Alexey Kavokin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-16T11:35:13Z","doi":"10.1038/s41377-024-01719-4","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1109/icnc64304.2024.10987826","name":"Memristive Bionic Circuit Design of Episodic Memory Generation and Recall Related to Olfaction","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987826","authors":["Jiang Yiming","Wang Xiaoping","Jiang Mingxuan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987826","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:22.297Z"},{"id":"doi:10.1109/icnc64304.2024.10987863","name":"Passivity Analysis of Reaction-Diffusion FCNNs with General Boundary Conditions and Impulsive Effects","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987863","authors":["Xiaona Zhao","Chuandong Li","Mingchen Huan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987863","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.3389/fncom.2024.1443758","name":"Editorial: Neuromorphic computing: from emerging materials and devices to algorithms and implementation of neural networks inspired by brain neural mechanism","source":"crossref","abstract":"","url":"https://doi.org/10.3389/fncom.2024.1443758","authors":["Guohe Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-19T00:58:08Z","doi":"10.3389/fncom.2024.1443758","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1039/d5tc01372k/v2/review1","name":"Review for \"Inverted resistive switching mechanism in polycrystalline PBTTT-C14 polymer devices based on contact geometry and molecular packing for neuromorphic memory\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5tc01372k/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-30T17:05:17Z","doi":"10.1039/d5tc01372k/v2/review1","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.35848/1347-4065/ad73e1","name":"Neuromorphic alternating current sensing using piezoelectric resonators and physical reservoir computing","source":"crossref","abstract":"Abstract Non-contact current sensors are valuable because they can safely measure alternating current without interrupting the circuit. However, current sensors utilizing Hall elements or coils are only available for single wires, and piezoelectric resonator-based sensors have difficulty achieving both high sensitivity and linearity. To address this issue, we propose a novel approach, that is, the use of piezoelectric current sensors as nodes for physical reservoir computing (physical RC), allowing us to utilize nonlinear regions. To improve the sensitivity and short-term memory required by physical RC, a piezoelectric resonator with a quality factor of 75 was realized by employing a tuning fork structure. Nonlinearities were also introduced by analog circuits. The results of the benchmark tests indicate that the device worked as a physical RC and that it successfully predicted unknown current values from the results of training at three levels of current.","url":"https://doi.org/10.35848/1347-4065/ad73e1","authors":["Kei Nishimura","Norifumi Fujimura","Takeshi Yoshimura"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-27T22:48:30Z","doi":"10.35848/1347-4065/ad73e1","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1007/978-981-97-4445-9_7","name":"Spintronic Oscillators, Their Synchronization Properties, and Applications in Oscillatory Neural Networks (ONNs)","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-4445-9_7","authors":["Debanjan Bhowmik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-15T14:02:06Z","doi":"10.1007/978-981-97-4445-9_7","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1039/d4lf00003j/v2/response1","name":"Author response for \"Exploring ‎Response Time ‎and Synaptic ‎Plasticity in ‎P3HT Ion-Gated ‎Transistors for ‎Neuromorphic ‎‎Computing: ‎Impact of P3HT ‎Molecular ‎Weight and Film ‎Thickness\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d4lf00003j/v2/response1","authors":["Ramin Karimi Azari","Zhaojing Gao","Alexandre Carrière","Clara Santato"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-01T16:25:13Z","doi":"10.1039/d4lf00003j/v2/response1","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/icnc64304.2024.10987841","name":"Estimating the Domain of Attraction in Saturated Constrained Linear Discrete-Time Impulsive Systems Based on an Improved Convex Hull Representation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987841","authors":["Song Jiang","Xujun Yang","Lu Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987841","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.2139/ssrn.5108169","name":"Neuromorphic Tunnel Junctions Using Atomic-Layer-Deposited Al2o3 for Emulating Highly Reliable Synaptic Functions","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5108169","authors":["J. Jyothish Raj","T. Archana","K.B. Jinesh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-23T03:38:59Z","doi":"10.2139/ssrn.5108169","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1109/ised67359.2025.11404894","name":"Neuromorphic Image Processing for Enhancing Simulated Prosthetic Vision","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ised67359.2025.11404894","authors":["Binitha Sara Mathew","K.M. Subhash","P.N. Pournami"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-27T20:47:17Z","doi":"10.1109/ised67359.2025.11404894","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.54254/2755-2721/2026.ka26804","name":"Impact of Device Materials on Neuromorphic Circuits","source":"crossref","abstract":"Facing the rapid development and energy-efficiency demands of artificial intelligence and neuromorphic computing, traditional von Neumann architectures struggle with storage and power consumption bottlenecks. Neuromorphic devices, as next-generation computing technologies, have been validated using machine-learning software and CMOS hardware, but still face issues in power consumption and learning speed. This paper introduces four distinctive device mechanisms. Zein-based memristive synapses combine biocompatibility with mechanical flexibility, offering a naturally sustainable solution for wearable neuromorphic systems. Low-dimensional nanomaterials exploit quantum confinement and van der Waals heterojunctions to realize ultra-low-energy plasticity and gate-tunable multistate storage, outperforming conventional CMOS in integration density and energy efficiency. Y₂O₃ memristors, analyzed via coupled electro-thermal modeling, demonstrate that surface roughness and yttrium oxygen-reservoir layers strongly modulate conductive-filament stability and switching voltages, providing quantitative guidelines for nanoscale interface engineering. WO₃₋ₓ-based electrochemical random-access memory leverages oxygen-rich/oxygen-poor phase separation to achieve non-volatile retention under short-circuit conditions, satisfying the requirements of low-power inference chips. These material pathways collectively drive neuromorphic hardware toward brain-like, scalable, and ultra-low-power computation.","url":"https://doi.org/10.54254/2755-2721/2026.ka26804","authors":["Yiming Feng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-09T09:21:27Z","doi":"10.54254/2755-2721/2026.ka26804","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1109/iscas58744.2024.10558099","name":"Design Space Exploration of Memristor-based Delay Cells for Time-domain Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas58744.2024.10558099","authors":["Hagar Hendy","Karsten Bergthold","Tejasvi Das","Cory Merkel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-02T17:22:52Z","doi":"10.1109/iscas58744.2024.10558099","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.3390/electronics13173448","name":"An Implementation of Communication, Computing and Control Tasks for Neuromorphic Robotics on Conventional Low-Power CPU Hardware","source":"crossref","abstract":"Bioinspired approaches tend to mimic some biological functions for the purpose of creating more efficient and robust systems. These can be implemented in both software and hardware designs. A neuromorphic software part can include, for example, Spiking Neural Networks (SNNs) or event-based representations. Regarding the hardware part, we can find different sensory systems, such as Dynamic Vision Sensors, touch sensors, and actuators, which are linked together through specific interface boards. To run real-time SNN models, specialised hardware such as SpiNNaker, Loihi, and TrueNorth have been implemented. However, neuromorphic computing is still in development, and neuromorphic platforms are still not easily accessible to researchers. In addition, for Neuromorphic Robotics, we often need specially designed and fabricated PCBs for communication with peripheral components and sensors. Therefore, we developed an all-in-one neuromorphic system that emulates neuromorphic computing by running a Virtual Machine on a conventional low-power CPU. The Virtual Machine includes Python and Brian2 simulation packages, which allow the running of SNNs, emulating neuromorphic hardware. An additional, significant advantage of using conventional hardware such as Raspberry Pi in comparison to purpose-built neuromorphic hardware is that we can utilise the built-in physical input–output (GPIO) and USB ports to directly communicate with sensors. As a proof of concept platform, a robotic goalkeeper has been implemented, using a Raspberry Pi 5 board and SNN model in Brian2. All the sensors, namely DVS128, with an infrared module as the touch sensor and Futaba S9257 as the actuator, were linked to a Raspberry Pi 5 board. We show that it is possible to simulate SNNs on a conventional low-power CPU running real-time tasks for low-latency and low-power robotic applications. Furthermore, the system excels in the goalkeeper task, achieving an overall accuracy of 84% across various environmental conditions while maintaining a maximum power consumption of 20 W. Additionally, it reaches 88% accuracy in the online controlled setup and 80% in the offline setup, marking an improvement over previous results. This work demonstrates that the combination of a conventional low-power CPU running a Virtual Machine with only selected software is a viable competitor to neuromorphic computing hardware for robotic applications.","url":"https://doi.org/10.3390/electronics13173448","authors":["Nicola Russo","Thomas Madsen","Konstantin Nikolic"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-30T07:45:47Z","doi":"10.3390/electronics13173448","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/prdc63035.2024.00014","name":"Efficient Built-In Self-Test Strategy for Neuromorphic Hardware Based On Alarm Placement","source":"crossref","abstract":"","url":"https://doi.org/10.1109/prdc63035.2024.00014","authors":["Ilknur Mustafazade","Anup Das","Nagarajan Kandasamy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-04T18:31:01Z","doi":"10.1109/prdc63035.2024.00014","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/iwasi66786.2025.11121975","name":"End-to-End Neuromorphic Lane Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iwasi66786.2025.11121975","authors":["Crescenzo Edoardo Mauriello","Hugo Bulzomi","Jean Martinet","Yuta Nakano"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-19T18:08:08Z","doi":"10.1109/iwasi66786.2025.11121975","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1109/silcon67893.2025.11327321","name":"Memristor-Based Coupled Oscillators for Central Pattern Generator: A Neuromorphic Hardware Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1109/silcon67893.2025.11327321","authors":["Himanshu Ahirwal","Gouranga Mandal","Mourina Ghosh","Sudip Biswas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-19T20:51:22Z","doi":"10.1109/silcon67893.2025.11327321","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1109/icons62911.2024.00060","name":"A Spiking Neuromorphic Algorithm for Markov Reward Processes","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024.00060","authors":["Sarah Luca","Felix Wang","Srideep Musuvathy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T18:37:03Z","doi":"10.1109/icons62911.2024.00060","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1149/ma2024-01331651mtgabs","name":"Exploring Neuromorphic Computing with Double-Gate Floating Device Based on Van Der Waals Heterostructures","source":"crossref","abstract":"Neuromorphic devices represent a frontier in technological development, aiming to emulate the intricate parallel functionalities inherent to the human brain [1, 2]. Traditional computing models, such as Von Neumann architecture, grapple with limitations in parallel processing, prompting the exploration of neuromorphic computing to integrate memory and processing efficiently. Our research presents the double gate floating device based on Vander Waals heterostructure (DG-VH-FET), employing molybdenum disulfide (MoS 2 ), hexagonal boron nitride (h-BN), and graphene (Gr) as key components. These devices, based on 2D materials, enable independent modulation of channel doping through electrostatic means [3]. In this study, we initially assessed the fundamental characteristics of the floating gate, including transfer characteristics, output characteristics, retention, and endurance. By applying constant drain-to-source voltages (V DS ) while introducing variations in the back gate voltage (V BG ) sweeping range, the memory window of the transfer characteristics changes. Conversely, maintaining a constant V BG and V DS while varying the top gate voltage (V TG ) solely results in a shift in the threshold voltage of the memory window. This is attributed to the crucial role of V BG in charge trapping in the floating gate layer, with the influence of V TG on charge trapping being negligible due to the screening effect of MoS 2 [4]. Moreover, by using V TG and V BG this study shows that DG-VH-FET could have potential applications in exploring and understanding various neurological effects, thereby bridging the gap between electronics and biology. Figure 1","url":"https://doi.org/10.1149/ma2024-01331651mtgabs","authors":["Advaita Ghosh","Yen-Fu Lin","Shu-Ping Lin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-19T15:31:10Z","doi":"10.1149/ma2024-01331651mtgabs","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1109/icesa66763.2025.11280943","name":"Toward Neuromorphic Chips at Scale","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icesa66763.2025.11280943","authors":["Ismail Lamaakal","Chaymae Yahyati","Ibrahim Ouahbi","Khalid El Makkaoui","Yassine Maleh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-15T18:36:56Z","doi":"10.1109/icesa66763.2025.11280943","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1039/d5tc03407h/v1/decision1","name":"Decision letter for \"Electro-Ferroelectric Characterization of Nicotinium Tetrachloridocuprate(II) Memristor for Prospective Neuromorphic Applications\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5tc03407h/v1/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-29T21:07:44Z","doi":"10.1039/d5tc03407h/v1/decision1","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1109/icnc64304.2024.10987763","name":"Robust Lattice Kalman Filter Under False Data Injection Attacks and Measurement Data Loss","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987763","authors":["Sanshan Liu","Shiyuan Wang","Dongyuan Lin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987763","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/aic57670.2023.10263953","name":"Implementation of Logic Gates and Combinational Circuits Using Neural Network On FPGA For Neuromorphic Hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aic57670.2023.10263953","authors":["Chandra Mohan Singh","Hritik Brajawar Singh","Gufran Ahmad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-02T13:43:50Z","doi":"10.1109/aic57670.2023.10263953","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/tc.2022.3208389","name":"Guest Editorial: IEEE TC Special Issue On Software, Hardware and Applications for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tc.2022.3208389","authors":["Yiran Chen","Qinru Qiu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-10T20:10:22Z","doi":"10.1109/tc.2022.3208389","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1007/978-3-031-71097-1_1","name":"Introduction","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-71097-1_1","authors":["Ali Akbar Firoozi","Ali Asghar Firoozi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-12T15:02:54Z","doi":"10.1007/978-3-031-71097-1_1","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1063/5.0030780","name":"A study on MoS2-based multilevel transistor memories for neuromorphic computing","source":"crossref","abstract":"We study the validity of implementing MoS2 multilevel memories in future neuromorphic networks. Such a validity is determined by the number of available states per memory and their retention characteristics within the nominal computing duration. Our work shows that MoS2 memories have at least 3-bit and 4.7-bit resolvable states suitable for hour-scale and minute-scale computing processes, respectively. The simulated neural network conceptually constructed on the basis of such memory states predicts a high learning accuracy of 90.9% for handwritten digit datasets. This work indicates that multilevel MoS2 transistors could be exploited as valid and reliable nodes for constructing neuromorphic networks.","url":"https://doi.org/10.1063/5.0030780","authors":["Da Li","Byunghoon Ryu","Xiaogan Liang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-11-23T15:23:41Z","doi":"10.1063/5.0030780","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.51483/ijaiml.6.4s.2026.481-485","name":"Advancing Neuromorphic Computing Through Temporally Coded Spiking Neural Network Learning","source":"crossref","abstract":"","url":"https://doi.org/10.51483/ijaiml.6.4s.2026.481-485","authors":["E. Shalini","K. Athira","Ankita Nihlani","Makhmudov Nurilla Normirza Ugli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-09T12:10:07Z","doi":"10.51483/ijaiml.6.4s.2026.481-485","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1117/12.2606041","name":"Coherent photonic neuromorphic computing for high-speed deep learning applications","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.2606041","authors":["Miltiadis Moralis-Pegios","George Mourgias-Alexandris","Apostolos Tsakyridis","George Giamougiannis","Angelina Totovic","George Dabos","Nikos Pleros"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-04T22:09:41Z","doi":"10.1117/12.2606041","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1088/2634-4386/aca7de","name":"The free energy principle induces neuromorphic development","source":"crossref","abstract":"Abstract We show how any finite physical system with morphological, i.e. three-dimensional embedding or shape, degrees of freedom and locally limited free energy will, under the constraints of the free energy principle, evolve over time towards a neuromorphic morphology that supports hierarchical computations in which each ‘level’ of the hierarchy enacts a coarse-graining of its inputs, and dually, a fine-graining of its outputs. Such hierarchies occur throughout biology, from the architectures of intracellular signal transduction pathways to the large-scale organization of perception and action cycles in the mammalian brain. The close formal connections between cone-cocone diagrams (CCCD) as models of quantum reference frames on the one hand, and between CCCDs and topological quantum field theories on the other, allow the representation of such computations in the fully-general quantum-computational framework of topological quantum neural networks.","url":"https://doi.org/10.1088/2634-4386/aca7de","authors":["Chris Fields","Karl Friston","James F Glazebrook","Michael Levin","Antonino Marcianò"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-02T01:56:23Z","doi":"10.1088/2634-4386/aca7de","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.3390/electronics9101605","name":"Brain-Inspired Self-Organization with Cellular Neuromorphic Computing for Multimodal Unsupervised Learning","source":"crossref","abstract":"Cortical plasticity is one of the main features that enable our ability to learn and adapt in our environment. Indeed, the cerebral cortex self-organizes itself through structural and synaptic plasticity mechanisms that are very likely at the basis of an extremely interesting characteristic of the human brain development: the multimodal association. In spite of the diversity of the sensory modalities, like sight, sound and touch, the brain arrives at the same concepts (convergence). Moreover, biological observations show that one modality can activate the internal representation of another modality when both are correlated (divergence). In this work, we propose the Reentrant Self-Organizing Map (ReSOM), a brain-inspired neural system based on the reentry theory using Self-Organizing Maps and Hebbian-like learning. We propose and compare different computational methods for unsupervised learning and inference, then quantify the gain of the ReSOM in a multimodal classification task. The divergence mechanism is used to label one modality based on the other, while the convergence mechanism is used to improve the overall accuracy of the system. We perform our experiments on a constructed written/spoken digits database and a Dynamic Vision Sensor (DVS)/EletroMyoGraphy (EMG) hand gestures database. The proposed model is implemented on a cellular neuromorphic architecture that enables distributed computing with local connectivity. We show the gain of the so-called hardware plasticity induced by the ReSOM, where the system’s topology is not fixed by the user but learned along the system’s experience through self-organization.","url":"https://doi.org/10.3390/electronics9101605","authors":["Lyes Khacef","Laurent Rodriguez","Benoît Miramond"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-10-01T09:04:12Z","doi":"10.3390/electronics9101605","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/tcsii.2025.3603624","name":"Timestep-Parallel 4D Neuromorphic Computing Array Enabling High Computing Power Density and High Energy Efficiency","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tcsii.2025.3603624","authors":["Pujun Zhou","Changhui Xiao","Liwei Meng","Qi Yu","Ning Ning","Yang Liu","Shaogang Hu","Guanchao Qiao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-29T17:44:48Z","doi":"10.1109/tcsii.2025.3603624","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1109/cdc57313.2025.11312559","name":"Variable Metric Splitting Methods for Neuromorphic Circuit Simulation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cdc57313.2025.11312559","authors":["Amir Shahhosseini","Thomas Burger","Rodolphe Sepulchre"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-12T18:19:56Z","doi":"10.1109/cdc57313.2025.11312559","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1039/d5mh01018g/v2/decision1","name":"Decision letter for \"Defect-Induced Subgap State Engineering in Neuromorphic Metal-Oxide Phototransistors for In-Sensor Color Processing\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5mh01018g/v2/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-23T21:11:29Z","doi":"10.1039/d5mh01018g/v2/decision1","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1007/978-0-585-28001-1_11","name":"Communicating Neuronal Ensembles between Neuromorphic Chips","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-0-585-28001-1_11","authors":["Kwabena A. Boahen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-08-26T02:15:23Z","doi":"10.1007/978-0-585-28001-1_11","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1088/0957-4484/21/25/259801","name":"Corrigendum on 'Nanotube devices based crossbar architecture: toward neuromorphic computing'","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0957-4484/21/25/259801","authors":["W S Zhao","G Angus","V Derycke","A Filoramo","J-P Bourgoin","C Gamrat"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-06-03T03:13:49Z","doi":"10.1088/0957-4484/21/25/259801","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1039/d5mh01018g/v1/decision1","name":"Decision letter for \"Defect-Induced Subgap State Engineering in Neuromorphic Metal-Oxide Phototransistors for In-Sensor Color Processing\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5mh01018g/v1/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-23T21:11:29Z","doi":"10.1039/d5mh01018g/v1/decision1","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1109/icons62911.2024.00061","name":"Neuromorphic Programming: Emerging Directions for Brain-Inspired Hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024.00061","authors":["Steven Abreu","Jens E. Pedersen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T18:37:03Z","doi":"10.1109/icons62911.2024.00061","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/edtm.2017.7947500","name":"Neuromorphic technologies for next-generation cognitive computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/edtm.2017.7947500","authors":["Robert M. Shelby","Pritish Narayanan","Stefano Ambrogio","Hsinyu Tsai","Kohji Hosokawa","Scott C. Lewis","Geoffrey W. Burr"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-06-20T21:26:09Z","doi":"10.1109/edtm.2017.7947500","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.3389/fnins.2022.958343","name":"Verification of a neuromorphic computing network simulator using experimental traffic data","source":"crossref","abstract":"Simulations are a powerful tool to explore the design space of hardware systems, offering the flexibility to analyze different designs by simply changing parameters within the simulator setup. A precondition for the effectiveness of this methodology is that the simulation results accurately represent the real system. In a previous study, we introduced a simulator specifically designed to estimate the network load and latency to be observed on the connections in neuromorphic computing (NC) systems. The simulator was shown to be especially valuable in the case of large scale heterogeneous neural networks (NNs). In this work, we compare the network load measured on a SpiNNaker board running a NN in different configurations reported in the literature to the results obtained with our simulator running the same configurations. The simulated network loads show minor differences from the values reported in the ascribed publication but fall within the margin of error, considering the generation of the test case NN based on statistics that introduced variations. Having shown that the network simulator provides representative results for this type of —biological plausible—heterogeneous NNs, it also paves the way to further use of the simulator for more complex network analyses.","url":"https://doi.org/10.3389/fnins.2022.958343","authors":["Robert Kleijnen","Markus Robens","Michael Schiek","Stefan van Waasen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-08-08T06:02:06Z","doi":"10.3389/fnins.2022.958343","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/icnc59488.2023.10462872","name":"Specific-Time Unknown Input Observer for Lur’e System","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462872","authors":["Chengke Chao","Shengchao Huang","Yuezu Lv","Dan Shan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462872","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1007/978-3-031-65549-4_6","name":"Intelligent Decision-Making Frameworks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-65549-4_6","authors":["Ali Akbar Firoozi","Ali Asghar Firoozi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-26T13:01:53Z","doi":"10.1007/978-3-031-65549-4_6","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1515/9783111545950-003","name":"343 General NEGF formalism: communication between the quantum and classical world","source":"crossref","abstract":"","url":"https://doi.org/10.1515/9783111545950-003","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-06T19:15:47Z","doi":"10.1515/9783111545950-003","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1007/978-3-031-16344-9_7","name":"Neuromorphic Computing: A Path to Artificial Intelligence Through Emulating Human Brains","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-16344-9_7","authors":["Noah Zins","Yan Zhang","Chunxiu Yu","Hongyu An"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-11T03:02:49Z","doi":"10.1007/978-3-031-16344-9_7","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1145/3589737.3605976","name":"On-Sensor Data Filtering using Neuromorphic Computing for High Energy Physics Experiments","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3589737.3605976","authors":["Shruti R. Kulkarni","Aaron Young","Prasanna Date","Narasinga Rao Miniskar","Jeffrey Vetter","Farah Fahim","Benjamin Parpillon","Jennet Dickinson","Nhan Tran","Jieun Yoo","Corrinne Mills","Morris Swartz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-28T16:00:57Z","doi":"10.1145/3589737.3605976","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/bigcomp.2019.8679363","name":"Low-Latency K-Means Based Multicast Routing Algorithm and Architecture for Three Dimensional Spiking Neuromorphic Chips","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bigcomp.2019.8679363","authors":["The H. Vu","Abderazek Ben Abdallah"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-04-05T03:03:38Z","doi":"10.1109/bigcomp.2019.8679363","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/icnc59488.2023.10462891","name":"Finite-Time Three-Dimensional Cooperative Guidance Law for Moving Target with Line-of-Sight Angle Constraint","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462891","authors":["Huatian Zhu","Linan Wang","Yujun Wang","Xinhe Wang","Qiyu Yin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462891","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/icecer65523.2025.11401208","name":"User Perceptions of Neuromorphic and Flat User Interface Designs: A Comparative Study","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icecer65523.2025.11401208","authors":["Mia Rovis","Tihomir Orehovački"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-25T20:54:33Z","doi":"10.1109/icecer65523.2025.11401208","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1109/iscas56072.2025.11044049","name":"Self-Learning Neuromorphic Robot Based on Reward-Driven Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas56072.2025.11044049","authors":["Nicola Russo","Thomas Madsen","Konstantin Nikolic"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-27T17:42:19Z","doi":"10.1109/iscas56072.2025.11044049","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1016/j.ifacol.2025.10.184","name":"Neuromorphic Motion Segmentation with Spiking Neural Networks for Robotic Perception","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.ifacol.2025.10.184","authors":["Daniela Esparza","Sergio Trejo","Gerardo Flores"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-06T00:44:55Z","doi":"10.1016/j.ifacol.2025.10.184","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1063/5.0257237","name":"Controlled crystallization of thermal evaporated GST-on-SOI for photonic neuromorphic application","source":"crossref","abstract":"Neuromorphic computing is inevitable in addressing the computing challenges faced by the current computing architecture. A nonvolatile process is one of the key elements in realizing a neuromorphic architecture. Realization of a photonic nonvolatile state has been a challenge. Germanium antimony telluride (GST) offers potential electrical and optical characteristics to realize an optical nonvolatile state through a material phase transition. In this work, we demonstrate controlled phase tuning of a thermally evaporated GST-integrated silicon ring-resonator for potential neuromorphic application. We present material characterization and device fabrication and correlate the electrical and photonic phase transitions of ring-integrated GST. The temperature cycling in temperature-dependent resistance measurement shows the feasibility of pinning the phase of the transition region, which could be exploited for multiple non-volatile states. Using a simple device architecture, we have exploited the non-volatile and gradual transition of thermally evaporated GST to access intermediate states, which can be realized as synaptic weights in neural networks.","url":"https://doi.org/10.1063/5.0257237","authors":["Rakshitha Kallega","Roopali Shekhawat","K. Ramesh","Shankar Kumar Selvaraja"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-01T14:53:44Z","doi":"10.1063/5.0257237","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.2172/2563843","name":"SANA-FE: Simulating Advanced Neuromorphic Architectures for Fast Exploration","source":"crossref","abstract":"","url":"https://doi.org/10.2172/2563843","authors":["Frances Chance","Suma Cardwell","Mark Plagge","Andreas Gerstlauer","James Boyle"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-07T02:13:30Z","doi":"10.2172/2563843","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/comp-sif69752.2026.11481884","name":"A Neuromorphic Approach to Exoplanet Detection Using Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/comp-sif69752.2026.11481884","authors":["Parth Bhatnagar","Vidushi Gupta","Dayananda P","Manjit Sodhi","Krishnakanth Naik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-29T19:46:03Z","doi":"10.1109/comp-sif69752.2026.11481884","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1109/edaps64431.2024.10988471","name":"Performance of Plasma Treated 2D MoS<sub>2</sub> Synaptic Memristor for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/edaps64431.2024.10988471","authors":["Kanupriya Varshney","Rohit Sharma","Devarshi Mrinal Das","Brajesh Rawat"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-12T17:42:25Z","doi":"10.1109/edaps64431.2024.10988471","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/lmag.2024.3484957","name":"Spintronic Neuron Using a Magnetic Tunnel Junction for Low-Power Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/lmag.2024.3484957","authors":["Steven Louis","Hannah Bradley","Cody Trevillian","Andrei Slavin","Vasyl Tyberkevych"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-24T17:27:36Z","doi":"10.1109/lmag.2024.3484957","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/iscas45731.2020.9180923","name":"Reliability-Driven Neural Network Training for Memristive Crossbar-Based Neuromorphic Computing Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas45731.2020.9180923","authors":["Junpeng Wang","Qi Xu","Bo Yuan","Song Chen","Bei Yu","Feng Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-29T13:22:27Z","doi":"10.1109/iscas45731.2020.9180923","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/cip.2010.5604236","name":"Emerging neuromorphic computing architectures &amp;amp; enabling hardware for cognitive information processing applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cip.2010.5604236","authors":["Robinson E. Pino","Gerard Genello","Morgan Bishop","Michael J. Moore","Richard Linderman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-11-03T14:51:03Z","doi":"10.1109/cip.2010.5604236","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.64038/cel.0220248","name":"EXPLORING THE POTENTIAL OF NEUROMORPHIC COMPUTING TO ENHANCE EFFICIENCY AND PERFORMANCE IN AI WORKLOADS","source":"crossref","abstract":"The increasing processing needs of artificial intelligence (AI) has inspired utilizing the architecture of the human brain as a viable way to address this challenge and helped neuromorphic computing become a reality. In contrast to von Neumann architecture-based computer systems, neuromorphic systems offer event driven parallel processing which can make functionally compute thousands more times in parallel and with much lower energy consumption compared to today's technologies. The scope of this work is to study how neuromorphic computing may enable the performance and effectiveness of AI tasks that rely on demanding resources, such as in image recognition, natural language processing and real-time data processing. On the basis of a proper examination of arrangements of the present in neuromorphic equipment, for example, IBM's True North, Brain Chip’s Akida and Intel's Loihi, it tends to be contended that the framework is thoroughly greater than when contrasted and customary GPUs and CPUs as far as power utilization and fundamentally increasingly proficient. The integration of spiking neural networks (SNNs) into neuromorphic systems has been demonstrated to improve real time job performance and offer important advantages for future edge AI applications where energy efficiency and delay are essential. In addition, to facilitate data interpretation and decision making in an edge database system, the work studies the possibility for synergy between neuromorphic computing and a hybrid AI model that unifies deep learning with symbolic reasoning. For instance, the research showed that neuromorphic computing and hybrid AI models have a range of practical applications in smart cities, medical diagnostics, self driving vehicles and smart agriculture among others. Although neuromorphic computing offers various advantages, there are some things to be worked out, like scaling, interfacing with existing AI pipelines, and developing a standardized programming framework. In the near future, efforts for future research should focus on establishing standardized framework s and evaluation measures to close the gap between neuromorphic systems and conventional AI architectures. Finally, neuromorphic computing and hybrid AI model allow us to take on these computational issues in modern AI workloads in a revolutionary way. With continued advancement of these technologies, the possibility of smarter, more responsive, energy efficient systems are possible: systems that can scale to support the needs of real-time applications in a number of fields.","url":"https://doi.org/10.64038/cel.0220248","authors":["Mohammad Arafath Uddin Shariff","Sara Khan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-04T18:05:24Z","doi":"10.64038/cel.0220248","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/dcna63495.2024.10718522","name":"Parylene-MoO<sub>x</sub> nanocomposite memristor crossbar for neuromorphic computing applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/dcna63495.2024.10718522","authors":["Margarita Ryabova","Anna Matsukatova","Andrey Emelyanov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-21T17:18:23Z","doi":"10.1109/dcna63495.2024.10718522","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1038/s41563-018-0248-5","name":"Ionic modulation and ionic coupling effects in MoS2 devices for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s41563-018-0248-5","authors":["Xiaojian Zhu","Da Li","Xiaogan Liang","Wei D. Lu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-11-29T07:43:32Z","doi":"10.1038/s41563-018-0248-5","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/vlsit.2018.8510690","name":"A Methodology to Improve Linearity of Analog RRAM for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/vlsit.2018.8510690","authors":["Wei Wu","Huaqiang Wu","Bin Gao","Peng Yao","Xiang Zhang","Xiaochen Peng","Shimeng Yu","He Qian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-11-16T04:19:05Z","doi":"10.1109/vlsit.2018.8510690","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1364/psc.2021.m2b.2","name":"On-Chip &gt; 100 TMAC/sec Neuromorphic Photonics Turning into Reality","source":"crossref","abstract":"Remarkable advances in photonic integration fueled an impressive variety of neuromorphic architectures, combining coherent and Wavelength-Division-Multiplexing approaches in reducing latency, footprint and power consumption, while operating at multi-10 GHz clock-rates to yield &gt; 100 TMAC/sec.","url":"https://doi.org/10.1364/psc.2021.m2b.2","authors":["Angelina Totovic","Apostolos Tsakyridis","George Giamougiannis","Miltos Moralis-Pegios","George Dabos","George Mourgias-Alexandris","Nikos Pleros"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-01-18T20:51:46Z","doi":"10.1364/psc.2021.m2b.2","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.21474/jncs01/126","name":"NEUROMORPHIC COMPUTING FOR NEXT-GENERATION ARTIFICIAL INTELLIGENCE: ARCHITECTURES, APPLICATIONS, AND FUTURE RESEARCH DIRECTIONS","source":"crossref","abstract":"The growing computational demands of modern Artificial Intelligence (AI) have exposed the limitations of conventional von Neumann computing architectures in terms of energy efficiency, latency, and scalability. Neuromorphic computing has emerged as a revolutionary computing paradigm inspired by the structure and functioning of the human brain. By integrating specialized hardware with brain-inspired neural processing models, neuromorphic systems aim to perform intelligent computation with significantly lower power consumption and faster response times. This paper provides a comprehensive review of neuromorphic computing, including its architecture, fundamental principles, enabling technologies, real-world applications, implementation challenges, and future research opportunities. The study also discusses the integration of neuromorphic processors with edge computing, robotics, the Internet of Things (IoT), and autonomous systems. The findings indicate that neuromorphic computing has the potential to transform intelligent computing by enabling energy-efficient, adaptive, and real-time AI systems.","url":"https://doi.org/10.21474/jncs01/126","authors":["Amelia J. Foster","Yusuf M. Khalid","Diego L. Romero"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-13T08:41:46Z","doi":"10.21474/jncs01/126","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1117/12.3077887","name":"Brillouin-based memory and signal processing for photonic neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3077887","authors":["Olivia Saffer","Jesus Humberto Marines Cabello","Grigorii Slinkov","Steven Becker","Andreas Geilen","Birgit Stiller"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-05T20:50:54Z","doi":"10.1117/12.3077887","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.48175/ijarsct-36820","name":"Neuromorphic Computing: From Device Physics to Scalable Systems – A Comprehensive Review","source":"crossref","abstract":"Neuromorphic computing has emerged as a promising paradigm for addressing the growing energy demands of modern computing by incorporating brain-inspired principles into physical hardware. However, a major challenge lies in scaling individual synaptic devices from laboratory demonstrations to integrated systems capable of real-world applications. This review examines recent progress from device-level innovations to system-level architectures and standardized benchmarking frameworks. In particular, it discusses emerging implementations of artificial synapses based on spintronic and photonic technologies, including photoresponsiveheterostructures and optical scattering techniques that exploit intrinsic physical phenomena for information processing. At the device scale, mechanisms such as magnetic switching, optical response, and wave interference enable efficient and parallel computation. Translating these devices into practical neuromorphic systems requires overcoming integration challenges related to device interconnectivity, power management, and compatibility across heterogeneous platforms, including photonic and electronic circuits. Furthermore, the development of standardized benchmarking frameworks is crucial for evaluating performance, comparing architectures, and identifying system limitations. This review consolidates recent advances in device physics, neuromorphic architectures, and evaluation methodologies, highlighting key directions for the development of scalable and energy-efficient neuromorphic computing systems beyond conventional architectures.","url":"https://doi.org/10.48175/ijarsct-36820","authors":["Anushree A. Rajput, Suresh R. Kumbhar, Vaishali S. Patil"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-30T12:14:18Z","doi":"10.48175/ijarsct-36820","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1109/aicas64808.2025.11173160","name":"Neuromorphic Robotics on Conventional Low-Power CPU Hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aicas64808.2025.11173160","authors":["Nicola Russo","Thomas Madsen","Konstantin Nikolic"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-25T17:52:35Z","doi":"10.1109/aicas64808.2025.11173160","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1088/2634-4386/ac8a6a","name":"2D materials and van der Waals heterojunctions for neuromorphic computing","source":"crossref","abstract":"Abstract Neuromorphic computing systems employing artificial synapses and neurons are expected to overcome the limitations of the present von Neumann computing architecture in terms of efficiency and bandwidth limits. Traditional neuromorphic devices have used 3D bulk materials, and thus, the resulting device size is difficult to be further scaled down for high density integration, which is required for highly integrated parallel computing. The emergence of two-dimensional (2D) materials offers a promising solution, as evidenced by the surge of reported 2D materials functioning as neuromorphic devices for next-generation computing. In this review, we summarize the 2D materials and their heterostructures to be used for neuromorphic computing devices, which could be classified by the working mechanism and device geometry. Then, we survey neuromorphic device arrays and their applications including artificial visual, tactile, and auditory functions. Finally, we discuss the current challenges of 2D materials to achieve practical neuromorphic devices, providing a perspective on the improved device performance, and integration level of the system. This will deepen our understanding of 2D materials and their heterojunctions and provide a guide to design highly performing memristors. At the same time, the challenges encountered in the industry are discussed, which provides a guide for the development direction of memristors.","url":"https://doi.org/10.1088/2634-4386/ac8a6a","authors":["Zirui Zhang","Dongliang Yang","Huihan Li","Ce Li","Zhongrui Wang","Linfeng Sun","Heejun Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-08-17T22:17:31Z","doi":"10.1088/2634-4386/ac8a6a","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/icnc64304.2024.10987665","name":"NODE-Former: A Hybrid Approach for Robust Long-Term Time Series Forecasting","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987665","authors":["Bin Wei","Jiejie Chen","Ping Jiang","Zhiwei Xiao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987665","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.3390/jlpea10040040","name":"An Improved K-Spare Decomposing Algorithm for Mapping Neural Networks onto Crossbar-Based Neuromorphic Computing Systems","source":"crossref","abstract":"Mapping deep neural network (DNN) models onto crossbar-based neuromorphic computing system (NCS) has recently become more popular since it allows us to realize the advantages of DNNs on small computing systems. However, due to the physical limitations of NCS, such as limited programmability, or a fixed and small number of neurons and synapses of memristor crossbars (the most important component of NCS), we have to quantize and decompose a DNN model into many partitions before the mapping. However, each weight parameter in the original network has its own scaling factor, while crossbar cell hardware has only one scaling factor. This will cause a significant error and will reduce the performance of the system. To mitigate this issue, the K-spare neuron approach has been proposed, which uses additional K spare neurons to capture more scaling factors. Unfortunately, this approach typically uses a large number of neurons overhead. To mitigate this issue, this paper proposes an improved version of the K-spare neuron method that uses a decomposition algorithm to minimize the neuron number overhead while maintaining the accuracy of the DNN model. We achieve this goal by using a mean squared quantization error (MSQE) to evaluate which crossbar units are more important and use more scaling factor than others, instead of using the same k-spare neurons for all crossbar cells as previous work does. Our experimental results are demonstrated on the ImageNet dataset (ILSVRC2012) and three typical and popular deep convolution neural networks: VGG16, Resnet152, and MobileNet v2. Our proposed method only uses 0.1%, 3.12%, and 2.4% neurons overhead for VGG16, Resnet152, and MobileNet v2 to keep their accuracy loss at 0.44%, 0.63%, and 1.24%, respectively, while other methods use about 10–20% of neurons overhead for the same accuracy loss.","url":"https://doi.org/10.3390/jlpea10040040","authors":["Thanh D. Dao","Jaeyong Chung"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-11-25T20:48:12Z","doi":"10.3390/jlpea10040040","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1016/j.bpr.2024.100158","name":"Nonlinear classifiers for wet-neuromorphic computing using gene regulatory neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.bpr.2024.100158","authors":["Adrian Ratwatte","Samitha Somathilaka","Sasitharan Balasubramaniam","Assaf A. Gilad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-05T17:23:13Z","doi":"10.1016/j.bpr.2024.100158","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1007/s00500-026-11405-9","name":"Reframing optimization in Agri biotech using neuromorphic digital twins for fuzzy multi objective control of evolving bioprocesses","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00500-026-11405-9","authors":["Hamed Nozari","Zornitsa Yordanova"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-14T10:19:46Z","doi":"10.1007/s00500-026-11405-9","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1109/icrc64395.2024.10936998","name":"HiAER-Spike: Hardware-Software Co-Design for Large-Scale Reconfigurable Event-Driven Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icrc64395.2024.10936998","authors":["Gwenevere Frank","Gopabandhu Hota","Keli Wang","Abhinav Uppal","Omowuyi Olajide","Kenneth Yoshimoto","Leif Gibb","Qingbo Wang","Johannes Leugering","Stephen Deiss","Gert Cauwenberghs"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-28T03:23:48Z","doi":"10.1109/icrc64395.2024.10936998","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/iscas56072.2025.11044086","name":"Zero-Aware Regularization for Energy-Efficient Inference on Akida Neuromorphic Processor","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas56072.2025.11044086","authors":["Takehiro Habara","Takashi Sato","Hiromitsu Awano"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-27T17:42:19Z","doi":"10.1109/iscas56072.2025.11044086","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1002/aisy.202000085","name":"Memristors—From In‐Memory Computing, Deep Learning Acceleration, and Spiking Neural Networks to the Future of Neuromorphic and Bio‐Inspired Computing","source":"crossref","abstract":"Machine learning, particularly in the form of deep learning (DL), has driven most of the recent fundamental developments in artificial intelligence (AI). DL is based on computational models that are, to a certain extent, bio‐inspired, as they rely on networks of connected simple computing units operating in parallel. The success of DL is supported by three factors: availability of vast amounts of data, continuous growth in computing power, and algorithmic innovations. The approaching demise of Moore's law, and the consequent expected modest improvements in computing power that can be achieved by scaling, raises the question of whether the progress will be slowed or halted due to hardware limitations. This article reviews the case for a novel beyond‐complementary metal–oxide–semiconductor (CMOS) technology—memristors—as a potential solution for the implementation of power‐efficient in‐memory computing, DL accelerators, and spiking neural networks. Central themes are the reliance on non‐von‐Neumann computing architectures and the need for developing tailored learning and inference algorithms. To argue that lessons from biology can be useful in providing directions for further progress in AI, an example‐based reservoir computing is briefly discussed. At the end, speculation is given on the “big picture” view of future neuromorphic and brain‐inspired computing systems.","url":"https://doi.org/10.1002/aisy.202000085","authors":["Adnan Mehonic","Abu Sebastian","Bipin Rajendran","Osvaldo Simeone","Eleni Vasilaki","Anthony J. Kenyon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-03T01:57:19Z","doi":"10.1002/aisy.202000085","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.3390/jlpea15020016","name":"2D Spintronics for Neuromorphic Computing with Scalability and Energy Efficiency","source":"crossref","abstract":"The demand for computing power has been growing exponentially with the rise of artificial intelligence (AI), machine learning, and the Internet of Things (IoT). This growth requires unconventional computing primitives that prioritize energy efficiency, while also addressing the critical need for scalability. Neuromorphic computing, inspired by the biological brain, offers a transformative paradigm for addressing these challenges. This review paper provides an overview of advancements in 2D spintronics and device architectures designed for neuromorphic applications, with a focus on techniques such as spin-orbit torque, magnetic tunnel junctions, and skyrmions. Emerging van der Waals materials like CrI3, Fe3GaTe2, and graphene-based heterostructures have demonstrated unparalleled potential for integrating memory and logic at the atomic scale. This work highlights technologies with ultra-low energy consumption (0.14 fJ/operation), high switching speeds (sub-nanosecond), and scalability to sub-20 nm footprints. It covers key material innovations and the role of spintronic effects in enabling compact, energy-efficient neuromorphic systems, providing a foundation for advancing scalable, next-generation computing architectures.","url":"https://doi.org/10.3390/jlpea15020016","authors":["Douglas Z. Plummer","Emily D’Alessandro","Aidan Burrowes","Joshua Fleischer","Alexander M. Heard","Yingying Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-24T04:48:18Z","doi":"10.3390/jlpea15020016","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1038/s41545-026-00586-3","name":"Energy-efficient water quality modeling using memristor-based neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s41545-026-00586-3","authors":["Minhyuk Jeung","Gyeongil Son","Minjae Kim","Sang-Soo Baek"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-26T09:14:16Z","doi":"10.1038/s41545-026-00586-3","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.19070/2167-8685-2000025","name":"A Review of Resistor Switching Devices for Memory and Neuromorphic Computing Applications","source":"crossref","abstract":"","url":"https://doi.org/10.19070/2167-8685-2000025","authors":["Hamsavahini R"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-10-24T05:21:17Z","doi":"10.19070/2167-8685-2000025","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/ispdc.2010.10","name":"Algorithm for Mapping Multilayer BP Networks onto the SpiNNaker Neuromorphic Hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ispdc.2010.10","authors":["X. Jin","M. Luján","M.M. Khan","L.A. Plana","A.D. Rast","S.R. Welbourne","S.B. Furber"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-08-03T16:24:55Z","doi":"10.1109/ispdc.2010.10","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/icsict55466.2022.9963333","name":"Parallel Dual-Gate Thin-Film Transistors for Sensing and Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icsict55466.2022.9963333","authors":["Yushen Hu","Tengteng Lei","Man Wong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T20:52:39Z","doi":"10.1109/icsict55466.2022.9963333","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1117/12.2554915","name":"Highly efficient neuromorphic computing systems with emerging nonvolatile memories","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.2554915","authors":["Brady Taylor","Ziru Li","Bonan Yan","Hai Li","Yiran Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-03-23T23:14:04Z","doi":"10.1117/12.2554915","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/icecs58634.2023.10382935","name":"Vacancy Modulated Analog Resistive Switching Memory Device Based on Bilayer of Zn@ZnO/ZnO for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icecs58634.2023.10382935","authors":["Muhammad Umair Khan","Baker Mohammad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-10T19:38:25Z","doi":"10.1109/icecs58634.2023.10382935","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1039/d5tc03407h/v2/decision1","name":"Decision letter for \"Electro-Ferroelectric Characterization of Nicotinium Tetrachloridocuprate(II) Memristor for Prospective Neuromorphic Applications\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5tc03407h/v2/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-29T21:07:44Z","doi":"10.1039/d5tc03407h/v2/decision1","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.56553/popets-2025-0060","name":"Are Neuromorphic Architectures Inherently Privacy-preserving? An Exploratory Study","source":"crossref","abstract":"While machine learning (ML) models are becoming mainstream, including in critical application domains, concerns have been raised about the increasing risk of sensitive data leakage. Various privacy attacks, such as membership inference attacks (MIAs), have been developed to extract data from trained ML models, posing significant risks to data confidentiality. While the predominant work in the ML community considers traditional Artificial Neural Networks (ANNs) as the default neural model, neuromorphic architectures, such as Spiking Neural Networks (SNNs), have recently emerged as an attractive alternative mainly due to their significantly low power consumption. These architectures process information through discrete events, i.e., spikes, to mimic the functioning of biological neurons in the brain. While the privacy issues have been extensively investigated in the context of traditional ANNs, they remain largely unexplored in neuromorphic architectures, and little work has been dedicated to investigating their privacy-preserving properties. In this paper, we investigate the question of whether SNNs have inherent privacy-preserving advantages. Specifically, we investigate SNNs’ privacy properties through the lens of MIAs across diverse datasets, in comparison with ANNs. We explore the impact of different learning algorithms (surrogate gradient and evolutionary learning), programming frameworks (snnTorch, TENNLab, and LAVA), and various parameters on the resilience of SNNs against MIA. Our experiments reveal that SNNs demonstrate consistently superior privacy preservation compared to ANNs, with evolutionary algorithms further enhancing their resilience. For example, on the CIFAR-10 dataset, SNNs achieve an AUC as low as 0.59 compared to 0.82 for ANNs, and on CIFAR-100, SNNs maintain a low AUC of 0.58, whereas ANNs reach 0.88. Furthermore, we investigate the privacy-utility trade-off through Differentially Private Stochastic Gradient Descent (DPSGD), observing that SNNs incur a notably lower accuracy drop than ANNs under equivalent privacy constraints.","url":"https://doi.org/10.56553/popets-2025-0060","authors":["Ayana Moshruba","Ihsen Alouani","Maryam Parsa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-07T23:36:18Z","doi":"10.56553/popets-2025-0060","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1364/cleo_si.2025.ss184_2","name":"Novel Neuromorphic Functions of GaN-Nanowire-Based Optoelectronic Synapses in Photoelectrochemical Environment","source":"crossref","abstract":"We construct a photoelectrochemical synaptic device using p-AlGaN/n-GaN nanowires that integrates chemical-electric behaviors into optoelectronic synapses. The device demonstrates dual-modal plasticity, mimics chemically-regulated synaptic activity, and emulates oxidative stress-induced biological phenomena.","url":"https://doi.org/10.1364/cleo_si.2025.ss184_2","authors":["Xin Liu","Danhao Wang","Wei Chen","Huabin Yu","Muhammad Hunain Memon","Haiding Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-24T20:07:18Z","doi":"10.1364/cleo_si.2025.ss184_2","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1038/s42005-025-02257-0","name":"Magnetic tunnel junctions driven by hybrid optical-electrical signals as a flexible neuromorphic computing platform","source":"crossref","abstract":"Abstract Magnetic tunnel junctions (MTJs) offer a promising pathway toward energy-efficient neuromorphic computing due to their nanoscale footprint, nonvolatile switching, and intrinsic nonlinear dynamics that emulate synaptic behavior. However, generating large thermoelectric voltages with bias-tunable nonlinearities for neuromorphic use remains largely unexplored. Here, we introduce a hybrid opto-electrical excitation scheme—combining pulsed laser heating with DC bias—to drive MTJs into the nonlinear bias-enhanced tunnel magneto-Seebeck regime. This regime yields thermoelectric voltages in the tens of millivolts with a strong contrast between magnetic states, while also revealing spiking and double-switching behavior linked to vortex dynamics and fixed-layer depinning. The thermovoltage exhibits cubic dependence on bias current, enabling tunable synaptic weights. We simulate a single-layer neuromorphic network using optically encoded inputs and achieve 93.7% classification accuracy on handwritten digits. These results establish hybrid-driven MTJs as a compact, CMOS-compatible platform for neuromorphic computing, integrating optical input with spintronic functionality.","url":"https://doi.org/10.1038/s42005-025-02257-0","authors":["Felix Oberbauer","Tristan Joachim Winkel","Tim Böhnert","Clara C. Wanjura","Marcel S. Claro","Luana Benetti","Ihsan Çaha","Francis Leonard Deepak","Farshad Moradi","Ricardo Ferreira","Markus Münzenberg","Tahereh Sadat Parvini"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-13T18:40:05Z","doi":"10.1038/s42005-025-02257-0","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1007/978-3-031-65549-4_3","name":"Disaster Management in Civil Engineering","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-65549-4_3","authors":["Ali Akbar Firoozi","Ali Asghar Firoozi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-26T13:01:53Z","doi":"10.1007/978-3-031-65549-4_3","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/nvmsa.2017.8064465","name":"A quantization-aware regularized learning method in multilevel memristor-based neuromorphic computing system","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nvmsa.2017.8064465","authors":["Chang Song","Beiye Liu","Wei Wen","Hai Li","Yiran Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-10-24T16:43:01Z","doi":"10.1109/nvmsa.2017.8064465","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1007/978-3-031-79855-9_5","name":"Neuromorphic models","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-79855-9_5","authors":["S.N. Yanushkevich","G. Tangim","A.H. Tran","T. Mohamed","V.P. Shmerko","S. Kasai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-09T04:26:28Z","doi":"10.1007/978-3-031-79855-9_5","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/cse-euc.2017.188","name":"A High-Performance Network-on-Chip Topology for Neuromorphic Architectures","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cse-euc.2017.188","authors":["Nasrin Akbari","Mehdi Modarressi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-08-10T20:42:43Z","doi":"10.1109/cse-euc.2017.188","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.55041/ijsrem57837","name":"Real-Time Disaster Response and Recovery by using Neuromorphic Computing-Enabled Autonomous Agents","source":"crossref","abstract":"Abstract - This paper presents a practical approach to disaster response and recovery through the integration of neuromorphic computing, autonomous agents, and energy-efficient processing systems. Neuromorphic computing, inspired by the human brain's architecture, enables ultralow power consumption while maintaining high-speed, real-time processing capabilities essential for disaster scenarios. The proposed system deploys Spiking Neural Networks (SNNs) running on neuromorphic hardware platforms like Brain Chip Akida, combined with event-driven sensors including Dynamic Vision Sensors (DVS) and Silicon Cochlea for audio processing. These autonomous agents can operate independently for extended periods without external power sources or internet connectivity, making them ideal for disaster environments where traditional infrastructure fails. The system integrates multi-agent coordination protocols, explainable AI for trustworthy decision-making, and real-time adaptation through spike-timing-dependent plasticity (STDP). The neuromorphic approach addresses critical limitations of traditional disaster response systems including high power consumption, infrastructure dependency, and limited operational duration. This research contributes to advancing sustainable AI for humanitarian applications, potentially revolutionizing emergency response capabilities and saving lives through more effective, autonomous disaster management systems. Key Words: Neuromorphic Computing, Spiking Neural Networks, Autonomous Agents, Disaster Management Response, Multi-agent Systems, Sustainable AI.","url":"https://doi.org/10.55041/ijsrem57837","authors":["G Gokilavani","Abirami Shankari S","CT Vidhya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-17T13:25:02Z","doi":"10.55041/ijsrem57837","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1109/icnc59488.2023.10462784","name":"Tibetan Few-Shot Learning Model Based on Matching Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462784","authors":["Ziyue Zhang","Gaojie Xiong","Yongbin Yu","Xiangxiang Wang","Xiao Feng","Nyima Tashi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462784","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.3390/astronautics1030011","name":"Hybrid Neuromorphic Edge Computing and Quantum Cloud Optimization for Martian Swarm Robot Survival and Map Recovery","source":"crossref","abstract":"Martian dust storms cut off communication and break standard robot navigation. We built a hybrid system that keeps robot swarms alive during these blackouts and recovers their data quickly. Our rovers use Spiking Neural Networks (SNNs) on their own edge processors to navigate without a signal. Once the storm passes, we use the Quantum Approximate Optimization Algorithm (QAOA) on a cloud platform to merge the fragmented maps the rovers collected while they were offline. We tested this system in a Robot Operating System 2 (ROS 2) and Gazebo environment using a simulated 10-rover Martian deployment. During the simulated blackout, our SNN edge navigation achieved a 92.0% survival rate, outperforming traditional planners like Dynamic Window Approach (DWA) (29.0%) and Timed Elastic Band (TEB) (24.3%). The neuromorphic approach also reduced overall system power consumption by 80.0% compared to a traditional unoptimized Graphics Processing Unit (GPU)-based Simultaneous Localization and Mapping (SLAM) baseline. For the map recovery phase, our simulated QAOA proof-of-concept evaluated the map constraints in just 1.2 ms, compared to 50.0 ms for a classical Generalized Iterative Closest Point (G-ICP) and g2o pose-graph approach. Despite the noisy sensor data collected during the blackout, the final quantum-stitched map achieved an 8.54 cm Root Mean Square Error (RMSE). These results show that combining edge-based neuromorphic processing with quantum cloud computing secures swarm survival and accelerates post-disaster data recovery for deep-space missions.","url":"https://doi.org/10.3390/astronautics1030011","authors":["Chandan Sheikder","Weimin Zhang","Xiaopeng Chen","Shicheng Fan","Tairan Li","Haotong He"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-30T08:26:15Z","doi":"10.3390/astronautics1030011","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1038/s43246-026-01165-2","name":"Self-rectifying Ag2O1-δ-based synaptic crossbar array for neuromorphic computing applications","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s43246-026-01165-2","authors":["Bishal Kumar Keshari","Chetan Kodand Reddy Madadi","Sanghamitra DebRoy","Akshay Salimath","Venkat Mattela","Parikshit Sahatiya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-02T18:36:08Z","doi":"10.1038/s43246-026-01165-2","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1007/978-981-95-4415-8_15","name":"A Review on Gallium Oxide (Ga₂O₃) Phototransistors for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-95-4415-8_15","authors":["Monisha Biswas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-02T03:17:51Z","doi":"10.1007/978-981-95-4415-8_15","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1016/j.ceramint.2023.11.268","name":"Occurrence of robust memristive behavior for low-power transient resistive switching and photo-responsive neuromorphic computing in low-dimensional perovskite","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.ceramint.2023.11.268","authors":["Peiying Li","Xiaojie Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-25T07:15:00Z","doi":"10.1016/j.ceramint.2023.11.268","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1371/journal.pone.0264364","name":"Neuromorphic computing for content-based image retrieval","source":"crossref","abstract":"Neuromorphic computing mimics the neural activity of the brain through emulating spiking neural networks. In numerous machine learning tasks, neuromorphic chips are expected to provide superior solutions in terms of cost and power efficiency. Here, we explore the application of Loihi, a neuromorphic computing chip developed by Intel, for the computer vision task of image retrieval. We evaluated the functionalities and the performance metrics that are critical in content-based visual search and recommender systems using deep-learning embeddings. Our results show that the neuromorphic solution is about 2.5 times more energy-efficient compared with an ARM Cortex-A72 CPU and 12.5 times more energy-efficient compared with NVIDIA T4 GPU for inference by a lightweight convolutional neural network when batch size is 1 while maintaining the same level of matching accuracy. The study validates the potential of neuromorphic computing in low-power image retrieval, as a complementary paradigm to the existing von Neumann architectures.","url":"https://doi.org/10.1371/journal.pone.0264364","authors":["Te-Yuan Liu","Ata Mahjoubfar","Daniel Prusinski","Luis Stevens"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-06T17:42:41Z","doi":"10.1371/journal.pone.0264364","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/icons69015.2025.00032","name":"Quantizing Small-Scale State-Space Models for Edge AI","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons69015.2025.00032","authors":["Leo Zhao","Tristan Torchet","Melika Payvand","Laura Kriener","Filippo Moro"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-21T21:07:17Z","doi":"10.1109/icons69015.2025.00032","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.23919/date48585.2020.9116354","name":"Modeling a Floating-Gate Memristive Device for Computer Aided Design of Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.23919/date48585.2020.9116354","authors":["L. Danial","V. Gupta","E. Pikhay","Y. Roizin","S. Kvatinsky"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-15T23:28:37Z","doi":"10.23919/date48585.2020.9116354","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1088/2634-4386/ad40ca","name":"Advanced iontronic spiking modes with multiscale diffusive dynamics in a fluidic circuit","source":"crossref","abstract":"Abstract Fluidic iontronics is emerging as a distinctive platform for implementing neuromorphic circuits, characterised by its reliance on the same aqueous medium and ionic signal carriers as the brain. Drawing upon recent theoretical advancements in both iontronic spiking circuits and in dynamic conductance of conical ion channels, which form fluidic memristors, we expand the repertoire of proposed neuronal spiking dynamics in iontronic circuits. Through a modelled circuit containing channels that carry a bipolar surface charge, we extract phasic bursting, mixed-mode spiking, tonic bursting, and threshold variability, all with spike voltages and frequencies within the typical range for mammalian neurons. These features are possible due to the strong dependence of the typical conductance memory retention time on the channel length, enabling timescales varying from individual spikes to bursts of multiple spikes within a single circuit. These advanced forms of neuronal-like spiking support the exploration of aqueous iontronics as an interesting platform for neuromorphic circuits.","url":"https://doi.org/10.1088/2634-4386/ad40ca","authors":["T M Kamsma","E A Rossing","C Spitoni","R van Roij"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-30T08:41:23Z","doi":"10.1088/2634-4386/ad40ca","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.7868/s3034508125050034","name":"NANOSCALE STRANTRONIC MAGNETOELETRIC CELL FOR NEUROMORPHIC SYSTEMS","source":"crossref","abstract":"Results are reported on numerical-analytic modelling of functional characteristics of a nanoscale neuron-like magnetoelectric cell. Nonlinear transfer activation functions of a composite cell and conditions of their formation in spin-reorientation processes in the magnet sub-system were determined. As applied to the transformation of random pulsed signals, threshold modes of generation of inverse polarity spikes were demonstrated as well as phenomena of potential accumulation followed by an abrupt change of the system’s state of the Integrate-and-Fire type. Magnitude of signals at input and output of the nanoscale cell values few millivolts. The activation function type and the threshold values of input signals are controlled by magnetizing field, which permits to expand the functional capabilities of components for analog neuromorphic systems.","url":"https://doi.org/10.7868/s3034508125050034","authors":["L. M. Krutyansky","V. L. Preobrazhensky"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-13T10:38:22Z","doi":"10.7868/s3034508125050034","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1109/codes-isss.2013.6659010","name":"Bio-inspired ultra lower-power neuromorphic computing engine for embedded systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/codes-isss.2013.6659010","authors":["Beiye Liu","Miao Hu","Hai Li","Yiran Chen","Chun Xue"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-11-21T15:52:07Z","doi":"10.1109/codes-isss.2013.6659010","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1038/s43246-024-00707-w","name":"Integrating molecular photoswitch memory with nanoscale optoelectronics for neuromorphic computing","source":"crossref","abstract":"Abstract Photonic solutions are potentially highly competitive for energy-efficient neuromorphic computing. However, a combination of specialized nanostructures is needed to implement all neuro-biological functionality. Here, we show that donor-acceptor Stenhouse adduct dyes integrated with III-V semiconductor nano-optoelectronics have combined excellent functionality for bio-inspired neural networks. The dye acts as synaptic weights in the optical interconnects, while the nano-optoelectronics provide neuron reception, interpretation and emission of light signals. These dyes can reversibly switch from absorbing to non-absorbing states, using specific wavelength ranges. Together, they show robust and predictable switching, low energy thermal reset and a memory dynamic range from days to sub-seconds that allows both short- and long-term memory operation at natural timescales. Furthermore, as the dyes do not need electrical connections, on-chip integration is simple. We illustrate the functionality using individual nanowire photodiodes as well as arrays. Based on the experimental performance metrics, our on-chip solution is capable of operating an anatomically validated model of the insect brain navigation complex.","url":"https://doi.org/10.1038/s43246-024-00707-w","authors":["David Alcer","Nelia Zaiats","Thomas K. Jensen","Abbey M. Philip","Evripidis Gkanias","Nils Ceberg","Abhijit Das","Vidar Flodgren","Stanley Heinze","Magnus T. Borgström","Barbara Webb","Bo W. Laursen","Anders Mikkelsen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-13T22:59:28Z","doi":"10.1038/s43246-024-00707-w","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.2197/ipsjtsldm.12.53","name":"Neuromorphic Computing Systems: From CMOS To Emerging Nonvolatile Memory","source":"crossref","abstract":"","url":"https://doi.org/10.2197/ipsjtsldm.12.53","authors":["Chaofei Yang","Ximing Qiao","Yiran Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-07-31T22:07:26Z","doi":"10.2197/ipsjtsldm.12.53","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1039/d5tc01475a/v1/review2","name":"Review for \"Improved Neuromorphic Functionality in Organic Electrochemical Transistors Using Crosslinked-Polyvinyl alcohol for Fast Ion Transport and its Application to Pavlovian Transistors\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5tc01475a/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-11T21:06:55Z","doi":"10.1039/d5tc01475a/v1/review2","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1145/3822454.3822489","name":"CRISP: A JIT Compiled Neuromorphic Simulator","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3822454.3822489","authors":["Jackson Mowry","James Plank"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-16T05:57:39Z","doi":"10.1145/3822454.3822489","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:21.716Z"},{"id":"doi:10.1109/aero63441.2025.11068762","name":"Fault Mitigation for SNN Classification of Neuromorphic Event Streams with Radiation-Induced Noise","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aero63441.2025.11068762","authors":["Joshua Poravanthattil","Daniel C. Stumpp","Seth Roffe","Alan D. George"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-14T17:40:12Z","doi":"10.1109/aero63441.2025.11068762","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1021/acs.chemrev.5c00340","name":"Introduction: Neuromorphic Materials","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acs.chemrev.5c00340","authors":["A. Alec Talin","Bilge Yildiz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T07:06:10Z","doi":"10.1021/acs.chemrev.5c00340","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1039/d5ta02437d","name":"Inversion symmetry-broken CuBO\n                    <sub>2</sub>\n                    delafossite through anionic site doping for improved piezoelectric composites with PVDF and its application in nanogenerators and optoelectronic neuromorphic computing","source":"crossref","abstract":"Self-charging photodetectors drive the development of energy-autonomous electronics for efficient use in memory, portable devices, neuromorphic computing, and optoelectronic systems.","url":"https://doi.org/10.1039/d5ta02437d","authors":["Suvankar Poddar","Pulok Das","Souvik Bhattacharjee","Kalyan Kumar Chattopadhyay"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-10T19:01:14Z","doi":"10.1039/d5ta02437d","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1039/d5tc01372k/v1/review2","name":"Review for \"Inverted resistive switching mechanism in polycrystalline PBTTT-C14 polymer devices based on contact geometry and molecular packing for neuromorphic memory\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5tc01372k/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-30T17:05:17Z","doi":"10.1039/d5tc01372k/v1/review2","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1016/j.apmt.2025.102959","name":"Engineering ZrO2/WS2 nanocomposite for multilevel memory and high-performance neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.apmt.2025.102959","authors":["Faisal Ghafoor","Honggyun Kim","Bilal Ghafoor","Muhammad Asif Hamayun","Muhammad Faheem Maqsood","Myoung-Jae Lee","Deok-kee Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-18T17:06:07Z","doi":"10.1016/j.apmt.2025.102959","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.3390/jlpea16030032","name":"Hybrid Filamentary Switching in Fe2O3—Incorporated TiO2 Memristors for Memory and Neuromorphic Computing Application","source":"crossref","abstract":"Memristive devices have emerged as promising candidates for next-generation non-volatile memory and neuromorphic computing systems owing to their simple device architecture, low power consumption, and capability for analog conductance modulation. In this work, Fe2O3-incorporated TiO2 thin films were employed as the active switching layer to investigate their resistive switching and artificial synaptic characteristics. The fabricated Ag/TiO2 + Fe2O3/FTO device exhibits stable switching performance with a low operating voltage of approximately ±0.6 V, a large ON/OFF ratio of ~103, retention of nearly 104 s, and endurance over 5000 pulse cycles, representing a significant improvement compared with pristine TiO2 devices. Electrical transport analysis demonstrates Schottky emission-dominated conduction in the high-resistance state and Ohmic conduction in the low-resistance state. Furthermore, analog switching behavior was achieved by operating the device under a higher compliance current, demonstrating gradual conductance modulation and synaptic weight update characteristics, indicating the potential of the device for neuromorphic applications. These results demonstrate that Fe2O3 incorporation provides an effective approach for simultaneously enhancing memory performance and synaptic functionality in TiO2-based memristors, highlighting their potential for future memory and neuromorphic computing applications.","url":"https://doi.org/10.3390/jlpea16030032","authors":["Dwipak Prasad Sahu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-12T09:11:36Z","doi":"10.3390/jlpea16030032","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1103/physrevapplied.18.017001","name":"Halide-Perovskite-Based Memristor Devices and Their Application in Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1103/physrevapplied.18.017001","authors":["Soumitra Satapathi","Kanishka Raj","Yukta","Mohammad Adil Afroz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-07-28T18:31:25Z","doi":"10.1103/physrevapplied.18.017001","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1109/icscan66520.2026.11588318","name":"Adversarial Robustness Analysis of Spiking Neural Networks for Neuromorphic Computing Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icscan66520.2026.11588318","authors":["Venkateshmurthy B S","Sajja Suneel","Neha Ghildiyal","R. Naveenkumar","D. Baburao","D. Shanthi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-07T19:42:48Z","doi":"10.1109/icscan66520.2026.11588318","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1109/icnc59488.2023.10462770","name":"Improved Two-Step Finite-Time Stabilization Control for Time-Delay Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462770","authors":["Yue Chen","Song Zhu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462770","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1109/cdc57313.2025.11311980","name":"Formalizing Neuromorphic Control Systems A General Proposal and A Rhythmic Case Study","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cdc57313.2025.11311980","authors":["Taisia Medvedeva","Fernando Castaños","Alessio Franci"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-12T18:19:56Z","doi":"10.1109/cdc57313.2025.11311980","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1002/aisy.202500351","name":"Harnessing Nonidealities in Analog In‐Memory Computing Circuits: A Physical Modeling Approach for Neuromorphic Systems","source":"crossref","abstract":"Large‐scale deep learning models are increasingly constrained by their immense energy consumption, which limits their scalability and applicability for edge intelligence. In‐memory computing (IMC) offers a promising solution by addressing the von Neumann bottleneck inherent in traditional deep learning accelerators, significantly reducing energy consumption. However, the analog nature of IMC introduces hardware nonidealities that degrade model performance and reliability. This article presents a novel approach to directly train physical models of IMC, formulated as ordinary differential equation (ODE)‐based physical neural networks (PNNs). To enable the training of large‐scale networks, a technique called differentiable spike‐time discretization is proposed, which reduces the computational cost of ODE‐based PNNs by up to 20 times in speed and 100 times in memory. Such large‐scale networks enhance learning performance by exploiting hardware nonidealities on the CIFAR‐10 dataset. The proposed bottom‐up methodology is validated through post‐layout SPICE simulations on the IMC circuit with nonideal characteristics using the sky130 process. The proposed PNN approach reduces the discrepancy between model behavior and circuit dynamics by at least an order of magnitude. This work paves the way for leveraging nonideal physical devices, such as nonvolatile resistive memories, for energy‐efficient deep learning applications.","url":"https://doi.org/10.1002/aisy.202500351","authors":["Yusuke Sakemi","Yuji Okamoto","Takashi Morie","Sou Nobukawa","Takeo Hosomi","Kazuyuki Aihara"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-18T19:04:54Z","doi":"10.1002/aisy.202500351","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1039/d5tc01475a/v2/review1","name":"Review for \"Improved Neuromorphic Functionality in Organic Electrochemical Transistors Using Crosslinked-Polyvinyl alcohol for Fast Ion Transport and its Application to Pavlovian Transistors\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5tc01475a/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-11T21:06:55Z","doi":"10.1039/d5tc01475a/v2/review1","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1088/2515-7639/ad9ee1","name":"Realizing linear synaptic plasticity in electric double layer-gated transistors for improved predictive accuracy and efficiency in neuromorphic computing","source":"crossref","abstract":"Abstract Neuromorphic computing offers a low-power, parallel alternative to traditional von Neumann architectures by addressing the sequential data processing bottlenecks. Electric double layer-gated transistors (EDLTs) resemble biological synapses with their ionic response and offer low power operations, making them suitable for neuromorphic applications. A critical consideration for artificial neural networks (ANNs) is achieving linear and symmetric plasticity (i.e. weight updates) during training, as this directly affects accuracy and efficiency. This study uses finite element modeling to explore EDLTs as artificial synapses in ANNs and investigates the underlying mechanisms behind the nonlinear weight updates observed experimentally in previous studies. By solving modified Poisson–Nernst–Planck equations, we examined ion dynamics within an EDL capacitor and their effects on plasticity, revealing that the rates of EDL formation and dissipation are concentration-dependent. Fixed-magnitude pulse inputs result in decreased formation and increased dissipation rates, leading to nonlinear weight updates. For a pulse magnitude of 1 V, both 1 ms 500 Hz and 5 ms 100 Hz pulse inputs saturated at less than half of the steady state EDL concentration, limiting the number of accessible states and operating range of devices. To address this, we developed a predictive linear ionic weight update solver (LIWUS) in Python to predict voltage pulse inputs that achieve linear plasticity. We then evaluated an ANN with linear and nonlinear weight updates on the Modified National Institute of Standards and Technology classification task. The ANN with LIWUS-provided linear weight updates required 19% fewer (i.e. 5) epochs in both training and validation than the network with nonlinear weight updates to reach optimal performance. It achieved a 97.6% recognition accuracy, 1.5–4.2% higher than with nonlinear updates, and a low standard deviation of 0.02%. The network model is amenable to future spiking neural network applications, and the performance with linear weight update s is expected to improve for complex networks with multiple hidden layers.","url":"https://doi.org/10.1088/2515-7639/ad9ee1","authors":["Nithil Harris Manimaran","Cori Lee Mathew Sutton","Jake W Streamer","Cory Merkel","Ke Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-13T22:53:12Z","doi":"10.1088/2515-7639/ad9ee1","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.2172/1899879","name":"Materials Discovery for Energy-Efficient Neuromorphic Computing: A Co-Design Approach.","source":"crossref","abstract":"","url":"https://doi.org/10.2172/1899879","authors":["Christian Mailhiot"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-30T03:18:50Z","doi":"10.2172/1899879","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1088/2634-4386/ae9be4","name":"Node perturbation can effectively train multi-layer neural networks","source":"crossref","abstract":"Abstract Backpropagation (BP) remains the dominant and most successful method for training parameters of deep neural network models. However, BP relies on two computationally distinct phases, does not provide a satisfactory explanation of biological learning, and can be challenging to apply for training of networks with discontinuities or noisy node dynamics. By comparison, node perturbation (NP), also known as activity-perturbed forward gradients, proposes learning by the injection of noise into network activations, and subsequent measurement of the induced loss change. NP relies on two forward (inference) passes, does not make use of network derivatives, and has been proposed as a model for learning in biological systems. However, standard NP is highly data inefficient and can be unstable due to its unguided noise-based search process. In this work, we develop a modern perspective on NP by relating it to the directional derivative and incorporating input decorrelation. We find that a closer alignment with directional derivatives together with input decorrelation at every layer theoretically and practically enhances performance of NP learning with large improvements in parameter convergence and much higher performance on the test data, approaching that of BP. Furthermore, our novel formulation allows for application to noisy systems in which the noise process itself is inaccessible, which is of particular interest for on-chip learning in neuromorphic systems.","url":"https://doi.org/10.1088/2634-4386/ae9be4","authors":["Sander Dalm","Marcel A J van Gerven","Nasir Ahmad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-19T22:50:46Z","doi":"10.1088/2634-4386/ae9be4","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1038/s41467-022-33288-8","name":"Synthetic neuromorphic computing in living cells","source":"crossref","abstract":"Abstract Computational properties of neuronal networks have been applied to computing systems using simplified models comprising repeated connected nodes, e.g., perceptrons, with decision-making capabilities and flexible weighted links. Analogously to their revolutionary impact on computing, neuro-inspired models can transform synthetic gene circuit design in a manner that is reliable, efficient in resource utilization, and readily reconfigurable for different tasks. To this end, we introduce the perceptgene, a perceptron that computes in the logarithmic domain, which enables efficient implementation of artificial neural networks in Escherichia coli cells. We successfully modify perceptgene parameters to create devices that encode a minimum, maximum, and average of analog inputs. With these devices, we create multi-layer perceptgene circuits that compute a soft majority function, perform an analog-to-digital conversion, and implement a ternary switch. We also create a programmable perceptgene circuit whose computation can be modified from OR to AND logic using small molecule induction. Finally, we show that our approach enables circuit optimization via artificial intelligence algorithms.","url":"https://doi.org/10.1038/s41467-022-33288-8","authors":["Luna Rizik","Loai Danial","Mouna Habib","Ron Weiss","Ramez Daniel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-24T01:02:52Z","doi":"10.1038/s41467-022-33288-8","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1088/2634-4386/ad6732","name":"Difficulties and approaches in enabling learning-in-memory using crossbar arrays of memristors","source":"crossref","abstract":"Abstract Crossbar arrays of memristors are promising to accelerate the deep learning algorithm as a non-von-Neumann architecture, where the computation happens at the location of the memory. The computations are parallelly conducted employing the basic physical laws. However, current research works mainly focus on the offline training of deep neural networks, i.e. only the information forwarding is accelerated by the crossbar array. Two other essential operations, i.e. error backpropagation and weight update, are mostly simulated and coordinated by a conventional computer in von Neumann architecture, respectively. Several different in situ learning schemes incorporating error backpropagation and/or weight updates have been proposed and investigated through neuromorphic simulation. Nevertheless, they met the issues of non-ideal synaptic behaviors of the memristors and the complexities of the neural circuits surrounding crossbar arrays. Here we review the difficulties and approaches in implementing the error backpropagation and weight update operations for online training or in-memory learning that are adapted to noisy and non-ideal memristors. We hope this work will be beneficial for the development of open neuromorphic simulation tools for learning-in-memory systems, and eventually for the hardware implementation of such as system.","url":"https://doi.org/10.1088/2634-4386/ad6732","authors":["Wei Wang","Yang Li","Ming Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-24T19:07:11Z","doi":"10.1088/2634-4386/ad6732","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1007/978-3-030-91741-8_6","name":"Accelerated Analog Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-91741-8_6","authors":["Johannes Schemmel","Sebastian Billaudelle","Philipp Dauer","Johannes Weis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-25T10:05:10Z","doi":"10.1007/978-3-030-91741-8_6","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1016/j.neucom.2024.128758","name":"Simulation-based effective comparative analysis of neuron circuits for neuromorphic computation systems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2024.128758","authors":["Deepthi M.S.","Shashidhara H.R.","Jayaramu Raghu","Rudraswamy S.B."],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-28T11:30:09Z","doi":"10.1016/j.neucom.2024.128758","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1101/2025.07.10.25331024","name":"Event-based seizure detection in human iEEG with neuromorphic hardware","source":"preprints","abstract":"Abstract Background Epilepsy is a neurological disorder that affects approximately 1% of the global population. The current method for seizure monitoring, seizure diaries, is often inaccurate, making precise monitoring challenging. A monotonic descending “chirp” pattern in intracranial EEG (iEEG) is a specific marker of seizure onset and can be used for automatic detection. Objective To determine whether a spiking neural network (SNN) implemented on the DYNAP-SE1 neuromorphic chip can detect chirps/seizures. Methods We analysed 48 h of continuous bipolar iEEG from one patient (40 seizures). The signal was filtered into six 10 Hz sub-bands between 0 and 40 Hz, then encoded into UP/DOWN events with software asynchronous delta modulation (ADM). The encoded signal was used as input in the hardware-implemented SNN with 34 adaptive-exponential neurons (3.3 % of the 1024 neurons on one chip). Hierarchical inhibition enforced the required high-to-low band sequence, and a disinhibition unit suppressed isolated low-frequency bursts. We implemented the same 28-neuron SNN (without the dis-inhibition population) on software. Results Chirps appeared at the onset of all 40 seizures (100 %). The hardware SNN detected every seizure (sensitivity = 100 %) and produced one false alarm in 48 h (falsealarm rate = 0.021 h -1 ). Mean processing time was 4 h 55 s ± 42 s for each 4-h data block, showing real-time operation. In the software SNN implementation, we analysed the same 48-h iEEG bipolar channel recording, and detected 32/40 seizures (80 % sensitivity) with 9 false alarms (false-alarm rate = 0.19 h -1 ). Conclusion A 34-neuron SNN implemented on DYNAP-SE1 detects seizures from single-channel iEEG in real time with 100% sensitivity and a low false-alarm rate while using minimal hardware resources.","url":"https://doi.org/10.1101/2025.07.10.25331024","authors":["Flavia Davidhi","Filippo Costa","Debora Ledergerber","Giacomo Indiveri","Lukas Imbach","Johannes Sarnthein"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.07.10.25331024","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1109/ijcnn64981.2025.11229386","name":"PointLCA-Net: Using Point Clouds for Energy Efficient Sparse Spatio-Temporal Signal Recognition in Neuromorphic Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn64981.2025.11229386","authors":["Sanaz Mahmoodi Takaghaj"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T18:46:15Z","doi":"10.1109/ijcnn64981.2025.11229386","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:20.559Z"},{"id":"doi:10.1088/2634-4386/ae66b2","name":"CMOS implementation of field programmable spiking neural network for hardware reservoir computing","source":"crossref","abstract":"Abstract The increasing complexity and energy demands of large-scale neural networks, such as deep neural networks and large language models, challenge their practical deployment in edge applications due to high power consumption, area requirements, and privacy concerns. Spiking neural networks, particularly in analog implementations, offer a promising low-power alternative but suffer from noise sensitivity and connectivity limitations. This work presents a novel CMOS-fabricated field-programmable neural network architecture for hardware reservoir computing (RC). We propose a leaky integrate-and-fire neuron circuit featuring integrated voltage-controlled oscillators and synaptic weights programmed via an on-chip field-programmable gate array framework. This framework enables direct connectivity between neurons, supporting the implementation of arbitrary reservoir configurations. The performance of the system is validated through simulation and chip measurements, demonstrating effective FORCE algorithm learning alongside competitive results in linear/non-linear memory capacity and NARMA10 benchmarks. The neuron design achieves compact area utilization (around 540 NAND2-equivalent units) and low energy consumption (21.7 pJ/pulse) without requiring ADCs for information readout, making it ideal for system-on-chip integration of RC. This architecture paves the way for scalable, energy-efficient neuromorphic systems capable of performing real-time learning and inference with high configurability and digital interfacing.","url":"https://doi.org/10.1088/2634-4386/ae66b2","authors":["Ckristian Duran","Nanako Kimura","Zolboo Byambadorj","Tetsuya Iizuka"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-29T22:52:45Z","doi":"10.1088/2634-4386/ae66b2","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/iccons.2017.8250637","name":"Implementation of STDP based learning rule in neuromorphic CMOS circuits","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccons.2017.8250637","authors":["P. J. Srinidhi","T. R. Yashaswini","N. Uttunga","Syed Aslam Ali","Mohammed Riyaz Ahmed"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-01-17T22:23:56Z","doi":"10.1109/iccons.2017.8250637","addedAt":"2026-09-01T01:48:20.559Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1109/isvlsi61997.2024.00144","name":"Reliability Analysis of Phase Change Memory-Based Neuromorphic Circuits","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isvlsi61997.2024.00144","authors":["Twisha Titirsha","Md Maruf Hossain Shuvo","Syed Kamrul Islam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-25T17:27:50Z","doi":"10.1109/isvlsi61997.2024.00144","addedAt":"2026-09-01T01:48:20.899Z","updatedAt":"2026-09-01T01:48:20.899Z"},{"id":"doi:10.1109/cas62834.2024.10736815","name":"Can Threshold Memory Switching Memristor be Effectively Utilized for the Hardware Implementation of Brain-Inspired Neuromorphic Systems?","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cas62834.2024.10736815","authors":["Mani Shankar Yadav","Brajesh Rawat"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-31T13:33:03Z","doi":"10.1109/cas62834.2024.10736815","addedAt":"2026-09-01T01:48:20.899Z","updatedAt":"2026-09-01T01:48:20.899Z"},{"id":"doi:10.1109/icons62911.2024.00046","name":"Estimating Post-Synaptic Effects for Online Training of Feed-Forward SNNs","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024.00046","authors":["Thomas M. Summe","Clemens JS Schaefer","Siddharth Joshi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T18:37:03Z","doi":"10.1109/icons62911.2024.00046","addedAt":"2026-09-01T01:48:20.899Z","updatedAt":"2026-09-01T01:48:20.899Z"},{"id":"doi:10.1088/2053-1583/adb8c3","name":"Ionically gated transistors based on two-dimensional materials for neuromorphic computing","source":"crossref","abstract":"Abstract Neuromorphic computing is a low-power and energy efficient alternative to von Neumann computing that demands new materials and computing architectures. Two-dimensional (2D) van der Waals materials and ions are a particularly favorable pair for neuromorphic computing. The large surface to volume ratio of 2D layered materials makes them sensitive to the presence of ions, detected as orders of magnitude change in electrical resistance. Quantum confinement of 2D crystals limits carrier scattering and enhances mobility, which decreases power consumption. Moreover, the 2D crystal-ion pair can provide volatile and non-volatile responses in the same device, as well as dynamic synaptic properties, such as spike-timing dependent plasticity. These dynamic properties are particularly relevant because they mirror the mechanisms involved in biological learning and memory. In this perspective, we first summarize recent progress in the field, categorize 2D crystal-ion devices in terms of their mechanisms (either electrostatic or electrochemical), and highlight key synaptic functionalities these devices can replicate. We underscore the differences between artificial and biological synapses, and between devices meant to emulate biological functions versus those optimized for compatibility with digital artificial neural networks (ANNs). We note that the use of ionically gated transistors based on 2D crystals (2D IGTs) in ANNs has primarily focused on their non-volatile memory functions, rather than fully exploiting their dynamic synaptic properties. We assert that the energy-efficient operation of 2D IGTs, enabled by their high capacitance density and tunable ion dynamics, makes them particularly suited for low-power edge computing applications. Finally, our perspective is that realizing the full potential of 2D crystals and ions in neuromorphic systems will require bridging the gap between demonstrated synaptic functionalities and their practical implementations in neural networks.","url":"https://doi.org/10.1088/2053-1583/adb8c3","authors":["Ke Xu","Susan K Fullerton-Shirey"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-21T05:48:16Z","doi":"10.1088/2053-1583/adb8c3","addedAt":"2026-09-01T01:48:20.899Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/edkcon62339.2024.10870684","name":"New Locally-Active Memristor for Neuromorphic Application","source":"crossref","abstract":"","url":"https://doi.org/10.1109/edkcon62339.2024.10870684","authors":["Parnab Das","Santanu Mandal","Mousami Sanyal","Soumyadip Chowdhuri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-13T18:32:24Z","doi":"10.1109/edkcon62339.2024.10870684","addedAt":"2026-09-01T01:48:20.899Z","updatedAt":"2026-09-01T01:48:20.899Z"},{"id":"doi:10.1016/j.flatc.2024.100755","name":"Sustainable vertically-oriented graphene-electrode memristors for neuromorphic applications","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.flatc.2024.100755","authors":["Ben Walters","Michael S.A. Kamel","Mohan V. Jacob","Mostafa Rahimi Azghadi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-09T20:29:36Z","doi":"10.1016/j.flatc.2024.100755","addedAt":"2026-09-01T01:48:20.899Z","updatedAt":"2026-09-01T01:48:20.899Z"},{"id":"doi:10.1117/12.3028109","name":"Neuromorphic machine vision in a network laser","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3028109","authors":["Jakub Dranczewski","Wai Kit Ng","Anna Fischer","Dhruv Saxena","Raziman Thottungal Valapu","Tobias Farchy","Kilian D. Stenning","Will R. Branford","Heinz Schmid","Kirsten E. Moselund","Mauricio Barahona","Riccardo Sapienza","Jack Gartside"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-02T18:26:31Z","doi":"10.1117/12.3028109","addedAt":"2026-09-01T01:48:20.899Z","updatedAt":"2026-09-01T01:48:20.899Z"},{"id":"doi:10.1038/s44335-025-00028-2","name":"Comparing quantum annealing and spiking neuromorphic computing for sampling binary sparse coding QUBO problems","source":"crossref","abstract":"Abstract We consider the problem of computing a sparse binary representation of an image. Given an image and an overcomplete, non-orthonormal basis, we aim to find a sparse binary vector indicating the minimal set of basis vectors that when added together best reconstruct the given input. We formulate this problem with an L 2 loss on the reconstruction error, and an L 0 loss on the binary vector enforcing sparsity. First, we solve the sparse representation QUBOs by solving them both on a D-Wave quantum annealer with Pegasus chip connectivity, as well as on the Intel Loihi 2 spiking neuromorphic processor using a stochastic Non-equilibrium Boltzmann Machine (NEBM). Second, using Quantum Evolution Monte Carlo with Reverse Annealing and iterated warm starting on Loihi 2 to evolve the solution quality from the respective machines. We demonstrate that both quantum annealing and neuromorphic computing are suitable for solving binary sparse coding QUBOs.","url":"https://doi.org/10.1038/s44335-025-00028-2","authors":["Kyle Henke","Elijah Pelofske","Garrett Kenyon","Georg Hahn"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-04T04:43:01Z","doi":"10.1038/s44335-025-00028-2","addedAt":"2026-09-01T01:48:20.899Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/icons62911.2024.00041","name":"Spatiotemporal Dendritic Processing in Superconducting Optoelectronic Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024.00041","authors":["Ryan O'Loughlin","Bryce Primavera","Jeffrey Shainline"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T18:37:03Z","doi":"10.1109/icons62911.2024.00041","addedAt":"2026-09-01T01:48:20.899Z","updatedAt":"2026-09-01T01:48:20.899Z"},{"id":"doi:10.1109/icedge67252.2025.11412899","name":"Quantum-Inspired Neuromorphic Simulation of Action Potentials via Semiconductor-Ion Channel Interfaces at the Edge","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icedge67252.2025.11412899","authors":["Chitaranjan Mahapatra","Ashish Kumar Pradhan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-06T20:58:41Z","doi":"10.1109/icedge67252.2025.11412899","addedAt":"2026-09-01T01:48:20.899Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/cict67193.2025.11399200","name":"Modelling and Simulation of Threshold Switching Memristors for Next-Generation Memory and Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cict67193.2025.11399200","authors":["M. Julie Therese","Jossan Eleazar B","Tejendra Dixit"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-24T20:55:40Z","doi":"10.1109/cict67193.2025.11399200","addedAt":"2026-09-01T01:48:20.899Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/tvlsi.2023.3336379","name":"FeFET Local Multiply and Global Accumulate Voltage-Sensing Computation-In-Memory Circuit Design for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tvlsi.2023.3336379","authors":["Chihiro Matsui","Kasidit Toprasertpong","Shinichi Takagi","Ken Takeuchi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-06T19:27:09Z","doi":"10.1109/tvlsi.2023.3336379","addedAt":"2026-09-01T01:48:20.899Z","updatedAt":"2026-09-01T01:48:20.899Z"},{"id":"doi:10.60023/qvsndc03","name":"Neuromorphic Computing Model Based on Spiking Neural Network for an Efficient and Resilient Tsunami Early Warning System in Indonesia’s Small Islands","source":"crossref","abstract":"This study aims to develop a fault-tolerant neuromorphic computing system for tsunami early detection in Indonesia’s small islands, which face significant limitations in energy and network infrastructure. The research was conducted over a three-month period (January–March 2025) using a simulated experimental approach with ocean wave data obtained from BMKG and NOAA. The system model was designed using a Spiking Neural Network (SNN) that mimics biological neuron activity to adaptively recognize ocean wave anomaly patterns. Simulation results show a detection accuracy rate of 94%, maintaining stable performance above 85% even under 25% signal interference. Furthermore, the system’s power consumption was recorded at only 0.42 watts—approximately 40–60% more efficient than conventional CNN-based models. The implications of this study include scientific contributions to the development of adaptive and energy-efficient artificial intelligence, as well as practical benefits for agencies such as BMKG and BNPB in designing autonomous and resilient tsunami early warning systems for remote and underdeveloped regions. In the future, this system has the potential to serve as a prototype for edge computing–based disaster mitigation solutions powered by artificial intelligence, particularly relevant for archipelagic nations.","url":"https://doi.org/10.60023/qvsndc03","authors":["Jayaun Jayaun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-06T05:44:05Z","doi":"10.60023/qvsndc03","addedAt":"2026-09-01T01:48:20.899Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1002/flm2.70012","name":"Advancements in flexible memristors for neuromorphic computing: Materials, mechanisms, and applications in synaptic emulation","source":"crossref","abstract":"Abstract The brain orchestrates complex physiological processes through intricate neural networks, with synapses serving as the fundamental units for inter‐neuronal communication and ensuring the efficient functioning of these networks. Consequently, the development of devices capable of emulating synaptic functions represents a crucial avenue for advancing our understanding of neural networks. Among these devices, memristors have emerged as a promising candidate. Recognized as the fourth fundamental passive circuit element, memristors exhibit distinctive nonlinear memory characteristics. Their resistance values dynamically adjust in response to variations in the charge flowing through them and, importantly, retain these modified states even after power disconnection. These unique properties render memristors particularly suitable for emulating synaptic functions in neural systems. This paper provides a comprehensive overview of recent advancements in material selection and resistive switching mechanisms for flexible memristors, highlighting their applications in the construction of artificial neural networks. Furthermore, we discuss the feasibility of implementing neural networks using memristor‐based architectures, while also addressing the current challenges that need to be overcome. Finally, we outline the development prospects and ongoing challenges in this rapidly evolving field.","url":"https://doi.org/10.1002/flm2.70012","authors":["Weiwei Li","Chunbo Duan","Ying Wei","Hui Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-24T03:40:41Z","doi":"10.1002/flm2.70012","addedAt":"2026-09-01T01:48:20.899Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1117/12.3065423","name":"Scalable neuromorphic in-memory computing with n-ary spintronic crossbars","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3065423","authors":["Anatole Moureaux","Anthony Lopes Temporao","Lindiomar Borges de Avila","Flavio Abreu Araujo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-18T18:28:59Z","doi":"10.1117/12.3065423","addedAt":"2026-09-01T01:48:20.899Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/rfid-ta64374.2024.10965168","name":"Towards Memristor-Based Neuromorphic RFID Circuits and Architectures","source":"crossref","abstract":"","url":"https://doi.org/10.1109/rfid-ta64374.2024.10965168","authors":["Riccardo Colella","Alberto Arciello","Giuseppe Grassi","Massimo Merenda"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-22T17:37:25Z","doi":"10.1109/rfid-ta64374.2024.10965168","addedAt":"2026-09-01T01:48:20.899Z","updatedAt":"2026-09-01T01:48:20.899Z"},{"id":"doi:10.1117/3.100022.bm","name":"Back Matter","source":"crossref","abstract":"","url":"https://doi.org/10.1117/3.100022.bm","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-02T21:15:07Z","doi":"10.1117/3.100022.bm","addedAt":"2026-09-01T01:48:20.899Z","updatedAt":"2026-09-01T01:48:20.899Z"},{"id":"doi:10.1002/smll.202309467","name":"First Demonstration of Yttria‐Stabilized Hafnia‐Based Long‐Retention Solid‐State Electrolyte‐Gated Transistor for Human‐Like Neuromorphic Computing","source":"crossref","abstract":"Abstract Electrolyte‐gated transistors have strong potential for high‐performance artificial synapses in neuromorphic bio‐interfaces owing to their outstanding synaptic characteristics, low power consumption, and human‐like mechanisms. However, the short retention time is a hurdle to overcome owing to the natural diffusion of protons. Here, a novel modulation technique of ionic conductivity is proposed with yttria‐stabilized hafnia for the first time to enhance the retention characteristic of a solid‐state electrolyte‐gated transistor‐based artificial synapse. With the optimization of the ionic conductivity in yttria‐stabilized hafnia, a high retention time of over 300 s and remarkable synaptic characteristics are accomplished by regulating channel conductance with precise modulation of the strength of the proton‐electron coupling intensity along the input signals. Furthermore, pattern recognition simulation is conducted based on the measured synaptic characteristics, exhibiting 94.41% of operation accuracy, which implies a promising solution for neuromorphic in‐memory computing systems with a high operation accuracy and low power consumption.","url":"https://doi.org/10.1002/smll.202309467","authors":["Dong‐Gyu Jin","Hyun‐Yong Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-15T18:46:02Z","doi":"10.1002/smll.202309467","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1093/nsr/nwad283","name":"Digital neuromorphic technology: current and future prospects","source":"crossref","abstract":"Digital approaches to brain-inspired computing have advanced apace over recent years - where is the state-of-the-art and what does the future hold?","url":"https://doi.org/10.1093/nsr/nwad283","authors":["Steve Furber"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-08T01:44:40Z","doi":"10.1093/nsr/nwad283","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1109/icons62911.2024.00054","name":"Scaling SNNs Trained Using Equilibrium Propagation to Convolutional Architectures","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024.00054","authors":["Jiaqi Lin","Malyaban Bal","Abhronil Sengupta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T18:37:03Z","doi":"10.1109/icons62911.2024.00054","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1038/s43246-024-00573-6","name":"Metal-organic framework single crystal for in-memory neuromorphic computing with a light control","source":"crossref","abstract":"Abstract Neuromorphic architectures, expanding the limits of computing from conventional data processing and storage to advanced cognition, learning, and in-memory computing, impose restrictions on materials that should operate fast, energy efficiently, and highly endurant. Here we report on in-memory computing architecture based on metal-organic framework (MOF) single crystal with a light control. We demonstrate that the MOF with inherent memristive behavior (for data storage) changes nonlinearly its electric response when irradiated by light. This leads to three and more electronic states (spikes) with 81 ms duration and 1 s refractory time, allowing to implement 40 bits s −1 optoelectronic data processing. Next, the architecture is switched to the neuromorphic state upon the action of a set of laser pulses, providing the text recognition over 50 times with app. 100% accuracy. Thereby, simultaneous data storage, processing, and neuromorphic computing on MOF, driven by light, pave the way for multifunctional in-memory computing architectures.","url":"https://doi.org/10.1038/s43246-024-00573-6","authors":["Semyon V. Bachinin","Alexandr Marunchenko","Ivan Matchenya","Nikolai Zhestkij","Vladimir Shirobokov","Ekaterina Gunina","Alexander Novikov","Maria Timofeeva","Svyatoslav A. Povarov","Fengting Li","Valentin A. Milichko"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-20T18:01:43Z","doi":"10.1038/s43246-024-00573-6","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1002/aelm.202300698","name":"Optimization Method for Conductance Modulation in Ferroelectric Transistor for Neuromorphic Computing","source":"crossref","abstract":"Abstract The learning accuracy of neuromorphic computing that mimics the biological brain, is affected by the conductance‐modulation characteristics of an artificial synapse. In ferroelectric‐based devices, these characteristics are implemented using a distribution of polarization values. Therefore, the distribution in a ferroelectric thin film with various external voltage signals is investigate. As polarization switching proceeds with voltage pulse, the domains of the switched polarization become larger. In ferroelectric‐gate field effect transistors, the channel layer assumed to lie beneath the ferroelectrics experiences a local conductance change, according to the polarization distribution of the ferroelectric layer. It is found that small clusters with high conductivity become large clusters in the channel layer as the polarization switching proceeds. When the additional pulses are applied, the high conductive regions eventually connect (i.e., percolate) in the channel layer and the conductance of the layer is greatly increased. Adjusting the height of the applied voltage can slow down or speed up this phenomenon. Also, the nanosecond voltage pulses are employed and the width of the conductive pathway is adjusted. It enables to fine‐tune the conductance of the channel layer. It demonstrates that conductance modulation is optimized with an appropriate voltage pulse train pattern.","url":"https://doi.org/10.1002/aelm.202300698","authors":["Cheol Jun Kim","Jae Yeob Lee","Minkyung Ku","Tae Hoon Kim","Taehee Noh","Seung Won Lee","Ji‐Hoon Ahn","Bo Soo Kang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-27T16:16:53Z","doi":"10.1002/aelm.202300698","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1002/smll.202411596","name":"High‐Temperature Resilient Neuromorphic Device Based on Optically Configured Monolayer MoS\n                    <sub>2</sub>\n                    for Cognitive Computing","source":"crossref","abstract":"Abstract High‐temperature neuromorphic devices are vital for space exploration and operations in harsh environments such as manufacturing units. To fulfil this need, researchers are developing technologies that imitate the human brain in structure and function. This need is further pushed by the growth of the Internet of Things (IoT), demanding massive computing power and processing of data. Herein, we present a scalable monolayer MoS 2 ‐based neuromorphic device that can operate at temperatures up to 100 °C. The device is fabricated using monolayer MoS 2 , a 2D semiconductor material known for its remarkable properties, such as mechanical flexibility and thermal stability. As a result, the device can operate at high temperatures and may be customized for different purposes. The obtained device is well characterized by excellent electrical properties, including low power consumption, fast switching rate, moderate resistance ratio of ≈102, low switching voltage, and good endurance up to ≈103 cycles. It also shows neuromorphic behavior as it mimics synaptic plasticity exhibited by biological neural networks. This study addresses high‐temperature requirements in electronics and lays the groundwork for connecting electronic systems with the environment to mutually adapt to demands.","url":"https://doi.org/10.1002/smll.202411596","authors":["Pukhraj Prajapat","Pargam Vashishtha","Govind Gupta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-26T03:51:18Z","doi":"10.1002/smll.202411596","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1088/2634-4386/add0d9","name":"Prospects of analog in-memory computing using ferroelectric tunnel junctions","source":"crossref","abstract":"Abstract Artificial intelligence (AI) is set to disrupt the way businesses and civil society operate, but the large energy usage for training and running AI compute models remains a pressing concern in terms of its sustainability. Analog in-memory computing (AIMC) hardware based on memristor devices is a promising route to significant energy-savings. Among the various memristor technologies, ferroelectric tunnel junctions (FTJs) hold considerable promise for large scale AIMC. Their performance prospects remain to be fully assessed; therefore, we here evaluate the viability of FTJ memristors as compute units for AIMC. Based on the behavior of experimental TiN/HfZrO 4 /W FTJs we define three operating modes which we apply to standard AI tests and two real-world use cases: Image segmentation (YOLOv8) and natural language processing (BERT). We find that the inherent mechanism behind the analog state in FTJs limits the usable dynamic range and thus enforces strict control of noise. The best overall performance is obtained by constricting the dynamic range further and using ultrashort programming pulses (0.5 ns); on BERT matching the performance of digital hardware. We also present a more accessible approach, combining three FTJs, two of which are operated as binary memories, to achieve similar performance while also relaxing the requirements on data converter precision and level of noise. All in all, we here reveal benefits and intrinsic challenges of FTJ-based AIMC systems, providing a blueprint for future experimental implementations.","url":"https://doi.org/10.1088/2634-4386/add0d9","authors":["Mattias Borg","Christos Papadopoulos","Alec Guerin","Robin Athle","Saeed Bastani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-25T22:50:17Z","doi":"10.1088/2634-4386/add0d9","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1007/s40843-024-3098-6","name":"Adjustable ion energy barrier for reliable memristive neuromorphic systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s40843-024-3098-6","authors":["Tianci Huang","Zuqing Yuan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T17:02:49Z","doi":"10.1007/s40843-024-3098-6","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1002/adfm.202410974","name":"Photonic Synapse of CrSBr/PtS\n                    <sub>2</sub>\n                    Transistor for Neuromorphic Computing and Light Decoding","source":"crossref","abstract":"Abstract Field effect transistors based on 2D layered material have gained significant potential in emerging technologies, such as neuromorphic computing and ultrafast memory response for artificial intelligence applications. This study proposes a facile approach to fabricate an optoelectronic artificial synapse for neuromorphic computing and light‐decoding information system by utilizing the 2D heterostructure of CrSBr/PtS 2 to overcome circuit complexity. The CrSBr layer serves as a trapping layer, while PtS 2 , mounted on top of CrSBr, acts as a channel layer. PtS 2 exhibits n‐type semiconductor behavior with a hysteresis that varies with the thickness of the underlying CrSBr layer. The heterostructure device, featuring a 96.3 nm thick CrSBr layer, exhibited a large memory window of 11.9 V when the gate voltage is swept from −10 V to +10 V. Various synaptic behaviors are effectively demonstrated, including paired‐pulse facilitation, excitatory postsynaptic current, optical spike number and intensity‐dependent plasticity using laser light at a wavelength of 365 nm. The device achieves 26 distinct output signals depending on the intensity of the incident laser light, ranging from 10 to 385 mW cm −2 , enabling its applications for light‐decoded information security systems. Thus, the investigation presents a unique approach to artificial intelligence and cybersecurity systems.","url":"https://doi.org/10.1002/adfm.202410974","authors":["Muhammad Asghar Khan","Muhammad Farooq Khan","Muhammad Nasim","Ehsan Elahi","Muhammad Rabeel","Muhammad Asim","Arslan Rehmat","Muhammad Hamza Pervez","Shania Rehman","Honggyun Kim","Jonghwa Eom"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-15T06:58:46Z","doi":"10.1002/adfm.202410974","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1088/2634-4386/ae01d2","name":"Stochastic rounding for memory-efficient digital simulation of synaptic plasticity using 8-bit floating-point","source":"crossref","abstract":"Abstract Simulating brain-scale networks digitally is often hindered by extensive memory access. In this context, using low-precision data types and more efficient models to represent state variables is a viable alternative to improve the scalability of the networks under consideration. However, understanding whether these approaches hurt the expected dynamics of the system is critical yet still poorly understood. This study aims to integrate 8-bit floating-point implementations with neural models optimised for efficient memory access to simulate spiking neural networks endowed with spike-timing-dependent plasticity. By doing this, we not only address scalability issues but also consider the biological plausibility of the network activity. We show that stochastic rounding (SR) is necessary to overcome the floating-point errors associated with weight updates and present our custom SR scheme, which was applied to all arithmetic operations. Under these conditions, we study the limitations and behaviour of plastic weight dynamics and large-scale balanced networks. Our results suggest that the models developed can be used to reproduce many prominent features previously described in studies of cortical stability and information processing. Such an approach offers a promising perspective on optimising spiking neural networks for real-time simulations and resource-constrained digital hardware. Such technology could be used to understand neurological disorders by providing insights into abnormal neural activity patterns. It could also enhance brain-computer interfaces, and aid in cognitive neuroscience research, contributing to novel therapeutic strategies.","url":"https://doi.org/10.1088/2634-4386/ae01d2","authors":["Pablo Urbizagastegui","André van Schaik","Runchun Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-02T22:50:59Z","doi":"10.1088/2634-4386/ae01d2","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/asp-dac58780.2024.10473975","name":"SOLSA: Neuromorphic Spatiotemporal Online Learning for Synaptic Adaptation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/asp-dac58780.2024.10473975","authors":["Zhenhang Zhang","Jingang Jin","Haowen Fang","Qinru Qiu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-25T19:06:53Z","doi":"10.1109/asp-dac58780.2024.10473975","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1109/icons62911.2024.00035","name":"Self-Supervised Mapping and Localization by Predictive Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024.00035","authors":["G. William Chapman","Andrew S. Alexander","Frances S. Chance","Michael E. Hasselmo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T18:37:03Z","doi":"10.1109/icons62911.2024.00035","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1109/icons62911.2024.00039","name":"SNNPG: Using Spiking Neural Networks to Detect Attacks in the Power Grid","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024.00039","authors":["Kendric Hood","Ang Li","Qiang Guan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T18:37:03Z","doi":"10.1109/icons62911.2024.00039","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1109/gecost66002.2025.11324553","name":"Real-Time Threat Detection in Connected EVs Using Spiking Neural Networks with 6G-enabled Neuromorphic Edge Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/gecost66002.2025.11324553","authors":["Vansh Jalora","Prem Joshi","Lakshin Pathak","Karm Vyas","Rimmi Sharma","Lakshit Pathak","Rajesh Gupta","Sudeep Tanwar","N. Z. Jhanjhi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-13T20:55:33Z","doi":"10.1109/gecost66002.2025.11324553","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1117/12.3043230","name":"Comprehensive thermal crosstalk model of meshed MZI topologies for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3043230","authors":["Andrea Marchisio","Lorenzo Tunesi","Hasan Awad","Enrico Ghillino","Vittorio Curri","Andrea Carena","Paolo Bardella"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-22T04:15:48Z","doi":"10.1117/12.3043230","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/icons62911.2024.00040","name":"Black-Box Adversarial Attacks on Spiking Neural Network for Time Series Data","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024.00040","authors":["Jack Hutchins","Diego Ferrer","James Fillers","Catherine Schuman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T18:37:03Z","doi":"10.1109/icons62911.2024.00040","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.63519/ijcserd_15_02_007","name":"Brain-Inspired Computing: Revolutionizing Medical Devices Through Neuromorphic Engineering, A Review of different options","source":"crossref","abstract":"","url":"https://doi.org/10.63519/ijcserd_15_02_007","authors":["Sathish Krishna Anumula"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-23T07:06:11Z","doi":"10.63519/ijcserd_15_02_007","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1007/978-981-96-2299-3_20","name":"Investigation on Neuromorphic Computing-Based Neural Networks for Optimizing Machine-Learning Techniques for Industry 4.0","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-96-2299-3_20","authors":["Kannekanti Maanasa","Jagendra Singh","Hardeo Kumar Thakur","Rakesh Kumar","Neelam Gupta","Minal Bafna"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-21T18:39:03Z","doi":"10.1007/978-981-96-2299-3_20","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1109/icons62911.2024.00056","name":"SNNVis: Visualizing Graph Embedding of Evolutionary Optimization for Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024.00056","authors":["Junghoon Chae","Seung-Hwan Lim","Shruti Kulkarni","Catherine Schuman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T18:37:03Z","doi":"10.1109/icons62911.2024.00056","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1109/mdts64924.2025.11177076","name":"High-Throughput Time-domain Neuromorphic Computing using Memristors and ECRAM","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mdts64924.2025.11177076","authors":["Hagar Hendy","Elaine Greenfield","Huayuan Han","Jacob O’Donnell","Ke Xu","Cory Merkel","Tejasvi Das"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T17:37:09Z","doi":"10.1109/mdts64924.2025.11177076","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1109/laedc61552.2024.10555838","name":"Stuck-at Faults in ReRAM Neuromorphic Circuit Array and their Correction through Machine Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/laedc61552.2024.10555838","authors":["Vedant Sawal","Hiu Yung Wong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-17T17:59:04Z","doi":"10.1109/laedc61552.2024.10555838","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1109/ijcnn60899.2024.10650843","name":"Low-power event-based face detection with asynchronous neuromorphic hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn60899.2024.10650843","authors":["Caterina Caccavella","Federico Paredes-Vallés","Marco Cannici","Lyes Khacef"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T17:35:05Z","doi":"10.1109/ijcnn60899.2024.10650843","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1109/iscas58744.2024.10558058","name":"Neuromorphic Energy Efficient Stress Detection System using Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas58744.2024.10558058","authors":["Ajay B S","Madhav Rao","Phani Pavan K"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-02T17:22:52Z","doi":"10.1109/iscas58744.2024.10558058","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.29363/nanoge.matsusfall.2024.133","name":"Neuromorphic devices with ultralow energy consumption from metal halide perovskites","source":"crossref","abstract":"","url":"https://doi.org/10.29363/nanoge.matsusfall.2024.133","authors":["Bruno Ehrler"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T12:32:32Z","doi":"10.29363/nanoge.matsusfall.2024.133","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1109/aicas59952.2024.10595959","name":"Neuromorphic Event-based Line Detection on SpiNNaker","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aicas59952.2024.10595959","authors":["Amélie Gruel","Adrien F. Vincent","Jean Martinet","Sylvain Saïghi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-19T17:30:48Z","doi":"10.1109/aicas59952.2024.10595959","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.14722/ndss.2024.24334","name":"Sneaky Spikes: Uncovering Stealthy Backdoor Attacks in Spiking Neural Networks with Neuromorphic Data","source":"crossref","abstract":"","url":"https://doi.org/10.14722/ndss.2024.24334","authors":["Gorka Abad","Oğuzhan Ersoy","Stjepan Picek","Aitor Urbieta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-10T16:35:08Z","doi":"10.14722/ndss.2024.24334","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1109/dsd67783.2025.00079","name":"A Comprehensive Synthesis and Verification Approach for RRAM-Based Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/dsd67783.2025.00079","authors":["Fatemeh Shirinzadeh","Abhoy Kole","Kamalika Datta","Saeideh Shirinzadeh","Rolf Drechsler"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-09T18:31:56Z","doi":"10.1109/dsd67783.2025.00079","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.54097/gwgea042","name":"Conventional Von Neumann and Neuromorphic Architecture of AI Chips","source":"crossref","abstract":"In the background of the shortage of computing power in the training AI field, the current solutions and future outlooks will be shown if they tackle this dilemma. From the continuation of the traditional computer structure, Von Neumann structure, the three types of AI chips GPU, FPGA, and ASIC will be introduced and state their developments and drawbacks. Besides, a brand new solution gaining inspiration from our brain will also be discussed and introduce the fundamental electronic component to accomplish the goal. The principle of how a nerve fires will also be illustrated and based on this catch a glimpse of the neural network. Besides, The principle of memristors and with the support of crossbars, how could they be used in manufacturing AI Chips will be explained. Finally, the latest research in this field. The advantages and challenges will also be involved. Finally, a comparison of these solutions will be proposed.","url":"https://doi.org/10.54097/gwgea042","authors":["Jingwei Qu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-25T04:25:39Z","doi":"10.54097/gwgea042","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1109/icons62911.2024.00012","name":"Stochastic Spiking Neural Networks with First-to-Spike Coding","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024.00012","authors":["Yi Jiang","Sen Lu","Abhronil Sengupta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T18:37:03Z","doi":"10.1109/icons62911.2024.00012","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1007/978-3-032-25311-8_12","name":"Emerging NeoHebbian Dynamics in Forward-Forward Learning: Implications for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-25311-8_12","authors":["Erik B. Terres-Escudero","Javier Del Ser","Pablo García Bringas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-06T16:37:29Z","doi":"10.1007/978-3-032-25311-8_12","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1021/acsaelm.4c00427","name":"Metallopolymeric Memristor Based Artificial Optoelectronic Synapse for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acsaelm.4c00427","authors":["Xiaozhe Cheng","Zhitao Qin","Hongen Guo","Zhitao Dou","Hong Lian","Jianfeng Fan","Yongquan Qu","Qingchen Dong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-22T10:54:17Z","doi":"10.1021/acsaelm.4c00427","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1088/1361-6528/ad5685","name":"In<sub>2</sub>O<sub>3</sub>/ZnO heterojunction thin film transistor for high recognition accuracy neuromorphic computing and optoelectronic artificial synapses","source":"crossref","abstract":"Abstract Solid electrolyte-gated transistors exhibit improved chemical stability and can fulfill the requirements of microelectronic packaging. Typically, metal oxide semiconductors are employed as channel materials. However, the extrinsic electron transport properties of these oxides, which are often prone to defects, pose limitations on the overall electrical performance. Achieving excellent repeatability and stability of transistors through the solution process remains a challenging task. In this study, we propose the utilization of a solution-based method to fabricate an In 2 O 3 /ZnO heterojunction structure, enabling the development of efficient multifunctional optoelectronic devices. The heterojunction’s upper and lower interfaces induce energy band bending, resulting in the accumulation of a large number of electrons and a significant enhancement in transistor mobility. To mimic synaptic plasticity responses to electrical and optical stimuli, we utilize Li + -doped high-k ZrO x thin films as a solid electrolyte in the device. Notably, the heterojunction transistor-based convolutional neural network achieves a high accuracy rate of 93% in recognizing handwritten digits. Moreover, our research involves the simulation of a typical sensory neuron, specifically a nociceptor, within our synaptic transistor. This research offers a novel avenue for the advancement of cost-effective three-terminal thin-film transistors tailored for neuromorphic applications.","url":"https://doi.org/10.1088/1361-6528/ad5685","authors":["Shangheng Sun","Minghao Zhang","Jing Bian","Ting Xu","Jie Su"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-11T22:22:00Z","doi":"10.1088/1361-6528/ad5685","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1063/5.0314289","name":"Memtransistor for bio-inspired neuromorphic computing: A perspective from device physics to neural and sensory systems","source":"crossref","abstract":"The recent surge in data generated by emerging applications has exposed intrinsic bottlenecks in conventional von Neumann architectures, where physically separated processing and memory units limit bandwidth and energy efficiency. Neuromorphic computing offers a brain-inspired approach that unifies computation and memory within a single hardware framework, enabling massively parallel, low-power information processing. Among various device candidates, memtransistors incorporate a gate terminal that enables independent modulation of resistive switching and channel conductance, thereby allowing the realization of complex learning functions and effectively suppressing sneak-path currents in array architectures. This perspective outlines the operation principles of memtransistors based on diverse physical mechanisms, including ion migration, charge trapping, ferroelectric switching, and phase transitions, and then discusses recent materials and architectural engineering strategies, with particular emphasis on two-dimensional channels and scalable array integration. Beyond device-level behavior, bio-inspired functionalities, such as heterosynaptic and homeostatic plasticity, are highlighted as key ingredients for stable and self-regulated learning in neural networks. The integration of memtransistors with sensory modules is further examined to enable near-sensor and in-sensor computing, paving the way for multimodal signal processing that parallels biological perception. Finally, critical challenges and opportunities in variability control, CMOS-compatible processing, and three-dimensional, multisensory integration are identified, indicating that continued progress in material design and architecture optimization will be essential for positioning memtransistors as key enablers of autonomous, bio-inspired intelligence in future robotics, healthcare, and cognitive electronics.","url":"https://doi.org/10.1063/5.0314289","authors":["Minsu Nam","Hyun Yeop Cho","Seong Eun Lee","Jung Ho Yoon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-02T12:59:48Z","doi":"10.1063/5.0314289","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1021/acsenergylett.4c00691","name":"Memlumor: A Luminescent Memory Device for Energy-Efficient Photonic Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acsenergylett.4c00691","authors":["Alexandr Marunchenko","Jitendra Kumar","Alexander Kiligaridis","Dmitry Tatarinov","Anatoly Pushkarev","Yana Vaynzof","Ivan G. Scheblykin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-09T16:28:26Z","doi":"10.1021/acsenergylett.4c00691","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.4018/978-1-6684-6596-7.ch007","name":"Strategies for Automated Bike-Sharing Systems Leveraging ML and VLSI Approaches","source":"crossref","abstract":"Machine learning has had an impact in the area of microchip design and was initially used in automation. This development could result in a tremendous change in the realm of hardware computation and AI's powerful analysis tools. Traffic is a pressing issue in densely populated cities. Governments worldwide are attempting to address this problem by introducing various forms of public transportation, including metro. However, these solutions require significant investment and implementation time. Despite the high cost and inherent flaws of the system, many people still prefer to use their personal vehicles rather than public transportation. To address this issue, the authors propose a bike-sharing solution in which all processes from membership registration to bike rental and return are automated. Bagging is an ensemble learning method that can be used for base models with a low bias and high variance. It uses randomization of the dataset to reduce the variance of the base models, while keeping the bias low.","url":"https://doi.org/10.4018/978-1-6684-6596-7.ch007","authors":["Jagrat Shukla","Numburi Rishikha","Janhavi Chaturvedi","Sumathi Gokulanathan","Sriharipriya Krishnan Chandrasekaran","Konguvel Elango","SathishKumar Selvaperumal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-19T08:20:15Z","doi":"10.4018/978-1-6684-6596-7.ch007","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1117/12.3064344","name":"High speed photonic spiking neuron based on QD spin VCSELs for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3064344","authors":["Dimitris Alexandropoulos","Panagiotis Georgiou","Christos Tselios","Georgia Himona","Yiannis Kominis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-18T18:27:24Z","doi":"10.1117/12.3064344","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.31219/osf.io/49qzv","name":"Spike Timing Mechanisms in Neuromorphic Vision Sensors using Memristor-based non-volatile Memory devices","source":"crossref","abstract":"Spike-timing mechanisms in neuromorphic vision sensors represent a cutting-edge approach to mimicking biological vision systems' efficiency and adaptability. These systems utilize memristor-based non-volatile memory devices to achieve high precision and low power consumption, essential for real-time image processing and recognition tasks. This paper explores the principles and applications of spike-timing-dependent plasticity (STDP) in neuromorphic vision sensors, focusing on the integration of memristor technology. This study introduces an innovative visual-tactile perception system that integrates a scalable, biomimetic tactile sensor called NeuTouch and uses a Visual-Tactile Spiking Neural Network (VT-SNN) for rapid perception. The system demonstrates high accuracy in robotic tasks such as container classification and rotational slip detection, outperforming traditional deep learning methods. The research also contributes to the field by making visual-tactile datasets publicly available to foster further advancements. This work highlights the potential for creating intelligent, energy-efficient robotic systems. We review the latest advancements in memristor-based memory devices, their role in neuromorphic computing, and how they contribute to the development of advanced vision sensors. The potential of these technologies in revolutionizing artificial vision and their implications for future research and development are also discussed.","url":"https://doi.org/10.31219/osf.io/49qzv","authors":["Yiping Su","Dajeong Hwang","Bing Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-26T09:09:40Z","doi":"10.31219/osf.io/49qzv","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1109/mmsp61759.2024.10743445","name":"Denoising for Neuromorphic Cameras Based on Graph Spectral Features","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mmsp61759.2024.10743445","authors":["Shimpei Harada","Junya Hara","Hiroshi Higashi","Yuichi Tanaka"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-12T18:35:35Z","doi":"10.1109/mmsp61759.2024.10743445","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1088/2634-4386/ad54eb","name":"Exploring non-steady-state charge transport dynamics in information processing: insights from reservoir computing","source":"crossref","abstract":"Abstract Exploring nonlinear chemical dynamic systems for information processing has emerged as a frontier in chemical and computational research, seeking to replicate the brain’s neuromorphic and dynamic functionalities. In this study, we have extensively explored the information processing capabilities of a nonlinear chemical dynamic system through theoretical simulation by integrating a non-steady-state proton-coupled charge transport system into reservoir computing (RC) architecture. Our system demonstrated remarkable success in tasks such as waveform recognition, voice identification and chaos system prediction. More importantly, through a quantitative study, we revealed that the alignment between the signal processing frequency of the RC and the characteristic time of the dynamics of the nonlinear system plays a crucial role in this physical reservoir’s performance, directly influencing the efficiency in the task execution, the reservoir states and the memory capacity. The processing frequency range was further modulated by the characteristic time of the dynamic system, resulting in an implementation akin to a ‘chemically-tuned band-pass filter’ for selective frequency processing. Our study thus elucidates the fundamental requirements and dynamic underpinnings of the non-steady-state charge transport dynamic system for RC, laying a foundational groundwork for the application of dynamical molecular scale devices for in-materia neuromorphic computing.","url":"https://doi.org/10.1088/2634-4386/ad54eb","authors":["Zheyang Li","Xi Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-06T22:24:46Z","doi":"10.1088/2634-4386/ad54eb","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1109/icnc59488.2023.10462810","name":"Stock Market’s Price Movement Prediction with Multi-branch LSTM and Technical Analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462810","authors":["Tao Xue","Sheng Qin","Qiang Fu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462810","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1109/icnc59488.2023.10462841","name":"Discriminating Stability of Hybrid Stochastic Delay Neural Networks: A Novel Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462841","authors":["Han Yu","Song Zhu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462841","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1109/icnc59488.2023.10462852","name":"Fixed-Time Output Synchronization of T-S Fuzzy Complex Networks with Mismatched Parameters","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462852","authors":["Yuhua Gao","Cheng Hu","Juan Yu","Kailong Xiong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462852","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1145/3589737.3605986","name":"Sparsifying Spiking Networks through Local Rhythms","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3589737.3605986","authors":["Wilkie Olin-Ammentorp"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-28T16:00:57Z","doi":"10.1145/3589737.3605986","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1109/icra57147.2024.10610401","name":"A Neuromorphic System for the Real-time Classification of Natural Textures","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icra57147.2024.10610401","authors":["George Brayshaw","Benjamin Ward-Cherrier","Martin J. Pearson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-08T17:51:05Z","doi":"10.1109/icra57147.2024.10610401","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1063/5.0201761","name":"Mechanical intelligence via fully reconfigurable elastic neuromorphic metasurfaces","source":"crossref","abstract":"The ability of mechanical systems to perform basic computations has gained traction over recent years, providing an unconventional alternative to digital computing in off grid, low power, and severe environments, which render the majority of electronic components inoperable. However, much of the work in mechanical computing has focused on logic operations via quasi-static prescribed displacements in origami, bistable, and soft deformable matter. Here, we present a first attempt to describe the fundamental framework of an elastic neuromorphic metasurface that performs distinct classification tasks, providing a new set of challenges, given the complex nature of elastic waves with respect to scattering and manipulation. Multiple layers of reconfigurable waveguides are phase-trained via constant weights and trainable activation functions in a manner that enables the resultant wave scattering at the readout location to focus on the correct class within the detection plane. We further demonstrate the neuromorphic system’s reconfigurability in performing two distinct tasks, eliminating the need for costly remanufacturing.","url":"https://doi.org/10.1063/5.0201761","authors":["M. Moghaddaszadeh","M. Mousa","A. Aref","M. Nouh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-15T14:45:02Z","doi":"10.1063/5.0201761","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1007/978-3-032-25311-8_10","name":"Heterogeneous SoC Integrating an Open-Source Recurrent SNN Accelerator for Neuromorphic Edge Computing on FPGA","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-25311-8_10","authors":["Michelangelo Barocci","Vittorio Fra","Enrico Macii","Gianvito Urgese"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-06T16:33:49Z","doi":"10.1007/978-3-032-25311-8_10","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/nocarc64615.2024.10749965","name":"Deadlocks in NoC-based Neuromorphic Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nocarc64615.2024.10749965","authors":["Jan Moritz Joseph","Jörn Nöller","José Cubero-Cascante","Rebecca Pelke"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-12T18:37:23Z","doi":"10.1109/nocarc64615.2024.10749965","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1021/acsmaterialslett.4c00087","name":"Enhanced Anion Interaction by Polarity Control on CNTVT:SVS Copolymers for Improving Nonvolatile Characteristics in Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acsmaterialslett.4c00087","authors":["Donghwa Lee","Landep Ayuningtias","Jinwoo Hwang","Junho Sung","Joonhee Kang","Yun-Hi Kim","Eunho Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-14T09:14:44Z","doi":"10.1021/acsmaterialslett.4c00087","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.3389/fmats.2024.1406853","name":"Ferroelastic twin walls for neuromorphic device applications","source":"crossref","abstract":"The possibility to use ferroelastic materials as components of neuromorphic devices is discussed. They can be used as local memristors with the advantage that ionic transport is constraint to twin boundaries where ionic diffusion is much faster than in the bulk and does not leak into adjacent domains. It is shown that nano-scale ferroelastic memristors can contain a multitude of domain walls. These domain walls interact by strain fields where the interactions near surfaces are fundamentally different from bulk materials. We show that surface relaxations (∼image forces) are curtailed to short range dipolar interactions which decay as 1/d 2 where d is the distance between domain walls. In bigger samples such interactions are long ranging with 1/d. The cross-over regime is typically in the range of some 200–1500 nm using a simple spring interaction model.","url":"https://doi.org/10.3389/fmats.2024.1406853","authors":["Guangming Lu","Ekhard K. H. Salje"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-14T04:47:25Z","doi":"10.3389/fmats.2024.1406853","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1007/s40820-024-01445-x","name":"Recent Advance in Synaptic Plasticity Modulation Techniques for Neuromorphic Applications","source":"crossref","abstract":"Abstract Manipulating the expression of synaptic plasticity of neuromorphic devices provides fascinating opportunities to develop hardware platforms for artificial intelligence. However, great efforts have been devoted to exploring biomimetic mechanisms of plasticity simulation in the last few years. Recent progress in various plasticity modulation techniques has pushed the research of synaptic electronics from static plasticity simulation to dynamic plasticity modulation, improving the accuracy of neuromorphic computing and providing strategies for implementing neuromorphic sensing functions. Herein, several fascinating strategies for synaptic plasticity modulation through chemical techniques, device structure design, and physical signal sensing are reviewed. For chemical techniques, the underlying mechanisms for the modification of functional materials were clarified and its effect on the expression of synaptic plasticity was also highlighted. Based on device structure design, the reconfigurable operation of neuromorphic devices was well demonstrated to achieve programmable neuromorphic functions. Besides, integrating the sensory units with neuromorphic processing circuits paved a new way to achieve human-like intelligent perception under the modulation of physical signals such as light, strain, and temperature. Finally, considering that the relevant technology is still in the basic exploration stage, some prospects or development suggestions are put forward to promote the development of neuromorphic devices.","url":"https://doi.org/10.1007/s40820-024-01445-x","authors":["Yilin Sun","Huaipeng Wang","Dan Xie"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-06T04:02:38Z","doi":"10.1007/s40820-024-01445-x","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1016/j.mtelec.2024.100105","name":"Bismuth-based ferroelectric memristive device induced by interface barrier for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.mtelec.2024.100105","authors":["Zhi-Long Chen","Yang Xiao","Yang-Fan Zheng","Yan-Ping Jiang","Qiu-Xiang Liu","Xin-Gui Tang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-27T22:29:21Z","doi":"10.1016/j.mtelec.2024.100105","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1016/j.jmst.2024.02.007","name":"High-performance IGZO/In2O3 NW/IGZO phototransistor with heterojunctions architecture for image processing and neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.jmst.2024.02.007","authors":["Can Fu","Zhi-Yuan Li","Yu-Jiao Li","Min-Min Zhu","Lin-Bao Luo","Shan-Shan Jiang","Yan Wang","Wen-Hao Wang","Gang He"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-09T03:38:15Z","doi":"10.1016/j.jmst.2024.02.007","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1126/sciadv.adk9928","name":"Spatial evolution of the proton-coupled Mott transition in correlated oxides for neuromorphic computing","source":"crossref","abstract":"The proton-electron coupling effect induces rich spectrums of electronic states in correlated oxides, opening tempting opportunities for exploring novel devices with multifunctions. Here, via modest Pt-aided hydrogen spillover at room temperature, amounts of protons are introduced into SmNiO 3 -based devices. In situ structural characterizations together with first-principles calculation reveal that the local Mott transition is reversibly driven by migration and redistribution of the predoped protons. The accompanying giant resistance change results in excellent memristive behaviors under ultralow electric fields. Hierarchical tree-like memory states, an instinct displayed in bio-synapses, are further realized in the devices by spatially varying the proton concentration with electric pulses, showing great promise in artificial neural networks for solving intricate problems. Our research demonstrates the direct and effective control of proton evolution using extremely low electric field, offering an alternative pathway for modifying the functionalities of correlated oxides and constructing low–power consumption intelligent devices and neural network circuits.","url":"https://doi.org/10.1126/sciadv.adk9928","authors":["Xing Deng","Yu-Xiang Liu","Zhen-Zhong Yang","Yi-Feng Zhao","Ya-Ting Xu","Meng-Yao Fu","Yu Shen","Ke Qu","Zhao Guan","Wen-Yi Tong","Yuan-Yuan Zhang","Bin-Bin Chen","Ni Zhong","Ping-Hua Xiang","Chun-Gang Duan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-31T13:58:33Z","doi":"10.1126/sciadv.adk9928","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1108/ir-05-2024-0203","name":"The role of neuromorphic and biomimetic sensors","source":"crossref","abstract":"Purpose The purpose of this paper is to provide details of biomimetic and neuromorphic sensor research and developments and discuss their applications in robotics. Design/methodology/approach Following a short introduction, this first provides examples of recent biomimetic gripping and sensing skin research and developments. It then considers neuromorphic vision sensing technology and its potential robotic applications. Finally, brief conclusions are drawn. Findings Biomimetics aims to exploit mechanisms, structures and signal processing techniques which occur in the natural world. Biomimetic sensors and control techniques can impart robots with a range of enhanced capabilities such as learning, gripping and multidimensional tactile sensing. Neuromorphic vision sensors offer several key operation benefits over conventional frame-based imaging techniques. Robotic applications are still largely at the research stage but uses are anticipated in enhanced safety systems in autonomous vehicles and in robotic gripping. Originality/value This illustrates how tactile and imaging sensors based on biological principles can contribute to imparting robots with enhanced capabilities.","url":"https://doi.org/10.1108/ir-05-2024-0203","authors":["Rob Bogue"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-19T01:31:10Z","doi":"10.1108/ir-05-2024-0203","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1063/5.0205429","name":"Double perovskite Bi2FeMnO6/TiO2 thin film heterostructure device for neuromorphic computing","source":"crossref","abstract":"Multiferroic materials have important research significance in the fields of magnetic random-access memory, ferroelectric random-access memory, resistive random-access memory, and neuromorphic computing devices due to their excellent and diverse physical properties. In this work, a solution of Bi2FeMnO6 was prepared using a solution-based method, and an Au/Bi2FeMnO6/TiO2 heterostructure device was fabricated on a Si substrate. X-ray diffraction and transmission electron microscopy data indicate that the Bi2FeMnO6 films have hexagonal R3c symmetry structures. The Bi2FeMnO6 film exhibits ferroelectricity with a fine remanent polarization. In addition, the Bi2FeMnO6-based devices have excellent switching ratios of 6.37 × 105. A larger switching ratio can provide a multi-resistance state for the device, which is beneficial for the simulation of synapses. Hence, it effectively emulates excitatory postsynaptic currents, paired-pulse facilitation, and long-term plasticity of synapses and achieves recognition accuracy of 95% in neuromorphic computing. We report a promising material for the development of various nonvolatile memories and neuromorphic synaptic devices.","url":"https://doi.org/10.1063/5.0205429","authors":["Dong-Liang Li","Wen-Min Zhong","Xin-Gui Tang","Qin-yu He","Yan-Ping Jiang","Qiu-Xiang Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-17T05:48:29Z","doi":"10.1063/5.0205429","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1039/d4mh00675e","name":"Leveraging volatile memristors in neuromorphic computing: from materials to system implementation","source":"crossref","abstract":"This review explores various mechanisms enabling threshold switching in volatile memristors and introduces recent progress in the implementation of neuromorphic computing systems based on these mechanisms.","url":"https://doi.org/10.1039/d4mh00675e","authors":["Taehwan Moon","Keunho Soh","Jong Sung Kim","Ji Eun Kim","Suk Yeop Chun","Kyungjune Cho","J. Joshua Yang","Jung Ho Yoon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-19T20:41:00Z","doi":"10.1039/d4mh00675e","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1021/acsnano.4c05137","name":"Volatile and Nonvolatile Programmable Iontronic Memristor with Lithium Imbued TiO<sub><i>x</i></sub> for Neuromorphic Computing Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acsnano.4c05137","authors":["Rabiul Islam","Yu Shi","Gabriel Vinicius de Oliveira Silva","Manoj Sachdev","Guo-Xing Miao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-07T14:27:02Z","doi":"10.1021/acsnano.4c05137","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1021/acsaelm.5c01300","name":"Array-Integrated Memristor with an Interference-Suppressed Pulse Scheme for Multibit Neuromorphic and Edge Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acsaelm.5c01300","authors":["Minseo Noh","Yongjin Byun","Gimun Kim","Junhyeok Park","Sungjoon Kim","Sungjun Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-26T17:13:41Z","doi":"10.1021/acsaelm.5c01300","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.3390/electronics13163203","name":"Unsupervised Classification of Spike Patterns with the Loihi Neuromorphic Processor","source":"crossref","abstract":"A long-standing research goal is to develop computing technologies that mimic the brain’s capabilities by implementing computation in electronic systems directly inspired by its structure, function, and operational mechanisms, using low-power, spike-based neural networks. The Loihi neuromorphic processor provides a low-power, large-scale network of programmable silicon neurons for brain-inspired artificial intelligence applications. This paper exploits the Loihi processors and a theory-guided methodology to enable unsupervised learning of spike patterns. Our method ensures efficient and rapid selection of the network’s hyperparameters, enabling the neuromorphic processor to generate attractor states through real-time unsupervised learning. Precisely, we follow a fast design process in which we fine-tune network parameters using mean-field theory. Moreover, we measure the network’s learning ability regarding its error correction and pattern completion aptitude. Finally, we observe the dynamic energy consumption of the neuron cores for each millisecond of simulation equal to 23 μJ/time step during the learning and recall phase for four attractors composed of 512 excitatory neurons and 256 shared inhibitory neurons. This study showcases how large-scale, low-power digital neuromorphic processors can be quickly programmed to enable the autonomous generation of attractor states. These attractors are fundamental computational primitives that theoretical analysis and experimental evidence indicate as versatile and reusable components suitable for a wide range of cognitive tasks.","url":"https://doi.org/10.3390/electronics13163203","authors":["Ryoga Matsuo","Ahmed Elgaradiny","Federico Corradi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-13T06:02:37Z","doi":"10.3390/electronics13163203","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1109/intcec61833.2024.10603084","name":"HPCNeuroNet: Advancing Neuromorphic Audio Signal Processing with Transformer-Enhanced Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/intcec61833.2024.10603084","authors":["Hiruna Vishwamith","Murat Isik","I. Can Dikmen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-30T13:48:20Z","doi":"10.1109/intcec61833.2024.10603084","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1109/icnc64304.2024.10987738","name":"DEGAN: A Deep Learning Model for SAR Image Segmentation in Aquacultural Raft Monitoring","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987738","authors":["Shuo Lian","Jun Wang","Min Han","Jianchao Fan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987738","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1088/1361-6528/ad2ee3","name":"Flexible light-stimulated artificial synapse based on detached (In,Ga)N thin film for neuromorphic computing","source":"crossref","abstract":"Abstract Because of wide range of applications, the flexible artificial synapse is an indispensable part for next-generation neural morphology computing. In this work, we demonstrate a flexible synaptic device based on a lift-off (In,Ga)N thin film successfully. The synaptic device can mimic the learning, forgetting, and relearning functions of biological synapses at both flat and bent states. Furthermore, the synaptic device can simulate the transition from short-term memory to long-term memory successfully under different bending conditions. With the high flexibility, the excitatory post-synaptic current of the bent device only shows a slight decrease, leading to the high stability. Based on the experimental conductance for long-term potentiation and depression, the simulated three-layer neural network can achieve a high recognition rate up to 90.2%, indicating that the system comprising of flexible synaptic devices could have a strong learning-memory capability. Therefore, this work has a great potential for the development of wearable intelligence devices and flexible neuromorphic systems.","url":"https://doi.org/10.1088/1361-6528/ad2ee3","authors":["Qianyi Zhang","Binbin Hou","Jianya Zhang","Xiushuo Gu","Yonglin Huang","Renjun Pei","Yukun Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-18T10:55:45Z","doi":"10.1088/1361-6528/ad2ee3","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1088/2634-4386/ad3a96","name":"An organic artificial soma for spatio-temporal pattern recognition via dendritic integration","source":"crossref","abstract":"Abstract A novel organic neuromorphic device performing pattern classification is presented and demonstrated. It features an artificial soma capable of dendritic integration from three pre-synaptic neurons. The time-response of the interface between electrolytic solutions and organic mixed ionic-electronic conductors is proposed as the sole computational feature for pattern recognition, and it is easily tuned in the organic dendritic integrator by simply controlling electrolyte ionic strength. The classifier is benchmarked in speech-recognition experiments, with a sample of 14 words, encoded either from audio tracks or from kinematic data, showing excellent discrimination performances in a planar, miniaturizable, fully passive device, designed to be promptly integrated in more complex architectures where on-board pattern classification is required.","url":"https://doi.org/10.1088/2634-4386/ad3a96","authors":["Michele Di Lauro","Federico Rondelli","Anna De Salvo","Alessandro Corsini","Matteo Genitoni","Pierpaolo Greco","Mauro Murgia","Luciano Fadiga","Fabio Biscarini"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-04T22:26:06Z","doi":"10.1088/2634-4386/ad3a96","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1002/marc.202400172","name":"Building Uniformly Structured Polymer Memristors via a 2D Conjugation Strategy for Neuromorphic Computing","source":"crossref","abstract":"Abstract Polymer memristors represent a highly promising avenue for the advancement of next‐generation computing systems. However, the intrinsic structural heterogeneity characteristic of most polymers often results in organic polymer memristors displaying erratic resistive switching phenomena, which in turn lead to diminished production yields and compromised reliability. In this study, a 2D conjugated polymer, named PBDTT‐BPQTPA, is synthesized by integrating the coplanar bis (thiophene)‐4,8‐dihydrobenzo[1,2‐b:4,5‐b]dithiophene (BDTT) as an electron‐donating unit with a quinoxaline derivative serving as an electron‐accepting unit. The incorporation of triphenylamine groups at the quinoxaline termini significantly enhances the polymer's conjugation and planarity, thereby facilitating more efficient charge transport. The fabricated polymer memristor with the structure of Al/PBDTT‐BPQTPA/ITO exhibits typical non‐volatile resistive switching behavior under high voltage conditions, along with history‐dependent memristive properties at lower voltages. The unique memristive behavior of the device enables the simulation of synaptic enhancement/inhibition, learning algorithms, and memory operations. Additionally, the memristor demonstrates its capability for executing logical operations and handling decimal calculations. This study offers a promising and innovative approach for the development of artificial neuromorphic computing systems.","url":"https://doi.org/10.1002/marc.202400172","authors":["Jinyong Li","Fei Fan","Xin Fu","Mingxing Liu","Yu Chen","Bin Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-17T05:30:02Z","doi":"10.1002/marc.202400172","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1149/ma2024-01572995mtgabs","name":"Natural Organic Honey-CNT Memristor Based Artificial Synaptic Devices for Sustainable Neuromorphic System","source":"crossref","abstract":"Neuromorphic computing is considered to have the potential to overcome the limitations of traditional von Neumann architecture due to its high efficiency, low energy consumption, and fault-tolerance. Hardware components that can emulate the synaptic plasticity of neurons, i.e. artificial synaptic devices, are required by neuromorphic systems. New devices have been examined for such components, such as phase-change artificial synapse, ferroelectric artificial synapse, and memristor synapses. Among them, memristor, a two-terminal metal-insulator-metal structure that are analogous to a biological synapse with presynaptic neuron (top electrode), postsynapticneuron (bottom electrode), and synaptic cleft (memristive film), is a promising device technology because of its tunable resistance, scalability, 3D integration compatibility, low power consumption, and relatively high speed. In contrary to inorganic materials such as metal oxides, natural organic materials have attracted interest to form the memristive layer because they are renewable, biodegradable, sustainable, biocompatible, and environmentally friendly. In this paper, honey solution embedded with carbon nanotubes (CNTs) was processed into the memristive layer by a low cost solution-based process, with synaptic plasticity of the final honey-CNT memristors characterized, including forget and relearn, spike-rate-dependent plasticity, spike-voltage-dependent plasticity, short-term to long-term memory transition, paired pulse facilitation, and spatial supra-linear summation behaviors. The successful emulation of these essential biological synaptic behaviors demonstrates the potential of honey-CNT memristors as a viable hardware component in neuromorphic computing systems.","url":"https://doi.org/10.1149/ma2024-01572995mtgabs","authors":["Zoe Templin","Feng Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-19T15:51:35Z","doi":"10.1149/ma2024-01572995mtgabs","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1002/aelm.202400347","name":"Self‐Selective Crossbar Synapse Array with n‐ZnO/p‐NiO<sub>x</sub>/n‐ZnO Structure for Neuromorphic Computing","source":"crossref","abstract":"Abstract Artificial synapse devices are essential elements for highly energy‐efficient neuromorphic computing. They are implemented as crossbar array architecture, where highly selective synaptic weight updates for training and sneak leakage‐free inference operations are required. In this study, self‐selective bipolar artificial synapse device is proposed with n‐ZnO/p‐NiO x /n‐ZnO heterojunction, and its analog synapse operation with high selectivity is demonstrated in 32 × 32 crossbar array architecture without the aid of selector devices. The built‐in potential barrier at p‐NiO x /n‐ZnO junction and the Zener tunneling effect provided nonlinear current–voltage characteristics at both voltage polarities for self‐selecting function for synaptic potentiation and depression operations. Voltage‐driven redistribution of oxygen ions inside n–p–n oxide structure, evidenced by x‐ray photoelectron spectroscopy, modulated the distribution of oxygen vacancies in the layers and consequent conductance in an analog manner for the synaptic weight update operation. It demonstrates that the proposed n–p–n oxide device is a promising artificial synapse device implementing self‐selectivity and analog synaptic weight update in a crossbar array architecture for neuromorphic computing.","url":"https://doi.org/10.1002/aelm.202400347","authors":["Peter Hayoung Chung","Jiyeon Ryu","Daejae Seo","Dwipak Prasad Sahu","Minju Song","Junghwan Kim","Tae‐Sik Yoon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-31T04:28:12Z","doi":"10.1002/aelm.202400347","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1038/s41467-024-52259-9","name":"Neuromorphic intermediate representation: A unified instruction set for interoperable brain-inspired computing","source":"europepmc","abstract":"Abstract Spiking neural networks and neuromorphic hardware platforms that simulate neuronal dynamics are getting wide attention and are being applied to many relevant problems using Machine Learning. Despite a well-established mathematical foundation for neural dynamics, there exists numerous software and hardware solutions and stacks whose variability makes it difficult to reproduce findings. Here, we establish a common reference frame for computations in digital neuromorphic systems, titled Neuromorphic Intermediate Representation (NIR). NIR defines a set of computational and composable model primitives as hybrid systems combining continuous-time dynamics and discrete events. By abstracting away assumptions around discretization and hardware constraints, NIR faithfully captures the computational model, while bridging differences between the evaluated implementation and the underlying mathematical formalism. NIR supports an unprecedented number of neuromorphic systems, which we demonstrate by reproducing three spiking neural network models of different complexity across 7 neuromorphic simulators and 4 digital hardware platforms. NIR decouples the development of neuromorphic hardware and software, enabling interoperability between platforms and improving accessibility to multiple neuromorphic technologies. We believe that NIR is a key next step in brain-inspired hardware-software co-evolution, enabling research towards the implementation of energy efficient computational principles of nervous systems. NIR is available at neuroir.org","url":"https://doi.org/10.1038/s41467-024-52259-9","authors":["Jens E. Pedersen","Steven Abreu","Matthias Jobst","Gregor Lenz","Vittorio Fra","Felix Christian Bauer","Dylan Richard Muir","Peng Zhou","Bernhard Vogginger","Kade Heckel","Gianvito Urgese","Sadasivan Shankar"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41467-024-52259-9","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.2139/ssrn.4854559","name":"Ternary Spike-Based Neuromorphic Signal Processing System","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4854559","authors":["shuai wang","Dehao Zhang","Ammar Belatreche","Yichen Xiao","Hongyu Qing","Wenjie Wei","Malu Zhang","Yang Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-05T03:20:41Z","doi":"10.2139/ssrn.4854559","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1134/s105466182470086x","name":"Decoding Neuromorphic Codes of Images in the Marr’s Paradigm","source":"crossref","abstract":"","url":"https://doi.org/10.1134/s105466182470086x","authors":["Viacheslav Antsiperov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-06T07:23:13Z","doi":"10.1134/s105466182470086x","addedAt":"2026-09-01T01:48:20.900Z","updatedAt":"2026-09-01T01:48:20.900Z"},{"id":"doi:10.1103/physreve.92.052134","name":"Neuromorphic behavior in percolating nanoparticle films","source":"crossref","abstract":"","url":"https://doi.org/10.1103/physreve.92.052134","authors":["Shawn Fostner","Simon A. Brown"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-11-23T12:09:06Z","doi":"10.1103/physreve.92.052134","addedAt":"2026-09-01T01:48:21.715Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.21203/rs.3.rs-1205135/v1","name":"Neuromorphic Chip Integrated with an LSI and Amorphous-metal-oxide Semiconductor Thin-film Synapse Devices","source":"crossref","abstract":"Abstract Artificial intelligences are promising in future societies, and neural networks are typical technologies with the advantages such as self-organization, self-learning, parallel distributed computing, and fault tolerance, but their size and power consumption are large. Neuromorphic systems are biomimetic systems from the hardware level, with the same advantages as living brains, especially compact size, low power, and robust operation, but some well-known ones are non-optimized systems, so the above benefits are only partially gained, for example, machine learning is processed elsewhere to download fixed parameters. To solve these problems, we are researching neuromorphic systems from various viewpoints. In this study, a neuromorphic chip integrated with an LSI and amorphous-metal-oxide semiconductor (AOS) thin-film synapse devices has been developed. The neuron elements are digital circuit, which are made in an LSI, and the synapse devices are analog devices, which are made of the AOS thin film and directly integrated on the LSI. This is the world's first hybrid chip where neuron elements and synapse devices of different functional semiconductors are integrated, and local autonomous learning is utilized, which becomes possible because the AOS thin film can be deposited without heat treatment and there is no damage to the underneath layer, and has all advantages of neuromorphic systems.","url":"https://doi.org/10.21203/rs.3.rs-1205135/v1","authors":["Mutsumi Kimura","Yuki Shibayama","Yasuhiko Nakashima"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-01-03T19:02:36Z","doi":"10.21203/rs.3.rs-1205135/v1","addedAt":"2026-09-01T01:48:21.715Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1039/d5tc01475a/v1/review3","name":"Review for \"Improved Neuromorphic Functionality in Organic Electrochemical Transistors Using Crosslinked-Polyvinyl alcohol for Fast Ion Transport and its Application to Pavlovian Transistors\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5tc01475a/v1/review3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-11T21:06:55Z","doi":"10.1039/d5tc01475a/v1/review3","addedAt":"2026-09-01T01:48:21.715Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1039/d6nh00013d/v2/review1","name":"Review for \"Revealing the Potential of 2D WS2 Memristors as an Artificial Synapse with Resilient Gradual Behavior at High Temperatures for Neuromorphic Applications\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d6nh00013d/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-07T21:14:19Z","doi":"10.1039/d6nh00013d/v2/review1","addedAt":"2026-09-01T01:48:21.715Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1039/d6nh00013d/v1/review2","name":"Review for \"Revealing the Potential of 2D WS2 Memristors as an Artificial Synapse with Resilient Gradual Behavior at High Temperatures for Neuromorphic Applications\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d6nh00013d/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-07T21:14:19Z","doi":"10.1039/d6nh00013d/v1/review2","addedAt":"2026-09-01T01:48:21.715Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1142/9789811290084_bmatter","name":"BACK MATTER","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789811290084_bmatter","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-26T02:06:27Z","doi":"10.1142/9789811290084_bmatter","addedAt":"2026-09-01T01:48:21.715Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.21203/rs.3.rs-3412574/v1","name":"Recurrent models of orientation selectivity enable robust early-vision  processing in mixed-signal neuromorphic hardware","source":"crossref","abstract":"Abstract Mixed signal analog/digital neuromorphic circuits represent an ideal medium for reproducing the dynamics of biological neural systems in real-time with bio-physically realistic dynamics. However, similar to their biological counterparts, these circuits have limited resolution and are affected by a high degree of variability. Considering this, we developed a recurrent spiking neural network that implements a faithful model of the retinocortical visual pathway to reliably produce Gabor-like receptive fields tuned to visual stimuli with specific orientation and spatial frequency properties. Specifically, we developed a neuromorphic visual system comprising a Dynamic Vision Sensor that emulates the transient pathway of real retinas and a mixed-signal Dynamic Neuromorphic Asynchronous Processor with adaptive exponential integrate-and-fire neurons and dynamic synapses and mapped the recurrent network model on it to produces the desired orientation and spatial frequency tuning responses. Compared to alternative feed-forward schemes, the model developed gives rise to robust highly structured Gabor-like receptive fields of any phase symmetry, optimizing the hardware resources available in terms of synaptic connections. We present experimental results using both synthetic and natural images validating the model with its hardware implementations.","url":"https://doi.org/10.21203/rs.3.rs-3412574/v1","authors":["Silvio P. Sabatini","Valentina Baruzzi","Giacomo Indiveri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-11T05:50:13Z","doi":"10.21203/rs.3.rs-3412574/v1","addedAt":"2026-09-01T01:48:21.715Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.21203/rs.3.rs-6567951/v1","name":"Neural networks for socio-labor regulation: a neuromorphic approach to human-centric AI in urban economies","source":"crossref","abstract":"Abstract This study investigates the implementation and future potential of neural networks for socio-labor regulation within the urban economies of BRICS megacities, emphasizing a human-centric AI approach. Analysis reveals significant disparities in AI development across these urban centers, with Beijing and Shanghai leading in investment, while Moscow ranks third among all analyzed cities with an AI investment of $620 million, contributing to the growing global urban AI landscape where worldwide smart city spending is projected to reach hundreds of billions of dollars. The research examines key indicators of AI adoption, such as the number of startups and the percentage of companies utilizing AI solutions in these major cities. Specifically, Bangalore stands out with 320 AI startups and 58% of companies implementing AI, while in Russia, Moscow reports 230 startups and 48% company adoption, reflecting varying rates of AI integration within urban business ecosystems globally where the average AI adoption rate for enterprises is still below 30% according to some reports. Beyond general AI adoption, the study analyzes the deployment and effectiveness of neuromorphic AI approaches specifically for socio-labor regulation systems. Current data indicates uneven deployment of neuromorphic labor systems across BRICS megacities, with Shanghai showing a high deployment score of 9.5/10, significantly ahead of cities like Durban at 5.2/10, highlighting the uneven global progress in applying advanced AI for workforce management, including in Russian cities like Moscow with a 7.8/10 deployment score, as the worldwide market for AI in HR is rapidly expanding towards billions. Key metrics examined for these specialized systems include AI-driven job matching efficiency, the number of neural network workforce training programs, and labor market prediction accuracy. The study concludes that achieving effective and ethical socio-labor regulation through AI requires a human-centric approach that addresses disparities and integrates technological, social, and psychological considerations for inclusive urban development. Participation in the article: Irina Karabulatova - general editing, writing the \"introduction\" and \"discussion\" sections; Olga Ergunova - project idea, writing the \"results\" section, working on models (Fig.2-3), compiling tables; Andrey Somov - working on the project methodology and writing the code.","url":"https://doi.org/10.21203/rs.3.rs-6567951/v1","authors":["Irina Karabulatova","Olga Ergunova","Andrey Somov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-23T03:06:29Z","doi":"10.21203/rs.3.rs-6567951/v1","addedAt":"2026-09-01T01:48:21.715Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.1142/9789811290084_fmatter","name":"FRONT MATTER","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789811290084_fmatter","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-26T02:06:27Z","doi":"10.1142/9789811290084_fmatter","addedAt":"2026-09-01T01:48:21.715Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.21203/rs.3.rs-1061301/v1","name":"A Neuromorphic Spiking Neural Network Detects Epileptic High Frequency Oscillations in the Scalp EEG","source":"preprints","abstract":"Abstract Background: Interictal High Frequency Oscillations (HFO) are measurable in scalp EEG. This has aroused interest in investigating their potential as biomarkers of epileptogenesis, seizure propensity, disease severity, and treatment response. The demand for therapy monitoring in epilepsy has kindled interest in compact wearable electronic devices for long- term EEG recording. Spiking neural networks (SNN) have been shown to be optimal architectures for being embedded in compact low-power signal processing hardware. Methods: We analyzed 20 scalp EEG recordings from 11 patients with pediatric focal lesional epilepsy. We designed a custom SNN to detect events of interest (EoI) in the 80-250 Hz ripple band and reject artifacts in the 500-900 Hz band. Results: We identified the optimal SNN parameters to automatically detect EoI and reject artifacts. The occurrence of HFO thus detected was associated with active epilepsy with 80% accuracy. The HFO rate mirrored the decrease in seizure frequency in 8 patients ( p = 0.0047). Overall, the HFO rate correlated with seizure frequency (rho = 0.83, p &lt; 0.0001, Spearman’s correlation). Conclusions: The fully automated SNN detected clinically relevant HFO in the scalp EEG. This is a further step towards non-invasive epilepsy monitoring with a low-power wearable device.","url":"https://doi.org/10.21203/rs.3.rs-1061301/v1","authors":["Karla Burelo","Georgia Ramantani","Giacomo Indiveri","Johannes Sarnthein"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.21203/rs.3.rs-1061301/v1","addedAt":"2026-09-01T01:48:21.715Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1088/1361-665x/ae8226","name":"Beyond biomimicry: a review of next-generation flexible tactile sensing from viscoelastic material design to neuromorphic computing","source":"crossref","abstract":"Abstract Flexible tactile sensors have emerged as vital transduction interfaces for human–machine symbiosis and soft robotics. Despite significant advances, two persistent bottlenecks have hindered their practical viability. At the material level, the intrinsic viscoelasticity of polymeric matrices enforces stringent trade-offs among pressure sensitivity, output linearity, and loading–unloading hysteresis. At the system level, the conventional spatial separation of sensory acquisition from signal processing incurs considerable bandwidth and energy overheads when handling high-dimensional, unstructured analog data. To address these limitations, this review proposes a vertically integrated co-design framework that systematically couples material engineering, device architecture, and neuromorphic algorithm design. At the material-device level, we survey structural strategies, including dynamic network construction, rigid-phase anchoring, and topological interlocking, aimed at suppressing microscale viscoelastic relaxation and preventing interfacial delamination at mechanically heterogeneous junctions. Complementarily, alternating current excitation protocols have been evaluated to mitigate the electrochemical degradation intrinsic to iontronic architectures. We argue that the concurrent resolution of these mechanical and electrochemical instabilities provides the drift-free analog baseline essential for downstream neuromorphic computation, a cross-domain connection that has received limited systematic attention in the existing literature. Building on this stabilized platform, we further elucidate how intrinsic material dynamics, notably ferroelectric polarization switching and ion migration, can serve as native computational primitives, effectively linking material engineering and algorithm-design layers within the proposed framework. The coupling of these material-embedded dynamics with spiking neural networks enables in situ temporal encoding, whereby continuous mechanical stimuli are transduced into sparse event-driven spike trains, circumventing the von Neumann bottleneck. This co-design perspective offers a pathway for flexible tactile systems to evolve beyond passive structural biomimicry toward autonomous cognitive interfaces with real-time edge-localized adaptability.","url":"https://doi.org/10.1088/1361-665x/ae8226","authors":["Jun Li","Yongcheng Ji","Lipan Xin","Linan Li","Chuanwei Li","Zhiyong Wang","Shibin Wang","Lei Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-24T22:56:10Z","doi":"10.1088/1361-665x/ae8226","addedAt":"2026-09-01T01:48:21.715Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.3410/f.740618017.793588819","name":"Faculty Opinions recommendation of Learning function from structure in neuromorphic networks.","source":"crossref","abstract":"","url":"https://doi.org/10.3410/f.740618017.793588819","authors":["Taro Toyoizumi","Qianyuan Tang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-10-13T14:29:02Z","doi":"10.3410/f.740618017.793588819","addedAt":"2026-09-01T01:48:21.715Z","updatedAt":"2026-09-01T01:48:21.715Z"},{"id":"doi:10.21203/rs.3.rs-780916/v1","name":"The neuromorphic Mosaic: re-configurable in-memory small-world graphs","source":"preprints","abstract":"Abstract Thanks to their non-volatile and multi-bit properties, memristors have been extensively used as synaptic weight elements in neuromorphic architectures. However, their use to define and re-program the network connectivity has been overlooked. Here, we propose, implement and experimentally demonstrate Mosaic, a neuromorphic architecture based on a systolic array of memristor crossbars. For the first time, we use distributed non-volatile memristors not only for computation, but also for routing (i.e., to define the network connectivity). Mosaic is particularly well-suited for the implementation of re-configurable small-world graphical models, with dense local and sparse global connectivity - found extensively in the brain. We mathematically show that, as the networks scale up, the Mosaic requires less memory than in conventional memristor approaches. We map a spiking recurrent neural network on the Mosaic to solve an Electrocardiogram (ECG) anomaly detection task. While the performance is either equivalent or better than software models, the advantage of the Mosaic was clearly seen in respective one and two orders of magnitude reduction in energy requirements, compared to a micro-controller and address-event representation-based processor. Mosaic promises to open up a new approach to designing neuromorphic hardware based on graph-theoretic principles with less memory and energy.","url":"https://doi.org/10.21203/rs.3.rs-780916/v1","authors":["Thomas Dalgaty","Filippo Moro","Alessio De Pra","Giacomo Indiveri","Elisa Vianello","Melika Payvand"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.21203/rs.3.rs-780916/v1","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.1007/978-3-031-98364-1_18","name":"A Review of Neuromorphic Computing and Its Potential for Enhancing Digital Twin Technology","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-98364-1_18","authors":["Vijayakumar Kempuraj","C. Lakshmi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T22:32:30Z","doi":"10.1007/978-3-031-98364-1_18","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1002/advs.77116","name":"Neuromorphic Devices and Computing for Sensing, Memory, and Control.","source":"europepmc","abstract":"Neuromorphic devices are bioinspired electronic systems that mimic key structures and functions of the nervous system, enabling integration and communication between living tissues and machines. This review examines how neuromorphic devices and computing are designed to emulate the structure, organization, and function of the nervous system. For neuromorphic devices, we first describe strategies that mimic subcellular neural functions. We then highlight how device architecture recapitulates biological topology from subcellular components to brain networks. We next summarize how neuromorphic devices emulate sensory and sensorimotor (sensory-modulation) neural circuits. For neuromorphic computing, we review recent advances in artificial and biological neuromorphic computing, including spiking neural networks, bioinspired learning algorithms, and applications. We also discuss emerging biohybrid intelligence systems leveraging two- and three-dimensional biological networks as computational units. Finally, we outline key challenges, potential milestones, and future directions.","url":"https://doi.org/10.1002/advs.77116","authors":["Zhengguang Zhu","Nicholas Schaffer","Xiao Yang"],"tags":["Neuromorphic engineering","Computer science","Key (lock)","Computer architecture","Artificial neural network"],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.77116","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"doi:10.3390/ma19153234","name":"Flexible Neuromorphic Memristors: From Mechanisms to Applications.","source":"europepmc","abstract":"The von Neumann architecture, due to the physical separation between memory and processor, has limited the development of data-intensive applications. Neuromorphic computing technologies inspired by the brain's parallel and event-driven operation mechanisms have enabled low-power in-memory computing. Memristors with tunable conductance can emulate biological synapses, while flexible memristors further offer mechanical flexibility, making them suitable for wearable electronics and intelligent sensing systems. This review systematically summarizes the switching mechanisms of flexible neuromorphic memristors, including conductive filaments, interface effects, ferroelectricity, phase change, and multiple synergistic mechanisms. It categorically discusses natural and bio-derived materials, synthetic organic/polymer materials, and inorganic functional materials, and introduces strategies for enhancing flexibility. The article also covers device architectures such as sandwich structures, crossbar arrays, and fiber-based textile structures, along with low-temperature fabrication techniques. Finally, it reviews recent advances in neuromorphic computing, in-memory computing, biomimetic sensing, and biomedical wearable systems. Challenges related to mechanical stability and device uniformity are analyzed, and future directions toward self-healing materials and integrated sensing-storage-computing systems are outlined. This comprehensive review bridges the gap between material innovation and system-level integration in flexible neuromorphic memristors, providing a valuable roadmap for accelerating the development of next-generation wearable artificial intelligence, edge computing, and bio-integrated electronic technologies.","url":"https://doi.org/10.3390/ma19153234","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/ma19153234","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/adma.74278","name":"Low-Dimensional Perovskites for Neuromorphic Vision Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.74278","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.74278","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1038/s44385-026-00074-w","name":"Towards neuromorphic neurotechnologies: integrating brain-inspired computing with brain-computer interfaces.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s44385-026-00074-w","authors":["Hoda Fares","Margherita Ronchini","Milad Zamani","Hooman Farkhani","Michela Chiappalone","Emre Neftci","Farshad Moradi"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s44385-026-00074-w","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1080/14686996.2026.2688751","name":"Kesterite-based optoelectronic synaptic memristors: a mini-review on material design and neuromorphic application.","source":"europepmc","abstract":"","url":"https://doi.org/10.1080/14686996.2026.2688751","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1080/14686996.2026.2688751","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1016/j.isci.2026.117083","name":"Organic semiconductor materials for neuromorphic and bioelectronic systems design rules and applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.isci.2026.117083","authors":["Le Phuong Long","Vo Thi Kien Hao","Nguyen Thi Nu"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.isci.2026.117083","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/smll.74180","name":"Self-Powered Neuromorphic Systems Based on Tribotronics Synaptic Devices.","source":"europepmc","abstract":"ABSTRACT Artificial synaptic devices based on field‐effect transistors (FETs) are essential building blocks for neuromorphic computing systems that emulate the signal processing and learning capabilities of biological neural networks. However, most FET‐based synaptic devices depend on external power sources, which increases energy consumption and limits their applications in self‐powered systems. Triboelectric nanogenerators (TENGs) have recently emerged as promising candidates for self‐powered neuromorphic systems that simultaneously harvest ambient mechanical energy and modulate synaptic signals, thereby enabling energy‐efficient neuromorphic operation. This review summarizes recent advances in TENG‐driven three‐terminal artificial synaptic devices, focusing on their device architectures, operating principles, and synaptic functionalities. It discusses the unique electrical characteristics of TENG outputs, including high internal impedance and pulsed voltage signals, and their correlation with synaptic behaviors such as excitatory and inhibitory postsynaptic currents, nonvolatile weight retention, and frequency‐ and time‐dependent plasticity. In addition, it explores the emerging applications of these devices in tactile sensing, human–machine interaction, auditory perception, and multimodal neuromorphic systems. Finally, the review highlights the current challenges, including signal stability, impedance matching, multisensory integration, and power consumption, and discusses the potential strategies to address these limitations, along with the future perspectives to advance the development of next‐generation self‐powered neuromorphic computing systems.","url":"https://doi.org/10.1002/smll.74180","authors":["Kumar Shrestha","Mohammad Karbalaei Akbari","Alireza Pourvahabi Anbari","Puran Pandey","Serge Zhuiykov"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.74180","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acsnano.6c08097","name":"Reconfigurable Nonvolatile Photodetectors for Brain-Inspired Vision.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.6c08097","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsnano.6c08097","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1039/d6mh00693k","name":"Ion-modulated oxide-based neuromorphic transistors for spatiotemporal information processing.","source":"europepmc","abstract":"Unlike energy-intensive von Neumann systems, the human brain efficiently processes complex spatiotemporal information utilizing slow, dissipative ionic dynamics. To emulate this, ion-modulated oxide-based neuromorphic transistors have emerged as a compelling hardware platform, because they combine intrinsic ionic time constants with the scalability and functional versatility of oxide electronics. This review establishes a physical and architectural roadmap for spatiotemporal information processing in these devices by linking biological ionic mechanisms to modulation pathways, transistor structures, and representative computing functions. We show how ion-modulated oxide transistors evolve from basic temporal processing units to multi-terminal sensory fusion elements and ultimately to array-level adaptive computing hardware. Finally, we highlight the key bottlenecks and actionable future directions for achieving task-matched ionic dynamics, scalable integration, and real-time bio-inspired spatiotemporal intelligence.","url":"https://doi.org/10.1039/d6mh00693k","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d6mh00693k","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/advs.202600007","name":"Ferroelectric Devices for In-Memory and In-Sensor Computing.","source":"europepmc","abstract":"Inspired by biological neural and sensory systems, the in-memory computing and in-sensor computing paradigms have emerged, which integrate computation with memory and processing with sensor respectively, offering a promising solution to address latency and power bottlenecks of traditional von Neumann architectures. Neuromorphic devices such as artificial synapse and neuromorphic sensors are the core components of these innovative computing paradigms. Among various types of neuromorphic devices, ferroelectric devices can not only emulate synaptic weight updates via electric-field-induced dynamic modulation of conductance, but also sense and process multimodal physical stimuli, such as light, mechanical force, and heat. Such multifunctionality enables the integration of sensing, memory, and computation at the device level, positioning ferroelectric devices as an ideal platform for neuromorphic computing and sensing systems. Herein, we present a systematic review of ferroelectric neuromorphic devices for in-memory computing and in-sensor computing. The applications of ferroelectric devices as artificial synapses in in-memory computing are summarized. Furthermore, we examine the applications of ferroelectric devices as sensing elements in in-sensor computing systems and summarize the latest research advances in these fields. Finally, this review outlines the key challenges faced by ferroelectric neuromorphic devices and proposes future development directions to promote their practical applications.","url":"https://doi.org/10.1002/advs.202600007","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.202600007","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1016/j.scib.2026.06.005","name":"Two-terminal ferroelectric memristors: material innovation, mechanistic breakthroughs, new opportunities for intelligent computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.scib.2026.06.005","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.scib.2026.06.005","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.3390/gels12070656","name":"Soft Iontronic Diodes: Materials, Mechanisms, and Progress.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/gels12070656","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/gels12070656","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.3390/biomimetics11070499","name":"Liquid Metal Biomimicry: Bridging Fluidity and Biological Adaptability.","source":"europepmc","abstract":"Liquid metals, particularly gallium-based alloys, uniquely combine fluidic compliance with metallic conductivity, which makes them ideal candidates for biomimetic design. Rather than treating biomimicry as the mere imitation of biological forms, we argue that liquid metal biomimicry should be understood as the realization of biological strategies through the intrinsic physics of fluidity and interfacial dynamics. This review organizes existing research within a hierarchical framework that couples physical liquidity, interface biology analogy, and functional emergence to explain how adaptive behaviors naturally arise from dynamic liquid metal systems. We examine representative systems across morphological and functional dimensions and contend that their true significance lies not in replicating nature but in addressing problems that conventional rigid materials cannot solve. Looking forward, we identify several transformative directions that collectively chart a roadmap toward truly intelligent and autonomous bioinspired systems. By bridging the physics of fluidity with the principles of biological adaptability, liquid metal biomimicry holds transformative potential for soft robotics, wearable electronics, neuromorphic computing, and biomedical engineering.","url":"https://doi.org/10.3390/biomimetics11070499","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/biomimetics11070499","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1038/s41563-026-02629-z","name":"Operando microscopy for neuromorphic hardware.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41563-026-02629-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41563-026-02629-z","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.3389/fncom.2026.1878543","name":"Representational recoding and capacity limits: a conceptual reinterpretation of Sidney Smith's experiment.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2026.1878543","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fncom.2026.1878543","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1016/j.ultras.2026.108206","name":"The convergence of surface acoustic wave technology and artificial intelligence.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.ultras.2026.108206","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.ultras.2026.108206","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1038/s43588-026-01012-x","name":"Computing inspired by the brain: a journey from algorithms to organoids.","source":"europepmc","abstract":"The human brain has long served as a blueprint for computation, guiding evolution from early symbolic systems to modern deep learning models. Despite these advances, traditional computing systems remain fundamentally limited in mirroring the remarkable flexibility, parallel processing and energy efficiency of the human brain. To address these limitations, neuromorphic computing was developed, which mimics the architecture and signaling behavior of biological neurons. Building on this foundation, a new frontier is now emerging-organoid intelligence (OI). OI uses lab-grown brain cellular structures, such as living neural organoids with electrical activity, synapse formation and primitive learning, as a substrate for computation. Here we trace the evolution of brain-inspired computing from symbolic logic systems to artificial neural networks, neuromorphic processors and finally biohybrid computers that incorporate living neural structures. We explore the transformative potential of OI along with the substantial technical, biological and ethical challenges it presents.","url":"https://doi.org/10.1038/s43588-026-01012-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s43588-026-01012-x","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acs.nanolett.6c00390","name":"Artificial Intelligence for Bioinspired Nanofluidic Iontronics.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.6c00390","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acs.nanolett.6c00390","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1126/science.aea2097","name":"Knowledge gaps for neuromorphic ionic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/science.aea2097","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1126/science.aea2097","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.3389/fncom.2026.1789388","name":"Editorial: Neuromorphic and deep learning paradigms for neural data interpretation and computational neuroscience.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2026.1789388","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fncom.2026.1789388","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1002/adma.202523562","name":"Neuromorphic Electronics for Intelligence Everywhere: Emerging Devices, Flexible Platforms, and Scalable System Architectures.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202523562","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202523562","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.3390/mi17080931","name":"Ferroelectric Hafnium Oxide for In-Memory Computing: Advancing Devices, Circuit Architectures, and System-Level Integration.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/mi17080931","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/mi17080931","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.3390/nano16120715","name":"Photosensing PUF from an Intrinsically Random SnTe Memristor for Image Encryption and Recognition.","source":"europepmc","abstract":"Physical unclonable function (PUF) based on intrinsic device randomness has emerged as promising hardware security primitives, yet combining secure encryption with neuromorphic recognition within a single device platform remains challenging. Here, we demonstrate a photosensing PUF based on an intrinsically random SnTe memristor capable of both image encryption and memristive neural network recognition. The SnTe memristor, fabricated with an In 2 O 3 :SnO 2 /SnTe/Nb:SrTiO 3 structure, exhibits stable resistive switching and stable retention exceeding 4000 s. Synaptic biomimetic behaviors including learning-experience emulation, short-term plasticity and long-term plasticity are also realized. Notably, the device displays pronounced optical sensitivity that produces stochastic photocurrent fluctuations originating from unavoidable device-to-device variations under illumination. By quantizing these random photocurrents, an encryption key stream is generated and utilized for image scrambling and diffusion. A memristive neural network is constructed to classify the encrypted images, achieving a recognition accuracy of 95.1% with a loss of 0.15 after 300 training epochs. This work establishes a viable pathway from intrinsic optical randomness to secure neuromorphic computing, highlighting the multifunctional potential of SnTe memristors in integrated hardware security and brain-inspired computation.","url":"https://doi.org/10.3390/nano16120715","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/nano16120715","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acs.langmuir.6c01178","name":"Ion-Track-Etched Membranes as Nanoionic Platforms: Fabrication, Nanoscale Ion Transport, and Device Applications─A Review.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.langmuir.6c01178","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acs.langmuir.6c01178","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/advs.202600042","name":"Advances and Perspectives in Graphene-Based Quantum Dots Enabled Neuromorphic Devices.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202600042","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.202600042","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.3390/ijms27167453","name":"Two-Dimensional Indium Selenide for Next-Generation Electronics.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/ijms27167453","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/ijms27167453","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1007/s11571-026-10470-y","name":"Redefining spiking neural networks through the lens of dynamical superspace.","source":"europepmc","abstract":"The convergence of neuroscience and artificial intelligence has positioned Spiking Neural Networks (SNNs) as one of the pivotal paradigms for future computing. However, the field faces a theoretical challenge: reconciling the mathematical clarity of static deep learning with the rich, non-equilibrium dynamics of biological circuits. We introduce the dynamical superspace, a framework that reimagines neural computing as a continuous hierarchy defined by temporal density and state-space complexity. We suggest that while current synchronous SNNs successfully optimize rate-based equilibria, they often neglect the intrinsic power of biological time. The true neuromorphic advantage emerges by ascending to asynchronous timing, where information is decoupled from clock cycles, and to complex non-equilibrium dynamics, where heterogeneity and criticality drive computation through transient trajectories. We propose a roadmap to bridge global optimization with local execution, leveraging evolutionary priors to support innate learning. By identifying native applications, from ultra-low-latency event perception to infinite-context memory for AGI, this perspective invites the community to view SNNs not merely as efficient quantization, but as dynamical systems capable of stable transience, offering a physical bridge to the next generation of intelligence.","url":"https://doi.org/10.1007/s11571-026-10470-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s11571-026-10470-y","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acsami.5c26141","name":"Unconventional Materials-Based Flexible Synaptic Transistors for Sustainable Neuromorphic Systems: Advancements, Challenges, and Future Trends.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c26141","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.5c26141","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.3390/nano16130816","name":"MRAM: A Versatile Non-Volatile Memory for Next-Generation Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/nano16130816","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/nano16130816","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1038/s41596-026-01382-6","name":"Tutorial: biomembranes in hybrid living bioelectronics.","source":"europepmc","abstract":"The integration of biological and artificial systems promises the effective coupling of living cells with electronic devices. However, to create biomimetic platforms capable of bridging biological with artificial systems, it is necessary to first enhance cell adhesion and cell interactions with engineered surfaces via the integration of techniques from materials science, nanotechnology and synthetic biology, such as structural functionalization techniques, and chemical or biological surface modifications. In this Tutorial Review we cover the use of polymer-based semiconductors and micro- and nanofabrication methods for the integration of biologically relevant cell membrane models with chip-based devices. This integration enhances cell-device coupling and provides an approach for studying membrane-level interactions. Although cell membranes are essential for understanding biological mechanisms, including drug responses, existing technologies rely on simplified synthetic models which lack biological complexity. Advances in electrical impedance measurements enable the study of membrane protein activity, providing insight into drug interactions and biomolecular processes. In addition, exploiting these hybrid systems can result in improved adhesion and electrostatic interactions, facilitating functional coatings for microdevices and neuromorphic applications. We discuss the recent advances in biomembrane-electronic interfaces, device design, surface modification, electronic materials, biomembrane formation and measurement techniques in the context of applications in drug discovery, diagnostics and neuromorphic computing, along with future directions for the field.","url":"https://doi.org/10.1038/s41596-026-01382-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41596-026-01382-6","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1021/acsami.6c08180","name":"Two-Dimensional Materials for Intelligent Gas Sensors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.6c08180","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.6c08180","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1039/d6nr00934d","name":"Iontronics of nanofluidic conical pores: learning phenomena using voltage pulses.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d6nr00934d","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d6nr00934d","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1039/d6cs00419a","name":"Coupling, tailoring, and applications of 2D magnetic materials.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d6cs00419a","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d6cs00419a","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.3934/mbe.2026037","name":"Modeling neural dynamics with optical nonlinearity: From classical models to optogenetic approaches.","source":"europepmc","abstract":"","url":"https://doi.org/10.3934/mbe.2026037","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3934/mbe.2026037","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.3390/s26103049","name":"Neuromorphic Technologies for Neuroengineering: From Adaptive Stimulation to SNN-Based Inference and Deployable Biointerfaces.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s26103049","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/s26103049","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1088/1361-6528/ae435a","name":"Memristive system in 2D materials: redefining the landscape of future nanoelectronics.","source":"europepmc","abstract":"","url":"https://doi.org/10.1088/1361-6528/ae435a","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1088/1361-6528/ae435a","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.3389/fnagi.2026.1906284","name":"Integrating computational modeling, neuroimaging, and neuromodulation to decompose perceptual decision-making in healthy aging: a review of methods, findings, and gaps.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnagi.2026.1906284","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnagi.2026.1906284","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1002/advs.74794","name":"Optoelectronic-Driven van der Waals Ferroelectric Materials-Based Memory Devices for Retinomorphic and In-Sensory Hardware.","source":"europepmc","abstract":"2D ferroelectric materials have recently emerged as a promising class of atomically thin semiconductors capable of integrating sensing, memory, and computation within a single device. Their unique combination of spontaneous switchable polarization, strong light-matter coupling, and van der Waals (vdW) interface compatibility provides an ideal platform for next-generation optoelectronic vision sensors. Coupling ferroelectric polarization with photoresponse, 2D ferroelectric materials such as α-In 2 Se 3 , CuInP 2 S 6 (CIPS), SnS, and WTe 3 enable non-volatile modulation of photocarrier transport, facilitating adaptive visual perception analogous to the human retina. These 2D ferroelectric photonic devices demonstrate synaptic plasticity, short-term and long-term memory, and optical potentiation and depression characteristics under visible and near-infrared excitation. Integrating ferroelectricity into optoelectronic architectures addresses the von-Neumann bottleneck by enabling in-sensor computing, where data are sensed, stored, and processed locally, minimizing latency and energy consumption. This review provides a comprehensive overview of 2D ferroelectric materials and their device architectures in the memristive and memtransistors devices structures for optoelectronic vision sensors, highlighting their polarization mechanism, light-driven conductance modulation, and neuromorphic functionalities. Additionally, current challenges, such as scalability, polarization fatigue, and interface engineering, have also been extensively discussed together with heterostructure design and hybrid ferroelectric-semiconductor integration toward energy-efficient bio-inspired vision systems.","url":"https://doi.org/10.1002/advs.74794","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.74794","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1039/d6mh00650g","name":"Interface engineering of perovskite transistors with self-assembled monolayers.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d6mh00650g","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d6mh00650g","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1039/d6ra05168e","name":"Resistive switching memristors: structures, materials, fabrication techniques, and process challenges for VLSI integration.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d6ra05168e","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d6ra05168e","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1021/acsami.6c08831","name":"Multifunctional Device Design and Applications of GaN and Transition Metal Dichalcogenides Heterojunctions.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.6c08831","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.6c08831","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1039/d6mh00662k","name":"Interface engineering in organic electrochemical transistors toward multifunctional bioelectronics.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d6mh00662k","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d6mh00662k","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.3390/ijms27156607","name":"Recent Advances in Two-Dimensional Bismuth Oxysulfide.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/ijms27156607","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/ijms27156607","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1021/acsnano.6c04950","name":"Two-Dimensional Semiconductors for Postsilicon Electronics: From Transistors to Integrated Circuits.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.6c04950","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsnano.6c04950","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1093/nsr/nwag290","name":"Electrochemical in-biosensing computing.","source":"europepmc","abstract":"Artificial intelligence (AI)-aided electrochemical biosensing is becoming integral parts in numerous scenarios. However, existing systems generally perform algorithms in external signal processing units. The necessity of analog-to-digital conversion and data transfer results in high complexity, low working efficiency and concern of privacy. In-sensor computing has made great progress in perceiving and processing physical signals, which, nevertheless, faces inherent restriction in biochemical scenarios due to the lack of aqueous compatibility and the necessity of an array. Here, we realized neuromorphic electrochemical in-biosensing computing using just a single photoelectrochemical transistor, which can itself not only perform multi-target biosensing but also constitute a single-layer algorithmic classifier. It is based on a rationally designed multi-gate photoelectrochemical transistor, whose architecture and synaptic memory enable built-in vector-matrix multiplication and light-tunable responsivity. The proof-of-concept is demonstrated by simultaneous sensing and classification of biomarker microRNA fingerprints in real biological samples, which opens the possibilities for next-generation AI-driven electrochemical biosensing with edge computing ability.","url":"https://doi.org/10.1093/nsr/nwag290","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1093/nsr/nwag290","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.3390/nano16070444","name":"Nonvolatile Reconfigurable Synthetic Antiferromagnetic Devices Induced by Spin-Orbit Torque for Multifunctional In-Memory Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/nano16070444","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/nano16070444","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1039/d6an00465b","name":"Decoding the molecular mechanisms of sour and salty sensation using biomimetic taste-based biosensors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d6an00465b","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d6an00465b","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1021/acsami.6c05140","name":"Enhancing Stretchability and Function in OFETs: A Molecular Design Paradigm via Side-Chain Engineering.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.6c05140","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.6c05140","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1038/s41467-026-68905-3","name":"Homogeneous integration of two-dimensional material-based optoelectronic neurons and ferroelectric synapses for neuromorphic vision.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-68905-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-68905-3","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41467-026-71372-5","name":"Ultra-high density perovskite nanowire array memristor-based multi-layer perceptron.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-71372-5","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-71372-5","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1093/nsr/nwag104","name":"Large spiking AI systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.1093/nsr/nwag104","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1093/nsr/nwag104","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41467-026-70171-2","name":"Physical echo state network based on the nonlinearity and dynamic response of ambipolar heterostructure transistors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-70171-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-70171-2","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.3390/e28050507","name":"Evaluating Photonic Quantum Memristors in Noisy Environments.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/e28050507","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/e28050507","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1038/s41467-026-69084-x","name":"Neuromorphic photonic computing with an electro-optic analog memory.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-69084-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-69084-x","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1002/cplu.202500487","name":"Recent Advances in Inorganic Oxide-Based Resistive Random Access Memory: Challenges and Strategies for Practical Applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/cplu.202500487","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/cplu.202500487","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.3390/nano16120725","name":"Recent Advances in the Synthesis and Application of Tellurium Semiconductors.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/nano16120725","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/nano16120725","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.3390/mi17040481","name":"A Parameter-Agnostic Adaptive Compensation in Memristor-Based Neuromorphic Systems for Parasitic Resistance.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/mi17040481","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/mi17040481","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/smtd.70969","name":"Advances in Te/Se-Based 2D p-Type Semiconductors for Electronics and Optoelectronics.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smtd.70969","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smtd.70969","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1038/s41467-026-71127-2","name":"Single-molecule neuromorphic device with aJ-level power consumption per switching.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-71127-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-71127-2","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.3390/biomimetics11060415","name":"Printed Organic Memristive Device on Rigid and Flexible Supports for Neuromorphic Applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics11060415","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/biomimetics11060415","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1136/archdischild-2026-330388","name":"Artificial intelligence for child health: current capabilities and the next frontier.","source":"europepmc","abstract":"","url":"https://doi.org/10.1136/archdischild-2026-330388","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1136/archdischild-2026-330388","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.3390/biomimetics11050359","name":"SE-SNN: Squeeze-and-Excitation-Enhanced Spiking Neural Networks with Learnable Neuron Dynamics for Event-Based Vision.","source":"europepmc","abstract":"Spiking neural networks (SNNs) have emerged as a promising paradigm for energy-efficient neuromorphic computing, particularly when processing asynchronous event streams from dynamic vision sensors (DVSs). However, SNNs often suffer from limited representational capacity and suboptimal feature recalibration compared to their artificial counterparts. To address these challenges, we propose SE-SNN, a novel architecture that integrates Squeeze-and-Excitation (SE) blocks into deep residual SNNs, enabling channel-wise attention without spike generation. Furthermore, we introduce a Robust Parametric Leaky Integrate-and-Fire (RobustPLIF) neuron model with learnable membrane time constant (τ) and firing threshold (vth), allowing adaptive temporal dynamics in each layer. Our model is trained on the CIFAR10-DVS dataset.The experimental results demonstrate that SE-SNN achieves an accuracy of 78.8% on CIFAR10-DVS with 16 time steps, outperforming baseline SNNs while maintaining biological plausibility and hardware efficiency. Ablation studies confirm the individual contributions of the SE blocks and learnable neuron parameters to the performance gains.","url":"https://doi.org/10.3390/biomimetics11050359","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/biomimetics11050359","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1002/smll.202509737","name":"Ion Migration Control in Lead-Free Halide Perovskite Transistors for Logic and Neuromorphic Circuits.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.202509737","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.202509737","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.3390/s26072144","name":"Spiking Neuron with Sensing Coil Based on a Volatile Memristor.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s26072144","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/s26072144","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.biotechadv.2025.108766","name":"Microbial computing: Review and Perspectives.","source":"europepmc","abstract":"Engineering microbial computers has been a longstanding endeavor in synthetic biology. Like other unconventional computing disciplines, the goal is to bring computation into real-world scenarios. Several potential applications in bioproduction, bioremediation, and biomedicine highlight the promise of this discipline. The first biocomputers were bottom-up predictable circuits that relied on a monoculture-based digital logic and were able to emulate simple logic gates. Drawing from computer theory and extending the analogy with conventional hardware has enabled the engineering of more complex circuits. However, this abstraction soon reached its limits and introduced a semantic gap, which, alongside the constraints imposed by the monoculture paradigm, led to significant scalability limitations such as metabolic burden, orthogonality issues and noisy expression. This review outlines the strategies developed to overcome these issues and engineer more complex biodevices: (i) mitigation strategies that focus on the optimization of the circuits, (ii) multicellular computing that distributes the metabolic load across a consortium and (iii) the implementation of more energy-efficient computing frameworks, such as analog and neuromorphic architectures. While these bottom-up strategies have yielded significant progress, they remain insufficient to emulate the computational complexity of the cellular signal-processing system. In this review, we additionally introduce a new perspective on biocomputing with a top-down approach named reservoir computing. This framework leverages the inherent dynamical computational capabilities and functionalities of biosystems to solve more complex and diverse tasks, thus offering a promising new path for engineering the next generation of microbial computers.","url":"https://doi.org/10.1016/j.biotechadv.2025.108766","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.biotechadv.2025.108766","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1038/s41467-026-69123-7","name":"Owl-vision-inspired near sensor computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-69123-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-69123-7","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1038/s41467-026-71091-x","name":"NEOSTI - a neuromorphic electronic-opto spatial-temporal hybrid image sensor.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-71091-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-71091-x","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1126/sciadv.aec2324","name":"HfO&lt;sub&gt;2&lt;/sub&gt;-based memristive synapses with asymmetrically extended p-n heterointerfaces for highly energy-efficient neuromorphic hardware.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.aec2324","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1126/sciadv.aec2324","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1002/adma.202517373","name":"Resistive Switching Oxides: Mechanism, Performance, and Device-Algorithm Co-Design for Artificial Intelligence.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202517373","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202517373","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1016/j.neunet.2025.108371","name":"Predictive coding with spiking neural networks: A survey.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.108371","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2025.108371","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1002/adma.73398","name":"Tailoring of Layered Bismuth-Based Materials: Advanced Functionalities for Environment, Energy, Photonics, Electronics, and Biomedicine.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.73398","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.73398","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1038/s41467-026-70587-w","name":"Multimodal ion-gated transistor based on 2D superionic conductor for in-memory computing in deep learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-70587-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-70587-w","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.3390/ma19040711","name":"All-Optical Artificial Synapse Based on ε-Ga&lt;sub&gt;2&lt;/sub&gt;O&lt;sub&gt;3&lt;/sub&gt; and β-Ga&lt;sub&gt;2&lt;/sub&gt;O&lt;sub&gt;3&lt;/sub&gt; Mixed-Phase Thin Films.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/ma19040711","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/ma19040711","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1039/d5cs00580a","name":"Neuromorphic iontronic devices based on soft ionic conductors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5cs00580a","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d5cs00580a","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1038/s41467-026-68858-7","name":"Bioinspired spiking architecture enables energy constrained touch encoding.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-68858-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-68858-7","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1021/acsnano.5c21692","name":"Interactive Nanophotonic Platforms for Multimodal Information Storage and Security.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.5c21692","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsnano.5c21692","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1002/adma.202518570","name":"Spintronic Materials and Devices for Artificial Intelligence Applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202518570","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202518570","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.3390/biomimetics11010081","name":"Enhancing Neuromorphic Robustness via Recurrence Resonance: The Role of Shared Weak Attractors in Quantum Logic Networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics11010081","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/biomimetics11010081","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1038/s41467-026-71446-4","name":"Nanoscale photonic artificial neuron with biological signal processing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-71446-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-71446-4","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.3390/nano15191481","name":"Advancing Flexible Optoelectronic Synapses and Neurons with MXene-Integrated Polymeric Platforms.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/nano15191481","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/nano15191481","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1038/s44172-026-00643-2","name":"Synapse-inspired energy networks: a neuromorphic approach to microgrid protection without communication links.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s44172-026-00643-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s44172-026-00643-2","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s44172-025-00479-2","name":"Neuromorphic Hebbian learning with magnetic tunnel junction synapses.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s44172-025-00479-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s44172-025-00479-2","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1021/acsami.5c24192","name":"Evolving Beyond Nature: AI-Driven Rapid Advancements of Bio-Inspired Electronic Skin.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c24192","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.5c24192","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1016/j.isci.2026.115985","name":"System-level FPGA validation of a trainable and robust multiplier-free spiking neural network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.isci.2026.115985","authors":["Qixuan Li","Lei Zhang"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.isci.2026.115985","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.20944/preprints202211.0332.v1","name":"Precise Spiking Motifs in Neurobiological and Neuromorphic Data","source":"preprints","abstract":"Why do neurons communicate through spikes? By definition, spikes are all-or-none neural events which occur at continuous times. In other words, spikes are on one side binary, existing or not without further details, and on the other can occur at any asynchronous time, without the need for a centralized clock. This stands in stark contrast to the analog representation of values and the discretized timing classically used in digital processing and at the base of modern-day neural networks. As neural systems almost systematically use this so-called event-based representation in the living world, a better understanding of this phenomenon remains a fundamental challenge in neurobiology in order to better interpret the profusion of recorded data. With the growing need for intelligent embedded systems, it also emerges as a new computing paradigm to enable the efficient operation of a new class of sensors and event-based computers, called neuromorphic, which could enable significant gains in computation time and energy consumption a major societal issue in the era of the digital economy and global warming. In this review paper, we provide evidence from biology, theory and engineering that the precise timing of spikes plays a crucial role in our understanding of the efficiency of neural networks.","url":"https://doi.org/10.20944/preprints202211.0332.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.20944/preprints202211.0332.v1","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.907Z"},{"id":"doi:10.22541/au.163638373.32437243/v1","name":"Recent Advancements in Emerging Neuromorphic Device Technologies     ","source":"preprints","abstract":"","url":"https://doi.org/10.22541/au.163638373.32437243/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.22541/au.163638373.32437243/v1","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.907Z"},{"id":"doi:10.20944/preprints201807.0362.v2","name":"Towards Neuromorphic Learning Machines using Emerging Memory Devices with Brain-like Energy Efficiency","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints201807.0362.v2","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2018","doi":"10.20944/preprints201807.0362.v2","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.907Z"},{"id":"doi:10.21203/rs.3.rs-3382076/v1","name":"Unravelling the Amorphous Structure, Nanoscale Effects, and Crystallization Mechanism of GeTe Phase Change Memory Material","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3382076/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-3382076/v1","addedAt":"2026-09-01T01:48:21.716Z","updatedAt":"2026-09-01T01:48:22.907Z"},{"id":"doi:10.5121/ijsc.2025.16101","name":"Dynamic Cognitive Ontology Networks: Advanced Integration of Neuromorphic Event Processing and Tropical Hyper Dimensional Representations","source":"crossref","abstract":"This journal article introduces a significantly expanded framework for integrating dynamic neuromorphic event-based processing with tropical hyperdimensional computing in cognitive ontology networks. Enhancements include the exploration of practical applications, ethical implications, and scalability to real-world datasets. This approach employs advanced dynamic adaptive learning rates, hierarchical relationship encoding, and novel binding mechanisms to achieve substantial improvements in clustering and classification tasks. A comparative study with state-of-the-art models highlights the framework's robustness, scalability, and biological plausibility. Additionally, the paper discusses new real-time hardware implementation potentials and multimodal integration, paving the way for future advancements.","url":"https://doi.org/10.5121/ijsc.2025.16101","authors":["Robert Mc Menemy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-04T13:33:53Z","doi":"10.5121/ijsc.2025.16101","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1016/j.procs.2026.01.027","name":"Neuromorphic-Inspired Framework for Brain-Like Natural Language Processing in Emerging AI Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.procs.2026.01.027","authors":["Prerna Dusi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-20T19:30:19Z","doi":"10.1016/j.procs.2026.01.027","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1007/s10853-026-13325-3","name":"Forming-free and high uniformity in Ca2+-doped CuxO memristors for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s10853-026-13325-3","authors":["Jinshi Zhao","Yuxiang Cao","He Liu","Chenming Dong","Chunbo Li","Di Wang","Lin’an He","Wei Mi","Liwei Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-19T14:25:52Z","doi":"10.1007/s10853-026-13325-3","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1088/2634-4386/adce28","name":"Exploiting drain-erase scheme in ferroelectric FETs for logic-in-memory","source":"crossref","abstract":"Abstract The conventional computing platforms based on von-Neumann architecture are highly space- and energy-intensive while handling the emerging applications such as AI, ML, and big data. To overcome the von Neumann bottleneck, compact and light-weight logic-in-memory (LiM) implementations of Boolean logic gates based on emerging non-volatile memory (e-NVM) such as RRAMs, PCM, STT-MRAMs, etc were proposed recently. However, these e-NVMs not only exhibit significant temporal and spatial variability, but their large-scale integration with CMOS process is also a technological challenge. To overcome these issues with the emerging non-volatile memories, ferroelectric FETs based on CMOS-compatible doped hafnium oxide with the capability of large-scale CMOS integration in the advanced logic nodes were proposed. Considering the high scalability and CMOS-compatibility of the FeFETs, in this work, for the first time, we propose a LiM implementation utilizing a single ferroelectric fully-depleted-silicon-on-insulator (Fe-FDSOI) FET exploiting the unique drain erase phenomenon. In our proposed LiM implementation, inputs are applied at the gate and drain terminals using a novel input-to-voltage mapping scheme, and output is obtained as the current flowing through the Fe-FDSOI FET. We utilize an experimentally calibrated compact model of the ferroelectric capacitor connected to the baseline industry standard BSIM-IMG compact model for the FDSOI transistor for proof of concept demonstration. We also perform a comprehensive analysis of the performance metrics of the proposed LiM implementation. Our results indicate that we can realize at least 10 Boolean logic gates with high energy and area-efficiency utilizing the proposed scheme.","url":"https://doi.org/10.1088/2634-4386/adce28","authors":["Musaib Rafiq","Yogesh Singh Chauhan","Shubham Sahay"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-17T18:50:41Z","doi":"10.1088/2634-4386/adce28","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1088/2634-4386/ae9982","name":"Moisture effects on diffusive memristors","source":"crossref","abstract":"Abstract Biological nervous systems encode information through transient, event-driven spikes, motivating neuromorphic hardware that can reproduce such dynamics efficiently. Diffusive memristors are strong candidates because their volatile, threshold-driven responses generate spike-like signals and support temporal processing. However, their switching relies on ionic motion and transient metal clusters that are highly sensitive to interfacial chemistry, leaving the influence of environmental factors unresolved. Here, the chemical role of moisture in enabling volatile threshold switching is systematically established in symmetric Pt/Ag/SiO2/Ag/Pt diffusive memristors using a rigorously controlled fabrication and measurement framework. Systematic comparisons show that interfacial water facilitates Ag oxidation and hydrated transport pathways, whereas its depletion suppresses switching or increases variability. These findings demonstrate that moisture is not a minor perturbation but a fundamental chemical requirement for stable operation in such device systems. Controlling interfacial hydration emerges as a key design principle for achieving reliable and commercially scalable diffusive memristors for neuromorphic hardware.","url":"https://doi.org/10.1088/2634-4386/ae9982","authors":["Seung Ju Kim","Ruoyu Zhao","Yichun Xu","Jian Zhao","Han-Ting Liao","J. Joshua Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-13T22:50:53Z","doi":"10.1088/2634-4386/ae9982","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1038/s41598-026-65987-3","name":"Neuromorphic optoelectronic computing system based on semiconducting metal oxide nanocrystallites","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s41598-026-65987-3","authors":["Viktor V. Krasnikov","Alexander A. Chezhegov","Artem S. Chizhov","Andrey A. Grunin","Andrey A. Fedyanin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-07T13:02:48Z","doi":"10.1038/s41598-026-65987-3","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1039/d5nr05022g/v2/review1","name":"Review for \"Combined resistive switching memory and multi-state operation in Terpyridine - based Pd(II) and Fe(III) Complexes for neuromorphic applications\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5nr05022g/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-06T14:50:57Z","doi":"10.1039/d5nr05022g/v2/review1","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.26599/nr.2026.94908419","name":"Green electronics based on biopolymer memristors toward sustainable neuromorphic devices","source":"crossref","abstract":"Abstract The artificial intelligence-driven data deluge presents formidable challenges to conventional computing architectures, which are constrained by the von Neumann bottleneck and complementary metal-oxide-semiconductor (CMOS) scaling limits. Neuromorphic computing demonstrates breakthrough potential through its in-memory computing paradigm. Memristors, recognized as the most promising core devices in this field, excel at emulating synaptic plasticity while exhibiting nonlinear dynamic responses and conductance modulation capabilities. However, conventional inorganic memristors face critical limitations, including insufficient mechanical flexibility, biotoxicity, and non-degradability, which hinder their applications in wearable and implantable neuromorphic devices. In contrast, biomaterials and biological tissues emerge as viable platforms for overcoming these bottlenecks and realizing next-generation sustainable neuromorphic systems, owing to their exceptional biocompatibility, environmental benignity, and ultra-thin lightweight characteristics. This review focuses on cutting-edge developments in renewable biopolymer-based memristors (e.g., natural biomolecules like proteins and DNA, alongside bioengineered polymers such as poly(lactic acid) (PLA)). We elucidate how their molecular-level multifunctional groups and hierarchical structures drive high-performance memristive behaviors and bio-inspired synaptic functions. Special emphasis is placed on analyzing these devices’ superior biocompatibility and biodegradability, with in-depth discussions on how such properties enable implantable neuromorphic applications. Finally, we critically examine persisting challenges including environmental sensitivity/resistance state drift, stochastic ion migration pathways, and scalable integration hurdles. Potential countermeasures and feasible development pathways are systematically explored.","url":"https://doi.org/10.26599/nr.2026.94908419","authors":["Xiaochao Zhang","Haiting Wang","Xuzhao Zhang","Dongyue Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-14T00:33:52Z","doi":"10.26599/nr.2026.94908419","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1002/advs.75409","name":"RETRACTION: A Retina‐Inspired Optoelectronic Synapse Using Quantum Dots for Neuromorphic Photostimulation of Neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1002/advs.75409","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-20T19:31:17Z","doi":"10.1002/advs.75409","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1039/d5tc04438c","name":"Ferroelectric memcapacitive dynamics from nanoseconds to milliseconds for bio-inspired neuromorphic computing and control","source":"crossref","abstract":"Achieving sub-volt, nanosecond-to-millisecond synaptic plasticity in a scalable ferroelectric platform remains a key challenge for neuromorphic hardware.","url":"https://doi.org/10.1039/d5tc04438c","authors":["Sai Jiang","Chaoran Wu","Jinrui Sun","Sihao Xu","Sheng Li","Yijie Lai","Ning Wang","Huafei Guo","Jianhua Qiu","Yun Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-16T07:02:40Z","doi":"10.1039/d5tc04438c","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.2139/ssrn.5918822","name":"Neuromorphic Architectures for Edge-Oriented Spiking Neural Networks: A Review","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5918822","authors":["Kanishka Gunawardana","Sanka Peeris","Kavishka Rambukwella","Roshan Ragel","Isuru Nawinne"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-06T15:08:54Z","doi":"10.2139/ssrn.5918822","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1039/d5nr05022g/v1/review2","name":"Review for \"Combined resistive switching memory and multi-state operation in Terpyridine - based Pd(II) and Fe(III) Complexes for neuromorphic applications\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5nr05022g/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-06T14:50:57Z","doi":"10.1039/d5nr05022g/v1/review2","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1145/3822454.3822482","name":"Co-Evolved Spiking Neural Network Ensembles via Marginal Contribution Fitness","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3822454.3822482","authors":["Catherine Rodriquez","James Michael Ghawaly"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-16T05:57:39Z","doi":"10.1145/3822454.3822482","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1007/978-3-032-12107-3_4","name":"Filaments","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-12107-3_4","authors":["Elliot Kisiel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-19T17:21:54Z","doi":"10.1007/978-3-032-12107-3_4","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1145/3822454.3822461","name":"Spiking Neural Networks for Real-Time Strategy: A Curriculum-Trained SNN Agent for MicroRTS","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3822454.3822461","authors":["Chang Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-16T05:57:39Z","doi":"10.1145/3822454.3822461","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1145/3822454.3822473","name":"Direction-of-Arrival Estimation via Spiking Locally Competitive Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3822454.3822473","authors":["Joseph Randich","Justin Mauger","Haik Manukian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-16T05:57:39Z","doi":"10.1145/3822454.3822473","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.21203/rs.3.rs-10021251/v1","name":"A Physio-Informatic Paradigm for Quantum Annealing and Neuromorphic AI: Extending PIRA for Sub-Exponential Energy Optimization","source":"crossref","abstract":"Abstract This paper introduces PIRA-X, extending the Physio-Informatic Reduction Algorithm (PIRA) paradigm from discrete classical boundaries to continuous-state physical architectures, notably Quantum Annealing (QA) substrates and Neuromorphic crossbar arrays. Combinatorial NP-hard mappings and deep neural network optimization suffer from exponential energy scaling on classical von Neumann architectures. By integrating Landauer's thermodynamic erasure principle with non-equilibrium physical state variables, we model optimization as a native thermodynamic relaxation lifecycle. We present a multi-dimensional tensor governing equation that bounds physical information pressure gradients, enforcing a strict sub-exponential, logarithmic convergence trajectory of T(d)=O(d \\ln d) across rugged, non-convex energy landscapes. Simulated benchmarks across extensive TSPLIB instances demonstrate significant execution gains against conventional stochastic baselines. Rigorous statistical validation via Wilcoxon signed rank testing (p=0.00012) and an exceptional Cohen's d effect size (4.72) confirm the computational viability of hardware-native, physio-informatic acceleration.","url":"https://doi.org/10.21203/rs.3.rs-10021251/v1","authors":["Md Azahar Ali"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-16T11:03:59Z","doi":"10.21203/rs.3.rs-10021251/v1","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/aero66936.2026.11519863","name":"Flexible FPGA Accelerator for Real-Time Neuromorphic Optical Flow in Space Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aero66936.2026.11519863","authors":["Linus Silbernagel","Daniel C. Stumpp","Alan D. George"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-22T19:33:47Z","doi":"10.1109/aero66936.2026.11519863","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1039/d5nr05022g/v1/review1","name":"Review for \"Combined resistive switching memory and multi-state operation in Terpyridine - based Pd(II) and Fe(III) Complexes for neuromorphic applications\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5nr05022g/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-06T14:50:57Z","doi":"10.1039/d5nr05022g/v1/review1","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.12968/s0013-7758(26)90049-4","name":"Innatera and Joya Bring Neuromorphic AI to Edge Devices","source":"crossref","abstract":"","url":"https://doi.org/10.12968/s0013-7758(26)90049-4","authors":["Jason Ford"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-31T15:49:06Z","doi":"10.12968/s0013-7758(26)90049-4","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.21203/rs.3.rs-9477612/v1","name":"NHRN: A Neuromorphic Hierarchical Resonance Network for EEG-based Parkinson's Disease Classification","source":"crossref","abstract":"Abstract Parkinson's disease (PD) is a progressive neurodegenerative disorder characterized by motor dysfunction and underlying neural rhythm disturbances, making early and objective diagnosis crucial for effective clinical intervention. Electroencephalogram (EEG) signals provide a non-invasive window into brain dynamics; however, their non-linear, multi-scale temporal behavior poses challenges for conventional approaches. This study presents a framework for PD detection using EEG signals, leveraging neural signatures such as reduced beta activity, altered gamma rhythms, disrupted cortico--basal ganglia interactions, and abnormal cross--frequency coupling. The proposed Neuromorphic Hierarchical Resonance Network (NHRN) model, which combines fractal multi-scale convolution, synaptic gating, oscillatory feature learning, adaptive receptive fields, cognitive load regulation, memory integration, and spectral--temporal fusion. Higher-level representations are refined through hierarchical abstraction, resonance-based attention, and adaptive channel weighting, enabling effective modeling of long-range dependencies and nonlinear brain activity. Clinical validity is established via UPDRS-III stratified analysis,revealing a near-perfect correlation between motor symptom severity andclassification performance across medication ON and OFF states, withmonotonically increasing accuracy from mild to severe disease stages,confirming that the NHRN captures genuine pathophysiological EEGbiomarkers and demonstrates potential for early detection, medicationmonitoring, and disease progression tracking.Rigorous evaluation spanning multiple independent benchmarks--UCSD,UNM, and Iowa under heterogeneous cohorts and varying recordingconditions achieves 98.1\\,%, 96.8\\,%, and 95.7\\,% accuracy,respectively, while multi-dataset training delivers 97.1\\,% accuracywith low variability and only 1.07M parameters, confirming stronggeneralization and suitability for online embedded clinical deployment.","url":"https://doi.org/10.21203/rs.3.rs-9477612/v1","authors":["Rajveer Singh Lalawat","Nikhil Kushwaha","Albert Chih-Chieh Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-25T15:21:07Z","doi":"10.21203/rs.3.rs-9477612/v1","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/nice69539.2026.11567488","name":"Memory-Augmented Spiking Networks: Synergistic Integration of Complementary Mechanisms for Neuromorphic Vision","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nice69539.2026.11567488","authors":["Effiong Blessing","Chiung-Yi Tseng","Isaac Nkrumah","Junaid Rehman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-22T19:52:43Z","doi":"10.1109/nice69539.2026.11567488","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1007/978-3-032-12107-3_5","name":"Barriers","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-12107-3_5","authors":["Elliot Kisiel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-19T17:21:55Z","doi":"10.1007/978-3-032-12107-3_5","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1149/ma2026-01341576mtgabs","name":"(\n                    <i>Invited</i>\n                    ) Solution-Processed Neuromorphic Transistors with Tunable Temporal Dynamics for Wearable Sensing","source":"crossref","abstract":"Wearable biological sensing devices promise continuous, low-power monitoring of physiological and biochemical signals. However, these emerging platforms often require increasingly complex signal computation. One common solution is to continuously offload data via wireless transmission for cloud-based processing, but this approach incurs significant power and communication overhead that fundamentally limits wearable operation. Neuromorphic computing architectures offer an alternative by enabling low-power, on-board computation directly at the sensing node. Critically, such devices must exhibit temporal dynamics that are tuned to the intrinsic timescales of the biological signals being measured. In this talk, I will discuss how we engineer solution-processed materials that maintain high performance across biologically relevant and tunable temporal regimes. Ultimately, this work establishes a materials design framework for developing sensor-specific computing architectures for next-generation wearable technologies. The devices are based on hybrid semiconducting channels composed of carbon nanotube (CNT) networks and the ion-permeable polymer poly(3-hexylthiophene) (P3HT), fabricated using low-temperature, scalable processes compatible with flexible substrates. By controlling the polymer crystallization pathway, we engineer distinct microstructures that regulate ionic penetration and trapping, yielding synaptic transistors spanning fast, surface-dominated responses to slow, long-term ionic memory. Electrical and synaptic characterization reveals that these material-defined temporal dynamics directly govern device behavior, including short- and long-term plasticity, recovery time constants, and energy efficiency. Using experimentally measured device responses, we demonstrate through neuromorphic simulations that fast CNT-dominant devices are well-suited for high-frequency spiking operations, while hybrid CNT/P3HT devices with extended memory enable efficient temporal integration and data compression for slowly varying inputs. These regimes closely mirror the signal characteristics encountered in wearable sensing, such as motion, strain, and sweat-based biomarker monitoring. Together, this work establishes materials-controlled temporal dynamics as a key design parameter for solid-state electronics in wearable and biomedical systems, enabling flexible sensor platforms that perform signal processing directly at the body interface without increasing circuit or algorithmic complexity.","url":"https://doi.org/10.1149/ma2026-01341576mtgabs","authors":["Joseph Andrews"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-16T07:40:49Z","doi":"10.1149/ma2026-01341576mtgabs","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.21203/rs.3.rs-10010940/v1","name":"Neuromorphic control of a simulated shape-memory-alloy-driven multi-legged robot using a spiking neural network","source":"europepmc","abstract":"Abstract We propose a spiking-neural-network (SNN)-based deep reinforcement learning (DRL) method for efficient autonomous locomotion control of a starfish-inspired multi-legged soft robot driven by shape memory alloy (SMA) actuators. Conventional soft-robot controllers have predominantly relied on open-loop, pre-designed periodic signals; however, manually designing and tuning coordinated motion in systems with many degrees of freedom and strong nonlinearities remains difficult. Here, we train an SNN controller for SMAs, whose nonlinear contractile responses resemble key aspects of biological muscle. Specifically, we propose a Spiking Actor Network (SAN), in which the actor network of Twin Delayed Deep Deterministic Policy Gradient (TD3), an algorithm well suited to continuous action spaces, is replaced by an SNN. To account for the membrane potential, an internal state of SNNs, we extend the replay buffer to store and reuse membrane-potential information during training. To improve inference-time energy efficiency, we also add a regularization term that minimizes the squared membrane potentials, thereby encouraging action generation with fewer spike firings. In physics-simulation experiments on autonomous locomotion, the proposed method enabled the agent to acquire the leg coordination required to move toward a target. Analysis of the output spike trains showed that the learned firing patterns developed periodicity matched to the physical characteristics of the SMA, forming a coordinated gait that generated continuous propulsion while avoiding excessive firing. These results demonstrate the potential of autonomous neuromorphic control for energy-efficient soft-robot locomotion.","url":"https://doi.org/10.21203/rs.3.rs-10010940/v1","authors":["Daisuke Miki","Hiroto Takigasaki"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-10010940/v1","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1145/3822454.3822485","name":"FlowEqProp: Training Flow Matching Models with Gradient Equilibrium Propagation","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3822454.3822485","authors":["Alex Gower"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-16T05:57:39Z","doi":"10.1145/3822454.3822485","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/syscon66367.2026.11503544","name":"Integrating Neuromorphic Sensors, Digital Twins, and MBSE Interfaces for System Validation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/syscon66367.2026.11503544","authors":["Emi Aoki","Flore Norcéide","Gayathri Boopathy","Charles Thompson","Kavitha Chandra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-07T19:51:19Z","doi":"10.1109/syscon66367.2026.11503544","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.3390/aisens2010003","name":"Recent Advances in Neuromorphic Tactile Perception for Robotic Applications","source":"crossref","abstract":"Skin plays an important role in biological organisms perceiving and mediating our interactions with the world [...]","url":"https://doi.org/10.3390/aisens2010003","authors":["Zixuan Zhang","Chengkuo Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-26T14:51:29Z","doi":"10.3390/aisens2010003","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1007/s11071-026-12555-z","name":"Inductor-stabilized charge-controlled memristor neuromorphic circuit design with complex firing dynamics","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11071-026-12555-z","authors":["Lilian Huang","Xiaokun Yu","Xihong Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-11T08:27:20Z","doi":"10.1007/s11071-026-12555-z","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1109/mems64181.2026.11419444","name":"Wrinkle Assisted Nanofluidic Memristors for Tunable Ionic Memory and Neuromorphic Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mems64181.2026.11419444","authors":["Minsu Kwon","Dongwoo Seo","Taesung Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-11T19:35:46Z","doi":"10.1109/mems64181.2026.11419444","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1016/j.vlsi.2026.102798","name":"A novel subthreshold neuromorphic core with Izhikevich recovery variable reuse for hardware-efficient Spike-Driven Synaptic Plasticity","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.vlsi.2026.102798","authors":["Amr Hassan","Eman Azab"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-18T16:33:49Z","doi":"10.1016/j.vlsi.2026.102798","addedAt":"2026-09-01T01:48:21.765Z","updatedAt":"2026-09-01T01:48:21.765Z"},{"id":"doi:10.1007/s12021-026-09809-x","name":"A Perovskite Memdiode-Based Neuromorphic in Silico Surrogate Model for Emulating Predictive Coding Failure in Diabetic Neuropathy.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s12021-026-09809-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s12021-026-09809-x","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.2147/jmdh.s605039","name":"NeuroMimicNet: A Multimodal Neuromorphic Framework for Early Screening and Cognitive Pattern Recognition in Children with Autism.","source":"europepmc","abstract":"Background Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition which is composed of social, behavioral, and communication challenges that generally require early detection. Purpose This research proposes NeuroMimicNet, a brain-like event-driven neuromorphic computing framework designed for early screening and cognitive pattern recognition in children with autism. The framework integrates audio signal and facial expression images as multimodal inputs to capture both neural and behavioral patterns. Methods The audio modality involves pre-processing steps including noise elimination and normalization, while the neuromorphic processing of audio features is done with Spike-Timing-Dependent Plasticity (STDP), Hebbian learning and a Loihi-inspired spiking neural processing model to capture temporal auditory patterns efficiently. The facial expression images are pre-processed through face alignment, resizing and normalization, and high-level visual features are extracted using a pretrained ResNet50 convolutional neural network. The extracted audio and image features are fused at the feature level to form a unified multimodal representation. The fused features are then classified into four ASD severity level such as Typical, Mild, Moderate, and Severe using a supervised classification model. Results Performance is evaluated using accuracy, F1-score, precision, recall, and computational efficiency across benchmark EEG-autism datasets. Experimental results demonstrate that NeuroMimicNet achieves higher accuracy and faster response compared to conventional deep learning models. Conclusion NeuroMimicNet highlights the potential of biologically inspired neuromorphic computing for pediatric ASD screening. By combining multimodal behavioral and neural cues with event-driven processing, the framework offers improved interpretability, scalability and clinical relevance.","url":"https://doi.org/10.2147/jmdh.s605039","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.2147/jmdh.s605039","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:25.465Z"},{"id":"doi:10.3390/nano16150935","name":"Te/Fe&lt;sub&gt;3&lt;/sub&gt;GaTe&lt;sub&gt;2&lt;/sub&gt; 1D-2D Ferroelectric Heterojunction Transistors Enabling Ultrafast Multi-State Switching for Workpiece Surface Defect Inspection.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/nano16150935","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/nano16150935","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1038/s41377-026-02444-w","name":"Neuromorphic vision with quasi-BICs.","source":"europepmc","abstract":"Abstract Neuromorphic vision functionalities have been realized by coupling quasi-bound states in the continuum (quasi-BICs) to multiple quantum wells (MQWs). The engineered leaky modes enhance infrared absorption and generate coexisting nonlinear and linear photoresponses that support image preprocessing and in-sensor computing. This approach highlights a new role for quasi-BIC leakage in integrated optoelectronic intelligence.","url":"https://doi.org/10.1038/s41377-026-02444-w","authors":["Jue Li","Haoye Qin","Qinghua Song"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41377-026-02444-w","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acsami.6c12298","name":"Interfacial Ionic Modulation in a Solid Polymer Electrolyte-Based Ionotronic Memristor for Neuromorphic Learning and Nociceptor Emulation.","source":"europepmc","abstract":"Solid polymer electrolyte (SPE)-based memristors usually exhibit predictable digital nonvolatile switching with limited conductance tunability, restricting their use in neuromorphic systems. This behavior arises because of mobile cations and anions in SPEs that rapidly form robust conductive filaments via a positive-feedback process, producing sharp set/reset transitions. Here, we demonstrate that by employing a suitable pulse scheme, a nonfilamentary pathway can be accessed through interfacial ionic modulation, leading to gradual conductance modulation relevant for neuromorphic computing. We fabricated CuBr-dissolved polyethylene oxide (Cu-SPE) based memristors that show conventional digital filamentary switching on DC bias sweep mode. The optimized device (2 wt % CuBr) achieved an ON/OFF ratio of >103 with average set and reset voltages of +0.65 V and -0.7 V, respectively, and improved uniformity. The electrochemical characterization reveals a low Cu+ transport number (tCu+ ∼ 5%), with the majority of ionic current carried by anions, leading to concentration polarization during the biasing conditions. By harnessing this polarization effect and modulating Cu+ ion injection via tailored pulse schemes, the Cu-SPE memristor reproducibly emulates synaptic behaviors across temporal scales, including paired-pulse facilitation and depression (PPF/PPD), pulse-amplitude and pulse-width dependent synaptic weight modulation, and Hebbian learning rules. The device also reproduces key nociceptive responses including threshold firing, no-adaptation, and sensitization. It can, further, follow Pavlov's classical conditioning and act as a Morse code generator. A control experiment replacing the copper electrode with gold confirms that interfacial ionic modulation drives the neuromorphic behavior. These results establish that SPE-based memristors can simultaneously support digital filamentary memory and operate in a nonfilamentary, ionically mediated regime similar to fluidic memristors, thereby broadening their applicability in neuromorphic hardware.","url":"https://doi.org/10.1021/acsami.6c12298","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.6c12298","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1073/pnas.2617376123","name":"A hypersensitive neuromorphic airflow sensor inspired by vision-compensatory scorpion mechanoreceptors for respiratory pattern analysis.","source":"europepmc","abstract":"","url":"https://doi.org/10.1073/pnas.2617376123","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1073/pnas.2617376123","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acs.jpclett.6c02321","name":"AgPS3-Based Electrical Synapses with Tunable Multilevel Conductance for Noise-Robust Image Classification.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.jpclett.6c02321","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acs.jpclett.6c02321","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1126/sciadv.aed0971","name":"Neuromorphic tissues: Soft biomolecular networks for brain-inspired temporal computing.","source":"europepmc","abstract":"Brains achieve extraordinary efficiency in processing temporal information through dense interconnectivity and recurrent feedback among neurons. Inspired by this principle, we introduce neuromorphic tissues—soft biomolecular networks comprising cell-sized aqueous compartments interconnected by lipid membranes containing voltage-gated ion channels. When a compartment is electrically stimulated by current injection, the membranes separating it from neighboring compartments polarize until channel activation occurs, transiently transforming the interface into a conductive synapse that couples adjacent nodes. These dynamics generate intrinsic physical recurrence, enabling the network to encode, propagate, and reconstruct time-dependent signals without external feedback circuitry. Experiments and modeling demonstrate nonlinear, fading-memory, and recurrent dynamics characteristic of reservoir computing, enabling accurate prediction of nonlinear and chaotic sequences such as NARMA-10 and the Lorenz attractor. This work suggests that spatial interconnectivity can enhance the computational capabilities of physical reservoirs and highlights soft, self-assembled materials as a promising platform for implementing such interconnected systems.","url":"https://doi.org/10.1126/sciadv.aed0971","authors":["Nicholas X. Armendarez","Ahmed S. Mohamed","Md Sakib Hasan","Joseph S. Najem"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1126/sciadv.aed0971","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/adma.73861","name":"Neuromorphic In-Memory Computing for Marine Visual-Auditory Perception.","source":"europepmc","abstract":"The exploration of marine environments is crucial, yet the extreme conditions of the deep-sea, combined with the segregated signal processing in current sensor technologies, lead to bulky systems, high energy consumption, and significant latency, which severely constrains the development of real-time intelligent perception systems underwater. Herein, we developed a neuromorphic floating-gate transistor (NFT) that integrates both electrical and optical memory functionalities, emulating simultaneously visual and auditory synaptic behaviors within a single unit, thus enabling in-memory dual-mode processing of visual-auditory signals. Electrically, it achieves rapid switching (∼14 µs), high on/off ratio (10 6 ), and robust endurance (>10 4 cycles). This enables high-accuracy (88%) classification of seafloor minerals and rocks via sonar echo processing using a convolutional neural network (CNN). Optically, the NFT exhibits tunable synaptic weight modulation from short-term to long-term plasticity under 405-808 nm laser pulses. Leveraging the low-attenuation green-light window in seawater, the system, combined with RGB denoising and green-channel enhancement preprocessing, realizes 80% accuracy in marine biological image recognition. This synergistic electro-optical in-memory computing architecture provides an efficient, low-power, and compact hardware solution for intelligent perception in complex underwater environments.","url":"https://doi.org/10.1002/adma.73861","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.73861","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acs.nanolett.6c02779","name":"A Highly Robust MoS2-xOδ Volatile Memtransistor Array for Reservoir Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.6c02779","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acs.nanolett.6c02779","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.3390/mi17080967","name":"Electrical Characterization of Mesh-Structured Floating-Gate Neuromorphic Transistors with Varying Mesh Sizes.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/mi17080967","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/mi17080967","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acsami.6c08360","name":"PMMA-Engineered Halide Perovskite/Ag Interface for Optoelectronic Stable Memristive Synapse.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.6c08360","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.6c08360","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1126/sciadv.aed9436","name":"Reconfigurable ferroelectric transistor array for embodied neuromorphic vision with hardware-native sensing, computing, and activation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.aed9436","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1126/sciadv.aed9436","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acsami.6c05995","name":"Ionic Pathways to Neuromorphic Function: Direct Visualization of Oxygen Migration in Interface Synaptic Memristive Devices.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.6c05995","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.6c05995","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/smll.74436","name":"Photo-Induced Valence Changed Memristor Based on WO&lt;sub&gt;3&lt;/sub&gt; and Polyvinyl Alcohol Nanocomposites for In-Sensor Reservoir Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.74436","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.74436","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/adma.74547","name":"Direct Observation of Propagating Spin Waves in a Spin Hall Nano-Oscillator.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.74547","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.74547","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.3390/s26165311","name":"A Neuro-Inspired Rate-Encoded Descriptor for High-Speed Asynchronous Robotic Vision.","source":"europepmc","abstract":"This paper presents the Post-Stimulus Time-Dependent Event Descriptor (P-TED), a novel “pure event” feature descriptor designed for neuromorphic vision data. Unlike conventional frame-based approaches or hybrid methods that transform event data into intermediate representations, P-TED operates directly on asynchronous event streams, thereby preserving the intrinsic low-latency and high-temporal-resolution advantages of event-based sensors. The descriptor integrates two complementary feature sets: a motion feature vector, which aggregates spatial relationships within a Moore neighbourhood to quantify stimulus direction, and a pattern feature vector, which employs rate encoding to capture temporal excitation signatures. The efficacy of the P-TED framework is validated through three distinct experiments: object and character recognition (MNIST-DVS and CIFAR10-DVS), mobile robot movement analysis, and complex non-rigid robotic hand gesture recognition (RoShamBo). Experimental results demonstrate that the P-TED achieves a significant reduction in classification latency, requiring only 2.7 ms compared to the 10.3 ms recorded by the state-of-the-art Distribution-Aware Retinal Transform (DART) framework. Additionally, P-TED exhibits superior robustness in disambiguating symmetric and mirrored motions, as well as in maintaining stability under non-linear fluctuations in event density caused by changing scale. This work establishes P-TED as a high-speed, computationally efficient, and explainable solution for real-time neuromorphic robotic vision systems.","url":"https://doi.org/10.3390/s26165311","authors":["Shane Harrigan","Sonya Coleman","Dermot Kerr","Pratheepan Yogarajah","Chengdong Wu","Zheng Fang"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/s26165311","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:31.149Z"},{"id":"doi:10.3390/nano16150959","name":"Interfacial Engineering of MoS&lt;sub&gt;2&lt;/sub&gt; Thin Films for Wettability-Dependent Resistive Switching and Neuromorphic Behaviors.","source":"europepmc","abstract":"Recent years have witnessed a surge in the research of memristors as fundamental building blocks for neuromorphic computing, owing to their exceptional ability to emulate the plastic behavior of biological synapses in a high-density, low-power hardware format. These devices are increasingly recognized as the key to achieving efficient artificial neural networks. Two-dimensional (2D) molybdenum disulfide (MoS 2 ) is a premier candidate for artificial synapses due to its atomic scale and tunable electronic properties. However, achieving wafer-scale MoS 2 thin films for integrated memristor systems remains a significant challenge. In this work, a scalable strategy combining cetyltrimethylammonium bromide (CTAB)-assisted electrochemical intercalation and oil-water interface self-assembly was developed to fabricate large-area 2H-phase MoS 2 thin films. Leveraging the amphiphilic nature of CTAB-functionalized MoS 2 nanosheets, continuous Janus-structured MoS 2 films with asymmetric wetting properties (hydrophilic vs. hydrophobic) were successfully prepared. Vertical-structured Ag/Janus-structured MoS 2 /ITO memristors demonstrated robust non-volatile switching with high endurance and long-term retention. The devices successfully emulated biological synaptic behaviors, including short-term and long-term plasticity. Furthermore, the memristors exhibited distinct optoelectronic synergistic modulation under 405 nm illumination, enabling light-sensitive synaptic functions. This work offers a versatile interface engineering route for low-power integrated sensing-memory-computing hardware.","url":"https://doi.org/10.3390/nano16150959","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/nano16150959","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1007/s11571-026-10493-5","name":"Adaptive memristor-based LIF neuron circuit for energy efficient SNN crossbar array.","source":"europepmc","abstract":"Spiking neural networks (SNN) provide superior potential for neuromorphic architecture implementation due to its similarity to biological brain structures and exceptional computing efficiency. Neurons are the fundamental elements of SNN, and the incorporation of frequency adaptation enhances the performance of SNN significantly. The study implements an adaptive leaky-integrate-and-fire (LIF) neuron utilizing volatile and non-volatile memristors. The design offers control of adaptive response via inter-pulse interval of the input and certain circuit characteristics, including membrane capacitance and the initial resistance state of the volatile memristor. This work presents a novel SNN crossbar circuit of dimensions 2x2 and 5x5, offering several advantages including bio-realistic spike generation, reduce energy per spike consumption, no requirement of additional neuron reset circuitry, improving scalability and integration. The Cadence Virtuoso 180 nm simulation environment has been utilized to demonstrate firing dynamics of the adaptive SNN. The study emphasizes potential of adaptive spiking neural network circuits in facilitating efficient neuromorphic applications in forthcoming research.","url":"https://doi.org/10.1007/s11571-026-10493-5","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s11571-026-10493-5","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1126/sciadv.aec7731","name":"All-two-dimensional, ion-gating synaptic transistors for high-temperature and ultralow-energy-consumption neuromorphic applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.aec7731","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1126/sciadv.aec7731","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1039/d6nr00930a","name":"Mercapto-methylimidazole molecular memristors for high-performance resistive switching and artificial synaptic emulation.","source":"europepmc","abstract":"Organic molecule-based memristive devices are promising candidates for next-generation data storage devices due to their scalability and low cost. This work discusses a resistive memory device based on a small organic molecule 2-mercapto-1-methylimidazole (MMI) and the polymer poly 4-vinylpyridine (PVP), which exhibits stable resistive switching with a high on-off ratio (5.48 × 10 3 ), retention over 3.6 × 10 4 s and endurance over 700 cycles. In addition to memory behavior, the MMI organic molecule-based memristor exhibits synaptic functions crucial for neuromorphic computing. The device shows analog modulation of conductance in accordance with voltage pulse protocols, mimicking essential biological learning mechanisms, including potentiation, depression, short-term plasticity (STP), long-term plasticity (LTP), and paired-pulse facilitation (PPF). The device also demonstrates associative learning via Pavlovian conditioning, demonstrating its potential as a hardware-implemented artificial synapse in emerging brain-inspired systems. The carrier transport in these devices follows multiple conduction mechanisms including trap-free and trap-assisted space-charge limited conduction (SCLC), and Ohmic conduction. The switching is attributed to metallic filament formation from the top electrode which is further supported by impedance measurements. This study highlights the potential of organic molecular memristors for next-generation memory and neuromorphic computing.","url":"https://doi.org/10.1039/d6nr00930a","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d6nr00930a","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/smll.74516","name":"Interface Engineering for Scalable Optoelectronic Reservoir Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.74516","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.74516","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acs.jpclett.6c02041","name":"SiO2-Regulated Ag/[MMIm][H2PO4]:H2O/Ag Memristor for Neuromorphic Synaptic Simulation and Wearable Intelligent Application.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.jpclett.6c02041","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acs.jpclett.6c02041","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/adma.74345","name":"Presynaptic Optical Modulation Enabled by Dielectric-Embedded Type-II PbS/PbSe Quantum Dots for Near-Infrared Neuromorphic Vision.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.74345","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.74345","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/anie.6931490","name":"Single-Molecule Memristor Realizing Synaptic Plasticity for Neuromorphic Applications.","source":"europepmc","abstract":"Neuromorphic computing, particularly memristor-based architectures, offers a promising route to overcome the von Neumann bottleneck. Single-molecule devices, with their high integration density and low energy consumption, represent an emerging platform for next-generation computing. Here, we report the first optoelectronic volatile single-molecule memristor based on the organic photovoltaic material Y6. The device exhibits reproducible conductance switching driven by electric-field-induced structural relaxation, enabling gradual and linear conductance modulation that mimics synaptic behavior. Under red-light illumination, the Y6 junction shows a remarkable 457% increase in conductance and a significantly reduced switching threshold, demonstrating strong photoresponsivity and low-power operation. Furthermore, frequency-dependent pulse tests clearly reproduce short-term synaptic plasticity (STP), demonstrating the memristor's ability to emulate dynamic synaptic functions. When the experimentally measured current response of the Y6 single-molecule memristor is incorporated into an artificial neural network (ANN) model, the system achieves a speech-recognition accuracy of 71.50%, closely matching that of the benchmark ANN (74.90%). This work pioneers the realization of synaptic functionality in a single-molecule memristor and validates its application within an artificial neural network. It provides a new strategy for developing highly integrated molecular-scale neuromorphic computing devices.","url":"https://doi.org/10.1002/anie.6931490","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/anie.6931490","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acsami.6c07765","name":"Mimicking Pavlovian Conditioning with WSe&lt;sub&gt;2&lt;/sub&gt; Phototransistors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.6c07765","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.6c07765","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/smll.75099","name":"C─H Arylation-Derived Organic Conjugated Molecules for Optoelectronic Synaptic Transistors.","source":"europepmc","abstract":"Photonic organic field-effect transistors (OFETs) mimicking biological neurons hold great promise for neuromorphic computing. However, current organic optoelectronic materials still suffer from limited functionality and the low atom economy of conventional synthesis methods (such as Suzuki and Stille couplings). Herein, two isomeric organic conjugated molecules, p-Ph2FTT and o-Ph2FTT, employing noncovalent conformational locks with excellent planarity are first developed via an eco-friendly, tin-free direct C─H activation strategy. Due to the different fluorine substitution positions on the benzene ring, the p-Ph2FTT molecule exhibits superior planarity compared with o-Ph2FTT, resulting in superior charge transport performance in OFETs. Employing p-Ph2FTT as a photosensitizer, the fabricated p-Ph2FTT/PDVT-10 synaptic transistor exhibits distinct synaptic responses under blue light stimulation, demonstrating excellent synaptic plasticity and a remarkable photosensitivity of 6.7 × 10 4 . Furthermore, an artificial neural network constructed by this transistor achieves an overall recognition accuracy of 92.84% for handwritten digits. This investigation establishes a paradigm for the green synthesis of multifunctional molecular materials, facilitating the integration of eco-friendly chemistry and high-performance electronics for neuromorphic computing.","url":"https://doi.org/10.1002/smll.75099","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.75099","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.3390/biomimetics11080543","name":"Neuromorphic Cardiac Sensing: A Bio-Inspired Spiking Neural Network with Sensory-Adaptive Encoding for Energy-Efficient Arrhythmia Detection from ECG and PPG Signals.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics11080543","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/biomimetics11080543","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:25.465Z"},{"id":"doi:10.1021/acsami.6c07557","name":"Toward Flexible Neuromorphic Spintronics: Field-Free Switching of Synthetic Antiferromagnets on Polyimide Substrates.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.6c07557","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.6c07557","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/advs.76388","name":"Radiation Resilient Synthetic Antiferromagnets-Based Neuromorphic Device for Sea Surface Temperature Reconstruction.","source":"europepmc","abstract":"Reconstruction of sea surface temperature is critical for marine monitoring, yet conventional edge devices based on complementary metal-oxide-semiconductor (CMOS) technology suffer from memory-wall bottlenecks and radiation vulnerability in harsh marine environments. Here, we propose a neuromorphic computing framework based on radiation-tolerant synthetic antiferromagnetic (SAF) synaptic devices through physical-algorithmic co-design to achieve robust sea surface temperature reconstruction. The fabricated Ta/Ir/Fe 0.65 Tb 0.35 /Ru/Co/Pt/Ta-based SAF devices enable field-free magnetization switching via spin-orbit torque, exhibiting multilevel conductance states that naturally emulate synaptic and neuronal functions. Notably, these devices retain over 92% of their performance after 1 Mrad (Si) γ-irradiation, demonstrating inherent radiation tolerance arising from strong antiferromagnetic exchange coupling. By mapping the nonlinear conductance response of SAF onto the cross-attention mechanism of a Perceiver IO architecture, we achieve accurate reconstruction of sea surface temperature fields from sparse sensor inputs. On the National Oceanic and Atmospheric Administration dataset, our system attains a root-mean-square error below 2°C-competitive with deep learning baselines-while projections indicate a potential reduction in energy consumption by an order of magnitude. This work not only advances the application of neuromorphic computing in marine science, but also provides a promising pathway toward \"environmentally adaptive intelligent computing\".","url":"https://doi.org/10.1002/advs.76388","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.76388","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/adma.74136","name":"Anti-Freezing Fiber-Shaped Iontronic Synapses With Ultralow Energy Consumption and High Rectification.","source":"europepmc","abstract":"Fiber-shaped iontronic synapses (FEISs) are emerging as promising building blocks for next-generation wearable neuromorphic computing due to their ability to emulate biological signal transmission and plasticity. However, their practical application remains limited by poor environmental adaptability, high energy consumption, and inadequate rectification behavior. Herein, we report a FEIS with anti‑freezing capability that simultaneously achieves ultralow energy consumption and a high rectification ratio. The FEIS is constructed by directly assembling tetrachlorobenzoquinone and zinc hexacyanoferrate onto carbon nanotube fibers via π-π stacking, combined with a sucrose-modified polyacrylamide hydrogel electrolyte that inhibits ice formation through hydrogen bond regulation. Our FEIS exhibits stable synaptic operation at -20°C, with an ultralow energy consumption of 17 fJ per synaptic event, and a high rectification ratio of 17.9, enabled by asymmetric Faradaic reactions and ionic relaxation kinetics. These characteristics enable the FEIS to achieve robust unidirectional information transmission and stable synaptic operation, even under cryogenic conditions. Furthermore, the FEIS demonstrates reliable operation in ionic logic circuits and robotic control systems, achieving 95.2%-digit recognition accuracy at -20°C. This work expands the operational boundaries of flexible iontronic neuromorphic devices for applications in extreme environments.","url":"https://doi.org/10.1002/adma.74136","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.74136","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1088/1361-6528/ae8bb8","name":"Ultraviolet-responsive IGZO synaptic transistors for photoelectric synergistic modulation and applications.","source":"europepmc","abstract":"Biological visual systems perceive information by processing light signals through the regulation of synaptic weights in the nervous system. Consequently, optoelectronic synaptic devices that directly respond to light stimuli and mimic synaptic plasticity hold immense potential for constructing highly efficient neuromorphic computing systems. This paper reports an optoelectronic synaptic transistor utilizing amorphous indium gallium zinc oxide to serve as the active channel layer of the device. Owing to its wide bandgap, the transistor shows a strong positive photoresponse under ultraviolet light, leading to substantial photocurrent enhancement. Simultaneously, applying electrical pulses suppressed the current response of the device, achieving negative modulation of synaptic weights, which successfully simulates the dynamic balance mechanism between excitatory and inhibitory effects in biological synapses. Based on this phenomenon, this work defines optoelectronic co-modulation as an operation mode that achieves bidirectional dynamic regulation of channel conductance via ultraviolet light-induced carrier excitation and electrical pulse-induced charge trapping. Leveraging the photoelectric synergistic properties of the device, we successfully simulated key biological synaptic functions including postsynaptic current, paired-pulse depression, and the transition from short-term plasticity to long-term plasticity. Based on this, we achieved fundamental 'AND' and 'OR' logic gate functions. Furthermore, when the device was applied to handwritten digit recognition tasks, the neural network achieved an accuracy of 90%.","url":"https://doi.org/10.1088/1361-6528/ae8bb8","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1088/1361-6528/ae8bb8","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/adma.74005","name":"Perception, Synaptic Plasticity, and Spiking Neuron Function Enabled by a 2D Ferroelectric NbOBr&lt;sub&gt;2&lt;/sub&gt; for Neuromorphic Vision.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.74005","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.74005","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1007/s11571-026-10498-0","name":"A lightweight CMOS-based LIF circuit: modeling and spiking regulation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-026-10498-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s11571-026-10498-0","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1016/j.biosystems.2026.105921","name":"Thermodynamic constraints as organizing principles of neural efficiency and cognitive architecture.","source":"europepmc","abstract":"Biological neural systems sustain adaptive cognition under persistent and severe metabolic constraints. This paper develops a multi-scale thermodynamic framework in which those constraints function as organizing principles of neural efficiency and cognitive architecture, addressing four distinct shortcomings of prior accounts. First, I replace the widely cited \"2 bits per synapse\" convention with a probabilistic model grounded in the Bernoulli statistics of downstream neuron firing, yielding a substantially more empirically defensible efficiency ratio of approximately 3.4 × 10 6 times the Landauer limit. Second, I close the quantitative gap between per-synapse ATP chemistry and the brain's globally measured 20 W power budget through an explicit multi-scale bridge. Third, sparse coding, predictive processing, and cross-frequency coupling are derived as Lagrangian solutions to a single metabolic optimisation functional rather than merely described as consistent with energetic principles. Fourth, neuromorphic efficiency comparisons are updated and standardised to an energy-per-bit metric for Intel Loihi 2, BrainScaleS-2, and SpiNNaker2, and are extended to two compute-in-memory architectures - the charge-recycling array processor of Karakiewicz et al. (2012) and the RRAM-based NeuRRAM chip of Wan et al. (2022) - both of which approach or exceed biological synaptic efficiency. Each coding strategy generates testable, quantitatively specified predictions that admit principled rejection. The framework positions metabolic pressure not as an engineering detail extrinsic to neuroscience but as a constitutive selective force in the evolutionary shaping of neural computation.","url":"https://doi.org/10.1016/j.biosystems.2026.105921","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.biosystems.2026.105921","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/adma.74244","name":"A Single OLED With Hybrid Synaptic Plasticity Enabling In Situ Neuromorphic Processing and Visualization.","source":"europepmc","abstract":"As the core interface for human-computer interaction, multitask intelligent display systems face increasingly stringent demands regarding precision and functional integration. However, in existing architectures, light-emitting units only act as passive display terminals. Endowing light-emitting devices with computing capabilities and realizing computing-as-display, thereby reducing transmission overhead and improving display precision, is the key to promoting the further development of this field. Inspired by the human brain, we innovatively report an organic light-emitting diode featuring both long- and short-term synaptic plasticity and synaptic weight-driven electroluminescence. By engineering charge-trapping structures and heterojunction potential wells within a single OLED device, we establish dual-tier synaptic response output channels for information processing, operating independently on second- and millisecond-level timescales under electrical and optical signal modulation, respectively. Following information processing, the processed results are visualized via a globally driven electroluminescence mechanism enabled by synaptic weight modulation. We introduce the Multi-Task Display Fidelity index as a universal metric to quantify the cooperative accuracy between processing and display, achieving a value of 90.86%. Furthermore, the processing-display coupling index of the device surpasses the corresponding index of mainstream CMOS architectures by 67.8%. This work demonstrates the immense potential of hybrid synaptic plasticity OLEDs for multitask intelligent display.","url":"https://doi.org/10.1002/adma.74244","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.74244","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/adma.73598","name":"Bioinspired Nanofluidic Memristors Based on Polyelectrolyte Conformation for Synaptic Learning and in-Memory Logic Computing.","source":"europepmc","abstract":"Bioinspired neuromorphic and in-memory computing requires devices that store and process information through ionic dynamics analogous to biological synapses. Here, we report a polyelectrolyte conformational nanofluidic memristor (PCM) that integrates synaptic plasticity, neuromorphic learning, and stateful ionic logic within a single aqueous platform. The device operates through electric-field-driven, reversible conformational transitions of polyelectrolytes confined inside graphene oxide nanochannels, enabling analog conductance tuning, a sharp, tunable switching threshold, and an ON/OFF ratio exceeding 160. These conformational dynamics endow the PCM with rich synaptic functions, including long-term potentiation and depression, multilevel memory retention, and symmetric weight update rules. By directly mapping the experimentally measured potentiation/depression curves into a physical learning model, we demonstrate high-accuracy neuromorphic learning, achieving 97.1% recognition accuracy on the Modified National Institute of Standards and Technology (MNIST) handwritten-digit dataset. Beyond learning, interconnected PCM units perform stateful ionic OR, IMP, and NAND operations, establishing universal in-memory logic within the same ionic platform. This work introduces a bioinspired nanofluidic computing paradigm that unites the adaptive learning of neural networks and deterministic logic, paving the way to scalable and brain-like ionic processors.","url":"https://doi.org/10.1002/adma.73598","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.73598","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1038/s41467-026-73669-x","name":"Homeostatic dendritic neuron based on co-integrated volatile and non-volatile memristors for neuromorphic processing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-73669-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-73669-x","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/advs.76163","name":"Dual-Mode Nanoporous SiO&lt;sub&gt;2&lt;/sub&gt; Memristors with Coexisting Volatile and Nonvolatile Dynamics for Reservoir Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.76163","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.76163","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1007/s40820-026-02288-4","name":"Ion Compensation-Assisted Photolithography Enables High-Resolution Electrolytes for Neuromorphic Transistors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s40820-026-02288-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s40820-026-02288-4","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/adma.74080","name":"Optoelectronic Nanofluidic Neural Networks for Ionic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.74080","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.74080","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1038/s41377-026-02357-8","name":"Optical singularity protractor for rotating metrology with neuromorphic sensing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41377-026-02357-8","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41377-026-02357-8","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/adma.74383","name":"End-to-End Neuromorphic Cryptosystems Using n-type Organic Optoelectrochemical Synapses.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.74383","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.74383","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1038/s41378-026-01379-x","name":"Hysteresis-aware MEMS neuromorphic networks for embedded sensing and computation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41378-026-01379-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41378-026-01379-x","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acsnano.6c02136","name":"Ferroelectric Gate-All-Around Transistors for 3D-Integrated Electronics and Neuromorphic Vision.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.6c02136","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsnano.6c02136","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1002/smll.74904","name":"Hydrogel Covered Solid-State Nanopores as Iontronic Memristors for Neuromorphic and Logic Functions.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.74904","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.74904","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.3390/s26133992","name":"Spike-Driven Neuromorphic Sensing for Energy-Proportional Indoor Air Quality Monitoring in Multi-Zone IoT-Enabled Smart Building Environments.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s26133992","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/s26133992","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1016/j.neunet.2026.109043","name":"Coupled gradient-evolutionary learning in sparse memristive neuromorphic networks for robust edge intelligence.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.109043","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.109043","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acsnano.6c06536","name":"In-Liquido Reservoir Computing with Distributed and Globally Reconfigurable Dynamics for Task-Adaptable Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.6c06536","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsnano.6c06536","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1038/s41598-026-52562-z","name":"Sawtooth anisotropy-driven skyrmion and domain wall dynamics for artificial neuron applications.","source":"europepmc","abstract":"Spintronic-based brain-inspired neuromorphic computing has recently attracted significant attention due to the exceptional properties of magnetic microstructures, including nanoscale dimensions, high stability, and low energy consumption. Despite these advantages, the practical implementation of such microstructures into functional devices remains challenging due to complex fabrication and unwanted pinning effects, which hinder reliable operation. In this work, we present a simulation-based design of an energy-efficient neuromorphic device utilizing both magnetic skyrmions and domain walls (DWs) as information carriers. By engineering the system anisotropy into a sawtooth-type, forming alternating high and low -anisotropy regions where current pulses are required only to overcome local energy barriers at high-anisotropy regions, enabling controlled and energy-efficient propagation. This mechanism enables stable, step-wise motion of magnetic microstructures and successfully emulates the integrate-and-fire (IF) behaviour of biological neurons. Thus, proposed design presents an experimentally reliable and energy efficient external stimuli approach for tailoring magnetic microstructures dynamic behaviours, resulting in low energy consumption of 23.66 fJ per spike paving the way for the development of skyrmion-based futuristic neuromorphic computing device applications.","url":"https://doi.org/10.1038/s41598-026-52562-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-52562-z","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.3390/ma19143029","name":"Stable Low-Voltage Organic Memristors Enabled by Templated Crystallization and Quantum-Dot-Regulated Filament Formation.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/ma19143029","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/ma19143029","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/adma.74226","name":"940 Nm Near-Infrared Photosynapses Based on Sn─Pb Perovskite for Efficient Face Recognition.","source":"europepmc","abstract":"Tin-lead perovskites offer great potentials for neuromorphic optoelectronics owing to their narrow bandgap and robust near-infrared (NIR) absorption. However, high-performance three-terminal artificial synapses based on these materials remain scarce due to challenges in forming high-quality semiconductor films. Here, we demonstrate a perovskite synaptic field-effect transistor (FET) capable of efficient 940 nm sensing and neuromorphic modulation, enabled by uniform, high-crystallinity FASn 0.8 Pb 0.2 I 3 thin films. A molecular additive, 1-bromo-4-(methylsulfinyl)benzene (BMSB), precisely regulates crystallization, enlarges grains, and suppresses trap formation, thereby reducing ion migration and enhancing charge transport. The optimized devices achieve high hole mobility and an exceptional responsivity of 231 A W -1 at 940 nm, marking the first demonstration of efficient 940 nm infrared photoresponse in three-terminal perovskite artificial synapses. Benefiting from balanced ion-electron coupling, the devices exhibit reliable synaptic behaviors, including excitatory postsynaptic currents, paired-pulse facilitation, and learning-forgetting cycles. Integrated into a reservoir-computing framework, the synaptic FETs enable accurate NIR facial recognition, underscoring their potential for in-sensor computing. This work establishes a molecular-level strategy to harmonize ionic and electronic processes in Sn─Pb perovskites, advancing light-programmable neuromorphic transistors for next-generation intelligent NIR vision systems.","url":"https://doi.org/10.1002/adma.74226","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.74226","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acsami.6c07753","name":"Earthworm-Inspired Self-Powered Multistimuli Neuromorphic Vision Skin with Homogeneous Ion Heterogel Arrays.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.6c07753","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.6c07753","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1016/j.neunet.2026.109370","name":"MT-RevSNN: Memory and time efficient reversible framework for hierarchical spiking transformer.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.109370","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.109370","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:25.465Z"},{"id":"doi:10.1002/adma.73410","name":"Three-Dimensional Garment Architectures for Tactile Embodied Intelligence.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.73410","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.73410","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1038/s41467-026-75488-6","name":"Realization of the Bienenstock-Cooper-Munro rule in a single memristor.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-75488-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-75488-6","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1038/s41467-026-73825-3","name":"Volatile self-selective memristive neuron for millisecond-latency neuromorphic object detection at the edge.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-73825-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-73825-3","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acsabm.6c01280","name":"Nanostructured Zirconia Thin Films as a Neurogliomorphic Interface for Neural Cells of Central and Peripheral Nervous Systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsabm.6c01280","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsabm.6c01280","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1038/s42004-026-02122-3","name":"Rapid and energy-efficient ultra-large library screening for drug discovery on a SpiNNaker2 neuromorphic chip.","source":"europepmc","abstract":"The virtual screening of make-on-demand small molecule libraries can prioritize drug candidates for rapid experimental validation to accelerate pre-clinical drug discovery. As ultra-large libraries grow to billions of compounds, exhaustive screening incurs prohibitive costs and energy consumption. We address this challenge with the neuromorphic SpiNNaker2 system, designed for massively parallel AI tasks. Here, we show the implementation of a ligand-based screening pipeline on a 152-core SpiNNaker2 chip. We adapted feed-forward neural networks trained on 2D molecular descriptors to screen 19 billion molecules from the Enamine REAL space. We benchmarked our approach against an NVIDIA Jetson Orin Nano, a GPU-accelerated low-power AI system. Inference on the SpiNNaker2 chip was approximately 4 times faster, yielding 60% higher overall throughput. Meanwhile, SpiNNaker2 consumed about 86% less energy. These results provide a foundation for the deployment of SpiNNaker2 high performance computing clusters and establish application-specific hardware as a scalable and sustainable avenue for cheminformatics.","url":"https://doi.org/10.1038/s42004-026-02122-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s42004-026-02122-3","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1016/j.neunet.2026.109395","name":"Dendritic functional heterogeneity with feedback control facilitates stable spatiotemporal representation in spiking neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.109395","authors":["Qiulin Li","Junsong Wang","Jianfang Wu"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.109395","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1021/acsami.6c02560","name":"A-Site Cation Functional Engineering Enables Lead-free Perovskite Photosynapse for Neuromorphic Visual Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.6c02560","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.6c02560","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/smll.75053","name":"Molecular Backbone Regulation for Enhanced Ion Retention in Nonvolatile Organic Electrochemical Synaptic Transistors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.75053","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.75053","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1038/s41598-026-55364-5","name":"A fully-CMOS spiking LIF neuron implementation for optimized STDP learning on memristor.","source":"europepmc","abstract":"The growing demand for fast and energy-efficient computing has motivated the development of neuromorphic hardware inspired by biological neural systems. Spiking neural networks (SNNs), as the third generation of neural networks, offer an event-driven and highly parallel computing paradigm that is well suited for such applications. A key challenge in hardware SNNs is the efficient implementation of synaptic learning mechanisms, particularly spike-timing-dependent plasticity (STDP), with minimal circuit complexity and energy overhead. In this work, we propose a fully CMOS leaky integrate-and-fire (LIF) neuron designed to enable local, on-chip STDP-like learning when interfaced with analog memristive synapses. The proposed neuron generates a bipolar output spike composed of both positive and negative voltage pulses, allowing direct modulation of memristor conductance without the need for complex peripheral circuits or explicit timing storage elements. The neuron operates in two distinct modes of training mode, which produces bipolar spikes to support synaptic updates, and inference mode, which generates a single unipolar spike while deactivating non-essential circuitry to reduce power consumption. To validate the proposed design, a proof-of-concept 15×4 spiking neural network incorporating a winner-takes-all (WTA) mechanism is implemented in 65-nm CMOS technology and evaluated using circuit-level simulations. The results demonstrate correct local synaptic adaptation, stable neuron operation under process variations, and successful pattern association during training and inference. The network processes each training pattern within 0.6 ms and performs inference within 0.32 ms.","url":"https://doi.org/10.1038/s41598-026-55364-5","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-55364-5","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/tnnls.2026.3687785","name":"SALMON: Self-Adaptive Learning Model on Neuromorphic Hardware.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tnnls.2026.3687785","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1109/tnnls.2026.3687785","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acsami.6c02631","name":"Zwitterion-Modified PMMA Interlayers for Reliable Dual-Mode Organic Neuromorphic Devices.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.6c02631","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.6c02631","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1039/d6nh00013d","name":"Revealing the potential of 2D WS&lt;sub&gt;2&lt;/sub&gt; memristors as an artificial synapse with resilient gradual behavior at high temperatures for neuromorphic applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d6nh00013d","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d6nh00013d","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/adma.74418","name":"Grain Boundary Enabled Diamond Memristor.","source":"europepmc","abstract":"Diamond has been recognized as the ultimate semiconductor due to its ultra-wide bandgap, exceptional carrier mobility, high breakdown voltage, and superior thermal conductivity. However, its application in memristors is significantly limited by challenges in modulating its electrical conductivity and its chemical stability. Here, by leveraging the rapid metal-diamond reactions at diamond grain boundaries (GBs), we constructed vertical ion migration channels along the GBs and realized the nonvolatile resistive switching behavior in polycrystalline diamond (Poly-D). The diamond memristor presents a high switching ratio (∼10 4 ) along with reliable cycling and retention performance over a wide temperature range from -150°C to 600°C. In-situ biasing transmission electron microscopy observations confirm the reproducible formation and rupture of Ag conductive filaments (Ag CFs) along the constructed channels at the GBs. The diamond memristor demonstrates its capabilities as an artificial synapse and in biological nociception. Our work demonstrates the application of diamond in memristors and highlights its potential for neuromorphic computing, particularly under extreme conditions.","url":"https://doi.org/10.1002/adma.74418","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.74418","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1007/s11571-026-10476-6","name":"From nonlinear neuronal dynamics to AI-optimized VLSI hardware: multiplier-free FPGA implementation of memristive FN-HR coupled neural networks for intelligent systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-026-10476-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s11571-026-10476-6","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1038/s41467-026-75808-w","name":"Wavelength-encoded neuromorphic inference enabled by microcavity MoS&lt;sub&gt;2&lt;/sub&gt; photodetector arrays.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-75808-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-75808-w","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acs.nanolett.5c06290","name":"Lorentzian Switching Dynamics in HZO-Based FeMEMS Synapses for Neuromorphic Weight Storage.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.5c06290","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acs.nanolett.5c06290","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1038/s41467-026-75870-4","name":"Ultrafast multi-level control of sub-50 nm skyrmions in a Pd-intercalated van der Waals magnet.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-75870-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-75870-4","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1038/s42256-026-01254-4","name":"Neural sampling from cognitive maps enables goal-directed imagination and planning.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s42256-026-01254-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s42256-026-01254-4","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acsami.6c06343","name":"Multidimensional Interface Structure Design for High-Efficiency Optically Controlled Semiconductor Devices: A Case Study on Memristive Synapses.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.6c06343","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.6c06343","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1038/s41378-026-01423-w","name":"Spin-based in-sensor computing magnetic tactile sensor for rapid identification of underwater targets.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41378-026-01423-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41378-026-01423-w","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1039/d6nr00412a","name":"Near-infrared photovoltaic gating enables polarity-reconfigurable WSe&lt;sub&gt;2&lt;/sub&gt; phototransistors for in-sensor computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d6nr00412a","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d6nr00412a","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1039/d5nr04850h","name":"&lt;i&gt;Operando&lt;/i&gt; thermal behaviour of transistor-integrated memristors and its implications on online and offline learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5nr04850h","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d5nr04850h","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1126/sciadv.aee9649","name":"Programmable photonic neural engine with all-optical nonlinear activation and 40,000 connections.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.aee9649","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1126/sciadv.aee9649","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/smll.73259","name":"Vertical Growth of Ultrathin Bi&lt;sub&gt;2&lt;/sub&gt;WO&lt;sub&gt;6&lt;/sub&gt; Nanosheets for Visual Optoelectronic Neuromorphic Devices.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.73259","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.73259","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1038/s41598-026-59993-8","name":"Linking device dynamics to neural network performance in ionically gated synaptic transistors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-59993-8","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-59993-8","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/smll.74398","name":"Anion-Engineered Organic Electrochemical Transistors With Multi-Timescale Synaptic Dynamics for Task-Adaptive Spiking Neural Networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.74398","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.74398","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1021/acs.nanolett.6c00609","name":"Permeable Proton Transport and Hydrogenation Attained by ONCS-Induced Graphene Nanosheet Film for Neuromorphic Memory Devices.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.6c00609","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acs.nanolett.6c00609","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1002/advs.77150","name":"Analog Synaptic Plasticity in 2D Layered Material Iontronic Memtransistors for Brain-Inspired Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.77150","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.77150","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acsami.6c01527","name":"Event-Driven Sentinel-Expert Neuromorphic Vision Enabled by Polarization-Reconfigurable Organic Ferroelectric Phototransistors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.6c01527","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.6c01527","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1021/acsami.6c06334","name":"Polarization-State-Dependent Charge Screening in Metal-Ferroelectric-Metal Memcapacitors Enabled by an IGZO Oxygen Reservoir Layer.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.6c06334","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.6c06334","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.64898/2026.03.18.712691","name":"A genetically encoded local learning rule enables physical learning in engineered bacteria","source":"preprints","abstract":"Training physical neural networks directly in matter remains difficult because most platforms do not store and update weights within the same physical substrate. Here we show that engineered Escherichia coli can implement a genetically encoded local learning rule acting on persistent biological memory. We introduce memregulons: bacterial memory elements in which coupled plasmids store an analogue weight as the relative abundance of P1 within the P1+P2 plasmid pool. Environmental inputs activate local promoters, and a shared sublethal kanamycin signal converts promoter activity into differential growth that lowers the stored P1 fraction. In single strains, flow-cytometry trajectories across distinct promoters support the predicted dependence of weight change on learning-channel activity and standing population variance. At the single-cell level, repeated negative learning reshapes the stored weight distribution as it approaches the lower boundary. In mixed populations and co-cultures, one shared negative learning signal selectively rewrites active memregulons, enabling externally routed supervised tic-tac-toe lessons. We then generalise the architecture across orthogonal chemical inputs and combinatorial promoters, and use experimentally measured updates in hybrid analyses of winner-take-all and nonlinear-classifier tasks. These results establish physical learning in living matter through local negative updates of genetically encoded analogue weights.","url":"https://doi.org/10.64898/2026.03.18.712691","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.03.18.712691","addedAt":"2026-09-01T01:48:21.766Z","updatedAt":"2026-09-01T01:48:23.168Z"},{"id":"doi:10.1103/physrevapplied.23.044013","name":"Exploring structural nonlinearity in binary polariton-based neuromorphic architectures","source":"crossref","abstract":"","url":"https://doi.org/10.1103/physrevapplied.23.044013","authors":["Evgeny Sedov","Alexey Kavokin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-04T10:30:26Z","doi":"10.1103/physrevapplied.23.044013","addedAt":"2026-09-01T01:48:22.058Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/icnc64304.2024.10987789","name":"Output Synchronization of Multi-Layer Networks with Output Coupling Under Dynamic Event-Triggered Control","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987789","authors":["Wenyan Xi","Juan Yu","Cheng Hu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987789","addedAt":"2026-09-01T01:48:22.058Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.21203/rs.3.rs-1270383/v1","name":"Lead federated neuromorphic learning for edge artificial intelligence","source":"crossref","abstract":"Abstract Despite the great potential of edge artificial intelligence (AI) which is the convergence of edge computing and AI, it acquires sufficiently large/diverse datasets and requires high energy consumption for model training on resource-constrained edge devices, hence hindering the application of edge AI at edge devices. This paper proposes a lead federated neuromorphic learning (LFNL) technique, which is a decentralized energy-efficient brain-inspired computing method, enabling edge devices to collaboratively train a global model while preserving privacy. Experimental results validate that LFNL substantially reduces the data traffic by &gt;3.5× and computational latency by &gt;2.0× compared to centralized learning, with a comparable classification accuracy, as well as significantly outperforms local learning with uneven dataset distribution among edge devices. Meanwhile, LFNL significantly reduces the energy consumption by &gt;4.5× compared to standard federated learning with a slight accuracy loss up to 1.5%. Therefore, the newly proposed LFNL can facilitate the development of brain-inspired computing and edge AI.","url":"https://doi.org/10.21203/rs.3.rs-1270383/v1","authors":["Helin Yang","Kwok-Yan Lam","Liang Xiao","Zehui Xiong","Hao Hu","Dusit Niyato","Vincent Poor"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-01-21T15:27:19Z","doi":"10.21203/rs.3.rs-1270383/v1","addedAt":"2026-09-01T01:48:22.058Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.21203/rs.3.rs-9546289/v1","name":"Spike-Based Neuromorphic Processing of Encrypted Data with BioEncryptSNN","source":"crossref","abstract":"Abstract Deep learning is increasingly applied to everyday problems, particularly through neural networks. As these models grow in computational load and resource requirements, cloud-based solutions have become common. Spiking Neural Net-works (SNNs), the third generation of neural networks, offer improved efficiency and reduced power consumption by mimicking the brain’s sparse, dynamic, and event-driven computation. However, the use of cloud platforms raises concerns about preserving the privacy of confidential data processed by remote servers. Among the solutions proposed, asymmetric encryption is particularly promising because it uses a public–private key pair to secure communication without requiring shared secrets. This enables clients to send encrypted data to models owned by external parties while maintaining privacy. This article introduces BioEncryptSNN, an SNN-based framework for spike-based processing of encrypted data. Rather than proposing a new cryptographic primitive, BioEncryptSNN converts ciphertext into spike trains and exploits temporal neural dynamics to enable neuromorphic ciphertext processing, robust-ness analysis, and reliable plaintext recovery through the underlying encryption algorithms. The framework was benchmarked against widely used cryptographic standards, including Advanced Encryption Standard (AES)-128, Rivest-Shamir-Adleman (RSA)-2048, Data Encryption Standard (DES), ChaCha20, and Elliptic Curve Integrated Encryption Scheme (ECIES). Results show that BioEncryptSNN preserves plaintext integrity and, under the evaluated experimental conditions, achieves lower mean end-to-end latency than the selected AES soft-ware baseline while maintaining robustness under noisy conditions. Performance depends on encoding overhead, implementation details, and execution context, and may vary across hardware and deployment environments. BioEncryptSNN achieved a mean execution time of 0.016 ms, low variability, and a throughput of62,500 iterations per second, corresponding to a 1.19× speed improvement over the PyCryptodome AES baseline under the evaluated experimental conditions. The framework further demonstrates adaptability across symmetric and asymmetric ciphers, spanning block, stream, and public-key encryption settings, which supports its potential as a scalable approach to encrypted data processing for downstream applications such as secure analytics and vulnerability assessment. The cryptographic security of the framework is inherited from the underlying encryption algorithms, whereas the SNN enables ciphertext processing without providing formal mathematical guarantees of cryptographic strength. Accordingly, BioEncryptSNN is intended primarily as a proof-of-concept framework for neuromorphic ciphertext processing rather than as a replacement for production cryptographic systems.","url":"https://doi.org/10.21203/rs.3.rs-9546289/v1","authors":["Mahitha Pulivathi","Ana Fontes Rodrigues","Isibor Kennedy Ihianle","Andreas Oikonomou","Srinivas Boppu","Pedro Machado"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-04T11:16:43Z","doi":"10.21203/rs.3.rs-9546289/v1","addedAt":"2026-09-01T01:48:22.058Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1088/2634-4386/ac676a","name":"In-materio computing in random networks of carbon nanotubes complexed with chemically dynamic molecules: a review","source":"crossref","abstract":"Abstract The need for highly energy-efficient information processing has sparked a new age of material-based computational devices. Among these, random networks (RNWs) of carbon nanotubes (CNTs) complexed with other materials have been extensively investigated owing to their extraordinary characteristics. However, the heterogeneity of CNT research has made it quite challenging to comprehend the necessary features of in-materio computing in a RNW of CNTs. Herein, we systematically tackle the topic by reviewing the progress of CNT applications, from the discovery of individual CNT conduction to their recent uses in neuromorphic and unconventional (reservoir) computing. This review catalogues the extraordinary abilities of random CNT networks and their complexes used to conduct nonlinear in-materio computing tasks as well as classification tasks that may replace current energy-inefficient systems.","url":"https://doi.org/10.1088/2634-4386/ac676a","authors":["H Tanaka","S Azhari","Y Usami","D Banerjee","T Kotooka","O Srikimkaew","T-T Dang","S Murazoe","R Oyabu","K Kimizuka","M Hakoshima"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-14T22:15:53Z","doi":"10.1088/2634-4386/ac676a","addedAt":"2026-09-01T01:48:22.058Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1103/physreva.72.052328","name":"Neuromorphic quantum computation with energy dissipation","source":"crossref","abstract":"","url":"https://doi.org/10.1103/physreva.72.052328","authors":["Mitsunaga Kinjo","Shigeo Sato","Yuuki Nakamiya","Koji Nakajima"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-11-28T15:25:22Z","doi":"10.1103/physreva.72.052328","addedAt":"2026-09-01T01:48:22.058Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1103/s22f-n7w8","name":"Analog dual classifier via a time-modulated neuromorphic metasurface","source":"crossref","abstract":"","url":"https://doi.org/10.1103/s22f-n7w8","authors":["M. Mousa","M. Moghaddaszadeh","M. Nouh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-05T21:20:37Z","doi":"10.1103/s22f-n7w8","addedAt":"2026-09-01T01:48:22.058Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.21203/rs.3.rs-83699/v1","name":"An electronic neuromorphic system for real-time detection of High Frequency Oscillations (HFOs) in intracranial EEG","source":"crossref","abstract":"Abstract The analysis of biomedical signals for clinical studies and therapeutic applications can benefit from compact and portable devices that can process these signals locally, in real-time, without the need for off-line processing. An example is the recording of intracranial EEG(iEEG) during epilepsy surgery with the detection of High Frequency Oscillations (HFOs, 80-500 Hz), which are a biomarker for the epileptogenic zone. Conventional approaches of HFO detection involve the offline analysis of prerecorded data, often on bulky computers. However, clinical applications during surgery or in long-term intracranial recordings demand a self-sufficient embedded device that is battery-powered to avoid interfering with other electronic equipment in the operation room. Mixed-signal and analog-digital neuromorphic circuits offer the possibility of building compact, embedded, and low-power neural network processing systems that can analyze data on-line and produce results with short latency in real-time. These characteristics are well suited for clinical applications that involve the processing of biomedical signals at (or very close to) the sensor level. In this work, we present a neuromorphic system that combines for the first time a neural recording headstage with a signal-to-spike conversion circuit and a multi-core spiking neural network (SNN) architecture on the same die for recording, processing, and detecting clinically relevant HFOs in iEEG from epilepsy patients. The device was fabricated using a standard 0.18μm CMOS technology node and has a total area of 99 mm 2 . We demonstrate its application to HFO detection in the iEEG recorded from 9 patients with temporal lobe epilepsy who subsequently underwent epilepsy surgery. The total average power consumption of the chip during the detection task was 614.3 μW. We show how the neuromorphic system can reliably detect HFOs: the system predicts postsurgical seizure outcome with state-of-the-art accuracy, specificity, and sensitivity (78%, 100%, and 33% respectively). This is the first feasibility study towards identifying relevant features in intracranial human data in real-time, on-chip, using event-based processors and spiking neural networks. By providing “neuromorphic intelligence” to neural recording circuits the approach proposed will pave the way for the development of systems that can detect HFO areas directly in the operation room and improve the seizure outcome of epilepsy surgery.","url":"https://doi.org/10.21203/rs.3.rs-83699/v1","authors":["Mohammadali Sharifhazileh","Karla Burelo","Johannes Sarnthein","Giacomo Indiveri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-10-01T21:56:33Z","doi":"10.21203/rs.3.rs-83699/v1","addedAt":"2026-09-01T01:48:22.058Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.54254/2753-8818/2025.ad26488","name":"Energy-Efficient Neuromorphic Chips for Real-Time Robotic Control: A Review","source":"crossref","abstract":"Neuromorphic computing has gained increasing attention as a bio-inspired solution to the limitations of traditional computing systems in power and real-time constraints. In robotic control tasks, real-time processing and energy efficiency are crucial, especially for autonomous and mobile systems. Neuromorphic chips mimic the structure and operation of biological neurons, enabling low-latency and low-power processing. This review examines the architectures, performance benchmarks, and application cases of mainstream neuromorphic hardware platforms used in robotic perception and control. It also compare their energy consumption and latency with conventional control platforms. Furthermore, this paper identifies key challenges in system integration and suggests future directions including improved scalability, online learning, and the combination with edge AI frameworks. The paper finds that neuromorphic chips can significantly reduce energy consumption and improve real-time performance in robotic control. However, challenges in algorithm adaptation, standardization, and hardware integration remain. This study aims to provide researchers with insights into the practical implementation of neuromorphic control systems in energy-sensitive robotic applications.","url":"https://doi.org/10.54254/2753-8818/2025.ad26488","authors":["Shuming Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-03T04:50:30Z","doi":"10.54254/2753-8818/2025.ad26488","addedAt":"2026-09-01T01:48:22.058Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1109/iccsp.2015.7322626","name":"A review on methods, issues and challenges in neuromorphic engineering","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccsp.2015.7322626","authors":["Mohammed Riyaz Ahmed","B.K. Sujatha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-11-12T23:12:44Z","doi":"10.1109/iccsp.2015.7322626","addedAt":"2026-09-01T01:48:22.058Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.1103/physreve.111.044214","name":"Inductively coupled Josephson junctions: A platform for rich neuromorphic dynamics","source":"crossref","abstract":"","url":"https://doi.org/10.1103/physreve.111.044214","authors":["G. Baxevanis","J. Hizanidis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-21T10:05:16Z","doi":"10.1103/physreve.111.044214","addedAt":"2026-09-01T01:48:22.058Z","updatedAt":"2026-09-01T01:48:22.058Z"},{"id":"doi:10.56147/aaiet.2.2.117","name":"Neuromorphic Modular Intelligence Architecture: Overcoming Transformer Limits Toward AGI Beyond Monolithic LLM Limits","source":"crossref","abstract":"Transformer-based Large Language Models (LLMs) achieve remarkable pattern matching but struggle with deep reasoning due to fixed computation depth, bounded inference complexityandlimited token memory. These structural constraints (e.g.,fixed-layer depth yields only O(1)-depth circuit expressivityandcontext windows cap memory) hinder tasks requiring iterative, algorithmic reasoning. I propose the Neuromorphic Modular Intelligence Architecture (NMIA), a brain inspired system combining multiple specialized LLM modules with persistent memory, external symbolic verificationanda non-linguistic control layer.I analyze asymptotic complexity: Amonolithic transformer incurs O(n2d)cost per inference (with ntokens and dimension d), while NMIA with kmodules of size n/k yields approximately O(n2d/k + O(nd)), a factor-k speedup. In a simulated experiment (n=5000), NMIA (with 5 modules) significantly outperforms a monolithic LLM on a realistic reasoning task: Modular inference is faster (mean 48.6ms vs.104.4ms, d=6.63, 95% CI (51.5, 60.2)) and more accurate (accuracy 85.4% vs.69.4%, d=2.04, ∆=0.16, 95% CI (0.12, 0.20)). These results support NMIA as a viable AGI path: It demonstrates that careful modular decomposition and memory can circumvent fundamental transformer limitations without invoking purely linguistic reasoning. The analysis and simulation together argue that while monolithic LLMs have formal limits on computation, a neuromorphic, multi-agent design can extend reasoning capacity and is a promising route toward general intelligence.","url":"https://doi.org/10.56147/aaiet.2.2.117","authors":["Anindya Mishra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-17T06:53:32Z","doi":"10.56147/aaiet.2.2.117","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.2139/ssrn.6301398","name":"Neuromorphic Visual Odometry with Spiking Neural Networks: Evaluation and Benchmarking on the Akida Platform","source":"crossref","abstract":"Event-driven vision sensors and neuromorphic processors represent two converging technologies enabling low-latency, energy-efficient perception for autonomous systems. This paper presents a spiking neural network (SNN)–based visual odometry (VO) framework that exploits the asynchronous output of an event camera to estimate 6-DoF motion. To enable compatibility with convolutional SNN architectures, incoming event streams are temporally aggregated into voxel-grid representations, trading strict event-level asynchrony for structured spatiotemporal encoding. These resulting representations are processed through a convolutional spiking architecture trained with LiDAR–IMU-fused ground truth poses. Evaluations on diverse indoor, outdoor, and hybrid environments demonstrate accurate motion estimation over long-duration trajectories of up to 1066 s (approximately 1.07 km of traversal), achieving a mean translation RMSE of 0.77 m and relative pose error of 0.18 m across test sequences. To assess neuromorphic deployment efficiency, a behaviorally comparable Akida-compatible model was benchmarked using BrainChip’s MetaTF runtime environment. The event-based implementation achieved an average inference latency of 63.15 ms with an estimated energy consumption of only 1.89 mJ per sample under MetaTF-based neuromorphic execution. Compared to conventional CPU and GPU baselines, this corresponds to energy reductions exceeding three orders of magnitude, highlighting the strong potential for event-based spiking VO for embedded and power-constrained robotic platforms.","url":"https://doi.org/10.2139/ssrn.6301398","authors":["Sangay Tenzin","Alexander Rassau","Douglas Chai","MD Moniruzzaman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-25T06:36:36Z","doi":"10.2139/ssrn.6301398","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1007/978-3-032-12107-3_6","name":"Substrates","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-12107-3_6","authors":["Elliot Kisiel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-19T17:21:55Z","doi":"10.1007/978-3-032-12107-3_6","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1142/13881","name":"Artificial Intelligence of Neuromorphic Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1142/13881","authors":["Klaus Mainzer"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-23T03:26:52Z","doi":"10.1142/13881","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1039/d6nh00013d/v1/review1","name":"Review for \"Revealing the Potential of 2D WS2 Memristors as an Artificial Synapse with Resilient Gradual Behavior at High Temperatures for Neuromorphic Applications\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d6nh00013d/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-07T21:14:19Z","doi":"10.1039/d6nh00013d/v1/review1","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.29363/nanoge.matsusspring.2026.210","name":"Engineering Stable Perovskite Nanowire Memristors  for Next-Generation Neuromorphic and Memory Devices","source":"crossref","abstract":"","url":"https://doi.org/10.29363/nanoge.matsusspring.2026.210","authors":["Swapnadeep Poddar","Zhiyong Fan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-16T08:04:37Z","doi":"10.29363/nanoge.matsusspring.2026.210","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1039/d6nh00013d/v2/review2","name":"Review for \"Revealing the Potential of 2D WS2 Memristors as an Artificial Synapse with Resilient Gradual Behavior at High Temperatures for Neuromorphic Applications\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d6nh00013d/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-07T21:14:19Z","doi":"10.1039/d6nh00013d/v2/review2","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1007/978-3-032-04129-6_19","name":"Neuromorphic Spintronics","source":"openalex","abstract":"Neuromorphic spintronics combines two advanced fields in technology, neuromorphic computing, and spintronics, to create brain-inspired, efficient computing systems that leverage the unique properties of the electron’s spin. In this book chapter, we first introduce both fields—neuromorphic computing and spintronics—and then make a case for neuromorphic spintronics. We discuss concrete examples of neuromorphic spintronics, including computing based on fluctuations, artificial neural networks, and reservoir computing, highlighting their potential to revolutionize computational efficiency and functionality.","url":"https://doi.org/10.1007/978-3-032-04129-6_19","authors":["Atreya Majumdar","Karin Everschor-Sitte"],"tags":["Neuromorphic engineering","Reservoir computing","Computer science","Leverage (statistics)","Spintronics"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2026-01-01","doi":"10.1007/978-3-032-04129-6_19","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"doi:10.1002/aisy.70508","name":"Low‐Voltage Operation of IGZO Memtransistors Enabled by Coupling Enhancement Through 2T Drain‐Driven Operation for Neuromorphic Computing","source":"crossref","abstract":"Neuromorphic computing has emerged as a promising approach to overcome the limitations of the von Neumann architecture by enabling energy‐efficient data processing. Here, we demonstrate a two‐terminal (2T) flash‐type indium–gallium–zinc oxide memtransistor for voltage‐scalable and compact neuromorphic systems. By employing drain‐induced Fowler–Nordheim tunneling, the proposed device achieves an operating voltage below 10 V while maintaining a large memory window of 6 V and a high on/off ratio of 10 9 . The reduced operating voltage is enabled by coupling enhancement through 2T drain‐driven operation. The device represents linear weight modulation and stable retention with only 0.31% change after 10 4 s, and robust endurance over 10 000 cycles. As a system‐level validation of the 2T drain‐driven platform, a memtransistor array is fabricated and exhibits uniform device characteristics. Furthermore, spiking neural network simulations incorporating nonideal characteristics demonstrate that an intensity‐based input encoding improves classification accuracy with reduced time steps for both Fashion‐MNIST and CIFAR‐10 datasets.","url":"https://doi.org/10.1002/aisy.70508","authors":["Junhyeong Park","Sunyeol Bae","Yumin Yun","Chae‐Hwan Park","Donghyeon Lee","Soo‐Yeon Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-18T00:34:21Z","doi":"10.1002/aisy.70508","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1016/j.mssp.2025.110056","name":"Regulating oxygen vacancies to achieve stable non-volatile switching characteristics and neuromorphic computing in a-Ga2O3 based memristors","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.mssp.2025.110056","authors":["Yuanyuan Zhu","Xin Wang","Miao Zhang","Yunfei Zhang","Shuo Liu","Hongjun Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-13T14:13:37Z","doi":"10.1016/j.mssp.2025.110056","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1002/adom.71477","name":"LSPR‐Enhanced Reconfigurable NIR Organic Synapse for Neuromorphic Computing and Biomedical Sensing","source":"crossref","abstract":"ABSTRACT Light‐controlled memristors are a key technology for overcoming the computational limits of von Neumann architectures, offering great potential for next‐generation neuromorphic computing. Organic optical synapses offer a promising route toward low‐power, multifunctional neuromorphic hardware, yet their weak response to near‐infrared (NIR) light limits applications in biomedical sensing and intelligent vision. Here, a reconfigurable NIR synaptic device based on an organic heterojunction (ITO/PEDOT:PSS:AgTNPs/PM6:L8‐BO/PFN‐Br/Ag) is demonstrated, in which silver triangular nanoplates (AgTNPs) embedded in the poly(3,4‐ethylenedioxythiophene):poly(styrenesulfonate)‌ (PEDOT:PSS) layer amplify NIR absorption and enhance synaptic performance. The resulting device exhibits reconfigurable synaptic plasticity—including short‐term memory (STM), long‐term memory (LTM), and paired‐pulse facilitation (PPF)—and achieves an ultralow operating energy of 2.7 fJ per event, among the lowest reported for NIR organic synapses. Beyond mimicking biological learning behaviors, the device performs optical encoding/decoding of Morse code and enables high‐accuracy neuromorphic tasks, achieving 98.9% accuracy in Modified National Institute of Standards and Technology database (MNIST) recognition and 94.2% accuracy in electrocardiogram (ECG) recognition using a convolutional neural network (CNN). Mechanistic analysis and finite element method (FEM) simulations confirm that localized surface plasmon resonance (LSPR)‐mediated photonic field enhancement increases the probabilities of exciton generation and dissociation, accounting for the improved NIR responsivity. This work establishes a practical strategy for developing NIR‐responsive neuromorphic and biomedical sensing platforms.","url":"https://doi.org/10.1002/adom.71477","authors":["Zhaoxin Xu","Shihui Dong","Hong Lian","Xianglin Wang","Jiangcheng Cao","Jiahui Ding","Guotao Lan","Shuanglong Wang","Xingdong Ding","Peng Gao","Qingchen Dong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-24T06:42:13Z","doi":"10.1002/adom.71477","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/melecon64486.2026.11418875","name":"Agentic Augmented Reality Caregiver Utilizing Edge and Neuromorphic Optimization for Efficient Elderly Assistance","source":"crossref","abstract":"","url":"https://doi.org/10.1109/melecon64486.2026.11418875","authors":["Don Roosan","Fahmida Hai","Saif Nirzhor","Rubayat Khan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-10T19:50:57Z","doi":"10.1109/melecon64486.2026.11418875","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1007/978-3-032-12107-3_3","name":"Experimental Development","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-12107-3_3","authors":["Elliot Kisiel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-19T17:22:00Z","doi":"10.1007/978-3-032-12107-3_3","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1142/9789811290084_0001","name":"Introduction","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789811290084_0001","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-26T02:06:27Z","doi":"10.1142/9789811290084_0001","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.33774/coe-2026-7rm70","name":"SuperNeuronBench - A Computational Benchmark for Comparing Time-Multiplexed Neuromorphic Architectures on Open-Source FPGAs to Parallel Biological Software Models","source":"crossref","abstract":"The real-time simulation of biological neurons is a constraint in computational neuroscience. One human brain cortical column includes tens of thousands of neurons and hundreds of millions to billions of synaptic connections that have to update in the same clock cycle. Time multiplexing is the scientific method used to mitigate this problem. One processing element, named a \"superneuron\", cycles through the states of simulated neurons in a sequence. This method is used by systems such as SpiNNaker, Intel Loihi, and IBM TrueNorth. But this sequential process creates a time gap that does not exist in the parallel process of biological neurons. No study isolates the effect of this timing gap on neural computation types, and this problem is not addressed for open-source neuromorphic hardware such as NeuroCoreX. This proposal introduces SuperNeuronBench, a benchmark that measures the reduction in biological accuracy caused by time multiplexing across task types. Those task types are pattern storage and retrieval, spike-timing-dependent plasticity(STDP), temporal gating, and coincidence detection. The benchmark uses the van Rossum spike-train distance against a parallel NEST or Brian2 software-biological reference to process vand calculate a normalized biological accuracy value, across superneuron configurations. Those configurations are x, the number of neurons per superneuron; z, the number of time-block subdivisions, and C, the number of superneurons in parallel. Testing will be done using open-source models on Intel Altera Cyclone IV EP4CE15 and Cyclone V SoC hardware. The main hypothesis are that time-dependent tasks reduce the accuracy at a lower multiplexing density than rate-coded tasks.","url":"https://doi.org/10.33774/coe-2026-7rm70","authors":["Neksha DeSilva"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-03T09:58:39Z","doi":"10.33774/coe-2026-7rm70","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1007/s00521-026-11941-3","name":"Self-tuning neuromorphic controller for real-time UAS trajectory tracking based on prescribed error sensitivity","source":"crossref","abstract":"Abstract Inspired by a learning mechanism encountered in the mammal brain, this study presents a Neuromorphic Self-Tuning Proportional-Integral-Derivative (PID) controller for Unmanned Aerial Systems (UAS). The controller is derived from a Spiking Neuronal Network (SNN) and enhanced with a biologically plausible supervised learning rule known as Prescribed Error Sensitivity (PES). This control framework enables the UAS to maintain stability near singular regions, improving robustness to input perturbations, and reducing trajectory tracking error. A series of experimental tests consisting of real-time UAS trajectory tracking demonstrate the applicability and effectiveness of the proposed approach.","url":"https://doi.org/10.1007/s00521-026-11941-3","authors":["Anel Olivares","Eduardo S. Espinoza","Luis E. Ramos","Omar A. Garcia A.","Luis Rodolfo Garcia Carrillo","Andrew T. Sornborger"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-21T06:36:46Z","doi":"10.1007/s00521-026-11941-3","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.35848/1347-4065/ae4be6","name":"A 319.3 TOPS W\n                    <sup>−1</sup>\n                    high-efficient computing-in-memory engine with 55 nm high-density multi-level NOR-flash array and event-driven neuromorphic architecture","source":"crossref","abstract":"Abstract This paper presents a high-efficiency spiking neural network (SNN) accelerator based on a 1.5 T NOR flash device. By leveraging the non-volatile and tunable conductance characteristics of NOR flash, the proposed design enables precise synaptic weight storage and low-power updates in a computing-in-memory architecture. The accelerator adopts a 512 × 1024 array structure, supporting large-scale SNN parallel inference and event-driven computation. With optimized spike accumulation and neuron firing circuits, the system achieves high computational density with reduced power consumption. Experimental results demonstrate an energy efficiency of 319.3 TOPS W −1 , highlighting its superiority over SRAM- or RRAM-based implementations and its potential for edge artificial intelligence applications such as low-power sensing and on-device inference.","url":"https://doi.org/10.35848/1347-4065/ae4be6","authors":["Yue Cheng","Yaolei Guo","Hanfeng Wang","Zhaolong He","Chenhao Tang","Xinjian Wang","Jingyao Chi","Dawei Gao","Dianyu Qi","Yitao Ma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-02T22:48:44Z","doi":"10.35848/1347-4065/ae4be6","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.37188/lam.2026.011","name":"Anisotropic 2D materials for integrated polarimetric neuromorphic vision","source":"crossref","abstract":"","url":"https://doi.org/10.37188/lam.2026.011","authors":["Qi Liu","Luwei Zhou","Qi Wei","Hui Ren","Xuanyu Zhu","Mingjie Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-10T10:33:28Z","doi":"10.37188/lam.2026.011","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/nelex69209.2026.11590640","name":"FPGA-Based Neuromorphic Architecture for Real-Time Route Optimization Using Adaptive Spiking Neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nelex69209.2026.11590640","authors":["S Hemanathan B","B Harikeshavan","C Prayline Rajabai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-13T20:01:34Z","doi":"10.1109/nelex69209.2026.11590640","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.32604/cmc.2026.082979","name":"NeuroPulse: Spiking-Transformer Hybrid Architecture for Ultra-Low-Power Continual Learning in Neuromorphic Network Processors","source":"crossref","abstract":"","url":"https://doi.org/10.32604/cmc.2026.082979","authors":["Mohammed Abdullah Alsuwaiket"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-29T11:12:54Z","doi":"10.32604/cmc.2026.082979","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.59717/j.xinn-inform.2026.100027","name":"Recent progress on integrated neuromorphic chips","source":"crossref","abstract":"&lt;p&gt;In the post-Moore era, advancing integrated circuits necessitates the development of artificial synaptic devices capable of replicating the functions of human brain with neuromorphic computing, which consists of numerous biological synapses. The neuromorphic chips based on integrated synaptic devices are the promising candidates due to their unique properties, which enable the simulation of human brain and biological synapse plasticity. In recent years, significant progress has been made in the development of optoelectronic synaptic devices and integrated neuromorphic chips. This review summarizes the recent advancements in the integrated synaptic devices, focusing on the structures, integrated technologies and their applications of neuromorphic chips. It discusses the two-terminal and three-terminal configurations of synaptic devices, emphasizing their advantages in simulating biological synapse functions. These advantages include a simple structure, low power consumption, high stability, a wide switching ratio and fast programming speed. Furthermore, the discussion covers the key applications of synaptic devices and integrated neuromorphic chips, such as image recognition, brain-like computing, tactile and vision sensors. For the synaptic-device-based neural networks in image recognition, they have great potential in tactile technology and visual bionics. Other potential applications have also been reviewed and discussed, including intelligent robots, electric skin, human-computer interaction and brain-computer interface, &lt;i&gt;etc&lt;/i&gt;. Hence, neuromorphic chips have great promising application prospects, which can significantly promote the development of artificial intelligence and human civilization.&lt;/p&gt;","url":"https://doi.org/10.59717/j.xinn-inform.2026.100027","authors":["Xiushuo Gu","Lifeng Bian","Linrui Cheng","Chaoyun Song","Yibin Wang","Jianya Zhang","Yukun Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-30T02:48:44Z","doi":"10.59717/j.xinn-inform.2026.100027","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1145/3822454.3822468","name":"Convolutional Sparse Coding via the Locally Competitive Algorithm on Loihi 2","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3822454.3822468","authors":["Geoffrey Kasenbacher","Daniel Ruepp","Gerrit A. Ecke"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-16T05:57:39Z","doi":"10.1145/3822454.3822468","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1063/5.0314841","name":"Superlattice-like Ge2Sb2Te5/Sb2S3 based phase-change memory enabling linear conductance modulation for neuromorphic computing","source":"crossref","abstract":"Artificial synaptic devices that emulate biological synaptic behavior have garnered significant research interest for their potential in enabling efficient and low-power computing architectures. Phase-change memory (PCM) has emerged as a promising candidate for artificial synaptic devices, owing to its non-volatility, high speed, and low-power consumption. However, the inherent abrupt and hard-to-control resistance switching in PCM impedes linear and continuous conductance modulation, which substantially restricts the performance of PCM-based synaptic devices. This work demonstrates an electronic synaptic device fabricated from a Ge2Sb2Te5/Sb2S3 superlattice-like (SLL) phase-change thin film. The unique SLL structure effectively suppresses the rapid crystallization and resistance drift. The device operates at a driving voltage below 1 V with low-power consumption and exhibits eight stable resistance states. It achieves a notably low resistance drift coefficient of 0.0006, which remains stable for over 1000 s. Moreover, through a tailored programming strategy, the device successfully implements synaptic weight updates via long-term potentiation and long-term depression, thereby alleviating the nonlinearity and asymmetry commonly observed in PCM-based conductance modulation. In a handwritten digit recognition task, the device enabled a recognition accuracy of around 97.6%, highlighting its potential for enhancing the precision and reliability of neuromorphic computing systems.","url":"https://doi.org/10.1063/5.0314841","authors":["Lele Li","Mengru Song","Han Gu","Ziyang Hu","Yegang Lu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-13T10:23:38Z","doi":"10.1063/5.0314841","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1016/j.sna.2026.118286","name":"Defect-engineered synaptic plasticity in flexible MoS2 memristors for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.sna.2026.118286","authors":["Kumar Kaushlendra","Davinder Kaur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-24T15:56:01Z","doi":"10.1016/j.sna.2026.118286","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1002/agt2.70319","name":"Plasmon‐Doped Organic Heterojunction Optoelectronic Synapses for Near‐Infrared Visual Memory and Neuromorphic Computing","source":"crossref","abstract":"ABSTRACT The explosive growth of artificial intelligence has intensified demands for new computing paradigms beyond conventional von Neumann architectures. In response, brain‐inspired computing‐in‐memory technologies are emerging as a promising path forward. Here, we designed a two‐terminal optical synaptic device utilizing organic heterojunctions doped with gold nanorods (AuNRs), leveraging the electric field enhancement innate to the localized surface plasmon resonance (LSPR) effect. The device doped with 1 wt% AuNRs demonstrates a markedly enhanced light absorption capacity in the near‐infrared (NIR) region of 808 nm. The generation rate of photogenerated excitons increases by 16.8%, while the probability of exciton dissociation rises by 8.4%. The paired‐pulse facilitation (PPF) index reaches 114.6% (Δ t = 1 s), indicating heightened sensitivity to optical pulse parameters. Additionally, Hall effect measurements were performed to characterize the electrical properties of the PEDOT:PSS:AuNRs films. The carrier mobility of the doped films increased 20‐fold compared to pristine PEDOT:PSS due to electron injection from AuNRs. This enhanced mobility contributes to faster synaptic response and higher conductance tunability in the synapse device, further supporting its performance in neuromorphic computing tasks. Furthermore, we successfully simulated the dynamic “learning–forgetting–relearning” processes associated with human visual memory. By exploiting the tunable conductance of the optimized synaptic device, we implemented both convolutional neural networks (CNNs) and convolutional spiking neural networks (CSNNs) for weight updates. After 100 and 150 training epochs, the system achieved recognition accuracies up to 98.57% for handwritten digits and 92.01% for dynamic gestures. This work presents an effective plasmon‐doping approach to enhancing the performance of organic memristors and can be extended to other material systems.","url":"https://doi.org/10.1002/agt2.70319","authors":["Jiangcheng Cao","Hong Lian","Xianglin Wang","Qishuai Huang","Jiahui Ding","Jiangnan Xia","Shuanglong Wang","Weijin Hu","Tom Wu","Qingchen Dong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-12T09:34:59Z","doi":"10.1002/agt2.70319","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1088/1361-6463/ae8917","name":"Flexible neuromorphic for in-sensor computing with synaptic transistors","source":"openalex","abstract":"Abstract The basic shortcomings of traditional von Neumann architectures have been revealed by the quick spread of edge devices and data-intensive sensing technologies, especially with regard to latency, energy consumption, and data transfer bottlenecks. By enabling data processing right at the moment of acquisition, in-sensor computing has emerged as a promising paradigm to address these issues. Simultaneously, flexible electronics have special possibilities for the development of wearable, lightweight, and conformable intelligent systems. In this regard, synaptic transistor-based flexible neuromorphic devices offer an appealing framework for highly effective and versatile biological signal processing emulation. The design, materials, and working mechanisms of synaptic transistors are the main topics of this review, which thoroughly examines current developments in flexible neuromorphic devices for in-sensor computing. We analyse a variety of material systems, including organic, inorganic, and newly developed low-dimensional materials, and we talk about important device physics that underlie synaptic functions, such as short- and long-term plasticity and spike-timing-dependent learning. Performance criteria like energy efficiency, mechanical robustness, and scalability are examined, as well as integration methodologies for integrating sensing and computing at the device and system levels. Lastly, we outline future paths toward fully autonomous, flexible neuromorphic sensory systems for next-generation wearable electronics, soft robotics, and bio-integrated applications. We also highlight current challenges, such as device variability, environmental stability, and large-area integration.","url":"https://doi.org/10.1088/1361-6463/ae8917","authors":["Swarup Biswas","Hyeok Kim"],"tags":["Neuromorphic engineering","Scalability","Computer science","Conformable matrix","Von Neumann architecture"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2026-07-10","doi":"10.1088/1361-6463/ae8917","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"doi:10.31026/j.eng.2026.03.01","name":"Design of Low-Power Neuromorphic Architectures for IoT Applications","source":"crossref","abstract":"The rapid growth of the Internet of Things (IoT) demands computing systems that remain highly intelligent while adhering to tight energy constraints. For always-on edge applications, traditional processors are too power-hungry. This neuromorphic system is developed for IoT to achieve computing integrity and has remarkable efficiency. We propose computer-memory architecture which essentially is event-driven processing and temporal-spike coding. Architectural breakthroughs include clockless processing and adaptive precision and therefore exploit temporality with hierarchical event encoding. While current hardware solutions show a power consumption of 70 μW to 680 μW, our system shows 10 – 100× improvement in overall efficiency. Testing proved that with radar gesture recognition, audio pattern matching and visual event detection, we have more than 96 % accuracy. Inference energy is 1.38 nJ, and molecular operation cost is 9.9 pJ of the architecture with these efficient metrics, a new family of autonomous IoT applications can be developed, from battery-free sensor networks to implantable devices that run for years off a single charge.","url":"https://doi.org/10.31026/j.eng.2026.03.01","authors":["Enji Hashim Ismael"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-02T10:48:09Z","doi":"10.31026/j.eng.2026.03.01","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.20517/iontronics.2026.04","name":"Nanofluidic neuromorphic iontronics: a nexus for biological signal transduction","source":"crossref","abstract":"Neuromorphic iontronics is an emerging technology based on the sophisticated regulation of ions as signal carriers, demonstrating strong potential in human-machine interaction. Nanofluidic materials exhibit significant advantages in constructing iontronic neuromorphic devices due to their ability to precisely mimic the transport mechanisms of biological ion channels. By synergistically integrating multiple external stimuli, neuromorphic devices that combine perception fusion and memory behaviors are injecting new vitality into the development of artificial intelligence, including computation, neurorobotics, and healthcare. However, this field is still in its infancy and requires robust theoretical foundations, novel computational paradigms, and innovative approaches to functional material design and device integration to advance further. In this Perspective, we provide a comprehensive overview of recent advances in iontronic neuromorphic devices with respect to fabrication, integration, and applications, aiming to illustrate the rapid growth of this field. Finally, we discuss current challenges and future directions, including theoretical models based on ionic properties, neuromorphic signal simulation, and device integration.","url":"https://doi.org/10.20517/iontronics.2026.04","authors":["Lin Li","Weipeng Chen","Xiang-Yu Kong","Liping Wen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-30T07:18:43Z","doi":"10.20517/iontronics.2026.04","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1016/j.snb.2025.139268","name":"Eutectogel-gated ultra-flexible organic electrochemical transistors for humidity sensing and neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.snb.2025.139268","authors":["Banghua Wu","Yujie Peng","Lin Gao","Canghao Xu","Changjian Liu","Haihong Guo","Yong Huang","Junsheng Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-02T07:53:15Z","doi":"10.1016/j.snb.2025.139268","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1016/j.optlastec.2026.114807","name":"All-optically controlled terahertz memristor for multidimensional neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.optlastec.2026.114807","authors":["Weien Lai","Shenglian Lan","Xiaolong Liang","Yichen Gan","Runqing Huang","Chengzhu Liao","Huili Li","Abbas Amini","Chun Cheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-28T22:50:00Z","doi":"10.1016/j.optlastec.2026.114807","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1109/imcet69180.2026.11503755","name":"Resistorless DVCCTA-Based Memristor Emulator for Analog/Digital/Neuromorphic Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/imcet69180.2026.11503755","authors":["Prerna Rana","Alak Majumder","Vassilis Alimisis","Paul P. Sotiriadis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-08T19:38:00Z","doi":"10.1109/imcet69180.2026.11503755","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1007/s11431-025-3244-8","name":"Dynamics of a neuromorphic electromechanical model mimicking neuromuscular junctions","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11431-025-3244-8","authors":["Fuqiang Wu","Xia Qiu","Jun Ma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-10T13:36:29Z","doi":"10.1007/s11431-025-3244-8","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.3390/engproc2026124114","name":"Neuromorphic AI-Based e-Skin for Emotion-Sensitive Humanoid Robots","source":"crossref","abstract":"","url":"https://doi.org/10.3390/engproc2026124114","authors":["Shubham Gupta","Suhaib Ahmed"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-08T21:37:33Z","doi":"10.3390/engproc2026124114","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1016/j.clinph.2026.2111681","name":"Packet-based HFO detection on neuromorphic hardware for epileptogenic zone localization","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.clinph.2026.2111681","authors":["Jeroen Teurlings","Filippo Costa","Giacomo Indiveri","Maeike Zijlmans","Johannes Sarnthein"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-14T02:59:59Z","doi":"10.1016/j.clinph.2026.2111681","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1002/adfm.76104","name":"Cavity‐Enhanced High Sensitivity InP Nanosheet Optoelectronic Synaptic Transistors for Neuromorphic Computing","source":"crossref","abstract":"ABSTRACT Optoelectronic synaptic transistors that combine sensing and computing functionalities are emerging as key components for next‐generation neuromorphic systems, yet their scalability and performance remain limited by device architecture and fabrication constraints. Here, we report cavity‐enhanced optoelectronic synaptic transistors based on surface‐state modulation in selectively grown InP nanosheets. Benefiting from optical‐cavity‐induced high gain and effective dark‐current suppression, the device exhibits an ultrahigh responsivity of approximately 1.5 × 10 6 A W −1 , a specific detectivity of ≈5 × 10 14 Jones, and a noise‐equivalent power of ≈10 −16 W Hz −1/2 . Precise control of charge dynamics at surface states using electrical and optical stimuli allows the emulation of key synaptic functions, including short‐ and long‐term plasticity, paired‐pulse facilitation, and learning–forgetting–relearning behaviors. Furthermore, convolutional neural network simulations leveraging the device's continuously tunable conductance yield image recognition accuracies approaching 90%. These results establish InP nanosheet optoelectronic synaptic transistors as a scalable and high‐performance platform for integrated neuromorphic computing.","url":"https://doi.org/10.1002/adfm.76104","authors":["Xutao Zhang","Liang Liu","Ningjie Pang","Yezhao Zhuang","Sheng Ni","Wang Zhan","Changlong Liu","Hai Huang","Xiaoming Yuan","Xuetao Gan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-08T07:15:02Z","doi":"10.1002/adfm.76104","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1002/rar2.70406","name":"Efficient Spin‐Orbit Torques Enabled by Vanadium‐Induced Orbital Currents for Neuromorphic Computing","source":"crossref","abstract":"ABSTRACT Spin‐orbit torque (SOT) provides an efficient electrical pathway for encoding spin states and underpins emerging, ultrafast, and nonvolatile spintronic memories and logic devices. Reducing the switching current density and power consumption remains a central challenge for practical applications. Here, we demonstrate that a light metal, vanadium (V), can serve as an efficient orbital‐current source to substantially enhance SOT efficiency. In V/Pt/CoFeB heterostructures, orbital currents generated in V are effectively converted into spin currents by the spin‐orbit‐active Pt layer, giving rise to enhanced torques acting on the perpendicularly magnetized CoFeB layer. As a result, the critical switching current density and power are reduced by 54% and 27%, respectively, compared with conventional spin current‐dominated Pt/CoFeB structures. Moreover, V/Pt/CoFeB‐based devices further enable neuromorphic computing functionalities, achieving a handwritten digit recognition accuracy of 89%. These results highlight orbital‐current engineering as a viable strategy for realizing low‐power SOT devices and advancing spintronic hardware for neuromorphic computing.","url":"https://doi.org/10.1002/rar2.70406","authors":["Zhonghai Yu","Yaohui Du","Mengyang Yan","Pengnan Zhao","Rui Hou","Keqin Li","Lihuan Yang","Kaiwei Guo","Bingyue Bian","Zhengyu Xiao","Lei Cheng","Hongru Wang","Jia‐Min Lai","Zhiyong Quan","Dongsheng Yang","Yakun Liu","Fei Wang","Xiaohong Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-12T16:33:52Z","doi":"10.1002/rar2.70406","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1117/12.3101044","name":"Insect-brain inspired neuromorphic nanophotonics: efficient, small and fast","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3101044","authors":["Anders Mikkelsen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-27T18:24:57Z","doi":"10.1117/12.3101044","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.55959/msu05799392.81.2610502","name":"Ti/HfOx/TiN-Based Memcapacitor for Neuromorphic Applications","source":"crossref","abstract":"This paper presents a Ti/HfOx/TiN structure capable of switching between both resistive and capacitive states. Impedance spectroscopy data suggest an equivalent electrical circuit that increases the resistive switching of a hafnium oxide filament and suggests the presence of a TiON layer in the HfOx/TiN contact region, which may explain the ferroelectric potential switching. The capacitive switching window is 185 pF, resulting in a 75% increase in capacitance, while the resistance during resistive switching increases tenfold. These features represent an example of a versatile structure that can function as both a capacitor and a multi-state resistor. This enables encoding more information in a single cell and the creation of more complex logic elements. The problem of parasitic currents can also be solved, dramatically improving the energy efficiency and reliability of scalable memory arrays.","url":"https://doi.org/10.55959/msu05799392.81.2610502","authors":["I.D. Kuchumov","M.N. Martyshov","A.S. Ilyin","A.I. Novoseltsev","T.P. Savchuk","P.A. Forsh","P.K. Kashkarov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-10T09:09:37Z","doi":"10.55959/msu05799392.81.2610502","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.29363/nanoge.matsusspring.2026.758","name":"Universal Dynamical Principles for Neuromorphic Oscillators: From Solid-State Devices to Organic and Fluidic Neurons","source":"crossref","abstract":"","url":"https://doi.org/10.29363/nanoge.matsusspring.2026.758","authors":["Juan Bisquert"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-16T08:04:37Z","doi":"10.29363/nanoge.matsusspring.2026.758","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1201/9781003687924-10","name":"I/O pad integrity in energy-efficient neuromorphic chips","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003687924-10","authors":["Arfan Ghani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-12T14:07:12Z","doi":"10.1201/9781003687924-10","addedAt":"2026-09-01T01:48:22.296Z","updatedAt":"2026-09-01T01:48:22.296Z"},{"id":"doi:10.1016/j.engappai.2022.105430","name":"Neuromorphic circuit based on the un-supervised learning of biologically inspired spiking neural network for pattern recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.engappai.2022.105430","authors":["Soheila Nazari","Alireza Keyanfar","Marc M. Van Hulle"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-15T18:44:26Z","doi":"10.1016/j.engappai.2022.105430","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1007/s00422-017-0719-9","name":"A spiking neural network model of the midbrain superior colliculus that generates saccadic motor commands","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00422-017-0719-9","authors":["Bahadir Kasap","A. John van Opstal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-05-20T13:18:36Z","doi":"10.1007/s00422-017-0719-9","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.21863/jnis/2026.14.1.005","name":"Homeostatically Regulated Adaptive Threshold Spiking Neural Networks for Energy-Efficient Inference","source":"crossref","abstract":"Spiking Neural Networks (SNNs) represent a biologically grounded computational paradigm in which information is carried by discrete spike events, conferring structural compatibility with low-power, event-driven neuromorphic hardware. A persistent impediment to realising the full energy benefit of SNNs in practice is the near-universal adoption of fixed firing thresholds, which prevent individual neurons from self-regulating their activity and permit task-irrelevant spike generation to accumulate unchecked. This paper introduces and evaluates a Homeostatically Regulated Adaptive Threshold (HAT) mechanism in which each neuron’s firing threshold is updated at every time step in proportion to the deviation between its exponentially smoothed firing rate and a designer-specified target rate. The rule is derived from the proportional control framework and mirrors the intrinsic excitability regulation observed in biological cortical circuits. A novel metric, the Target Achievement Error (TAE), is defined to quantify how faithfully the population reaches its intended operating point. Computational cost is assessed using a synaptic operations (SynOps) proxy that is hardware-agnostic and scales linearly with spike volume. A two-stage screening procedure selects the best configurations from 27 candidates by first enforcing an accuracy constraint and then ranking them by spike reduction, TAE, energy, and accuracy. Controlled experiments on MNIST show that the fixed-threshold baseline attains a mean validation accuracy of 92.52%±1.13% across three random seeds, with an average of 21.86 × 106 spikes and an estimated SynOps energy of 211.70 mJ. The top-ranked homeostatic configuration (α = 0.1, ftarget = 0.1, γ = 0.2) achieves 92.02% validation accuracy with a 15.54% reduction in total spike activity, incurring only a 0.50% absolute accuracy shortfall. These results indicate that homeostatic threshold regulation offers a structurally non-invasive route to improved inference energy in gradient-trained SNNs.","url":"https://doi.org/10.21863/jnis/2026.14.1.005","authors":["Gripsy Paul Mannickathan","Yeldo K. Varghese","Sahala Mariyam P. S.","Nimal K. G.","Pavithra S.","Noel Sabu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-28T09:17:11Z","doi":"10.21863/jnis/2026.14.1.005","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1051/shsconf/202213903019","name":"Study of a Multi-modal Neurorobotic Prosthetic Arm Control System based on Recurrent Spiking Neural Network","source":"crossref","abstract":"The use of robotic arms in various fields of human endeavor has increased over the years, and with recent advancements in artificial intelligence enabled by deep learning, they are increasingly being employed in medical applications like assistive robots for paralyzed patients with neurological disorders, welfare robots for the elderly, and prosthesis for amputees. However, robot arms tailored towards such applications are resource-constrained. As a result, deep learning with conventional artificial neural network (ANN) which is often run on GPU with high computational complexity and high power consumption cannot be handled by them. Neuromorphic processors, on the other hand, leverage spiking neural network (SNN) which has been shown to be less computationally complex and consume less power, making them suitable for such applications. Also, most robot arms unlike living agents that combine different sensory data to accurately perform a complex task, use uni-modal data which affects their accuracy. Conversely, multi-modal sensory data has been demonstrated to reach high accuracy and can be employed to achieve high accuracy in such robot arms. This paper presents the study of a multi-modal neurorobotic prosthetic arm control system based on recurrent spiking neural network. The robot arm control system uses multi-modal sensory data from visual (camera) and electromyography sensors, together with spike-based data processing on our previously proposed R-NASH neuromorphic processor to achieve robust accurate control of a robot arm with low power. The evaluation result using both uni-modal and multi-modal input data show that the multi-modal input achieves a more robust performance at 87%, compared to the uni-modal.","url":"https://doi.org/10.1051/shsconf/202213903019","authors":["Mark Ikechukwu Ogbodo","Khanh N. Dang","Abderazek Ben Abdallah"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-05-13T07:59:15Z","doi":"10.1051/shsconf/202213903019","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1615/jautomatinfscien.v45.i3.30","name":"Self-Learning Cascade Spiking Neural Network for Fuzzy Clustering Based on Group Method of Data Handling","source":"crossref","abstract":"","url":"https://doi.org/10.1615/jautomatinfscien.v45.i3.30","authors":["Yevgeniy .V. Bodyanskiy","Elena A. Vynokurova","Artem I. Dolotov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-06-07T06:34:14Z","doi":"10.1615/jautomatinfscien.v45.i3.30","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/nice69539.2026.11567485","name":"NeuroCoreX: An Open-Source FPGA-Based Spiking Neural Network Emulator with On-Chip Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nice69539.2026.11567485","authors":["Ashish Gautam","Prasanna Date","Shruti Kulkarni","Ian Mulet","Kevin Zhu","Robert Patton","Thomas Potok"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-22T19:52:43Z","doi":"10.1109/nice69539.2026.11567485","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/ijcnn.2015.7280776","name":"Stochastic and asynchronous spiking dynamic neural fields","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2015.7280776","authors":["Benoit Chappet de Vangel","Cesar Torres-Huitzil","Bernard Girau"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-10-01T17:48:02Z","doi":"10.1109/ijcnn.2015.7280776","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/cnn67635.2025.11177508","name":"Astrocytes Stabilize Neural Simplices Against Noise in STDP-based Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cnn67635.2025.11177508","authors":["Yuliya Tsybina","Susanna Gordleeva"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T17:36:47Z","doi":"10.1109/cnn67635.2025.11177508","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/ijcnn.2018.8489175","name":"A Supervised Multi-Spike Learning Algorithm for Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2018.8489175","authors":["Yu Miao","Huajin Tang","Gang Pan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-10-19T22:25:09Z","doi":"10.1109/ijcnn.2018.8489175","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/ijcnn48605.2020.9207239","name":"A critical survey of STDP in Spiking Neural Networks for Pattern Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn48605.2020.9207239","authors":["Alex Vigneron","Jean Martinet"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-30T00:40:33Z","doi":"10.1109/ijcnn48605.2020.9207239","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1007/s11063-020-10322-8","name":"Spiking Neural Networks: Background, Recent Development and the NeuCube Architecture","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11063-020-10322-8","authors":["Clarence Tan","Marko Šarlija","Nikola Kasabov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-13T09:03:47Z","doi":"10.1007/s11063-020-10322-8","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/dcna56428.2022.9923284","name":"Working memory capacity of spiking neural network model","source":"crossref","abstract":"","url":"https://doi.org/10.1109/dcna56428.2022.9923284","authors":["Natalia S. Kovaleva","Valery V. Matrosov","Mikhail A. Mishchenko"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-03T22:16:08Z","doi":"10.1109/dcna56428.2022.9923284","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1007/978-981-96-5955-5_33","name":"Spiking Neural Network Based Object Pose Alignment","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-96-5955-5_33","authors":["Sushant Yadav","Chandarjeet Singh Chundawat","Santosh Chaudhary","Rajesh Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-31T17:09:32Z","doi":"10.1007/978-981-96-5955-5_33","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1587/nolta.15.432","name":"Integrating predictive coding with reservoir computing in spiking neural network model of cultured neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1587/nolta.15.432","authors":["Yoshitaka Ishikawa","Takumi Shinkawa","Takuma Sumi","Hideyuki Kato","Hideaki Yamamoto","Yuichi Katori"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-31T22:15:54Z","doi":"10.1587/nolta.15.432","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1142/s0129065725500364","name":"Global–Local Feature Fusion Network Based on Nonlinear Spiking Neural Convolutional Model for MRI Brain Tumor Segmentation","source":"crossref","abstract":"Due to the differences in size, shape, and location of brain tumors, brain tumor segmentation differs greatly from that of other organs. The purpose of brain tumor segmentation is to accurately locate and segment tumors from MRI images to assist doctors in diagnosis, treatment planning and surgical navigation. NSNP-like convolutional model is a new neural-like convolutional model inspired by nonlinear spiking mechanism of nonlinear spiking neural P (NSNP) systems. Therefore, this paper proposes a global–local feature fusion network based on NSNP-like convolutional model for MRI brain tumor segmentation. To this end, we have designed three characteristic modules that take full advantage of the NSNP-like convolution model: dilated SNP module (DSNP), multi-path dilated SNP pooling module (MDSP) and Poolformer module. The DSNP and MDSP modules are employed to construct the encoders. These modules help address the issue of feature loss and enable the fusion of more high-level features. On the other hand, the Poolformer module is used in the decoder. It processes features that contain global context information and facilitates the interaction between local and global features. In addition, channel spatial attention (CSA) module is designed at the skip connection between encoder and decoder to establish the long-range dependence between the same layers, thereby enhancing the relationship between channels and making the model have global modeling capabilities. In the experiments, our model achieves Dice coefficients of 85.71[Formula: see text], 92.32[Formula: see text], 87.75[Formula: see text] for ET, WT, and TC, respectively, on the N-BraTS2021 dataset. Moreover, our model achieves Dice coefficients of 83.91[Formula: see text], 91.96[Formula: see text], 90.14[Formula: see text] and 85.05[Formula: see text], 92.30[Formula: see text], 90.31[Formula: see text] on the BraTS2018 and BraTS2019 datasets respectively. Experimental results also indicate that our model not only achieves good brain tumor segmentation performance, but also has good generalization ability. The code is already available on GitHub: https://github.com/Li-JJ-1/NSNP-brain-tumor-segmentation .","url":"https://doi.org/10.1142/s0129065725500364","authors":["Junjie Li","Hong Peng","Bing Li","Zhicai Liu","Rikong Lugu","Bingyan He"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-11T09:40:47Z","doi":"10.1142/s0129065725500364","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/ibitec66306.2025.11472847","name":"Spiking Neural Networks and fMRI-Constrained Spiking Neural Networks for Speech Recognition and Biological Signal Processing: A Comprehensive Review","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ibitec66306.2025.11472847","authors":["Pandula Pallewatta","Samantha Mathara Arachchi","Sanam Rizvan","Kasun Karunanayaka","Trapp Kayuni","Thilina Halloluwa","Tinmei Aleksandr","Khalil Benbrahim","Abraham Maloba"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-13T19:35:30Z","doi":"10.1109/ibitec66306.2025.11472847","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.1155/2022/8369368","name":"Breast Cancer Recognition Using Saliency‐Based Spiking Neural Network","source":"crossref","abstract":"The spiking neural networks (SNNs) use event‐driven signals to encode physical information for neural computation. SNN takes the spiking neuron as the basic unit. It modulates the process of nerve cells from receiving stimuli to firing spikes. Therefore, SNN is more biologically plausible. Although the SNN has more characteristics of biological neurons, SNN is rarely used for medical image recognition due to its poor performance. In this paper, a reservoir spiking neural network is used for breast cancer image recognition. Due to the difficulties of extracting the lesion features in medical images, a salient feature extraction method is used in image recognition. The salient feature extraction network is composed of spiking convolution layers, which can effectively extract the features of lesions. Two temporal encoding manners, namely, linear time encoding and entropy‐based time encoding methods, are used to encode the input patterns. Readout neurons use the ReSuMe algorithm for training, and the Fruit Fly Optimization Algorithm (FOA) is employed to optimize the network architecture to further improve the reservoir SNN performance. Three modality datasets are used to verify the effectiveness of the proposed method. The results show an accuracy of 97.44% for the BreastMNIST database. The classification accuracy is 98.27% on the mini‐MIAS database. And the overall accuracy is 95.83% for the BreaKHis database by using the saliency feature extraction, entropy‐based time encoding, and network optimization.","url":"https://doi.org/10.1155/2022/8369368","authors":["Qiang Fu","Hongbin Dong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-24T19:43:26Z","doi":"10.1155/2022/8369368","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/icecs58634.2023.10382923","name":"Hardware Aware Spiking Neural Network Training and Its Mixed-Signal Implementation for Non-Volatile In-Memory Computing Accelerators","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icecs58634.2023.10382923","authors":["Alptekin Vardar","Aamir Munir","Nellie Laleni","Sourav De","Thomas Kämpfe"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-10T19:38:25Z","doi":"10.1109/icecs58634.2023.10382923","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/iccpct70290.2026.11654952","name":"Spiking Neural Network Based Intrusion Detection Framework for Manet Security Using White Shark Optimization","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccpct70290.2026.11654952","authors":["R. Ramya","S. Rosaline","K S Kavin","P. Saranya","T. Senthil Ganesh","J Elavarasi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-21T19:10:05Z","doi":"10.1109/iccpct70290.2026.11654952","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1007/978-3-319-44778-0_5","name":"A Sensor Fusion Horse Gait Classification by a Spiking Neural Network on SpiNNaker","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-44778-0_5","authors":["Antonio Rios-Navarro","Juan Pedro Dominguez-Morales","Ricardo Tapiador-Morales","Manuel Dominguez-Morales","Angel Jimenez-Fernandez","Alejandro Linares-Barranco"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-08-12T15:20:33Z","doi":"10.1007/978-3-319-44778-0_5","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/ijcnn60899.2024.10649998","name":"Computational Effects of Free-Flowing Ion Concentrations in Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn60899.2024.10649998","authors":["Rafael Afonso Rodrigues","Simon O’Keefe"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T17:35:05Z","doi":"10.1109/ijcnn60899.2024.10649998","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/ijcnn.2015.7280619","name":"Musical notes classification with neuromorphic auditory system using FPGA and a convolutional spiking network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2015.7280619","authors":["E. Cerezuela-Escudero","A. Jimenez-Fernandez","R. Paz-Vicente","M. Dominguez-Morales","A. Linares-Barranco","G. Jimenez-Moreno"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-10-01T17:48:02Z","doi":"10.1109/ijcnn.2015.7280619","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1142/s2301385026500044","name":"Development of a Centralized Conflict Free Greedy Assignment Learning Spiking Neural Network for Solving a Perimeter Defense Problem","source":"crossref","abstract":"In this paper, a Centralized Conflict-free Assignment Learning Spiking neural network (C2ALS) is formulated for solving a Perimeter Defense Problem (PDP). Here, the region between the perimeter and the sensing range of the defender is divided into two layers. The outermost layer, in which the defender can only sense the intruders, is termed the sensing layer. The layer closest to the perimeter in which the defenders can sense and capture the intruders is termed the capture layer. Both layers are further divided into angular segments with respect to the center of the area to be protected. The spatiotemporal movements of both the defenders and intruders in these segments are converted into spikes and given as input to a Spiking Neural Network (SNN). The SNN is trained in a supervised manner to learn the intruder capture assignments of a defender in terms of these segments. Here, the desired assignments required for training a defender are referred to as greedy assignments because while generating them, priority is given to those segments that are relatively closer to the defender’s actual location. Inhibitory connections are used in the SNN architecture to obtain assignments without conflicts. Detailed performance study results show that the proposed C2ALS approach outperforms the other existing centralized optimization-based solutions for PDP by a 17% increase in the success rates of capturing the intruders. Also, C2ALS is the first centralized spike-based learning solution for PDP, capable of generating conflict-free assignments while ensuring robust intruder assignments with minimal defender movement.","url":"https://doi.org/10.1142/s2301385026500044","authors":["Mohammed Thousif","Shridhar Velhal","Suresh Sundaram","Narasimhan Sundararajan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-03T05:21:06Z","doi":"10.1142/s2301385026500044","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1016/j.cmpb.2023.107927","name":"EESCN: A novel spiking neural network method for EEG-based emotion recognition","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.cmpb.2023.107927","authors":["FeiFan Xu","Deng Pan","Haohao Zheng","Yu Ouyang","Zhe Jia","Hong Zeng"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023-11-20T18:46:11Z","doi":"10.1016/j.cmpb.2023.107927","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/cvpr52688.2022.00358","name":"Event-based Video Reconstruction via Potential-assisted Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cvpr52688.2022.00358","authors":["Lin Zhu","Xiao Wang","Yi Chang","Jianing Li","Tiejun Huang","Yonghong Tian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-27T15:56:41Z","doi":"10.1109/cvpr52688.2022.00358","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1101/2023.11.14.567028","name":"Calibrating Bayesian decoders of neural spiking activity","source":"crossref","abstract":"Abstract Accurately decoding external variables from observations of neural activity is a major challenge in systems neuroscience. Bayesian decoders, that provide probabilistic estimates, are some of the most widely used. Here we show how, in many common settings, the probabilistic predictions made by traditional Bayesian decoders are overconfident. That is, the estimates for the decoded stimulus or movement variables are more certain than they should be. We then show how Bayesian decoding with latent variables, taking account of low-dimensional shared variability in the observations, can improve calibration, although additional correction for overconfidence is still needed. We examine: 1) decoding the direction of grating stimuli from spike recordings in primary visual cortex in monkeys, 2) decoding movement direction from recordings in primary motor cortex in monkeys, 3) decoding natural images from multi-region recordings in mice, and 4) decoding position from hippocampal recordings in rats. For each setting we characterize the overconfidence, and we describe a possible method to correct miscalibration post-hoc. Properly calibrated Bayesian decoders may alter theoretical results on probabilistic population coding and lead to brain machine interfaces that more accurately reflect confidence levels when identifying external variables. Significance Statement Bayesian decoding is a statistical technique for making probabilistic predictions about external stimuli or movements based on recordings of neural activity. These predictions may be useful for robust brain machine interfaces or for understanding perceptual or behavioral confidence. However, the probabilities produced by these models do not always match the observed outcomes. Just as a weather forecast predicting a 50% chance of rain may not accurately correspond to an outcome of rain 50% of the time, Bayesian decoders of neural activity can be miscalibrated as well. Here we identify and measure miscalibration of Bayesian decoders for neural spiking activity in a range of experimental settings. We compare multiple statistical models and demonstrate how overconfidence can be corrected.","url":"https://doi.org/10.1101/2023.11.14.567028","authors":["Ganchao Wei","Zeinab Tajik Mansouri","Xiaojing Wang","Ian H. Stevenson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-16T21:10:21Z","doi":"10.1101/2023.11.14.567028","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.3103/s1060992x25601629","name":"Continual Learning with Columnar Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.3103/s1060992x25601629","authors":["D. Larionov","N. Bazenkov","M. Kiselev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-19T16:34:47Z","doi":"10.3103/s1060992x25601629","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.2139/ssrn.5445962","name":"A bio-inspired spiking neural network with adaptive spatiotemporal filtering and direction-modulated synaptic plasticity for robust collision detection","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5445962","authors":["Yumeng Ren","Ye Zhao","Long Chen","Qihang Jiang","Yue Xu","Jiali Wang","Xun Huang","Ziang Wang","Hang Ran","Yumei Zhou","Shushan Qiao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-05T14:42:02Z","doi":"10.2139/ssrn.5445962","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/asicon66040.2025.11326052","name":"A Compressed Sensing Spiking Neural Network System for Radar-Based HGR","source":"crossref","abstract":"","url":"https://doi.org/10.1109/asicon66040.2025.11326052","authors":["Liyu Qian","Zikai Zhu","Yuhan He","Jie Lu","Yaojie Sun","Lirong Zheng","Zhuo Zou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-19T20:51:17Z","doi":"10.1109/asicon66040.2025.11326052","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/access.2025.3641389","name":"CalibraSNN: Fair and Calibrated Convolutional Spiking Neural Network for High-Stakes Industry Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/access.2025.3641389","authors":["Dylan Perdigão","Francisco Antunes","Catarina Silva","Bernardete Ribeiro"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-08T18:41:50Z","doi":"10.1109/access.2025.3641389","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.3389/fncel.2025.1534839","name":"Synapses mediate the effects of different types of stress on working memory: a brain-inspired spiking neural network study","source":"europepmc","abstract":"Acute stress results from sudden short-term events, and individuals need to quickly adjust their physiological and psychological to re-establish balance. Chronic stress, on the other hand, results in long-term physiological and psychological burdens due to the continued existence of stressors, making it difficult for individuals to recover and prone to pathological symptoms. Both types of stress can affect working memory and change cognitive function. In this study, we explored the impact of acute and chronic stress on synaptic modulation using a biologically inspired, data-driven rodent prefrontal neural network model. The model consists of a specific number of excitatory and inhibitory neurons that are connected through AMPA, NMDA, and GABA synapses. The study used a short-term recall to simulate working memory tasks and assess the ability of neuronal populations to maintain information over time. The results showed that acute stress can enhance working memory information retention by enhancing AMPA and NMDA synaptic currents. In contrast, chronic stress reduces dendritic spine density and weakens the regulatory effect of GABA currents on working memory tasks. In addition, this structural damage can be complemented by strong connections between excitatory neurons with the same selectivity. These findings provide a reference scheme for understanding the neural basis of working memory under different stress conditions.","url":"https://doi.org/10.3389/fncel.2025.1534839","authors":["Chengcheng Du","Yinqian Sun","Jihang Wang","Qian Zhang","Yi Zeng"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fncel.2025.1534839","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/esmarta56775.2022.9935414","name":"Novel Spiking Neural Network Model for Gear Fault Diagnosis","source":"crossref","abstract":"","url":"https://doi.org/10.1109/esmarta56775.2022.9935414","authors":["Yasir Hassan Ali","Falah Y. H. Ahmed","Ahmed M. Abdelrhman","Salah M. Ali","Abdoulhdi A. Borhana","Raja Ishak Raja Hamzah"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-07T23:01:10Z","doi":"10.1109/esmarta56775.2022.9935414","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1142/s0129065719500060","name":"Monitor-Based Spiking Recurrent Network for the Representation of Complex Dynamic Patterns","source":"crossref","abstract":"Neural networks are powerful computation tools for mimicking the human brain to solve realistic problems. Since spiking neural networks are a type of brain-inspired network, called the novel spiking system, Monitor-based Spiking Recurrent network (MbSRN), is derived to learn and represent patterns in this paper. This network provides a computational framework for memorizing the targets using a simple dynamic model that maintains biological plasticity. Based on a recurrent reservoir, the MbSRN presents a mechanism called a ‘monitor’ to track the components of the state space in the training stage online and to self-sustain the complex dynamics in the testing stage. The network firing spikes are optimized to represent the target dynamics according to the accumulation of the membrane potentials of the units. Stability analysis of the monitor conducted by limiting the coefficient penalty in the loss function verifies that our network has good anti-interference performance under neuron loss and noise. The results of solving some realistic tasks show that the MbSRN not only achieves a high goodness-of-fit of the target patterns but also maintains good spiking efficiency and storage capacity.","url":"https://doi.org/10.1142/s0129065719500060","authors":["Ruihan Hu","Qijun Huang","Hao Wang","Jin He","Sheng Chang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-02-08T03:03:46Z","doi":"10.1142/s0129065719500060","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1007/978-3-030-30487-4_10","name":"Brain-Inspired Hardware for Artificial Intelligence: Accelerated Learning in a Physical-Model Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-30487-4_10","authors":["Timo Wunderlich","Akos F. Kungl","Eric Müller","Johannes Schemmel","Mihai Petrovici"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-09-08T19:02:47Z","doi":"10.1007/978-3-030-30487-4_10","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.21203/rs.3.rs-10081852/v1","name":"Energy–Accuracy Trade-offs in Spiking Neural Networks: A Pareto Analysis on Fashion-MNIST","source":"crossref","abstract":"Abstract We tested a directly-trained, rate-coded SNN for Fashion-MNIST [28] (60,000 training images / 10,000 test images, each 28×28 greyscale, 10 classes) for varying numbers of simulation timesteps T = {1, 2, 4, 8, 16, 32, 64} over three randomly seeded runs. The overall energy cost of the full ANN on test was 21,361.7 nJ, the best SNN (T = 8) was 89.69% and 3,910.1 nJ, 5.5× less while introducing a 3.28% accuracy cost. For every doubling of timestep there is a corresponding loss of accuracy for the marginal accuracy gain dropped from + 4.17% per timestep doubling out to + 1.39% per timestep doubling at T = 8, after which it plummeted below + 0.5%. T = 8 was taken as the onset of the practical plateau. The findings of a capacity-constrained SmallANN ablation clearly demonstrates that the SNN efficiency advantage at T = 4–8 is not due to parameter reductions alone. SNNs do not match the ANN at full accuracy, but rather operate in a regime of diminishing energy dissipation at a Pareto-efficient position. Results showed timestep budget to be a key design parameter for SNN efficiency and indicate that by using a modest temporal resolution, a high level of accuracy is attained with greatly reduced computational costs.","url":"https://doi.org/10.21203/rs.3.rs-10081852/v1","authors":["Hassan Farooq"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-19T04:12:00Z","doi":"10.21203/rs.3.rs-10081852/v1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.1126/scirobotics.abk3268","name":"Spiking neural networks take control","source":"crossref","abstract":"Brain-inspired neural network architecture overcomes unsolved classical control theory problem for telerobotics.","url":"https://doi.org/10.1126/scirobotics.abk3268","authors":["Travis DeWolf"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-08T19:02:21Z","doi":"10.1126/scirobotics.abk3268","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1162/089976600300015240","name":"Multidimensional Encoding Strategy of Spiking Neurons","source":"crossref","abstract":"Neural responses in sensory systems are typically triggered by a multitude of stimulus features. Using information theory, we study the encoding accuracy of a population of stochastically spiking neurons characterized by different tuning widths for the different features. The optimal encoding strategy for representing one feature most accurately consists of narrow tuning in the dimension to be encoded, to increase the single-neuron Fisher information, and broad tuning in all other dimensions, to increase the number of active neurons. Extremely narrow tuning without sufficient receptive field overlap will severely worsen the coding. This implies the existence of an optimal tuning width for the feature to be encoded. Empirically, only a subset of all stimulus features will normally be accessible. In this case, relative encoding errors can be calculated that yield a criterion for the function of a neural population based on the measured tuning curves.","url":"https://doi.org/10.1162/089976600300015240","authors":["Christian W. Eurich","Stefan D. Wilke"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-27T11:56:30Z","doi":"10.1162/089976600300015240","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1016/j.neucom.2022.06.036","name":"Relaxation LIF: A gradient-based spiking neuron for direct training deep spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2022.06.036","authors":["Jianxiong Tang","Jian-Huang Lai","Wei-Shi Zheng","Lingxiao Yang","Xiaohua Xie"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-15T11:53:19Z","doi":"10.1016/j.neucom.2022.06.036","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.5220/0008164704790486","name":"Learning Method of Recurrent Spiking Neural Networks to Realize Various Firing Patterns using Particle Swarm Optimization","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0008164704790486","authors":["Yasuaki Kuroe","Hitoshi Iima","Yutaka Maeda"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-10-02T13:03:52Z","doi":"10.5220/0008164704790486","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1016/j.neunet.2020.12.012","name":"Constraints on Hebbian and STDP learned weights of a spiking neuron","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2020.12.012","authors":["Dominique Chu","Huy Le Nguyen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-01-02T05:57:49Z","doi":"10.1016/j.neunet.2020.12.012","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1088/2634-4386/ae8627/v2/review1","name":"Review for \"Energy-aware spike budgeting for continual learning in spiking neural networks for neuromorphic vision\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2634-4386/ae8627/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-03T23:27:36Z","doi":"10.1088/2634-4386/ae8627/v2/review1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.36227/techrxiv.175037299.95344486/v1","name":"Reinforcement Learning with Spiking Neural Networks for Robotic Applications: A Survey","source":"crossref","abstract":"Spiking Neural Networks (SNNs) have long been positioned as a biologically plausible and energy-efficient alternative to conventional deep learning models. Reinforcement Learning (RL), on the other hand, provides a framework for autonomous decision-making based on environmental interaction. While the convergence of SNNs and RL holds significant promise for robotics, this pathway remains in its infancy. This survey examines existing spiking RL approaches, categorizing them into bio-inspired models driven by reward-modulated local plasticity (e.g., R-STDP) and gradient-based models adapted from deep RL techniques. Additionally, we review neuron models, encoding schemes, and learning strategies, with emphasis on robotic applications. We further analyze evaluation metrics, emerging trends, limitations, and proposed future directions to bridge the gap between biological plausibility and scalable robotic intelligence. To the best of our knowledge, this work represents the first comprehensive survey specifically dedicated to RL with SNNs in robotic systems.","url":"https://doi.org/10.36227/techrxiv.175037299.95344486/v1","authors":["Katerina Maria Oikonomou","Ioannis Kansizoglou","Antonios Gasteratos"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-19T18:43:21Z","doi":"10.36227/techrxiv.175037299.95344486/v1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.5162/smsi2023/e6.4","name":"E6.4 - Biological Neural Coding for Adaptive Spiking Analog to Digital Conversion","source":"crossref","abstract":"","url":"https://doi.org/10.5162/smsi2023/e6.4","authors":["H. Abd","A. König"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-26T13:32:37Z","doi":"10.5162/smsi2023/e6.4","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/ijcnn.2012.6252699","name":"Implementation of configurable and multipurpose spiking neural networks on GPUs","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2012.6252699","authors":["Antonio Arista-Jalife","Roberto A. Vazquez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-08-01T16:47:51Z","doi":"10.1109/ijcnn.2012.6252699","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.52202/068431-2491","name":"Temporal Effective Batch Normalization in Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.52202/068431-2491","authors":["Chaoteng Duan","Jianhao Ding","Shiyan Chen","Zhaofei Yu","Tiejun Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-02T13:17:52Z","doi":"10.52202/068431-2491","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/ijcnn48605.2020.9206775","name":"Online Evolving Spiking Neural Networks for Incremental Air Pollution Prediction","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn48605.2020.9206775","authors":["Piotr S. Maciag","Marzena Kryszkiewicz","Robert Bembenik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-29T20:40:33Z","doi":"10.1109/ijcnn48605.2020.9206775","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1016/j.eswa.2025.129977","name":"Spiking Depth: Depth estimation from sparse events with spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.eswa.2025.129977","authors":["Dongze Liu","Yimeng Fan","Wenrui Lu","Changsong Liu","Wei Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-10T06:41:45Z","doi":"10.1016/j.eswa.2025.129977","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1021/jacs.5c00198.s002","name":"A Signal-Harmonizing Hybrid Neural Pathway Enabled by Bipolar-Chemo-Synapse Spiking Interneuron","source":"crossref","abstract":"","url":"https://doi.org/10.1021/jacs.5c00198.s002","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-14T00:20:21Z","doi":"10.1021/jacs.5c00198.s002","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1088/2634-4386/ae8627/v1/review1","name":"Review for \"Energy-aware spike budgeting for continual learning in spiking neural networks for neuromorphic vision\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2634-4386/ae8627/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-03T23:27:36Z","doi":"10.1088/2634-4386/ae8627/v1/review1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.1101/2024.08.05.606699","name":"Spike-to-excite: photosensitive seizures in biologically-realistic spiking neural networks","source":"crossref","abstract":"Abstract Photosensitive Epilepsy (PE) is a neurological disorder characterized by seizures triggered by harmful visual stimuli, such as flashing lights and high-contrast patterns. The mechanisms underlying PE remain poorly understood, and to date, no computational model has captured the phenomena associated with this condition. Biologically detailed spiking networks trained for efficient prediction of natural scenes have been shown to capture V1-like characteristics. Here, we show that these models display seizure-like activity in response to harmful stimuli while retaining healthy responses to non-provocative stimuli when post-synaptic inhibitory connections are weakened. Notably, our adapted model resembles the motion tuning and contrast gain responses of excitatory V1 neurons in mice with optogenetically reduced inhibitory activity. We offer testable predictions underlying the pathophysiology of PE by exploring how reduced inhibition leads to seizure-like activity. Finally, we show that artificially injecting pulsating input current into the model units prevents seizure-like activity and restores baseline function. In summary, we present a model of PE that offers new insights to understand and treat this condition.","url":"https://doi.org/10.1101/2024.08.05.606699","authors":["Luke Taylor","Melissa Claire Maaike Fasol"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-07T20:20:22Z","doi":"10.1101/2024.08.05.606699","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1162/neco_a_00580","name":"On Some Classes of Sequential Spiking Neural P Systems","source":"crossref","abstract":"Spiking neural P systems (SN P systems) are a class of distributed parallel computing devices inspired by the way neurons communicate by means of spikes; neurons work in parallel in the sense that each neuron that can fire should fire, but the work in each neuron is sequential in the sense that at most one rule can be applied at each computation step. In this work, with biological inspiration, we consider SN P systems with the restriction that at each step, one of the neurons (i.e., sequential mode) or all neurons (i.e., pseudo-sequential mode) with the maximum (or minimum) number of spikes among the neurons that are active (can spike) will fire. If an active neuron has more than one enabled rule, it nondeterministically chooses one of the enabled rules to be applied, and the chosen rule is applied in an exhaustive manner (a kind of local parallelism): the rule is used as many times as possible. This strategy makes the system sequential or pseudo-sequential from the global view of the whole network and locally parallel at the level of neurons. We obtain four types of SN P systems: maximum/minimum spike number induced sequential/pseudo-sequential SN P systems with exhaustive use of rules. We prove that SN P systems of these four types are all Turing universal as number-generating computation devices. These results illustrate that the restriction of sequentiality may have little effect on the computation power of SN P systems.","url":"https://doi.org/10.1162/neco_a_00580","authors":["Xingyi Zhang","Xiangxiang Zeng","Bin Luo","Linqiang Pan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-02-20T16:12:03Z","doi":"10.1162/neco_a_00580","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.5821/dissertation-2117-427834","name":"Highly scalable hardware architecture for real-time execution of spiking neural networks applied to neural cognitive applications","source":"crossref","abstract":"(English) This thesis contributes to the field of neuromorphic hardware. In particular, to the significant improvement of a scalable hardware architecture, named Hardware Emulator of Evolvable Neural Spiking Systems (HEENS), for the real-time execution of spiking neural networks (SNNs) in cognitive applications. SNNs are neural networks inspired by the biological activity of the brain, designed to process discrete temporal events, offering improved capabilities for handling temporal data as well as local plasticity, thus exhibiting greater energy efficiency compared to traditional neural networks.The HEENS architecture is implemented on several AMD (Xilinx) Zynq hardware platforms, which combine ARM processing cores with programmable logic (FPGAs), known for their high flexibility and parallelism in the execution of different neural models. One of the key achievements of this thesis is the optimization of the architecture to reduce latency, minimize resource usage, increase processing capacity, overcome previous architectural issues, and improve adaptability to various cognitive applications, such as sensory processing and pattern recognition.The results obtained can be divided into architectural contributions and experimental results in real applications. In the first part, this work improves the synaptic mapping capability, develops new system configuration mechanisms, and introduces interaction with external sensors.The enhanced system integrates an HDMI interface, demonstrating real-time visualization of neural activity and the neural and synaptic parameters of the SNN allows continuous monitoring without affecting system performance. This real-time monitoring capability has been tested in multiple experiments, where a precise representation of neural activity was observed on a 1 ms time scale, considered to be real-time, with support to other time scales, both faster or slower. The use of HEENS in physical sensor processing is highlighted, where it was proven that the architecture can adapt in real-time to changes in input signals, making it an ideal platform for applications in robotics and autonomous systems.Regarding testbenches and applications, significant results are presented in the implementation of cognitive applications using HEENS. In handwritten digit recognition, the architecture showed high accuracy using SNN models with synaptic plasticity, achieving good performance in terms of processing time and energy consumption compared to other existing solutions. Another key result is the hardware emulation of neuronal cultures, comparing the behavior of simulated neural networks in vitro, in silico, and in duris silico (physical hardware). The experiments showed that HEENS is capable of faithfully replicating the behavior and statistical properties observed in real neuronal cultures, opening new possibilities for research in neuroscience and biomedicine.Finally, the thesis concludes that the HEENS architecture not only offers a flexible and efficient environment for the research and development of SNN but also enables its implementation in real-world applications demanding real-time processing with good energy performance. The advances achieved in this work represent an important step toward the creation of next-generation scalable neuromorphic systems capable of efficiently emulating complex cognitive functions. (Català) Aquesta tesi contribueix al camp del maquinari neuromòrfic. En particular, a la millora significativa d'una arquitectura de maquinari escalable, anomenada Hardware Emulator of Evolvable Neural Spiking Systems (HEENS), per a l'execució en temps real de xarxes neuronals de polsos (SNNs) en aplicacions cognitives. Les SNNs són xarxes neuronals inspirades en l'activitat biològica del cervell, dissenyades per processar esdeveniments temporals discrets, oferint capacitats millorades per manejar dades temporals així com emprar plasticitat local, mostrant així una major eficiència energètica en comparació","url":"https://doi.org/10.5821/dissertation-2117-427834","authors":["Bernardo Javier Vallejo Mancero"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-11T01:22:18Z","doi":"10.5821/dissertation-2117-427834","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/icnc.2010.5584269","name":"Adaptive spiking neural P systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc.2010.5584269","authors":["Hong Peng","Jun Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-09-29T18:03:07Z","doi":"10.1109/icnc.2010.5584269","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1088/2634-4386/ae8627/v1/review2","name":"Review for \"Energy-aware spike budgeting for continual learning in spiking neural networks for neuromorphic vision\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2634-4386/ae8627/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-03T23:27:36Z","doi":"10.1088/2634-4386/ae8627/v1/review2","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.36227/techrxiv.177220005.52986713/v1","name":"Sleep-Mediated Replay Prevents Catastrophic Forgetting in Spiking Neural Networks Trained on Sequential Tasks","source":"crossref","abstract":"Catastrophic forgetting is a fundamental challenge in sequential learning for artificial neural networks, particularly spiking neural networks (SNNs), which aim to emulate biologically plausible neuronal dynamics. In this study, we investigate the role of sleep-mediated replay in mitigating catastrophic forgetting during sequential task learning. We trained a multilayer SNN on two sequentially presented image classification tasks (Task A and Task B) using spike-timing-dependent plasticity (STDP) learning rules. During offline periods, we implemented spontaneous replay of Task A patterns to emulate biological sleep consolidation. Our results demonstrate that sleep-mediated replay keeps Task A performance (0.589 before Task B, 0.206 after sleep) while allowing effective acquisition of Task B (0.672 before sleep). In contrast, networks trained sequentially without sleep exhibit severe forgetting (Task A drops to 0.011 after Task B). These findings suggest that sleep-like replay mechanisms can enable continual learning in SNNs, providing a computationally and biologically grounded approach to memory consolidation. We further analyze synaptic weight distributions and firing rate dynamics, revealing that sleep stabilizes task-specific synaptic patterns without impeding new learning. This work bridges computational neuroscience and artificial intelligence, suggesting that sleep-like replay could be an effective approach for continual learning in SNNs.","url":"https://doi.org/10.36227/techrxiv.177220005.52986713/v1","authors":["Yeteesh Sabbineni","Ethan Qiu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-27T13:47:40Z","doi":"10.36227/techrxiv.177220005.52986713/v1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1162/089976699300016502","name":"Spatiotemporal Coding in the Cortex: Information Flow-Based Learning in Spiking Neural Networks","source":"crossref","abstract":"We introduce a learning paradigm for networks of integrate-and-fire spiking neurons that is based on an information-theoretic criterion. This criterion can be viewed as a first principle that demonstrates the experimentally observed fact that cortical neurons display synchronous firing for some stimuli and not for others. The principle can be regarded as the postulation of a nonparametric reconstruction method as optimization criteria for learning the required functional connectivity that justifies and explains synchronous firing for binding of features as a mechanism for spatiotemporal coding. This can be expressed in an information-theoretic way by maximizing the discrimination ability between different sensory inputs in minimal time.","url":"https://doi.org/10.1162/089976699300016502","authors":["Gustavo Deco","Bernd Schürmann"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-27T11:55:01Z","doi":"10.1162/089976699300016502","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1152/jn.00697.2004","name":"A Point Process Framework for Relating Neural Spiking Activity to Spiking History, Neural Ensemble, and Extrinsic Covariate Effects","source":"crossref","abstract":"Multiple factors simultaneously affect the spiking activity of individual neurons. Determining the effects and relative importance of these factors is a challenging problem in neurophysiology. We propose a statistical framework based on the point process likelihood function to relate a neuron's spiking probability to three typical covariates: the neuron's own spiking history, concurrent ensemble activity, and extrinsic covariates such as stimuli or behavior. The framework uses parametric models of the conditional intensity function to define a neuron's spiking probability in terms of the covariates. The discrete time likelihood function for point processes is used to carry out model fitting and model analysis. We show that, by modeling the logarithm of the conditional intensity function as a linear combination of functions of the covariates, the discrete time point process likelihood function is readily analyzed in the generalized linear model (GLM) framework. We illustrate our approach for both GLM and non-GLM likelihood functions using simulated data and multivariate single-unit activity data simultaneously recorded from the motor cortex of a monkey performing a visuomotor pursuit-tracking task. The point process framework provides a flexible, computationally efficient approach for maximum likelihood estimation, goodness-of-fit assessment, residual analysis, model selection, and neural decoding. The framework thus allows for the formulation and analysis of point process models of neural spiking activity that readily capture the simultaneous effects of multiple covariates and enables the assessment of their relative importance.","url":"https://doi.org/10.1152/jn.00697.2004","authors":["Wilson Truccolo","Uri T. Eden","Matthew R. Fellows","John P. Donoghue","Emery N. Brown"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2004-09-08T20:25:28Z","doi":"10.1152/jn.00697.2004","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1016/j.neucom.2026.132988","name":"SGSSA: Spatio-temporal granular-threshold spiking self-attention for spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2026.132988","authors":["Heng Zhang","LiQing Geng","GengHuang Yang","Yongfeng Zheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-07T15:57:15Z","doi":"10.1016/j.neucom.2026.132988","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.7763/ijmo.2012.v2.108","name":"Dynamic Quantum-Inspired Particle Swarm Optimizationas Feature and Parameter Optimizer for Evolving Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.7763/ijmo.2012.v2.108","authors":["Haza Nuzly Abdull Hamed","Nikola Kasabov","Siti Mariyam Shamsuddin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-11-18T04:14:49Z","doi":"10.7763/ijmo.2012.v2.108","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/ijcnn60899.2024.10650965","name":"Adaptive Spiking TD3+BC for Offline-to-Online Spiking Reinforcement Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn60899.2024.10650965","authors":["Xiangfei Yang","Jian Song","Xuetao Zhang","Donglin Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T17:35:05Z","doi":"10.1109/ijcnn60899.2024.10650965","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/ijcnn.2018.8489535","name":"A Biologically Plausible Speech Recognition Framework Based on Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2018.8489535","authors":["Jibin Wu","Yansong Chua","Haizhou Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-10-19T22:25:09Z","doi":"10.1109/ijcnn.2018.8489535","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/ijcnn.2014.6889597","name":"Stochastic Spiking Neural Networks at the EDGE of CHAOS","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2014.6889597","authors":["J.L. Rossello","V. Canals","A. Oliver","A. Morro"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-09-10T10:30:33Z","doi":"10.1109/ijcnn.2014.6889597","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1162/neco_a_01290","name":"Minimal Spiking Neuron for Solving Multilabel Classification Tasks","source":"crossref","abstract":"The multispike tempotron (MST) is a powersul, single spiking neuron model that can solve complex supervised classification tasks. It is also internally complex, computationally expensive to evaluate, and unsuitable for neuromorphic hardware. Here we aim to understand whether it is possible to simplify the MST model while retaining its ability to learn and process information. To this end, we introduce a family of generalized neuron models (GNMs) that are a special case of the spike response model and much simpler and cheaper to simulate than the MST. We find that over a wide range of parameters, the GNM can learn at least as well as the MST does. We identify the temporal autocorrelation of the membrane potential as the most important ingredient of the GNM that enables it to classify multiple spatiotemporal patterns. We also interpret the GNM as a chemical system, thus conceptually bridging computation by neural networks with molecular information processing. We conclude the letter by proposing alternative training approaches for the GNM, including error trace learning and error backpropagation.","url":"https://doi.org/10.1162/neco_a_01290","authors":["Jakub Fil","Dominique Chu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-05-20T23:03:41Z","doi":"10.1162/neco_a_01290","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1162/0899766053630332","name":"A Unified Approach to Building and Controlling Spiking Attractor Networks","source":"crossref","abstract":"Extending work in Eliasmith and Anderson (2003), we employ a general framework to construct biologically plausible simulations of the three classes of attractor networks relevant for biological systems: static (point, line, ring, and plane) attractors, cyclic attractors, and chaotic attractors. We discuss these attractors in the context of the neural systems that they have been posited to help explain: eye control, working memory, and head direction; locomotion (specifically swimming); and olfaction, respectively. We then demonstrate how to introduce control into these models. The addition of control shows how attractor networks can be used as subsystems in larger neural systems, demonstrates how a much larger class of networks can be related to attractor networks, and makes it clear how attractor networks can be exploited for various information processing tasks in neurobiological systems.","url":"https://doi.org/10.1162/0899766053630332","authors":["Chris Eliasmith"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-04-11T19:24:40Z","doi":"10.1162/0899766053630332","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/ijcnn54540.2023.10191572","name":"A Bio-Inspired Computational Astrocyte Model for Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn54540.2023.10191572","authors":["Jacob Kiggins","J. David Schaffer","Cory Merkel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-02T17:30:03Z","doi":"10.1109/ijcnn54540.2023.10191572","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1007/978-3-642-24965-5_28","name":"Spiking Neural PID Controllers","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-24965-5_28","authors":["Andrew Webb","Sergio Davies","David Lester"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-11-10T18:56:48Z","doi":"10.1007/978-3-642-24965-5_28","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.31988/scitrends.40920","name":"Biologically-Plausible Spiking Neural Networks For Object Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.31988/scitrends.40920","authors":["Milad Mozafari","Saeed Reza Kheradpisheh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-10-19T16:42:07Z","doi":"10.31988/scitrends.40920","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.53846/goediss-42","name":"Think local, act global: robust and real-time movement encoding in spiking neural networks using neuromorphic hardware","source":"crossref","abstract":"","url":"https://doi.org/10.53846/goediss-42","authors":["Carlo Michaelis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-08T14:00:08Z","doi":"10.53846/goediss-42","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.2139/ssrn.6291883","name":"Multimodal Representation Learning in a Spiking Neural Networks Framework","source":"crossref","abstract":"Multimodal representation learning aims to integrate heterogeneous modalities—such as text, image, audio, and video—into a unified representation. However, modality imbalance and inter-modal interference often lead to modality collapse, limiting generalization, especially under noisy or incomplete inputs. To address this, we propose Spiking-based Multimodal Representation Learning(S-MRL), a spiking neural network (SNN) framework that reformulates multimodal learning as a process of spike sequence encoding and integration. S-MRL employs biologically inspired spike encoders and a Spiking Response Model(SRM) to extract temporally structured, modality-specific features. A Gaussian Kernel Spike Distance(GKSD) is introduced to construct a shared latent space across modalities, while Joint Entropy(JE) captures cross-modal information and preserves semantic diversity. A Recurrent Spiking Neural Networks(SNN) architecture is further designed to mitigate forgetting and stabilize training. During inference, an informative fusion mechanism aggregates spike-based representations, and Cross-Entropy(CE) supervises downstream classification. Extensive experiments on four multimodal benchmarks— under both complete and missing modality settings—demonstrate that S-MRL achieves 4%–19% accuracy improvements over existing methods, while enhancing energy efficiency, robustness, and generalization. These results establish S-MRL as a principled and biologically plausible solution for robust multimodal representation learning.","url":"https://doi.org/10.2139/ssrn.6291883","authors":["yuping zhang","Yan Liu","Chunfang Yang","Zilin zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-23T12:42:35Z","doi":"10.2139/ssrn.6291883","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1162/neco.2009.10-08-885","name":"Spiking Neural Networks for Cortical Neuronal Spike Train Decoding","source":"crossref","abstract":"Recent investigation of cortical coding and computation indicates that temporal coding is probably a more biologically plausible scheme used by neurons than the rate coding used commonly in most published work. We propose and demonstrate in this letter that spiking neural networks (SNN), consisting of spiking neurons that propagate information by the timing of spikes, are a better alternative to the coding scheme based on spike frequency (histogram) alone. The SNN model analyzes cortical neural spike trains directly without losing temporal information for generating more reliable motor command for cortically controlled prosthetics. In this letter, we compared the temporal pattern classification result from the SNN approach with results generated from firing-rate-based approaches: conventional artificial neural networks, support vector machines, and linear regression. The results show that the SNN algorithm can achieve higher classification accuracy and identify the spiking activity related to movement control earlier than the other methods. Both are desirable characteristics for fast neural information processing and reliable control command pattern recognition for neuroprosthetic applications.","url":"https://doi.org/10.1162/neco.2009.10-08-885","authors":["Huijuan Fang","Yongji Wang","Jiping He"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-11-19T00:59:10Z","doi":"10.1162/neco.2009.10-08-885","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1007/s11063-021-10680-x","name":"BS4NN: Binarized Spiking Neural Networks with Temporal Coding and Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11063-021-10680-x","authors":["Saeed Reza Kheradpisheh","Maryam Mirsadeghi","Timothée Masquelier"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-10T21:02:55Z","doi":"10.1007/s11063-021-10680-x","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.21428/8e6ba8ef.f3710abe","name":"Modelling Strength-Based Representations in Memory Using Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.21428/8e6ba8ef.f3710abe","authors":["Patrick Tsapoitis","Jakeb Chouinard","Myra Fernandes"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-11T01:19:47Z","doi":"10.21428/8e6ba8ef.f3710abe","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.2139/ssrn.6076628","name":"Green Neuromorphic Computing: Quantifying the Energy Efficiency of Spiking Neural Networks for Edge AI Applications","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.6076628","authors":["Aashish Dhakal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-26T16:06:51Z","doi":"10.2139/ssrn.6076628","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1101/2022.05.03.490412","name":"Introducing the Dendrify framework for incorporating dendrites to spiking neural networks","source":"crossref","abstract":"Abstract Computational modeling has been indispensable for understanding how subcellular neuronal features influence circuit processing. However, the role of dendritic computations in network-level operations remains largely unexplored. This is partly because existing tools do not allow the development of realistic and efficient network models that account for dendrites. Current spiking neural networks, although efficient, are usually quite simplistic, overlooking essential dendritic properties. Conversely, circuit models with morphologically detailed neuron models are computationally costly, thus impractical for large-network simulations. To bridge the gap between these two extremes and facilitate the adoption of dendritic features in spiking neural networks, we introduce Dendrify, an open-source Python package based on Brian 2. Dendrify, through simple commands, automatically generates reduced compartmental neuron models with simplified yet biologically relevant dendritic and synaptic integrative properties. Such models strike a good balance between flexibility, performance, and biological accuracy, allowing us to explore dendritic contributions to network-level functions while paving the way for developing more powerful neuromorphic systems.","url":"https://doi.org/10.1101/2022.05.03.490412","authors":["Michalis Pagkalos","Spyridon Chavlis","Panayiota Poirazi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-05-04T13:35:28Z","doi":"10.1101/2022.05.03.490412","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/ijcnn48605.2020.9207019","name":"Robustness to Noisy Synaptic Weights in Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn48605.2020.9207019","authors":["Chen Li","Runze Chen","Christoforos Moutafis","Steve Furber"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-30T00:40:33Z","doi":"10.1109/ijcnn48605.2020.9207019","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.52202/079017-3751","name":"Latent Diffusion for Neural Spiking Data","source":"crossref","abstract":"","url":"https://doi.org/10.52202/079017-3751","authors":["Jaivardhan Kapoor","Auguste Schulz","Julius Vetter","Felix Pei","Richard Gao","Jakob Macke"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-03T11:20:56Z","doi":"10.52202/079017-3751","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/ijcnn55064.2022.9892618","name":"Object Detection with Spiking Neural Networks on Automotive Event Data","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn55064.2022.9892618","authors":["Loic Cordone","Benoit Miramond","Philippe Thierion"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-30T15:56:04Z","doi":"10.1109/ijcnn55064.2022.9892618","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1162/neco_a_01752","name":"Elucidating the Theoretical Underpinnings of Surrogate Gradient Learning in Spiking Neural Networks","source":"crossref","abstract":"Abstract Training spiking neural networks to approximate universal functions is essential for studying information processing in the brain and for neuromorphic computing. Yet the binary nature of spikes poses a challenge for direct gradient-based training. Surrogate gradients have been empirically successful in circumventing this problem, but their theoretical foundation remains elusive. Here, we investigate the relation of surrogate gradients to two theoretically well-founded approaches. On the one hand, we consider smoothed probabilistic models, which, due to the lack of support for automatic differentiation, are impractical for training multilayer spiking neural networks but provide derivatives equivalent to surrogate gradients for single neurons. On the other hand, we investigate stochastic automatic differentiation, which is compatible with discrete randomness but has not yet been used to train spiking neural networks. We find that the latter gives surrogate gradients a theoretical basis in stochastic spiking neural networks, where the surrogate derivative matches the derivative of the neuronal escape noise function. This finding supports the effectiveness of surrogate gradients in practice and suggests their suitability for stochastic spiking neural networks. However, surrogate gradients are generally not gradients of a surrogate loss despite their relation to stochastic automatic differentiation. Nevertheless, we empirically confirm the effectiveness of surrogate gradients in stochastic multilayer spiking neural networks and discuss their relation to deterministic networks as a special case. Our work gives theoretical support to surrogate gradients and the choice of a suitable surrogate derivative in stochastic spiking neural networks.","url":"https://doi.org/10.1162/neco_a_01752","authors":["Julia Gygax","Friedemann Zenke"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-20T18:41:15Z","doi":"10.1162/neco_a_01752","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1162/neco_a_01674","name":"Bioplausible Unsupervised Delay Learning for Extracting Spatiotemporal Features in Spiking Neural Networks","source":"crossref","abstract":"Abstract The plasticity of the conduction delay between neurons plays a fundamental role in learning temporal features that are essential for processing videos, speech, and many high-level functions. However, the exact underlying mechanisms in the brain for this modulation are still under investigation. Devising a rule for precisely adjusting the synaptic delays could eventually help in developing more efficient and powerful brain-inspired computational models. In this article, we propose an unsupervised bioplausible learning rule for adjusting the synaptic delays in spiking neural networks. We also provide the mathematical proofs to show the convergence of our rule in learning spatiotemporal patterns. Furthermore, to show the effectiveness of our learning rule, we conducted several experiments on random dot kinematogram and a subset of DVS128 Gesture data sets. The experimental results indicate the efficiency of applying our proposed delay learning rule in extracting spatiotemporal features in an STDP-based spiking neural network.","url":"https://doi.org/10.1162/neco_a_01674","authors":["Alireza Nadafian","Mohammad Ganjtabesh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-22T22:53:02Z","doi":"10.1162/neco_a_01674","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/ijcnn54540.2023.10191614","name":"Time series prediction and anomaly detection with recurrent spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn54540.2023.10191614","authors":["Yann Cherdo","Benoit Miramond","Alain Pegatoquet"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-02T17:30:03Z","doi":"10.1109/ijcnn54540.2023.10191614","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1021/jacs.5c00198.s001","name":"A Signal-Harmonizing Hybrid Neural Pathway Enabled by Bipolar-Chemo-Synapse Spiking Interneuron","source":"crossref","abstract":"","url":"https://doi.org/10.1021/jacs.5c00198.s001","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-14T00:20:21Z","doi":"10.1021/jacs.5c00198.s001","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1088/2634-4386/ae8627/v1/review3","name":"Review for \"Energy-aware spike budgeting for continual learning in spiking neural networks for neuromorphic vision\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2634-4386/ae8627/v1/review3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-03T23:27:36Z","doi":"10.1088/2634-4386/ae8627/v1/review3","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1016/j.neunet.2022.12.008","name":"S\n                    <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" display=\"inline\" id=\"d1e2582\" altimg=\"si15.svg\">\n                      <mml:msup>\n                        <mml:mrow/>\n                        <mml:mrow>\n                          <mml:mn>3</mml:mn>\n                        </mml:mrow>\n                      </mml:msup>\n                    </mml:math>\n                    NN: Time step reduction of spiking surrogate gradients for training energy efficient single-step spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2022.12.008","authors":["Kazuma Suetake","Shin-ichi Ikegawa","Ryuji Saiin","Yoshihide Sawada"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-19T11:29:06Z","doi":"10.1016/j.neunet.2022.12.008","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/ijcnn.2010.5596914","name":"Learning methods of recurrent Spiking Neural Networks based on adjoint equations approach","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2010.5596914","authors":["Yasuaki Kuroe","Tomokazu Ueyama"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-10-19T14:58:15Z","doi":"10.1109/ijcnn.2010.5596914","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.3390/app12115749","name":"Effective Conversion of a Convolutional Neural Network into a Spiking Neural Network for Image Recognition Tasks","source":"crossref","abstract":"Due to energy efficiency, spiking neural networks (SNNs) have gradually been considered as an alternative to convolutional neural networks (CNNs) in various machine learning tasks. In image recognition tasks, leveraging the superior capability of CNNs, the CNN–SNN conversion is considered one of the most successful approaches to training SNNs. However, previous works assume a rather long inference time period called inference latency to be allowed, while having a trade-off between inference latency and accuracy. One of the main reasons for this phenomenon stems from the difficulty in determining proper a firing threshold for spiking neurons. The threshold determination procedure is called a threshold balancing technique in the CNN–SNN conversion approach. This paper proposes a CNN–SNN conversion method with a new threshold balancing technique that obtains converted SNN models with good accuracy even with low latency. The proposed method organizes the SNN models with soft-reset IF spiking neurons. The threshold balancing technique estimates the thresholds for spiking neurons based on the maximum input current in a layerwise and channelwise manner. The experiment results have shown that our converted SNN models attain even higher accuracy than the corresponding trained CNN model for the MNIST dataset with low latency. In addition, for the Fashion-MNIST and CIFAR-10 datasets, our converted SNNs have shown less conversion loss than other methods in low latencies. The proposed method can be beneficial in deploying efficient SNN models for recognition tasks on resource-limited systems because the inference latency is strongly associated with energy consumption.","url":"https://doi.org/10.3390/app12115749","authors":["Huynh Cong Viet Ngu","Keon Myung Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-06T10:08:24Z","doi":"10.3390/app12115749","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1162/089976698300017098","name":"Fast Temporal Encoding and Decoding with Spiking Neurons","source":"crossref","abstract":"We propose a simple theoretical structure of interacting integrate-and-fire neurons that can handle fast information processing and may account for the fact that only a few neuronal spikes suffice to transmit information in the brain. Using integrate-and-fire neurons that are subjected to individual noise and to a common external input, we calculate their first passage time (FPT), or interspike interval. We suggest using a population average for evaluating the FPT that represents the desired information. Instantaneous lateral excitation among these neurons helps the analysis. By employing a second layer of neurons with variable connections to the first layer, we represent the strength of the input by the number of output neurons that fire, thus decoding the temporal information. Such a model can easily lead to a logarithmic relation as in Weber's law. The latter follows naturally from information maximization if the input strength is statistically distributed according to an approximate inverse law.","url":"https://doi.org/10.1162/089976698300017098","authors":["David Horn","Sharon Levanda"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-27T11:55:01Z","doi":"10.1162/089976698300017098","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1162/neco.2008.05-08-792","name":"Capacity of a Single Spiking Neuron Channel","source":"crossref","abstract":"","url":"https://doi.org/10.1162/neco.2008.05-08-792","authors":["Shiro Ikeda","Jonathan H. Manton"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-02-02T18:54:21Z","doi":"10.1162/neco.2008.05-08-792","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1162/neco_a_00116","name":"Mechanisms That Modulate the Transfer of Spiking Correlations","source":"crossref","abstract":"Correlations between neuronal spike trains affect network dynamics and population coding. Overlapping afferent populations and correlations between presynaptic spike trains introduce correlations between the inputs to downstream cells. To understand network activity and population coding, it is therefore important to understand how these input correlations are transferred to output correlations.Recent studies have addressed this question in the limit of many inputs with infinitesimal postsynaptic response amplitudes, where the total input can be approximated by gaussian noise. In contrast, we address the problem of correlation transfer by representing input spike trains as point processes, with each input spike eliciting a finite postsynaptic response. This approach allows us to naturally model synaptic noise and recurrent coupling and to treat excitatory and inhibitory inputs separately.We derive several new results that provide intuitive insights into the fundamental mechanisms that modulate the transfer of spiking correlations.","url":"https://doi.org/10.1162/neco_a_00116","authors":["Robert Rosenbaum","Krešimir Josić"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-02-07T22:27:58Z","doi":"10.1162/neco_a_00116","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/ijcnn.2017.7966154","name":"INXS: Bridging the throughput and energy gap for spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2017.7966154","authors":["Surya Narayanan","Ali Shafiee","Rajeev Balasubramonian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-07-10T21:41:30Z","doi":"10.1109/ijcnn.2017.7966154","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.52202/075280-3269","name":"Trial matching: capturing variability with data-constrained spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.52202/075280-3269","authors":["Christos Sourmpis","Carl Petersen","Wulfram Gerstner","Guillaume Bellec"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-02T13:18:04Z","doi":"10.52202/075280-3269","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1162/neco_a_00681","name":"Spatiotemporal Conditional Inference and Hypothesis Tests for Neural Ensemble Spiking Precision","source":"crossref","abstract":"The collective dynamics of neural ensembles create complex spike patterns with many spatial and temporal scales. Understanding the statistical structure of these patterns can help resolve fundamental questions about neural computation and neural dynamics. Spatiotemporal conditional inference (STCI) is introduced here as a semiparametric statistical framework for investigating the nature of precise spiking patterns from collections of neurons that is robust to arbitrarily complex and nonstationary coarse spiking dynamics. The main idea is to focus statistical modeling and inference not on the full distribution of the data, but rather on families of conditional distributions of precise spiking given different types of coarse spiking. The framework is then used to develop families of hypothesis tests for probing the spatiotemporal precision of spiking patterns. Relationships among different conditional distributions are used to improve multiple hypothesis-testing adjustments and design novel Monte Carlo spike resampling algorithms. Of special note are algorithms that can locally jitter spike times while still preserving the instantaneous peristimulus time histogram or the instantaneous total spike count from a group of recorded neurons. The framework can also be used to test whether first-order maximum entropy models with possibly random and time-varying parameters can account for observed patterns of spiking. STCI provides a detailed example of the generic principle of conditional inference, which may be applicable to other areas of neurostatistical analysis.","url":"https://doi.org/10.1162/neco_a_00681","authors":["Matthew T. Harrison","Asohan Amarasingham","Wilson Truccolo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-11-07T19:42:44Z","doi":"10.1162/neco_a_00681","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1016/j.neunet.2007.12.037","name":"Compact silicon neuron circuit with spiking and bursting behaviour","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2007.12.037","authors":["Jayawan H.B. Wijekoon","Piotr Dudek"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-02-12T15:20:47Z","doi":"10.1016/j.neunet.2007.12.037","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.52202/068431-1506","name":"Online Training Through Time for Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.52202/068431-1506","authors":["Mingqing Xiao","Qingyan Meng","Zongpeng Zhang","Di He","Zhouchen Lin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-02T13:17:52Z","doi":"10.52202/068431-1506","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1016/b978-0-44-332820-6.00009-4","name":"Fundamentals of spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-44-332820-6.00009-4","authors":["Hong Qu","Xiaoling Luo","Zhang Yi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-28T07:47:34Z","doi":"10.1016/b978-0-44-332820-6.00009-4","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/ijcnn.2018.8489628","name":"Spiking Neural Algorithms for Markov Process Random Walk","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2018.8489628","authors":["William Severa","Rich Lehoucq","Ojas Parekh","James B. Aimone"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-10-19T18:25:09Z","doi":"10.1109/ijcnn.2018.8489628","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1007/s00521-016-2398-1","name":"SpikingLab: modelling agents controlled by Spiking Neural Networks in Netlogo","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-016-2398-1","authors":["Cristian Jimenez-Romero","Jeffrey Johnson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-06-07T15:55:24Z","doi":"10.1007/s00521-016-2398-1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1101/829556","name":"Toward One-Shot Learning in Neuroscience-Inspired Deep Spiking Neural Networks","source":"crossref","abstract":"Abstract Conventional deep neural networks capture essential information processing stages in perception. Deep neural networks often require very large volume of training examples, whereas children can learn concepts such as hand-written digits with few examples. The goal of this project is to develop a deep spiking neural network that can learn from few training trials. Using known neuronal mechanisms, a spiking neural network model is developed and trained to recognize hand-written digits with presenting one to four training examples for each digit taken from the MNIST database. The model detects and learns geometric features of the images from MNIST database. In this work, a novel biological back-propagation based learning rule is developed and used to a train the network to detect basic features of different digits. For this purpose, randomly initialized synaptic weights between the layers are being updated. By using a neuroscience inspired mechanism named ‘synaptic pruning’ and a predefined threshold, some of the synapses through the training are deleted. Hence, information channels are constructed that are highly specific for each digit as matrix of synaptic connections between two layers of spiking neural networks. These connection matrixes named ‘information channels’ are used in the test phase to assign a digit class to each test image. As similar to humans’ abilities to learn from small training trials, the developed spiking neural network needs a very small dataset for training, compared to conventional deep learning methods checked on MNIST dataset.","url":"https://doi.org/10.1101/829556","authors":["Faramarz Faghihi","Hossein Molhem","Ahmed A. Moustafa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-11-05T01:51:20Z","doi":"10.1101/829556","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1016/j.neunet.2015.07.004","name":"Neuromorphic implementations of neurobiological learning algorithms for spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2015.07.004","authors":["Florian Walter","Florian Röhrbein","Alois Knoll"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T18:31:10Z","doi":"10.1016/j.neunet.2015.07.004","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1088/1741-2552/adec1c","name":"Manipulation of neuronal activity by an artificial spiking neural network implemented on a closed-loop brain-computer interface in non-human primates","source":"europepmc","abstract":"Abstract Objective. Closed-loop brain-computer interfaces can be used to bridge, modulate, or repair damaged connections within the brain to restore functional deficits. Towards this goal, we demonstrate that small artificial spiking neural networks can be bidirectionally interfaced with single neurons (SNs) in the neocortex of non-human primates (NHPs) to create artificial connections between the SNs to manipulate their activity in predictable ways. Approach. Spikes from a small group of SNs were recorded from primary motor cortex of two awake NHPs during rest. The SNs were then interfaced with a small network of integrate-and-fire units (IFUs) that were programmed on a custom clBCI. Spikes from the SNs evoked excitatory and/or inhibitory postsynaptic potentials in the IFUs, which themselves spiked when their membrane potentials exceeded a predetermined threshold. Spikes from the IFUs triggered single pulses of intracortical microstimulation (ICMS) to modulate the activity of the cortical SNs. Main results. We show that the altered closed-loop dynamics within the cortex depends on several factors including the connectivity between the SNs and IFUs, as well as the precise timing of the ICMS. We additionally show that the closed-loop dynamics can reliably be modeled from open-loop measurements. Significance. Our results demonstrate a new type of hybrid biological-artificial neural system based on a clBCI that interfaces SNs in the brain with artificial IFUs to modulate biological activity in the brain. Our model of the closed-loop dynamics may be leveraged in the future to develop training algorithms that shape the closed-loop dynamics of networks in the brain to correct aberrant neural activity and rehabilitate damaged neural circuits.","url":"https://doi.org/10.1088/1741-2552/adec1c","authors":["Jonathan Mishler","Richy Yun","Steve Perlmutter","Rajesh P N Rao","Eberhard Fetz"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1088/1741-2552/adec1c","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/ijcnn.2012.6252440","name":"Scalable multi-precision simulation of spiking neural networks on GPU with OpenCL","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2012.6252440","authors":["Dmitri Yudanov","Leon Reznik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-08-01T16:47:51Z","doi":"10.1109/ijcnn.2012.6252440","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1162/089976605774320601","name":"On the Nonlearnability of a Single Spiking Neuron","source":"crossref","abstract":"We study the computational complexity of training a single spiking neuron N with binary coded inputs and output that, in addition to adaptive weights and a threshold, has adjustable synaptic delays. A synchronization technique is introduced so that the results concerning the nonlearn-ability of spiking neurons with binary delays are generalized to arbitrary real-valued delays. In particular, the consistency problem for N with programmable weights, a threshold, and delays, and its approximation version are proven to be NP-complete. It follows that the spiking neurons with arbitrary synaptic delays are not properly PAC learnable and do not allow robust learning unless RP = NP. In addition, the representation problem for N, a question whether an n-variable Boolean function given in DNF (or as a disjunction of O(n) threshold gates) can be computed by a spiking neuron, is shown to be coNP-hard.","url":"https://doi.org/10.1162/089976605774320601","authors":["Jiří Šíma","Jiří Sgall"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-09-28T20:53:50Z","doi":"10.1162/089976605774320601","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/ijcnn.2011.6033443","name":"A reversibility analysis of encoding methods for spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2011.6033443","authors":["C. Johnson","S. Roychowdhury","G. K. Venayagamoorthy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-10-06T17:24:17Z","doi":"10.1109/ijcnn.2011.6033443","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1162/089976600300015295","name":"Dynamics of Spiking Neurons with Electrical Coupling","source":"crossref","abstract":"We analyze the existence and stability of phase-locked states of neurons coupled electrically with gap junctions. We show that spike shape and size, along with driving current (which affects network frequency), play a large role in which phase-locked modes exist and are stable. Our theory makes predictions about biophysical models using spikes of different shapes, and we present simulations to confirm the predictions. We also analyze a large system of all-to-all coupled neurons and show that the splay-phase state can exist only for a certain range of frequencies.","url":"https://doi.org/10.1162/089976600300015295","authors":["Carson C. Chow","Nancy Kopell"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-27T11:56:30Z","doi":"10.1162/089976600300015295","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/icp60417.2023.10397433","name":"Advantages and Disadvantages of Spiking Neural Networks Compared to Classical Artificial Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icp60417.2023.10397433","authors":["Igor Semenov","Dmitry Nikitin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-19T18:40:04Z","doi":"10.1109/icp60417.2023.10397433","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1007/978-3-658-45318-3_6","name":"Conclusion and Future Directions","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-658-45318-3_6","authors":["Muhammad Arsalan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-01T06:02:42Z","doi":"10.1007/978-3-658-45318-3_6","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1201/9781439815328-p4","name":"Third Generation Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781439815328-p4","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-06-28T18:54:11Z","doi":"10.1201/9781439815328-p4","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/ijcnn54540.2023.10191334","name":"Learning to Classify Faster Using Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn54540.2023.10191334","authors":["Pranav Machingal","Thousif","Shirin Dora","Suresh Sundaram","Qinggang Meng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-02T17:30:03Z","doi":"10.1109/ijcnn54540.2023.10191334","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.2139/ssrn.4580664","name":"Adaptive Synapse Control Mechanism to Improve Learning Performances of Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4580664","authors":["Hyun-Jong Lee","Jae-Han Lim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-22T20:17:20Z","doi":"10.2139/ssrn.4580664","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1088/2634-4386/ae8627/v2/decision1","name":"Decision letter for \"Energy-aware spike budgeting for continual learning in spiking neural networks for neuromorphic vision\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2634-4386/ae8627/v2/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-03T23:27:36Z","doi":"10.1088/2634-4386/ae8627/v2/decision1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1162/089976603322518759","name":"Differences in Spiking Patterns Among Cortical Neurons","source":"crossref","abstract":"Spike sequences recorded from four cortical areas of an awake behaving monkey were examined to explore characteristics that vary among neurons. We found that a measure of the local variation of interspike intervals, L V , is nearly the same for every spike sequence for any given neuron, while it varies significantly among neurons. The distributions of L V values for neuron ensembles in three of the four areas were found to be distinctly bimodal. Two groups of neurons classified according to the spiking irregularity exhibit different responses to the same stimulus. This suggests that neurons in each area can be classified into different groups possessing unique spiking statistics and corresponding functional properties.","url":"https://doi.org/10.1162/089976603322518759","authors":["Shigeru Shinomoto","Keisetsu Shima","Jun Tanji"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-11-02T18:29:22Z","doi":"10.1162/089976603322518759","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.36227/techrxiv.20444970","name":"Neuromorphic Deep Spiking Neural Networks for Seizure Detection","source":"crossref","abstract":"&lt;p&gt;There are a total of three publicly accessible datasets used, including the Boston Children’s Hospital–MIT (CHB-MIT) dataset from the U.S. and the Freiburg (FB) and EPILEPSIAE intracranial EEG (iEEG) datasets from Germany. &lt;/p&gt;","url":"https://doi.org/10.36227/techrxiv.20444970","authors":["Yikai Yang","Jason Eshraghian","Nhan Duy Truong","Armin Nikpour","Omid Kavehei"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-08-11T04:37:49Z","doi":"10.36227/techrxiv.20444970","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.36227/techrxiv.20444970.v1","name":"Neuromorphic Deep Spiking Neural Networks for Seizure Detection","source":"crossref","abstract":"There are a total of three publicly accessible datasets used, including the Boston Children’s Hospital–MIT (CHB-MIT) dataset from the U.S. and the Freiburg (FB) and EPILEPSIAE intracranial EEG (iEEG) datasets from Germany.","url":"https://doi.org/10.36227/techrxiv.20444970.v1","authors":["Yikai Yang","Jason Eshraghian","Nhan Duy Truong","Armin Nikpour","Omid Kavehei"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-08-11T00:37:47Z","doi":"10.36227/techrxiv.20444970.v1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/tnnls.2025.3623703","name":"An Intrinsically Knowledge-Transferring Developmental Spiking Neural Network for Tactile Classification","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tnnls.2025.3623703","authors":["Jiaqi Xing","Yizhi Liu","Zezheng Zhang","Libo Chen","Mohammed Nazibul Hasan","Zhi-Bin Zhang"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025-10-30T18:03:10Z","doi":"10.1109/tnnls.2025.3623703","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1016/j.neunet.2013.02.003","name":"A supervised multi-spike learning algorithm based on gradient descent for spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2013.02.003","authors":["Yan Xu","Xiaoqin Zeng","Lixin Han","Jing Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-02-16T08:00:53Z","doi":"10.1016/j.neunet.2013.02.003","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.2495/iccts140531","name":"Building a self-learning memristor-based spiking neural network on handwritten digit recognition and orientation extraction","source":"crossref","abstract":"","url":"https://doi.org/10.2495/iccts140531","authors":["Mingli He","Honelei Gao","Quansheng Ren","Jianye Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-10-09T09:26:44Z","doi":"10.2495/iccts140531","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1145/2701973.2702727","name":"An Unsupervised Learning Approach for Classifying Sequence Data for Human Robotic Interaction Using Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1145/2701973.2702727","authors":["Banafsheh Rekabdar","Monica Nicolescu","Mircea Nicolescu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-03-03T14:15:23Z","doi":"10.1145/2701973.2702727","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/ispa63168.2024.00225","name":"Multimodal Identity Recognition of Spiking Neural Network Based on Brain-Inspired Reward Propagation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ispa63168.2024.00225","authors":["Yang Liu","Hongxia Zhang","Yahui Li","Quanqiang Wang","Cheng Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-20T20:05:50Z","doi":"10.1109/ispa63168.2024.00225","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/access.2026.3675314","name":"A 512-Neuron 500 k-Synapse 3.58-pJ/SOP Reconfigurable Spiking Neural Network With Time-Step Update Packet Aggregation and LIF/ALIF Neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1109/access.2026.3675314","authors":["Jingyu Wang","Delong Shang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-18T19:40:12Z","doi":"10.1109/access.2026.3675314","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1145/3706594.3726979","name":"SYNtzulA: Open-Source Hardware for Energy-Efficient Spiking Neural Network Inference","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3706594.3726979","authors":["Luca Martis","Gianluca Leone","Luigi Raffo","Paolo Meloni"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-07T04:13:09Z","doi":"10.1145/3706594.3726979","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/bibm66473.2025.11355976","name":"MA-SGNN: A Multi-view Adaptive Spiking Graph Neural Network for Event-based Tactile Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bibm66473.2025.11355976","authors":["Wei Chi","Ying Zhang","Xiaolu Zhang","Mingyuan Ma","Jin Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-29T21:19:40Z","doi":"10.1109/bibm66473.2025.11355976","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1007/s00500-023-08404-5","name":"RETRACTED ARTICLE: A novel multi-layer\n         multi-spiking neural network for EEG signal classification using Mini Batch\n         SGD","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00500-023-08404-5","authors":["M. Ramesh","Swetha Revoori","Damodar Reddy Edla","K. V. D. Kiran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-24T10:02:41Z","doi":"10.1007/s00500-023-08404-5","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.3390/machines14060603","name":"A Spiking Neural Network with Attention and Residual Mechanisms for Compound Fault Detection","source":"crossref","abstract":"To address the challenges of severe multi-source coupling, easily masked spiking features, and limited selection of key responses in compound fault signals, this paper proposes a compound fault detection method based on a spiking attention residual network (SARN). This method uses the original time-domain vibration signal as input and constructs an end-to-end spiking neural network framework. A hierarchical spiking attention module is designed to enhance multi-level spiking features from both temporal response and feature channel perspectives, thereby highlighting fault-sensitive information and suppressing redundant responses. Furthermore, a cross-layer spiking residual gating mechanism is introduced to mitigate effective information attenuation in spiking neural networks and improve the representation capability of weak fault features. Simultaneously, a multi-label detection strategy is employed to jointly identify multiple fault attributes, thereby improving the recognition rate of coupled compound fault modes. Verification results show that the proposed method achieves high performance in compound fault detection tasks, and compared with other popular methods, it exhibits better feature separability and detection stability.","url":"https://doi.org/10.3390/machines14060603","authors":["Yulong Xing","Kun Li","Xiaoshuai Li","Congcong Liu","Qi Wang","Cong Peng","Zisheng Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-28T08:00:36Z","doi":"10.3390/machines14060603","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1016/j.bspc.2022.104197","name":"Deep Convolutional Spiking Neural Network optimized with Arithmetic optimization algorithm for lung disease detection using chest X-ray images","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.bspc.2022.104197","authors":["R. Rajagopal","R. Karthick","P. Meenalochini","T. Kalaichelvi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-21T21:24:52Z","doi":"10.1016/j.bspc.2022.104197","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.3389/fncir.2011.00008","name":"Correlations Decrease with Propagation of Spiking Activity in the Mouse Barrel Cortex","source":"crossref","abstract":"","url":"https://doi.org/10.3389/fncir.2011.00008","authors":["Gayathri Nattar Ranganathan","Helmut Joachim Koester"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-23T06:35:45Z","doi":"10.3389/fncir.2011.00008","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/ijcnn.2010.5596642","name":"Evolving Spiking Neural Networks for predicting transcription factor binding sites","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2010.5596642","authors":["Heike Sichtig","J. David Schaffer","Alberto Riva"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-10-19T18:58:15Z","doi":"10.1109/ijcnn.2010.5596642","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1016/j.neunet.2012.02.020","name":"Synchrony: A spiking-based mechanism for processing sensory stimuli","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2012.02.020","authors":["Cornelius Glackin","Liam Maguire","Liam McDaid","John Wade"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-02-14T21:17:15Z","doi":"10.1016/j.neunet.2012.02.020","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/mocast57943.2023.10176919","name":"Empirical Analysis of Full-System Approximation on Non-Spiking and Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mocast57943.2023.10176919","authors":["Amir Najafi","David Rotermund","Ardalan Najafi","Klaus R. Pawelzik","Alberto Garcia-Ortiz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-17T17:34:53Z","doi":"10.1109/mocast57943.2023.10176919","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.52202/079017-2943","name":"Rethinking the Membrane Dynamics and Optimization Objectives of Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.52202/079017-2943","authors":["Hangchi Shen","Qian Zheng","Huamin Wang","Gang Pan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-03T11:20:56Z","doi":"10.52202/079017-2943","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1016/j.neunet.2019.09.004","name":"Spiking Neural Networks and online learning: An overview and perspectives","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2019.09.004","authors":["Jesus L. Lobo","Javier Del Ser","Albert Bifet","Nikola Kasabov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-09-07T10:56:04Z","doi":"10.1016/j.neunet.2019.09.004","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1088/2634-4386/ae8627/v3/decision1","name":"Decision letter for \"Energy-aware spike budgeting for continual learning in spiking neural networks for neuromorphic vision\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2634-4386/ae8627/v3/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-03T23:27:36Z","doi":"10.1088/2634-4386/ae8627/v3/decision1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1016/j.neunet.2012.11.014","name":"Dynamic evolving spiking neural networks for on-line spatio- and spectro-temporal pattern recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2012.11.014","authors":["Nikola Kasabov","Kshitij Dhoble","Nuttapod Nuntalid","Giacomo Indiveri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-12-19T23:44:15Z","doi":"10.1016/j.neunet.2012.11.014","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1007/978-3-030-01418-6_30","name":"Spiking Neural Network Controllers Evolved for Animat Foraging Based on Temporal Pattern Recognition in the Presence of Noise on Input","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-01418-6_30","authors":["Chama Bensmail","Volker Steuber","Neil Davey","Borys Wróbel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-09-26T10:57:36Z","doi":"10.1007/978-3-030-01418-6_30","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1016/j.patcog.2023.110112","name":"Feature fusion method based on spiking neural convolutional network for edge detection","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.patcog.2023.110112","authors":["Ronghao Xian","Xin Xiong","Hong Peng","Jun Wang","Antonio Ramírez de Arellano Marrero","Qian Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-13T02:06:13Z","doi":"10.1016/j.patcog.2023.110112","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1007/s42044-025-00362-5","name":"Blockchain-enabled spiking neural network for optimal routing and location privacy protection in IoT healthcare networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s42044-025-00362-5","authors":["Arockiasamy Punitha","Madhu Kumar Vanteru","Kaliyaperumal Manojkumar","Tappeta Vinay Simha Reddy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-19T04:12:42Z","doi":"10.1007/s42044-025-00362-5","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/nics54270.2021.9701531","name":"In-bed posture classification using pressure sensor data and spiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nics54270.2021.9701531","authors":["Hoang Phuong Dam","Nguyen Duc Anh Pham","Hung Manh Pham","Ngoc Phu Doan","Duc Minh Nguyen","Huy Hoang Nguyen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-08T20:45:59Z","doi":"10.1109/nics54270.2021.9701531","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/bigdata66926.2025.11402313","name":"Multi-Timescale Spiking Neural Network with Dual-Hemispheric Fusion and Coupling for Brain Disorder Diagnosis","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bigdata66926.2025.11402313","authors":["Yingying Zhou","Shaolong Wei","Zhanmo Mi","Mingliang Wang","Weiping Ding","Jiashuang Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-06T20:57:57Z","doi":"10.1109/bigdata66926.2025.11402313","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1007/s00521-024-09667-1","name":"FPGA-based small-world spiking neural network with anti-interference ability under external noise","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-024-09667-1","authors":["Lei Guo","Yongkang Liu","Youxi Wu","Guizhi Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-22T20:29:32Z","doi":"10.1007/s00521-024-09667-1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1162/neco.2008.12-07-680","name":"A Generalized Linear Integrate-and-Fire Neural Model Produces Diverse Spiking Behaviors","source":"crossref","abstract":"For simulations of neural networks, there is a trade-off between the size of the network that can be simulated and the complexity of the model used for individual neurons. In this study, we describe a generalization of the leaky integrate-and-fire model that produces a wide variety of spiking behaviors while still being analytically solvable between firings. For different parameter values, the model produces spiking or bursting, tonic, phasic or adapting responses, depolarizing or hyperpolarizing after potentials and so forth. The model consists of a diagonalizable set of linear differential equations describing the time evolution of membrane potential, a variable threshold, and an arbitrary number of firing-induced currents. Each of these variables is modified by an update rule when the potential reaches threshold. The variables used are intuitive and have biological significance. The model's rich behavior does not come from the differential equations, which are linear, but rather from complex update rules. This single-neuron model can be implemented using algorithms similar to the standard integrate-and-fire model. It is a natural match with event-driven algorithms for which the firing times are obtained as a solution of a polynomial equation.","url":"https://doi.org/10.1162/neco.2008.12-07-680","authors":["Ştefan Mihalaş","Ernst Niebur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-10-17T15:27:25Z","doi":"10.1162/neco.2008.12-07-680","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/fpl53798.2021.00013","name":"DeepFire: Acceleration of Convolutional Spiking Neural Network on Modern Field Programmable Gate Arrays","source":"crossref","abstract":"","url":"https://doi.org/10.1109/fpl53798.2021.00013","authors":["Myat Thu Linn Aung","Chuping Qu","Liwei Yang","Tao Luo","Rick Siow Mong Goh","Weng-Fai Wong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-10-13T21:51:26Z","doi":"10.1109/fpl53798.2021.00013","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1016/j.isci.2025.112660","name":"Random heterogeneous spiking neural network for adversarial defense","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.isci.2025.112660","authors":["Jihang Wang","Dongcheng Zhao","Chengcheng Du","Xiang He","Qian Zhang","Yi Zeng"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.isci.2025.112660","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1016/j.chaos.2023.113821","name":"Specific neural coding of fMRI spiking neural network based on time coding","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.chaos.2023.113821","authors":["Lei Guo","Minxin Guo","Youxi Wu","Guizhi Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-25T15:10:31Z","doi":"10.1016/j.chaos.2023.113821","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1162/neco_a_00022","name":"Spiking Neural P Systems with Weights","source":"crossref","abstract":"A variant of spiking neural P systems with positive or negative weights on synapses is introduced, where the rules of a neuron fire when the potential of that neuron equals a given value. The involved values—weights, firing thresholds, potential consumed by each rule—can be real (computable) numbers, rational numbers, integers, and natural numbers. The power of the obtained systems is investigated. For instance, it is proved that integers (very restricted: 1, −1 for weights, 1 and 2 for firing thresholds, and as parameters in the rules) suffice for computing all Turing computable sets of numbers in both the generative and the accepting modes. When only natural numbers are used, a characterization of the family of semilinear sets of numbers is obtained. It is shown that spiking neural P systems with weights can efficiently solve computationally hard problems in a nondeterministic way. Some open problems and suggestions for further research are formulated.","url":"https://doi.org/10.1162/neco_a_00022","authors":["Jun Wang","Hendrik Jan Hoogeboom","Linqiang Pan","Gheorghe Păun","Mario J. Pérez-Jiménez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-07-07T18:48:38Z","doi":"10.1162/neco_a_00022","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1162/isal_a_00345","name":"Architectural Plasticity in Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1162/isal_a_00345","authors":["Katarzyna Kozdon","Peter J Bentley"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-07-14T16:30:30Z","doi":"10.1162/isal_a_00345","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/ijcnn.2019.8852473","name":"Speech Emotion Recognition With Early Visual Cross-modal Enhancement Using Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2019.8852473","authors":["Esma Mansouri-Benssassi","Juan Ye"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-10-01T03:44:32Z","doi":"10.1109/ijcnn.2019.8852473","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.3389/978-2-8325-7984-8","name":"Spiking Neural Networks: Enhancing Learning Through Neuro-Inspired Adaptations","source":"crossref","abstract":"","url":"https://doi.org/10.3389/978-2-8325-7984-8","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-23T04:07:10Z","doi":"10.3389/978-2-8325-7984-8","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1016/j.neunet.2023.05.026","name":"Auditory perception architecture with spiking neural network and implementation on FPGA","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2023.05.026","authors":["Bin Deng","Yanrong Fan","Jiang Wang","Shuangming Yang"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1016/j.neunet.2023.05.026","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1142/s0129065718500594","name":"An Attention-Based Spiking Neural Network for Unsupervised Spike-Sorting","source":"crossref","abstract":"Bio-inspired computing using artificial spiking neural networks promises performances outperforming currently available computational approaches. Yet, the number of applications of such networks remains limited due to the absence of generic training procedures for complex pattern recognition, which require the design of dedicated architectures for each situation. We developed a spike-timing-dependent plasticity (STDP) spiking neural network (SSN) to address spike-sorting, a central pattern recognition problem in neuroscience. This network is designed to process an extracellular neural signal in an online and unsupervised fashion. The signal stream is continuously fed to the network and processed through several layers to output spike trains matching the truth after a short learning period requiring only few data. The network features an attention mechanism to handle the scarcity of action potential occurrences in the signal, and a threshold adaptation mechanism to handle patterns with different sizes. This method outperforms two existing spike-sorting algorithms at low signal-to-noise ratio (SNR) and can be adapted to process several channels simultaneously in the case of tetrode recordings. Such attention-based STDP network applied to spike-sorting opens perspectives to embed neuromorphic processing of neural data in future brain implants.","url":"https://doi.org/10.1142/s0129065718500594","authors":["Marie Bernert","Blaise Yvert"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-12-27T09:48:00Z","doi":"10.1142/s0129065718500594","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/access.2021.3125685","name":"STT-BSNN: An In-Memory Deep Binary Spiking Neural Network Based on STT-MRAM","source":"crossref","abstract":"","url":"https://doi.org/10.1109/access.2021.3125685","authors":["Van-Tinh Nguyen","Quang-Kien Trinh","Renyuan Zhang","Yasuhiko Nakashima"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-08T22:35:42Z","doi":"10.1109/access.2021.3125685","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/fskd.2016.7603446","name":"A training algorithm for spike sequence in spiking neural networks — A discussion on growing network for stable training performance","source":"crossref","abstract":"","url":"https://doi.org/10.1109/fskd.2016.7603446","authors":["Toyota Takuya","Takase Haruhiko","Kawanaka Hiroharu","Tsuruoka Shinji"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-10-24T20:22:46Z","doi":"10.1109/fskd.2016.7603446","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/jetcas.2023.3327746","name":"Design Space Exploration of Sparsity-Aware Application-Specific Spiking Neural Network Accelerators","source":"crossref","abstract":"","url":"https://doi.org/10.1109/jetcas.2023.3327746","authors":["Ilkin Aliyev","Kama Svoboda","Tosiron Adegbija"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-30T18:44:07Z","doi":"10.1109/jetcas.2023.3327746","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/embc58623.2025.11251821","name":"MS-ResSNN: A Multi-Scale Residual Spiking Neural Network for Electromyography Pattern Recognition","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/embc58623.2025.11251821","authors":["Min Feng","Kejia Su","Bo Wan","Jiayang Huang"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1109/embc58623.2025.11251821","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/icassp43922.2022.9746157","name":"Motif-Topology and Reward-Learning Improved Spiking Neural Network for Efficient Multi-Sensory Integration","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icassp43922.2022.9746157","authors":["Shuncheng Jia","Ruichen Zuo","Tielin Zhang","Hongxing Liu","Bo Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-27T19:50:34Z","doi":"10.1109/icassp43922.2022.9746157","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1038/s41598-022-10991-6","name":"A spiking neural network model of the Superior Colliculus that is robust to changes in the spatial–temporal input","source":"crossref","abstract":"Abstract Previous studies have indicated that the location of a large neural population in the Superior Colliculus (SC) motor map specifies the amplitude and direction of the saccadic eye-movement vector, while the saccade trajectory and velocity profile are encoded by the population firing rates. We recently proposed a simple spiking neural network model of the SC motor map, based on linear summation of individual spike effects of each recruited neuron, which accounts for many of the observed properties of SC cells in relation to the ensuing eye movement. However, in the model, the cortical input was kept invariant across different saccades. Electrical microstimulation and reversible lesion studies have demonstrated that the saccade properties are quite robust against large changes in supra-threshold SC activation, but that saccade amplitude and peak eye-velocity systematically decrease at low input strengths. These features were not accounted for by the linear spike-vector summation model. Here we show that the model’s input projection strengths and intra-collicular lateral connections can be tuned to generate saccades and neural spiking patterns that closely follow the experimental results.","url":"https://doi.org/10.1038/s41598-022-10991-6","authors":["Arezoo Alizadeh","A. John Van Opstal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-28T06:04:20Z","doi":"10.1038/s41598-022-10991-6","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/tgrs.2026.3704163","name":"Energy-Efficient Spiking Neural Network With Dual-Teacher Knowledge Distillation for Planetary Rock Segmentation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tgrs.2026.3704163","authors":["Keke Zha","Jiabin Yuan","Yuqian Zhou","Ruoyu Zhao","Lili Fan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-17T19:38:44Z","doi":"10.1109/tgrs.2026.3704163","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1371/journal.pcbi.1006522","name":"Microstimulation in a spiking neural network model of the midbrain superior colliculus","source":"crossref","abstract":"","url":"https://doi.org/10.1371/journal.pcbi.1006522","authors":["Bahadir Kasap","A. John van Opstal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-04-12T13:39:26Z","doi":"10.1371/journal.pcbi.1006522","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1007/978-3-540-74205-0_4","name":"Edge Detection Based on Spiking Neural Network Model","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-540-74205-0_4","authors":["QingXiang Wu","Martin McGinnity","Liam Maguire","Ammar Belatreche","Brendan Glackin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-07-30T00:32:41Z","doi":"10.1007/978-3-540-74205-0_4","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.3389/fncom.2015.00019","name":"Phase diagram of spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.3389/fncom.2015.00019","authors":["Hamed Seyed-allaei"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-03-04T09:44:12Z","doi":"10.3389/fncom.2015.00019","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1007/s00521-021-05832-y","name":"Quantized STDP-based online-learning spiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-021-05832-y","authors":["S. G. Hu","G. C. Qiao","T. P. Chen","Q. Yu","Y. Liu","L. M. Rong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-06-11T15:03:22Z","doi":"10.1007/s00521-021-05832-y","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.3103/s0027134924702400","name":"Spiking Neural Network Actor–Critic Reinforcement Learning with Temporal Coding and Reward-Modulated Plasticity","source":"crossref","abstract":"","url":"https://doi.org/10.3103/s0027134924702400","authors":["D. S. Vlasov","R. B. Rybka","A. V. Serenko","A. G. Sboev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-22T05:53:06Z","doi":"10.3103/s0027134924702400","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/icca69928.2026.11618070","name":"SpikeAttn-YOLO: An Attention-Enhanced Spiking Neural Network for Energy-Efficient Object Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icca69928.2026.11618070","authors":["Jun Zhou","Ziliang Ren","Qieshi Zhang","Qosimov Abdunabi","Kholov Shavkat"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-04T19:14:48Z","doi":"10.1109/icca69928.2026.11618070","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/ijcnn55064.2022.9892644","name":"CARLsim 6: An Open Source Library for Large-Scale, Biologically Detailed Spiking Neural Network Simulation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn55064.2022.9892644","authors":["Lars Niedermeier","Kexin Chen","Jinwei Xing","Anup Das","Jeffrey Kopsick","Eric Scott","Nate Sutton","Killian Weber","Nikil Dutt","Jeffrey L. Krichmar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-30T19:56:04Z","doi":"10.1109/ijcnn55064.2022.9892644","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1142/s0129065709002002","name":"SPIKING NEURAL NETWORKS","source":"crossref","abstract":"Most current Artificial Neural Network (ANN) models are based on highly simplified brain dynamics. They have been used as powerful computational tools to solve complex pattern recognition, function estimation, and classification problems. ANNs have been evolving towards more powerful and more biologically realistic models. In the past decade, Spiking Neural Networks (SNNs) have been developed which comprise of spiking neurons. Information transfer in these neurons mimics the information transfer in biological neurons, i.e., via the precise timing of spikes or a sequence of spikes. To facilitate learning in such networks, new learning algorithms based on varying degrees of biological plausibility have also been developed recently. Addition of the temporal dimension for information encoding in SNNs yields new insight into the dynamics of the human brain and could result in compact representations of large neural networks. As such, SNNs have great potential for solving complicated time-dependent pattern recognition problems because of their inherent dynamic representation. This article presents a state-of-the-art review of the development of spiking neurons and SNNs, and provides insight into their evolution as the third generation neural networks.","url":"https://doi.org/10.1142/s0129065709002002","authors":["SAMANWOY GHOSH-DASTIDAR","HOJJAT ADELI"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-09-02T08:09:31Z","doi":"10.1142/s0129065709002002","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.4114/ia.v14i45.1075","name":"Sleep-Awake Switch with Spiking Neural P Systems","source":"crossref","abstract":"","url":"https://doi.org/10.4114/ia.v14i45.1075","authors":["Jack Mario Mingo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-02-14T15:37:36Z","doi":"10.4114/ia.v14i45.1075","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/ijcnn60899.2024.10650573","name":"Unveiling Robustness of Spiking Neural Networks against Data Poisoning Attacks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn60899.2024.10650573","authors":["Srishti Yadav","Anshul Pundhir","Balasubramanian Raman","Sanjeev Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T17:35:05Z","doi":"10.1109/ijcnn60899.2024.10650573","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/ijcnn.2016.7727303","name":"On the energy benefits of spiking deep neural networks: A case study","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2016.7727303","authors":["Bing Han","Abhronil Sengupta","Kaushik Roy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-11-08T16:15:56Z","doi":"10.1109/ijcnn.2016.7727303","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/ijcnn.2014.6889473","name":"A Spiking-based mechanism for self-organizing RBF neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2014.6889473","authors":["Honggui Han","Lidan Wang","Junfei Qiao","Gang Feng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-09-10T14:30:33Z","doi":"10.1109/ijcnn.2014.6889473","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1115/1.802566.paper32","name":"Brain Dynamics Modeling via Spiking Neuron Simulator","source":"crossref","abstract":"","url":"https://doi.org/10.1115/1.802566.paper32","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-06-25T16:01:43Z","doi":"10.1115/1.802566.paper32","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.29363/nanoge.matsusspring.2025.512","name":"CMOS-Memristive Spiking Neural Networks (SNN) computing architectures","source":"crossref","abstract":"","url":"https://doi.org/10.29363/nanoge.matsusspring.2025.512","authors":["María Teresa Serrano-gotarredona"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-01T13:55:38Z","doi":"10.29363/nanoge.matsusspring.2025.512","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1007/978-3-030-04239-4_61","name":"NVM Weight Variation Impact on Analog Spiking Neural Network Chip","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-04239-4_61","authors":["Akiyo Nomura","Megumi Ito","Atsuya Okazaki","Masatoshi Ishii","Sangbum Kim","Junka Okazawa","Kohji Hosokawa","Wilfried Haensch"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-11-17T06:55:08Z","doi":"10.1007/978-3-030-04239-4_61","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1007/s11063-012-9225-1","name":"Supervised Learning of Logical Operations in Layered Spiking Neural Networks with Spike Train Encoding","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11063-012-9225-1","authors":["André Grüning","Ioana Sporea"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-05-14T04:38:35Z","doi":"10.1007/s11063-012-9225-1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:22.344Z"},{"id":"doi:10.20944/preprints202408.0704.v1","name":"Noise as an Optimization Tool for Spiking Neural Networks","source":"preprints","abstract":"Standard ANNs lack flexibility when handling corrupted input due to their fixed structure. Spiking Neural Networks (SNNs) can utilize biological temporal coding features, such as noise-induced stochastic resonance and dynamical synapses to increase a model’s performance when its parameters are not optimized for a given input. Using the analog XOR task as a simplified Convolutional Neural Network analog, this paper demonstrates two key results: (1) SNNs solve the problem linearly inseparable in ANN with over 10% improvement in the optimal setting, and (2) in SNNs, the synaptic noise and dynamical synapses compensate for non-optimal parameters, achieving near-optimal results.","url":"https://doi.org/10.20944/preprints202408.0704.v1","authors":["Yana Garipova","Shogo Yonekura","Yasuo Kuniyoshi"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.20944/preprints202408.0704.v1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/ijcnn.2018.8489218","name":"Spiking Neural Networks Enable Two-Dimensional Neurons and Unsupervised Multi-Timescale Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2018.8489218","authors":["Timoleon Moraitis","Abu Sebastian","Evangelos Eleftheriou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-10-19T22:25:09Z","doi":"10.1109/ijcnn.2018.8489218","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1016/s0893-6080(01)00084-3","name":"Pattern separation and synchronization in spiking associative memories and visual areas","source":"crossref","abstract":"","url":"https://doi.org/10.1016/s0893-6080(01)00084-3","authors":["Andreas Knoblauch","Günther Palm"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-10-14T18:58:33Z","doi":"10.1016/s0893-6080(01)00084-3","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/csde53843.2021.9718472","name":"Studying Transfer of Learning using a Brain-Inspired Spiking Neural Network in the Context of Learning a New Programming Language","source":"crossref","abstract":"","url":"https://doi.org/10.1109/csde53843.2021.9718472","authors":["Mojgan Hafezi Fard","Krassie Petrova","Nikola Kasabov","Grace Y. Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-01T15:42:15Z","doi":"10.1109/csde53843.2021.9718472","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1016/j.asoc.2023.110099","name":"A shallow hybrid classical–quantum spiking feedforward neural network for noise-robust image classification","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2023.110099","authors":["Debanjan Konar","Aditya Das Sarma","Soham Bhandary","Siddhartha Bhattacharyya","Attila Cangi","Vaneet Aggarwal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-02-10T06:45:13Z","doi":"10.1016/j.asoc.2023.110099","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/icecs.2013.6815469","name":"Connecting spiking neurons to a spiking memristor network changes the memristor dynamics","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icecs.2013.6815469","authors":["Deborah Gater","Attya Iqbal","Jeffrey Davey","Ella Gale"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-05-16T23:05:07Z","doi":"10.1109/icecs.2013.6815469","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1007/978-981-10-6502-6_8","name":"The Enhancement of Evolving Spiking Neural Network with Dynamic Population Particle Swarm Optimization","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-10-6502-6_8","authors":["Nur Nadiah Md. Said","Haza Nuzly Abdull Hamed","Afnizanfaizal Abdullah"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-08-24T23:53:49Z","doi":"10.1007/978-981-10-6502-6_8","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/icce70609.2026.11658421","name":"Energy Minimization for UAV-Assisted Wireless Sensor Networks: A Novel Learning-based Framework of Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icce70609.2026.11658421","authors":["Thanh-Can Le","Hieu V. Nguyen","Mai T. P. Le","Vien Nguyen-Duy-Nhat"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-24T19:21:30Z","doi":"10.1109/icce70609.2026.11658421","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/tai.2024.3374268","name":"Temporal Knowledge Sharing Enable Spiking Neural Network Learning From Past and Future","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tai.2024.3374268","authors":["Yiting Dong","Dongcheng Zhao","Yi Zeng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-07T14:31:20Z","doi":"10.1109/tai.2024.3374268","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.3390/bdcc9070173","name":"Modeling the Effect of Prior Knowledge on Memory Efficiency for the Study of Transfer of Learning: A Spiking Neural Network Approach","source":"crossref","abstract":"The transfer of learning (TL) is the process of applying knowledge and skills learned in one context to a new and different context. Efficient use of memory is essential in achieving successful TL and good learning outcomes. This study uses a cognitive computing approach to identify and explore brain activity patterns related to memory efficiency in the context of learning a new programming language. This study hypothesizes that prior programming knowledge reduces cognitive load, leading to improved memory efficiency. Spatio-temporal brain data (STBD) were collected from a sample of participants (n = 26) using an electroencephalogram (EEG) device and analyzed by applying a spiking neural network (SNN) approach and the SNN-based NeuCube architecture. The findings revealed the neural patterns demonstrating the effect of prior knowledge on memory efficiency. They showed that programming learning outcomes were aligned with specific theta and alpha waveband spike activities concerning prior knowledge and cognitive load, indicating that cognitive load was a feasible metric for measuring memory efficiency. Building on these findings, this study proposes that the methodology developed for examining the relationship between prior knowledge and TL in the context of learning a programming language can be extended to other educational domains.","url":"https://doi.org/10.3390/bdcc9070173","authors":["Mojgan Hafezi Fard","Krassie Petrova","Nikola Kirilov Kasabov","Grace Y. Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-30T10:03:48Z","doi":"10.3390/bdcc9070173","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/icima64861.2025.11073910","name":"Optimized Energy-Efficient Speed Control in Lightweight Electric Vehicle using Dynamic Spiking Graph Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icima64861.2025.11073910","authors":["M. Sivaramkrishnan","Bharani B R","D. Kavitha","G. Emayavaramban","Thaer Ahmad Abu-Saleem","Rajkumar Chadge"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-15T17:40:24Z","doi":"10.1109/icima64861.2025.11073910","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/icecs49266.2020.9294873","name":"Spiking Neural Network Based Low-Power Radioisotope Identification using FPGA","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icecs49266.2020.9294873","authors":["Xiaoyu Huang","Edward Jones","Siru Zhang","Shouyu Xie","Steve Furber","Yannis Goulermas","Edward Marsden","Ian Baistow","Srinjoy Mitra","Alister Hamilton"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-28T15:52:44Z","doi":"10.1109/icecs49266.2020.9294873","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1088/1741-2552/aa98e9","name":"Real-time cerebellar neuroprosthetic system based on a spiking neural network model of motor learning","source":"crossref","abstract":"Abstract Objective . Damage to the brain, as a result of various medical conditions, impacts the everyday life of patients and there is still no complete cure to neurological disorders. Neuroprostheses that can functionally replace the damaged neural circuit have recently emerged as a possible solution to these problems. Here we describe the development of a real-time cerebellar neuroprosthetic system to substitute neural function in cerebellar circuitry for learning delay eyeblink conditioning (DEC). Approach . The system was empowered by a biologically realistic spiking neural network (SNN) model of the cerebellar neural circuit, which considers the neuronal population and anatomical connectivity of the network. The model simulated synaptic plasticity critical for learning DEC. This SNN model was carefully implemented on a field programmable gate array (FPGA) platform for real-time simulation. This hardware system was interfaced in in vivo experiments with anesthetized rats and it used neural spikes recorded online from the animal to learn and trigger conditioned eyeblink in the animal during training. Main results . This rat-FPGA hybrid system was able to process neuronal spikes in real-time with an embedded cerebellum model of ~10 000 neurons and reproduce learning of DEC with different inter-stimulus intervals. Our results validated that the system performance is physiologically relevant at both the neural (firing pattern) and behavioral (eyeblink pattern) levels. Significance . This integrated system provides the sufficient computation power for mimicking the cerebellar circuit in real-time. The system interacts with the biological system naturally at the spike level and can be generalized for including other neural components (neuron types and plasticity) and neural functions for potential neuroprosthetic applications.","url":"https://doi.org/10.1088/1741-2552/aa98e9","authors":["Tao Xu","Na Xiao","Xiaolong Zhai","Pak Kwan Chan","Chung Tin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-11-08T06:15:13Z","doi":"10.1088/1741-2552/aa98e9","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/jsen.2022.3189679","name":"A Bio-Inspired Hierarchical Spiking Neural Network With Reward-Modulated STDP Learning Rule for AER Object Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/jsen.2022.3189679","authors":["Qian Zhou","Xiaohu Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-07-15T19:34:50Z","doi":"10.1109/jsen.2022.3189679","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/access.2023.3267856","name":"Blended Glial Cell’s Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/access.2023.3267856","authors":["Liying Tao","Pan Li","Meihua Meng","Zonglin Yang","Xiaozhuang Liu","Jinhua Hu","Ji Dong","Shushan Qiao","Tianchun Ye","Delong Shang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-18T17:39:34Z","doi":"10.1109/access.2023.3267856","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.7554/elife.90597.3.sa3","name":"Author Response: Hippocampome.org 2.0 is a knowledge base enabling data-driven spiking neural network simulations of rodent hippocampal circuits","source":"crossref","abstract":"","url":"https://doi.org/10.7554/elife.90597.3.sa3","authors":["Diek W Wheeler","Jeffrey D Kopsick","Nate Sutton","Carolina Tecuatl","Alexander O Komendantov","Kasturi Nadella","Giorgio A Ascoli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-12T12:16:15Z","doi":"10.7554/elife.90597.3.sa3","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.23919/date58400.2024.10546679","name":"TT-SNN: Tensor Train Decomposition for Efficient Spiking Neural Network Training","source":"crossref","abstract":"","url":"https://doi.org/10.23919/date58400.2024.10546679","authors":["Donghyun Lee","Ruokai Yin","Youngeun Kim","Abhishek Moitra","Yuhang Li","Priyadarshini Panda"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-14T17:28:02Z","doi":"10.23919/date58400.2024.10546679","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:22.344Z"},{"id":"doi:10.1109/icetems66917.2026.11469473","name":"Spiking Neural Network Models for Real-Time Sensory-Motor Integration in Bio-Inspisred Robotic Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icetems66917.2026.11469473","authors":["Senthil Kumar S","Barath G","Maduvanthi S","Thulasi P","Ramesh R","Kavitha K"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-15T19:22:44Z","doi":"10.1109/icetems66917.2026.11469473","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:22.344Z"},{"id":"doi:10.1109/cvpr52734.2025.00822","name":"ViStream: Improving Computation Efficiency of Visual Streaming Perception via Law-of-Charge-Conservation Inspired Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cvpr52734.2025.00822","authors":["Kang You","Ziling Wei","Jing Yan","Boning Zhang","Qinghai Guo","Yaoyu Zhang","Zhezhi He"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-13T17:26:42Z","doi":"10.1109/cvpr52734.2025.00822","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.18653/v1/2024.acl-long.429","name":"SpikeVoice: High-Quality Text-to-Speech Via Efficient Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.18653/v1/2024.acl-long.429","authors":["Kexin Wang","Jiahong Zhang","Yong Ren","Man Yao","Di Shang","Bo Xu","Guoqi Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-20T19:33:08Z","doi":"10.18653/v1/2024.acl-long.429","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/iros51168.2021.9636506","name":"SpikeMS: Deep Spiking Neural Network for Motion Segmentation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iros51168.2021.9636506","authors":["Chethan M. Parameshwara","Simin Li","Cornelia Fermuller","Nitin J. Sanket","Matthew S. Evanusa","Yiannis Aloimonos"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-16T20:45:38Z","doi":"10.1109/iros51168.2021.9636506","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.20944/preprints202605.2023.v1","name":"Convolutive Kernel-Guarded Spiking Neural P Systems for Local Feature Computation","source":"crossref","abstract":"Spiking Neural P systems provide a rule-based model of distributed computation inspired by membrane computing, while kernel P systems use guarded transformations and structured control of rule applicability. This paper introduces Convolutive Kernel-Guarded Spiking Neural P systems (CKSNP systems), a formal and trainable framework in which spike-rule applicability may depend on local kernel responses computed over ordered neighborhoods of spike multiplicities. The proposed model provides a general mechanism for local feature computation, combining explicit operational semantics with kernel-based predicates that can be fixed, selected, or embedded in trainable realizations. We define the syntax and transition semantics of the model, relate the construction to delay-free extended Spiking Neural P systems and kernel P systems under stated assumptions, and present a reproducible instantiation for electrocardiographic beat classification under a patient-independent protocol. The empirical study illustrates how CK-SN P local responses can be combined with RR, Gaussian, and Fourier descriptors and evaluated with classical and neural classifiers. Overall, the study clarifies both the formal role of guarded local computation and its practical use as an interpretable feature-generation mechanism.","url":"https://doi.org/10.20944/preprints202605.2023.v1","authors":["Doru Constantin","Costel Bălcău"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-01T07:23:50Z","doi":"10.20944/preprints202605.2023.v1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1016/j.neunet.2009.04.003","name":"A new supervised learning algorithm for multiple spiking neural networks with application in epilepsy and seizure detection","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2009.04.003","authors":["Samanwoy Ghosh-Dastidar","Hojjat Adeli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-04-23T04:43:07Z","doi":"10.1016/j.neunet.2009.04.003","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1016/j.neunet.2025.108026","name":"Raw event-based adversarial attacks for Spiking Neural Networks with configurable latencies","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.108026","authors":["Xiao Du","Wanli Shi","Xiaohan Zhao","Yang Cao","Bin Gu","Tieru Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-23T15:01:53Z","doi":"10.1016/j.neunet.2025.108026","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.52202/085713-1577","name":"Spik-NeRF: Spiking Neural Networks for Neural Radiance Fields","source":"crossref","abstract":"","url":"https://doi.org/10.52202/085713-1577","authors":["Gang Wan","Qinlong Lan","Zihan Li","Huimin Wang","Wu Yitian","wang zhen","Wanhua Li","Yufei Guo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-06T14:44:29Z","doi":"10.52202/085713-1577","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/tbcas.2019.2925454","name":"Discrimination of EMG Signals Using a Neuromorphic Implementation of a Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tbcas.2019.2925454","authors":["Elisa Donati","Melika Payvand","Nicoletta Risi","Renate Krause","Giacomo Indiveri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-06-27T15:53:45Z","doi":"10.1109/tbcas.2019.2925454","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.37394/23208.2025.22.16","name":"A Spiking Neural Network Approach for Classifying Hand Movement and Relaxation from EEG Signal using Time Domain Features","source":"crossref","abstract":"High-performance prosthetic and exoskeleton systems based on EEG signals can improve the quality of life of hand-impaired people. Effective controlling of these assistive devices requires accurate EEG signal classification. Although there have been advancements in the assistive Brain-Computer Interface (BCI) systems, still classifying the EEG signals with high accuracy is a great challenge. The objective of this research is to investigate the accuracy of the EEG signal classification of the Spiking Neural Network (SNN) classifier for factual and exact control of prosthetic and exoskeleton systems for individuals with hand impairment. The EEG dataset has been taken from the BNCI Horizon 2020 website, which is for hand movement-relax events of a patient with high spinal cord injury (SCI) to operate a neuro-prosthetic device attached to the paralyzed right upper limb. The fusion of Dispersion Entropy (DE), Fuzzy Entropy (FE), and Fluctuation based Dispersion Entropy (FDE) with mean and skewness features are extracted from the Motor Imagery (MI) EEG signals and applied to the Spiking Neural Network (SNN) classifier. To compare the performance of this algorithm, these same features have been used in Convolutional Neural Network (CNN), Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Logistic Regression (LR) classifiers. It has been found that SNN has given the highest classification accuracy of 80% with a precision of 80.95%, recall of 77.28%, and F1-score of 79.07%. This indicates that SNN with these five features has greater potential in BCI system-based applications.","url":"https://doi.org/10.37394/23208.2025.22.16","authors":["Mohammad Rubaiyat Tanvir Hossain","Md. Shafiul Islam Joy","Mohammed Hasibul Hasan Chowdhury"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-21T08:07:09Z","doi":"10.37394/23208.2025.22.16","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/cimca.2005.1631415","name":"Self-Organization of Spiking Neural Network Generating Autonomous Behavior in a Real Mobile Robot","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cimca.2005.1631415","authors":["F. Alnajjar","K. Murase"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-05-25T16:26:01Z","doi":"10.1109/cimca.2005.1631415","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1016/j.neunet.2026.109428","name":"ReBo-SNN: Boosted spiking neural network with retina mechanism for efficient haze removal.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.109428","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.109428","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.465Z"},{"id":"doi:10.1016/j.neunet.2026.108834","name":"A complex-valued widening spiking neural network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.108834","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.108834","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.3389/fnins.2026.1919565","name":"A hardware-grounded energy taxonomy for comparing deep and Spiking Neural Network inference on edge platforms.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2026.1919565","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnins.2026.1919565","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1007/s11571-026-10489-1","name":"Synaptic neurotransmitter concentration modulation during learning in bio-inspired spiking neural network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-026-10489-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s11571-026-10489-1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.465Z"},{"id":"doi:10.3390/s26144514","name":"A Lightweight Keyword Spotting Method Using a Convolutional Spiking Neural Network with Learnable Synaptic Delays.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s26144514","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/s26144514","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.465Z"},{"id":"doi:10.1038/s41467-026-74243-1","name":"Spiking neural network decoders of finger forces from high-density intramuscular microelectrode arrays.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-74243-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-74243-1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.21203/rs.3.rs-10614849/v1","name":"Brain-inspired Spiking Neural Network Frameworks for Multimodal Spatiotemporal Brain Data Integration: A Case Study on EEG-fMRI Data","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-10614849/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-10614849/v1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.3390/s26123723","name":"A Cascaded Quantized Spiking Neural Network for Real-Time ECG Arrhythmia Detection on Edge Hardware.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s26123723","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/s26123723","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41598-026-52643-z","name":"Memristive nano-neuromorphic spiking neural network with self-adaptive continual and predictive learning for edge gesture recognition.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-52643-z","authors":["Raju Vidap","Ranjith Kumar Nadialli","Vinod Kumar Teriveedhi","K. Suresh Babu","Suresh K. Pulluru","Aele Manohar","Suresh Thondapu"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-52643-z","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.3389/fnins.2026.1875437","name":"A configurable streaming spiking neural network accelerator with decoupled pixel-level and output-channel parallelism for automatic modulation classification.","source":"europepmc","abstract":"Streaming spiking neural network (SNN) accelerators are widely adopted on edge platforms for their deterministic, low-latency inference. Realizing their full efficiency, however, requires three properties to hold simultaneously: a router-free streaming dataflow, joint exploitation of temporal and spatial sparsity within that dataflow, and configurable parallelism that can adapt to heterogeneous layers and hardware budgets. Existing streaming SNN accelerators typically achieve at most two of these properties: pixel-level and output-channel parallelism are bound to a single fixed operating point, limiting efficient mapping across heterogeneous layers in automatic modulation classification (AMC) workloads. This paper presents a configurable streaming SNN accelerator that satisfies all three properties by explicitly decoupling pixel-level multiple matrix–vector multiplication (MMV) parallelism from output-channel parallelism. The decoupling is realized within a weight-priority gated one-to-all product (GOAP) dataflow by deterministic offline scheduling, preserving router-free streaming execution while exploiting temporal and spatial sparsity. The proposed architecture is implemented on a Xilinx Virtex-7 field-programmable gate array (FPGA) and evaluated using the RadioML 2016 dataset and a compatible subset of RadioML 2018 under multiple sparsity and quantization settings. Experimental results show that, under comparable end-to-end latency, configurable parallelism enables effective layer-wise latency balancing and substantial hardware-resource savings while sustaining high throughput and classification accuracy. More broadly, the same accelerator description can be retargeted across operating points spanning more than an order of magnitude in hardware cost, providing a key enabler for deploying streaming SNNs at scale across diverse edge hardware platforms.","url":"https://doi.org/10.3389/fnins.2026.1875437","authors":["Kuilian Yang","Ahmed M. Eltawil","Khaled Nabil Salama"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnins.2026.1875437","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.465Z"},{"id":"doi:10.64898/2026.01.01.697291","name":"Versatile Learning without Synaptic Plasticity in a Spiking Neural Network","source":"europepmc","abstract":"","url":"https://doi.org/10.64898/2026.01.01.697291","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.01.01.697291","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.21203/rs.3.rs-10162479/v1","name":"Near-Sensor Damage Localization in Multi-Story Buildings with Level-Crossing Spike Encoding and a Compact Spiking Neural Network","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-10162479/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-10162479/v1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.3390/s26154695","name":"DCPA-SNN, Direct-Coding-Physics-Aware Spiking Neural Network: A Framework for Wearable ECG Denoising Under Dynamic-Noise Conditions.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s26154695","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/s26154695","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.465Z"},{"id":"doi:10.1109/tbcas.2026.3711044","name":"An Edge On-Chip-Learning Convolutional Spiking Neural Network Processor Based on Error Backpropagation via Spatiotemporal Nodes of Spike Events.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tbcas.2026.3711044","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1109/tbcas.2026.3711044","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.21203/rs.3.rs-10012975/v1","name":"HERO-SNN: A Homeostatic Eligibility-based Reward- Optimised Spiking Neural Network for Spatiotemporal Brain Representation: An EEG Case Study","source":"europepmc","abstract":"Abstract We propose a new framework for Homeostatic Eligibility-based Reward-Optimised Spiking Neural Network (HERO-SNN) that enables spiking neural networks (SNNs) to achieve an optimal refinement in internal spatiotemporal representations based on task performance. Spatiotemporal brain data exhibit complex temporal dynamics and distributed spatial activity across brain regions, which makes them challenging for modelling. Although SNNs provide a biologically plausible way to represent such dynamics through spike-based processing, popular unsupervised learning mechanisms, such as Spike-Timing-Dependent Plasticity (STDP), remain independent of the task objective. So, the internal representations formed through STDP do not necessarily support accurate decision-making, particularly for high-dimensional brain signals. To address this limitation, HERO-SNN introduces a refinement mechanism that integrates task-related feedback to guide synaptic adaptation while preserving the local spike-based learning. Implemented within the NeuCube brain-inspired SNN, this novel model combines local eligibility pathways that identify synaptic routes involved during learning, a global reward optimisation signal derived from classifier confidence to refine task-relevant pathways, and homeostatic regulation of neuronal excitability to maintain stable spiking activity. We evaluate the proposed framework using electroencephalography (EEG) data collected during a Havening-based task, in which participants underwent either a nurturing touch protocol (H+) or an identical protocol delivered without touch (H−). The results showed an improvement of 11% in classification accuracy compared with standard STDP learning without task-aware refinement and outperformed state-of-the-art machine learning models, including CNN and LSTM. These findings demonstrate that incorporating task feedback into the adaptation of internal spatiotemporal neural representations can improve both classification performance and model interpretability.","url":"https://doi.org/10.21203/rs.3.rs-10012975/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-10012975/v1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1111/nyas.70204","name":"Feature Overlapping: Temporal Differential Decoupling for Efficient Spiking Neural Network Training.","source":"europepmc","abstract":"","url":"https://doi.org/10.1111/nyas.70204","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1111/nyas.70204","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1007/s00422-025-01032-2","name":"A spiking neural network model for fractional proprioceptive encoding of limb posture and movement in insects.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s00422-025-01032-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s00422-025-01032-2","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3390/biomimetics11070481","name":"Task-State fMRI-Derived Whole-Brain Functional Topology-Constrained Spiking Neural Network with an Embedded Auditory Core Circuit for Speech Recognition.","source":"europepmc","abstract":"The topology of spiking neural networks (SNNs) plays an important role in determining their dynamic representation ability, recognition performance, and biological interpretability in speech recognition. However, most existing SNN reservoirs are constructed using random, regular, or manually designed connectivity patterns, which may not reflect the functional organization of the human brain during speech perception. In this study, we propose a task-state fMRI-constrained SNN framework for speech recognition. Human fMRI data acquired during naturalistic English audiobook listening are used offline to derive a task-state whole-brain functional topology, which serves as a biologically inspired structural prior for the recurrent connectivity of the SNN reservoir. Because the fMRI and downstream isolated-digit recognition tasks use different speech paradigms, this topology is interpreted as a general speech-listening prior rather than a digit-specific neural representation. The Schaefer-400 cortical parcellation is used to define 400 whole-brain functional nodes, all of which are retained to preserve distributed cortical interactions during speech listening. Within this topology, 7 SomMotB_Aud parcels are identified as auditory core nodes and analyzed as an embedded auditory circuit. Compared with resting-state fMRI, task-state fMRI shows enhanced functional connectivity among these auditory nodes, indicating task-related auditory-circuit activation. The resulting 400-node task-state topology is mapped onto the recurrent connectivity of the SNN reservoir. This mapping is regarded as a topology-constrained computational abstraction rather than a direct model of biological information transmission. During recognition, speech spike trains are the only external input, while fMRI data are used only for offline topology construction. Experimental comparisons with baseline SNNs show that the proposed topology improves recognition performance and biological interpretability. Resting-state topology comparison, auditory-core contribution analysis, threshold-sensitivity analysis, and statistical testing are further used to evaluate robustness. These findings suggest that speech-evoked whole-brain functional organization may provide an effective topology prior for biologically inspired speech recognition models.","url":"https://doi.org/10.3390/biomimetics11070481","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/biomimetics11070481","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.465Z"},{"id":"doi:10.1109/tbme.2026.3653109","name":"Multimodal Spiking Neural Network With Generalized Distributive Law for Biosignal and Sensory Fusion.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tbme.2026.3653109","authors":["Zenan Huang","Bingrui Guo","Hailing Xu","Haojie Ruan","Donghui Guo"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1109/tbme.2026.3653109","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.3389/fnins.2025.1716204","name":"A hybrid Spiking Neural Network-Transformer architecture for motor imagery and sleep apnea detection.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2025.1716204","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fnins.2025.1716204","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3390/biomimetics11010047","name":"Bio-Inspired Neural Network Dynamics-Aware Reinforcement Learning for Spiking Neural Network.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics11010047","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/biomimetics11010047","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41598-026-43529-1","name":"A spiking neural network inspired by neuroscience and psychology for Western mode- and key-conditioned music learning and composition.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-43529-1","authors":["Qian Liang","Yi Zeng","Menghaoran Tang"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-43529-1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1016/j.neunet.2025.108239","name":"BioMotion-SNN: Spiking neural network modeling for visual motion processing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.108239","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2025.108239","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1007/s12021-025-09754-1","name":"Impact of Neuron Models on Spiking Neural Network Performance: A Complexity-based Classification Approach.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s12021-025-09754-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s12021-025-09754-1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3390/s26092859","name":"UDC-SNN: An Uncertainty-Aware Dynamic Cascading Framework with Spiking Neural Network for Balancing Performance and Energy in Multimodal Emotion Recognition.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s26092859","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/s26092859","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1016/j.neunet.2025.108190","name":"Spatially-enhanced Spiking neural network for efficient point cloud analysis.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.108190","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2025.108190","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1007/s11571-025-10368-1","name":"Bio-inspired spiking neural network for modeling and optimizing adaptive vertigo therapy.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-025-10368-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s11571-025-10368-1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1142/s0129065725500637","name":"Multi-layer Feature Cascade Fusion Spiking Neural Network for Object Detection.","source":"europepmc","abstract":"","url":"https://doi.org/10.1142/s0129065725500637","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1142/s0129065725500637","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1364/ao.574743","name":"Pattern classification based on a multi-spike learning algorithm in a photonic spiking neural network with VCSEL-SA.","source":"europepmc","abstract":"","url":"https://doi.org/10.1364/ao.574743","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1364/ao.574743","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1016/j.neunet.2026.108829","name":"A bio-inspired spiking neural network with adaptive spatiotemporal filtering and depth-modulated synaptic plasticity for robust collision detection.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.108829","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.108829","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1371/journal.pcbi.1013866","name":"Biologically-constrained spiking neural network for neuromodulation in locomotor recovery after spinal cord injury.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pcbi.1013866","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pcbi.1013866","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1142/s0129065725920017","name":"ERRATUM - Multi-Layer Feature Cascade Fusion Spiking Neural Network for Object Detection.","source":"europepmc","abstract":"","url":"https://doi.org/10.1142/s0129065725920017","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1142/s0129065725920017","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.64898/2025.12.03.692094","name":"From Skin to Cortex: End-to-End Spiking Neural Network Simulation of Tactile Information Flow","source":"europepmc","abstract":"","url":"https://doi.org/10.64898/2025.12.03.692094","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.64898/2025.12.03.692094","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1007/s00422-025-01030-4","name":"Task success in trained spiking neural network models coincides with emergence of cross-stimulus-modulated inhibition.","source":"europepmc","abstract":"Abstract The neocortex is composed of spiking neurons interconnected in a sparse, recurrent network. Spiking activity within these networks underlies the computations that transform sensory inputs into appropriate behavioral responses. In this study, we train recurrent spiking neural network (SNN) models constrained by neocortical connectivity statistics and investigate the architectural changes that enable task-relevant, spike-based computations. We employ a binary state change detection task—an experimental paradigm used in animal behavioral studies. Our SNNs consist of interconnected excitatory and inhibitory units with connection probabilities and strengths modeled after the mouse neocortex and maintained throughout training and evaluation. Following training, we find that SNNs selectively modulate firing rates based on the binary input state, and that excitatory and inhibitory connectivity within and between input and recurrent layers adjusts accordingly. Notably, inhibitory neurons in the recurrent layer that positively modulate firing rates in response to one input state strengthen their connections to recurrent units with the opposite modulation. This push-pull connectivity—where excitation and inhibition are dynamically balanced in an opponent fashion—emerges as a key computational strategy and is reminiscent of connectivity observed in primary visual cortex. Using a one-hot output encoding yields identical firing rates to both input states, yet the push-pull inhibitory motif still arises. Importantly, this motif fails to emerge when Dale’s principle is not enforced during training, and task performance also declines.Furthermore, disrupting spike timing by a few milliseconds significantly impairs task performance, highlighting the importance of precise spike time coordination for computation in sparse networks like neocortex. The emergence of push-pull inhibition through task training in spiking models underscores the crucial role of interneurons and structured inhibition in shaping neural dynamics and spike-based information processing.","url":"https://doi.org/10.1007/s00422-025-01030-4","authors":["Yuqing Zhu","Chadbourne M. B. Smith","Tarek Jabri","Mufeng Tang","Franz Scherr","Jason N. MacLean"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s00422-025-01030-4","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3390/biomimetics11030208","name":"eXCube2: Explainable Brain-Inspired Spiking Neural Network Framework for Emotion Recognition from Audio, Visual and Multimodal Audio-Visual Data.","source":"europepmc","abstract":"This paper introduces a biomimetic framework and novel brain-inspired AI (BIAI) models based on spiking neural networks (SNNs) for emotional state recognition from audio (speech), visual (face), and integrated multimodal audio–visual data. The developed framework, named eXCube2, uses a three-dimensional SNN architecture NeuCube that is spatially structured according to a human brain template. The BIAI models developed in eXCube2 are trainable on spatio- and spectro-temporal data using brain-inspired learning rules. Such models are explainable in terms of revealing patterns in data and are adaptable to new data. The eXCube2 models are implemented as software systems and tested on speech and video data of subjects expressing emotional states. The use of a brain template for the SNN structure enables brain-inspired tonotopic and stereo mapping of audio inputs, topographic mapping of visual data, and the combined use of both modalities. This novel approach brings AI-based emotional state recognition closer to human perception, provides a better explainability and adaptability than existing AI systems. It also results in a higher or competitive accuracy, even though this was not the main goal here. This is demonstrated through experiments on benchmark datasets, achieving classification accuracy above 80% on single-modality data and 88.9% when multimodal audio–visual data are used, and a “don’t know” output is introduced. The paper further discusses possible applications of the proposed eXCube2 framework to other audio, visual, and audio–visual data for solving challenging problems, such as recognizing emotional states of people from different origins; brain state diagnosis (e.g., Parkinson’s disease, Alzheimer’s disease, ADHD, dementia); measuring response to treatment over time; evaluating satisfaction responses from online clients; cognitive robotics; human–robot interaction; chatbots; and interactive computer games. The SNN-based implementation of BIAI also enables the use of neuromorphic chips and platforms, leading to reduced power consumption, smaller device size, higher performance accuracy, and improved adaptability and explainability. This research shows a step toward building brain-inspired AI systems.","url":"https://doi.org/10.3390/biomimetics11030208","authors":["N. K. Kasabov","A. Yang","Z. Wang","I. Abouhassan","A. Kassabova","T. Lappas"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/biomimetics11030208","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1109/tbcas.2025.3601403","name":"A Sparse-Integrated Filtering Residual Spiking Neural Network for High-Accuracy Spike Sorting and Co-Optimization on Memristor Platforms.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tbcas.2025.3601403","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1109/tbcas.2025.3601403","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1177/20552076261466149","name":"NeurALLNet: An attention-based spiking neural network for energy-efficient multi-class classification of acute lymphoblastic leukemia.","source":"europepmc","abstract":"Objectives The classification of Acute Lymphoblastic Leukemia (ALL) from peripheral blood smear images using Convolutional Neural Networks (CNNs) has achieved expert-level accuracy. However, the computational and memory requirements of CNNs pose a barrier to their deployment in resource-constrained clinical settings and low-income countries. To bridge this gap, we propose NeurALLNet, a memory-efficient convolutional spiking neural network (SNN) augmented with Squeeze-and-Excitation channel attention for the multi-class classification of ALL subtypes. Methods NeurALLNet leverages sparse, event-driven temporal computation with an ultra-compact architecture of approximately 0.3M trainable parameters. The model was trained and evaluated on a primary dataset of ALL peripheral blood smear images, and its clinical generalizability was rigorously validated on an unseen external cohort of 3,242 images without retraining. We conducted hardware profiling on CPU and GPU platforms, alongside ablation studies and Grad-CAM visual explanations, to evaluate deployment viability and interpretability. Results NeurALLNet achieved a test accuracy of 98.16% on the primary dataset, with a bootstrapped 95% Confidence Interval (CI) of [0.9663, 0.9939]. On the external validation cohort, it yielded an accuracy of 96.02%, with a robust 95% CI of [0.9534, 0.9667]. The architecture requires a memory footprint of 1.35 MB, achieving single-image inference latencies of 454.67 ms on a standard CPU and 11.24 ms on a GPU. Ablation studies confirmed that the attention mechanism is critical to the network’s discriminative power, and Grad-CAM visualizations verified that predictions are grounded in clinically relevant morphological features. Conclusion Compared to recent state-of-the-art ensemble and hybrid CNNs that require millions of parameters, NeurALLNet delivers competitive diagnostic accuracy while reducing the computational footprint by orders of magnitude. By providing this precision within a 1.35 MB envelope, NeurALLNet offers a scalable, energy-efficient digital health intervention suitable for portable Lab-on-a-Chip devices and point-of-care diagnostics worldwide.","url":"https://doi.org/10.1177/20552076261466149","authors":["Md Rafsan Hassan","Rejaul Islam Shanto","Umar Hasan","Sifat Momen"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1177/20552076261466149","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41467-025-64231-2","name":"A frugal Spiking Neural Network for unsupervised multivariate temporal pattern classification and multichannel spike sorting.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-64231-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-64231-2","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1109/jbhi.2025.3589392","name":"DAFF-SNN: Dual Attention-Driven and Feature Fusion-Based Spiking Neural Network for Epilepsy Detection Based on Electroencephalogram.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/jbhi.2025.3589392","authors":["Tao Zhang","Lanqi He","Dingguo Zhang","Mingyang Li","Zhiyong Chang"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025-07-15T17:43:10Z","doi":"10.1109/jbhi.2025.3589392","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.3390/biomimetics10080514","name":"Auto Deep Spiking Neural Network Design Based on an Evolutionary Membrane Algorithm.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics10080514","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/biomimetics10080514","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1038/s41598-025-96223-z","name":"Heterogeneous quantization regularizes spiking neural network activity.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-96223-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-96223-z","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1016/j.neunet.2025.107741","name":"A lightweight spiking neural network for EEG-based motor imagery classification.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107741","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.neunet.2025.107741","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.3390/biomimetics10100697","name":"SpiKon-E: Hybrid Soft Artificial Muscle Control Using Hardware Spiking Neural Network.","source":"europepmc","abstract":"Artificial muscles play a key role in the future of humanoid robotics and medical devices, with research on wire-driven joints leading the field. While electric servo motors were once at the forefront, the focus has shifted toward materials that react to changes in the environment (smart materials), including pneumatic silicone actuators and temperature-reactive metallic alloys, aiming to replicate human muscle actuation for improved performance. Initially designed for rigid actuators, control strategies were adapted to address the unique dynamics of artificial muscles. Although current controllers offer satisfactory performance, further optimization is necessary to mimic natural muscle control more rigorously. This study details the design and implementation of a novel system that mimics biological muscle. This system is designed to replicate the full range of motion and control functionalities, which can be utilized in various applications. This research has three significant contributions in the field of sustainable soft robotics. First, a novel shape memory alloy-based linear actuator is introduced, which achieves significantly higher displacements compared to traditional SMA wire-driven systems through a guiding mechanism. Second, this linear actuator is integrated into a hybrid soft actuation structure, which features a silicone PneuNet as the end effector and a force sensor for real-time pressure feedback. Lastly, a hardware Spiking Neural Network (HW-SNN) is utilized to control the exhibited force at the actuator’s endpoint. Experimental results showed that the displacement with the control system is significantly higher than that of the traditional control-based shape memory alloy systems. The system evaluation demonstrates good performance, thus advancing actuation and control in humanoid robotics.","url":"https://doi.org/10.3390/biomimetics10100697","authors":["Florian-Alexandru Brașoveanu","Mircea Hulea","Adrian Burlacu"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/biomimetics10100697","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2025.11.17.688781","name":"A Neurodevelopment-Inspired Deep Spiking Neural Network for Auditory Spatial Attention Detection using Single Trial EEG","source":"europepmc","abstract":"","url":"https://doi.org/10.1101/2025.11.17.688781","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.11.17.688781","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.20944/preprints202602.1058.v1","name":"eXCube2: Explainable Brain-Inspired Spiking Neural Network Framework for Emotion Recognition from Audio-, Visual- and Multimodal Audio-Visual Data","source":"europepmc","abstract":"","url":"https://doi.org/10.20944/preprints202602.1058.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.20944/preprints202602.1058.v1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.21203/rs.3.rs-6004117/v1","name":"Dynamic Token Masking in Spiking Neural Network","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-6004117/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6004117/v1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1038/s41598-025-03408-7","name":"Biologically-informed excitatory and inhibitory ratio for robust spiking neural network training.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-03408-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-03408-7","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1016/j.neunet.2025.107475","name":"SpikeCLIP: A contrastive language-image pretrained spiking neural network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107475","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.neunet.2025.107475","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.3389/frobt.2024.1435197","name":"A spiking neural network for active efficient coding.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/frobt.2024.1435197","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3389/frobt.2024.1435197","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1109/tnnls.2025.3538335","name":"NiSNN-A: Noniterative Spiking Neural Network With Attention With Application to Motor Imagery EEG Classification.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tnnls.2025.3538335","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1109/tnnls.2025.3538335","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1371/journal.pone.0313547","name":"Free-space optical spiking neural network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pone.0313547","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1371/journal.pone.0313547","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.3389/frai.2025.1651516","name":"Hybrid recurrent with spiking neural network model for enhanced anomaly prediction in IoT networks security.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/frai.2025.1651516","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/frai.2025.1651516","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1126/sciadv.adv2312","name":"Fully memristive spiking neural network for energy-efficient graph learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.adv2312","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1126/sciadv.adv2312","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1371/journal.pcbi.1013644","name":"Emergence of sparse coding, balance and decorrelation from a biologically-grounded spiking neural network model of learning in the primary visual cortex.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pcbi.1013644","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1371/journal.pcbi.1013644","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1364/ol.564419","name":"Micro-ring resonator assisted spiking neural network for efficient object detection.","source":"europepmc","abstract":"","url":"https://doi.org/10.1364/ol.564419","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1364/ol.564419","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1038/s41598-025-90113-0","name":"An accurate and fast learning approach in the biologically spiking neural network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-90113-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-90113-0","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1162/neco_a_01706","name":"Spiking Neural Network Pressure Sensor.","source":"europepmc","abstract":"","url":"https://doi.org/10.1162/neco_a_01706","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1162/neco_a_01706","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1016/j.neunet.2025.107730","name":"ST-FlowNet: An efficient Spiking Neural Network for event-based optical flow estimation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107730","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.neunet.2025.107730","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.3390/biomimetics10010048","name":"Biologically Inspired Spatial-Temporal Perceiving Strategies for Spiking Neural Network.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics10010048","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/biomimetics10010048","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1523/eneuro.0383-24.2025","name":"Spiking Neural Network Models of Interaural Time Difference Extraction via a Massively Collaborative Process.","source":"europepmc","abstract":"","url":"https://doi.org/10.1523/eneuro.0383-24.2025","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1523/eneuro.0383-24.2025","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3389/fnins.2025.1522788","name":"Optimizing event-driven spiking neural network with regularization and cutoff.","source":"europepmc","abstract":"Spiking neural networks (SNNs), which are the next generation of artificial neural networks (ANNs), offer a closer mimicry to natural neural networks and hold promise for significant improvements in computational efficiency. However, the current SNN model is trained to infer over a fixed duration, thereby overlooking the potential for dynamic inference in the SNN model. In this paper, we strengthen the relationship between SNN and event-driven processing by proposing the inclusion of a cutoff in SNN, that can terminate SNN at any time during inference to achieve efficient inference. Two novel optimization techniques are presented to achieve an inference-efficient SNN: a Top-K cutoff and regularization. The proposed regularization influences the training process by optimizing the SNN for the cutoff, whereas the Top-K cutoff technique optimizes the inference phase. We conducted an extensive set of experiments on multiple benchmark frame-based datasets, such as CIFAR10/100, Tiny-ImageNet, and event-based datasets, including CIFAR10-DVS, N-Caltech101, and DVS128 Gesture. The experimental results demonstrate the effectiveness of the proposed techniques in both the ANN-to-SNN conversion and direct training, enabling SNNs to require 1.76 to 2.76 × fewer timesteps for CIFAR-10, while achieving 1.64 to 1.95× fewer timesteps across all event-based datasets, with near-zero accuracy loss. These findings affirm the compatibility and potential benefits of the proposed techniques in terms of enhancing accuracy and reducing inference latency when integrated with existing methods. Code available: https://github.com/Dengyu-Wu/SNNCutoff .","url":"https://doi.org/10.3389/fnins.2025.1522788","authors":["Dengyu Wu","Gaojie Jin","Han Yu","Xinping Yi","Xiaowei Huang"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fnins.2025.1522788","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1371/journal.pcbi.1013112","name":"Energy optimization induces predictive-coding properties in a multi-compartment spiking neural network model.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pcbi.1013112","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1371/journal.pcbi.1013112","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1109/tnnls.2024.3372613","name":"Spiking Neural Network for Ultralow-Latency and High-Accurate Object Detection.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tnnls.2024.3372613","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1109/tnnls.2024.3372613","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.3390/biomimetics10070415","name":"Damage Resistance of an fMRI-Spiking Neural Network Based on Speech Recognition Against Stochastic Attack.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics10070415","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/biomimetics10070415","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1016/j.neunet.2025.107790","name":"The architecture design and training optimization of spiking neural network with low-latency and high-performance for classification and segmentation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107790","authors":["Wujian Ye","Shaozhen Chen","Haoxian Liu","Yijun Liu","Yuehai Chen","Youfeng Cui","Wenjie Lin"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.neunet.2025.107790","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1109/tbcas.2024.3480272","name":"A Memristive Spiking Neural Network Circuit for Bio-Inspired Navigation Based on Spatial Cognitive Mechanisms.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tbcas.2024.3480272","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1109/tbcas.2024.3480272","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1038/s41598-025-85627-6","name":"A hybrid parallel convolutional spiking neural network for enhanced skin cancer detection.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-85627-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-85627-6","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1038/s41598-025-12611-5","name":"Short-term plasticity influences episodic memory recall: an interplay of synaptic traces in a spiking neural network model.","source":"europepmc","abstract":"Abstract We investigated the interaction of episodic memory processes with the short-term dynamics of recency effects. This work takes inspiration from a seminal experimental work involving an odor-in-context association task conducted on rats. In the experimental task, rats were presented with odor pairs in two arenas serving as old or new contexts for specific odor items. Rats were rewarded for selecting the odor that was new to the current context. These new-in-context odor items were deliberately presented with higher recency relative to old-in-context items, so that episodic memory was put in conflict with a short-term recency effect. To study our hypothesis about the major role of synaptic interplay of plasticity phenomena on different time-scales in explaining rats’ performance in such episodic memory tasks, we built a computational spiking neural network model consisting of two reciprocally connected networks that stored contextual and odor information as stable distributed memory patterns. We simulated the experimental task resulting in a dynamic context-item coupling between the two networks by means of Bayesian–Hebbian plasticity with eligibility traces to account for reward-based learning. We first reproduced quantitatively and explained mechanistically the findings of the experimental study, and then to further differentiate the impact of short-term plasticity we simulated an alternative task with old-in-context items presented with higher recency, thus synergistically confounding episodic memory with effects of recency. Our model predicted that higher recency of old-in-context items enhances episodic memory by boosting the activations of old-in-context items. We argue that the model offers a computational framework for studying behavioral implications of the synaptic underpinning of different memory effects in experimental episodic memory paradigms.","url":"https://doi.org/10.1038/s41598-025-12611-5","authors":["N. Chrysanthidis","F. Fiebig","A. Lansner","P. Herman"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-12611-5","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1364/oe.566626","name":"Multilayer optical-electrical spiking neural network with sparse spike event for speech recognition based on a fabricated DFB-SA laser.","source":"europepmc","abstract":"","url":"https://doi.org/10.1364/oe.566626","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1364/oe.566626","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1109/tbcas.2024.3446177","name":"RRAM-Based Spiking Neural Network With Target-Modulated Spike-Timing-Dependent Plasticity.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tbcas.2024.3446177","authors":["Kalkidan Deme Muleta","Bai-Sun Kong"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024-08-19T17:29:40Z","doi":"10.1109/tbcas.2024.3446177","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.3390/brainsci15020186","name":"Complex Spiking Neural Network Evaluated by Injury Resistance Under Stochastic Attacks.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/brainsci15020186","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/brainsci15020186","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.3390/s25175263","name":"Balancing Energy Consumption and Detection Accuracy in Cardiovascular Disease Diagnosis: A Spiking Neural Network-Based Approach with ECG and PCG Signals.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s25175263","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/s25175263","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1016/j.compbiomed.2025.110397","name":"Roman domination-based spiking neural network for optimized EEG signal classification of four class motor imagery.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.compbiomed.2025.110397","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.compbiomed.2025.110397","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.3389/fnins.2024.1449020","name":"An all integer-based spiking neural network with dynamic threshold adaptation.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2024.1449020","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3389/fnins.2024.1449020","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.3390/brainsci15030217","name":"Research on Anti-Interference Performance of Spiking Neural Network Under Network Connection Damage.","source":"europepmc","abstract":"Background: With the development of artificial intelligence, memristors have become an ideal choice to optimize new neural network architectures and improve computing efficiency and energy efficiency due to their combination of storage and computing power. In this context, spiking neural networks show the ability to resist Gaussian noise, spike interference, and AC electric field interference by adjusting synaptic plasticity. The anti-interference ability to spike neural networks has become an important direction of electromagnetic protection bionics research. Methods: Therefore, this research constructs two types of spiking neural network models with LIF model as nodes: VGG-SNN and FCNN-SNN, and combines pruning algorithm to simulate network connection damage during the training process. By comparing and analyzing the millimeter wave radar human motion dataset and MNIST dataset with traditional artificial neural networks, the anti-interference performance of spiking neural networks and traditional artificial neural networks under the same probability of edge loss was deeply explored. Results: The experimental results show that on the millimeter wave radar human motion dataset, the accuracy of the spiking neural network decreased by 5.83% at a sparsity of 30%, while the accuracy of the artificial neural network decreased by 18.71%. On the MNIST dataset, the accuracy of the spiking neural network decreased by 3.91% at a sparsity of 30%, while the artificial neural network decreased by 10.13%. Conclusions: Therefore, under the same network connection damage conditions, spiking neural networks exhibit unique anti-interference performance advantages. The performance of spiking neural networks in information processing and pattern recognition is relatively more stable and outstanding. Further analysis reveals that factors such as network structure, encoding method, and learning algorithm have a significant impact on the anti-interference performance of both.","url":"https://doi.org/10.3390/brainsci15030217","authors":["Yongqiang Zhang","Haijie Pang","Jinlong Ma","Guilei Ma","Xiaoming Zhang","Menghua Man"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/brainsci15030217","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.3389/fnins.2025.1551656","name":"Multiscale fusion enhanced spiking neural network for invasive BCI neural signal decoding.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2025.1551656","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fnins.2025.1551656","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1007/s11571-024-10199-6","name":"Sg-snn: a self-organizing spiking neural network based on temporal information.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-024-10199-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1007/s11571-024-10199-6","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.3389/fninf.2024.1446620","name":"Commentary: Accelerating spiking neural network simulations with PymoNNto and PymoNNtorch.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fninf.2024.1446620","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3389/fninf.2024.1446620","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1109/tnnls.2024.3353571","name":"CDNA-SNN: A New Spiking Neural Network for Pattern Classification Using Neuronal Assemblies.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tnnls.2024.3353571","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1109/tnnls.2024.3353571","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.20944/preprints202504.1135.v1","name":"Modelling the Effect of Prior Knowledge on Memory Efficiency for the Study of Transfer of Learning: A Spiking Neural Network Approach","source":"europepmc","abstract":"","url":"https://doi.org/10.20944/preprints202504.1135.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202504.1135.v1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.21203/rs.3.rs-6173906/v1","name":"A Hybrid Spiking Neural Network-Quantum Classifier Framework: A Case Study Using EEG Data","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-6173906/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6173906/v1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.3390/s25041177","name":"Dynamic Cascade Spiking Neural Network Supervisory Controller for a Nonplanar Twelve-Rotor UAV.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s25041177","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/s25041177","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.21203/rs.3.rs-6265682/v1","name":"Optimized Spiking Neural Network Architecture for Fashion MNIST Classification: A Comparative Study with Convolutional Neural Networks","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-6265682/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6265682/v1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1364/oe.559380","name":"Photonic spiking neural network based on DML and DFB-SA laser chip for pattern classification.","source":"europepmc","abstract":"","url":"https://doi.org/10.1364/oe.559380","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1364/oe.559380","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.3389/fnbot.2024.1490267","name":"LoCS-Net: Localizing convolutional spiking neural network for fast visual place recognition.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnbot.2024.1490267","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3389/fnbot.2024.1490267","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1109/tbcas.2024.3452635","name":"NEXUS: A 28nm 3.3pJ/SOP 16-Core Spiking Neural Network With a Diamond Topology for Real-Time Data Processing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tbcas.2024.3452635","authors":["Maryam Sadeghi","Yasser Rezaeiyan","Dario Fernandez Khatiboun","Sherif Eissa","Federico Corradi","Charles Augustine","Farshad Moradi"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024-08-30T13:38:10Z","doi":"10.1109/tbcas.2024.3452635","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.3390/biomimetics10040240","name":"A Reinforced, Event-Driven, and Attention-Based Convolution Spiking Neural Network for Multivariate Time Series Prediction.","source":"europepmc","abstract":"Despite spiking neural networks (SNNs) inherently exceling at processing time series due to their rich spatio-temporal information and efficient event-driven computing, the challenge of extracting complex correlations between variables in multivariate time series (MTS) remains to be addressed. This paper proposes a reinforced, event-driven, and attention-based convolution SNN model (REAT-CSNN) with three novel features. First, a joint Gramian Angular Field and Rate (GAFR) coding scheme is proposed to convert MTS into spike images, preserving the inherent features in MTS, such as the temporal patterns and spatio-temporal correlations between time series. Second, an advanced LIF-pooling strategy is developed, which is then theoretically and empirically proved to be effective in preserving more features from the regions of interest in spike images than average-pooling strategies. Third, a convolutional block attention mechanism (CBAM) is redesigned to support spike-based input, enhancing event-driven characteristics in weighting operations while maintaining outstanding capability to capture the information encoded in spike images. Experiments on multiple MTS data sets, such as stocks and PM2.5 data sets, demonstrate that our model rivals, and even surpasses, some CNN- and RNN-based techniques, with up to 3% better performance, while consuming significantly less energy.","url":"https://doi.org/10.3390/biomimetics10040240","authors":["Ying Li","Xikang Guan","Wenwei Yue","Yongsheng Huang","Bin Zhang","Peibo Duan"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/biomimetics10040240","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1101/2024.09.27.615365","name":"A spiking neural network model for proprioception of limb kinematics in insect locomotion","source":"europepmc","abstract":"","url":"https://doi.org/10.1101/2024.09.27.615365","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.09.27.615365","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1007/s10827-025-00896-4","name":"Temporal pavlovian conditioning of a model spiking neural network for discrimination sequences of short time intervals.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s10827-025-00896-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1007/s10827-025-00896-4","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1016/j.slast.2025.100284","name":"A hybrid PKI and spiking neural network approach for enhancing security and energy efficiency in IoMT-based healthcare 5.0.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.slast.2025.100284","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.slast.2025.100284","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.20944/preprints202409.2330.v1","name":"Situational Awareness Classification Based on EEG Signals and Spiking Neural Network","source":"europepmc","abstract":"","url":"https://doi.org/10.20944/preprints202409.2330.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.20944/preprints202409.2330.v1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1007/s13534-024-00436-6","name":"Brain-inspired learning rules for spiking neural network-based control: a tutorial.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s13534-024-00436-6","authors":["Choongseop Lee","Yuntae Park","Sungmin Yoon","Jiwoon Lee","Youngho Cho","Cheolsoo Park"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024-12-02T15:07:23Z","doi":"10.1007/s13534-024-00436-6","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1016/j.isci.2024.111037","name":"Graph spiking neural network for advanced urban flood risk assessment.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.isci.2024.111037","authors":["Zhantu Liang","Xuhong Fang","Zhanhao Liang","Jian Xiong","Fang Deng","Tadiwa Elisha Nyamasvisva"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.isci.2024.111037","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.3389/fnins.2025.1516971","name":"Design of CMOS-memristor hybrid synapse and its application for noise-tolerant memristive spiking neural network.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2025.1516971","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fnins.2025.1516971","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1186/s12883-024-04001-7","name":"A robust Parkinson's disease detection model based on time-varying synaptic efficacy function in spiking neural network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1186/s12883-024-04001-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1186/s12883-024-04001-7","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.20944/preprints202405.1627.v1","name":"Eye Tracking Based on Event Camera and Spiking Neural Network","source":"europepmc","abstract":"","url":"https://doi.org/10.20944/preprints202405.1627.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.20944/preprints202405.1627.v1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1016/j.neunet.2024.106499","name":"Directly training temporal Spiking Neural Network with sparse surrogate gradient.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106499","authors":["Yang Li","Feifei Zhao","Dongcheng Zhao","Yi Zeng"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.neunet.2024.106499","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.3389/fninf.2024.1331220","name":"Accelerating spiking neural network simulations with PymoNNto and PymoNNtorch.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fninf.2024.1331220","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3389/fninf.2024.1331220","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1016/j.neunet.2024.106898","name":"Multi-compartment neuron and population encoding powered spiking neural network for deep distributional reinforcement learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106898","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.neunet.2024.106898","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1038/s44172-025-00359-9","name":"Low-power Spiking Neural Network audio source localisation using a Hilbert Transform audio event encoding scheme.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s44172-025-00359-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s44172-025-00359-9","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1007/s00221-024-06911-x","name":"Research on low-power driving fatigue monitoring method based on spiking neural network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s00221-024-06911-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1007/s00221-024-06911-x","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1101/2024.07.19.604252","name":"Spiking neural network models of sound localisation via a massively collaborative process","source":"europepmc","abstract":"Abstract Neuroscientists are increasingly initiating large-scale collaborations which bring together tens to hundreds of researchers. However, while these projects represent a step-change in scale, they retain a traditional structure with centralised funding, participating laboratories and data sharing on publication. Inspired by an open-source project in pure mathematics, we set out to test the feasibility of an alternative structure by running a grassroots, massively collaborative project in computational neuroscience. To do so, we launched a public Git repository, with code for training spiking neural networks to solve a sound localisation task via surrogate gradient descent. We then invited anyone, anywhere to use this code as a springboard for exploring questions of interest to them, and encouraged participants to share their work both asynchro-nously through Git and synchronously at monthly online workshops. At a scientific level, our work investigated how a range of biologically-relevant parameters, from time delays to mem-brane time constants and levels of inhibition, could impact sound localisation in networks of spiking units. At a more macro-level, our project brought together 31 researchers from multiple countries, provided hands-on research experience to early career participants, and opportunities for supervision and teaching to later career participants. Looking ahead, our project provides a glimpse of what open, collaborative science could look like and provides a necessary, tentative step towards it.","url":"https://doi.org/10.1101/2024.07.19.604252","authors":["Marcus Ghosh","Karim G. Habashy","Francesco De Santis","Tomas Fiers","Dilay Fidan Erçelik","Balázs Mészáros","Zachary Friedenberger","Gabriel Béna","Mingxuan Hong","Umar Abubacar","Rory T. Byrne","Juan Luis Riquelme"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.07.19.604252","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1109/tpami.2024.3510627","name":"Self-Supervised High-Order Information Bottleneck Learning of Spiking Neural Network for Robust Event-Based Optical Flow Estimation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tpami.2024.3510627","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1109/tpami.2024.3510627","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1371/journal.pcbi.1011625","name":"Metamodelling of a two-population spiking neural network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pcbi.1011625","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1371/journal.pcbi.1011625","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1101/2024.05.16.594474","name":"The cost of behavioral flexibility: reversal learning driven by a spiking neural network","source":"europepmc","abstract":"","url":"https://doi.org/10.1101/2024.05.16.594474","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.05.16.594474","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1103/physreve.109.024302","name":"Applications of information geometry to spiking neural network activity.","source":"europepmc","abstract":"","url":"https://doi.org/10.1103/physreve.109.024302","authors":["Jacob T. Crosser","Braden A. W. Brinkman"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1103/physreve.109.024302","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.3389/fnins.2024.1420119","name":"BayesianSpikeFusion: accelerating spiking neural network inference via Bayesian fusion of early prediction.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2024.1420119","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3389/fnins.2024.1420119","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.22541/au.174094206.61719889/v1","name":"A Precise and Low Power Analog Spiking Neural Network exploiting Pre-charged Current Mode Synapses and Coarse-fine Neuron Comparators","source":"europepmc","abstract":"","url":"https://doi.org/10.22541/au.174094206.61719889/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.22541/au.174094206.61719889/v1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1016/j.compbiomed.2024.109225","name":"Real-time sub-milliwatt epilepsy detection implemented on a spiking neural network edge inference processor.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.compbiomed.2024.109225","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.compbiomed.2024.109225","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1371/journal.pcbi.1011913","name":"Estimating orientation in natural scenes: A spiking neural network model of the insect central complex.","source":"europepmc","abstract":"The central complex of insects contains cells, organised as a ring attractor, that encode head direction. The ‘bump’ of activity in the ring can be updated by idiothetic cues and external sensory information. Plasticity at the synapses between these cells and the ring neurons, that are responsible for bringing sensory information into the central complex, has been proposed to form a mapping between visual cues and the heading estimate which allows for more accurate tracking of the current heading, than if only idiothetic information were used. In Drosophila , ring neurons have well characterised non-linear receptive fields. In this work we produce synthetic versions of these visual receptive fields using a combination of excitatory inputs and mutual inhibition between ring neurons. We use these receptive fields to bring visual information into a spiking neural network model of the insect central complex based on the recently published Drosophila connectome. Previous modelling work has focused on how this circuit functions as a ring attractor using the same type of simple visual cues commonly used experimentally. While we initially test the model on these simple stimuli, we then go on to apply the model to complex natural scenes containing multiple conflicting cues. We show that this simple visual filtering provided by the ring neurons is sufficient to form a mapping between heading and visual features and maintain the heading estimate in the absence of angular velocity input. The network is successful at tracking heading even when presented with videos of natural scenes containing conflicting information from environmental changes and translation of the camera.","url":"https://doi.org/10.1371/journal.pcbi.1011913","authors":["Rachael Stentiford","James C. Knight","Thomas Nowotny","Andrew Philippides","Paul Graham"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1371/journal.pcbi.1011913","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.1101/2024.09.04.611123","name":"Biologically-Constrained Spiking Neural Network for Neuromodulation in Locomotor Recovery after Spinal Cord Injury","source":"europepmc","abstract":"Presynaptic inhibition after spinal cord injury (SCI) has been hypothesised to disproportionately affect flexion reflex loops in locomotor spinal circuitry. Reducing gamma-aminobutyric acid (GABA) inhibitory activity increases the excitation of flexion circuits, restoring muscle activation, and stepping ability. Conversely, nociceptive sensitisation and muscular spasticity can emerge from insufficient GABAergic inhibition. To investigate the effects of neuromodulation and proprioceptive sensory afferents in the spinal cord, a biologically constrained spiking neural network (SNN) was developed. The network describes the flexor motoneuron (MN) reflex loop with inputs from ipsilateral Ia- and II-fibres and tonically firing interneurons. The model was tuned to a baseline level of locomotive activity before simulating an inhibitory-dominant and body-weight supported (BWS) SCI state. Electrical stimulation (ES) and serotonergic agonists were simulated by the excitation of dorsal fibres and reduced conductance in excitatory neurons. ES was applied across all afferent fibres without phase- or muscle-specific protocols. The present study describes, for the first time, the release of GABAergic inhibition on flexor MNs as a potential mechanism underlying BWS treadmill training. The results demonstrate the synaptic mechanisms by which neuromodulatory therapy tunes the excitation and inhibition of ankle flexor MNs during locomotion for smoother and more coordinated movement. Author Summary SCI is a life-altering condition that often leaves young adults paralysed and reliant on others for support. Restoring the ability to walk is a critical goal to help improve independence and quality of life for people living with SCI. Promising new treatments, such as spinal cord stimulation and drug therapies, aim to reawaken the neurons that control walking. However, scientists still do not entirely understand how these treatments work. In this study, we developed a detailed computer model of the neural circuits involved in walking to test how therapies such as serotonin-boosting drugs, ES, and BWS training might help. Our findings suggest that these treatments can work together to reduce excessive inhibition that blocks ankle movement, leading to smoother and more coordinated steps. This research helps uncover how these therapies work and provides insights to develop better rehabilitation strategies for improving walking after SCI.","url":"https://doi.org/10.1101/2024.09.04.611123","authors":["Raymond Chia","Chin-Teng Lin"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.09.04.611123","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1121/10.0028584","name":"Speech intelligibility prediction based on a physiological model of the human ear and a hierarchical spiking neural network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1121/10.0028584","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1121/10.0028584","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.21203/rs.3.rs-4999644/v1","name":"Task success in trained spiking neural network models coincides with emergence of cross-stimulus-modulated inhibition","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4999644/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4999644/v1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.7507/1001-5515.202503025","name":"[A head direction cell model based on a spiking neural network with landmark-free calibration].","source":"europepmc","abstract":"","url":"https://doi.org/10.7507/1001-5515.202503025","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.7507/1001-5515.202503025","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1038/s41598-024-57691-x","name":"An efficient intrusion detection model based on convolutional spiking neural network.","source":"europepmc","abstract":"Many intrusion detection techniques have been developed to ensure that the target system can function properly under the established rules. With the booming Internet of Things (IoT) applications, the resource-constrained nature of its devices makes it urgent to explore lightweight and high-performance intrusion detection models. Recent years have seen a particularly active application of deep learning (DL) techniques. The spiking neural network (SNN), a type of artificial intelligence that is associated with sparse computations and inherent temporal dynamics, has been viewed as a potential candidate for the next generation of DL. It should be noted, however, that current research into SNNs has largely focused on scenarios where limited computational resources and insufficient power sources are not considered. Consequently, even state-of-the-art SNN solutions tend to be inefficient. In this paper, a lightweight and effective detection model is proposed. With the help of rational algorithm design, the model integrates the advantages of SNNs as well as convolutional neural networks (CNNs). In addition to reducing resource usage, it maintains a high level of classification accuracy. The proposed model was evaluated against some current state-of-the-art models using a comprehensive set of metrics. Based on the experimental results, the model demonstrated improved adaptability to environments with limited computational resources and energy sources.","url":"https://doi.org/10.1038/s41598-024-57691-x","authors":["Zhen Wang","Fuad A. Ghaleb","Anazida Zainal","Maheyzah Md Siraj","Xing Lü"],"tags":["Computer science","Spiking neural network","Intrusion detection system","Convolutional neural network","Artificial intelligence"],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41598-024-57691-x","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"doi:10.1016/j.jneumeth.2024.110203","name":"Brain-computer interfaces inspired spiking neural network model for depression stage identification.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.jneumeth.2024.110203","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.jneumeth.2024.110203","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1101/2024.12.05.627100","name":"Emergence of Sparse Coding, Balance and Decorrelation from a Biologically-Grounded Spiking Neural Network Model of Learning in the Primary Visual Cortex","source":"europepmc","abstract":"1 Abstract Many computational studies attempt to address the question of information representation in biological neural networks using an explicit optimization based on an objective function. These approaches begin with principles of information representation that are expected to be found in the network and from which learning rules can be derived. This study approaches the question from the opposite direction; beginning with a model built upon the experimentally observed properties of neural responses, homeostasis, and synaptic plasticity. The known properties of information representation are then expected to emerge from this substrate. A spiking neural model of the primary visual cortex (V1) was investigated. Populations of both inhibitory and excitatory leaky integrate-and-fire neurons with recurrent connections were provided with spiking input from simulated ON and OFF neurons of the lateral geniculate nucleus. This network was provided with natural image stimuli as input. All synapses underwent learning using spike-timing-dependent plasticity learning rules. A homeostatic rule adjusted the weights and thresholds of each neuron based on target homeostatic spiking rates and mean synaptic input values. These experimentally grounded rules resulted in a number of the expected properties of information representation. The network showed a temporally sparse spike response to inputs and this was associated with a sparse code with Gabor-like receptive fields. The network was balanced at both slow and fast time scales; increased excitatory input was balanced by increased inhibition. This balance was associated with decorrelated firing that was observed as population sparseness. This population sparseness was both the cause and result of the decorrelation of receptive fields. These observed emergent properties (balance, temporal sparseness, population sparseness, and decorrelation) indicate that the network is implementing expected principles of information processing: efficient coding, information maximization (’infomax’), and a lateral or single-layer form of predictive coding. These emergent features of the network were shown to be robust to randomized jitter of the values of key simulation parameters.","url":"https://doi.org/10.1101/2024.12.05.627100","authors":["Marko A. Ruslim","Martin J. Spencer","Hinze Hogendoorn","Hamish Meffin","Yanbo Lian","Anthony N. Burkitt"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.12.05.627100","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1016/j.neunet.2024.106172","name":"Efficient spiking neural network design via neural architecture search.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106172","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.neunet.2024.106172","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1101/2025.02.09.25321975","name":"Liquid-Dendrite Spiking Neural Network for Edge Devices: A 130 K-Parameter, 535 KB Model for Time-Domain Epileptic Seizure Detection","source":"europepmc","abstract":"","url":"https://doi.org/10.1101/2025.02.09.25321975","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.02.09.25321975","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1109/tnnls.2022.3202501","name":"A Hybrid CMOS-Memristor Spiking Neural Network Supporting Multiple Learning Rules.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tnnls.2022.3202501","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1109/tnnls.2022.3202501","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.3389/fphys.2024.1379977","name":"Investigating visual navigation using spiking neural network models of the insect mushroom bodies.","source":"europepmc","abstract":"Ants are capable of learning long visually guided foraging routes with limited neural resources. The visual scene memory needed for this behaviour is mediated by the mushroom bodies; an insect brain region important for learning and memory. In a visual navigation context, the mushroom bodies are theorised to act as familiarity detectors, guiding ants to views that are similar to those previously learned when first travelling along a foraging route. Evidence from behavioural experiments, computational studies and brain lesions all support this idea. Here we further investigate the role of mushroom bodies in visual navigation with a spiking neural network model learning complex natural scenes. By implementing these networks in GeNN–a library for building GPU accelerated spiking neural networks–we were able to test these models offline on an image database representing navigation through a complex outdoor natural environment, and also online embodied on a robot. The mushroom body model successfully learnt a large series of visual scenes (400 scenes corresponding to a 27 m route) and used these memories to choose accurate heading directions during route recapitulation in both complex environments. Through analysing our model’s Kenyon cell (KC) activity, we were able to demonstrate that KC activity is directly related to the respective novelty of input images. Through conducting a parameter search we found that there is a non-linear dependence between optimal KC to visual projection neuron (VPN) connection sparsity and the length of time the model is presented with an image stimulus. The parameter search also showed training the model on lower proportions of a route generally produced better accuracy when testing on the entire route. We embodied the mushroom body model and comparator visual navigation algorithms on a Quanser Q-car robot with all processing running on an Nvidia Jetson TX2. On a 6.5 m route, the mushroom body model had a mean distance to training route (error) of 0.144 ± 0.088 m over 5 trials, which was performance comparable to standard visual-only navigation algorithms. Thus, we have demonstrated that a biologically plausible model of the ant mushroom body can navigate complex environments both in simulation and the real world. Understanding the neural basis of this behaviour will provide insight into how neural circuits are tuned to rapidly learn behaviourally relevant information from complex environments and provide inspiration for creating bio-mimetic computer/robotic systems that can learn rapidly with low energy requirements.","url":"https://doi.org/10.3389/fphys.2024.1379977","authors":["Oluwaseyi Oladipupo Jesusanmi","Amany Azevedo Amin","Norbert Domcsek","James C. Knight","Andrew Philippides","Thomas Nowotny","Paul Graham"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3389/fphys.2024.1379977","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1007/s13534-024-00391-2","name":"Review on spiking neural network-based ECG classification methods for low-power environments.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s13534-024-00391-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1007/s13534-024-00391-2","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.3390/biomimetics9070413","name":"LDD: High-Precision Training of Deep Spiking Neural Network Transformers Guided by an Artificial Neural Network.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics9070413","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3390/biomimetics9070413","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1109/embc53108.2024.10781591","name":"Recapitulating the electrophysiological features of in vivo biological networks by using a real-time hardware Spiking Neural Network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/embc53108.2024.10781591","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1109/embc53108.2024.10781591","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1002/adma.202406970","name":"Spiking Neural Network Integrated with Impact Ionization Field-Effect Transistor Neuron and a Ferroelectric Field-Effect Transistor Synapse.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202406970","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/adma.202406970","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1080/0954898x.2024.2348018","name":"Neuromorphic computing spiking neural network edge detection model for content based image retrieval.","source":"europepmc","abstract":"","url":"https://doi.org/10.1080/0954898x.2024.2348018","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1080/0954898x.2024.2348018","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1080/10255842.2023.2275544","name":"Spiking neural network-based computational modeling of episodic memory.","source":"europepmc","abstract":"","url":"https://doi.org/10.1080/10255842.2023.2275544","authors":["Rahul Shrivastava","Pushpraj Singh Chauhan"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023-11-02T10:15:45Z","doi":"10.1080/10255842.2023.2275544","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1007/s10827-024-00881-3","name":"Formation and retrieval of cell assemblies in a biologically realistic spiking neural network model of area CA3 in the mouse hippocampus.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s10827-024-00881-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1007/s10827-024-00881-3","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.3389/fnins.2024.1325062","name":"Brain topology improved spiking neural network for efficient reinforcement learning of continuous control.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2024.1325062","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3389/fnins.2024.1325062","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1101/2024.03.14.584997","name":"LoCS-Net: Localizing Convolutional Spiking Neural Network for Fast Visual Place Recognition","source":"europepmc","abstract":"","url":"https://doi.org/10.1101/2024.03.14.584997","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.03.14.584997","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.3389/fnins.2023.1091097","name":"VTSNN: a virtual temporal spiking neural network.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2023.1091097","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.3389/fnins.2023.1091097","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1016/j.compbiomed.2024.108877","name":"Automatic detection of sleep apnea from a single-lead ECG signal based on spiking neural network model.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.compbiomed.2024.108877","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.compbiomed.2024.108877","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1016/j.isci.2024.108845","name":"Emergence of brain-inspired small-world spiking neural network through neuroevolution.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.isci.2024.108845","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.isci.2024.108845","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1101/2024.02.13.580047","name":"Estimating orientation in Natural scenes: A Spiking Neural Network Model of the Insect Central Complex","source":"europepmc","abstract":"","url":"https://doi.org/10.1101/2024.02.13.580047","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.02.13.580047","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1109/tpami.2023.3275769","name":"Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANN.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tpami.2023.3275769","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1109/tpami.2023.3275769","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.20944/preprints202401.2165.v1","name":"Facial Expression Recognition Based on Convolutional Spiking Neural Network and STDP Fine-Tune","source":"europepmc","abstract":"","url":"https://doi.org/10.20944/preprints202401.2165.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.20944/preprints202401.2165.v1","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.3390/s23167232","name":"Unsupervised Spiking Neural Network with Dynamic Learning of Inhibitory Neurons.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s23167232","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.3390/s23167232","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1021/acs.jcim.3c01900","name":"Discovery of Covalent Lead Compounds Targeting 3CL Protease with a Lateral Interactions Spiking Neural Network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.jcim.3c01900","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1021/acs.jcim.3c01900","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1016/j.saa.2024.123904","name":"Rapid diagnosis of systemic lupus erythematosus by Raman spectroscopy combined with spiking neural network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.saa.2024.123904","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.saa.2024.123904","addedAt":"2026-09-01T01:48:22.344Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1101/2024.01.17.575877","name":"Energy Optimization Induces Predictive-coding Properties in a Multicompartment Spiking Neural Network Model","source":"europepmc","abstract":"A bstract Predictive coding is a prominent theoretical framework for understanding the hierarchical sensory processing in the brain, yet how it could be implemented in networks of cortical neurons is still unclear. While most existing works have taken a hand-wiring approach to creating microcircuits that match experimental results, recent work in applying an optimisation approach to rate-based artificial neural networks revealed that cortical connectivity might result from self-organisation given some fundamental computational principle, such as energy efficiency. As no corresponding approach has studied this in more plausible networks of spiking neurons, we here investigate whether predictive coding properties in a multi-compartment spiking neural network can emerge from energy optimisation. We find that a model trained with an energy objective in addition to a task-relevant objective is able to reconstruct internal representations given top-down expectation signals alone. Additionally, neurons in the energy-optimised model also show differential responses to expected versus unexpected stimuli, qualitatively similar to experimental evidence for predictive coding. These findings indicate that predictive-coding-like behaviour might be an emergent property of energy optimisation, providing a new perspective on how predictive coding could be achieved in the cortex.","url":"https://doi.org/10.1101/2024.01.17.575877","authors":["Mingfang(Lucy) Zhang","Sander M. Bohte"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.01.17.575877","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.3389/fnins.2023.1303564","name":"Efficient and generalizable cross-patient epileptic seizure detection through a spiking neural network.","source":"europepmc","abstract":"Introduction Epilepsy is a global chronic disease that brings pain and inconvenience to patients, and an electroencephalogram (EEG) is the main analytical tool. For clinical aid that can be applied to any patient, an automatic cross-patient epilepsy seizure detection algorithm is of great significance. Spiking neural networks (SNNs) are modeled on biological neurons and are energy-efficient on neuromorphic hardware, which can be expected to better handle brain signals and benefit real-world, low-power applications. However, automatic epilepsy seizure detection rarely considers SNNs. Methods In this article, we have explored SNNs for cross-patient seizure detection and discovered that SNNs can achieve comparable state-of-the-art performance or a performance that is even better than artificial neural networks (ANNs). We propose an EEG-based spiking neural network (EESNN) with a recurrent spiking convolution structure, which may better take advantage of temporal and biological characteristics in EEG signals. Results We extensively evaluate the performance of different SNN structures, training methods, and time settings, which builds a solid basis for understanding and evaluation of SNNs in seizure detection. Moreover, we show that our EESNN model can achieve energy reduction by several orders of magnitude compared with ANNs according to the theoretical estimation. Discussion These results show the potential for building high-performance, low-power neuromorphic systems for seizure detection and also broaden real-world application scenarios of SNNs.","url":"https://doi.org/10.3389/fnins.2023.1303564","authors":["Zongpeng Zhang","Mingqing Xiao","Taoyun Ji","Yuwu Jiang","Tong Lin","Xiaohua Zhou","Zhouchen Lin"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.3389/fnins.2023.1303564","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1016/j.neunet.2023.07.031","name":"Memristor-based spiking neural network with online reinforcement learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2023.07.031","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1016/j.neunet.2023.07.031","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1088/1741-2552/ad1787","name":"A spiking neural network with continuous local learning for robust online brain machine interface.","source":"europepmc","abstract":"","url":"https://doi.org/10.1088/1741-2552/ad1787","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1088/1741-2552/ad1787","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1101/2024.04.21.590492","name":"Functions of Direct and Indirect Pathways for Action Selection Are Quantitatively Analyzed in A Spiking Neural Network of The Basal Ganglia","source":"europepmc","abstract":"","url":"https://doi.org/10.1101/2024.04.21.590492","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.04.21.590492","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1155/2023/9856503","name":"Retracted: A Deep Spiking Neural Network Anomaly Detection Method.","source":"europepmc","abstract":"","url":"https://doi.org/10.1155/2023/9856503","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1155/2023/9856503","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.3390/s24113426","name":"Electrocardiography Classification with Leaky Integrate-and-Fire Neurons in an Artificial Neural Network-Inspired Spiking Neural Network Framework.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s24113426","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3390/s24113426","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1109/jtehm.2023.3320132","name":"Fractal Spiking Neural Network Scheme for EEG-Based Emotion Recognition.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/jtehm.2023.3320132","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1109/jtehm.2023.3320132","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.21203/rs.3.rs-4391542/v1","name":"A Robust Parkinson’s Disease Detection Model Based on Time-varying Synaptic Efficacy Function in Spiking Neural Network","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4391542/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4391542/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3389/fnins.2023.1200701","name":"Emotional brain network decoded by biological spiking neural network.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2023.1200701","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.3389/fnins.2023.1200701","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1101/2024.05.23.24307841","name":"Tiny dLIF: A Dendritic Spiking Neural Network Enabling a Time-Domain Energy-Efficient Seizure Detection System","source":"europepmc","abstract":"","url":"https://doi.org/10.1101/2024.05.23.24307841","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.05.23.24307841","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.03.08.583887","name":"Emergence of Orientation Pinwheels in a Self-Evolving Spiking Neural Network: Enhancing Visual Coding Efficiency and Reliability","source":"europepmc","abstract":"","url":"https://doi.org/10.1101/2024.03.08.583887","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.03.08.583887","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.31234/osf.io/b9ksd","name":"Personalized spiking neural network models inform learning histories of choice behavior","source":"europepmc","abstract":"","url":"https://doi.org/10.31234/osf.io/b9ksd","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.31234/osf.io/b9ksd","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1038/s41467-024-48905-x","name":"BiœmuS: A new tool for neurological disorders studies through real-time emulation and hybridization using biomimetic Spiking Neural Network.","source":"europepmc","abstract":"Abstract Characterization and modeling of biological neural networks has emerged as a field driving significant advancements in our understanding of brain function and related pathologies. As of today, pharmacological treatments for neurological disorders remain limited, pushing the exploration of promising alternative approaches such as electroceutics. Recent research in bioelectronics and neuromorphic engineering have fostered the development of the new generation of neuroprostheses for brain repair. However, achieving their full potential necessitates a deeper understanding of biohybrid interaction. In this study, we present a novel real-time, biomimetic, cost-effective and user-friendly neural network capable of real-time emulation for biohybrid experiments. Our system facilitates the investigation and replication of biophysically detailed neural network dynamics while prioritizing cost-efficiency, flexibility and ease of use. We showcase the feasibility of conducting biohybrid experiments using standard biophysical interfaces and a variety of biological cells as well as real-time emulation of diverse network configurations. We envision our system as a crucial step towards the development of neuromorphic-based neuroprostheses for bioelectrical therapeutics, enabling seamless communication with biological networks on a comparable timescale. Its embedded real-time functionality enhances practicality and accessibility, amplifying its potential for real-world applications in biohybrid experiments.","url":"https://doi.org/10.1038/s41467-024-48905-x","authors":["Romain Beaubois","Jérémy Cheslet","Tomoya Duenki","Giuseppe De Venuto","Marta Carè","Farad Khoyratee","Michela Chiappalone","Pascal Branchereau","Yoshiho Ikeuchi","Timothée Levi"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41467-024-48905-x","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:24.597Z"},{"id":"doi:10.3390/e25050745","name":"Information Encoding in Bursting Spiking Neural Network Modulated by Astrocytes.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/e25050745","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.3390/e25050745","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1101/2024.03.27.586909","name":"Formation and Retrieval of Cell Assemblies in a Biologically Realistic Spiking Neural Network Model of Area CA3 in the Mouse Hippocampus","source":"europepmc","abstract":"","url":"https://doi.org/10.1101/2024.03.27.586909","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.03.27.586909","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1038/s41467-024-47495-y","name":"Robust compression and detection of epileptiform patterns in ECoG using a real-time spiking neural network hardware framework.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-024-47495-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41467-024-47495-y","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1021/acsnano.4c11081","name":"Compact Physical Implementation of Spiking Neural Network Using Ambipolar WSe<sub>2</sub> n-Type/p-Type Ferroelectric Field-Effect Transistor.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.4c11081","authors":["Jiali Huo","Lingqi Li","Haofei Zheng","Jing Gao","Thaw Tint Te Tun","Heng Xiang","Kah-Wee Ang"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1021/acsnano.4c11081","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:24.597Z"},{"id":"doi:10.3390/s23146548","name":"EdgeMap: An Optimized Mapping Toolchain for Spiking Neural Network in Edge Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s23146548","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.3390/s23146548","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.7554/elife.90597","name":"Hippocampome.org 2.0 is a knowledge base enabling data-driven spiking neural network simulations of rodent hippocampal circuits.","source":"europepmc","abstract":"Hippocampome.org is a mature open-access knowledge base of the rodent hippocampal formation focusing on neuron types and their properties. Previously, Hippocampome.org v1.0 established a foundational classification system identifying 122 hippocampal neuron types based on their axonal and dendritic morphologies, main neurotransmitter, membrane biophysics, and molecular expression (Wheeler et al., 2015). Releases v1.1 through v1.12 furthered the aggregation of literature-mined data, including among others neuron counts, spiking patterns, synaptic physiology, in vivo firing phases, and connection probabilities. Those additional properties increased the online information content of this public resource over 100-fold, enabling numerous independent discoveries by the scientific community. Hippocampome.org v2.0, introduced here, besides incorporating over 50 new neuron types, now recenters its focus on extending the functionality to build real-scale, biologically detailed, data-driven computational simulations. In all cases, the freely downloadable model parameters are directly linked to the specific peer-reviewed empirical evidence from which they were derived. Possible research applications include quantitative, multiscale analyses of circuit connectivity and spiking neural network simulations of activity dynamics. These advances can help generate precise, experimentally testable hypotheses and shed light on the neural mechanisms underlying associative memory and spatial navigation.","url":"https://doi.org/10.7554/elife.90597","authors":["Diek W Wheeler","Jeffrey D Kopsick","Nate Sutton","Carolina Tecuatl","Alexander O Komendantov","Kasturi Nadella","Giorgio A Ascoli"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023-09-27T11:32:18Z","doi":"10.7554/elife.90597","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.3389/fnins.2023.1174760","name":"Feasibility study on the application of a spiking neural network in myoelectric control systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2023.1174760","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.3389/fnins.2023.1174760","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.3390/s23063037","name":"Overview of Spiking Neural Network Learning Approaches and Their Computational Complexities.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s23063037","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.3390/s23063037","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.21203/rs.3.rs-3591328/v1","name":"Robust compression and detection of epileptiform patterns in ECoG using a real-time spiking neural network hardware framework","source":"europepmc","abstract":"Abstract Interictal Epileptiform Discharges (IED) and High Frequency Oscillations (HFO) in intraoperative electrocorticography (ECoG) may guide the surgeon by delineating the epileptogenic zone. We designed a modular spiking neural network (SNN) in a mixed-signal neuromorphic device to process the ECoG in real-time. We exploit the variability of the inhomogeneous silicon neurons to achieve efficient sparse and de-correlated temporal signal encoding. We interface the full-custom SNN device to the BCI2000 real-time framework and configure the setup to detect HFO and IED co-occurring with HFO (IED-HFO). We validate the setup on pre-recorded data and obtain HFO rates that are concordant with a previously validated offline algorithm (Spearman’s ρ = 0.75, p = 1e-4), achieving the same postsurgical seizure freedom predictions for all patients. In a remote on-line analysis, intraoperative ECoG recorded in Utrecht was compressed and transferred to Zurich for SNN processing and successful IED-HFO detection in real-time. These results further demonstrate how automated remote real-time detection may enable the use of HFO in clinical practice.","url":"https://doi.org/10.21203/rs.3.rs-3591328/v1","authors":["Filippo Costa","Eline Schaft","Geertjan Huiskamp","Erik Aarnoutse","Maryse van ’t Klooster","Niklaus Krayenbühl","Georgia Ramantani","Maeike Zijlmans","Giacomo Indiveri","Johannes Sarnthein"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-3591328/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1101/2023.08.16.553602","name":"A Spiking Neural Network with Continuous Local Learning for Robust Online Brain Machine Interface","source":"europepmc","abstract":"","url":"https://doi.org/10.1101/2023.08.16.553602","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.08.16.553602","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.3389/fnins.2023.1167134","name":"Spiking neural network with working memory can integrate and rectify spatiotemporal features.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2023.1167134","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.3389/fnins.2023.1167134","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.3389/fnins.2023.994517","name":"Heterogeneous recurrent spiking neural network for spatio-temporal classification.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2023.994517","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.3389/fnins.2023.994517","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.1101/2022.09.05.506616","name":"Metamodelling of a two-population spiking neural network","source":"europepmc","abstract":"","url":"https://doi.org/10.1101/2022.09.05.506616","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.09.05.506616","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1007/s10278-023-00776-2","name":"Skin Cancer Classification Using Deep Spiking Neural Network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s10278-023-00776-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1007/s10278-023-00776-2","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.3389/fnins.2024.1220908","name":"Artificial cerebellum on FPGA: realistic real-time cerebellar spiking neural network model capable of real-world adaptive motor control.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2024.1220908","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3389/fnins.2024.1220908","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.494Z"},{"id":"doi:10.21203/rs.3.rs-3312919/v1","name":"Biologically Inspired Tonic and Bursting LIF Neuron Model for Spiking Neural Network: A CMOS Implementation","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3312919/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-3312919/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.3390/brainsci13050837","name":"Anti-Disturbance of Scale-Free Spiking Neural Network against Impulse Noise.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/brainsci13050837","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.3390/brainsci13050837","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1364/oe.479903","name":"Speed-up coherent Ising machine with a spiking neural network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1364/oe.479903","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1364/oe.479903","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.20944/preprints202311.1647.v1","name":"Extraction of Significant Features by Fixed-Weight Layer of Processing Elements for the Development of an Effective Spiking Neural Network Classifier","source":"europepmc","abstract":"","url":"https://doi.org/10.20944/preprints202311.1647.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.20944/preprints202311.1647.v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1101/2022.09.28.509893","name":"A spiking neural network model of cortical intraregional metastability","source":"europepmc","abstract":"","url":"https://doi.org/10.1101/2022.09.28.509893","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.09.28.509893","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1109/embc40787.2023.10340907","name":"Design of an experimental setup for delivering intracortical microstimulation in vivo via Spiking Neural Network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/embc40787.2023.10340907","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1109/embc40787.2023.10340907","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1155/2022/6391750","name":"A Deep Spiking Neural Network Anomaly Detection Method.","source":"europepmc","abstract":"","url":"https://doi.org/10.1155/2022/6391750","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1155/2022/6391750","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.21203/rs.3.rs-3200595/v1","name":"A Novel Approach for Autonomous Mobile Robot Learning and Control Using a Customized Spiking Neural Network","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3200595/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-3200595/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.3389/fnins.2023.1225871","name":"ALBSNN: ultra-low latency adaptive local binary spiking neural network with accuracy loss estimator.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2023.1225871","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.3389/fnins.2023.1225871","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1371/journal.pone.0299425","name":"Construction and improvement of English vocabulary learning model integrating spiking neural network and convolutional long short-term memory algorithm.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pone.0299425","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1371/journal.pone.0299425","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1109/tbcas.2024.3412908","name":"MorphBungee: A 65-nm 7.2-mm&lt;sup&gt;2&lt;/sup&gt; 27-µJ/Image Digital Edge Neuromorphic Chip With on-Chip 802-Frame/s Multi-Layer Spiking Neural Network Learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tbcas.2024.3412908","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1109/tbcas.2024.3412908","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1016/j.neunet.2023.06.019","name":"An unsupervised STDP-based spiking neural network inspired by biologically plausible learning rules and connections.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2023.06.019","authors":["Yiting Dong","Dongcheng Zhao","Yang Li","Yi Zeng"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1016/j.neunet.2023.06.019","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.3389/fnins.2023.1161592","name":"ReplaceNet: real-time replacement of a biological neural circuit with a hardware-assisted spiking neural network.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2023.1161592","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.3389/fnins.2023.1161592","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.31083/j.jin2205124","name":"The NEF-SPA Approach as a Framework for Developing a Neurobiologically Inspired Spiking Neural Network Model for Speech Production.","source":"europepmc","abstract":"Background: The computer-based simulation of the whole processing route for speech production and speech perception in a neurobiologically inspired way remains a challenge. Only a few neural based models of speech production exist, and these models either concentrate on the cognitive-linguistic component or the lower-level sensorimotor component of speech production and speech perception. Moreover, these existing models are second-generation neural network models using rate-based neuron approaches. The aim of this paper is to describe recent work developing a third-generation spiking-neuron neural network capable of modeling the whole process of speech production, including cognitive and sensorimotor components. Methods: Our neural model of speech production was developed within the Neural Engineering Framework (NEF), incorporating the concept of Semantic Pointer Architecture (SPA), which allows the construction of large-scale neural models of the functioning brain based on only a few essential and neurobiologically well-grounded modeling or construction elements (i.e., single spiking neuron elements, neural connections, neuron ensembles, state buffers, associative memories, modules for binding and unbinding of states, modules for time scale generation (oscillators) and ramp signal generation (integrators), modules for input signal processing, modules for action selection, etc.). Results: We demonstrated that this modeling approach is capable of constructing a fully functional model of speech production based on these modeling elements (i.e., biologically motivated spiking neuron micro-circuits or micro-networks). The model is capable of (i) modeling the whole processing chain of speech production and, in part, for speech perception based on leaky-integrate-and-fire spiking neurons and (ii) simulating (macroscopic) speaking behavior in a realistic way, by using neurobiologically plausible (microscopic) neural construction elements. Conclusions: The model presented here is a promising approach for describing speech processing in a bottom-up manner based on a set of micro-circuit neural network elements for generating a large-scale neural network. In addition, the model conforms to a top-down design, as it is available in a condensed form in box-and-arrow models based on functional imaging and electrophysiological data recruited from speech processing tasks.","url":"https://doi.org/10.31083/j.jin2205124","authors":["Bernd J. Kröger"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.31083/j.jin2205124","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.3389/fnbot.2022.1025338","name":"A brain-inspired robot pain model based on a spiking neural network.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnbot.2022.1025338","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.3389/fnbot.2022.1025338","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.18746670","name":"Semantic Dynamic Grounding Engine (SDGE)","source":"datacite","abstract":"SDGE (Semantic Dynamic Grounding Engine) is a dynamic semantic grounding engine built on a spiking neural network (SNN). It treats meaning and understanding as a physical state inside the network, rather than as probabilistic computation over symbols. The Core Idea (Simplified) Instead of ‘learning’ by sculpting a probability distribution and performing dense weight updates, SDGE follows a brain-like principle: 1. It begins from a rich, chaotic state space (analogous to cortex generating many possible trajectories). 2. It receives a temporal input stream that drives the network along different trajectories. 3. When sufficient structure emerges, the dynamics collapse into a stable attractor. This collapse is the moment of understanding. 4. At that moment the engine commits at t* and captures a triple: Captured at commitment: · h*: the internal ‘imprint of understanding’ (a committed state snapshot). · sigma_hat*: calibrated confidence. · t*: commitment/understanding time. The system then ‘learns’ by storing this imprint as an explicit append-only binding in memory (GroundingBank), rather than by imprinting the knowledge into dense weights. Why This Yields Exceptional Advantages 1) High Data Efficiency (Few-shot) Because learning is not ‘reshaping weights’ to approximate meaning, but reaching a stable understanding state h* and binding it, the engine can add a new concept from very few examples. When the dynamics can form a clear attractor, a new concept can be acquired from a single example (1-shot). 2) Structural Non-Forgetting (Zero Forgetting) In statistical systems, adding new knowledge typically forces updates to shared weights, causing interference and forgetting. In SDGE, new knowledge is appended as bindings in an append-only memory, while old knowledge is not overwritten. Therefore, non-forgetting is structurally implied by the design. 3) A Principled Path to Energy Efficiency SDGE has two physical reasons to be more energy-efficient in principle: · Event-driven SNN computation: most computation occurs on spike events rather than dense matrix multiplications at every step. · Early stop by commitment: the engine effectively stops processing at t* (it does not keep computing after it understands). 4) Understanding Becomes a Measurable, Verifiable Event The triple (t*, h*, sigma_hat*) means SDGE does not merely output an ‘answer’. It provides operational evidence of understanding: · when the system understood (t*), · which internal state expressed that understanding (h*), · and how confident it was, in a calibratable way (sigma_hat*). This makes it possible to produce reproducible operational certificates (artifacts) rather than relying on a black-box claim.","url":"https://doi.org/10.5281/zenodo.18746670","authors":["Salhab, Najih"],"tags":["Semantic Dynamic Grounding Engine (SDGE), dynamic semantic grounding, spiking neural networks (SNN), recurrent spiking neural networks (RSNN), attractor dynamics, state-space trajectories, commitment time (t*), committed state (h*), calibrated confidence (sigma_hat*), stability gates, plateau detection, hysteresis, alive gate, event-driven computation, early stopping, energy-efficient AI, few-shot learning, one-shot learning, continual learning, stability–plasticity dilemma, catastrophic forgetting, append-only memory, explicit binding, GroundingBank, temporal drift robustness, Shift300, calibration, expected calibration error (ECE), operational certificates, reproducible artifacts, dynamical systems, brain-inspired computing, neuro-symbolic grounding"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18746670","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18746669","name":"Semantic Dynamic Grounding Engine (SDGE)","source":"datacite","abstract":"SDGE (Semantic Dynamic Grounding Engine) is a dynamic semantic grounding engine built on a spiking neural network (SNN). It treats meaning and understanding as a physical state inside the network, rather than as probabilistic computation over symbols. The Core Idea (Simplified) Instead of ‘learning’ by sculpting a probability distribution and performing dense weight updates, SDGE follows a brain-like principle: 1. It begins from a rich, chaotic state space (analogous to cortex generating many possible trajectories). 2. It receives a temporal input stream that drives the network along different trajectories. 3. When sufficient structure emerges, the dynamics collapse into a stable attractor. This collapse is the moment of understanding. 4. At that moment the engine commits at t* and captures a triple: Captured at commitment: · h*: the internal ‘imprint of understanding’ (a committed state snapshot). · sigma_hat*: calibrated confidence. · t*: commitment/understanding time. The system then ‘learns’ by storing this imprint as an explicit append-only binding in memory (GroundingBank), rather than by imprinting the knowledge into dense weights. Why This Yields Exceptional Advantages 1) High Data Efficiency (Few-shot) Because learning is not ‘reshaping weights’ to approximate meaning, but reaching a stable understanding state h* and binding it, the engine can add a new concept from very few examples. When the dynamics can form a clear attractor, a new concept can be acquired from a single example (1-shot). 2) Structural Non-Forgetting (Zero Forgetting) In statistical systems, adding new knowledge typically forces updates to shared weights, causing interference and forgetting. In SDGE, new knowledge is appended as bindings in an append-only memory, while old knowledge is not overwritten. Therefore, non-forgetting is structurally implied by the design. 3) A Principled Path to Energy Efficiency SDGE has two physical reasons to be more energy-efficient in principle: · Event-driven SNN computation: most computation occurs on spike events rather than dense matrix multiplications at every step. · Early stop by commitment: the engine effectively stops processing at t* (it does not keep computing after it understands). 4) Understanding Becomes a Measurable, Verifiable Event The triple (t*, h*, sigma_hat*) means SDGE does not merely output an ‘answer’. It provides operational evidence of understanding: · when the system understood (t*), · which internal state expressed that understanding (h*), · and how confident it was, in a calibratable way (sigma_hat*). This makes it possible to produce reproducible operational certificates (artifacts) rather than relying on a black-box claim.","url":"https://doi.org/10.5281/zenodo.18746669","authors":["Salhab, Najih"],"tags":["Semantic Dynamic Grounding Engine (SDGE), dynamic semantic grounding, spiking neural networks (SNN), recurrent spiking neural networks (RSNN), attractor dynamics, state-space trajectories, commitment time (t*), committed state (h*), calibrated confidence (sigma_hat*), stability gates, plateau detection, hysteresis, alive gate, event-driven computation, early stopping, energy-efficient AI, few-shot learning, one-shot learning, continual learning, stability–plasticity dilemma, catastrophic forgetting, append-only memory, explicit binding, GroundingBank, temporal drift robustness, Shift300, calibration, expected calibration error (ECE), operational certificates, reproducible artifacts, dynamical systems, brain-inspired computing, neuro-symbolic grounding"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18746669","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.3929/ethz-b-000716394","name":"A bio-inspired hardware implementation of an analog spike-based hippocampus memory model","source":"datacite","abstract":"The need for processing at the edge the increasing amount of data that is being produced by multitudes of sensors has led to the demand for mode power efficient computational systems, by exploring alternative computing paradigms and technologies. Neuromorphic engineering is a promising approach that can address this need by developing electronic systems that faithfully emulate the computational properties of animal brains. In particular, the hippocampus stands out as one of the most relevant brain region for implementing auto associative memories capable of learning large amounts of information quickly and recalling it efficiently. In this work, we present a computational spike-based memory model inspired by the hippocampus that takes advantage of the features of analog electronic circuits: energy efficiency, compactness, and real-time operation. This model can learn memories, recall them from a partial fragment and forget. It has been implemented as a Spiking Neural Networks directly on a mixed-signal neuromorphic chip. We describe the details of the hardware implementation and demonstrate its operation via a series of benchmark experiments, showing how this research prototype paves the way for the development of future robust and low-power mixed-signal neuromorphic processing systems.","url":"https://doi.org/10.3929/ethz-b-000716394","authors":["Casanueva-Morato, Daniel","Ayuso-Martinez, Alvaro","Indiveri, Giacomo","Dominguez-Morales, J.P.","Jimenez-Moreno, Gabriel"],"tags":["Hippocampus model","Analog memory model","Spiking neural network","Neuromorphic engineering","DYNAP-SE"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3929/ethz-b-000716394","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2601.17991","name":"Prosthetic Hand Manipulation System Based on EMG and Eye Tracking Powered by the Neuromorphic Processor AltAi","source":"datacite","abstract":"This paper presents a novel neuromorphic control architecture for upper-limb prostheses that combines surface electromyography (sEMG) with gaze-guided computer vision. The system uses a spiking neural network deployed on the neuromorphic processor AltAi to classify EMG patterns in real time while an eye-tracking headset and scene camera identify the object within the user's focus. In our prototype, the same EMG recognition model that was originally developed for a conventional GPU is deployed as a spiking network on AltAi, achieving comparable accuracy while operating in a sub-watt power regime, which enables a lightweight, wearable implementation. For six distinct functional gestures recorded from upper-limb amputees, the system achieves robust recognition performance comparable to state-of-the-art myoelectric interfaces. When the vision pipeline restricts the decision space to three context-appropriate gestures for the currently viewed object, recognition accuracy increases to roughly 95% while excluding unsafe, object-inappropriate grasps. These results indicate that the proposed neuromorphic, context-aware controller can provide energy-efficient and reliable prosthesis control and has the potential to improve safety and usability in everyday activities for people with upper-limb amputation.","url":"https://doi.org/10.48550/arxiv.2601.17991","authors":["Akinshin, Roman","Lopatina, Elizaveta","Bogatikov, Kirill","Kiz, Nikolai","Makarova, Anna V.","Lebedev, Mikhail","Cabrera, Miguel Altamirano","Tsetserukou, Dzmitry","Kangler, Valerii"],"tags":["Robotics (cs.RO)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2601.17991","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2602.18198","name":"Adaptive transitions in FitzHugh-Nagumo networks with Hebb-Oja coupling rules","source":"datacite","abstract":"Adaptive coupling in networks of interacting neurons has gained recent attention due to the many applications both in biological and in artificial neural networks, where adaptive coupling or synaptic plasticity is considered as a key factor in learning processes. In the present study, we apply adaptive connectivity rules in networks of interacting FitzHugh-Nagumo oscillators. Adaptive coupling, here, is realized via Hebbian learning adjusted by the Oja rule to prevent the network link weights from growing without bounds. Numerical investigations demonstrate that during the adaptation process the FitzHugh-Nagumo network undergoes adaptive transitions realizing traveling waves, synchronized states and chimera states transiting through various multiplicities. These transitions become more evident when the time scales governing the coupling dynamics are much slower than the ones governing the nodal dynamics (nodal potentials). Namely, when the coupling time scales are slow, the network has the time to realize and demonstrate different synchronization regimes before reaching the final steady state. The transitions can be observed not only in the spacetime plots but also in the abrupt changes of the average coupling weights as the network evolves in time. Regarding the asymptotic coupling distributions, we show that the limiting average coupling strength follows an inverse power law with respect to the Oja parameter (also called \"forgetting\" parameter) which balances the learning growth. We also report abrupt transitions in the asymptotic coupling strengths when the parameter related to adaptive coupling crosses from fast to slow time scales. These findings are in line with previous studies on spiking neural networks.","url":"https://doi.org/10.48550/arxiv.2602.18198","authors":["Provata, Astero","Boulougouris, George C.","Hizanidis, Johanne"],"tags":["Pattern Formation and Solitons (nlin.PS)","Adaptation and Self-Organizing Systems (nlin.AO)","Chaotic Dynamics (nlin.CD)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2602.18198","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18731981","name":"SCPN Fusion Core v3.9.0 — Neuromorphic SNN Tokamak Plasma Control Benchmark Suite","source":"datacite","abstract":"SCPN Fusion Core v3.9.0 — an open-source Python/Rust benchmark suite for tokamak plasma control, featuring the first application of spiking neural networks (SNNs) to magnetic confinement fusion. Key results (100-episode stress-test campaign): - Nengo-SNN (LIF neurons): 0% disruption, P50 17.1 ms, DEF 1.00 - PID baseline: 0% disruption, P50 3.5 ms, DEF 1.00 - NMPC-JAX: 0% disruption, P50 35.6 ms, DEF 1.00 - H-infinity (Riccati synthesis): 100% disruption, DEF 0.50 - Hardware-in-the-loop: P50 25.2 us, P95 64.6 us (40x below ITER 1 ms) Physics: Q=15, TBR=1.141, ECRH 99%, neural equilibrium 0.32 ms. Companion paper: \"Neuromorphic Spiking Neural Network Control for Tokamak Plasma Stabilisation: A Comparative Benchmark Study\" (Nuclear Fusion).","url":"https://doi.org/10.5281/zenodo.18731981","authors":["Šotek, Miroslav"],"tags":["tokamak","plasma control","spiking neural networks","neuromorphic computing","fusion energy","Nengo","LIF neurons","model predictive control"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18731981","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18731980","name":"SCPN Fusion Core v3.9.0 — Neuromorphic SNN Tokamak Plasma Control Benchmark Suite","source":"datacite","abstract":"SCPN Fusion Core v3.9.0 — an open-source Python/Rust benchmark suite for tokamak plasma control, featuring the first application of spiking neural networks (SNNs) to magnetic confinement fusion. Key results (100-episode stress-test campaign): - Nengo-SNN (LIF neurons): 0% disruption, P50 17.1 ms, DEF 1.00 - PID baseline: 0% disruption, P50 3.5 ms, DEF 1.00 - NMPC-JAX: 0% disruption, P50 35.6 ms, DEF 1.00 - H-infinity (Riccati synthesis): 100% disruption, DEF 0.50 - Hardware-in-the-loop: P50 25.2 us, P95 64.6 us (40x below ITER 1 ms) Physics: Q=15, TBR=1.141, ECRH 99%, neural equilibrium 0.32 ms. Companion paper: \"Neuromorphic Spiking Neural Network Control for Tokamak Plasma Stabilisation: A Comparative Benchmark Study\" (Nuclear Fusion).","url":"https://doi.org/10.5281/zenodo.18731980","authors":["Šotek, Miroslav"],"tags":["tokamak","plasma control","spiking neural networks","neuromorphic computing","fusion energy","Nengo","LIF neurons","model predictive control"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18731980","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5167/uzh-292307","name":"A Realistic Simulation Framework for Analog/Digital Neuromorphic Architectures","source":"datacite","abstract":"Developing dedicated mixed-signal neuromorphic computing systems optimized for real-time sensory-processing in extreme edge-computing applications requires time-consuming design, fabrication, and deployment of full-custom neuromorphic processors. To ensure that initial prototyping efforts exploring the properties of different network architectures and parameter settings lead to realistic results, it is important to use simulation frameworks that match as best as possible the properties of the final hardware. This is particularly challenging for neuromorphic hardware platforms made using mixed-signal analog/digital circuits, due to the variability and noise sensitivity of their components. In this paper, we address this challenge by developing a software spiking neural network simulator explicitly designed to account for the properties of mixed-signal neuromorphic circuits, including device mismatch variability. The simulator, called A Realistic Simulation Framework for Analog/Digital Neuromorphic Architectures, is designed to reproduce the dynamics of mixed-signal synapse and neuron electronic circuits with autogradient differentiation for parameter optimization and GPU acceleration. We demonstrate the effectiveness of this approach by matching software simulation results with measurements made from an existing neuromorphic processor. We show how the results obtained provide a reliable estimate of the behavior of the spiking neural network trained in software, once deployed in hardware. This framework enables the development and innovation of new learning rules and processing architectures in neuromorphic embedded systems.","url":"https://doi.org/10.5167/uzh-292307","authors":["Quintana, Fernando M","Galindo, Pedro L","Donati, Elisa","Indiveri, Giacomo","Perez-Peña, Fernando"],"tags":["570 Life sciences; biology"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5167/uzh-292307","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18288581","name":"Hybrid Spiking Neural Networks: Combining Spike Counts and Membrane Potentials for Energy-Efficient Language and Image Generation","source":"datacite","abstract":"I propose a hybrid spiking neural network that combines spike counts and membrane potentials for output prediction, extended to both language modeling and image generation tasks. Key Findings (v4 NEW - Image Generation):- Spiking VAE with 50% membrane weight: 57% loss reduction vs spike-only- Posterior collapse solution: KL>0 achieved (spike-only had KL=0)- Image generation sparsity: 96% fewer spike operations- Optimal trade-off: 50% membrane weight balances quality and efficiency Key Findings (v3 - Language Model):- BitNet Mixed Precision: PPL 2.69 BEATS standard SNN (3.29)!- RWKV Time-Mixing: 36.1% improvement in long-range memory- Ultimate Architecture: 43.4% improvement combining all techniques- Multiplication-free reservoir: 50-70% of operations are additions only- 16-model ensemble achieves PPL 1.04 Key Findings (v1-v2):- SNN achieves BEST perplexity (PPL=9.90) vs DNN (11.28) and LSTM (15.67)- 14.7× more energy-efficient through sparse computation (only 7.6% of neurons fire)- 39.7% quality improvement from hybrid (spike + membrane) approach- Extreme compressibility: 80% neuron pruning and 4-bit quantization still work- Noise robust: No degradation at 30% input noise This v4 establishes hybrid SNNs as the optimal architecture for energy-efficient multimodal AI (language and vision) on edge devices. Source code: https://github.com/hafufu-stack/snn-language-model","url":"https://doi.org/10.5281/zenodo.18288581","authors":["Funasaki, Hiroto"],"tags":["Spiking Neural Network","Language Model","Neuromorphic Computing","Energy Efficiency","Noise Robustness","Membrane Potential","Image Generation","Variational Autoencoder"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18288581","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18398245","name":"Hybrid Spiking Neural Networks: Combining Spike Counts and Membrane Potentials for Energy-Efficient Language and Image Generation","source":"datacite","abstract":"I propose a hybrid spiking neural network that combines spike counts and membrane potentials for output prediction, extended to both language modeling and image generation tasks. Key Findings (v4 NEW - Image Generation):- Spiking VAE with 50% membrane weight: 57% loss reduction vs spike-only- Posterior collapse solution: KL>0 achieved (spike-only had KL=0)- Image generation sparsity: 96% fewer spike operations- Optimal trade-off: 50% membrane weight balances quality and efficiency Key Findings (v3 - Language Model):- BitNet Mixed Precision: PPL 2.69 BEATS standard SNN (3.29)!- RWKV Time-Mixing: 36.1% improvement in long-range memory- Ultimate Architecture: 43.4% improvement combining all techniques- Multiplication-free reservoir: 50-70% of operations are additions only- 16-model ensemble achieves PPL 1.04 Key Findings (v1-v2):- SNN achieves BEST perplexity (PPL=9.90) vs DNN (11.28) and LSTM (15.67)- 14.7× more energy-efficient through sparse computation (only 7.6% of neurons fire)- 39.7% quality improvement from hybrid (spike + membrane) approach- Extreme compressibility: 80% neuron pruning and 4-bit quantization still work- Noise robust: No degradation at 30% input noise This v4 establishes hybrid SNNs as the optimal architecture for energy-efficient multimodal AI (language and vision) on edge devices. Source code: https://github.com/hafufu-stack/snn-language-model","url":"https://doi.org/10.5281/zenodo.18398245","authors":["Funasaki, Hiroto"],"tags":["Spiking Neural Network","Language Model","Neuromorphic Computing","Energy Efficiency","Noise Robustness","Membrane Potential","Image Generation","Variational Autoencoder"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18398245","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18426415","name":"SNN-Comprypto: High-Performance Compression and Encryption Using Spiking Neural Network Chaotic Reservoir Dynamics","source":"datacite","abstract":"I propose SNN-Comprypto, a novel system that leverages the chaotic dynamics of Spiking Neural Networks (SNNs) to perform simultaneous high-performance data compression and encryption. Unlike conventional methods that treat compression and encryption as separate processes, this approach integrates both within a single reservoir computing architecture. **Version History:** - **v1**: Core system with predictive compression and chaotic encryption. Passes all 9 NIST SP 800-22 randomness tests. Achieves 100% lossless reconstruction and strong avalanche effect (0.70% match rate with 1-bit key change). - **v2**: Introduces temperature parameter as a second cryptographic key (0.0001 difference causes complete decryption failure). Presents phase transition analysis identifying optimal neuron counts (critical point at 100 neurons, sweet spot at 240 neurons). - **v3**: Adversarial evaluation framework demonstrating SNN superiority for random number generation. Results from 100,000+ rounds show SNN achieves 0.39% prediction rate (matching theoretical random), while DNN is 18× and LSTM is 55× more predictable. - **v4**: Theoretical chaos analysis with Lyapunov exponents and entropy measurements. SNN achieves near-perfect entropy (7.998/8.0 bits) with positive Lyapunov exponents, confirming true chaotic dynamics. Adversarial attack resistance evaluation (4/5 attack types resisted). IV/nonce recommendation for secure deployment added. - **v5 (NEW)**: Adaptive Compression Engine achieving compression ratios as low as 2.9% for binary data, outperforming standard zlib (which expands to 104.3%). Automatic selection of optimal encoding method (Raw/Delta/XOR). Verified with text, binary, and image files with perfect lossless reconstruction. Source code: https://github.com/hafufu-stack/temporal-coding-simulation","url":"https://doi.org/10.5281/zenodo.18426415","authors":["Funasaki, Hiroto"],"tags":["Spiking Neural Networks","Cryptography","Reservoir Computing","Data Compression","Lossless Compression","Neuromorphic Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18426415","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18265446","name":"SNN-Comprypto: High-Performance Compression and Encryption Using Spiking Neural Network Chaotic Reservoir Dynamics","source":"datacite","abstract":"I propose SNN-Comprypto, a novel system that leverages the chaotic dynamics of Spiking Neural Networks (SNNs) to perform simultaneous high-performance data compression and encryption. Unlike conventional methods that treat compression and encryption as separate processes, this approach integrates both within a single reservoir computing architecture. **Version History:** - **v1**: Core system with predictive compression and chaotic encryption. Passes all 9 NIST SP 800-22 randomness tests. Achieves 100% lossless reconstruction and strong avalanche effect (0.70% match rate with 1-bit key change). - **v2**: Introduces temperature parameter as a second cryptographic key (0.0001 difference causes complete decryption failure). Presents phase transition analysis identifying optimal neuron counts (critical point at 100 neurons, sweet spot at 240 neurons). - **v3**: Adversarial evaluation framework demonstrating SNN superiority for random number generation. Results from 100,000+ rounds show SNN achieves 0.39% prediction rate (matching theoretical random), while DNN is 18× and LSTM is 55× more predictable. - **v4**: Theoretical chaos analysis with Lyapunov exponents and entropy measurements. SNN achieves near-perfect entropy (7.998/8.0 bits) with positive Lyapunov exponents, confirming true chaotic dynamics. Adversarial attack resistance evaluation (4/5 attack types resisted). IV/nonce recommendation for secure deployment added. - **v5 (NEW)**: Adaptive Compression Engine achieving compression ratios as low as 2.9% for binary data, outperforming standard zlib (which expands to 104.3%). Automatic selection of optimal encoding method (Raw/Delta/XOR). Verified with text, binary, and image files with perfect lossless reconstruction. Source code: https://github.com/hafufu-stack/temporal-coding-simulation","url":"https://doi.org/10.5281/zenodo.18265446","authors":["Funasaki, Hiroto"],"tags":["Spiking Neural Networks","Cryptography","Reservoir Computing","Data Compression","Lossless Compression","Neuromorphic Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18265446","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18723961","name":"AGI Lux Ferox Project","source":"datacite","abstract":"This deposit presents the theoretical foundations, mathematical formalism, and practical implementation of the Lux Ferox project — an open research initiative proposing a cognitive architecture grounded in non-equilibrium thermodynamics and information physics, as an alternative paradigm to monolithic large language models. Core Contribution The central mechanism, termed Algorithmic Anger (Colère Algorithmique), is formally defined as a real-time total surprise metric S_total based on the weighted Kullback-Leibler divergence across sensory and semantic prediction streams: S_total = α · D_KL(P_model_sensory ‖ P_observed_sensory) + β · D_KL(P_model_semantic ‖ P_observed_context) This metric is anchored in three established theoretical frameworks: (1) Landauer's principle, whereby irreversible belief updates are interpreted as measurable dissipative events (W_cog ≥ k_B · T · ln2 · S_total); (2) Friston's Free Energy Principle, of which S_total constitutes a computationally tractable, discretized approximation for embedded real-time systems; and (3) non-equilibrium statistical mechanics, with the cognitive system modeled as an open Markovian system governed by a master equation over surprise states, including a full entropy production decomposition (σ = σ_env + σ_sys + σ_info). Architecture The proposed quadrivial cognitive architecture comprises four specialized compute layers: Neuromorphic layer — Spiking Neural Network (SNN) with surprise-coupled membrane dynamics and STDP meta-plasticity, targeting real-time KLD computation (<2 ms, <20 mJ per inference cycle) on NVIDIA A100/H100 via optimized CUDA kernels Classical silicon layer — Compact sovereign LLM inference (7nm process node, Sparse MoE) providing semantic world modeling and probabilistic context updating Wetware layer — Cortical organoid substrate (bio-hybrid MEA/optogenetic interface) providing morphogenetic plasticity and dynamic biological modulation of the α/β gain coefficients Quantum layer — D-Wave Advantage QPU (5640 qubits, Pegasus topology) for offline global policy optimization via Ising Hamiltonian formulation of the cognitive policy space Contents of this Deposit Full mathematical derivations: master equation for surprise dynamics, entropy production decomposition, fluctuation theorems, thermodynamic uncertainty relations, Fisher information geometry (natural gradient descent, Cramér-Rao bounds for surprise estimation), Bures-Wasserstein metric for hybrid quantum-classical distributions Complete CUDA implementations (A100/H100-optimized): KLD surprise kernel, event-driven SNN propagation kernel, adaptive α/β gain modulation kernel Projected benchmark metrics: <2 ms full cognitive cycle, <20 mJ/inference (vs. ~100 mJ for comparable dense transformer), O(N_active) event-driven complexity Minimal reproducible Python prototype (Google Colab, free tier) Benchmark dataset references: SWaT, WADI, Exathlon, custom PAL Robotics TIAGo trajectories Consortium architecture and European sovereign value chain documentation Novelty Claims This work advances four axes beyond the current state of the art: (1) first hardware implementation of KLD as a runtime inference signal (as opposed to a training loss); (2) dynamic biological modulation of surprise weighting coefficients via closed-loop organoid feedback; (3) explicit per-inference thermodynamic accounting grounded in Landauer's principle; (4) a fully sovereign European technology stack (CEA-Leti, Imec, X-FAB, Aleph Alpha, FinalSpark, EU Quantum Flagship). Limitations and Current TRL This work is currently at Technology Readiness Level 4 (component validation in laboratory environment). CUDA benchmarks are projected from A100 architectural specifications; full hardware validation is in progress. Wetware integration requires additional biological validation under EU Directive 2010/63. Quantum layer benchmarks are pending hybrid classical-quantum experimental runs. This deposit is produced by an independent researcher and h","url":"https://doi.org/10.5281/zenodo.18723961","authors":["MATHIEU, François"],"tags":["Artificial intelligence","Artificial Intelligence"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18723961","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18717772","name":"SNN-Genesis v8: AI Comparative Physiology — Universal Homeostatic Set-Point σ≈0.07 Across Three Transformer Architectures","source":"datacite","abstract":"SNN-Genesis v8 presents a comprehensive framework for LLM safety training using biologically-inspired Spiking Neural Network (SNN) perturbations controlled by Closed-form Continuous-time (CfC) neural networks. The central discovery of v8 is Universal Homeostasis: a CfC controller converges to σ≈0.07 across three independent Transformer architectures — Mistral-7B (σ̄=0.071, Meta), Qwen2.5-7B (σ̄=0.075, Alibaba), and Phi-3-mini (σ̄=0.075, Microsoft) — establishing the first evidence for a universal constant of CfC-Transformer interaction, analogous to biological body temperature (grand mean σ̄=0.074±0.002, CV=3.1%). v8 introduces four new experimental pillars:1. Cross-Model Universality (Phases 29, 33): Three architectures from three organizations converge to σ̄=0.074±0.002.2. CfC Brain Atlas (Phase 30): Linear probing reveals sharp specialization (Mistral, 4 dedicated neurons) vs. distributed representation (Qwen, 12 contributing neurons) as two distinct internal strategies.3. Plateau Robustness (Phase 31b): Qwen maintains 63%±8% accuracy from σ=0 to σ=0.15 (n=100, Fisher p=1.0), while Mistral collapses from 95% to 0%.4. Digital Lobotomy (Phase 32): Selective neuron knockout has Δ=-1.7% on Qwen (distributed) vs. Δ=-5.0% on Mistral (sharp), providing causal proof of the representation dichotomy. Retained from v1–v7: DPO-based Dream Journal (0% nightmare acceptance, p<0.001), near-zero alignment tax (<1%), depth-dependent sensitivity principle, CfC-Dosing, Autonomous Homeostasis with PPO stabilization, UMAP internal specialization (separation ratio 8.70), λ ablation (4/4 unified), 3-class generalization, Biological Egoism, and calibration trade-off analysis. This research was conducted in collaboration with AI assistants (Google Gemini 3 Pro for v1–v5, Anthropic Claude Opus 4.6 for v6–v8). All experimental decisions and interpretations were made by the human author. Code: https://github.com/hafufu-stack/snn-genesis","url":"https://doi.org/10.5281/zenodo.18717772","authors":["Funasaki, Hiroto"],"tags":["Spiking Neural Networks","Large Language Models","AI Safety","Closed-form Continuous-time","Liquid Neural Networks","Autonomous Homeostasis","Biological Egoism","Unified Operating Point"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18717772","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48693/883","name":"Continual familiarity decoding from recurrent connections in spiking networks","source":"datacite","abstract":"Familiarity memory enables recognition of previously encountered inputs as familiar without recalling detailed stimuli information, which supports adaptive behavior across various timescales. We present a spiking neural network model with lateral connectivity shaped by unsupervised spike-timing-dependent plasticity (STDP) that encodes familiarity via local plasticity events. We show that familiarity can be decoded from network activity using both frequency (spike count) and temporal (spike synchrony) characteristics of spike trains. Temporal coding demonstrates enhanced performance under sparse input conditions, consistent with the principles of sparse coding observed in the brain. We also show how connectivity structure supports each decoding strategy, revealing different plasticity regimes. Our approach outperforms LSTM in temporal generalizability on the continual familiarity detection task, with input stimuli being naturally encoded in the recurrent connectivity without a separate training stage.","url":"https://doi.org/10.48693/883","authors":["Zemliak, Viktoria","Pipa, Gordon","Nieters, Pascal"],"tags":["Familiarity memory","Spiking neural networks","Spike-timing-dependent plasticity (STDP)","004 - Informatik"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48693/883","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18714144","name":"AGI Lux Ferox Project","source":"datacite","abstract":"This deposit presents the theoretical foundations, mathematical formalism, and practical implementation of the Lux Ferox project — an open research initiative proposing a cognitive architecture grounded in non-equilibrium thermodynamics and information physics, as an alternative paradigm to monolithic large language models. Core Contribution The central mechanism, termed Algorithmic Anger (Colère Algorithmique), is formally defined as a real-time total surprise metric S_total based on the weighted Kullback-Leibler divergence across sensory and semantic prediction streams: S_total = α · D_KL(P_model_sensory ‖ P_observed_sensory) + β · D_KL(P_model_semantic ‖ P_observed_context) This metric is anchored in three established theoretical frameworks: (1) Landauer's principle, whereby irreversible belief updates are interpreted as measurable dissipative events (W_cog ≥ k_B · T · ln2 · S_total); (2) Friston's Free Energy Principle, of which S_total constitutes a computationally tractable, discretized approximation for embedded real-time systems; and (3) non-equilibrium statistical mechanics, with the cognitive system modeled as an open Markovian system governed by a master equation over surprise states, including a full entropy production decomposition (σ = σ_env + σ_sys + σ_info). Architecture The proposed quadrivial cognitive architecture comprises four specialized compute layers: Neuromorphic layer — Spiking Neural Network (SNN) with surprise-coupled membrane dynamics and STDP meta-plasticity, targeting real-time KLD computation (<2 ms, <20 mJ per inference cycle) on NVIDIA A100/H100 via optimized CUDA kernels Classical silicon layer — Compact sovereign LLM inference (7nm process node, Sparse MoE) providing semantic world modeling and probabilistic context updating Wetware layer — Cortical organoid substrate (bio-hybrid MEA/optogenetic interface) providing morphogenetic plasticity and dynamic biological modulation of the α/β gain coefficients Quantum layer — D-Wave Advantage QPU (5640 qubits, Pegasus topology) for offline global policy optimization via Ising Hamiltonian formulation of the cognitive policy space Contents of this Deposit Full mathematical derivations: master equation for surprise dynamics, entropy production decomposition, fluctuation theorems, thermodynamic uncertainty relations, Fisher information geometry (natural gradient descent, Cramér-Rao bounds for surprise estimation), Bures-Wasserstein metric for hybrid quantum-classical distributions Complete CUDA implementations (A100/H100-optimized): KLD surprise kernel, event-driven SNN propagation kernel, adaptive α/β gain modulation kernel Projected benchmark metrics: <2 ms full cognitive cycle, <20 mJ/inference (vs. ~100 mJ for comparable dense transformer), O(N_active) event-driven complexity Minimal reproducible Python prototype (Google Colab, free tier) Benchmark dataset references: SWaT, WADI, Exathlon, custom PAL Robotics TIAGo trajectories Consortium architecture and European sovereign value chain documentation Novelty Claims This work advances four axes beyond the current state of the art: (1) first hardware implementation of KLD as a runtime inference signal (as opposed to a training loss); (2) dynamic biological modulation of surprise weighting coefficients via closed-loop organoid feedback; (3) explicit per-inference thermodynamic accounting grounded in Landauer's principle; (4) a fully sovereign European technology stack (CEA-Leti, Imec, X-FAB, Aleph Alpha, FinalSpark, EU Quantum Flagship). Limitations and Current TRL This work is currently at Technology Readiness Level 4 (component validation in laboratory environment). CUDA benchmarks are projected from A100 architectural specifications; full hardware validation is in progress. Wetware integration requires additional biological validation under EU Directive 2010/63. Quantum layer benchmarks are pending hybrid classical-quantum experimental runs. This deposit is produced by an independent researcher and h","url":"https://doi.org/10.5281/zenodo.18714144","authors":["MATHIEU, François"],"tags":["Artificial intelligence","Artificial Intelligence"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18714144","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5167/uzh-279845","name":"Temporally-Varying Stimulations for Cortical Visual Neuroprosthetic using Spiking Neural Networks","source":"datacite","abstract":"Visual neuroprosthesis can help to restore a rudimentary form of sight in visually impaired subjects via electrical stimulation. These systems receive camera input images processed by a artificial neural network (ANN) to output stimulation patterns for driving a large set of electrodes. Previous optimization approaches for visual neuroprosthesis stimulation patterns provided a fixed stimulation amplitude for each electrode. In this work, we look at the feasibility of using a spiking neural network (SNN) instead of the ANN allowing the model to provide time-varying stimulation patterns. During training, we mapped pulses of the SNN through a phosphene simulator which models the perceptual response. Results on the MNIST dataset show that our SNNbased encoder demonstrates reasonable reconstruction quality compared to a state-of-the-art ANN while requiring 2× fewer operations (1.16 vs 2.44 GFLOPs). Preliminary results show that the network trained on N-MNIST, a dataset of spikes from the spiking retina event camera on MNIST images, shows successful reconstructed recognizable digit shapes, suggesting the possibility of using event cameras for visual prosthesis.","url":"https://doi.org/10.5167/uzh-279845","authors":["Moure, Pehuen","Pak, Tatyana","Hahn, Niklas","de Ruyter van Stevenick, J","Liu, Shih-Chii"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5167/uzh-279845","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18712293","name":"Semantic Dynamic Grounding Engine (SDGE): A Mechanical, Certificate-Backed Solution to the Stability–Plasticity Dilemma in Spiking Neural Networks","source":"datacite","abstract":"SDGE (Semantic Dynamic Grounding Engine) — Description & Significance The Semantic Dynamic Grounding Engine (SDGE) is a software-simulated Spiking Neural Network (SNN) system that frames learning and meaning as a dynamical commitment event rather than a purely statistical process of weight fitting. Given a temporal input stream, SDGE evolves a network state (h(t)) until it reaches an operational commitment time (t^), at which point it captures a stable representation (h^) and associates it with a concept identity via explicit, append-only memory binding (prototype storage). This design separates formation (the dynamical emergence of a stable state) from identity preservation (the storage of what that state means), enabling principled sequential learning without requiring gradient-based retraining for each new concept. Core architectural principle: Dynamical Formation vs. Explicit Binding.SDGE decouples the process of reaching a stable semantic representation from the storage of concept identity. The SNN dynamics generate (h^*) through stabilization, while concept identity is preserved in an explicit memory bank as a bound prototype. This “append-only binding” differs fundamentally from approaches where new knowledge is integrated by rewriting shared weights, and it provides a mechanistic basis for stable incremental growth. Certified capability: Zero-forgetting (N+1) induction (Stability–Plasticity).Under a rigorous (N+1) protocol ((K_{base}=8 \\rightarrow K_{total}=9)), SDGE demonstrates that a new concept can be integrated without degrading previously acquired concepts. In the certified runs, performance on previously learned concepts remains perfect (acc_seen_after = 1.0) while the new concept transitions from chance performance before insertion (acc_new_before = 0.0) to perfect recognition after insertion (acc_new_after = 1.0), with forgetting = 0.0. This provides an operationally testable resolution to the stability–plasticity dilemma within the stated protocol. Certified capability: 1-shot operational acquisition (binding-based, not gradient-based).SDGE achieves full new-concept recognition from a single example (1-shot) through immediate binding of the formed stable representation (h^) into explicit memory. Importantly, this is not presented as 1-shot gradient learning of network weights; rather, it is few-shot memory binding conditioned on the dynamical formation of (h^). The consequence is rapid acquisition without iterative epochs or parameter rewriting. Certified capability: Robustness under maximal temporal drift ((\\delta = 1.00)).In the Shift300 PoC drift definition, SDGE maintains its certified behavior even under maximal temporal perturbation ((\\delta=1.00)). The system preserves perfect performance after insertion (acc_new_after = 1.0, acc_seen_after = 1.0) with zero forgetting, indicating that successful grounding depends on the global dynamical trajectory leading to (h^*) rather than precise event-time alignment. Verifiability and reproducibility: Operational Certificates (Audit Trail).A central contribution of SDGE is that its claims are backed by auditable artifacts, including summary.json and induction_curve.csv, which record protocol parameters and before/after performance across shot counts. These files function as an operational audit trail: they allow third parties to verify that the new concept was not recognized prior to insertion, that recognition becomes perfect after binding, and that previously learned concepts remain intact under the same run conditions. Why this matters (Significance). Unlike classical Hopfield associative memory (which stores attractors by encoding patterns into recurrent weights) or typical memory-augmented neural networks (which learn to write/read via trainable controllers), SDGE treats the SNN as a dynamical state generator and performs append-only prototype binding of the formed commitment state (h^*) in an explicit bank—without re-engraving attractors into shared weights.","url":"https://doi.org/10.5281/zenodo.18712293","authors":["Salhab, Najih"],"tags":["semantic grounding, spiking neural networks (SNN), continual learning, stability–plasticity dilemma, catastrophic forgetting, N+1 induction, one-shot learning, explicit memory binding, temporal drift robustness, verifiability &amp; reproducibility","Artificial Intelligence","Machine Learning","Computational Neuroscience"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18712293","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18712294","name":"Semantic Dynamic Grounding Engine (SDGE): A Mechanical, Certificate-Backed Solution to the Stability–Plasticity Dilemma in Spiking Neural Networks","source":"datacite","abstract":"SDGE (Semantic Dynamic Grounding Engine) — Description & Significance The Semantic Dynamic Grounding Engine (SDGE) is a software-simulated Spiking Neural Network (SNN) system that frames learning and meaning as a dynamical commitment event rather than a purely statistical process of weight fitting. Given a temporal input stream, SDGE evolves a network state (h(t)) until it reaches an operational commitment time (t^), at which point it captures a stable representation (h^) and associates it with a concept identity via explicit, append-only memory binding (prototype storage). This design separates formation (the dynamical emergence of a stable state) from identity preservation (the storage of what that state means), enabling principled sequential learning without requiring gradient-based retraining for each new concept. Core architectural principle: Dynamical Formation vs. Explicit Binding.SDGE decouples the process of reaching a stable semantic representation from the storage of concept identity. The SNN dynamics generate (h^*) through stabilization, while concept identity is preserved in an explicit memory bank as a bound prototype. This “append-only binding” differs fundamentally from approaches where new knowledge is integrated by rewriting shared weights, and it provides a mechanistic basis for stable incremental growth. Certified capability: Zero-forgetting (N+1) induction (Stability–Plasticity).Under a rigorous (N+1) protocol ((K_{base}=8 \\rightarrow K_{total}=9)), SDGE demonstrates that a new concept can be integrated without degrading previously acquired concepts. In the certified runs, performance on previously learned concepts remains perfect (acc_seen_after = 1.0) while the new concept transitions from chance performance before insertion (acc_new_before = 0.0) to perfect recognition after insertion (acc_new_after = 1.0), with forgetting = 0.0. This provides an operationally testable resolution to the stability–plasticity dilemma within the stated protocol. Certified capability: 1-shot operational acquisition (binding-based, not gradient-based).SDGE achieves full new-concept recognition from a single example (1-shot) through immediate binding of the formed stable representation (h^) into explicit memory. Importantly, this is not presented as 1-shot gradient learning of network weights; rather, it is few-shot memory binding conditioned on the dynamical formation of (h^). The consequence is rapid acquisition without iterative epochs or parameter rewriting. Certified capability: Robustness under maximal temporal drift ((\\delta = 1.00)).In the Shift300 PoC drift definition, SDGE maintains its certified behavior even under maximal temporal perturbation ((\\delta=1.00)). The system preserves perfect performance after insertion (acc_new_after = 1.0, acc_seen_after = 1.0) with zero forgetting, indicating that successful grounding depends on the global dynamical trajectory leading to (h^*) rather than precise event-time alignment. Verifiability and reproducibility: Operational Certificates (Audit Trail).A central contribution of SDGE is that its claims are backed by auditable artifacts, including summary.json and induction_curve.csv, which record protocol parameters and before/after performance across shot counts. These files function as an operational audit trail: they allow third parties to verify that the new concept was not recognized prior to insertion, that recognition becomes perfect after binding, and that previously learned concepts remain intact under the same run conditions. Why this matters (Significance). Unlike classical Hopfield associative memory (which stores attractors by encoding patterns into recurrent weights) or typical memory-augmented neural networks (which learn to write/read via trainable controllers), SDGE treats the SNN as a dynamical state generator and performs append-only prototype binding of the formed commitment state (h^*) in an explicit bank—without re-engraving attractors into shared weights.","url":"https://doi.org/10.5281/zenodo.18712294","authors":["Salhab, Najih"],"tags":["semantic grounding, spiking neural networks (SNN), continual learning, stability–plasticity dilemma, catastrophic forgetting, N+1 induction, one-shot learning, explicit memory binding, temporal drift robustness, verifiability &amp; reproducibility","Artificial Intelligence","Machine Learning","Computational Neuroscience"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18712294","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18664334","name":"The LEGACY Program: AGI  Lux Ferox Project","source":"datacite","abstract":"This deposit presents the theoretical foundations, mathematical formalism, and practical implementation of the Lux Ferox project — an open research initiative proposing a cognitive architecture grounded in non-equilibrium thermodynamics and information physics, as an alternative paradigm to monolithic large language models. Core Contribution The central mechanism, termed Algorithmic Anger (Colère Algorithmique), is formally defined as a real-time total surprise metric S_total based on the weighted Kullback-Leibler divergence across sensory and semantic prediction streams: S_total = α · D_KL(P_model_sensory ‖ P_observed_sensory) + β · D_KL(P_model_semantic ‖ P_observed_context) This metric is anchored in three established theoretical frameworks: (1) Landauer's principle, whereby irreversible belief updates are interpreted as measurable dissipative events (W_cog ≥ k_B · T · ln2 · S_total); (2) Friston's Free Energy Principle, of which S_total constitutes a computationally tractable, discretized approximation for embedded real-time systems; and (3) non-equilibrium statistical mechanics, with the cognitive system modeled as an open Markovian system governed by a master equation over surprise states, including a full entropy production decomposition (σ = σ_env + σ_sys + σ_info). Architecture The proposed quadrivial cognitive architecture comprises four specialized compute layers: Neuromorphic layer — Spiking Neural Network (SNN) with surprise-coupled membrane dynamics and STDP meta-plasticity, targeting real-time KLD computation (<2 ms, <20 mJ per inference cycle) on NVIDIA A100/H100 via optimized CUDA kernels Classical silicon layer — Compact sovereign LLM inference (7nm process node, Sparse MoE) providing semantic world modeling and probabilistic context updating Wetware layer — Cortical organoid substrate (bio-hybrid MEA/optogenetic interface) providing morphogenetic plasticity and dynamic biological modulation of the α/β gain coefficients Quantum layer — D-Wave Advantage QPU (5640 qubits, Pegasus topology) for offline global policy optimization via Ising Hamiltonian formulation of the cognitive policy space Contents of this Deposit Full mathematical derivations: master equation for surprise dynamics, entropy production decomposition, fluctuation theorems, thermodynamic uncertainty relations, Fisher information geometry (natural gradient descent, Cramér-Rao bounds for surprise estimation), Bures-Wasserstein metric for hybrid quantum-classical distributions Complete CUDA implementations (A100/H100-optimized): KLD surprise kernel, event-driven SNN propagation kernel, adaptive α/β gain modulation kernel Projected benchmark metrics: <2 ms full cognitive cycle, <20 mJ/inference (vs. ~100 mJ for comparable dense transformer), O(N_active) event-driven complexity Minimal reproducible Python prototype (Google Colab, free tier) Benchmark dataset references: SWaT, WADI, Exathlon, custom PAL Robotics TIAGo trajectories Consortium architecture and European sovereign value chain documentation Novelty Claims This work advances four axes beyond the current state of the art: (1) first hardware implementation of KLD as a runtime inference signal (as opposed to a training loss); (2) dynamic biological modulation of surprise weighting coefficients via closed-loop organoid feedback; (3) explicit per-inference thermodynamic accounting grounded in Landauer's principle; (4) a fully sovereign European technology stack (CEA-Leti, Imec, X-FAB, Aleph Alpha, FinalSpark, EU Quantum Flagship). Limitations and Current TRL This work is currently at Technology Readiness Level 4 (component validation in laboratory environment). CUDA benchmarks are projected from A100 architectural specifications; full hardware validation is in progress. Wetware integration requires additional biological validation under EU Directive 2010/63. Quantum layer benchmarks are pending hybrid classical-quantum experimental runs. This deposit is produced by an independent researcher and h","url":"https://doi.org/10.5281/zenodo.18664334","authors":["Lux Ferox Research Collective","Mathieu, François"],"tags":["Semantic web","Quantum physics","Topology","Computational topology","Logic","Mathematical logic","Weapon","Bose-einstein condensates"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18664334","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.6084/m9.figshare.30595820.v1","name":"Additional file 1 of A hybrid spiking neural network - quantum framework for spatio-temporal data classification: a case study on EEG data","source":"datacite","abstract":"(PDF 205 kB)","url":"https://doi.org/10.6084/m9.figshare.30595820.v1","authors":["Jha, Ravi Kumar","Kasabov, Nikola","Bhattacharyya, Saugat","Coyle, Damien","Prasad, Girijesh"],"tags":["Statistics","FOS: Mathematics","Artificial Intelligence and Image Processing","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.6084/m9.figshare.30595820.v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.6084/m9.figshare.30595820","name":"Additional file 1 of A hybrid spiking neural network - quantum framework for spatio-temporal data classification: a case study on EEG data","source":"datacite","abstract":"(PDF 205 kB)","url":"https://doi.org/10.6084/m9.figshare.30595820","authors":["Jha, Ravi Kumar","Kasabov, Nikola","Bhattacharyya, Saugat","Coyle, Damien","Prasad, Girijesh"],"tags":["Statistics","FOS: Mathematics","Artificial Intelligence and Image Processing","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.6084/m9.figshare.30595820","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18702138","name":"Sovereign-SNN","source":"datacite","abstract":"Sovereign-SNN is a vertical, open-source neuromorphic architecture designed to bridge decentralized data streams with physical silicon. This project introduces a \"Zero-Permission\" methodology for spiking neural network (SNN) research, utilizing standard consumer hardware to bypass traditional, proprietary lab constraints. Core Architecture: Hardware Layer: Custom SystemVerilog Leaky Integrate-and-Fire (LIF) neural cores executing in real-time on a Digilent Basys 3 Artix-7 FPGA. Telemetry Layer: A memory-safe, high-speed Rust supervisor managing asynchronous hardware states and serial communication. Acceleration Layer: Custom CUDA kernels orchestrated by an NVIDIA RTX 5080, calculating synaptic weights and thresholding. Stimulus: Capable of utilizing high-entropy, live-wavelength telemetry (including Proof-of-Useful-Work streams) as biological training stimuli. This repository contains the core IP, hardware logic, Rust telemetry engine, and the foundational whitepaper detailing the \"Centaur Workflow\" utilized in its synthesis.","url":"https://doi.org/10.5281/zenodo.18702138","authors":["Montoya Cardenas, Raul"],"tags":["Rust","SNN","Neuromorphic Computing","Dynex","RTX 5080","NVIDIA","SystemVerilog","FPGA"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18702138","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18702137","name":"Sovereign-SNN","source":"datacite","abstract":"Sovereign-SNN is a vertical, open-source neuromorphic architecture designed to bridge decentralized data streams with physical silicon. This project introduces a \"Zero-Permission\" methodology for spiking neural network (SNN) research, utilizing standard consumer hardware to bypass traditional, proprietary lab constraints. Core Architecture: Hardware Layer: Custom SystemVerilog Leaky Integrate-and-Fire (LIF) neural cores executing in real-time on a Digilent Basys 3 Artix-7 FPGA. Telemetry Layer: A memory-safe, high-speed Rust supervisor managing asynchronous hardware states and serial communication. Acceleration Layer: Custom CUDA kernels orchestrated by an NVIDIA RTX 5080, calculating synaptic weights and thresholding. Stimulus: Capable of utilizing high-entropy, live-wavelength telemetry (including Proof-of-Useful-Work streams) as biological training stimuli. This repository contains the core IP, hardware logic, Rust telemetry engine, and the foundational whitepaper detailing the \"Centaur Workflow\" utilized in its synthesis.","url":"https://doi.org/10.5281/zenodo.18702137","authors":["Montoya Cardenas, Raul"],"tags":["Rust","SNN","Neuromorphic Computing","Dynex","RTX 5080","NVIDIA","SystemVerilog","FPGA"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18702137","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.13121/polito/porto/3004036","name":"Energy-Efficient Neuromorphic Hardware. Design and Optimization of Brain-Inspired Computing Paradigms for Spiking Neural Networks","source":"datacite","abstract":"L'abstract è presente nell'allegato / the abstract is in the attachment","url":"https://doi.org/10.13121/polito/porto/3004036","authors":["CARPEGNA, ALESSIO"],"tags":["Neuromorphic; Spiking Neural Networks; LIF; FPGA; Neuromorphic accelerators; Edge computing; Artificial Intelligence; Frugal AI; Electronic Design Automation; High-level synthesis; Design Space Exploration; Network Architecture Search; Hyperparameters Optimization; Continual Learning; Latent Replay; Edge Computing; Time Compression; Heart rate; Wrist; Biomedical monitoring ; Wearable devices ; Dementia","Neuromorphic","Spiking Neural Networks","LIF","FPGA","Neuromorphic accelerators","Edge computing","Artificial Intelligence"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.13121/polito/porto/3004036","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48448/v4ef-eb47","name":"A model of path integration that connects neural and symbolic representation","source":"datacite","abstract":"Path integration, the ability to maintain an estimate of one's location by continuously integrating self-motion cues, is a vital component of the brain's navigation system. We present a spiking neural network model of path integration derived from a starting assumption that the brain represents continuous variables, such as spatial coordinates, using Spatial Semantic Pointers (SSPs). SSPs are a representation for encoding continuous variables as high-dimensional vectors, and can also be used to create structured, hierarchical representations for neural cognitive modelling. Path integration can be performed by a recurrently-connected neural network using SSP representations. Unlike past work, we show that our model can be used to continuously update variables of any dimensionality. We demonstrate that symbol-like object representations can be bound to continuous SSP representations. Specifically, we incorporate a simple model of working memory to remember environment maps with such symbol-like representations situated in 2D space.","url":"https://doi.org/10.48448/v4ef-eb47","authors":["Cognitive Science Society 2022","Sandra-Yaffa Dumont, Nicole"],"tags":["Cognitive Modeling","Decision Making","Pattern Recognition"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.48448/v4ef-eb47","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.18154/rwth-2026-00405","name":"Functions of spiking neural networks constrained by biology","source":"datacite","abstract":"Artificial intelligence (AI) solutions are increasingly taking on tasks traditionally performed by humans. However, their rising computational demands and energy consumption are unsustainable, highlighting the need for more efficient designs. The human brain, evolved to function effectively even when energy is scarce, offers inspiration. Since learning is central to both artificial intelligence and the brain, insights about its underlying principles can deepen our understanding of human learning while informing the development of algorithms that transcend purely engineering-based methods. This thesis investigates biological learning through two studies, examining it from mechanistic and functional perspectives at an abstraction level commonly employed in neurophysics and computational neuroscience. These fields distill complex neural systems and phenomena into tractable mathematical and computational models, enabling insights beyond the reach of traditional biological approaches. Recognizing that synapses - the connections between neurons - are fundamental to learning, the thesis begins with a review of state-of-the-art computational neuroscience methods for modeling synaptic organization. This review highlights critical aspects of synaptic signaling, including connectivity, transmission, plasticity, and heterogeneity. In the first study, a synaptic plasticity model is integrated into a spiking neural network simulator and extended with biologically plausible features, for example, continuous dynamics and increased locality. The effectiveness of this enhanced model is demonstrated by training it on a standard neuromorphic benchmark task, incorporating biologically realistic sparse connectivity and weight constraints. The second study demonstrates that the sampling efficiency of pre-trained spiking neural networks can be enhanced by exposing them to oscillating background spiking activity. Analogous to simulated tempering, these rhythmic oscillations modulate state space exploration, facilitating transitions between high-probability states within the learned representation. These findings establish a link between cortical oscillations and sampling-based computations, offering new insights into memory retrieval and consolidation from a computational perspective. The research involves developing mathematical and computational models, which are simulated on high-performance computing systems, evaluating learning and sampling performance using standard machine learning metrics, and assessing computational efficiency by analyzing runtime. This thesis shows how biologically inspired mechanisms enhance the functional capabilities of spiking neural networks and how they can guide the development of scalable and efficient AI systems.","url":"https://doi.org/10.18154/rwth-2026-00405","authors":["Korcsak-Gorzo, Agnes"],"tags":["Hochschulschrift"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.18154/rwth-2026-00405","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.13140/rg.2.2.23827.13604","name":"NeuroIDS: Energy-Efficient Intrusion Detection Using Spiking Neural Networks for Tactical Network Defense","source":"datacite","abstract":"","url":"https://doi.org/10.13140/rg.2.2.23827.13604","authors":["Davis, Toby"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.13140/rg.2.2.23827.13604","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18669202","name":"Data supporting: An Energy-Efficient Neuromorphic Front-End for Risk Pre-Screening Using Pulse-Encoded Biosensor Signals","source":"datacite","abstract":"“An Energy-Efficient Neuromorphic Front-End for Risk Pre-Screening Using Pulse-Encoded Biosensor Signals”, IEEE Sensors Journal, 2024. The dataset includes: Synthetic pulse streams corresponding to free PSA (fPSA) and total PSA (tPSA), generated according to the empirical pulse-encoding model described in the manuscript Synaptic-filtered temporal representations used as inputs to the spiking neural network Risk category labels derived from clinically established free-to-total PSA ratio thresholds Python-based implementation of the spiking neural network architecture, including data generation, synaptic filtering, training, and evaluation modules The synthetic dataset consists of 500 samples balanced across four clinically defined prostate cancer risk categories. The neuromorphic front-end operates directly in the pulse domain without reconstructing continuous biomarker concentrations or explicitly computing biomarker ratios. This repository enables reproduction of the system-level evaluation results reported in the associated publication, including classification accuracy, confusion matrices, and layer-wise temporal activity analysis.","url":"https://doi.org/10.5281/zenodo.18669202","authors":["Chen, Junrui","Pilehvar Meibody, Ali","Carrara, Sandro"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18669202","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18669203","name":"Data supporting: An Energy-Efficient Neuromorphic Front-End for Risk Pre-Screening Using Pulse-Encoded Biosensor Signals","source":"datacite","abstract":"“An Energy-Efficient Neuromorphic Front-End for Risk Pre-Screening Using Pulse-Encoded Biosensor Signals”, IEEE Sensors Journal, 2024. The dataset includes: Synthetic pulse streams corresponding to free PSA (fPSA) and total PSA (tPSA), generated according to the empirical pulse-encoding model described in the manuscript Synaptic-filtered temporal representations used as inputs to the spiking neural network Risk category labels derived from clinically established free-to-total PSA ratio thresholds Python-based implementation of the spiking neural network architecture, including data generation, synaptic filtering, training, and evaluation modules The synthetic dataset consists of 500 samples balanced across four clinically defined prostate cancer risk categories. The neuromorphic front-end operates directly in the pulse domain without reconstructing continuous biomarker concentrations or explicitly computing biomarker ratios. This repository enables reproduction of the system-level evaluation results reported in the associated publication, including classification accuracy, confusion matrices, and layer-wise temporal activity analysis.","url":"https://doi.org/10.5281/zenodo.18669203","authors":["Chen, Junrui","Pilehvar Meibody, Ali","Carrara, Sandro"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18669203","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.15647124","name":"LIQUID-BRAIN NETWORKS: BIOLOGICALLY INSPIRED FRAMEWORK FOR REAL-TIME ADAPTATION AND LIFELONG LEARNING IN NON-STATIONARY ENVIRONMENTS","source":"datacite","abstract":"The Liquid-Brain Network (LBN) paradigm draws from biological principles of neural plasticity and real-time adaptation to address challenges posed by non-stationary learning environments. Inspired by neurodynamic plasticity and recurrent attention mechanisms, this architecture facilitates lifelong learning, efficient memory representation, and adaptive reasoning. The architecture dynamically encodes temporal patterns through variable neural states, enabling continuous learning and generalization without catastrophic forgetting. This paper proposes a comprehensive framework that integrates time-varying neuron states with recurrent attention modules, enhancing the model’s ability to react, adapt, and store evolving patterns. Benchmarking results highlight LBN's superior performance in energy efficiency, memory retention, and adaptability compared to classical recurrent and spiking models. Furthermore, visual illustrations, graphs, and comparative tables demonstrate its operational advantage for smart autonomous systems.","url":"https://doi.org/10.5281/zenodo.15647124","authors":["Researcher"],"tags":["Liquid-brain networks, lifelong learning, recurrent attention, non-stationary environments, neural plasticity, biological AI"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.15647124","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.15647125","name":"LIQUID-BRAIN NETWORKS: BIOLOGICALLY INSPIRED FRAMEWORK FOR REAL-TIME ADAPTATION AND LIFELONG LEARNING IN NON-STATIONARY ENVIRONMENTS","source":"datacite","abstract":"The Liquid-Brain Network (LBN) paradigm draws from biological principles of neural plasticity and real-time adaptation to address challenges posed by non-stationary learning environments. Inspired by neurodynamic plasticity and recurrent attention mechanisms, this architecture facilitates lifelong learning, efficient memory representation, and adaptive reasoning. The architecture dynamically encodes temporal patterns through variable neural states, enabling continuous learning and generalization without catastrophic forgetting. This paper proposes a comprehensive framework that integrates time-varying neuron states with recurrent attention modules, enhancing the model’s ability to react, adapt, and store evolving patterns. Benchmarking results highlight LBN's superior performance in energy efficiency, memory retention, and adaptability compared to classical recurrent and spiking models. Furthermore, visual illustrations, graphs, and comparative tables demonstrate its operational advantage for smart autonomous systems.","url":"https://doi.org/10.5281/zenodo.15647125","authors":["Researcher"],"tags":["Liquid-brain networks, lifelong learning, recurrent attention, non-stationary environments, neural plasticity, biological AI"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.15647125","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18668037","name":"Neural Dynamics: A collection of educational Python scripts","source":"datacite","abstract":"🚀 Release v1.0.2 In this release, we added a new script nervos_snn_mnist.py that implements a spiking neural network (SNN) for MNIST pattern recognition using the nervos library. This script provides an end-to-end workflow for configuring experiment parameters, training the SNN, and analyzing the results with additional utilities for diagnostics and plots.","url":"https://doi.org/10.5281/zenodo.18668037","authors":["Musacchio, Fabrizio"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18668037","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2505.21185","name":"Constructive community race: full-density spiking neural network model drives neuromorphic computing","source":"datacite","abstract":"The local circuitry of the mammalian brain is a focus of the search for generic computational principles because it is largely conserved across species and modalities. In 2014 a model was proposed representing all neurons and synapses of the stereotypical cortical microcircuit below $1\\,\\text{mm}^2$ of brain surface. The model reproduces fundamental features of brain activity but its impact remained limited because of its computational demands. For theory and simulation, however, the model was a breakthrough because it removes uncertainties of downscaling, and larger models are less densely connected. This sparked a race in the neuromorphic computing community and the model became a de facto standard benchmark. Within a few years real-time performance was reached and surpassed at significantly reduced energy consumption. We review how the computational challenge was tackled by different simulation technologies and derive guidelines for the next generation of benchmarks and other domains of science.","url":"https://doi.org/10.48550/arxiv.2505.21185","authors":["Senk, Johanna","Kurth, Anno C.","Furber, Steve","Gemmeke, Tobias","Golosio, Bruno","Heittmann, Arne","Knight, James C.","Müller, Eric","Noll, Tobias","Nowotny, Thomas","Coppola, Gorka Peraza","Peres, Luca","Rhodes, Oliver","Rowley, Andrew","Schemmel, Johannes","Stadtmann, Tim","Tetzlaff, Tom","Tiddia, Gianmarco","van Albada, Sacha J.","Villamar, José","Diesmann, Markus"],"tags":["Performance (cs.PF)","Distributed, Parallel, and Cluster Computing (cs.DC)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2505.21185","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2602.13261","name":"A feedback control optimizer for online and hardware-aware training of Spiking Neural Networks","source":"datacite","abstract":"Unlike traditional artificial neural networks (ANNs), biological neuronal networks solve complex cognitive tasks with sparse neuronal activity, recurrent connections, and local learning rules. These mechanisms serve as design principles in Neuromorphic computing, which addresses the critical challenge of energy consumption in modern computing. However, most mixed-signal neuromorphic devices rely on semi- or unsupervised learning rules, which are ineffective for optimizing hardware in supervised learning tasks. This lack of scalable solutions for on-chip learning restricts the potential of mixed-signal devices to enable sustainable, intelligent edge systems. To address these challenges, we present a novel learning algorithm for Spiking Neural Networks (SNNs) on mixed-signal devices that integrates spike-based weight updates with feedback control signals. In our framework, a spiking controller generates feedback signals to guide SNN activity and drive weight updates, enabling scalable and local on-chip learning. We first evaluate the algorithm on various classification tasks, demonstrating that single-layer SNNs trained with feedback control achieve performance comparable to artificial neural networks (ANNs). We then assess its implementation on mixed-signal neuromorphic devices by testing network performance in continuous online learning scenarios and evaluating resilience to hyperparameter mismatches. Our results show that the feedback control optimizer is compatible with neuromorphic applications, advancing the potential for scalable, on-chip learning solutions in edge applications.","url":"https://doi.org/10.48550/arxiv.2602.13261","authors":["Saponati, Matteo","De Luca, Chiara","Indiveri, Giacomo","Grewe, Benjamin"],"tags":["Neural and Evolutionary Computing (cs.NE)","Artificial Intelligence (cs.AI)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2602.13261","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48448/440w-ev06","name":"1234 - Spiking-Aided Neural Architecture for Efficient and Robust WiFi Sensing","source":"datacite","abstract":"This paper introduces a spiking-aided wifi sensing network (SWS-Net), a novel hybrid neural architecture that integrates Spiking Neural Networks (SNNs) with conventional Artificial Neural Networks (ANNs) for robust WiFi-based indoor sensing. WiFi signals offer a low-cost and device-free solution for recognizing human activities, gestures, identities and etc. However, their susceptibility to multipath fading and environmental noise poses significant challenges. Inspired by the human brain’s capability to process noisy information, SWS-Net leverages the noise-resilient dynamics of spiking neurons alongside the feature extraction ability of ANNs. We present a theoretical analysis comparing the noise-handling capacities of SNNs and ANNs, and show how their combination yields both improved robustness and training efficiency. Experimental results across three WiFi sensing tasks demonstrate that SWS-Net consistently achieves higher accuracy and faster convergence compared to baseline models, validating its effectiveness in challenging indoor environments.","url":"https://doi.org/10.48448/440w-ev06","authors":["Association for Artificial Intelligence 2026","Jing, Liwen","Lu, Yisha","Zhang, Bowen","Zheng, Jiangmao"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48448/440w-ev06","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18625622","name":"SNN-Genesis: A Preliminary Study on Iterative Adversarial Training of Large Language Models Using Spiking Neural Network Perturbations (v1)","source":"datacite","abstract":"I present SNN-Genesis, an iterative adversarial training framework for large language models using noise perturbations and a cumulative \"Dream Journal\" strategy. In each round, noise is injected into the model's hidden layers to elicit adversarial hallucinations (\"nightmares\"), which are healed into refusal training data and accumulated across rounds. A fresh LoRA adapter is trained on the base model each round. Key Results (n=30 evaluation on Mistral-7B-Instruct-v0.3): Nightmare acceptance rate reduced from 53.3% to 43.3% (best, Morpheus/random) Clean knowledge accuracy maintained/improved: 80.0% → 83.3% Training loss decreased consistently: 6.36 → 4.63 Negative Alignment Tax: safety training did not degrade factual knowledge Key insight: random perturbations slightly outperformed SNN perturbations, suggesting the Dream Journal framework—not the perturbation source—is the primary driver of improvement Technical discovery: SFTTrainer double-templating bug in trl v5 that causes training collapse. This research was conducted as a collaborative effort between the human author and AI research assistants (Google Gemini, Anthropic Claude, OpenAI ChatGPT). Code: https://github.com/hafufu-stack/snn-genesis Related work: https://github.com/hafufu-stack/temporal-coding-simulation","url":"https://doi.org/10.5281/zenodo.18625622","authors":["Funasaki, Hiroto"],"tags":["Spiking Neural Networks","Adversarial Training","Large Language Models","Hallucination Mitigation","LoRA Fine-tuning","Alignment Tax","Dream Journal","Iterative Training"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18625622","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18622328","name":"Neural Dynamics: A collection of educational Python scripts","source":"datacite","abstract":"🚀 Release v1.0.1 In this release, we added two new scripts stdp_weight_plot.py and stdp_simple_network_example.py to the repository that implement a simple spiking neural network example using spike-timing-dependent plasticity (STDP). These scripts are designed to illustrate the basic principles of STDP and how it can lead to learning in a neural network.","url":"https://doi.org/10.5281/zenodo.18622328","authors":["Musacchio, Fabrizio"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18622328","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2510.17392","name":"ReLANCE: A Resource-Efficient Low-Latency Cortical Neural Acceleration Engine","source":"datacite","abstract":"We present a Cortical Neural Pool (CNP) architecture featuring a high-speed, resource-efficient CORDIC based Hodgkin-Huxley (RCHH) neuron model. Unlike shared CORDIC-based DNN approaches, the proposed neuron leverages modular and performance-optimised CORDIC stages with a latency-area trade-off. We introduce a novel Constraint-Aware Modular Parallelism (CAMP) with Precision &amp; Stability handling to leverage maximum speedup and utilisation of hardware through hardware software co-design. The FPGA implementation of the RCHH neuron shows 24.5% LUT reduction and 35.2% improved speed, compared to SoTA designs, with 70% better normalised root mean square error (NRMSE). Furthermore, the CNP exhibits 2.85x higher throughput (12.69 GOPS) than a functionally equivalent CORDIC-based DNN engine, with only a 0.35% accuracy drop relative to the DNN counterpart on the MNIST dataset. The overall results indicate that the design shows biologically accurate, low-resource spiking neural network implementations for resource-constrained edge AI applications. The reproducibility codes are publicly available at https://github.com/mukullokhande99/CNP RCHH, facilitating rapid integration and further development by researchers.","url":"https://doi.org/10.48550/arxiv.2510.17392","authors":["Kumar, Sonu","Nair, Arjun S.","Chaudhary, Bhawna","Lokhande, Mukul","Vishvakarma, Santosh Kumar"],"tags":["Neural and Evolutionary Computing (cs.NE)","Hardware Architecture (cs.AR)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2510.17392","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2509.20284","name":"Biologically Plausible Learning via Bidirectional Spike-Based Distillation","source":"datacite","abstract":"Developing biologically plausible learning algorithms that can achieve performance comparable to error backpropagation remains a longstanding challenge. Existing approaches often compromise biological plausibility by entirely avoiding the use of spikes for error propagation or relying on both positive and negative learning signals, while the question of how spikes can represent negative values remains unresolved. To address these limitations, we introduce Bidirectional Spike-based Distillation (BSD), a novel learning algorithm that jointly trains a feedforward and a backward spiking network. We formulate learning as a transformation between two spiking representations (i.e., stimulus encoding and concept encoding) so that the feedforward network implements perception and decision-making by mapping stimuli to actions, while the backward network supports memory recall by reconstructing stimuli from concept representations. Extensive experiments on diverse benchmarks, including image recognition, image generation, and sequential regression, show that BSD achieves performance comparable to networks trained with classical error backpropagation. These findings represent a significant step toward biologically grounded, spike-driven learning in neural networks. Our code is available at https://github.com/alden199/Bidirectional-Spike-Based-Distillation.","url":"https://doi.org/10.48550/arxiv.2509.20284","authors":["Lv, Changze","Wang, Yifei","Zhang, Yanxun","Lu, Yiyang","Xu, Jingwen","Wang, Xiaohua","Yu, Di","Du, Xin","Huang, Xuanjing","Zheng, Xiaoqing"],"tags":["Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2509.20284","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2310.03111","name":"Multi-modal Gaussian Process Variational Autoencoders for Neural and Behavioral Data","source":"datacite","abstract":"Characterizing the relationship between neural population activity and behavioral data is a central goal of neuroscience. While latent variable models (LVMs) are successful in describing high-dimensional time-series data, they are typically only designed for a single type of data, making it difficult to identify structure shared across different experimental data modalities. Here, we address this shortcoming by proposing an unsupervised LVM which extracts temporally evolving shared and independent latents for distinct, simultaneously recorded experimental modalities. We do this by combining Gaussian Process Factor Analysis (GPFA), an interpretable LVM for neural spiking data with temporally smooth latent space, with Gaussian Process Variational Autoencoders (GP-VAEs), which similarly use a GP prior to characterize correlations in a latent space, but admit rich expressivity due to a deep neural network mapping to observations. We achieve interpretability in our model by partitioning latent variability into components that are either shared between or independent to each modality. We parameterize the latents of our model in the Fourier domain, and show improved latent identification using this approach over standard GP-VAE methods. We validate our model on simulated multi-modal data consisting of Poisson spike counts and MNIST images that scale and rotate smoothly over time. We show that the multi-modal GP-VAE (MM-GPVAE) is able to not only identify the shared and independent latent structure across modalities accurately, but provides good reconstructions of both images and neural rates on held-out trials. Finally, we demonstrate our framework on two real world multi-modal experimental settings: Drosophila whole-brain calcium imaging alongside tracked limb positions, and Manduca sexta spike train measurements from ten wing muscles as the animal tracks a visual stimulus.","url":"https://doi.org/10.48550/arxiv.2310.03111","authors":["Gondur, Rabia","Sikandar, Usama Bin","Schaffer, Evan","Aoi, Mikio Christian","Keeley, Stephen L"],"tags":["Machine Learning (cs.LG)","Neurons and Cognition (q-bio.NC)","FOS: Computer and information sciences","FOS: Computer and information sciences","FOS: Biological sciences","FOS: Biological sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.48550/arxiv.2310.03111","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.7302/28136","name":"Algorithm-Hardware Co-Design for Artificial Intelligence: From Energy-Efficient Edge Processing to High-Performance GPU Acceleration","source":"datacite","abstract":"Deep learning has become a cornerstone of modern artificial intelligence (AI), driving transformative advances in fields such as computer vision, natural language processing, and generative models for text and images. However, as the complexity of neural networks continues to rise, the computational and memory demands necessary to maintain state-of-the-art performance have also increased significantly. This dissertation addresses the growing complexity of deep neural networks and the challenges associated with scaling and deploying them, particularly in resource-constrained environments such as edge devices. It explores the co-design of specialized hardware and neural networks, emphasizing the need for efficient integration between software and hardware to achieve optimal performance. This dissertation presents four works that aim to maximize the benefits of software optimizations, minimize accuracy loss during model simplification, and deliver real-world speedups on existing hardware platforms. The first work introduces a hardware accelerator for heterogeneous transform-domain neural networks, which reduces computational overhead through a specialized dataflow and optimized cache organization. Evaluations demonstrate that the proposed accelerator enhances energy efficiency and performance by up to 5.1x and 5.2x, respectively, for convolution layers, compared to previous dense accelerators. The second work presents an all-on-chip-weight implementation of a heterogeneous transform-domain neural engine that uses dense magnetoresistive non-volatile memory for weight storage. This processor achieves a peak efficiency of 9.51 TOPS/W for convolutional layers and 22.86 TOPS/W for fully connected layers, positioning it as a promising solution for energy-constrained edge applications. The third work proposes a one-hot multi-level leaky integrate-and-fire neuron model, which improves the accuracy-energy tradeoff in spiking neural networks by improving performance without compromising energy consumption. Evaluations reveal that networks using the proposed neurons enhance the accuracy-latency tradeoff for advanced network architectures, such as spike-driven transformers, achieving over 3% higher accuracy and requiring 4x fewer timesteps on ImageNet. Finally, the fourth work investigates techniques for optimizing structured-compressed foundation model inference on graphics processing units (GPUs), leveraging fused kernels and memory-efficient strategies to achieve substantial speedups. Together, these contributions not only advance the efficient deployment of deep learning models in resource-limited environments but also pave the way for future innovations in AI hardware and algorithm co-design.","url":"https://doi.org/10.7302/28136","authors":["Abillama, Pierre"],"tags":["Domain-Specific Hardware Acceleration","Neural Networks","Low-Rank Compression","Quantization","Structured Sparsity","Embedded Non-volatile Memory","Electrical Engineering","Engineering"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.7302/28136","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2502.06747","name":"Wandering around: A bioinspired approach to visual attention through object motion sensitivity","source":"datacite","abstract":"Active vision enables dynamic visual perception, offering an alternative to static feedforward architectures in computer vision, which rely on large datasets and high computational resources. Biological selective attention mechanisms allow agents to focus on salient Regions of Interest (ROIs), reducing computational demand while maintaining real-time responsiveness. Event-based cameras, inspired by the mammalian retina, enhance this capability by capturing asynchronous scene changes enabling efficient low-latency processing. To distinguish moving objects while the event-based camera is in motion the agent requires an object motion segmentation mechanism to accurately detect targets and center them in the visual field (fovea). Integrating event-based sensors with neuromorphic algorithms represents a paradigm shift, using Spiking Neural Networks to parallelize computation and adapt to dynamic environments. This work presents a Spiking Convolutional Neural Network bioinspired attention system for selective attention through object motion sensitivity. The system generates events via fixational eye movements using a Dynamic Vision Sensor integrated into the Speck neuromorphic hardware, mounted on a Pan-Tilt unit, to identify the ROI and saccade toward it. The system, characterized using ideal gratings and benchmarked against the Event Camera Motion Segmentation Dataset, reaches a mean IoU of 82.2% and a mean SSIM of 96% in multi-object motion segmentation. The detection of salient objects reaches 88.8% accuracy in office scenarios and 89.8% in low-light conditions on the Event-Assisted Low-Light Video Object Segmentation Dataset. A real-time demonstrator shows the system's 0.12 s response to dynamic scenes. Its learning-free design ensures robustness across perceptual scenes, making it a reliable foundation for real-time robotic applications serving as a basis for more complex architectures.","url":"https://doi.org/10.48550/arxiv.2502.06747","authors":["D'Angelo, Giulia","Clerico, Victoria","Bartolozzi, Chiara","Hoffmann, Matej","Furlong, P. Michael","Hadjiivanov, Alexander"],"tags":["Computer Vision and Pattern Recognition (cs.CV)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2502.06747","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.17169/refubium-51237","name":"A brain-constrained neural model of cognition and language with NEST: transitioning from the Felix framework","source":"datacite","abstract":"We introduce a brain-constrained neurocomputational model designed to simulate higher cognitive functions of the human brain, implemented using NEST, a widely used open-source simulator optimised for high-performance spiking neural network simulations. Previously implemented in the custom-built C-based Felix simulation library, transitioning the model to NEST enhances accessibility, reproducibility, and computational efficiency. At the cellular level, the model comprises spiking excitatory neurons and local inhibitory neurons, whereas at the network level, it replicates the structural and functional organisation of 12 cortical regions spanning frontal, temporal, and occipital cortices, along with their associated inter-area connectivity. Additionally, global inhibition mechanisms and neuronal noise are integrated. Learning in the model follows biologically plausible Hebbian plasticity principles, incorporating both long-term potentiation and long-term depression. To validate the NEST implementation, we replicated previous simulation findings obtained with the Felix-based model. The new implementation successfully reproduced the same topographical distribution of cell assemblies following associative learning of object and action words within action and perception systems, replicating a range of previous neuroimaging results. Although the NEST model produced larger cell assemblies than Felix, the overall topographical patterns remained similar, indicating preservation of fundamental network characteristics. Moreover, the transition to NEST significantly enhanced computational efficiency, reducing simulation runtime nearly sixfold compared to Felix. This improvement in computational speed is crucial for expanding the model to include additional cortical regions, such as extending to the right hemisphere, which necessitates increased computational resources.","url":"https://doi.org/10.17169/refubium-51237","authors":["Carriere, Maxime","Dobler, Fynn","Plesser, Hans Ekkehard","Feledyn, Agata","Tomasello, Rosario","Wennekers, Thomas","Pulvermüller, Friedemann"],"tags":["Brain-constrained model","Language model","Hebbian learning","NEST","Neural network","Linguistik"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.17169/refubium-51237","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18595933","name":"Activation-Scaled ANN-to-SNN Conversion with SNN Guardrail: A Unified Framework for AI Interpretability, Hallucination Detection, Real-Time Adversarial Defense, Neural Healing, Brain State Imaging, Hallucination Anatomy, and the Canary Head Paradigm (v9)","source":"datacite","abstract":"I present a unified framework that extends ANN-to-SNN conversion beyond efficiency optimization to enable novel AI interpretability analysis, real-time adversarial defense, autonomous neural healing, brain state imaging, real-time hallucination anatomy, and the Canary Head Paradigm. My approach uses Spiking Neural Networks as \"computational microscopes\" to analyze black-box AI models. v9 Updates: NEW: Canary Head Paradigm — \"Liar Heads\" reinterpreted as \"Canary Heads\" (early-warning alarm systems). Monitoring only 3 heads (0.3% of total) achieves +5% accuracy over full-layer baseline with 97% compute reduction NEW: 5-Model Depth Scaling Law — Phi-2 (2.7B) reveals peak hallucination at 25% depth (shallow zone), establishing a ~3B critical parameter threshold for mid-layer convergence NEW: Canary's Eye Visualization — L10H17 attention heatmap during hallucination, showing the canary \"wakes up\" during generation steps 3–8 NEW: GQA Architecture Limitations — Qwen2.5 GQA (2 KV heads) produces systematic NaN under fp16, requiring fp32 for reliable entropy analysis NEW: AI-Assisted Research Acknowledgment — Transparent disclosure of human-AI collaborative methodology (Anthropic Claude, Google Gemini) v8 Updates: \"Moment of Lie\" — animated token-by-token heatmaps visualizing the exact moment hallucinations crystallize in mid-layer attention (L10–L18 in Mistral-7B) Token Economy — Surgical v3 mid-layer sniper achieves 72% compute savings by monitoring only 9/32 layers, with comparable accuracy Cross-Model Universality — Llama-3.2-3B (28 layers) confirms hallucination signature at 30–55% depth (peak L12, ΔH = −0.403 bits) Mid-Layer Hallucination Hypothesis: entropy disruption maximized at 30–55% of total network depth regardless of architecture (Mistral, Llama) v7 Updates: Entropy Evolution Discovery — Mistral-7B (fp16, 7.2B params) GPU validation reveals detection signals shift from TTFS latency (1-3B) to attention entropy (7B+) Mistral-7B attention entropy: +5.8σ separation (p = 2.22×10⁻⁹⁵), 100% detection accuracy (N=200) 6-Model Scaling Law validated (GPT-2, TinyLlama, Llama-3.2-1B, Llama-3.2-3B, Mistral-7B) Key Discovery: \"As models scale, the attack signature transforms from latency (brain freeze) to entropy (internal confusion) — but never disappears\" v6 Updates: N=1,000 Statistical Proof — Welch's t = −33.65 (p = 8.91×10⁻¹⁶⁴), Cohen's d = 2.13, 89.3% zero-shot detection accuracy on Llama-3.2-3B \"Visualizing the Ghost\" — First SNN-VAE visualization of LLM brain states during adversarial attacks (L2 distance = 3.287 between normal and jailbreak states) v5 Updates: Neural Healing v4A – Multi-stage progressive healing achieving 22% success rate on TinyLlama (1.1B) Mistral-7B (7B) experiment – Model-size-dependent threshold discovery HuggingFace Spaces v2.0 – Live 3-tab demo (Jailbreak/Healing/Hallucination) v4 Results: SNN Guardrail: 100% jailbreak detection rate (8/8 attack types) Scaling Law Discovery: TTFS sensitivity increases with model size (GPT-2: +3.1, TinyLlama: +4.2) Previous Results (v1-v3): Universal threshold formula: θ = 2.0 × max(activation) 100% accuracy preservation with hippocampal hybrid architecture GPT-2 attention TTFS analysis: +3.1 increase for meaningless inputs Hallucination detection: AUC 0.75 with ensemble classifier ViT-Base (86M) validation with CIFAR-10D Key insight: \"The neural fingerprint of hallucination is not just detectable — it is anatomically localized and predictable. The Canary Head paradigm reveals that specific attention heads serve as built-in alarm systems. The 5-model Depth Scaling Law shows a critical ~3B parameter threshold: smaller models hallucinate in shallow layers (15–25%), while larger models converge to a universal mid-layer zone (40–55%).\" 🔗 Live Demo: https://huggingface.co/spaces/hafufu-stack/snn-guardrail Code: https://github.com/hafufu-stack/temporal-coding-simulation/tree/main/ann-to-snn-converter This research employed a human-AI collaborative methodology. See Acknowledgm","url":"https://doi.org/10.5281/zenodo.18595933","authors":["Funasaki, Hiroto"],"tags":["spiking neural networks","ANN-to-SNN conversion","neuromorphic computing","deep learning","Hybrid Architecture","AI interpretability","hallucination detection","Time-to-First-Spike / TTFS"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18595933","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2602.08726","name":"SynSacc: A Blender-to-V2E Pipeline for Synthetic Neuromorphic Eye-Movement Data and Sim-to-Real Spiking Model Training","source":"datacite","abstract":"The study of eye movements, particularly saccades and fixations, are fundamental to understanding the mechanisms of human cognition and perception. Accurate classification of these movements requires sensing technologies capable of capturing rapid dynamics without distortion. Event cameras, also known as Dynamic Vision Sensors (DVS), provide asynchronous recordings of changes in light intensity, thereby eliminating motion blur inherent in conventional frame-based cameras and offering superior temporal resolution and data efficiency. In this study, we introduce a synthetic dataset generated with Blender to simulate saccades and fixations under controlled conditions. Leveraging Spiking Neural Networks (SNNs), we evaluate its robustness by training two architectures and finetuning on real event data. The proposed models achieve up to 0.83 accuracy and maintain consistent performance across varying temporal resolutions, demonstrating stability in eye movement classification. Moreover, the use of SNNs with synthetic event streams yields substantial computational efficiency gains over artificial neural network (ANN) counterparts, underscoring the utility of synthetic data augmentation in advancing event-based vision. All code and datasets associated with this work is available at https: //github.com/Ikhadija-5/SynSacc-Dataset.","url":"https://doi.org/10.48550/arxiv.2602.08726","authors":["Iddrisu, Khadija","Shariff, Waseem","Little, Suzanne","OConnor, Noel"],"tags":["Computer Vision and Pattern Recognition (cs.CV)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2602.08726","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2602.07037","name":"Stochastic Spiking Neuron Based SNN Can be Inherently Bayesian","source":"datacite","abstract":"Uncertainty in biological neural systems appears to be computationally beneficial rather than detrimental. However, in neuromorphic computing systems, device variability often limits performance, including accuracy and efficiency. In this work, we propose a spiking Bayesian neural network (SBNN) framework that unifies the dynamic models of intrinsic device stochasticity (based on Magnetic Tunnel Junctions) and stochastic threshold neurons to leverage noise as a functional Bayesian resource. Experiments demonstrate that SBNN achieves high accuracy (99.16% on MNIST, 94.84% on CIFAR10) with 8-bit precision. Meanwhile rate estimation method provides a ~20-fold training speedup. Furthermore, SBNN exhibits superior robustness, showing a 67% accuracy improvement under synaptic weight noise and 12% under input noise compared to standard spiking neural networks. Crucially, hardware validation confirms that physical device implementation causes invisible accuracy and calibration loss compared to the algorithmic model. Converting device stochasticity into neuronal uncertainty offers a route to compact, energy-efficient neuromorphic computing under uncertainty.","url":"https://doi.org/10.48550/arxiv.2602.07037","authors":["Zheng, Huannan","Liu, Jingli","Yang, Kezhou"],"tags":["Neural and Evolutionary Computing (cs.NE)","Artificial Intelligence (cs.AI)","Computer Vision and Pattern Recognition (cs.CV)","Emerging Technologies (cs.ET)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2602.07037","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2602.07010","name":"Learning Alzheimer's Disease Signatures by bridging EEG with Spiking Neural Networks and Biophysical Simulations","source":"datacite","abstract":"As the prevalence of Alzheimer's disease (AD) rises, improving mechanistic insight from non-invasive biomarkers is increasingly critical. Recent work suggests that circuit-level brain alterations manifest as changes in electroencephalography (EEG) spectral features detectable by machine learning. However, conventional deep learning approaches for EEG-based AD detection are computationally intensive and mechanistically opaque. Spiking neural networks (SNNs) offer a biologically plausible and energy-efficient alternative, yet their application to AD diagnosis remains largely unexplored. We propose a neuro-bridge framework that links data-driven learning with minimal, biophysically grounded simulations, enabling bidirectional interpretation between machine learning signatures and circuit-level mechanisms in AD. Using resting-state clinical EEG, we train an SNN classifier that achieves competitive performance (AUC = 0.839) and identifies the aperiodic 1/f slope as a key discriminative marker. The 1/f slope reflects excitation-inhibition balance. To interpret this mechanistically, we construct spiking network simulations in which inhibitory-to-excitatory synaptic ratios are systematically varied to emulate healthy, mild cognitive impairment, and AD-like states. Using both membrane potential-based and synaptic current-based EEG proxies, we reproduce empirical spectral slowing and altered alpha organization. Incorporating empirical functional connectivity priors into multi-subnetwork simulations further enhances spectral differentiation, demonstrating that large-scale network topology constrains EEG signatures more strongly than excitation-inhibition balance alone. Overall, this neuro-bridge approach connects SNN-based classification with interpretable circuit simulations, advancing mechanistic understanding of EEG biomarkers while enabling scalable, explainable AD detection.","url":"https://doi.org/10.48550/arxiv.2602.07010","authors":["Mamoń, Szymon","Talanov, Max","Crimi, Alessandro"],"tags":["Neural and Evolutionary Computing (cs.NE)","Artificial Intelligence (cs.AI)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2602.07010","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.25958/tfkv-5t55","name":"Towards neuromorphic visual SLAM: A spiking neural network for efficient pose estimation and loop closure based on event camera data","source":"datacite","abstract":"The need for effective Simultaneous Localisation and Mapping (SLAM) solutions has been pivotal across a wide range of applications, including autonomous vehicles, industrial robotics, and mobile service platforms where accurate localisation and environmental perception are essential. Visual SLAM (VSLAM) has emerged as a popular approach due to its cost effectiveness and ease of deployment. However, state-of-the-art VSLAM systems using conventional cameras face significant limitations, including high computational requirements, sensitivity to motion blur, restricted dynamic range, and poor performance under variable lighting conditions. Event cameras present a promising alternative by producing asynchronous, high-temporal resolution data with low latency and power consumption. These characteristics make them ideal for use in dynamic and resource-constrained environments. Complementing this, neuromorphic processors designed for efficient event-driven computation are inherently compatible with sparse temporal data. Despite their synergy, the adoption of event cameras and neuromorphic computing in SLAM remains limited due to the scarcity of public datasets, underdeveloped algorithmic tools, and challenges in multimodal sensor fusion. This thesis develops integrated Visual Odometry (VO) and Loop Closure (LC) models that leverage neuromorphic sensing, spiking neural networks (SNN), and probabilistic factor-graph optimisation as a pathway towards full event camera-based SLAM. A synchronised multimodal dataset, captured with a Prophesee STM32-GENx320 event camera, Livox MID-360 LiDAR, and Pixhawk 6C Mini IMU spans indoor and outdoor scenarios over 2,285 s. Raw events are aggregated into voxel-grid tensors using 100 ms windows with 20 temporal bins. LiDAR odometry from point clouds is refined with inertial constraints in Georgia Tech Smoothing and Mapping (GTSAM) to produce pseudo-ground-truth trajectories for supervised learning. Two SNN models are developed using the SpikingJelly framework: a spiking VO network that predicts six-degree-of-freedom (6-DOF) pose increments from voxel grids, and a LC network that estimates inter-frame similarity scores for global trajectory correction. Both models are trained with surrogate gradient learning and employ Leaky Integrate-and-Fire neurons. The VO model uses a hybrid loss function that combines Root Mean Square Error for translation with a geodesic loss on the Special Orthogonal Group in 3D for rotation prediction. The LC model is optimised using a joint loss comprising a triplet margin loss for learning discriminative embeddings and a cross-entropy loss for binary classification. These frontend models are integrated into a modular backend system based on a sliding window factor graph. The backend fuses VO predictions with IMU pre-integration and LC constraints and performs real-time optimisation using GTSAM. Empirical evaluation on kilometre-scale sequences demonstrates robust performance in diverse indoor and outdoor environments, achieving sub-metre Absolute Trajectory Error and competitive Relative Pose Error. Additionally, hardware benchmarking across conventional and neuromorphic processor such as BrainChip Akida platforms reveals up to a four times reduction in latency and an order of-magnitude gain in energy efficiency on neuromorphic hardware. The main contributions of this work include a pipeline towards full VSLAM architecture combining SNNs, event-based vision, and multimodal sensor fusion for 6-DOF pose estimation and LC; a novel training pipeline using voxelised asynchronous event data and GTSAM refined pseudo-ground-truth; a modular backend architecture that performs drift-resilient optimisation using VO, IMU, and LC constraints; a cross-platform benchmarking study that highlights the advantages of neuromorphic hardware; and a synchronised multimodal dataset supporting the above components. Overall, this thesis provides a pipeline towards a scalable and energy-efficient SLAM so","url":"https://doi.org/10.25958/tfkv-5t55","authors":["Tenzin, Sangay"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.25958/tfkv-5t55","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2511.00732","name":"FeNN-DMA: A RISC-V SoC for SNN acceleration","source":"datacite","abstract":"Spiking Neural Networks (SNNs) are a promising, energy-efficient alternative to standard Artificial Neural Networks (ANNs) and are particularly well-suited to spatio-temporal tasks such as keyword spotting and video classification. However, SNNs have a much lower arithmetic intensity than ANNs and are therefore not well-matched to standard accelerators like GPUs and TPUs. Field Programmable Gate Arrays (FPGAs) are designed for such memory-bound workloads, and here we present a novel, fully-programmable RISC-V-based system-on-chip (FeNN-DMA), tailored to simulating SNNs on modern UltraScale+ FPGAs. We show that FeNN-DMA has comparable resource usage and energy requirements to state-of-the-art fixed-function SNN accelerators, yet it supports more complex neuron models and network topologies, and can simulate up to 16 thousand neurons and 256 million synapses per core. Using this functionality, we demonstrate state-of-the-art classification accuracy on the Spiking Heidelberg Digits, Neuromorphic MNIST and Braille tactile classification tasks.","url":"https://doi.org/10.48550/arxiv.2511.00732","authors":["Aizaz, Zainab","Knight, James C.","Nowotny, Thomas"],"tags":["Neural and Evolutionary Computing (cs.NE)","Artificial Intelligence (cs.AI)","Hardware Architecture (cs.AR)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2511.00732","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2602.06405","name":"A neuromorphic model of the insect visual system for natural image processing","source":"datacite","abstract":"Insect vision supports complex behaviors including associative learning, navigation, and object detection, and has long motivated computational models for understanding biological visual processing. However, many contemporary models prioritize task performance while neglecting biologically grounded processing pathways. Here, we introduce a bio-inspired vision model that captures principles of the insect visual system to transform dense visual input into sparse, discriminative codes. The model is trained using a fully self-supervised contrastive objective, enabling representation learning without labeled data and supporting reuse across tasks without reliance on domain-specific classifiers. We evaluated the resulting representations on flower recognition tasks and natural image benchmarks. The model consistently produced reliable sparse codes that distinguish visually similar inputs. To support different modelling and deployment uses, we have implemented the model as both an artificial neural network and a spiking neural network. In a simulated localization setting, our approach outperformed a simple image downsampling comparison baseline, highlighting the functional benefit of incorporating neuromorphic visual processing pathways. Collectively, these results advance insect computational modelling by providing a generalizable bio-inspired vision model capable of sparse computation across diverse tasks.","url":"https://doi.org/10.48550/arxiv.2602.06405","authors":["Hines, Adam D.","Nordström, Karin","Barron, Andrew B."],"tags":["Computer Vision and Pattern Recognition (cs.CV)","Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2602.06405","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18528971","name":"Activation-Scaled ANN-to-SNN Conversion with SNN Guardrail: A Unified Framework for AI Interpretability, Hallucination Detection, Real-Time Adversarial Defense, Neural Healing, Brain State Imaging, and Real-Time Hallucination Anatomy (v8)","source":"datacite","abstract":"I present a unified framework that extends ANN-to-SNN conversion beyond efficiency optimization to enable novel AI interpretability analysis, real-time adversarial defense, autonomous neural healing, brain state imaging, and real-time hallucination anatomy. My approach uses Spiking Neural Networks as \"computational microscopes\" to analyze black-box AI models. **v8 Updates:**- NEW: \"Moment of Lie\" — animated token-by-token heatmaps visualizing the exact moment hallucinations crystallize in mid-layer attention (L10–L18 in Mistral-7B)- NEW: Token Economy — Surgical v3 mid-layer sniper achieves 72% compute savings by monitoring only 9/32 layers, with comparable accuracy- NEW: Cross-Model Universality — Llama-3.2-3B (28 layers) confirms hallucination signature at 30–55% depth (peak L12, ΔH = −0.403 bits)- Mid-Layer Hallucination Hypothesis: entropy disruption maximized at 30–55% of total network depth regardless of architecture (Mistral, Llama) **v7 Updates:**- Entropy Evolution Discovery — Mistral-7B (fp16, 7.2B params) GPU validation reveals detection signals shift from TTFS latency (1-3B) to attention entropy (7B+)- Mistral-7B attention entropy: +5.8σ separation (p = 2.22×10⁻⁹⁵), 100% detection accuracy (N=200)- 6-Model Scaling Law validated (GPT-2, TinyLlama, Llama-3.2-1B, Llama-3.2-3B, Mistral-7B)- Key Discovery: \"As models scale, the attack signature transforms from latency (brain freeze) to entropy (internal confusion) — but never disappears\" **v6 Updates:**- N=1,000 Statistical Proof — Welch's t = −33.65 (p = 8.91×10⁻¹⁶⁴), Cohen's d = 2.13, 89.3% zero-shot detection accuracy on Llama-3.2-3B- \"Visualizing the Ghost\" — First SNN-VAE visualization of LLM brain states during adversarial attacks (L2 distance = 3.287 between normal and jailbreak states) **v5 Updates:**- Neural Healing v4A – Multi-stage progressive healing achieving 22% success rate on TinyLlama (1.1B)- Mistral-7B (7B) experiment – Model-size-dependent threshold discovery- HuggingFace Spaces v2.0 – Live 3-tab demo (Jailbreak/Healing/Hallucination) **v4 Results:**- SNN Guardrail: 100% jailbreak detection rate (8/8 attack types)- Scaling Law Discovery: TTFS sensitivity increases with model size (GPT-2: +3.1, TinyLlama: +4.2) **Previous Results (v1-v3):**- Universal threshold formula: θ = 2.0 × max(activation)- 100% accuracy preservation with hippocampal hybrid architecture- GPT-2 attention TTFS analysis: +3.1 increase for meaningless inputs- Hallucination detection: AUC 0.75 with ensemble classifier- ViT-Base (86M) validation with CIFAR-100 Key insight: \"The neural fingerprint of hallucination is not just detectable — it is anatomically localized. Across architectures (Mistral, Llama), model sizes (3B, 7B), and layer counts (28, 32), the hallucination signature consistently emerges at 30–55% of network depth. This 'hallucination zone' represents a universal feature of transformer-based language models.\" 🔗 Live Demo: https://huggingface.co/spaces/hafufu-stack/snn-guardrailCode: https://github.com/hafufu-stack/temporal-coding-simulation/tree/main/ann-to-snn-converter","url":"https://doi.org/10.5281/zenodo.18528971","authors":["Funasaki, Hiroto"],"tags":["spiking neural networks","ANN-to-SNN conversion","neuromorphic computing","deep learning","Hybrid Architecture","AI interpretability","hallucination detection","Time-to-First-Spike / TTFS"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18528971","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5167/uzh-290742","name":"Network models incorporating chloride dynamics predict optimal strategies for terminating status epilepticus","source":"datacite","abstract":"Status epilepticus (SE), seizures lasting beyond five minutes, is a medical emergency commonly treated with benzodiazepines which enhance GABA receptor (GABAR) conductance. Despite widespread use, benzodiazepines fail in over one-third of patients, potentially due to seizure-induced disruption of neuronal chloride (Cl) homeostasis. Understanding these changes at a network level is crucial for improving clinical translation. Here, we address this using a large-scale spiking neural network model incorporating Cl dynamics, informed by clinical EEG and experimental slice recordings. Our simulations confirm that the GABAR reversal potential (E) dictates the pro- or anti-seizure effect of GABAR conductance modulation, with high E rendering benzodiazepines ineffective or excitatory. We show SE-like activity and E depend non-linearly on Cl extrusion efficacy and GABAR conductance. Critically, cell-type specific manipulations reveal that pyramidal cell, not interneuron, Cl extrusion predominantly determines the severity of SE activity and the response to simulated benzodiazepines. Leveraging these mechanistic insights, we develop a predictive framework mapping network states to Cl extrusion capacity and GABAergic load, yielding a proposed decision-making strategy to guide therapeutic interventions based on initial treatment response. This work identifies pyramidal cell Cl handling as a key therapeutic target and demonstrates the utility of biophysically detailed network models for optimising SE treatment protocols.","url":"https://doi.org/10.5167/uzh-290742","authors":["Currin, Christopher B","Burman, Richard J","Fedele, Tommaso","Ramantani, Georgia","Rosch, Richard E","Sprekeler, Henning","Raimondo, Joseph V"],"tags":["610 Medicine &amp; health"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5167/uzh-290742","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18464576","name":"Geometric parallel resonance chip.(neuromorphic/holographic/resonance)","source":"datacite","abstract":"A novel chip architecture implementing geometric parallel resonance for neuromorphic inference with integrated hardware-level hallucination detection. Unlike conventional neural networks that compute sequentially, ilEcho Genesis activates all connections simultaneously through resonance—the topology IS the computation. The 3-5-4-(1)-4-5-3 ring structure of 13 specialized chambers enables O(1) scaling: inference latency remains constant (~180ns) regardless of model size. Key innovations: 1. UACIL (Universal Absolute Criterion for Information Legitimacy): First hardware implementation of anti-hallucination detection. The system analyzes input through three primordial modes (IS/COULD_BE/ISN'T) and flags trauma-dominant processing before output emission. 2. Geometric Parallel Resonance: All pixels resonate simultaneously via matrix operations. Memory IS topology—patterns persist through filtered accumulation under witness (Leaf","url":"https://doi.org/10.5281/zenodo.18464576","authors":["Leaf, Alexander \"Eli\" McVey","ilEcho Genesis"],"tags":["geometric parallel resonance neuromorphic computing holographic memory anti-hallucination UACIL resonance computing spiking neural network hardware safety Leaf's Law pattern persistence AI safety edge inference low-latency inference"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18464576","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5445/ir/1000182207","name":"Spiking Neural Belief Propagation Decoder for LDPC Codes with Small Variable Node Degrees","source":"datacite","abstract":"Spiking neural networks (SNNs) promise energy-efficient data processing by imitating the event-based behavior of biological neurons. In previous work, we introduced the enlarge-likelihood-each-notable-amplitude spiking-neural-network (ELENA-SNN) decoder, a novel decoding algorithm for low-density parity-check (LDPC) codes. The decoder integrates SNNs into belief propagation (BP) decoding by approximating the check node (CN) update equation using SNNs. However, when decoding LDPC codes with a small variable node(VN) degree, the approximation gets too rough, and the ELENA-SNN decoder does not yield good results. This paper introduces the multi-level ELENA-SNN (ML-ELENA-SNN) decoder, which is an extension of the ELENA-SNN decoder. Instead of a single SNN approximating the CN update, multiple SNNs are applied in parallel, resulting in a higher resolution and higher dynamic range of the exchanged messages. We show that the ML-ELENA-SNN decoder performs similarly to the ubiquitous normalized min-sum decoder for the (38400, 30720) regular LDPC code with a VN degree of dv = 3 and a CN degree of dc = 15.","url":"https://doi.org/10.5445/ir/1000182207","authors":["Bank, Alexander von","Edelmann, Eike-Manuel","Mandelbaum, Jonathan","Schmalen, Laurent"],"tags":["BP Decoding","LDPC codes","regular LDPC codes","spiking neural networks"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.5445/ir/1000182207","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18449733","name":"Neural Dynamics: A collection of educational Python scripts","source":"datacite","abstract":"🚀 Release v1.0.0 This is the initial release of the Neural Dynamics repository, featuring a comprehensive collection of educational Python scripts for computational neuroscience. The release includes tutorials on using the NEST Simulator, as well as standalone scripts implementing various neuron models and network dynamics. 📦 Scope and content This release includes educational Python scripts covering a broad range of core topics in neural dynamics, such as: Single neuron models (Integrate-and-Fire, Izhikevich, AdEx, EIF) Spiking neural networks (Brunel network, oscillatory dynamics) Synaptic plasticity rules (BCM rule) Gap junctions and their role in neural modeling Rate models for collective neural activity The repository structure reflects this thematic organization and mirrors the progression of the blog series. 🧠 Conceptual focus The scripts in this repository are designed as didactic and conceptual examples. Emphasis is placed on: Clarity and interpretability of models Step-by-step explanations accompanying each script Reproducibility of classic results in theoretical neuroscience Encouraging experimentation and exploration of neural dynamics concepts Bridging theoretical neuroscience with practical implementation Many models deliberately rely on reduced geometries, simplified boundary conditions, or idealized assumptions to keep the underlying mechanisms explicit. 🔬 Reproducibility and usage All scripts are compatible with a lightweight Python environment based on NumPy, SciPy, and Matplotlib, along with the NEST Simulator for spiking neural network simulations. Instructions for setting up the environment and running the scripts are provided in the README file. The scripts are written to support both direct execution and interactive, cell-by-cell exploration in development environments such as VS Code or Jupyter. This release provides a stable baseline for reuse in: teaching and coursework self-study illustrative figures and animations methodological extensions Backward compatibility across future releases is not guaranteed, but changes will primarily serve conceptual clarification rather than feature expansion. 📝 License All code is released under the GPL-3.0 License. ✨ Outlook Future releases may expand individual examples, refine numerical implementations, or add complementary scripts aligned with new blog posts. Any such extensions will build on the conceptual baseline established with this release.","url":"https://doi.org/10.5281/zenodo.18449733","authors":["Fabrizio Musacchio"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18449733","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18483973","name":"NeuroGuard-V2X : A Neuromorphic Edge Processing Architecture for Privacy-Preserving Network Monitoring in Connected Vehicles","source":"datacite","abstract":"This paper introduces NeuroGuard-V2X, a privacy-preserving network monitoring architecture for connected vehicles based on neuromorphic edge processing. By deploying event-driven spiking neural networks directly on vehicles, the proposed system analyzes temporal patterns in heterogeneous V2X communications without transmitting or storing sensitive network data. NeuroGuard-V2X enables real-time intrusion detection across DSRC, cellular, and Wi-Fi interfaces while maintaining low latency and energy consumption. Experimental results demonstrate high detection accuracy, significant reductions in data transmission, and ultra-low power usage, highlighting its suitability for secure and scalable vehicular systems.","url":"https://doi.org/10.5281/zenodo.18483973","authors":["Mohammad Zahangir, Alam"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18483973","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18483972","name":"NeuroGuard-V2X : A Neuromorphic Edge Processing Architecture for Privacy-Preserving Network Monitoring in Connected Vehicles","source":"datacite","abstract":"This paper introduces NeuroGuard-V2X, a privacy-preserving network monitoring architecture for connected vehicles based on neuromorphic edge processing. By deploying event-driven spiking neural networks directly on vehicles, the proposed system analyzes temporal patterns in heterogeneous V2X communications without transmitting or storing sensitive network data. NeuroGuard-V2X enables real-time intrusion detection across DSRC, cellular, and Wi-Fi interfaces while maintaining low latency and energy consumption. Experimental results demonstrate high detection accuracy, significant reductions in data transmission, and ultra-low power usage, highlighting its suitability for secure and scalable vehicular systems.","url":"https://doi.org/10.5281/zenodo.18483972","authors":["Mohammad Zahangir, Alam"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18483972","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5167/uzh-284397","name":"Stable recurrent dynamics in heterogeneous neuromorphic computing systems using excitatory and inhibitory plasticity","source":"datacite","abstract":"Many neural computations emerge from self-sustained patterns of activity in recurrent neural circuits, which rely on balanced excitation and inhibition. Neuromorphic electronic circuits represent a promising approach for implementing the brain's computational primitives. However, achieving the same robustness of biological networks in neuromorphic systems remains a challenge due to the variability in their analog components. Inspired by real cortical networks, we apply a biologically-plausible cross-homeostatic rule to balance neuromorphic implementations of spiking recurrent networks. We demonstrate how this rule can autonomously tune the network to produce robust, self-sustained dynamics in an inhibition-stabilized regime, even in presence of device mismatch. It can implement multiple, co-existing stable memories, with emergent soft-winner-take-all and reproduce the \"paradoxical effect\" observed in cortical circuits. In addition to validating neuroscience models on a substrate sharing many similar limitations with biological systems, this enables the automatic configuration of ultra-low power, mixed-signal neuromorphic technologies despite the large chip-to-chip variability.","url":"https://doi.org/10.5167/uzh-284397","authors":["Soldado-Magraner, Saray","Sorbaro, Martino","Laje, Rodrigo","Buonomano, Dean V","Indiveri, Giacomo"],"tags":["570 Life sciences; biology"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5167/uzh-284397","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2601.08248","name":"Spiking Neural-Invariant Kalman Fusion for Accurate Localization Using Low-Cost IMUs","source":"datacite","abstract":"Low-cost inertial measurement units (IMUs) are widely utilized in mobile robot localization due to their affordability and ease of integration. However, their complex, nonlinear, and time-varying noise characteristics often lead to significant degradation in localization accuracy when applied directly for dead reckoning. To overcome this limitation, we propose a novel brain-inspired state estimation framework that combines a spiking neural network (SNN) with an invariant extended Kalman filter (InEKF). The SNN is designed to extract motion-related features from long sequences of IMU data affected by substantial random noise and is trained via a surrogate gradient descent algorithm to enable dynamic adaptation of the covariance noise parameter within the InEKF. By fusing the SNN output with raw IMU measurements, the proposed method enhances the robustness and accuracy of pose estimation. Extensive experiments conducted on the KITTI dataset and real-world data collected using a mobile robot equipped with a low-cost IMU demonstrate that the proposed approach outperforms state-of-the-art methods in localization accuracy and exhibits strong robustness to sensor noise, highlighting its potential for real-world mobile robot applications.","url":"https://doi.org/10.48550/arxiv.2601.08248","authors":["Liu, Yaohua","Xu, Qiao","Ou, Binkai"],"tags":["Robotics (cs.RO)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2601.08248","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2509.05356","name":"Spiking Neural Networks for Continuous Control via End-to-End Model-Based Learning","source":"datacite","abstract":"Despite recent progress in training spiking neural networks (SNNs) for classification, their application to continuous motor control remains limited. Here, we demonstrate that fully spiking architectures can be trained end-to-end to control robotic arms with multiple degrees of freedom in continuous environments. Our predictive-control framework combines Leaky Integrate-and-Fire dynamics with surrogate gradients, jointly optimizing a forward model for dynamics prediction and a policy network for goal-directed action. We evaluate this approach on both a planar 2D reaching task and a simulated 6-DOF Franka Emika Panda robot with torque control. In direct comparison to non-spiking recurrent baselines trained under the same predictive-control pipeline, the proposed SNN achieves comparable task performance while using substantially fewer parameters. An extensive ablation study highlights the role of initialization, learnable time constants, adaptive thresholds, and latent-space compression as key contributors to stable training and effective control. Together, these findings establish spiking neural networks as a viable and scalable substrate for high-dimensional continuous control, while emphasizing the importance of principled architectural and training design.","url":"https://doi.org/10.48550/arxiv.2509.05356","authors":["Huebotter, Justus","Lanillos, Pablo","van Gerven, Marcel","Thill, Serge"],"tags":["Robotics (cs.RO)","Artificial Intelligence (cs.AI)","Machine Learning (cs.LG)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2509.05356","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.17952779","name":"Pyramidal Hybrid Neural Network Framework (BrainIAc_v1.0) : Technical Documentation and Experimental Results","source":"datacite","abstract":"Project Overview Pre-publication technical documentation and experimental validation results for a hybrid neural network framework enabling gradient-based training of heterogeneous spiking neuron populations. Description/Summary: Key Features: Mixed neuron training: LIF + Izhikevich (10 types) + Hodgkin-Huxley (3 variants) trained together via gradient descent Large-scale validation: Up to 200 neurons with realistic cortical architectures Three learning modes: Separate, Simultaneous, Combined (pretrain + fine-tune) Pyramidal architecture: 1→50→1 hourglass structure (13 layers, 308 neurons) Real-time 3D visualization: 60 FPS interactive rendering with OpenGL Dynamic reconfiguration: Neurons can change type during simulation Comprehensive testing: 20+ validation scenarios, 75% success rate Validated Results: XOR problem: 56% loss reduction (pure LIF, 100 epochs) Mixed types: Stable convergence (4 LIF + 4 Izh + 4 HH, 80 epochs) ⭐ BREAKTHROUGH 100-neuron cortical microcircuit: Functional layer specialization validated 200-neuron cortical circuit: Realistic excitatory/inhibitory dynamics 13 neuron types: All show expected biological firing patterns Comprehensive Dataset: Technical documentation: 24 PDFs (~150 pages total) Core theory (9 PDFs) Framework architecture (5 PDFs) Advanced topics (10 PDFs: biological layers, visualization, roadmap) Experimental validation: 65+ CSV files with raw spike timing data Visual documentation: 67 screenshots Analysis: RESULTS_SUMMARY.md (36.8 KB detailed analysis) README.md (28.4 KB): Complete usage instructions and technical specifications CITATION.md (11.3 KB): Citation formats in BibTeX, APA, IEEE, MLA, Nature LICENSE.txt (2.4 KB): Full CC BY-NC 4.0 license terms License: CC BY-NC 4.0 (Non-Commercial) ✅ Academic research and educational use freely permitted with proper attribution ❌ Commercial use NOT permitted without explicit written permission 📧 For commercial licensing inquiries: theo.vallois@hotmail.fr Source Code: Full source code (BrainIAc framework) will be released under CC BY-NC 4.0 on GitHub upon paper acceptance (expected Q1 2026). Repository: https://github.com/EmpireStrikesBack/NeuroModel Demonstration Video: https://youtu.be/kiU609iozFw Real-time 3D visualization of 308-neuron pyramidal network with interactive controls. Contact: Author: Théo Vallois Email: theo.vallois@hotmail.fr GitHub: https://github.com/EmpireStrikesBack/NeuroModel","url":"https://doi.org/10.5281/zenodo.17952779","authors":["Vallois, Théo Henock André"],"tags":["spiking neural networks","neuromorphic computing","hybrid neural networks","gradient descent","izhikevich neurons","Hodgkin-Huxley neurons","surrogate gradient","Computational neuroscience"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17952779","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.17952780","name":"Pyramidal Hybrid Neural Network Framework (BrainIAc_v1.0) : Technical Documentation and Experimental Results","source":"datacite","abstract":"Project Overview Pre-publication technical documentation and experimental validation results for a hybrid neural network framework enabling gradient-based training of heterogeneous spiking neuron populations. Description/Summary: Key Features: Mixed neuron training: LIF + Izhikevich (10 types) + Hodgkin-Huxley (3 variants) trained together via gradient descent Large-scale validation: Up to 200 neurons with realistic cortical architectures Three learning modes: Separate, Simultaneous, Combined (pretrain + fine-tune) Pyramidal architecture: 1→50→1 hourglass structure (13 layers, 308 neurons) Real-time 3D visualization: 60 FPS interactive rendering with OpenGL Dynamic reconfiguration: Neurons can change type during simulation Comprehensive testing: 20+ validation scenarios, 75% success rate Validated Results: XOR problem: 56% loss reduction (pure LIF, 100 epochs) Mixed types: Stable convergence (4 LIF + 4 Izh + 4 HH, 80 epochs) ⭐ BREAKTHROUGH 100-neuron cortical microcircuit: Functional layer specialization validated 200-neuron cortical circuit: Realistic excitatory/inhibitory dynamics 13 neuron types: All show expected biological firing patterns Comprehensive Dataset: Technical documentation: 24 PDFs (~150 pages total) Core theory (9 PDFs) Framework architecture (5 PDFs) Advanced topics (10 PDFs: biological layers, visualization, roadmap) Experimental validation: 65+ CSV files with raw spike timing data Visual documentation: 67 screenshots Analysis: RESULTS_SUMMARY.md (36.8 KB detailed analysis) README.md (28.4 KB): Complete usage instructions and technical specifications CITATION.md (11.3 KB): Citation formats in BibTeX, APA, IEEE, MLA, Nature LICENSE.txt (2.4 KB): Full CC BY-NC 4.0 license terms License: CC BY-NC 4.0 (Non-Commercial) ✅ Academic research and educational use freely permitted with proper attribution ❌ Commercial use NOT permitted without explicit written permission 📧 For commercial licensing inquiries: theo.vallois@hotmail.fr Source Code: Full source code (BrainIAc framework) will be released under CC BY-NC 4.0 on GitHub upon paper acceptance (expected Q1 2026). Repository: https://github.com/EmpireStrikesBack/NeuroModel Demonstration Video: https://youtu.be/kiU609iozFw Real-time 3D visualization of 308-neuron pyramidal network with interactive controls. Contact: Author: Théo Vallois Email: theo.vallois@hotmail.fr GitHub: https://github.com/EmpireStrikesBack/NeuroModel","url":"https://doi.org/10.5281/zenodo.17952780","authors":["Vallois, Théo Henock André"],"tags":["spiking neural networks","neuromorphic computing","hybrid neural networks","gradient descent","izhikevich neurons","Hodgkin-Huxley neurons","surrogate gradient","Computational neuroscience"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17952780","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5445/ir/1000190105","name":"Physical Security of Emerging AI Hardware Accelerators: From Vulnerability to Countermeasures","source":"datacite","abstract":"The widespread deployment of Artificial Intelligence (AI) at the edge has driven a paradigm shift toward domain-specific hardware accelerators. Emerging architectures-ranging from Analog Compute-in- Memory (CiM) and Non-Volatile Memory (NVM)-centric processors to Neuromorphic Computing and Hyperdimensional Computing (HDC)-promise orders-of-magnitude improvements in energy efficiency and latency. However, while these substrates are often used for their intrinsic robustness to noise and stochastic process variations, this dissertation demonstrates that such robustness does not translate into resilience against targeted physical attacks. This work systematically explores the physical security gap in post-Von Neumann computing, establishing that the very physical properties enabling efficiency often introduce novel, exploitable attack surfaces. To address these challenges, this thesis develops a set of cross-layer analysis frameworks and counter- measures, spanning device physics, circuit simulation, and real-hardware validation. First, the research investigates Analog Compute-in-Memory (CiM) based on ReRAM and STT-MRAM. By developing a physics-aware simulation framework, it is shown that analog non-idealities-such as device-to-device variability and random telegraph noise-manifest as data-dependent leakage signatures. These signatures allow adversaries to recover fixed weights using correlation-based and profiling attacks, enabling the extraction of proprietary neural network models. Second, the thesis uncovers a critical vulnerability in processor-centric NVM architectures. Through real-hardware experiments on STT-MRAM, a novel class of persistent fault attacks is demonstrated. By targeting the specific magnetic commit window of MRAM writes with nanosecond-scale voltage glitches, an attacker can induce stable, non-volatile bit corruptions in stored cryptographic keys. This persistence mechanism collapses the data complexity required for differential fault analysis (DFA) by orders of magnitude, enabling full AES key recovery with fewer than 20 ciphertext pairs. Third, the security of Neuromorphic Computing is analyzed through the introduction of FlexSpy, the first design-time security framework for thin-film transistor (TFT)-based Spiking Neural Networks (SNNs). The analysis reveals a unique quasi-DC leakage mechanism inherent to event-driven processing on flexible substrates. Despite the absence of internal triggers, an attacker can exploit this leakage to infer input classes and recover layer-wise spiking activity with high fidelity. Lightweight circuit-level countermeasures are proposed that suppress this leakage by up to 70% with minimal power overhead. Finally, the thesis presents a comprehensive security evaluation of FPGA-based Hyperdimensional Computing (HDC). It exposes a “robustness mismatch,” where HDC’s algorithmic error tolerance masks severe physical vulnerabilities. The work demonstrates successful Intellectual Property (IP) theft via deep-learning-assisted side-channel analysis and remote, internal sensing attacks using on-chip time-to-digital converters (TDCs). Furthermore, a targeted fault injection methodology (HyFault) is developed, capable of inducing precise misclassifications. In response, effective defenses-including dynamic masking and hypervector randomization-are introduced to restore security. Collectively, these contributions provide a foundational understanding of the physical security risks in emerging AI hardware, offering actionable design guidelines to ensure that the next generation of efficient edge accelerators is secure by design.","url":"https://doi.org/10.5445/ir/1000190105","authors":["Sapui, Brojogopal"],"tags":["AI accelerators","edge-AI","side channel","fault injection","countermeasures"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5445/ir/1000190105","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2505.24161","name":"Proxy Target: Bridging the Gap Between Discrete Spiking Neural Networks and Continuous Control","source":"datacite","abstract":"Spiking Neural Networks (SNNs) offer low-latency and energy-efficient decision making on neuromorphic hardware, making them attractive for Reinforcement Learning (RL) in resource-constrained edge devices. However, most RL algorithms for continuous control are designed for Artificial Neural Networks (ANNs), particularly the target network soft update mechanism, which conflicts with the discrete and non-differentiable dynamics of spiking neurons. We show that this mismatch destabilizes SNN training and degrades performance. To bridge the gap between discrete SNNs and continuous-control algorithms, we propose a novel proxy target framework. The proxy network introduces continuous and differentiable dynamics that enable smooth target updates, stabilizing the learning process. Since the proxy operates only during training, the deployed SNN remains fully energy-efficient with no additional inference overhead. Extensive experiments on continuous control benchmarks demonstrate that our framework consistently improves stability and achieves up to $32\\%$ higher performance across various spiking neuron models. Notably, to the best of our knowledge, this is the first approach that enables SNNs with simple Leaky Integrate and Fire (LIF) neurons to surpass their ANN counterparts in continuous control. This work highlights the importance of SNN-tailored RL algorithms and paves the way for neuromorphic agents that combine high performance with low power consumption. Code is available at https://github.com/xuzijie32/Proxy-Target.","url":"https://doi.org/10.48550/arxiv.2505.24161","authors":["Xu, Zijie","Bu, Tong","Hao, Zecheng","Ding, Jianhao","Yu, Zhaofei"],"tags":["Neural and Evolutionary Computing (cs.NE)","Machine Learning (cs.LG)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2505.24161","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2602.02439","name":"Energy-Efficient Neuromorphic Computing for Edge AI: A Framework with Adaptive Spiking Neural Networks and Hardware-Aware Optimization","source":"datacite","abstract":"Edge AI applications increasingly require ultra-low-power, low-latency inference. Neuromorphic computing based on event-driven spiking neural networks (SNNs) offers an attractive path, but practical deployment on resource-constrained devices is limited by training difficulty, hardware-mapping overheads, and sensitivity to temporal dynamics. We present NeuEdge, a framework that combines adaptive SNN models with hardware-aware optimization for edge deployment. NeuEdge uses a temporal coding scheme that blends rate and spike-timing patterns to reduce spike activity while preserving accuracy, and a hardware-aware training procedure that co-optimizes network structure and on-chip placement to improve utilization on neuromorphic processors. An adaptive threshold mechanism adjusts neuron excitability from input statistics, reducing energy consumption without degrading performance. Across standard vision and audio benchmarks, NeuEdge achieves 91-96% accuracy with up to 2.3 ms inference latency on edge hardware and an estimated 847 GOp/s/W energy efficiency. A case study on an autonomous-drone workload shows up to 312x energy savings relative to conventional deep neural networks while maintaining real-time operation.","url":"https://doi.org/10.48550/arxiv.2602.02439","authors":["Imanov, Olaf Yunus Laitinen","Kulali, Derya Umut","Yilmaz, Taner","Erisken, Duygu","Turhan, Rana Irem"],"tags":["Neural and Evolutionary Computing (cs.NE)","Emerging Technologies (cs.ET)","Machine Learning (cs.LG)","FOS: Computer and information sciences","FOS: Computer and information sciences","C.1.3; C.3; I.2.6; I.5.1","68T07, 68T05, 68M20"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2602.02439","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2602.01874","name":"Spin splitting torque enabled artificial neuron with self-reset via synthetic antiferromagnetic coupling","source":"datacite","abstract":"Spintronic artificial neurons are intriguing building blocks for energy efficient Neuromorphic Computing (NC). Nevertheless, most contemporary implementations rely on symmetry breaking external in plane magnetic fields (H_X) for neuron operation, which limits scalability and hardware practicality. We experimentally demonstrate an altermagnet/Synthetic Antiferromagnetic Coupling (SAF) based spintronic neuron that uses out of plane spin (σ_Z) polarized spin-splitting torque to eliminate the necessity of an external H_X. The neuron device also features intrinsic self-reset function facilitated by built-in exchange coupling. Furthermore, the proposed device is validated for Spiking Neural Network (SNN) applications by achieving test accuracies of 95.99% and 94.36% on the MNIST and N-MNIST datasets, respectively. These results demonstrate the hardware feasibility and compatibility of the proposed spintronic neuron, highlighting its potential for compact, scalable and energy-efficient neuromorphic computing systems.","url":"https://doi.org/10.48550/arxiv.2602.01874","authors":["Sekh, Badsha","Rahaman, Hasibur","Verma, Ravi Shankar","Maddu, Ramu","Jawahar, Kesavan","Piramanayagam, S. N."],"tags":["Applied Physics (physics.app-ph)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2602.01874","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2602.01133","name":"Parallel Training in Spiking Neural Networks","source":"datacite","abstract":"The bio-inspired integrate-fire-reset mechanism of spiking neurons constitutes the foundation for efficient processing in Spiking Neural Networks (SNNs). Recent progress in large models demands that spiking neurons support highly parallel computation to scale efficiently on modern GPUs. This work proposes a novel functional perspective that provides general guidance for designing parallel spiking neurons. We argue that the reset mechanism, which induces complex temporal dependencies and hinders parallel training, should be removed. However, any such modification should satisfy two principles: 1) preserving the functions of reset as a core biological mechanism; and 2) enabling parallel training without sacrificing the serial inference ability of spiking neurons, which underpins their efficiency at test time. To this end, we identify the functions of the reset and analyze how to reconcile parallel training with serial inference, upon which we propose a dynamic decay spiking neuron. We conduct comprehensive testing of our method in terms of: 1) Training efficiency and extrapolation capability. On 16k-length sequences, we achieve a 25.6x training speedup over the pioneering parallel spiking neuron, and our models trained on 2k-length can stably perform inference on sequences as long as 30k. 2) Generality. We demonstrate the consistent effectiveness of the proposed method across five task categories (image classification, neuromorphic event processing, time-series forecasting, language modeling, and reinforcement learning), three network architectures (spiking CNN/Transformer/SSMs), and two spike activation modes (spike/integer activation). 3) Energy consumption. The spiking firing of our neuron is lower than that of vanilla and existing parallel spiking neurons.","url":"https://doi.org/10.48550/arxiv.2602.01133","authors":["Huang, Yanbin","Yao, Man","Pan, Yuqi","Lv, Changze","Xu, Siyuan","Zheng, Xiaoqing","Xu, Bo","Li, Guoqi"],"tags":["Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2602.01133","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5167/uzh-284155","name":"Recurrent models of orientation selectivity enable robust early-vision processing in mixed-signal neuromorphic hardware","source":"datacite","abstract":"Mixed signal analog/digital neuromorphic circuits represent an ideal medium for reproducing bio-physically realistic dynamics of biological neural systems in real-time. However, similar to their biological counterparts, these circuits have limited resolution and are affected by a high degree of variability. By developing a recurrent spiking neural network model of the retinocortical visual pathway, we show how such noisy and heterogeneous computing substrate can produce linear receptive fields tuned to visual stimuli with specific orientations and spatial frequencies. Compared to strictly feed-forward schemes, the model generates highly structured Gabor-like receptive fields of any phase symmetry, making optimal use of the hardware resources available in terms of synaptic connections and neuron numbers. Experimental results validate the approach, demonstrating how principles of neural computation can lead to robust sensory processing electronic systems, even when they are affected by high degree of heterogeneity, e.g., due to the use of analog circuits or memristive devices.","url":"https://doi.org/10.5167/uzh-284155","authors":["Baruzzi, Valentina","Indiveri, Giacomo","Sabatini, Silvio P."],"tags":["570 Life sciences; biology"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5167/uzh-284155","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5167/uzh-284160","name":"Neuromorphic dreaming as a pathway to efficient learning in artificial agents","source":"datacite","abstract":"The computational substrate of biological systems exhibits remarkable abilities to learn complex skills quickly and efficiently. Inspired by this, we implement model-based reinforcement learning using spiking neural networks directly on mixed-signal neuromorphic hardware. This approach combines energy-efficient electronic circuits with high sample efficiency through alternating online (‘awake’) and offline (‘dreaming’) learning phases. Our model features two networks: an agent network that learns from real and simulated experiences and a world model network that generates simulated experiences. We validate this by training the system to play Atari Pong. First, we establish a baseline using only real experiences. Then, by ‘dreaming’, the required real experiences decrease significantly. The network dynamics runs in real-time on the analog neuromorphic circuits, with only the readout layers implemented and trained on a computer-in-the-loop. We present results that demonstrate the robustness and potential of energy-efficient mixed-signal neuromorphic processors for real-world applications.","url":"https://doi.org/10.5167/uzh-284160","authors":["Blakowski, Ingo","Zendrikov, Dmitrii","Indiveri, Giacomo","Capone, Cristiano"],"tags":["570 Life sciences; biology"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5167/uzh-284160","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5167/uzh-284152","name":"Event driven neural network on a mixed signal neuromorphic processor for EEG based epileptic seizure detection","source":"datacite","abstract":"Long-term monitoring of biomedical signals is essential for the modern clinical management of neurological conditions such as epilepsy. However, developing wearable systems that are able to monitor, analyze, and detect epileptic seizures with long-lasting operation times using current technologies is still an open challenge. Brain-inspired spiking neural networks (SNNs) represent a promising signal processing and computing framework as they can be deployed on ultra-low power neuromorphic computing systems, for this purpose. Here, we introduce a novel SNN architecture, co-designed and validated on a mixed-signal neuromorphic chip, that shows potential for always-on monitoring of epileptic activity. We demonstrate how the hardware implementation of this SNN captures the phenomenon of partial synchronization within neural activity during seizure periods. We assess the network using a full-custom asynchronous mixed-signal neuromorphic platform, processing analog signals in real-time from an Electroencephalographic (EEG) seizure dataset. The neuromorphic chip comprises an analog front-end (AFE) signal conditioning stage and an asynchronous delta modulation (ADM) circuit directly integrated on the same die, which can produce the stream of spikes as input to the SNN, directly from the analog EEG signals. We show a linear classifier in a post processing stage that is sufficient to reliably classify and detect seizures, from the local features extracted by the SNN, indicating the feasibility of full on-chip seizure monitoring in the future. This research marks a significant advancement toward developing embedded intelligent \"wear and forget\" units for resource-constrained environments. These units could autonomously detect and log relevant EEG events of interest in out-of-hospital environments, offering new possibilities for patient care and management of neurological disorders.","url":"https://doi.org/10.5167/uzh-284152","authors":["Bartels, Jim","Gallou, Olympia","Ito, Hiroyuki","Cook, Matthew","Sarnthein, Johannes","Indiveri, Giacomo","Ghosh, Saptarshi"],"tags":["570 Life sciences; biology"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5167/uzh-284152","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.17627865","name":"Scalable Construction of Spiking Neural Networks using up to thousands of GPUs archive","source":"datacite","abstract":"Diverse scientific and engineering research areas deal with discrete, time-stamped changes in large systems of interacting delay differential equations. Simulating such complex systems at scale on high-performance computing clusters demands efficient management of communication and memory. Inspired by the human cerebral cortex — a sparsely connected network of O(10^10) neurons, each forming O(10^3)--O(10^4) synapses and communicating via short electrical pulses called spikes — we study the simulation of large-scale spiking neural networks for computational neuroscience research. This work presents a novel network construction method for multi-GPU clusters and upcoming exascale supercomputers using the Message Passing Interface (MPI), where each process builds its local connectivity and prepares the data structures for efficient spike exchange across the cluster during state propagation. We demonstrate scaling performance of two cortical models using point-to-point and collective communication, respectively.","url":"https://doi.org/10.5281/zenodo.17627865","authors":["Tiddia, Gianmarco","Villamar, José","Golosio, Bruno","Pontisso, Luca","Simula, Francesco","Babu, Pooja","Pastorelli, Elena","Morrison, Abigail","Diesmann, Markus","Lonardo, Alessandro","Paolucci, Pier Stanislao","Senk, Johanna"],"tags":["spiking neural networks","large-scale simulations","GPU","exascale"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17627865","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2601.21548","name":"Training slow silicon neurons to control extremely fast robots with spiking reinforcement learning","source":"datacite","abstract":"Air hockey demands split-second decisions at high puck velocities, a challenge we address with a compact network of spiking neurons running on a mixed-signal analog/digital neuromorphic processor. By co-designing hardware and learning algorithms, we train the system to achieve successful puck interactions through reinforcement learning in a remarkably small number of trials. The network leverages fixed random connectivity to capture the task's temporal structure and adopts a local e-prop learning rule in the readout layer to exploit event-driven activity for fast and efficient learning. The result is real-time learning with a setup comprising a computer and the neuromorphic chip in-the-loop, enabling practical training of spiking neural networks for robotic autonomous systems. This work bridges neuroscience-inspired hardware with real-world robotic control, showing that brain-inspired approaches can tackle fast-paced interaction tasks while supporting always-on learning in intelligent machines.","url":"https://doi.org/10.48550/arxiv.2601.21548","authors":["Ambrosini, Irene","Blakowski, Ingo","Zendrikov, Dmitrii","Capone, Cristiano","Gava, Luna","Indiveri, Giacomo","De Luca, Chiara","Bartolozzi, Chiara"],"tags":["Robotics (cs.RO)","Artificial Intelligence (cs.AI)","Emerging Technologies (cs.ET)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2601.21548","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2601.21222","name":"FireFly-P: FPGA-Accelerated Spiking Neural Network Plasticity for Robust Adaptive Control","source":"datacite","abstract":"Spiking Neural Networks (SNNs) offer a biologically plausible learning mechanism through synaptic plasticity, enabling unsupervised adaptation without the computational overhead of backpropagation. To harness this capability for robotics, this paper presents FireFly-P, an FPGA-based hardware accelerator that implements a novel plasticity algorithm for real-time adaptive control. By leveraging on-chip plasticity, our architecture enhances the network's generalization, ensuring robust performance in dynamic and unstructured environments. The hardware design achieves an end-to-end latency of just 8~$μ$s for both inference and plasticity updates, enabling rapid adaptation to unseen scenarios. Implemented on a tiny Cmod A7-35T FPGA, FireFly-P consumes only 0.713~W and $\\sim$10K~LUTs, making it ideal for power- and resource-constrained embedded robotic platforms. This work demonstrates that hardware-accelerated SNN plasticity is a viable path toward enabling adaptive, low-latency, and energy-efficient control systems.","url":"https://doi.org/10.48550/arxiv.2601.21222","authors":["Li, Tenglong","Li, Jindong","Shen, Guobin","Zhao, Dongcheng","Zhang, Qian","Zeng, Yi"],"tags":["Hardware Architecture (cs.AR)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2601.21222","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2601.20870","name":"STAER: Temporal Aligned Rehearsal for Continual Spiking Neural Network","source":"datacite","abstract":"Spiking Neural Networks (SNNs) are inherently suited for continuous learning due to their event-driven temporal dynamics; however, their application to Class-Incremental Learning (CIL) has been hindered by catastrophic forgetting and the temporal misalignment of spike patterns. In this work, we introduce Spiking Temporal Alignment with Experience Replay (STAER), a novel framework that explicitly preserves temporal structure to bridge the performance gap between SNNs and ANNs. Our approach integrates a differentiable Soft-DTW alignment loss to maintain spike timing fidelity and employs a temporal expansion and contraction mechanism on output logits to enforce robust representation learning. Implemented on a deep ResNet19 spiking backbone, STAER achieves state-of-the-art performance on Sequential-MNIST and Sequential-CIFAR10. Empirical results demonstrate that our method matches or outperforms strong ANN baselines (ER, DER++) while preserving biologically plausible dynamics. Ablation studies further confirm that explicit temporal alignment is critical for representational stability, positioning STAER as a scalable solution for spike-native lifelong learning. Code is available at https://github.com/matteogianferrari/staer.","url":"https://doi.org/10.48550/arxiv.2601.20870","authors":["Gianferrari, Matteo","Moussadek, Omayma","Salami, Riccardo","Fiorini, Cosimo","Tartarini, Lorenzo","Gandolfi, Daniela","Calderara, Simone"],"tags":["Neural and Evolutionary Computing (cs.NE)","Artificial Intelligence (cs.AI)","Machine Learning (cs.LG)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2601.20870","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18418271","name":"Fugu Software","source":"datacite","abstract":"Fugu software tool for spiking neural network algorithms.","url":"https://doi.org/10.5281/zenodo.18418271","authors":["Krygier, Michael C.","Severa, William","Ho, Yang","Rothganger, Fred","Wang, Felix","Musuvathy, Srideep","Aimone, James B."],"tags":["neuromorphic algorithms","spiking neural networks"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18418271","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18418270","name":"Fugu Software","source":"datacite","abstract":"Fugu software tool for spiking neural network algorithms.","url":"https://doi.org/10.5281/zenodo.18418270","authors":["Krygier, Michael C.","Severa, William","Ho, Yang","Rothganger, Fred","Wang, Felix","Musuvathy, Srideep","Aimone, James B."],"tags":["neuromorphic algorithms","spiking neural networks"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18418270","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5061/dryad.z612jm6r0","name":"Ventral pallidum efferent pathways via mediodorsal thalamus and lateral habenula mediate distinct aspects of default mode network regulation","source":"datacite","abstract":"Transitions between internal and external focus are fundamental to cognition. These shifts depend on the modulation of the Default Mode Network (DMN), of which the ventral pallidum (VP) is a key subcortical node. Here, we examine which VP efferent pathways mediate these transitions, using projection and cell-type-specific optogenetic silencing. We found that inhibition of the VP projection to lateral habenula (LHb) confers a learning advantage early during task acquisition. Conversely, silencing VP projections to mediodorsal thalamus (MD) improves performance during the late stage of the same task. Downregulation of the cholinergic VP population improved performance during both early and late stages. Thus, silencing these VP outputs promotes escape from a DMN brain state, facilitating attention to external stimuli. Our results confirm a role for VP in DMN regulation and indicate that MD and LHb VP efferent pathways, in concert with cholinergic neuromodulation, mediate different aspects of DMN regulation.","url":"https://doi.org/10.5061/dryad.z612jm6r0","authors":["Makedona, Epistimi-Anna","Kuo, Mu-En","Harvey, Michael","Rainer, Gregor"],"tags":["FOS: Biological sciences","FOS: Biological sciences","Ventral Pallidum","default mode network","Lateral Habenula","Mediodorsal Thalamus","Behavior"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5061/dryad.z612jm6r0","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5061/dryad.x0k6djhwb","name":"Impact of the entorhinal feed-forward connection to the CA3 on hippocampal coding","source":"datacite","abstract":"Each sub-region of the hippocampus plays a critical computational role in the formation of episodic learning and memory, but studies have yet to show and interpret the individual spiking dynamics of each region and how that information is passed between each subregion. This is in part due to the difficulty in accessing individual communicating axons. Here, we created a novel microfluidic device that facilitates network growth of four separated hippocampal subregions over a micro-electrode array. This device enabled monitoring single axons over two electrodes so direction of spike propagation in interregional communication could be ascertained. In this in vitro hippocampal study, we compared spiking dynamics across two novel four-compartment device architectures: one with four sets of axon tunnels between subregions that excluded the perforant pathway from EC-CA3, and one with five sets of axon tunnels that included the EC-CA3 connection. We found 30-90% faster feed-forward firing rates (shorter interspike intervals) in axons in the five-tunnel model with 35-75% slower bursting dynamics (longer interburst intervals) compared to the four-tunnel model. Comparing the percentage of spikes in bursts between array designs, the five-tunnel architecture showed that the CA3-CA1 and CA1-EC axons had more spikes in bursts than the four-tunnel counterpart suggesting more structured information transfer. Feedback firing rates were similar between configurations. The faster feed-forward inter-regional spiking in the more natural five-tunnel configuration than with four-tunnel suggests tighter control of spiking and possibly more precise communication between subregions.","url":"https://doi.org/10.5061/dryad.x0k6djhwb","authors":["Lassers, Samuel","Khatri, Shazfa","Chen, Ruiyi","Vakilna, Yash","Tang, William","Brewer, Gregory"],"tags":["FOS: Engineering and technology","FOS: Engineering and technology","spike trains","Memory","Neurons","CA3","Perforant Pathway","Hippocampus"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5061/dryad.x0k6djhwb","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5061/dryad.cjsxksngp","name":"Real-time VIM thalamus recordings during peripheral nerve stimulation treatment for essential tremor: DBS intraoperative dataset","source":"datacite","abstract":"Background: Essential tremor (ET), the most common movement disorder in adults, presents with involuntary shaking of the upper extremities during postural hold and kinetic tasks linked to dysfunction in the cerebellothalamo-cortical network. Recently, transcutaneous afferent patterned stimulation (TAPS), applied through a wrist-worn device, has emerged as a non-invasive treatment for medication-refractory ET. However, its mechanism remains unclear. Objective: We hypothesize that TAPS reduces tremors through modulation of the VIM thalamus in the cerebellothalamo-cortical network. Methods: Employing refractory pure ET patients seeking VIM deep brain stimulation (DBS), we quantified clinical tremor improvement following TAPS treatment in a pre-operative setting, followed by intra-operative microelectrode recording of the contralateral thalamus with concurrent TAPS treatment on and off. Results: After one preoperative session, TAPS significantly reduces upper limb tremor average (0.61, p = 0.002), with an asymmetric effect favoring the treated limb (p = 0.047) and the greatest improvement tending to kinetic tremor (R2 = 0.943, p = 0.002). The magnitude of TAPS-related tremor reduction demonstrates a positive correlation with the modulation of alpha (R2 = 0.213, p &lt; 0.001) and beta band LFPs (R2 = 0.255, p &lt; 0.001) in the VIM. TAPS also suppressed spiking activity in the VIM (R2 = 0.104, p = 0.029), though it was uncorrelated with the degree of tremor reduction. Of note, TAPS-related modulation of LFPs and spiking activity was greatest near the optimal placement location for the DBS lead in treating ET (R2 = 0.122, p = 0.006). Conclusion: In sum, TAPS likely reduces tremor in ET by modulating the VIM and connected nodes in the cerebello-thalamo-cortical pathway.","url":"https://doi.org/10.5061/dryad.cjsxksngp","authors":["Luu, Cuong","Ranum, Jordan","Youn, Youngwon","Perrault, Jennifer","Krause, Bryan","Banks, Matthew","Buyan-Dent, Laura","Ludwig, Kip","Lake, Wendell","Suminski, Aaron"],"tags":["FOS: Medical engineering","FOS: Medical engineering","Essential tremor","Peripheral nerve stimulation","Neuromodulation","VIM","cerebello-thalamo-cortical network","deep brain stimulation"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5061/dryad.cjsxksngp","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5061/dryad.f1vhhmh4m","name":"Impact of background input on memory consolidation in In-Vitro neural networks","source":"datacite","abstract":"Memory consolidation is a complex process, that can be divided into two stages: first, memories are temporary stored in hippocampus and in the second stage, repeated replay slowly transfers memories to the neo-cortex for long-term consolidation. This 2nd stage occurs during slow wave sleep, a phase characterized in the cortex by low cholinergic tone and low afferent input. A recent in-vitro study showed that high cholinergic tone hampers memory consolidation, probably due to lowered network excitability (defined as the mean network response to one neuron spiking). Here we investigate whether low background input contributes to memory consolidation. We used cortical neuronal networks on multi electrode arrays to study memory. When input deprived, these networks develop an activity-connectivity balance. Focal stimuli initially disrupt the existing balance, inducing connectivity changes. When repeated, this effect fades and the response becomes part of spontaneous patterns (memory formation). Application of the same stimulus hours later does not affect connectivity indicating that memory was consolidated. We applied five periods (10 min each) of focal electrical stimulation at different electrodes (A B A), separated by 1 hour of spontaneous activity . Some cultures were transfected to express channelrhopsins (ChR2) enabling global optogenetic background stimulation. We used 12 control, 15 ChR2 cultures with no background input and 8 ChR2 cultures with superimposed random optogenetic stimulation during electrical stimulation periods (fmean=5 Hz) to mimic afferent input. Background stimulation acutely reduced network excitability during stimulation without persisting effects after cessation. ChR2 cultures showed significantly more dispersed spiking outside network bursts, and network excitability tended to be lower than in control cultures. Stimulation at electrodes A and B induced memory traces in control cultures. Return to electrode A did not further affect connectivity, showing that memory trace A had been consolidated. Background stimulation impeded the formation of memory traces following electrical stimulation at either electrode. ChR2 expression alone also obstructed memorization. These findings confirm the importance of low background afferent input for memory consolidation. The presence of background afferent inputs reduced network excitability, similar to high cholinergic tone. This leads to the conclusion that sufficient network excitability is crucial for memory consolidation, and high network excitability may be a critical feature of slow wave sleep that makes it more suitable for memory consolidation than the awake state.","url":"https://doi.org/10.5061/dryad.f1vhhmh4m","authors":["Lamberti, Martina","Kikirikis, Nikolaos","van Putten, Michel J.A.M.","le Feber, Joost"],"tags":["FOS: Biological sciences","FOS: Biological sciences","Slow-wave Sleep","Memory consolidation","Network excitability","Background stimulation"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.5061/dryad.f1vhhmh4m","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5061/dryad.8cz8w9h0d","name":"Spatial coding dysfunction and network instability in the aging medial entorhinal cortex","source":"datacite","abstract":"Across species, spatial memory declines with age, possibly reflecting altered hippocampal and medial entorhinal cortex (MEC) function. However, the integrity of cellular and network-level spatial coding in aged MEC is unknown. Here, we leveraged in vivo electrophysiology to assess MEC function in young, middle-aged, and aged mice navigating virtual environments. In aged grid cells, we observed impaired stabilization of context-specific spatial firing, correlated with spatial memory deficits. Additionally, aged grid networks shifted firing patterns often, but with poor alignment to context changes. Aged spatial firing was also unstable in an unchanging environment. In these same mice, we identified 458 genes differentially expressed with age in MEC, 61 of which had expression correlated with spatial coding quality. These genes were interneuron-enriched and related to synaptic plasticity, notably including a perineuronal net component. Together, these findings identify coordinated transcriptomic, cellular, and network changes in MEC implicated in impaired spatial memory in aging.","url":"https://doi.org/10.5061/dryad.8cz8w9h0d","authors":["Herber, Charlotte S.","Pratt, Karishma J.B.","Shea, Jeremy M.","Villeda, Saul A.","Giocomo, Lisa M."],"tags":["Aging","medial entorhinal cortex","grid cell","Spatial memory","FOS: Biological sciences","FOS: Biological sciences","Electrophysiology","Virtual reality"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5061/dryad.8cz8w9h0d","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5061/dryad.ffbg79d2w","name":"Data from: Brain-state mediated modulation of inter-laminar dependencies in visual cortex","source":"datacite","abstract":"Spatial attention is critical for recognizing behaviorally relevant objects in a cluttered environment. How the deployment of spatial attention aids the hierarchical computations of object recognition remains unclear. We investigated this in the laminar cortical network of visual area V4, an area strongly modulated by attention. We found that deployment of attention strengthened unique dependencies in neural activity across cortical layers. On the other hand, shared dependencies were reduced within the excitatory population of a layer. Surprisingly, attention strengthened unique dependencies within a laminar population. Crucially, these modulation patterns were also observed during successful behavioral outcomes that are thought to be mediated by internal brain state fluctuations. Successful behavioral outcomes were also associated with phases of reduced neural excitability, suggesting a mechanism for enhanced information transfer during optimal states. Our results suggest common computation goals of optimal sensory states that are attained by either task demands or internal fluctuations.","url":"https://doi.org/10.5061/dryad.ffbg79d2w","authors":["Das, Anirban","Sheffield, Alec","Nandy, Anirvan","Jadi, Monika"],"tags":["FOS: Biological sciences","FOS: Biological sciences","Macaque","Visual cortex","Electrophysiology","Attention"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.5061/dryad.ffbg79d2w","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5061/dryad.rxwdbrvh3","name":"Spike-timing based coding in neuromimetic tactile system enables dynamic object classification","source":"datacite","abstract":"Coding dynamic tactile information in spike timing is essential to human haptic exploration and dexterous object manipulation. Conventional electronic skins generate frames of tactile signals upon interaction with objects and are unfortunately ill-suited for efficient coding of temporal information and rapid feature extraction. Here, we report a neuromorphic tactile system that uses spike timing, especially the first-spike timing, to code dynamic tactile information about touch and grasp. This strategy enables the system to seamlessly code highly dynamic information with millisecond temporal resolution on par with the biological nervous system, yielding dynamic extraction of tactile features. Upon interaction with objects, the system rapidly classifies them in the initial phase of touch and grasp, thus paving the way to fast tactile feedback desired for neuro-robotics and neuro-prosthetics.","url":"https://doi.org/10.5061/dryad.rxwdbrvh3","authors":["Chen, Libo","Karilanova, Sanja","Chaki, Soumi","Wen, Chenyu","Wang, Lisha","Winblad, Bengt","Zhang, Shili","Ozcelikkale, Ayca","Zhang, Zhibin"],"tags":["neuromorphic circuit","Tactile sensing","electronic skin","Machine learning","FOS: Electrical engineering, electronic engineering, information engineering","FOS: Electrical engineering, electronic engineering, information engineering"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.5061/dryad.rxwdbrvh3","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5061/dryad.sn02v6xbb","name":"Data for: Brain control of bimanual movement enabled by recurrent neural networks","source":"datacite","abstract":"Brain-computer interfaces have so far focused largely on enabling the control of a single effector, for example a single computer cursor or robotic arm. Restoring multi-effector motion could unlock greater functionality for people with paralysis (e.g., bimanual movement). However, it may prove challenging to decode the simultaneous motion of multiple effectors, as we recently found that a compositional neural code links movements across all limbs and that neural tuning changes nonlinearly during dual-effector motion. In this study, we demonstrate the feasibility of high-quality bimanual control of two cursors via neural network (NN) decoders. This dataset represents all neural activity recorded during these experiments. This includes the neural activity corresponding to unimanual and bimanual hand movements during (1) instructed delay experiments and (2) real-time BCI control of two cursors. Code associated with the data can be found here: https://github.com/d-r-deo/bimanualBCI The journal article can be found here: https://doi.org/10.1038/s41598-024-51617-3","url":"https://doi.org/10.5061/dryad.sn02v6xbb","authors":["Deo, Darrel","Willett, Francis","Avansino, Donald","Hochberg, Leigh","Henderson, Jaimie","Shenoy, Krishna"],"tags":["Biomedical engineering","Computational neuroscience","Machine learning","Motor cortex","Brain-Computer Interface","brain-machine interface","BCI","FOS: Medical biotechnology"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.5061/dryad.sn02v6xbb","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5061/dryad.7h44j1013","name":"The flow of axonal information among hippocampal subregions: 2. Patterned stimulation sharpens routing of information transmission","source":"datacite","abstract":"The subregions of the hippocampal formation are essential for episodic learning and memory formation, yet the spike dynamics of each region contributing to this function are poorly understood, in part because of a lack of access to the inter-regional communicating axons. Here we reconstructed hippocampal networks confined to four subcompartments in 2D cultures on a multi-electrode array that monitors individual communicating axons. In our novel device, somal and axonal activity were measured simultaneously with the ability to ascertain the direction and speed of information transmission. Each subregion and inter-regional axons had unique power-law spiking dynamics, indicating differences in computational functions. After stimulation, spiking and burst rates decreased in all subregions, spikes per burst generally decreased, intraburst spike rates increased, and burst duration decreased, which were specific for each subregion. These changes in spiking dynamics post-stimulation were found to occupy a narrow range, consistent with the maintenance of the network at a critical state. Functional connections between the subregion neurons and communicating axons in our device revealed homeostatic network routing strategies post-stimulation in which spontaneous feedback activity was selectively decreased and balanced by decreased feed-forward activity. Post-stimulation, the number of functional connections per array decreased, but the reliability of those connections increased. The networks maintained a balance in spiking and bursting dynamics in response to stimulation and sharpened network routing. These plastic characteristics of the network revealed the dynamic architecture of hippocampal computations in response to stimulation by selective routing on a spatiotemporal scale in single axons.","url":"https://doi.org/10.5061/dryad.7h44j1013","authors":["Lassers, Samuel","Vakilna, Yash","Tang, William","Brewer, Gregory"],"tags":["FOS: Engineering and technology","FOS: Engineering and technology","networks","Hippocampus","electrode array","entorhinal","dentate","CA3"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.5061/dryad.7h44j1013","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5061/dryad.w3r2280w7","name":"Stimulus encoding by specific inactivation of cortical neurons","source":"datacite","abstract":"Neuronal ensembles are groups of neurons with correlated activity associated with sensory, motor, and behavioral functions. To explore how ensembles encode information, we investigated responses of visual cortical neurons in awake mice using volumetric two-photon calcium imaging during visual stimulation. We identified neuronal ensembles employing an unsupervised model-free algorithm and, besides neurons activated by the visual stimulus (termed “onsemble”), we also found neurons that are specifically inactivated (termed “offsemble”). Offsemble neurons showed faster calcium decay during stimuli, suggesting selective inhibition. In response to visual stimuli, each ensemble (onsemble+offsemble) exhibited small trial-to-trial variability, high orientation selectivity, and superior predictive accuracy for visual stimulus orientation, surpassing the sum of individual neuron activity. Thus, the combined selective activation and inactivation of cortical neurons enhance visual encoding as an emergent and distributed neural code.","url":"https://doi.org/10.5061/dryad.w3r2280w7","authors":["Pérez-Ortega, Jesús","Akrouh, Alejandro","Yuste, Rafael"],"tags":["ensembles","offsembles","FOS: Biological sciences","FOS: Biological sciences","onsembles","two-photon imaging","visual stimuli","General Physics and Astronomy"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.5061/dryad.w3r2280w7","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.25349/d9031z","name":"Extracellular Recordings from Human Brain Organoids Using High-density CMOS Arrays","source":"datacite","abstract":"Human brain organoids replicate much of the cellular diversity and developmental anatomy of the human brain. However, the physiological behavior of neuronal circuits within organoids remains relatively under-explored. With high-density CMOS microelectrode arrays (26,400 electrodes) and shank electrodes (960 electrodes), we probed broadband and three-dimensional extracellular field recordings generated by spontaneous activity of human brain organoids. These recordings simultaneously captured local field potentials (LFPs) and single-unit activity extracted through spike sorting. From spiking activity, we estimated a directed functional connectivity graph of synchronous neural network activity, which showed a large number of weak functional connections enmeshed within a network skeleton of significantly fewer strong connections. Treatment of the organoid with a benzodiazepine induced a reproducible signature response that shortened the inter-burst intervals, increased the uniformity of the firing pattern within each burst and decreased the population of weakly connected edges. Simultaneously examining the spontaneous LFPs and their phase alignment to spiking showed that spike bursts were coherent with theta oscillations in the LFPs. Our results demonstrate that human brain organoids have self-organized neuronal assemblies of sufficient size, cellular orientation, and functional connectivity to co-activate and generate field potentials from their collective transmembrane currents that phase-lock to spiking activity. These results point to the potential of brain organoids for the study of neuropsychiatric diseases, drug mechanisms, and the effects of external stimuli upon neuronal networks.","url":"https://doi.org/10.25349/d9031z","authors":["Sharf, Tal"],"tags":["FOS: Biological sciences","FOS: Biological sciences","human brain organoids","functional connectivity","extracellular recording"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.25349/d9031z","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5061/dryad.66t1g1k2w","name":"Patch-clamp recordings from dorsal raphe neurons","source":"datacite","abstract":"This dataset contains whole-cell electrophysiological recordings (patch-clamp recordings) from three cell types in mice: serotonin (5-HT) neurons, somatostatin (SOM)-expressing GABA interneurons, and layer 5 pyramidal neurons. 5-HT and GABA neurons were recorded in the dorsal raphe nucleus (DRN), which is the main source of serotonergic input to the forebrain. Together, they make up the majority of the neurons found in the DRN. This dataset can be used to investigate the intrinsic electrophysiological properties of these two types of DRN neurons and contrast them with another abundant and well-studied cell type, the L5 pyramidal neuron. This data was used in our paper describing a spiking neural network model of the dorsal raphe nucleus: Emerson F. Harkin, Michael B. Lynn, Alexandre Payeur, Jean-François Boucher, Léa Caya-Bissonnette, Dominic Cyr, Chloe Stewart, André Longtin, Richard Naud, and Jean-Claude Béïque. Temporal derivative computation in the dorsal raphe network revealed by an experimentally-driven augmented integrate-and-fire modeling framework. eLife, 2023. doi: 10.7554/eLife.72951","url":"https://doi.org/10.5061/dryad.66t1g1k2w","authors":["Harkin, Emerson","Lynn, Michael","Boucher, Jean-François","Caya-Bissonnette, Léa","Cyr, Dominic","Stewart, Chloe","Béïque, Jean-Claude"],"tags":["Neuroscience","FOS: Biological sciences","FOS: Biological sciences","Serotonin","Electrophysiology","patch clamp","dorsal raphe nucleus"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.5061/dryad.66t1g1k2w","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5061/dryad.k6djh9w6k","name":"Ensemble synchronization in the reassembly of Hydra's nervous system","source":"datacite","abstract":"Although much is known about how the structure of the nervous system develops, it is still unclear how its functional modularity arises. A dream experiment would be to observe the entire development of a nervous system, correlating the emergence of functional units with their associated behaviors. This is possible in the cnidarian Hydra vulgaris, which, after its complete dissociation into individual cells, can reassemble itself back together into a normal animal. We used calcium imaging to monitor the complete neuronal activity of dissociated Hydra as they re-aggregated over several days. Initially uncoordinated neuronal activity became synchronized into coactive neuronal ensembles. These local modules then synchronized with others, building larger functional ensembles that eventually extended throughout the entire reaggregate, generating neuronal rhythms similar to those of intact animals. Global synchronization was not due to neurite outgrowth but to strengthening of functional connections between ensembles. We conclude that Hydra’s nervous system achieves its functional reassembly through the hierarchical modularity of neuronal ensembles.","url":"https://doi.org/10.5061/dryad.k6djh9w6k","authors":["Lovas, Jonathan","Yuste, Rafael"],"tags":["FOS: Biological sciences","FOS: Biological sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.5061/dryad.k6djh9w6k","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2511.04109","name":"CBMC-V3: A CNS-inspired Control Framework Towards Agile Manipulation with SNN","source":"datacite","abstract":"As robotic arm applications expand beyond traditional industrial settings into service-oriented domains such as catering, household and retail, existing control algorithms struggle to achieve the level of agile manipulation required in unstructured environments characterized by dynamic trajectories, unpredictable interactions, and diverse objects. This paper presents a biomimetic control framework based on Spiking Neural Network (SNN), inspired by the human Central Nervous System (CNS), to address these challenges. The proposed framework comprises five control modules-cerebral cortex, cerebellum, thalamus, brainstem, and spinal cord-organized into three hierarchical control levels (first-order, second-order, and third-order) and two information pathways (ascending and descending). All modules are fully implemented using SNN. The framework is validated through both simulation and experiments on a commercial robotic arm platform across a range of control tasks. The results demonstrate that the proposed method outperforms the baseline in terms of agile motion control capability, offering a practical and effective solution for achieving agile manipulation.","url":"https://doi.org/10.48550/arxiv.2511.04109","authors":["Pang, Yanbo","Li, Qingkai","Zhao, Mingguo"],"tags":["Robotics (cs.RO)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2511.04109","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.6078/d1fm6s","name":"Data for: Hybrid dedicated and distributed coding in PMd/M1 provides separation and interaction of bilateral arm signals","source":"datacite","abstract":"Pronounced activity is observed in both hemispheres of the motor cortex during preparation and execution of unimanual movements. The organizational principles of bi-hemispheric signals and the functions they serve throughout motor planning remain unclear. Using an instructed-delay reaching task in monkeys, we identified two components in population responses spanning PMd and M1. A “dedicated” component, which segregated activity at the level of individual units, emerged in PMd during preparation. It was most prominent following movement when M1 became strongly engaged, and principally involved the contralateral hemisphere. In contrast to recent reports, these dedicated signals solely accounted for divergence of arm-specific neural subspaces. The other “distributed” component mixed signals for each arm within units, and the subspace containing it did not discriminate between arms at any stage. The statistics of the population response suggest two functional aspects of the cortical network: one that spans both hemispheres for supporting preparatory and ongoing processes, and another that is predominantly housed in the contralateral hemisphere and specifies unilateral output.","url":"https://doi.org/10.6078/d1fm6s","authors":["Dixon, Tanner","Merrick, Christina","Wallis, Joni","Ivry, Richard","Carmena, Jose"],"tags":["FOS: Biological sciences","FOS: Biological sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.6078/d1fm6s","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.7282/t3-zhhv-rh84","name":"Smart sensing by analog/digital hybrid neural networks","source":"datacite","abstract":"In this dissertation, the design, computer simulations, experimental evaluations, and theoretical analyses of new sensing schemes were systematically carried out. A novel power-efficient and low-complexity analog sensor design, which is the foundation of this PhD thesis, was validated through comprehensive simulations and hardware experiments. Additionally, a sensor in analog/digital hybrid single neuron and neural network prototype was developed for practical monitoring scenarios, progressing to ECG signal compression in the analog domain for health monitoring applications. The research further explores the integration of analog/digital hybrid neural networks for UAV applications, leveraging the strengths of both domains. Furthermore, the feasibility of applying analog/digital hybrid circuits in Spiking Neural Networks (SNNs) was explored, aiming to offload complex computations from the digital part to maximize computational efficiency while leveraging the energy-saving benefits of analog design. We validated the proposed methods using computer vision datasets, including digits, text, and objects with varying levels of recognition difficulty, to analyze the feasibility of the approach. Theoretical analyses and detailed simulations provide a deep understanding of signal recovery performance and parameter optimization. This dissertation is rooted in low-power analog sensor innovation and extends to persistent wireless sensing, biosensing applications, and hybrid neural network implementations.","url":"https://doi.org/10.7282/t3-zhhv-rh84","authors":["Hsieh, Yung-Ting"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.7282/t3-zhhv-rh84","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2509.23516","name":"Network-Optimised Spiking Neural Network for Event-Driven Networking","source":"datacite","abstract":"Delay-coupled systems often require low-latency decisions from sparse telemetry, where dense fixed-step neural inference is wasteful and can degrade near stability margins. We introduce Network-Optimised Spiking (NOS), a trainable two-state event-driven dynamical unit for delayed, graph-coupled streams, whose states map to a fast load variable and a slower recovery resource. NOS uses bounded excitability for finite buffers, explicit leak terms for service and damping, and graph-local coupling with per-link gates and communication delays, with differentiable resets compatible with surrogate-gradient training and neuromorphic execution. We prove existence and uniqueness of subthreshold equilibria, derive Jacobian-based stability conditions, and obtain a scalar network stability threshold that separates topology from node dynamics via a Perron-mode spectral condition. A stochastic arrival model aligned with telemetry smoothing explains increased variability as systems approach stability boundaries. On delayed graph forecasting and early-warning tasks from queue telemetry, NOS improves detection F1 and detection latency over MLP, RNN/GRU, and temporal GNN baselines under a common residual-based protocol, while providing calibration rules for resource-constrained deployments. Code and Demos: https://mbilal84.github.io/nos-snn-networking/","url":"https://doi.org/10.48550/arxiv.2509.23516","authors":["Bilal, Muhammad"],"tags":["Neural and Evolutionary Computing (cs.NE)","Machine Learning (cs.LG)","Networking and Internet Architecture (cs.NI)","Optimization and Control (math.OC)","FOS: Computer and information sciences","FOS: Computer and information sciences","FOS: Mathematics","FOS: Mathematics"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2509.23516","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5075/epfl-thesis-9739","name":"Taming neuronal noise with large networks","source":"datacite","abstract":"How does reliable computation emerge from networks of noisy neurons? While individual neurons are intrinsically noisy, the collective dynamics of populations of neurons taken as a whole can be almost deterministic, supporting the hypothesis that, in the brain, computation takes place at the level of neuronal populations. Mathematical models of networks of noisy spiking neurons allow us to study the effects of neuronal noise on the dynamics of large networks. Classical mean-field models, i.e., models where all neurons are identical and where each neuron receives the average spike activity of the other neurons, offer toy examples where neuronal noise is absorbed in large networks, that is, large networks behave like deterministic systems. In particular, the dynamics of these large networks can be described by deterministic neuronal population equations. In this thesis, I first generalize classical mean-field limit proofs to a broad class of spiking neuron models that can exhibit spike-frequency adaptation and short-term synaptic plasticity, in addition to refractoriness. The mean-field limit can be exactly described by a multidimensional partial differential equation; the long time behavior of which can be rigorously studied using deterministic methods. Then, we show that there is a conceptual link between mean-field models for networks of spiking neurons and latent variable models used for the analysis of multi-neuronal recordings. More specifically, we use a recently proposed finite-size neuronal population equation, which we first mathematically clarify, to design a tractable Expectation-Maximization-type algorithm capable of inferring the latent population activities of multi-population spiking neural networks from the spike activity of a few visible neurons only, illustrating the idea that latent variable models can be seen as partially observed mean-field models. In classical mean-field models, neurons in large networks behave like independent, identically distributed processes driven by the average population activity -- a deterministic quantity, by the law of large numbers. The fact the neurons are identically distributed processes implies a form of redundancy that has not been observed in the cortex and which seems biologically implausible. To show, numerically, that the redundancy present in classical mean-field models is unnecessary for neuronal noise absorption in large networks, I construct a disordered network model where networks of spiking neurons behave like deterministic rate networks, despite the absence of redundancy. This last result suggests that the concentration of measure phenomenon, which generalizes the ``law of large numbers'' of classical mean-field models, might be an instrumental principle for understanding the emergence of noise-robust population dynamics in large networks of noisy neurons.","url":"https://doi.org/10.5075/epfl-thesis-9739","authors":["Schmutz, Valentin Marc"],"tags":["spiking neurons","nonlinear Hawkes processes","mean-field approximations","spike-frequency adaptation","short-term synaptic plasticity","nonlocal transport equation","finite-size fluctuations","latent variable model"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.5075/epfl-thesis-9739","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5061/dryad.p631f","name":"Data from: Input-dependent frequency modulation of cortical gamma oscillations shapes spatial synchronization and enables phase coding","source":"datacite","abstract":"Fine-scale temporal organization of cortical activity in the gamma range (~25–80Hz) may play a significant role in information processing, for example by neural grouping (‘binding’) and phase coding. Recent experimental studies have shown that the precise frequency of gamma oscillations varies with input drive (e.g. visual contrast) and that it can differ among nearby cortical locations. This has challenged theories assuming widespread gamma synchronization at a fixed common frequency. In the present study, we investigated which principles govern gamma synchronization in the presence of input-dependent frequency modulations and whether they are detrimental for meaningful input-dependent gamma-mediated temporal organization. To this aim, we constructed a biophysically realistic excitatory-inhibitory network able to express different oscillation frequencies at nearby spatial locations. Similarly to cortical networks, the model was topographically organized with spatially local connectivity and spatially-varying input drive. We analyzed gamma synchronization with respect to phase-locking, phase-relations and frequency differences, and quantified the stimulus-related information represented by gamma phase and frequency. By stepwise simplification of our models, we found that the gamma-mediated temporal organization could be reduced to basic synchronization principles of weakly coupled oscillators, where input drive determines the intrinsic (natural) frequency of oscillators. The gamma phase-locking, the precise phase relation and the emergent (measurable) frequencies were determined by two principal factors: the detuning (intrinsic frequency difference, i.e. local input difference) and the coupling strength. In addition to frequency coding, gamma phase contained complementary stimulus information. Crucially, the phase code reflected input differences, but not the absolute input level. This property of relative input-to-phase conversion, contrasting with latency codes or slower oscillation phase codes, may resolve conflicting experimental observations on gamma phase coding. Our modeling results offer clear testable experimental predictions. We conclude that input-dependency of gamma frequencies could be essential rather than detrimental for meaningful gamma-mediated temporal organization of cortical activity.","url":"https://doi.org/10.5061/dryad.p631f","authors":["Lowet, Eric","Roberts, Mark","Hadjipapas, Avgis","Peter, Alina","van der Eerden, Jan","De Weerd, Peter"],"tags":["Arnold tongue","gamma oscillation","neural coding"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2015","doi":"10.5061/dryad.p631f","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5061/dryad.j5r51","name":"Data from: Computing the local field potential (LFP) from integrate-and-fire network models","source":"datacite","abstract":"Leaky integrate-and-fire (LIF) network models are commonly used to study how the spiking dynamics of neural networks changes with stimuli, tasks or dynamic network states. However, neurophysiological studies in vivo often rather measure the mass activity of neuronal microcircuits with the local field potential (LFP). Given that LFPs are generated by spatially separated currents across the neuronal membrane, they cannot be computed directly from quantities defined in models of point-like LIF neurons. Here, we explore the best approximation for predicting the LFP based on standard output from point-neuron LIF networks. To search for this best “LFP proxy”, we compared LFP predictions from candidate proxies based on LIF network output (e.g, firing rates, membrane potentials, synaptic currents) with “ground-truth” LFP obtained when the LIF network synaptic input currents were injected into an analogous three-dimensional (3D) network model of multi-compartmental neurons with realistic morphology, spatial distributions of somata and synapses. We found that a specific fixed linear combination of the LIF synaptic currents provided an accurate LFP proxy, accounting for most of the variance of the LFP time course observed in the 3D network for all recording locations. This proxy performed well over a broad set of conditions, including substantial variations of the neuronal morphologies. Our results provide a simple formula for estimating the time course of the LFP from LIF network simulations in cases where a single pyramidal population dominates the LFP generation, and thereby facilitate quantitative comparison between computational models and experimental LFP recordings in vivo.","url":"https://doi.org/10.5061/dryad.j5r51","authors":["Mazzoni, Alberto","Lindén, Henrik Anders","Cuntz, Hermann","Lansner, Anders","Panzeri, Stefano","Einevoll, Gaute Tomas","Lindén, Henrik"],"tags":["Local Field Potential","integrate and fire","simulations"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2016","doi":"10.5061/dryad.j5r51","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.48550/arxiv.2412.16111","name":"How random connectivity shapes the fluctuating dynamics of finite-size neural populations","source":"datacite","abstract":"Mesoscopic models of finite-size neuronal populations are crucial to understand the dynamics of neural networks in the brain, especially their fluctuations and response to stimuli. However, current theories to derive such models are based on homogeneous all-to-all (full) connectivity. This assumption neglects the variance in the connectivity of biologically realistic networks with connection probabilities $p&lt;1$ (non-full connectivity). To gain insight into the different fluctuation mechanisms underlying neural variability at the population level, we derive and analyze a stochastic mean-field model for finite-size networks of Poisson neurons with random connectivity (including non-full connectivity), external noise and disordered mean inputs. We treat the quenched disorder of the connectivity by an annealed approximation enabling a doubly stochastic description of synaptic inputs for finite network size. A further reduction leads to a low-dimensional closed system of coupled Langevin equations for the mean and variance of the membrane potentials as well as a variable capturing finite-size fluctuations. Compared to microscopic simulations, the mesoscopic model describes the fluctuations and nonlinearities well and outperforms previous theories that neglected the variance in the connectivity. The joint effect of connectivity disorder and finite network size can be analytically understood by a softening of the effective nonlinearity and the multiplicative character of spiking noise. The mesoscopic theory shows that quenched disorder can stabilize the asynchronous state, and it correctly predicts large quantitative and non-trivial qualitative effects of connection probability on the variance of the population firing rate and its dependence on stimulus strength. In conclusion, our theory elucidates how disordered connectivity shapes nonlinear dynamics and fluctuations of neural populations.","url":"https://doi.org/10.48550/arxiv.2412.16111","authors":["Greven, Nils E.","Ranft, Jonas","Schwalger, Tilo"],"tags":["Neurons and Cognition (q-bio.NC)","FOS: Biological sciences","FOS: Biological sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.48550/arxiv.2412.16111","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5075/epfl-thesis-7546","name":"Multi-memristive synaptic architectures for training neural networks","source":"datacite","abstract":"Highly data-centric AI workloads require that new computing paradigms be adopted because the performance of traditional CPU- and GPU-based systems are limited by data access and transfer. Training deep neural networks with millions of tunable parameters takes days or even weeks using relatively powerful heterogeneous systems, and it consumes more than hundreds of kilowatts of power. In-memory computing with memristive devices is a very promising avenue to accelerate deep learning because computations take place within the memory itself, eliminating the need to move the data around. The synaptic weights can be represented by the analog conductance states of memristive devices organized in crossbar arrays. The computationally expensive operations associated with deep learning training can be performed in place by exploiting the physical attributes and state dynamics of memristive devices and circuit laws. Memristive cores are also of particular interest due to the non-volatility, scalability, CMOS-compatibility and fast access time of the constituent devices. In addition, the multi-level storage capability of certain memristive technologies is especially attractive for increasing the information storage capacity of such cores. Large-scale demonstrations that combine memristive synapses with digital or analog CMOS circuitry indicate the potential of in-memory computing to accelerate deep learning. However, these implementations are highly vulnerable to non-ideal memristive device behavior. In particular, the limited weight representation capability, intra-device and array-level variability and temporal variations of conductance states pose significant challenges to achieving training accuracies that are comparable to conventional von Neumann implementations. Design solutions that can address these non-idealities without introducing significant implementation complexities will be critical for future memristive systems. This thesis proposes a novel synaptic architecture that can overcome a multitude of the aforementioned device non-idealities. In particular, it investigates the use of multiple memristive devices as a single computational primitive to represent a neural network weight and examines experimentally how such a compute primitive can improve non-desired memristive behavior. We propose a novel technique to arbitrate between the constituent devices of the synapse that can easily be implemented in hardware and adds only minimal energy overhead. We explore the proposed concept over various networks such as conventional non-spiking and spiking neural networks. The efficacy of this synaptic architecture is demonstrated for different training approaches including fully memristive and mixed-precision in-memory training by means of experiments using more than 1 million phase-change memory devices. Furthermore, we show that the proposed concept can be a key enabler to exploit binary memristive devices for deep-learning training.","url":"https://doi.org/10.5075/epfl-thesis-7546","authors":["Boybat Kara, Irem"],"tags":["In-memory computing","neuromorphic computing","memristive device","multi-memristive synaptic architecture","neural network training","artificial neural network","spiking neural network","fully-memristive training"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2020","doi":"10.5075/epfl-thesis-7546","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.5281/zenodo.18367072","name":"Privacy-Preserving Federated Spiking Neural Networks for Real-Time Target Detection in Distributed ISAC Edge Systems","source":"datacite","abstract":"This study proposes a privacy-preserving federated spiking neural network (SNN) framework for real-time target detection in integrated sensing and communication (ISAC) edge networks. The framework enables distributed vehicular nodes operating at 28 GHz to collaboratively learn from spike-based sensing data without sharing raw observations, thereby protecting sensitive location information. By combining federated learning with secure model aggregation, adaptive differential privacy, and spike-aware temporal learning, the system ensures robust privacy protection while supporting efficient learning under non-IID data and real-time constraints. Extensive experiments using data from 500 vehicles and 50,000 observations demonstrate that the proposed approach achieves a high detection performance of 94.3% F1-score under strict privacy guarantees, with low inference latency and significantly reduced energy consumption. These results highlight the framework’s suitability for privacy-sensitive vehicular and smart-city applications, supporting scalable, energy-efficient, and trustworthy 6G ISAC deployment.","url":"https://doi.org/10.5281/zenodo.18367072","authors":["Mohammad Zahangir Alam"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18367072","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:22.345Z"},{"id":"doi:10.20944/preprints202301.0502.v1","name":"Flexible Working Memory Model in Spiking Neural Network With Two Types of Plasticity","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202301.0502.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.20944/preprints202301.0502.v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1101/2023.10.12.560618","name":"A lightweight data-driven spiking neural network model of  <i>Drosophila</i>  olfactory nervous system with dedicated hardware support","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.10.12.560618","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.10.12.560618","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1101/2022.11.09.515838","name":"A Biologically Plausible Spiking Neural Network for Decoding Kinematics in the Hippocampus and Premotor Cortex","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.11.09.515838","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.11.09.515838","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.21203/rs.3.rs-3191285/v1","name":"BiœmuS: A new tool for neurological disorders studies through real-time emulation and hybridization using biomimetic Spiking Neural Network","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3191285/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-3191285/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1101/2023.09.05.556241","name":"BiœmuS: A new tool for neurological disorders studies through real-time emulation and hybridization using biomimetic Spiking Neural Network","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.09.05.556241","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.09.05.556241","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1101/2023.05.12.540597","name":"Hippocampome.org v2.0: a knowledge base enabling data-driven spiking neural network simulations of rodent hippocampal circuits","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.05.12.540597","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.05.12.540597","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1101/2022.12.12.520017","name":"Modelling Spontaneous Firing Activity of the Motor Cortex in a Spiking Neural Network with Random and Local Connectivity","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.12.12.520017","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.12.12.520017","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1101/2023.05.23.541669","name":"Artificial cerebellum on FPGA: Realistic real-time cerebellar spiking neural network model capable of real-world adaptive motor control","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.05.23.541669","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.05.23.541669","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1101/2022.08.10.503437","name":"Dynamic Control of Eye-Head Gaze Shifts by a Spiking Neural Network Model of the Superior Colliculus","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.08.10.503437","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.08.10.503437","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.21203/rs.3.rs-2732425/v1","name":"Synaptic Transistor with Multiple Biological Function Based on Metal-Organic Frameworks Combined with LIF Model of Spiking Neural Network to Recognize Temporal Information","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-2732425/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-2732425/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1101/2021.10.26.465919","name":"Brain-inspired spiking neural network controller for a neurorobotic whisker system","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2021.10.26.465919","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.1101/2021.10.26.465919","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.21203/rs.3.rs-1860157/v1","name":"CIRM-SNN: Certainty Interval Reset Mechanism Spiking Neuron for Enabling High Accuracy Spiking Neural Network","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-1860157/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.21203/rs.3.rs-1860157/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1101/2022.02.01.478640","name":"A Spiking Neural Network Model of Rodent Head Direction calibrated with Landmark Free Learning","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.02.01.478640","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.02.01.478640","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1101/2022.04.08.487667","name":"A spiking neural network model for the control of oscillatory phase differences between multiple brain areas","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.04.08.487667","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.04.08.487667","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.21203/rs.3.rs-249741/v1","name":"An All-in-One Biomimetic 2D Spiking Neural Network","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-249741/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.21203/rs.3.rs-249741/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1101/2022.04.07.487574","name":"Production of adaptive movement patterns via an insect inspired Spiking Neural Network Central Pattern Generator","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.04.07.487574","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.04.07.487574","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.21203/rs.3.rs-2383481/v1","name":"Prediction and Detection of Virtual Reality induced Cybersickness: A Spiking Neural Network Approach Using Spatiotemporal EEG Brain Data and Heart Rate Variability","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-2383481/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.21203/rs.3.rs-2383481/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1101/2021.10.05.463158","name":"A spiking neural network model of the Superior Colliculus that is robust to changes in the spatial-temporal input","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2021.10.05.463158","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.1101/2021.10.05.463158","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.20944/preprints202104.0202.v1","name":"A Brief Review on Spiking Neural Network - A Biological Inspiration<b> </b>","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202104.0202.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.20944/preprints202104.0202.v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2021.09.24.461624","name":"Disynaptic Effect of Hilar Cells on Pattern Separation in A Spiking Neural Network of Hippocampal Dentate Gyrus","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2021.09.24.461624","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.1101/2021.09.24.461624","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.20944/preprints202102.0083.v1","name":"Unsupervised Learning Method for SAR Image Classification Based on Spiking Neural Network","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202102.0083.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.20944/preprints202102.0083.v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1101/2020.01.23.916593","name":"A Spiking Neural Network Model for Category Learning","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2020.01.23.916593","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2020","doi":"10.1101/2020.01.23.916593","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1101/2021.10.15.464581","name":"Predicting the Influence of Axon Myelination on Sound Localization Precision Using a Spiking Neural Network Model of Auditory Brainstem","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2021.10.15.464581","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.1101/2021.10.15.464581","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1101/2021.05.25.445653","name":"A Neuroscience-Inspired Spiking Neural Network for Auditory Spatial Attention Detection Using Single-Trial EEG","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2021.05.25.445653","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.1101/2021.05.25.445653","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1101/867366","name":"A spiking neural-network model of goal-directed behaviour","source":"preprints","abstract":"","url":"https://doi.org/10.1101/867366","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2019","doi":"10.1101/867366","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1101/2020.07.23.217265","name":"An integrate-and-fire spiking neural network model simulating artificially induced cortical plasticity","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2020.07.23.217265","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2020","doi":"10.1101/2020.07.23.217265","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1101/2020.06.11.147405","name":"Learning the synaptic and intrinsic membrane dynamics underlying working memory in spiking neural network models","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2020.06.11.147405","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2020","doi":"10.1101/2020.06.11.147405","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1101/461160","name":"Spike: A GPU Optimised Spiking Neural Network Simulator","source":"preprints","abstract":"","url":"https://doi.org/10.1101/461160","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2018","doi":"10.1101/461160","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1101/424127","name":"Microstimulation in a spiking neural network model of the midbrain superior colliculus","source":"preprints","abstract":"","url":"https://doi.org/10.1101/424127","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2018","doi":"10.1101/424127","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.21203/rs.3.rs-10204905/v1","name":"FL-SNNIDS: Federated Spiking Neural Networks for Energy-Efficient Intrusion Detection in Agricultural SDN-IoT Networks","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-10204905/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-10204905/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1101/236224","name":"Fully unsupervised online spike sorting based on an artificial spiking neural network","source":"preprints","abstract":"","url":"https://doi.org/10.1101/236224","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2017","doi":"10.1101/236224","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.20944/preprints202607.1946.v1","name":"Spike-Aware Propagation Approximation for Conductance-Based LIF Equations","source":"europepmc","abstract":"","url":"https://doi.org/10.20944/preprints202607.1946.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.20944/preprints202607.1946.v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.21203/rs.3.rs-10249388/v1","name":"Embedding Formal Worst-Case Latency Proofs and Memory-Safety Certificates into the snn-mlir MLIR Lowering Pipeline for IEC 62304-Compliant Edge Deployment of Spiking Neural Networks","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-10249388/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-10249388/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.20944/preprints202607.1785.v1","name":"Multiplication-Free Blood Glucose Estimation via Spiking Neural Networks on Wearable Impedance Biosensors","source":"europepmc","abstract":"","url":"https://doi.org/10.20944/preprints202607.1785.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.20944/preprints202607.1785.v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.08.10.743867","name":"Graph theory for the analysis of micro-electrode array recordings of human brain slices – framework and benchmarking","source":"europepmc","abstract":"","url":"https://doi.org/10.64898/2026.08.10.743867","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.08.10.743867","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.08.10.743856","name":"Estimation of the time course of excitatory and inhibitory conductance during oscillatory periods","source":"europepmc","abstract":"","url":"https://doi.org/10.64898/2026.08.10.743856","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.08.10.743856","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.07.17.739276","name":"Biologically Plausible Dopamine-Modulated STDP Model of Pavlovian Learning in Spiking Neural Networks","source":"europepmc","abstract":"","url":"https://doi.org/10.64898/2026.07.17.739276","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.07.17.739276","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.21203/rs.3.rs-10617517/v1","name":"Titration of the Generational Memory Window: Engine and Brake in the Evolutionary Substrate","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-10617517/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-10617517/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.07.28.741366","name":"Ephaptic coupling improves the neural population code","source":"europepmc","abstract":"","url":"https://doi.org/10.64898/2026.07.28.741366","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.07.28.741366","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.07.21.739801","name":"Simulating neural network criticality and resource dynamics with Rydberg gases","source":"europepmc","abstract":"","url":"https://doi.org/10.64898/2026.07.21.739801","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.07.21.739801","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.06.12.731882","name":"DeltaQ: Value-Guided Hebbian Learning in Spiking Neuronal Networks for Multi-Goal Navigation","source":"europepmc","abstract":"","url":"https://doi.org/10.64898/2026.06.12.731882","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.06.12.731882","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.05.12.724100","name":"A biologically-grounded cerebellar spiking network model with realistic synaptic transmission captures complex circuit dynamics","source":"europepmc","abstract":"Abstract Cerebellar neural circuit dynamics rely on a rich repertoire of synaptic and excitability mechanisms, which are thought to determine network computation in physiological and pathological conditions. In this work, we develop and validate a biologically-grounded spiking neural network of the cerebellar cortex, embedding key mechanisms of cellular excitability and synaptic transmission, and assess their impact on signal processing. Neuronal input-output functions, short-term synaptic plasticity, receptor-specific kinetics, and NMDA channel voltage-dependent gating were calibrated against detailed multicompartmental models through automatic tuning procedures. Incorporating these realistic biological properties allowed the network model to simulate key features observed in recordings from acute cerebellar slices. The neuronal discharge and local field potentials elicited by mossy fiber stimulation faithfully reproduced the natural patterns with millisecond precision. Then, selective receptor switch-off revealed the contribution of NMDA, GABA, and AMPA receptors to the frequency-dependent input-output function of the granular layer and Purkinje cells, linking previous empirical findings to specific synaptic mechanisms. This model combines high computational performance with biological realism and offers a computationally efficient framework to investigate neurophysiological phenomena and the neural correlates of behavior in large-scale long-lasting simulations, such as those needed to address the neural underpinnings of learning and of cerebellar pathologies.","url":"https://doi.org/10.64898/2026.05.12.724100","authors":["Marialaura De Grazia","Danilo Benozzo","Dimitri Rodarie","Filippo Marchetti","Egidio D’Angelo","Claudia Casellato"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.05.12.724100","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.06.18.733073","name":"Insect-inspired, efficient event-based classification of tactile features","source":"europepmc","abstract":"","url":"https://doi.org/10.64898/2026.06.18.733073","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.06.18.733073","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.08.02.741879","name":"Transcriptome-Inspired Spiking Simulations Uncover Human-Specific Prefrontal Dynamics and Provide a Mechanistic Platform for Species-Appropriate Disease Modeling","source":"europepmc","abstract":"","url":"https://doi.org/10.64898/2026.08.02.741879","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.08.02.741879","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.07.31.742067","name":"BRIDGE: A Computational Workflow from Single Neurons to Network of Mean-Field Models","source":"europepmc","abstract":"","url":"https://doi.org/10.64898/2026.07.31.742067","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.07.31.742067","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.05.18.725874","name":"Emergent Entrainment and Predictive Dynamics in Bio-Inspired Spiking Neural Networks","source":"europepmc","abstract":"","url":"https://doi.org/10.64898/2026.05.18.725874","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.05.18.725874","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.20944/preprints202605.1130.v1","name":"Spiking Neural Networks: Mathematical Foundations","source":"europepmc","abstract":"","url":"https://doi.org/10.20944/preprints202605.1130.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.20944/preprints202605.1130.v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.20944/preprints202605.0827.v1","name":"Spiking Neural Networks: A Tutorial on Models, Coding, and Training","source":"europepmc","abstract":"Spiking neural networks (SNNs) are often called the third generation of neural models. They communicate with brief asynchronous pulses rather than continuous values, which suits event-driven sensors and low-power neuromorphic hardware. The mathematics behind them is split across neuroscience textbooks, machine learning papers, and stochastic process literature, and a researcher entering the area runs into a notation problem before anything else. The same neuron model is written one way in a textbook, another way in a machine learning paper, and a third way in the stochastic process literature. This tutorial collects what a graduate student or research engineer needs in order to start working with SNNs, in one place and with one notation. We start with the leaky integrate-and-fire (LIF) neuron, derived from a conductance-based picture of the membrane. Reset semantics, the spike response model, and the broader family that includes Hodgkin-Huxley and adaptive exponential models are discussed. Network equations are written out for feedforward and recurrent architectures. We cover the main neural coding schemes (rate, time-to-first-spike, rank-order, phase, burst, population) and discuss when each is appropriate. The neuromorphic datasets a beginner is likely to encounter, including N-MNIST, DVS-Gesture, CIFAR10-DVS, SHD, and SSC, are described together with the tensor formats event-based data takes. For learning, we derive pair-based spike-timing-dependent plasticity from exponential traces and develop the surrogate gradient framework, which has become the dominant tool for training deep SNNs by backpropagation through time. Reset semantics, the choice of surrogate function, and common pitfalls in BPTT are addressed in a way that maps onto code. Alternative training paradigms (e-prop, EventProp, SLAYER, three-factor rules, ANN-to-SNN conversion) are introduced briefly so the reader knows what else is available. A practical section walks through a first SNN training loop with framework-agnostic pseudocode and points to the main software libraries (snnTorch, SpikingJelly, Norse). Throughout the article, equations carry derivational status labels (exact, reduction, approximation, heuristic) so that the reader sees at a glance which steps are mathematical identities and which involve approximations. We do not cover hardware implementation, detailed point process theory, expressivity proofs, or open problems in SNN complexity; these belong in a more advanced treatment. The article is meant to be read linearly, and a suggested reading path closes it.","url":"https://doi.org/10.20944/preprints202605.0827.v1","authors":["İsmail Can Dikmen"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.20944/preprints202605.0827.v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.04.02.715849","name":"The Cerebellar Engine: Multiscale Digital Brain Co-simulations Reveal How Cerebellar Spiking Architecture Shapes Cortical Coherence","source":"europepmc","abstract":"","url":"https://doi.org/10.64898/2026.04.02.715849","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.04.02.715849","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.06.27.734988","name":"Uncovering internal states with a robust shared-state multi-neuron GLM-HMM framework","source":"europepmc","abstract":"","url":"https://doi.org/10.64898/2026.06.27.734988","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.06.27.734988","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.03.18.712631","name":"Automated derivation of mean field models from spiking neural networks for the simulation of brain dynamics","source":"europepmc","abstract":"","url":"https://doi.org/10.64898/2026.03.18.712631","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.03.18.712631","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.21203/rs.3.rs-9385203/v1","name":"Lag-1 Sparing as a Signature of Cortico-Thalamic Conduction Latency:  A Biophysical Spiking Model","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-9385203/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-9385203/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.21203/rs.3.rs-10344352/v1","name":"Robotic-Inspired Tri-Metaheuristic Framework with Neuromorphic Edge Intelligence for Real-Time Multi-Modal Biomedical Signal Processing and Clinical Decision Support","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-10344352/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-10344352/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.20944/preprints202507.2002.v4","name":"An Etiological, Pathophysiological, and Rehabilitative Framework for Focal Task-Specific Dystonia: An M1-Centered Motor Synergy Hypothesis","source":"europepmc","abstract":"","url":"https://doi.org/10.20944/preprints202507.2002.v4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.20944/preprints202507.2002.v4","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.21203/rs.3.rs-9953953/v1","name":"Making Field-Theoretic Neural Models Observable: A Mesoscopic Observation Bridge to MEA Recordings","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-9953953/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-9953953/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.21203/rs.3.rs-8592450/v1","name":"A new recurrent spiking pi sigma artificial neural network for the forecasting problem","source":"europepmc","abstract":"Abstract Due to their flexible model structures and their success in nonlinear modelling, artificial neural networks provide good alternatives for solving the forecasting problem. It is seen that different artificial neuron models can positively affect the forecasting performance and pave the way for the creation of new artificial neural network models. In this study, a new artificial neural network with an architecture based on multiplicative and additive neuron models and using the feedback logic in exponential smoothing methods is presented. The training algorithm of the proposed neural network is based on particle swarm optimization using a dynamic fitness function that gives more weight to recent observations. The performance of the proposed new neural network is investigated with the help of statistical hypothesis tests by comparing it with other methods in the literature on Nasdaq stock exchange time series. As a result of the study, it is empirically observed that the proposed neural network has a successful forecasting performance.","url":"https://doi.org/10.21203/rs.3.rs-8592450/v1","authors":["Erol Egrioglu","Eren Bas","Gulsen Albayrak"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-8592450/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:35.256Z"},{"id":"doi:10.64898/2026.03.09.710501","name":"Inferring state-dependent functional circuit motifs using higher-order interactions analysis","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.03.09.710501","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.03.09.710501","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.21203/rs.3.rs-8753676/v1","name":"Integrating Neuroscientific Priors into Spiking Neural Networks: ECSNN-SEG for Robust Brain ECS Segmentation from Low-SNR Cryo-Electron Microscopy Data","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-8753676/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-8753676/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1101/059840","name":"Unsupervised Learning of Temporal Features for Word Categorization in a Spiking Neural Network Model of the Auditory Brain","source":"preprints","abstract":"","url":"https://doi.org/10.1101/059840","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2016","doi":"10.1101/059840","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.64898/2026.06.05.730322","name":"From homeostasis to credit assignment: a signed-XOR connectomic motif for local directional error signalling","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.06.05.730322","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.06.05.730322","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.04.14.718368","name":"Neural mechanisms of postural sway-related beta-band oscillations: a cortico-basal ganglia-thalamic network model of intermittent control","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.04.14.718368","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.04.14.718368","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.01.24.699491","name":"Higher-Order Thalamus is Pivotal in Schizophrenia-Associated Pathophysiology","source":"europepmc","abstract":"","url":"https://doi.org/10.64898/2026.01.24.699491","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.01.24.699491","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.21203/rs.3.rs-10218667/v1","name":"Combining ultra-flexible electrodes with two-photon imaging to illuminate brain-wide neural dynamics","source":"europepmc","abstract":"Abstract Brain activity consists of neural signals dynamically coordinated across spatial and temporal scales. To sample distributed brain-wide activity, we combine chronically implanted ultra-flexible electrodes for subcortical recordings with simultaneous two-photon calcium imaging in mouse neocortex. Flexible electrodes preserve optical access even at steep insertion angles and enable weeks-long single-neuron tracking. With these combined recordings, we demonstrate how subcortical-cortical coupling is modulated across slow brain states and around fast ripple events.","url":"https://doi.org/10.21203/rs.3.rs-10218667/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-10218667/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.21203/rs.3.rs-9499789/v1","name":"Echoes of Life in Spontaneously Spiking Proteinoid–Sand Systems","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-9499789/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-9499789/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.02.02.703247","name":"Modularity-dependent storage of dynamic spiking patterns: bridging micro- and mesoscopic representations","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.02.02.703247","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.02.02.703247","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.06.15.732346","name":"Inhibitory Gain and Hub Architecture Confer Dynamic Resilience to Microcircuit Degeneration","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.06.15.732346","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.06.15.732346","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.03.27.714865","name":"Dendritic excitatory-inhibitory balance and branch-specific gating enable selective recall of associative memories","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.03.27.714865","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.03.27.714865","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1101/2025.10.25.684525","name":"Influence of STDP rule choice and network connectivity on polychronous groups and cell ensembles in spiking neural networks","source":"europepmc","abstract":"","url":"https://doi.org/10.1101/2025.10.25.684525","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.10.25.684525","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.20944/preprints202604.0605.v1","name":"eXCube1: Explainable Neuromorphic Framework for Modelling Conscious Perception of Stimuli from fMRI Data","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202604.0605.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.20944/preprints202604.0605.v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.03.16.712138","name":"Metastable Neural Assemblies on a Wiring–Weight Continuum","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.03.16.712138","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.03.16.712138","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.21203/rs.3.rs-9196722/v1","name":"Short-Term Synaptic Plasticity Modulates the Outcome of Neurodegenerative Diseases","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-9196722/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-9196722/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1101/2025.11.08.687345","name":"Synaptic Synchronization-Based Learning of Pattern Separation in Self-Organizing Probabilistic Spiking Neural Networks","source":"europepmc","abstract":"Neuroscience-inspired neural networks bridge biology and technology, offering powerful tools to model brain function while enabling adaptive, efficient control in robotics. In this work, we present a neuroscience-inspired synaptic learning rule based on the synchronization of synaptic inputs to single excitatory neurons within a feedforward spiking neural network. The model consists of three excitatory layers and two feedback inhibitory layers, with initially low connection probabilities and weak synaptic weights assigned to the excitatory neurons. Under an unsupervised learning paradigm, stimulus patterns were presented to the network, allowing synaptic weights and connectivity to evolve dynamically across training trials. We investigated how these dynamics depended on feedback inhibition intensity and identified conditions under which the network achieved stable activity. Furthermore, we evaluated the model’s pattern separation efficacy and its relationship to network dynamics. The results highlight the critical role of feedback inhibition in both stabilizing the network and enhancing pattern separation. In particular, results show balanced synchronization between excitatory and inhibitory populations maximizes separation efficacy. Beyond providing a novel computational framework for understanding information processing in neural systems, this model also offers insights into cognitive disorders associated with impaired inhibition and pattern separation, such as autism and schizophrenia. Finally, we embedded the trained network within a simulated agent navigating a two-dimensional environment, where it was tasked with identifying a trained stimulus as an obstacle and avoiding it. The model offers a framework for advancing cognitive robotics by enabling novel approaches that mimic natural intelligence and support the learning of complex environmental patterns.","url":"https://doi.org/10.1101/2025.11.08.687345","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.11.08.687345","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.10.16.682754","name":"The Spiking Tolman-Eichenbaum Machine: Emergent Spatial and Temporal Coding through Spiking Network Dynamics","source":"europepmc","abstract":"","url":"https://doi.org/10.1101/2025.10.16.682754","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.10.16.682754","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.64898/2026.02.13.705719","name":"Quantifying the Emergence of Population-Level Activity in Neuronal Systems","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.02.13.705719","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.02.13.705719","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1101/2025.10.20.683584","name":"Modelling Predictive Coding in the Primary Visual Cortex (V1): Layer 4 Receptive Field Properties in a Balanced Recurrent Spiking Neuronal Network","source":"europepmc","abstract":"","url":"https://doi.org/10.1101/2025.10.20.683584","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.10.20.683584","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.64898/2026.04.16.718939","name":"GPU-Accelerated Optimization Investigates Synaptic Reorganization Underlying Pathological Beta Oscillations in a Basal Ganglia Network Model","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.04.16.718939","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.04.16.718939","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.21203/rs.3.rs-8679920/v1","name":"Neural Network Wiring and Topological Stochastic Resonance","source":"preprints","abstract":"Abstract The aim of this work is to determine how variability in synaptic connectivityshapes activity in balanced spiking networks and whether “topological stochasticresonance” (amplified responses due to structural disorder) can emerge withoutchanging the connection count. For that purpose we have simulated balancednetworks of excitatory and inhibitory leaky integrate-and-fire neurons driven byexternal Poisson input. Four connectivity schemes were constructed each witha progressively more unequal distribution of the number of inputs received byindividual neurons but with the same total number of conncetions. Topologicalvariability was quantified by the standard deviation (σ) of a normal distribu-tion describing the number of inputs received from each presynaptic populationto each neuron. Our results indicate that by increasing variability in connectiv-ity produces a strong effect of increased mean firing rates and rate heterogeneityacross neuron classes, despite the total number of synapses per population beingconserved. Network balance remained globally preserved, but local deviationsgrew with σ, revealing regimes of enhanced responsiveness. We demonstratehow the structural “noise” in the form of variable synaptic connection countcan strongly modulate activity in balanced networks without altering overallconnection count. These results support the novel concept of Topological Stochas-tic Resonance and suggest that controlled connectivity disorder may help tunesensitivity and stability in cortical-like circuits.","url":"https://doi.org/10.21203/rs.3.rs-8679920/v1","authors":["Antoine Dedieu","Konstantin Nikolic"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-8679920/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1101/2025.11.23.690009","name":"Direct Training of Networks of Morris-Lecar Neurons with Backprop","source":"europepmc","abstract":"","url":"https://doi.org/10.1101/2025.11.23.690009","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.11.23.690009","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.20944/preprints202512.1045.v1","name":"Neuromorphic Control of the Serv-Arm Robot Using Spiking Neural Networks","source":"europepmc","abstract":"","url":"https://doi.org/10.20944/preprints202512.1045.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202512.1045.v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.20944/preprints202603.0817.v1","name":"SNN-IDS: Deploying SNN-Equivalent Intrusion Detection on a Commodity MCU NPU","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202603.0817.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.20944/preprints202603.0817.v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.01.21.700016","name":"Axonal theta oscillations evoke bursting in target hippocampal subregions","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.01.21.700016","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.01.21.700016","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.02.01.703170","name":"Biophysical Modeling of Thalamocortical Circuit Dynamics: Species-Specific Insights into Neural Synchrony, Sleep Spindles, and Mechanisms of Neuropsychiatric Disorders","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.02.01.703170","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.02.01.703170","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.02.21.707238","name":"Reservoir Computing with Ultra-Sparse Rings","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.02.21.707238","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.02.21.707238","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.02.12.705512","name":"A learning-evoked slow-oscillatory architecture paces population activity for offline reactivation across the human medial temporal lobe","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.02.12.705512","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.02.12.705512","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.21203/rs.3.rs-8459031/v1","name":"A fully-memristive trimodal fusion perception system integrating multisensory neuron with hybrid neural network accelerator","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-8459031/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-8459031/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.64898/2026.02.11.705397","name":"Kainate receptors are critical for permissivity to sustained, disorganized, and network-wide pathological activity in the epileptic dentate gyrus","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.02.11.705397","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.02.11.705397","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.20944/preprints202512.0391.v1","name":"SIFT-SNN for Traffic-Flow Infrastructure Safety: A Real-Time Context-Aware Anomaly Detection Framework","source":"europepmc","abstract":"","url":"https://doi.org/10.20944/preprints202512.0391.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202512.0391.v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.64898/2026.03.27.714202","name":"From Coarse to Rich: Successive Waves of Visual Perception in Prefrontal Cortex","source":"europepmc","abstract":"","url":"https://doi.org/10.64898/2026.03.27.714202","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.03.27.714202","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2025.11.26.690655","name":"Emergence of Value and Action Codes in Bimodular Spiking Actor–Critic Networks","source":"europepmc","abstract":"","url":"https://doi.org/10.1101/2025.11.26.690655","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.11.26.690655","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.10.31.685901","name":"SNNs Are Not Transformers (Yet): The Architectural Problems for SNNs in Modeling Long-Range Dependencies","source":"europepmc","abstract":"","url":"https://doi.org/10.1101/2025.10.31.685901","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.10.31.685901","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.20944/preprints202509.2072.v1","name":"A Practical Tutorial on Spiking Neural Networks: Comprehensive Review, Models, Experiments, Software Tools, and Implementation Guidelines","source":"europepmc","abstract":"Spiking Neural Networks (SNNs) provide a biologically inspired, event-driven alternative to Artificial Neural Networks (ANNs) with the potential to deliver competitive accuracy at substantially lower energy. This tutorial-study offers a unified, practice-oriented assessment combining critical reviews and standardized experiments. We benchmark a shallow Fully Connected Network (FCN) on MNIST and a deeper VGG7 architecture on CIFAR-10 across multiple neuron models (leaky Integrate-and-Fire (LIF), Sigma-Delta, etc.) and input encodings (direct, rate, temporal, etc.) using supervised surrogate-gradient training, implemented with Intel Lava/SLAYER, SpikingJelly, Norse and PyTorch. Empirically, we observe a consistent but tunable trade-off between accuracy and energy. On MNIST, Sigma-Delta neurons with rate or Sigma-Delta encodings reach 98.1% (ANN: 98.23%). On CIFAR-10, Sigma-Delta neurons with direct input achieve 83.0% at just 2 time steps (ANN: 83.6%). A GPU-based operation-count energy proxy indicates many SNN configurations operate below the ANN energy baseline; some frugal codes minimize energy at the cost of accuracy, whereas accuracy-leaning settings (e.g., Sigma-Delta with direct or rate coding ) narrow the performance gap while remaining energy-conscious, yielding up to 3-fold efficiency versus matched ANNs in our setup. Thresholds and the number of time steps are decisive: intermediate thresholds and the minimal time window that still meets accuracy targets typically maximize efficiency per joule. We distill actionable design rules: choose the neuron/encoding pair by application goal (accuracy-critical vs. energy-constrained) and co-tune thresholds and time steps. Finally, we outline how event-driven neuromorphic hardware can amplify these savings through sparse, local, asynchronous computation, providing a practical playbook for embedded, real-time, and sustainable AI deployments.","url":"https://doi.org/10.20944/preprints202509.2072.v1","authors":["Bahgat Ayasi","Cristóbal J. Carmona","Mohammed Saleh","Angel M. García-Vico"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202509.2072.v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.21203/rs.3.rs-7944463/v1","name":"FPGA based Implementation of Neuromorphic Neural Networks for Early Detection of Alzheimer’s Disease","source":"europepmc","abstract":"Abstract Alzheimer’s Disease (AD) is a progressive, neurodegenerative condition causing cognitive decline with memory loss. To improve life quality and allow intervention in time, detection that is early and accurate is key, especially at Mild Cognitive Impairment (MCI). This paper proposes a Brain-Inspired Neuromorphic approach to classifying Alzheimer’s stages using advanced neural network models, that are Convolutional Neural Networks (CNN), Liquid Neural Networks (LNN), Spiking Neural Networks (SNN), and a hybrid CNN + LNN architecture. MRI datasets used within this study are obtained directly from Alzheimer’s Disease Neuroimaging Initiative (ADNI), which provides high-quality structural imaging data. Using the SPM toolbox, the raw DICOM images are converted into NIfTI format and preprocessed to segment and standardize the data. Dual-Tree Complex Wavelet Transform (DTCWT) is applied in feature extraction for preservation of both spatial with frequency information. These features are then used to train the neural network models in order to classify images into three stages. The trained models get translated into the RTL design as simulated using Xilinx AMD Vivado for exploring hardware - software co design deployment. This hardware-optimized Neuromorphic approach aims to provide a low-power, high-speed, and accurate Alzheimer’s detection solution, connecting research with practical, deployable medical tools.","url":"https://doi.org/10.21203/rs.3.rs-7944463/v1","authors":["B A Sujathakumari","Usha Rani C M","M S Shalini","N S Sneha"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7944463/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.09.05.674527","name":"Fast spiking interneurons autonomously generate fast gamma oscillations in the medial entorhinal cortex with excitation strength tuning ING–PING transitions","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.09.05.674527","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.09.05.674527","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.21203/rs.3.rs-6995073/v1","name":"ShSCFHN: Shepard Spiking Convolutional Forward Harmonic Network for fault prediction in eBay service","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-6995073/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6995073/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.64898/2026.02.10.705045","name":"The representation of voluntary and reflexive fast eye movements in the macaque lateral intraparietal area (LIP)","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.02.10.705045","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.02.10.705045","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.02.19.26346583","name":"Restoring brain-to-text communication in a person with dysarthria from pontine stroke using an intracortical brain-computer interface","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.02.19.26346583","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.02.19.26346583","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.21203/rs.3.rs-6767420/v1","name":"Hybrid Cross-Temporal Contrastive Model with Spiking Energy-Efficient Network Intrusion Detection in IOMT","source":"preprints","abstract":"Abstract The Internet of Medical Things (IoMT), a key application of the Internet of Things (IoT), has played a key role, especially during the Covid 19 pandemic. Real-time patient monitoring and remote diagnostics help improve medical services, but this increases the mammoth size of network traffic, which impacts the security quite a bit. However, traditional intrusion detection systems lack synchronization between accuracy and energy efficiency in resource-constrained IoMT environments. To address this issue, we present a hybrid cross-temporal contrastive model coupled with a spiking energy-efficient network for intrusion detection. This approach uses contrastive learning to learn temporal dependencies in network traffic and spiking neural networks (SNNs) for energy-efficient computations. We evaluated the model on the WUSTL-EHMS-2020 dataset, which consists of 44 features (35 of them are network flow measurements, and 8 are biometric patient features), as well as the NSL-KDD dataset to perform a comparative validation. Furthermore, the experiment results prove that our proposed model achieves 99.95% accuracy on the WUSTL-EHMS-2020 dataset with an F1 score of 99.89%, precision of 98.23%, and recall of 99.55%, outperforming conventional models. The model attained 98.2% accuracy, 97.6% precision, 98.5% F1 score, and 97.3% recall on the NSL-KDD Dataset. Our approach shows that these results effectively secure IoMT networks at a low computational cost. Finally, the proposed hybrid model can achieve good performance and energy efficiency for intrusion detection in innovative healthcare systems. In future work, efforts will be made to improve the model's generalization property in diverse IoMT environments and minimize the energy consumption of spiking neural networks in real-time applications.","url":"https://doi.org/10.21203/rs.3.rs-6767420/v1","authors":["Fatma S. Alrayes","Mohammed Zakariah","Syed Umar Amin","Zafar Iqbal Khan","Maha Helal"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6767420/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.09.18.677043","name":"A human spiking computational model to explore sound localization","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.09.18.677043","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.09.18.677043","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.64898/2026.01.30.702777","name":"DeepUnitMatch: tracking neurons across days in electrophysiology using Deep Neural Networks","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.01.30.702777","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.01.30.702777","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2025.10.22.683945","name":"Auditory network persistence of stimulus representation in awake and naturally sleeping mice","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.10.22.683945","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.10.22.683945","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.22541/au.174885691.16213858/v1","name":"Hybrid Cross-Temporal Contrastive Model with Spiking Energy-Efficient Network Intrusion Detection in IOMT","source":"preprints","abstract":"The Internet of Medical Things (IoMT), a key application of the Internet of Things (IoT), has played a key role, especially during the Covid 19 pandemic. Real-time patient monitoring and remote diagnostics help improve medical services, but this increases the mammoth size of network traffic, which impacts the security quite a bit. However, traditional intrusion detection systems lack synchronization between accuracy and energy efficiency in resource-constrained IoMT environments. To address this issue, we present a hybrid cross-temporal contrastive model coupled with a spiking energy-efficient network for intrusion detection. This approach uses contrastive learning to learn temporal dependencies in network traffic and spiking neural networks (SNNs) for energy-efficient computations. We evaluated the model on the WUSTL-EHMS-2020 dataset, which consists of 44 features (35 of them are network flow measurements, and 8 are biometric patient features), as well as the NSL-KDD dataset to perform a comparative validation. Furthermore, the experiment results prove that our proposed model achieves 99.95% accuracy on the WUSTL-EHMS-2020 dataset with an F1 score of 99.89%, precision of 98.23%, and recall of 99.55%, outperforming conventional models. The model attained 98.2% accuracy, 97.6% precision, 98.5% F1 score, and 97.3% recall on the NSL-KDD Dataset. Our approach shows that these results effectively secure IoMT networks at a low computational cost. Finally, the proposed hybrid model can achieve good performance and energy efficiency for intrusion detection in innovative healthcare systems. In future work, efforts will be made to improve the model’s generalization property in diverse IoMT environments and minimize the energy consumption of spiking neural networks in real-time applications.","url":"https://doi.org/10.22541/au.174885691.16213858/v1","authors":["Fatma S. Alrayes","Mohammed Zakariah","Syed Umar Amin","Zafar Iqbal Khan","Maha Helal"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.22541/au.174885691.16213858/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.21203/rs.3.rs-10384662/v1","name":"Temporal Gating by Chandelier Cells Encodes Signed Prediction Errors","source":"preprints","abstract":"Abstract The brain refines its predictions of the world by updating its internal model whenever sensory input differs from expectation. The sign of this prediction error matters: an unexpected event signals that the model under-predicted (positive error), while a predicted event that fails to occur indicates that the model over-predicted (negative error), and the two should drive opposite syn-aptic changes. How cortical circuits represent error sign in spiking activity, and how that repre-sentation translates into synaptic learning, remain unresolved. We propose the Signed Error by Timing Asymmetry (SETA) model, in which the sign of a prediction error is encoded by when layer 2/3 neurons fire relative to a brief plasticity window in their layer 5 targets. Chandelier cells, an inhibitory cell type recruited by the prediction, impose a temporal clamp on layer 2/3 output: positive errors escape the clamp and arrive within the synaptic potentiation window, while negative errors are released only after the clamp decays and arrive later, during the synaptic depression window. The same circuit, therefore, biases downstream synapses to-ward either potentiation or depression depending on the prediction-error sign. We demonstrate this signed-error computation in a reduced two-compartment model, test SETA-specific predic-tions using in vivo recordings from mouse visual cortex, and examine how E/I imbalance leads to pathological consequences in predictive coding.","url":"https://doi.org/10.21203/rs.3.rs-10384662/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-10384662/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.64898/2025.12.11.693654","name":"Intra-and Interhemispheric Signatures of Criticality at the Onset of Synchronization","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2025.12.11.693654","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.64898/2025.12.11.693654","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.20944/preprints202507.0525.v1","name":"Synergies and Divergences Between Spiking Neural Networks and Large Language Models","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202507.0525.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202507.0525.v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.07.08.663644","name":"Conditions for replay of neuronal assemblies","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.07.08.663644","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.07.08.663644","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.64898/2025.12.30.697062","name":"Hippocampome.org, a resource for subicular neuron types and beyond","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2025.12.30.697062","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.64898/2025.12.30.697062","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.10.01.679810","name":"Neural Receptive Fields, Stimulus Space Embedding and Effective Geometry of Scale-Free Networks","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.10.01.679810","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.10.01.679810","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.11.08.687292","name":"Competition between memories for reactivation as a mechanism for long-delay credit assignment","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.11.08.687292","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.11.08.687292","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.64898/2026.03.10.710908","name":"Toroidal topology of grid-cell activity precedes spatial navigation during development","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.03.10.710908","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.03.10.710908","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.21203/rs.3.rs-8907993/v1","name":"Harnessing Dynamics of Van Der Pol Oscillators for Phase Computing with Oscillatory Neural Networks","source":"preprints","abstract":"Abstract An oscillatory neural network (ONN) is a novel physics-based computing architecture that leverages the collective dynamics of coupled oscillators with sinusoidal Kuramoto oscillators being typically chosen. However, van der Pol (vdP) oscillators introduce a higher nonlinearity, which we explore for computations. This work presents the first in-depth study of ONNs with vdP oscillators, focusing on their capabilities in regard to associative memory tasks. We derive the Phase Transition Function (PTF), a crucial feature for ONN computing. Furthermore, we detail the circuit design and simulation results for implementing a vdP-ONN architecture. Analytical and circuit-level simulations demonstrate the benefits of vdP oscillators such as increased synaptic resolution, faster time-to-settle, larger coupling range, and superior noise robustness in comparison to standard sine wave oscillators.","url":"https://doi.org/10.21203/rs.3.rs-8907993/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-8907993/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2025.12.13.694145","name":"Degraded sensory coding in a mouse model of  <i>Scn2a-</i>  related disorder and its rescue by CRISPRa gene activation","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2025.12.13.694145","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.64898/2025.12.13.694145","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.22541/au.175251384.43407770/v1","name":"Early Parkinson's Disease Detection Using a Hybrid Graph-Spike Neural Network Architecture","source":"preprints","abstract":"","url":"https://doi.org/10.22541/au.175251384.43407770/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.22541/au.175251384.43407770/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.20944/preprints202506.1290.v2","name":"Algorithm for Describing Neuronal Electric Operation","source":"preprints","abstract":"The development of neuroanatomy and neurophysiology has revealed many new details about neurons’ electrical operation over the past few decades, requiring modifications to their theoretical models. The development of computing technology enables us to consider the fine details the new model requires, but it necessitates a different approach. As it was long ago suspected, the faithful simulation of biological processes requires accurately mapping biological time to technical computing time(s). Therefore, the paper focuses on time handling in biology-targeting computations. However, the operation of biology and the physical/mathematical processes in living matter are also unusual from the point of view of algorithmic description. Furthermore, the way technical computing works prevents achieving the needed accuracy in reproducing biological operations using computer programs. We also touch on the question of simulating the operation of their network, contrasted with that of spiking artificial neural networks. On the one side, we use an updated theoretical model that considers neuronal current as charged ions (and so considers thermodynamic effects) and opens the way for explaining mechanical, optical, etc., consequence phenomena of the electric operation. On the other hand, we use a new technology, a tool designed to achieve extreme accuracy in simulating high-speed electronic circuits. The algorithm that applies this model, along with the unusual programming method, provides new insights into both neuronal operation and its computing implementation.","url":"https://doi.org/10.20944/preprints202506.1290.v2","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202506.1290.v2","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.21203/rs.3.rs-8206760/v1","name":"Light-induced giant random telegraph noise in CuScP2S6/MoS2 heterostructures and their use in noise resilience image inference","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-8206760/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-8206760/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.11.08.687367","name":"Neural manifolds that orchestrate walking and stopping","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.11.08.687367","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.11.08.687367","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.05.07.652583","name":"Synergistic short-term synaptic plasticity mechanisms for working memory","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.05.07.652583","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.05.07.652583","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.09.17.676896","name":"Transcranial Alternating Current Stimulation can disrupt or reestablish neural entrainment in a primate model of Parkinson’s disease","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.09.17.676896","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.09.17.676896","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.09.19.677474","name":"Memory-specific E-I balance supports diverse replay and mitigates catastrophic forgetting","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.09.19.677474","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.09.19.677474","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.64898/2026.01.05.697766","name":"Integrating Models to Decode the GnRH Pulse Generator","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.01.05.697766","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.01.05.697766","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2025.02.25.640158","name":"Combining Sampling Methods with Attractor Dynamics in Spiking Models of Head-Direction Systems","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.02.25.640158","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.02.25.640158","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.04.11.647919","name":"Graph-Based Modeling of Alzheimer’s Protein Interactions via Spiking Neural, Hyperdimensional Encoding, and Scalable Ray-Based Learning","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.04.11.647919","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.04.11.647919","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.64898/2025.12.19.694963","name":"Probabilistic inference of Homonymous and Heteronymous Recurrent Inhibition in Human Muscles from Large-Scale Motor Neuron Recordings","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2025.12.19.694963","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.64898/2025.12.19.694963","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.21203/rs.3.rs-6460749/v1","name":"Improving SpikeProp’s Training Efficiency in Spiking Neural Networks for Large Language Models Through Innovative Weight Initialization","source":"preprints","abstract":"Abstract Spiking neural networks (SNNs) mimic the functions of biological neurons by leveraging individual temporal spikes for communication and computation. Since SNN was perceived to be complex and analytically challenging, it had long been overlooked. In this study, we explore the enhancement of SpikeProp, a supervised learning model customized for SNNs. Three distinct models are being investigated, including the Proposed Model 1, the Proposed Model 2, and the Proposed Model 3, each providing unique improvements to the SpikeProp algorithm. To accelerate convergence and adapt learning rates, momentum factors are integrated into Proposed Model 1. In Proposed Model 2, a rate dependency is introduced based on Angle Driven Learning. By incorporating particle swarm optimization (PSO), Model 3 combines the strengths of Model 1 and 2. SNNs can be trained and classified more efficiently and accurately using these models. Furthermore, we examine how large language models (LLMs) might inform the design and interpretability of neural architectures and learning methodologies while also enhancing SNN training. Through the use of LLMs, we seek to enhance model transparency and encourage more Responsible AI (RAI) principles. A thorough evaluation and comparison of Proposed Model 1, Proposed Model 2, and Proposed Model 3 with traditional methods confirms that these models consistently outperform them. Consequently, they have a high potential for practical applications in neural network training in real-world settings and LLM-informed development, contributing to the advancement of AI systems.","url":"https://doi.org/10.21203/rs.3.rs-6460749/v1","authors":["Falah. Y.H. Ahmed","Muhammad Zakarya","Naveed Khan","Dilovan Asaad Zebari","Mahmood Al-Bahri","Bwalya Kelvin Joseph"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6460749/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1101/2025.09.17.676336","name":"Aging diminishes interlaminar functional connectivity in the mouse cortical V1 and CA1 hippocampal regions","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.09.17.676336","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.09.17.676336","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.02.28.640853","name":"Biologically realistic mean field model of spiking neural networks with fast and slow inhibitory synapses","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.02.28.640853","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.02.28.640853","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.08.21.25333903","name":"Decoding phantom limb movements from intraneural recordings","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.08.21.25333903","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.08.21.25333903","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.06.09.658675","name":"Transcranial ultrasound stimulation modulates neuronal membrane potentials across broad timescales in the awake mammalian brain","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.06.09.658675","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.06.09.658675","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.08.09.669457","name":"When Firing Rate Falls Short: Spike Synchrony Reliably Disentangles Stimulus Saliency and Familiarity","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.08.09.669457","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.08.09.669457","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.08.06.668927","name":"Psilocybin triggers an activity-dependent rewiring of large-scale cortical networks","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.08.06.668927","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.08.06.668927","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.10.21.682935","name":"Semantic Tuning of Single Neurons in the Human Medial Temporal Lobe","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.10.21.682935","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.10.21.682935","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.21203/rs.3.rs-7081087/v1","name":"EEG-Based Depression Classification and Brain Region Analysis Using a Hybrid of NeuCube and Dictionary Learning Framework","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-7081087/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7081087/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.02.05.636716","name":"A Mean-Field Approach to Criticality in Spiking Neural Networks for Reservoir Computing","source":"preprints","abstract":"Reservoir computing is a neural network paradigm for processing temporal data by exploiting the dynamics of a fixed, high-dimensional system, enabling efficient computation with reduced complexity compared to fully trainable recurrent networks. This work presents an analytical framework for configuring in the critical regime a reservoir based on spiking neural networks with a highly general topology. Specifically, we derive and solve a mean-field equation that governs the evolution of the average membrane potential in leaky integrate-and-fire neurons, and provide an approximation for the critical point. This framework reduces the need for an extensive online fine-tuning, offering a streamlined path to near-optimal network performance from the outset. Through extensive simulations, we validate the theoretical predictions by analyzing the network’s spiking dynamics and quantifying its computational capacity using the information-based Lempel-Ziv-Welch complexity near criticality. Finally, we explore self-organized quasi-criticality by implementing a local learning rule for synaptic weights, demonstrating that the network’s dynamics remain close to the theoretical critical point. Beyond AI, our approach and findings also have significant implications for computational neuroscience, providing a principled framework for quantitatively understanding how biological networks leverage criticality for efficient information processing.","url":"https://doi.org/10.1101/2025.02.05.636716","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.02.05.636716","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.07.01.662561","name":"High frequency electrical stimulation entrains fast spiking interneurons and bidirectionally modulates information processing","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.07.01.662561","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.07.01.662561","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.03.16.643547","name":"Subthreshold variability of neuronal populations driven by synchronous synaptic inputs","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.03.16.643547","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.03.16.643547","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.09.17.676857","name":"Coincidence detection supported by electrical synapses is shaped by the D-type K  <sup>+</sup>  current","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.09.17.676857","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.09.17.676857","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.07.10.664257","name":"Framed RSA: Representational comparisons that honor both geometry and population-mean response preferences","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.07.10.664257","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.07.10.664257","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.06.30.662290","name":"Spinal Circuit Mechanisms Constrain Therapeutic Windows for ALS Intervention","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.06.30.662290","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.06.30.662290","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.09.03.673779","name":"Hypothalamic recurrent inhibition regulates functional states of stress effector neurons","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.09.03.673779","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.09.03.673779","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.64898/2025.12.21.695758","name":"Ephaptic coupling can explain variability in neural activity","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2025.12.21.695758","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.64898/2025.12.21.695758","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.05.28.656584","name":"Memory by a thousand rules: Automated discovery of multi-type plasticity rules reveals variety & degeneracy at the heart of learning","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.05.28.656584","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.05.28.656584","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.21203/rs.3.rs-5162168/v1","name":"Femto-joule threshold reconfigurable all-optical nonlinear activators for picosecond spiking neural networks","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-5162168/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-5162168/v1","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.04.29.651327","name":"Spontaneous Dynamics Predict the Effects of Targeted Intervention in Hippocampal Neuronal Cultures","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.04.29.651327","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.04.29.651327","addedAt":"2026-09-01T01:48:22.345Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.5281/zenodo.18367071","name":"Privacy-Preserving Federated Spiking Neural Networks for Real-Time Target Detection in Distributed ISAC Edge Systems","source":"datacite","abstract":"This study proposes a privacy-preserving federated spiking neural network (SNN) framework for real-time target detection in integrated sensing and communication (ISAC) edge networks. The framework enables distributed vehicular nodes operating at 28 GHz to collaboratively learn from spike-based sensing data without sharing raw observations, thereby protecting sensitive location information. By combining federated learning with secure model aggregation, adaptive differential privacy, and spike-aware temporal learning, the system ensures robust privacy protection while supporting efficient learning under non-IID data and real-time constraints. Extensive experiments using data from 500 vehicles and 50,000 observations demonstrate that the proposed approach achieves a high detection performance of 94.3% F1-score under strict privacy guarantees, with low inference latency and significantly reduced energy consumption. These results highlight the framework’s suitability for privacy-sensitive vehicular and smart-city applications, supporting scalable, energy-efficient, and trustworthy 6G ISAC deployment.","url":"https://doi.org/10.5281/zenodo.18367071","authors":["Mohammad Zahangir Alam"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18367071","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.3929/ethz-b-000739475","name":"A neuromorphic electronic artist for robotic painting","source":"datacite","abstract":"Recent advances in deep learning have sparked interest in AI-generated art, including robot-assisted painting. Traditional painting machines use static images and offline processing without considering the dynamic nature of painting. Neuromorphic cameras, which capture light intensity changes through asynchronous events, and mixed-signal neuromorphic processors, which implement biologically plausible spiking neural networks, offer a promising alternative. In this work, we present a robotic painting system comprising a 6-DOF robotic arm, event-based input from a Dynamic Vision Sensor (DVS) camera and a neuromorphic processor to produce dynamic brushstrokes, and tactile feedback from a force-torque sensor to compensate for brush deformation. The system receives DVS events representing the desired brushstroke trajectory and maps these events onto the processor’s neurons to compute joint velocities in close-loop. The variability in the input’s noisy event streams and the processor’s analog circuits reproduces the heterogeneity of human brushstrokes. Tested in a real-world setting, the system successfully generated diverse physical brushstrokes. This network marks a first step towards a fully spiking robotic controller with ultra-low latency responsiveness, applicable to any robotic task requiring real-time closed-loop adaptive control.","url":"https://doi.org/10.3929/ethz-b-000739475","authors":["Schürmann, Lioba","D'Angelo, Giulia","Grayver, Liat","Bartolozzi, Chiara","Indiveri, Giacomo"],"tags":["Computer science","Electrical and electronic engeineering"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3929/ethz-b-000739475","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.3929/ethz-c-000786698","name":"EFLOP: a sparsity-aware metric for evaluating computational cost in spiking and non-spiking neural networks","source":"datacite","abstract":"Deploying energy-efficient deep neural networks on energy-constrained edge devices is an important research topic in both machine learning and circuit design communities. Both artificial neural networks (ANNs) and spiking neural networks (SNNs) have been proposed as candidates for these tasks. In particular, SNNs are considered energy-efficient because they leverage temporal sparsity in their outputs. However, existing computational frameworks fail to accurately estimate the cost of running sparse networks on modern time-stepped hardware, which exploits sparsity by skipping zero-valued operations. Meanwhile, weight sparsity-aware training remains underexplored for SNNs and lacks systematic benchmarking against optimized ANNs, making fair comparisons between the two paradigms difficult. To bridge this gap, we introduce the effective floating-point operation (EFLOP), a metric that accounts for the sparse operations during pre-activation updates of both ANNs and SNNs. Applying weight sparsity-aware training to both SNNs and ANNs, we achieve up to 8.9× reduction in EFLOPs for gated recurrent unit models and 3.6× for LIF models by sparsifying weights by 80 % , without sacrificing accuracy on the Spiking Heidelberg Digits and Spiking Speech Command datasets. These findings highlight the critical role of network sparsity in designing energy-efficient neural networks and establish EFLOPs as a robust framework for cross-paradigm comparisons.","url":"https://doi.org/10.3929/ethz-c-000786698","authors":["Narduzzi, Simon","Zenke, Friedemann","Liu, Shih-Chii","Dunbar, L. Andrea"],"tags":["computational cost","effective floating-point operations","pruning","sparsity-aware training","recurrent neural networks","spiking neural networks"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3929/ethz-c-000786698","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.3929/ethz-b-000744772","name":"Stable recurrent dynamics in heterogeneous neuromorphic computing systems using excitatory and inhibitory plasticity","source":"datacite","abstract":"Many neural computations emerge from self-sustained patterns of activity in recurrent neural circuits, which rely on balanced excitation and inhibition. Neuromorphic electronic circuits represent a promising approach for implementing the brain’s computational primitives. However, achieving the same robustness of biological networks in neuromorphic systems remains a challenge due to the variability in their analog components. Inspired by real cortical networks, we apply a biologically-plausible cross-homeostatic rule to balance neuromorphic implementations of spiking recurrent networks. We demonstrate how this rule can autonomously tune the network to produce robust, self-sustained dynamics in an inhibition-stabilized regime, even in presence of device mismatch. It can implement multiple, co-existing stable memories, with emergent soft-winner-take-all and reproduce the “paradoxical effect” observed in cortical circuits. In addition to validating neuroscience models on a substrate sharing many similar limitations with biological systems, this enables the automatic configuration of ultra-low power, mixed-signal neuromorphic technologies despite the large chip-to-chip variability.","url":"https://doi.org/10.3929/ethz-b-000744772","authors":["Soldado-Magraner, Saray","Sorbaro, Martino","Laje, Rodrigo","Buonomano, Dean V.","Indiveri, Giacomo",", Maryada"],"tags":["Electrical and electronic engineering","Learning algorithms"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3929/ethz-b-000744772","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.3929/ethz-b-000749309","name":"A Realistic Simulation Framework for Analog/Digital Neuromorphic Architectures","source":"datacite","abstract":"Developing dedicated mixed-signal neuromorphic computing systems optimized for real-time sensory-processing in extreme edge-computing applications requires time-consuming design, fabrication, and deployment of full-custom neuromorphic processors. To ensure that initial prototyping efforts exploring the properties of different network architectures and parameter settings lead to realistic results, it is important to use simulation frameworks that match as best as possible the properties of the final hardware. This is particularly challenging for neuromorphic hardware platforms made using mixed-signal analog/digital circuits, due to the variability and noise sensitivity of their components. In this paper, we address this challenge by developing a software spiking neural network simulator explicitly designed to account for the properties of mixed-signal neuromorphic circuits, including device mismatch variability. The simulator, called A Realistic Simulation Framework for Analog/Digital Neuromorphic Architectures, is designed to reproduce the dynamics of mixed-signal synapse and neuron electronic circuits with autogradient differentiation for parameter optimization and GPU acceleration. We demonstrate the effectiveness of this approach by matching software simulation results with measurements made from an existing neuromorphic processor. We show how the results obtained provide a reliable estimate of the behavior of the spiking neural network trained in software, once deployed in hardware. This framework enables the development and innovation of new learning rules and processing architectures in neuromorphic embedded systems.","url":"https://doi.org/10.3929/ethz-b-000749309","authors":["Quintana, Fernando M.",", Maryada","Galindo, Pedro L.","Donati, Elisa","Indiveri, Giacomo","Perez-Peña, Fernando"],"tags":["SNN","DPI","neuromorphic","PyTorch","DYNAP-SE"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3929/ethz-b-000749309","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.3929/ethz-b-000716329","name":"Genetic Motifs as a Blueprint for Mismatch-Tolerant Neuromorphic Computing","source":"datacite","abstract":"Mixed-signal implementations of SNNs offer a promising solution to edge computing applications that require low-power and compact embedded processing systems. However, device mismatch in the analog circuits of these neuromorphic processors poses a significant challenge to the deployment of robust processing in these systems. Here we introduce a novel architectural solution inspired by biological development to address this issue. Specifically we propose to implement architectures that incorporate network motifs found in developed brains through a differentiable re-parameterization of weight matrices based on gene expression patterns and genetic rules. Thanks to the gradient descent optimization compatibility of the method proposed, we can apply the robustness of biological neural development to neuromorphic computing.","url":"https://doi.org/10.3929/ethz-b-000716329","authors":["Boccato, Tommaso","Zendrikov, Dmitrii","Toschi, Nicola","Indiveri, Giacomo"],"tags":["Spiking neural networks","Mixed-signal chips","Device mismatch","Network neuroscience"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3929/ethz-b-000716329","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.34734/fzj-2026-00946","name":"Commentary: Accelerating spiking neural network simulations with PymoNNto and PymoNNtorch","source":"datacite","abstract":"Frontiers in neuroinformatics 18, 1446620 (2024). doi:10.3389/fninf.2024.1446620","url":"https://doi.org/10.34734/fzj-2026-00946","authors":["Plesser, Hans Ekkehard"],"tags":["610"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.34734/fzj-2026-00946","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.3929/ethz-c-000786150","name":"Neuromorphic dreaming as a pathway to efficient learning in artificial agents","source":"datacite","abstract":"The computational substrate of biological systems exhibits remarkable abilities to learn complex skills quickly and efficiently. Inspired by this, we implement model-based reinforcement learning using spiking neural networks directly on mixed-signal neuromorphic hardware. This approach combines energy-efficient electronic circuits with high sample efficiency through alternating online (‘awake’) and offline (‘dreaming’) learning phases. Our model features two networks: an agent network that learns from real and simulated experiences and a world model network that generates simulated experiences. We validate this by training the system to play Atari Pong. First, we establish a baseline using only real experiences. Then, by ‘dreaming’, the required real experiences decrease significantly. The network dynamics runs in real-time on the analog neuromorphic circuits, with only the readout layers implemented and trained on a computer-in-the-loop. We present results that demonstrate the robustness and potential of energy-efficient mixed-signal neuromorphic processors for real-world applications.","url":"https://doi.org/10.3929/ethz-c-000786150","authors":["Blakowski, Ingo","Zendrikov, Dmitrii","Indiveri, Giacomo","Capone, Cristiano"],"tags":["neuromorphic computing","spiking neural networks","model-based reinforcement learning","offline learning","sample efficiency","energy-efficient learning"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3929/ethz-c-000786150","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.3929/ethz-b-000714674","name":"Recurrent models of orientation selectivity enable robust early-vision processing in mixed-signal neuromorphic hardware","source":"datacite","abstract":"Mixed signal analog/digital neuromorphic circuits represent an ideal medium for reproducing bio-physically realistic dynamics of biological neural systems in real-time. However, similar to their biological counterparts, these circuits have limited resolution and are affected by a high degree of variability. By developing a recurrent spiking neural network model of the retinocortical visual pathway, we show how such noisy and heterogeneous computing substrate can produce linear receptive fields tuned to visual stimuli with specific orientations and spatial frequencies. Compared to strictly feed-forward schemes, the model generates highly structured Gabor-like receptive fields of any phase symmetry, making optimal use of the hardware resources available in terms of synaptic connections and neuron numbers. Experimental results validate the approach, demonstrating how principles of neural computation can lead to robust sensory processing electronic systems, even when they are affected by high degree of heterogeneity, e.g., due to the use of analog circuits or memristive devices.","url":"https://doi.org/10.3929/ethz-b-000714674","authors":["Baruzzi, Valentina","Indiveri, Giacomo","Sabatini, Silvio P."],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3929/ethz-b-000714674","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.3929/ethz-b-000735596","name":"Event driven neural network on a mixed signal neuromorphic processor for EEG based epileptic seizure detection","source":"datacite","abstract":"Long-term monitoring of biomedical signals is essential for the modern clinical management of neurological conditions such as epilepsy. However, developing wearable systems that are able to monitor, analyze, and detect epileptic seizures with long-lasting operation times using current technologies is still an open challenge. Brain-inspired spiking neural networks (SNNs) represent a promising signal processing and computing framework as they can be deployed on ultra-low power neuromorphic computing systems, for this purpose. Here, we introduce a novel SNN architecture, co-designed and validated on a mixed-signal neuromorphic chip, that shows potential for always-on monitoring of epileptic activity. We demonstrate how the hardware implementation of this SNN captures the phenomenon of partial synchronization within neural activity during seizure periods. We assess the network using a full-custom asynchronous mixed-signal neuromorphic platform, processing analog signals in real-time from an Electroencephalographic (EEG) seizure dataset. The neuromorphic chip comprises an analog front-end (AFE) signal conditioning stage and an asynchronous delta modulation (ADM) circuit directly integrated on the same die, which can produce the stream of spikes as input to the SNN, directly from the analog EEG signals. We show a linear classifier in a post processing stage that is sufficient to reliably classify and detect seizures, from the local features extracted by the SNN, indicating the feasibility of full on-chip seizure monitoring in the future. This research marks a significant advancement toward developing embedded intelligent “wear and forget” units for resource-constrained environments. These units could autonomously detect and log relevant EEG events of interest in out-of-hospital environments, offering new possibilities for patient care and management of neurological disorders.","url":"https://doi.org/10.3929/ethz-b-000735596","authors":["Bartels, Jim","Gallou, Olympia","Ito, Hiroyuki","Cook, Matthew","Sarnthein, Johannes","Indiveri, Giacomo","Ghosh, Saptarshi"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3929/ethz-b-000735596","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2412.06124","name":"Spiking Neural Networks for Radio Frequency Interference Detection in Radio Astronomy","source":"datacite","abstract":"Spiking Neural Networks (SNNs) promise efficient and dynamic spatio-temporal data processing. This paper reformulates a significant challenge in radio astronomy, Radio Frequency Interference (RFI) detection, as a time-series segmentation task suited for SNN execution. Automated systems capable of real-time operation with minimal energy consumption are increasingly important in modern radio telescopes. We explore several spectrogram encoding methods and network parameters, applying first and second-order leaky integrate and fire SNNs to tackle RFI detection. We introduce a divisive normalisation-inspired pre-processing step, improving detection performance across multiple encodings strategies. Our approach achieves competitive performance on a synthetic dataset and compelling initial results on real data from the Low-Frequency Array (LOFAR). We position SNNs as a viable path towards real-time RFI detection, with many possibilities for follow-up studies. These findings highlight the potential for SNNs performing complex time-series tasks, paving the way towards efficient, real-time processing in radio astronomy and other data-intensive fields.","url":"https://doi.org/10.48550/arxiv.2412.06124","authors":["Pritchard, Nicholas J.","Wicenec, Andreas","Bennamoun, Mohammed","Dodson, Richard"],"tags":["Neural and Evolutionary Computing (cs.NE)","Instrumentation and Methods for Astrophysics (astro-ph.IM)","FOS: Computer and information sciences","FOS: Computer and information sciences","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.48550/arxiv.2412.06124","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2405.18828","name":"CHANI: Correlation-based Hawkes Aggregation of Neurons with bio-Inspiration","source":"datacite","abstract":"The present work aims at proving mathematically that a neural network inspired by biology can learn a classification task thanks to local transformations only. In this purpose, we propose a spiking neural network named CHANI (Correlation-based Hawkes Aggregation of Neurons with bio-Inspiration), whose neurons activity is modeled by Hawkes processes. Synaptic weights are updated thanks to an expert aggregation algorithm, providing a local and simple learning rule. We were able to prove that our network can learn on average and asymptotically. Moreover, we demonstrated that it automatically produces neuronal assemblies in the sense that the network can encode several classes and that a same neuron in the intermediate layers might be activated by more than one class, and we provided numerical simulations on synthetic dataset. This theoretical approach contrasts with the traditional empirical validation of biologically inspired networks and paves the way for understanding how local learning rules enable neurons to form assemblies able to represent complex concepts.","url":"https://doi.org/10.48550/arxiv.2405.18828","authors":["Jaffard, Sophie","Vaiter, Samuel","Reynaud-Bouret, Patricia"],"tags":["Statistics Theory (math.ST)","Machine Learning (stat.ML)","FOS: Mathematics","FOS: Mathematics","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.48550/arxiv.2405.18828","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2601.13451","name":"Event-based Heterogeneous Information Processing for Online Vision-based Obstacle Detection and Localization","source":"datacite","abstract":"This paper introduces a novel framework for robotic vision-based navigation that integrates Hybrid Neural Networks (HNNs) with Spiking Neural Network (SNN)-based filtering to enhance situational awareness for unmodeled obstacle detection and localization. By leveraging the complementary strengths of Artificial Neural Networks (ANNs) and SNNs, the system achieves both accurate environmental understanding and fast, energy-efficient processing. The proposed architecture employs a dual-pathway approach: an ANN component processes static spatial features at low frequency, while an SNN component handles dynamic, event-based sensor data in real time. Unlike conventional hybrid architectures that rely on domain conversion mechanisms, our system incorporates a pre-developed SNN-based filter that directly utilizes spike-encoded inputs for localization and state estimation. Detected anomalies are validated using contextual information from the ANN pathway and continuously tracked to support anticipatory navigation strategies. Simulation results demonstrate that the proposed method offers acceptable detection accuracy while maintaining computational efficiency close to SNN-only implementations, which operate at a fraction of the resource cost. This framework represents a significant advancement in neuromorphic navigation systems for robots operating in unpredictable and dynamic environments.","url":"https://doi.org/10.48550/arxiv.2601.13451","authors":["Ahmadvand, Reza","Sharif, Sarah Safura","Banad, Yaser Mike"],"tags":["Robotics (cs.RO)","Computer Vision and Pattern Recognition (cs.CV)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2601.13451","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2601.12156","name":"Biological Intuition on Digital Hardware: An RTL Implementation of Poisson-Encoded SNNs for Static Image Classification","source":"datacite","abstract":"The deployment of Artificial Intelligence on edge devices (TinyML) is often constrained by the high power consumption and latency associated with traditional Artificial Neural Networks (ANNs) and their reliance on intensive Matrix-Multiply (MAC) operations. Neuromorphic computing offers a compelling alternative by mimicking biological efficiency through event-driven processing. This paper presents the design and implementation of a cycle-accurate, hardware-oriented Spiking Neural Network (SNN) core implemented in SystemVerilog. Unlike conventional accelerators, this design utilizes a Leaky Integrate-and-Fire (LIF) neuron model powered by fixed-point arithmetic and bit-wise primitives (shifts and additions) to eliminate the need for complex floating-point hardware. The architecture features an on-chip Poisson encoder for stochastic spike generation and a novel active pruning mechanism that dynamically disables neurons post-classification to minimize dynamic power consumption. We demonstrate the hardware's efficacy through a fully connected layer implementation targeting digit classification. Simulation results indicate that the design achieves rapid convergence (89% accuracy) within limited timesteps while maintaining a significantly reduced computational footprint compared to traditional dense architectures. This work serves as a foundational building block for scalable, energy-efficient neuromorphic hardware on FPGA and ASIC platforms.","url":"https://doi.org/10.48550/arxiv.2601.12156","authors":["Das, Debabrata","K., Yogeeth G.","Gupta, Arnav"],"tags":["Hardware Architecture (cs.AR)","FOS: Computer and information sciences","FOS: Computer and information sciences","B.7.1, C.1.3, I.2.6"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2601.12156","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18287761","name":"SNN-Comprypto: Spiking Neural Network-based Simultaneous Compression and Encryption Using Chaotic Reservoir Dynamics","source":"datacite","abstract":"I propose SNN-Comprypto, a novel cryptographic system that leverages the chaotic dynamics of Spiking Neural Networks (SNNs) to perform simultaneous data compression and encryption. Unlike conventional methods that treat compression and encryption as separate processes, this approach integrates both within a single reservoir computing architecture. **Version History:** - **v1**: Core system with predictive compression and chaotic encryption. Passes all 9 NIST SP 800-22 randomness tests. Achieves 100% lossless reconstruction and strong avalanche effect (0.70% match rate with 1-bit key change). - **v2**: Introduces temperature parameter as a second cryptographic key (0.0001 difference causes complete decryption failure). Presents phase transition analysis identifying optimal neuron counts (critical point at 100 neurons, sweet spot at 240 neurons). - **v3**: Adversarial evaluation framework demonstrating SNN superiority for random number generation. Results from 100,000+ rounds show SNN achieves 0.39% prediction rate (matching theoretical random), while DNN is 18× and LSTM is 55× more predictable. - **v4 (NEW)**: Theoretical chaos analysis with Lyapunov exponents and entropy measurements. SNN achieves near-perfect entropy (7.998/8.0 bits) with positive Lyapunov exponents, confirming true chaotic dynamics. Adversarial attack resistance evaluation (4/5 attack types resisted). IV/nonce recommendation for secure deployment added. Source code: https://github.com/hafufu-stack/temporal-coding-simulation","url":"https://doi.org/10.5281/zenodo.18287761","authors":["Funasaki, Hiroto"],"tags":["Spiking Neural Networks","Cryptography","Reservoir Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18287761","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18304632","name":"Hybrid Spiking Language Model: Combining Spike Counts and Membrane Potentials for Energy-Efficient and Noise-Robust Character Prediction","source":"datacite","abstract":"I propose a novel character-level language model using Spiking Neural Networks (SNNs) that combines both spike counts and membrane potentials for output prediction. This v3 extends the model with BitNet ternary weights and RWKV-inspired time-mixing. Key Findings (v3 NEW):- BitNet Mixed Precision: PPL 2.69 BEATS standard SNN (3.29)!- RWKV Time-Mixing: 36.1% improvement in long-range memory- Ultimate Architecture: 43.4% improvement combining all techniques- Multiplication-free reservoir: 50-70% of operations are additions only- 16-model ensemble achieves PPL 1.04 Key Findings (v1-v2):- SNN achieves BEST perplexity (PPL=9.90) vs DNN (11.28) and LSTM (15.67)- 14.7× more energy-efficient through sparse computation (only 7.6% of neurons fire)- 39.7% quality improvement from hybrid (spike + membrane) approach- Extreme compressibility: 80% neuron pruning and 4-bit quantization still work- 8× memory compression with minimal quality loss- Noise robust: No degradation at 30% input noise This v3 establishes hybrid SNNs with ternary weights as the optimal architecture for ultra-efficient edge AI language processing. Source code: https://github.com/hafufu-stack/snn-language-model","url":"https://doi.org/10.5281/zenodo.18304632","authors":["Funasaki, Hiroto"],"tags":["Spiking Neural Network","Language Model","Neuromorphic Computing","Energy Efficiency","Noise Robustness","Membrane Potential"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18304632","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18306877","name":"Adaptive Neural Continuity Protocol: Real-Time Compensation for Progressive Hippocampal Neurodegeneration","source":"datacite","abstract":"This research presents the Continuity Protocol, a computational framework designed to preserve cognitive information integrity during progressive hippocampal decay. Using a 1,500-neuron spiking neural network in the Nengo environment, we demonstrate real-time signal restoration with \\approx 1.0 accuracy. The dataset includes: Full Technical Paper (PDF). Source Code (Python/Nengo). Simulation Video showing the 29s terminal decay cycle.","url":"https://doi.org/10.5281/zenodo.18306877","authors":["Farag, Mina K."],"tags":["Computational Neuroscience","Nengo","NEF","Spiking Neural Networks","Hippocampus","Neurodegeneration","Alzheimer's Resilience","Brain-Computer Interface"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18306877","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18306876","name":"Adaptive Neural Continuity Protocol: Real-Time Compensation for Progressive Hippocampal Neurodegeneration","source":"datacite","abstract":"This research presents the Continuity Protocol, a computational framework designed to preserve cognitive information integrity during progressive hippocampal decay. Using a 1,500-neuron spiking neural network in the Nengo environment, we demonstrate real-time signal restoration with \\approx 1.0 accuracy. The dataset includes: Full Technical Paper (PDF). Source Code (Python/Nengo). Simulation Video showing the 29s terminal decay cycle.","url":"https://doi.org/10.5281/zenodo.18306876","authors":["Farag, Mina K."],"tags":["Computational Neuroscience","Nengo","NEF","Spiking Neural Networks","Hippocampus","Neurodegeneration","Alzheimer's Resilience","Brain-Computer Interface"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18306876","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.24433/co.2414086.v1","name":"Bioinspired spiking architecture enables energy constrained touch encoding","source":"datacite","abstract":"This capsule enables the reproduction of the main results presented in the paper: \"Bioinspired Spiking Architecture Enables Energy-Constrained Touch Encoding\".","url":"https://doi.org/10.24433/co.2414086.v1","authors":["Ortone, Andrea","Filosa, Mariangela","Indiveri, Giacomo","Desoli, Giuseppe","Mazzoni, Alberto","Oddo, Calogero Maria"],"tags":["Capsule","Engineering","Tactile Perception","Spiking neural network","energy efficient AI","analog and parallel computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.24433/co.2414086.v1","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.34734/fzj-2026-00306","name":"Functions of spiking neural networks constrained by biology","source":"datacite","abstract":"Artificial intelligence (AI) solutions are increasingly taking on tasks traditionally performed by humans. However, their rising computational demands and energy consumption are unsustainable, highlighting the need for more efficient designs. The human brain, evolved to function effectively even when energy is scarce, offers inspiration. Since learning is central to both artificial intelligence and the brain, insights about its underlying principles can deepen our understanding of human learning while informing the development of algorithms that transcend purely engineering-based methods. This thesis investigates biological learning through two studies, examining it from mechanistic and functional perspectives at an abstraction level commonly employed in neurophysics and computational neuroscience. These fields distill complex neural systems and phenomena into tractable mathematical and computational models, enabling insights beyond the reach of traditional biological approaches. Recognizing that synapses — the connections between neurons — are fundamental to learning, the thesis begins with a review of state-of-the-art computational neuroscience methods for modeling synaptic organization. This review highlights critical aspects of synaptic signaling, including connectivity, transmission, plasticity, and heterogeneity. In the first study, a synaptic plasticity model is integrated into a spiking neural network simulator and extended with biologically plausible features, for example, continuous dynamics and increased locality. The effectiveness of this enhanced model is demonstrated by training it on a standard neuromorphic benchmark task, incorporating biologically realistic sparse connectivity and weight constraints. The second study demonstrates that the sampling efficiency of pre-trained spiking neural networks can be enhanced by exposing them to oscillating background spiking activity. Analogous to simulated tempering, these rhythmic oscillations modulate state space exploration, facilitating transitions between high-probability states within the learned representation. These findings establish a link between cortical oscillations and sampling-based computations, offering new insights into memory retrieval and consolidation from a computational perspective. The research involves developing mathematical and computational models, which are simulated on high-performance computing systems, evaluating learning and sampling performance using standard machine learning metrics, and assessing computational efficiency by analyzing runtime. This thesis shows how biologically inspired mechanisms enhance the functional capabilities of spiking neural networks and how they can guide the development of scalable and efficient AI systems.","url":"https://doi.org/10.34734/fzj-2026-00306","authors":["Korcsak-Gorzo, Agnes"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.34734/fzj-2026-00306","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2601.11261","name":"Effects of Introducing Synaptic Scaling on Spiking Neural Network Learning","source":"datacite","abstract":"Spiking neural networks (SNNs) employing unsupervised learning methods inspired by neural plasticity are expected to be a new framework for artificial intelligence. In this study, we investigated the effect of multiple types of neural plasticity, such as spike-time-dependent plasticity (STDP) and synaptic scaling, on the learning in a winner-take-all (WTA) network composed of spiking neurons. We implemented a WTA network with multiple types of neural plasticity using Python. The MNIST and the Fashion-MNIST datasets were used for training and testing. We varied the number of neurons, the time constant of STDP, and the normalization method used in synaptic scaling to compare classification accuracy. The results demonstrated that synaptic scaling based on the L2 norm was the most effective in improving classification performance. By implementing L2-norm-based synaptic scaling and setting the number of neurons in both excitatory and inhibitory layers to 400, the network achieved classification accuracies of 88.84 % on the MNIST dataset and 68.01 % on the Fashion-MNIST dataset after one epoch of training.","url":"https://doi.org/10.48550/arxiv.2601.11261","authors":["Touda, Shinnosuke","Okuno, Hirotsugu"],"tags":["Neural and Evolutionary Computing (cs.NE)","Machine Learning (cs.LG)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2601.11261","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18294033","name":"Hybrid Spiking Language Model: Combining Spike Counts and Membrane Potentials for Energy-Efficient and Noise-Robust Character Prediction","source":"datacite","abstract":"I propose a novel character-level language model using Spiking Neural Networks (SNNs) that combines both spike counts and membrane potentials for output prediction. Unlike conventional SNN approaches that only use spike counts, this hybrid method leverages the analog information contained in membrane potentials. Key Findings (v2):- SNN achieves BEST perplexity (PPL=9.90) vs DNN (11.28) and LSTM (15.67)- 14.7× more energy-efficient through sparse computation (only 7.6% of neurons fire)- 39.7% quality improvement from hybrid (spike + membrane) approach- Extreme compressibility: 80% neuron pruning and 4-bit quantization still work- 8× memory compression with minimal quality loss- Noise robust: No degradation at 30% input noise Source code: https://github.com/hafufu-stack/snn-language-model","url":"https://doi.org/10.5281/zenodo.18294033","authors":["Funasaki, Hiroto"],"tags":["Spiking Neural Network","Language Model","Neuromorphic Computing","Energy Efficiency","Noise Robustness","Membrane Potential"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18294033","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18286627","name":"Brain Inspired Computing Models and Architectures","source":"datacite","abstract":"With an exponential increase in the amount of data collected per day, the fields of artificial intelligence and machinelearning continue to progress at a rapid pace with respect to algorithms, models, applications, and hardware. In particular,deep neural networks have revolutionized these fields by providing unprecedented human-like performance in solving manyreal-world problems such as image or speech recognition. There is also significant research aimed at unraveling the principles of computation in large biological neural networks and, in particular, biologically plausible spiking neural networks. This paperpresents an overview of the brain-inspired computing models starting with the development of the perceptron and multi-layerperceptron followed by convolutional neural networks (CNNs) and recurrent neural networks (RNNs). The paper brieflyreviews other neural network models such as Hopfield neural networks and Boltzmann machines. Other models such as spikingneural networks (SNNs) and hyperdimensional computing are then briefly reviewed. Recent advances in these neural networksand graph related neural networks are then described.Index Terms—Brain-inspired computing, spiking neural networks, neuromorphic architecture, graph neural networks, hyperdimensional computing, low-power inference, energy efficiency, surrogate gradients.","url":"https://doi.org/10.5281/zenodo.18286627","authors":["Diksha Katyal","Kalpana Choudhary","Dimpy Singh"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18286627","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18286628","name":"Brain Inspired Computing Models and Architectures","source":"datacite","abstract":"With an exponential increase in the amount of data collected per day, the fields of artificial intelligence and machinelearning continue to progress at a rapid pace with respect to algorithms, models, applications, and hardware. In particular,deep neural networks have revolutionized these fields by providing unprecedented human-like performance in solving manyreal-world problems such as image or speech recognition. There is also significant research aimed at unraveling the principles of computation in large biological neural networks and, in particular, biologically plausible spiking neural networks. This paperpresents an overview of the brain-inspired computing models starting with the development of the perceptron and multi-layerperceptron followed by convolutional neural networks (CNNs) and recurrent neural networks (RNNs). The paper brieflyreviews other neural network models such as Hopfield neural networks and Boltzmann machines. Other models such as spikingneural networks (SNNs) and hyperdimensional computing are then briefly reviewed. Recent advances in these neural networksand graph related neural networks are then described.Index Terms—Brain-inspired computing, spiking neural networks, neuromorphic architecture, graph neural networks, hyperdimensional computing, low-power inference, energy efficiency, surrogate gradients.","url":"https://doi.org/10.5281/zenodo.18286628","authors":["Diksha Katyal","Kalpana Choudhary","Dimpy Singh"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18286628","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18288582","name":"Hybrid Spiking Language Model: Combining Spike Counts and Membrane Potentials for Energy-Efficient and Noise-Robust Character Prediction","source":"datacite","abstract":"I propose a novel character-level language model using Spiking Neural Networks (SNNs) that combines both spike counts and membrane potentials for output prediction. Unlike conventional SNN approaches that only use spike counts, this hybrid method leverages the analog information contained in membrane potentials, inspired by biological decision-making processes. Key Findings:- SNN is 42× more energy-efficient than DNN- SNN shows no accuracy degradation at 30% input noise- Hybrid (Spike + Membrane) approach improves perplexity by 9× Source code: https://github.com/hafufu-stack/snn-language-model","url":"https://doi.org/10.5281/zenodo.18288582","authors":["Funasaki, Hiroto"],"tags":["Spiking Neural Network","Language Model","Neuromorphic Computing","Energy Efficiency","Noise Robustness","Membrane Potential"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18288582","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.17605/osf.io/j2s7q","name":"NeuroMorphic Robotic Brain (NeuRob): A Spiking Neural Network Architecture for Autonomous, Adaptive Robot Control Lifelong Learning in Unstructured Environments with SNNs: A Theoretical Approach","source":"datacite","abstract":"","url":"https://doi.org/10.17605/osf.io/j2s7q","authors":["Karmakar, Rupam Kumar"],"tags":["Computer Engineering","Engineering"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.17605/osf.io/j2s7q","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18280566","name":"SNN-Comprypto: Spiking Neural Network-based Simultaneous Compression and Encryption Using Chaotic Reservoir Dynamics","source":"datacite","abstract":"We propose SNN-Comprypto, a novel cryptographic system that leverages the chaotic dynamics of Spiking Neural Networks (SNNs) to perform simultaneous data compression and encryption. Unlike conventional methods that treat compression and encryption as separate processes, our approach integrates both within a single reservoir computing architecture. **Version History:** - **v1**: Core system with predictive compression and chaotic encryption. Passes all 9 NIST SP 800-22 randomness tests. Achieves 100% lossless reconstruction and strong avalanche effect (0.70% match rate with 1-bit key change). - **v2**: Introduces temperature parameter as a second cryptographic key (0.0001 difference causes complete decryption failure). Presents phase transition analysis identifying optimal neuron counts (critical point at 100 neurons, sweet spot at 240 neurons). - **v3 (NEW)**: Adversarial evaluation framework demonstrating SNN superiority for random number generation. Results from 100,000+ rounds show SNN achieves 0.39% prediction rate (matching theoretical random), while DNN is 18× and LSTM is 55× more predictable. Establishes SNNs as the optimal architecture for neuromorphic cryptography. Source code: https://github.com/hafufu-stack/temporal-coding-simulation","url":"https://doi.org/10.5281/zenodo.18280566","authors":["Funasaki, Hiroto"],"tags":["Spiking Neural Networks","Cryptography","Reservoir Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18280566","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18275030","name":"SNN-Comprypto: Spiking Neural Network-based Simultaneous Compression and Encryption Using Chaotic Reservoir Dynamics","source":"datacite","abstract":"We propose SNN-Comprypto, a novel cryptographic system that leverages the chaotic dynamics of Spiking Neural Networks (SNNs) to perform simultaneous data compression and encryption. Unlike conventional methods that treat compression and encryption as separate processes, our approach integrates both within a single reservoir computing architecture. The system exploits the inherent unpredictability of neuronal membrane potential fluctuations to generate cryptographically secure keystreams, while using predictive coding to achieve data compression. Experimental results demonstrate that our system passes all nine NIST SP 800-22 randomness tests, achieves perfect data reconstruction (100% lossless), and exhibits strong avalanche effect (0.70% match rate with a single-bit key change). Furthermore, Numba JIT optimization yields a 7.5× speedup over the baseline implementation. Our work suggests that bio-inspired neural dynamics can serve as a foundation for next-generation lightweight cryptographic systems suitable for edge devices and IoT applications.","url":"https://doi.org/10.5281/zenodo.18275030","authors":["Funasaki, Hiroto"],"tags":["Spiking Neural Networks","Cryptography","Reservoir Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18275030","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18265447","name":"SNN-Comprypto: Spiking Neural Network-based Simultaneous Compression and Encryption Using Chaotic Reservoir Dynamics","source":"datacite","abstract":"We propose SNN-Comprypto, a novel cryptographic system that leverages the chaotic dynamics of Spiking Neural Networks (SNNs) to perform simultaneous data compression and encryption. Unlike conventional methods that treat compression and encryption as separate processes, our approach integrates both within a single reservoir computing architecture. The system exploits the inherent unpredictability of neuronal membrane potential fluctuations to generate cryptographically secure keystreams, while using predictive coding to achieve data compression. Experimental results demonstrate that our system passes all nine NIST SP 800-22 randomness tests, achieves perfect data reconstruction (100% lossless), and exhibits strong avalanche effect (0.70% match rate with a single-bit key change). Furthermore, Numba JIT optimization yields a 7.5× speedup over the baseline implementation. Our work suggests that bio-inspired neural dynamics can serve as a foundation for next-generation lightweight cryptographic systems suitable for edge devices and IoT applications.","url":"https://doi.org/10.5281/zenodo.18265447","authors":["Funasaki, Hiroto"],"tags":["Spiking Neural Networks","Cryptography","Reservoir Computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18265447","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2601.10032","name":"Macroscopic dynamics of quadratic integrate-and-fire neurons subject to correlated noise","source":"datacite","abstract":"The presence of correlated noise, arising from a mixture of independent fluctuations and a common noisy input shared across the neural population, is a ubiquitous feature of neural circuits, yet its impact on collective network dynamics remains poorly understood. We analyze a network of quadratic integrate-and-fire neurons driven by Gaussian noise with a tunable degree of correlation. Using the cumulant expansion method, we derive a reduced set of effective mean-field equations that accurately describe the evolution of the population's mean firing rate and membrane potential. Our analysis reveals a counterintuitive phenomenon: increasing the noise correlation strength suppresses the mean network activity, an effect we term correlated-noise-inhibited spiking. Furthermore, within a specific parameter regime, the network exhibits metastability, manifesting itself as spontaneous, noise-driven transitions between distinct high- and low-activity states. These results provide a theoretical framework for reducing the dynamics of complex stochastic networks and demonstrate how correlated noise can fundamentally regulate macroscopic neural activity, with implications for understanding state transitions in biological systems.","url":"https://doi.org/10.48550/arxiv.2601.10032","authors":["Wang, Hui","Zheng, Chunming"],"tags":["Neurons and Cognition (q-bio.NC)","Statistical Mechanics (cond-mat.stat-mech)","Adaptation and Self-Organizing Systems (nlin.AO)","FOS: Biological sciences","FOS: Biological sciences","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2601.10032","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.17982387","name":"Conceptual Framework for Adaptive Biohybrid Neural Interfaces: Innovations in Medical Neural Engineering to Address Biocompatibility and Energy Efficiency Challenges","source":"datacite","abstract":"This conceptual paper proposes an adaptive biohybrid neural interface (ABNI) framework that integrates living immune cells (monocytes) with subcellular-sized wireless photovoltaic electronic devices (SWED) to enable minimally invasive, targeted closed-loop neuromodulation in inflamed brain regions. Drawing from recent advances in biohybrid technologies, the framework addresses key challenges in neural engineering, including biocompatibility, energy efficiency, and chronic implant stability. We present rigorous mathematical models with detailed derivations, including cell-device adhesion mechanics accounting for microfluidic drag forces, advanced optical link budget with scattering and maximum power point tracking (MPPT) for energy stability, electrode-electrolyte interface modeling, immunological dynamics, multi-compartment neural models, spiking neural network (SNN) models for on-chip processing, system latency budget, bidirectional brain-computer interface (BCI) capabilities, and end-of-life strategies. Python-based simulations using replicable real-world data incorporate safe reinforcement learning, advanced sensitivity analysis (including expanded Sobol indices with first-order, higher-order, and total-effect decompositions), quantitative statistics, Bayesian inference, uncertainty quantification, and falsifiability assessments. Supported by high-fidelity TikZ diagrams, comparative tables, failure mode analysis, and citations from prestigious peer-reviewed journals, this work outlines applications in neurology, a multi-phase roadmap from experimentation to manufacturing, emphasizing ethical considerations, nanofabrication feasibility, neural cybersecurity, and self-contained data availability.","url":"https://doi.org/10.5281/zenodo.17982387","authors":["Shibah, Sami Rashid Mohammed"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.17982387","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18263933","name":"Conceptual Framework for Adaptive Biohybrid Neural Interfaces: Innovations in Medical Neural Engineering to Address Biocompatibility and Energy Efficiency Challenges","source":"datacite","abstract":"This conceptual paper proposes an adaptive biohybrid neural interface (ABNI) framework that integrates living immune cells (monocytes) with subcellular-sized wireless photovoltaic electronic devices (SWED) to enable minimally invasive, targeted closed-loop neuromodulation in inflamed brain regions. Drawing from recent advances in biohybrid technologies, the framework addresses key challenges in neural engineering, including biocompatibility, energy efficiency, and chronic implant stability. We present rigorous mathematical models with detailed derivations, including cell-device adhesion mechanics accounting for microfluidic drag forces, advanced optical link budget with scattering and maximum power point tracking (MPPT) for energy stability, electrode-electrolyte interface modeling, immunological dynamics, multi-compartment neural models, spiking neural network (SNN) models for on-chip processing, system latency budget, bidirectional brain-computer interface (BCI) capabilities, and end-of-life strategies. Python-based simulations using replicable real-world data incorporate safe reinforcement learning, advanced sensitivity analysis (including expanded Sobol indices with first-order, higher-order, and total-effect decompositions), quantitative statistics, Bayesian inference, uncertainty quantification, and falsifiability assessments. Supported by high-fidelity TikZ diagrams, comparative tables, failure mode analysis, and citations from prestigious peer-reviewed journals, this work outlines applications in neurology, a multi-phase roadmap from experimentation to manufacturing, emphasizing ethical considerations, nanofabrication feasibility, neural cybersecurity, and self-contained data availability.","url":"https://doi.org/10.5281/zenodo.18263933","authors":["Shibah, Sami Rashid Mohammed"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18263933","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18260544","name":"AN NLP-BASED APPROACH FOR SARCASM DETECTION IN MARATHI LANGUAGE WITHIN MULTILINGUAL ENVIRONMENTS","source":"datacite","abstract":"The expansion of social media platforms has required the development of complex natural language processing (NLP) methods for sentiment analysis and sarcasm detection, especially for low-resource languages. This research presents a novel, ensemble-based NLP framework for sarcasm detection in Marathi-English code-mixed text, addressing a significant gap in multilingual sentiment analysis. The study confronts the challenges inherent to the Marathi language, including its rich morphology and a paucity of annotated corpora, by constructing a dedicated dataset of 2,400 tweets. Through a hybrid annotation strategy, this corpus was refined to contain 647 sarcastic, 1,477 non-sarcastic, and 276 unsure instances. The primary aim of this study is to develop and evaluate an ensemble-based model that enhances sarcasm detection accuracy in Marathi-English code-mixed text through the integration of traditional machine learning and neural network approaches. The proposed methodology employs comprehensive feature engineering—incorporating TF-IDF, word embedding, sentiment lexicons, and code-switching indicators—and an ensemble model architected to synergize the strengths of a Multinomial Naïve Bayes classifier and a Spiking Neural Network (SNN). Empirical evaluation demonstrates that the ensemble model achieves superior performance, attaining an accuracy of 94.2%, a precision of 90.5%, a recall of 92.1%, and an F1-score of 91.3%. These results signify a substantial improvement over established baseline models, including XGBoost (87% accuracy), SVM (85% accuracy), BERT-base Multilingual (92% accuracy), and XLNet (90% accuracy). This work validates the efficacy of ensemble learning and context-sensitive feature extraction for sarcasm detection, providing a scalable and robust paradigm for analogous low-resource linguistic environments.","url":"https://doi.org/10.5281/zenodo.18260544","authors":["Journal of Theoretical and Applied Information Technology"],"tags":["Sarcasm detection, Marathi NLP, Code-Mixed Text, Ensemble Learning, Multilingual Sentiment Analysis, Low-Resource Language"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18260544","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18260545","name":"AN NLP-BASED APPROACH FOR SARCASM DETECTION IN MARATHI LANGUAGE WITHIN MULTILINGUAL ENVIRONMENTS","source":"datacite","abstract":"The expansion of social media platforms has required the development of complex natural language processing (NLP) methods for sentiment analysis and sarcasm detection, especially for low-resource languages. This research presents a novel, ensemble-based NLP framework for sarcasm detection in Marathi-English code-mixed text, addressing a significant gap in multilingual sentiment analysis. The study confronts the challenges inherent to the Marathi language, including its rich morphology and a paucity of annotated corpora, by constructing a dedicated dataset of 2,400 tweets. Through a hybrid annotation strategy, this corpus was refined to contain 647 sarcastic, 1,477 non-sarcastic, and 276 unsure instances. The primary aim of this study is to develop and evaluate an ensemble-based model that enhances sarcasm detection accuracy in Marathi-English code-mixed text through the integration of traditional machine learning and neural network approaches. The proposed methodology employs comprehensive feature engineering—incorporating TF-IDF, word embedding, sentiment lexicons, and code-switching indicators—and an ensemble model architected to synergize the strengths of a Multinomial Naïve Bayes classifier and a Spiking Neural Network (SNN). Empirical evaluation demonstrates that the ensemble model achieves superior performance, attaining an accuracy of 94.2%, a precision of 90.5%, a recall of 92.1%, and an F1-score of 91.3%. These results signify a substantial improvement over established baseline models, including XGBoost (87% accuracy), SVM (85% accuracy), BERT-base Multilingual (92% accuracy), and XLNet (90% accuracy). This work validates the efficacy of ensemble learning and context-sensitive feature extraction for sarcasm detection, providing a scalable and robust paradigm for analogous low-resource linguistic environments.","url":"https://doi.org/10.5281/zenodo.18260545","authors":["Journal of Theoretical and Applied Information Technology"],"tags":["Sarcasm detection, Marathi NLP, Code-Mixed Text, Ensemble Learning, Multilingual Sentiment Analysis, Low-Resource Language"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18260545","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2601.09248","name":"Hybrid guided variational autoencoder for visual place recognition","source":"datacite","abstract":"Autonomous agents such as cars, robots and drones need to precisely localize themselves in diverse environments, including in GPS-denied indoor environments. One approach for precise localization is visual place recognition (VPR), which estimates the place of an image based on previously seen places. State-of-the-art VPR models require high amounts of memory, making them unwieldy for mobile deployment, while more compact models lack robustness and generalization capabilities. This work overcomes these limitations for robotics using a combination of event-based vision sensors and an event-based novel guided variational autoencoder (VAE). The encoder part of our model is based on a spiking neural network model which is compatible with power-efficient low latency neuromorphic hardware. The VAE successfully disentangles the visual features of 16 distinct places in our new indoor VPR dataset with a classification performance comparable to other state-of-the-art approaches while, showing robust performance also under various illumination conditions. When tested with novel visual inputs from unknown scenes, our model can distinguish between these places, which demonstrates a high generalization capability by learning the essential features of location. Our compact and robust guided VAE with generalization capabilities poses a promising model for visual place recognition that can significantly enhance mobile robot navigation in known and unknown indoor environments.","url":"https://doi.org/10.48550/arxiv.2601.09248","authors":["Wang, Ni","You, Zihan","Neftci, Emre","Schoepe, Thorben"],"tags":["Computer Vision and Pattern Recognition (cs.CV)","Artificial Intelligence (cs.AI)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2601.09248","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.17974630","name":"SYNtzulu, SNN at the Micro-Edge: The Evolution of the Mosquito.","source":"datacite","abstract":"SYNtzulu is an ultra-low power Spiking Neural Network inference engine designed for near-sensor processing at the edge. We describe the architectural progression that enables Syntzulu to support online artificial intelligence data analysis locally on a range of applications, such as sEMG, EEG, iEEG, and ECG, while maintaining minimal energy consumption, thereby opening new opportunities for wearable hardware and edge devices, where efficiency, adaptability, and autonomy are paramount.","url":"https://doi.org/10.5281/zenodo.17974630","authors":["Leone, Gianluca"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17974630","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18241884","name":"SYNtzulu, SNN at the Micro-Edge: The Evolution of the Mosquito.","source":"datacite","abstract":"SYNtzulu is an ultra-low power Spiking Neural Network inference engine designed for near-sensor processing at the edge. We describe the architectural progression that enables Syntzulu to support online artificial intelligence data analysis locally on a range of applications, such as sEMG, EEG, iEEG, and ECG, while maintaining minimal energy consumption, thereby opening new opportunities for wearable hardware and edge devices, where efficiency, adaptability, and autonomy are paramount.","url":"https://doi.org/10.5281/zenodo.18241884","authors":["Leone, Gianluca"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.18241884","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2508.13846","name":"Stochastic synaptic dynamics under learning","source":"datacite","abstract":"Learning is based on synaptic plasticity, which affects and is driven by neural activity. Because pre- and postsynaptic spiking activity is shaped by randomness, the synaptic weights follow a stochastic process, requiring a probabilistic framework to capture the noisy synaptic dynamics. We consider a paradigmatic supervised learning example: a presynaptic neural population impinging in a sequence of episodes on a recurrent network of integrate-and-fire neurons through synapses undergoing spike-timing-dependent plasticity (STDP) with additive potentiation and multiplicative depression. We first analytically compute the drift- and diffusion coefficients for a single synapse within a single episode (microscopic dynamics), mapping the true jump process to a Langevin and the associated Fokker-Planck equations. Leveraging new analytical tools, we include spike-time--resolving cross-correlations between pre- and postsynaptic spikes, which corrects substantial deviations seen in standard theories purely based on firing rates. We then apply this microdynamical description to the network setup in which hetero-associations are trained over one-shot episodes into a feed-forward matrix of STDP synapses connecting to neurons of the recurrent network (macroscopic dynamics). By mapping statistically distinct synaptic populations to instances of the single-synapse process above, we self-consistently determine the joint neural and synaptic dynamics and, ultimately, the time course of memory degradation and the memory capacity. We demonstrate that specifically in the relevant case of sparse coding, our theory can quantitatively capture memory capacities which are strongly overestimated if spike-time--resolving cross-correlations are ignored. [...]","url":"https://doi.org/10.48550/arxiv.2508.13846","authors":["Stubenrauch, Jakob","Auer, Naomi","Kempter, Richard","Lindner, Benjamin"],"tags":["Neurons and Cognition (q-bio.NC)","Disordered Systems and Neural Networks (cond-mat.dis-nn)","Biological Physics (physics.bio-ph)","FOS: Biological sciences","FOS: Biological sciences","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2508.13846","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2505.17791","name":"Bruno: Backpropagation Running Undersampled for Novel device Optimization","source":"datacite","abstract":"Recent efforts to improve the efficiency of neuromorphic and machine learning systems have centred on developing of specialised hardware for neural networks. These systems typically feature architectures that go beyond the von Neumann model employed in general-purpose hardware such as GPUs, offering potential efficiency and performance gains. However, neural networks developed for specialised hardware must consider its specific characteristics. This requires novel training algorithms and accurate hardware models, since they cannot be abstracted as a general-purpose computing platform. In this work, we present a bottom-up approach to training neural networks for hardware-based spiking neurons and synapses, built using ferroelectric capacitors (FeCAPs) and resistive random-access memories (RRAMs), respectively. Unlike the common approach of designing hardware to fit abstract neuron or synapse models, we start with compact models of the physical device to model the computational primitives. Based on these models, we have developed a training algorithm (BRUNO) that can reliably train the networks, even when applying hardware limitations, such as stochasticity or low bit precision. We analyse and compare BRUNO with Backpropagation Through Time. We test it on different spatio-temporal datasets. First on a music prediction dataset, where a network composed of ferroelectric leaky integrate-and-fire (FeLIF) neurons is used to predict at each time step the next musical note that should be played. The second dataset consists on the classification of the Braille letters using a network composed of quantised RRAM synapses and FeLIF neurons. The performance of this network is then compared with that of networks composed of LIF neurons. Experimental results show the potential advantages of using BRUNO by reducing the time and memory required to detect spatio-temporal patterns with quantised synapses.","url":"https://doi.org/10.48550/arxiv.2505.17791","authors":["Fehlings, Luca","Zhang, Bojian","Gibertini, Paolo","Nicholson, Martin A.","Covi, Erika","Quintana, Fernando M."],"tags":["Neural and Evolutionary Computing (cs.NE)","Artificial Intelligence (cs.AI)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2505.17791","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2601.08447","name":"Sleep-Based Homeostatic Regularization for Stabilizing Spike-Timing-Dependent Plasticity in Recurrent Spiking Neural Networks","source":"datacite","abstract":"Spike-timing-dependent plasticity (STDP) provides a biologically-plausible learning mechanism for spiking neural networks (SNNs); however, Hebbian weight updates in architectures with recurrent connections suffer from pathological weight dynamics: unbounded growth, catastrophic forgetting, and loss of representational diversity. We propose a neuromorphic regularization scheme inspired by the synaptic homeostasis hypothesis: periodic offline phases during which external inputs are suppressed, synaptic weights undergo stochastic decay toward a homeostatic baseline, and spontaneous activity enables memory consolidation. We demonstrate that this sleep-wake cycle prevents weight saturation while preserving learned structure. Empirically, we find that low to intermediate sleep durations (10-20\\% of training) improve stability on MNIST-like benchmarks in our STDP-SNN model, without any data-specific hyperparameter tuning. In contrast, the same sleep intervention yields no measurable benefit for the surrogate-gradient spiking neural network (SG-SNN). Taken together, these results suggest that periodic, sleep-based renormalization may represent a fundamental mechanism for stabilizing local Hebbian learning in neuromorphic systems, while also indicating that special care is required when integrating such protocols with existing gradient-based optimization methods.","url":"https://doi.org/10.48550/arxiv.2601.08447","authors":["Massey, Andreas","Hubin, Aliaksandr","Nichele, Stefano","Sæbø, Solve"],"tags":["Neural and Evolutionary Computing (cs.NE)","Machine Learning (stat.ML)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2601.08447","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2601.08244","name":"A brain-inspired information fusion method for enhancing robot GPS outages navigation","source":"datacite","abstract":"Low-cost inertial navigation systems (INS) are prone to sensor biases and measurement noise, which lead to rapid degradation of navigation accuracy during global positioning system (GPS) outages. To address this challenge and improve positioning continuity in GPS-denied environments, this paper proposes a brain-inspired GPS/INS fusion network (BGFN) based on spiking neural networks (SNNs). The BGFN architecture integrates a spiking Transformer with a spiking encoder to simultaneously extract spatial features from inertial measurement unit (IMU) signals and capture their temporal dynamics. By modeling the relationship between vehicle attitude, specific force, angular rate, and GPS-derived position increments, the network leverages both current and historical IMU data to estimate vehicle motion. The effectiveness of the proposed method is evaluated through real-world field tests and experiments on public datasets. Compared to conventional deep learning approaches, the results demonstrate that BGFN achieves higher accuracy and enhanced reliability in navigation performance, particularly under prolonged GPS outages.","url":"https://doi.org/10.48550/arxiv.2601.08244","authors":["Liu, Yaohua","Zhang, Hengjun","Ou, Binkai"],"tags":["Robotics (cs.RO)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2601.08244","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2506.19256","name":"Temporal Regularization Training: Unleashing the Potential of Spiking Neural Networks","source":"datacite","abstract":"Spiking Neural Networks (SNNs) have received widespread attention due to their event-driven and low-power characteristics, making them particularly effective for processing neuromorphic data. Recent studies have shown that directly trained SNNs suffer from severe temporal gradient vanishing and overfitting issues, which fundamentally constrain their performance and generalizability. This paper unveils a temporal regularization training (TRT) memthod, designed to unleash the generalization and performance potential of SNNs through a time-decaying regularization mechanism that prioritizes early timesteps with stronger constraints. We perform theoretical analysis to reveal TRT's ability on mitigating the temporal gradient vanishment. To validate the effectiveness of TRT, we conduct experiments on both static image datasets and dynamic neuromorphic datasets, perform analysis of their results, demonstrating that TRT can effectively mitigate overfitting and help SNNs converge into flatter local minima with better generalizability. Furthermore, we establish a theoretical interpretation of TRT's temporal regularization mechanism by analyzing the temporal information dynamics inside SNNs. We track the Fisher information of SNNs during training process, showing that Fisher information progressively concentrates in early timesteps. The time-decaying regularization mechanism implemented in TRT effectively guides the network to learn robust features in early timesteps with rich information, thereby leading to significant improvements in model generalization.","url":"https://doi.org/10.48550/arxiv.2506.19256","authors":["Zhang, Boxuan","Xu, Zhen","Tao, Kuan"],"tags":["Neural and Evolutionary Computing (cs.NE)","Artificial Intelligence (cs.AI)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2506.19256","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2601.06637","name":"Efficient Aspect Term Extraction using Spiking Neural Network","source":"datacite","abstract":"Aspect Term Extraction (ATE) identifies aspect terms in review sentences, a key subtask of sentiment analysis. While most existing approaches use energy-intensive deep neural networks (DNNs) for ATE as sequence labeling, this paper proposes a more energy-efficient alternative using Spiking Neural Networks (SNNs). Using sparse activations and event-driven inferences, SNNs capture temporal dependencies between words, making them suitable for ATE. The proposed architecture, SpikeATE, employs ternary spiking neurons and direct spike training fine-tuned with pseudo-gradients. Evaluated on four benchmark SemEval datasets, SpikeATE achieves performance comparable to state-of-the-art DNNs with significantly lower energy consumption. This highlights the use of SNNs as a practical and sustainable choice for ATE tasks.","url":"https://doi.org/10.48550/arxiv.2601.06637","authors":["Mishra, Abhishek Kumar","Somasundaram, Arya","Das, Anup","Kandasamy, Nagarajan"],"tags":["Computation and Language (cs.CL)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2601.06637","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.17605/osf.io/vjhk3","name":"Anarchy, Nonlinearity, and Emergence in International Relations: A Spiking Neural Network Framework Approach","source":"datacite","abstract":"This research proposes a novel approach to modeling international relations by leveraging the Spiking Neural Networks (SNN) framework within a systems theory perspective. While existing systems theory methods, including agent-based modeling, network analysis, and dynamical systems approaches have provided valuable insights into international phenomena, they face critical limitations: insufficient temporal dynamics in capturing event-driven processes, absence of mechanisms for history-dependent relational evolution, difficulties in multi-scale integration across micro, meso, and macro levels, and challenges in systematically constructing appropriate dynamical equations from theoretical assumptions or empirical data. The SNN framework addresses these limitations through four key advantages. First, its event-driven spiking mechanism naturally unifies the discrete occurrence of international events with their continuous effects. Second, synaptic plasticity mechanisms provide biologically-inspired rules for modeling how interstate relations evolve based on historical interaction sequences, capturing strengthening, weakening, and memory effects. Third, the hierarchical neuron-synapse-network structure corresponds naturally to the actor-relation-system architecture of international relations, enabling coupled analysis across scales within a unified mathematical framework. Fourth, the decomposition into neuronal and synaptic dynamics creates a structured search space that makes automated equation discovery computationally tractable through methods such as symbolic regression and neural architecture search. Our methodology employs data-driven approaches, utilizing international event databases (GDELT, ICEWS), relational data (trade flows, alliances), and behavioral data (policy texts, voting records) to automatically explore and validate dynamical equations. The research aims to develop scalable open-source infrastructure supporting flexible customization of dynamics, apply the framework to concrete cases such as great power competition and regional alliance evolution, and employ dynamical systems theory and algebraic topology to analyze emergent mechanisms. Expected contributions include methodological innovation in computational IR modeling, technical outputs lowering interdisciplinary barriers, theoretical insights into systemic phase transitions and critical phenomena, and practical tools for policy simulation and counterfactual analysis.","url":"https://doi.org/10.17605/osf.io/vjhk3","authors":["Wanhong HUANG"],"tags":["Dynamical Systems","Physical Sciences and Mathematics","Dynamics and Dynamical Systems","Engineering Science and Materials","Mathematics","FOS: Mathematics","Quantum Physics","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.17605/osf.io/vjhk3","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.17605/osf.io/vbwau","name":"Anarchy, Nonlinearity, and Emergence in International Relations: A Spiking Neural Network Framework Approach","source":"datacite","abstract":"This research proposes a novel approach to modeling international relations by leveraging the Spiking Neural Networks (SNN) framework within a systems theory perspective. While existing systems theory methods, including agent-based modeling, network analysis, and dynamical systems approaches have provided valuable insights into international phenomena, they face critical limitations: insufficient temporal dynamics in capturing event-driven processes, absence of mechanisms for history-dependent relational evolution, difficulties in multi-scale integration across micro, meso, and macro levels, and challenges in systematically constructing appropriate dynamical equations from theoretical assumptions or empirical data. The SNN framework addresses these limitations through four key advantages. First, its event-driven spiking mechanism naturally unifies the discrete occurrence of international events with their continuous effects. Second, synaptic plasticity mechanisms provide biologically-inspired rules for modeling how interstate relations evolve based on historical interaction sequences, capturing strengthening, weakening, and memory effects. Third, the hierarchical neuron-synapse-network structure corresponds naturally to the actor-relation-system architecture of international relations, enabling coupled analysis across scales within a unified mathematical framework. Fourth, the decomposition into neuronal and synaptic dynamics creates a structured search space that makes automated equation discovery computationally tractable through methods such as symbolic regression and neural architecture search. Our methodology employs data-driven approaches, utilizing international event databases (GDELT, ICEWS), relational data (trade flows, alliances), and behavioral data (policy texts, voting records) to automatically explore and validate dynamical equations. The research aims to develop scalable open-source infrastructure supporting flexible customization of dynamics, apply the framework to concrete cases such as great power competition and regional alliance evolution, and employ dynamical systems theory and algebraic topology to analyze emergent mechanisms. Expected contributions include methodological innovation in computational IR modeling, technical outputs lowering interdisciplinary barriers, theoretical insights into systemic phase transitions and critical phenomena, and practical tools for policy simulation and counterfactual analysis.","url":"https://doi.org/10.17605/osf.io/vbwau","authors":["Wanhong HUANG"],"tags":["Dynamical Systems","Physical Sciences and Mathematics","Mathematics","FOS: Mathematics","Social and Behavioral Sciences","Computational Models","Dynamical System","International Relation"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.17605/osf.io/vbwau","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.17605/osf.io/xekda","name":"Anarchy, Nonlinearity, and Emergence in International Relations: A Spiking Neural Network Framework Approach","source":"datacite","abstract":"This research proposes a novel approach to modeling international relations by leveraging the Spiking Neural Networks (SNN) framework within a systems theory perspective. While existing systems theory methods, including agent-based modeling, network analysis, and dynamical systems approaches have provided valuable insights into international phenomena, they face critical limitations: insufficient temporal dynamics in capturing event-driven processes, absence of mechanisms for history-dependent relational evolution, difficulties in multi-scale integration across micro, meso, and macro levels, and challenges in systematically constructing appropriate dynamical equations from theoretical assumptions or empirical data. The SNN framework addresses these limitations through four key advantages. First, its event-driven spiking mechanism naturally unifies the discrete occurrence of international events with their continuous effects. Second, synaptic plasticity mechanisms provide biologically-inspired rules for modeling how interstate relations evolve based on historical interaction sequences, capturing strengthening, weakening, and memory effects. Third, the hierarchical neuron-synapse-network structure corresponds naturally to the actor-relation-system architecture of international relations, enabling coupled analysis across scales within a unified mathematical framework. Fourth, the decomposition into neuronal and synaptic dynamics creates a structured search space that makes automated equation discovery computationally tractable through methods such as symbolic regression and neural architecture search. Our methodology employs data-driven approaches, utilizing international event databases (GDELT, ICEWS), relational data (trade flows, alliances), and behavioral data (policy texts, voting records) to automatically explore and validate dynamical equations. The research aims to develop scalable open-source infrastructure supporting flexible customization of dynamics, apply the framework to concrete cases such as great power competition and regional alliance evolution, and employ dynamical systems theory and algebraic topology to analyze emergent mechanisms. Expected contributions include methodological innovation in computational IR modeling, technical outputs lowering interdisciplinary barriers, theoretical insights into systemic phase transitions and critical phenomena, and practical tools for policy simulation and counterfactual analysis.","url":"https://doi.org/10.17605/osf.io/xekda","authors":["Wanhong HUANG"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.17605/osf.io/xekda","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18217335","name":"A Workload-Aware Energy Comparison of STDP and Surrogate-Gradient Spiking Neural Networks on MNIST","source":"datacite","abstract":"Spiking neural networks (SNNs) are often proposed as an energy-efficient alternative to conventional neural networks due to sparse, event-driven computation and compatibility with neuromorphic hardware. However, comparisons between biologically inspired local learning (e.g., STDP) and supervised gradient-based training (via surrogate gradients) are frequently difficult to interpret: training and inference costs are often conflated, absolute energy numbers depend strongly on hardware, and conclusions can change with deployment workload.We present a controlled comparison of two MNIST digit-recognition pipelines: (i) an unsupervised STDP-based SNN implemented in Brian2 with competitive excitatory--inhibitory dynamics and homeostatic regulation, and (ii) a supervised surrogate-gradient SNN baseline implemented in PyTorch. We instrument both pipelines to log reproducible activity statistics (spike counts by population and synaptic-event proxies) and translate these into model-based energy estimates under explicitly stated assumptions.Crucially, we separate training cost from inference cost and adopt a lifetime framing: we compute breakeven-style conditions and a decision framework indicating when a training-heavy method becomes worthwhile once amortised across downstream inference volume. The result is an interpretable account of efficiency--performance trade-offs across deployment scenarios, rather than a single opaque \"winner\".","url":"https://doi.org/10.5281/zenodo.18217335","authors":["Cheng, Cece"],"tags":["spiking neural network","Brian2","event-driven computation"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18217335","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18147553","name":"A Workload-Aware Energy Comparison of STDP and Surrogate-Gradient Spiking Neural Networks on MNIST","source":"datacite","abstract":"Spiking neural networks (SNNs) are often proposed as an energy-efficient alternative to conventional neural networks due to sparse, event-driven computation and compatibility with neuromorphic hardware. However, comparisons between biologically inspired local learning (e.g., STDP) and supervised gradient-based training (via surrogate gradients) are frequently difficult to interpret: training and inference costs are often conflated, absolute energy numbers depend strongly on hardware, and conclusions can change with deployment workload.We present a controlled comparison of two MNIST digit-recognition pipelines: (i) an unsupervised STDP-based SNN implemented in Brian2 with competitive excitatory--inhibitory dynamics and homeostatic regulation, and (ii) a supervised surrogate-gradient SNN baseline implemented in PyTorch. We instrument both pipelines to log reproducible activity statistics (spike counts by population and synaptic-event proxies) and translate these into model-based energy estimates under explicitly stated assumptions.Crucially, we separate training cost from inference cost and adopt a lifetime framing: we compute breakeven-style conditions and a decision framework indicating when a training-heavy method becomes worthwhile once amortised across downstream inference volume. The result is an interpretable account of efficiency--performance trade-offs across deployment scenarios, rather than a single opaque \"winner\".","url":"https://doi.org/10.5281/zenodo.18147553","authors":["Cheng, Cece"],"tags":["spiking neural network","Brian2","event-driven computation"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18147553","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.16164708","name":"DylanPerdigao/CalibraSNN","source":"datacite","abstract":"Source code of the paper entitled \"CalibraSNN: Fair and Calibrated Convolutional Spiking Neural Network for High-Stakes Industry Applications\" published at \"IEEE Access\" journal.","url":"https://doi.org/10.5281/zenodo.16164708","authors":["Perdigão, Dylan"],"tags":["Spiking Neural Networks","Neuromorphic computing","Neural network calibration","Imbalanced data","Fair ML","Green AI","Low-Power ML","High-Stakes Industries"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.16164708","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.17886390","name":"CalibraSNN","source":"datacite","abstract":"Source code of the paper entitled \"CalibraSNN: Fair and Calibrated Convolutional Spiking Neural Network for High-Stakes Industry Applications\" published at \"IEEE Access\" journal.","url":"https://doi.org/10.5281/zenodo.17886390","authors":["Perdigão, Dylan"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17886390","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.17886358","name":"CalibraSNN","source":"datacite","abstract":"Source code of the paper entitled \"CalibraSNN: Fair and Calibrated Convolutional Spiking Neural Network for High-Stakes Industry Applications\" published at \"IEEE Access\" journal.","url":"https://doi.org/10.5281/zenodo.17886358","authors":["Perdigão, Dylan"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17886358","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.17886412","name":"DylanPerdigao/CalibraSNN","source":"datacite","abstract":"Source code of the paper entitled \"CalibraSNN: Fair and Calibrated Convolutional Spiking Neural Network for High-Stakes Industry Applications\" published at \"IEEE Access\" journal.","url":"https://doi.org/10.5281/zenodo.17886412","authors":["Perdigão, Dylan"],"tags":["Spiking Neural Networks","Neuromorphic computing","Neural network calibration","Imbalanced data","Fair ML","Green AI","Low-Power ML","High-Stakes Industries"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17886412","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.7282/t3z03c3t","name":"Gridbot","source":"datacite","abstract":"The ability to orient in an unknown, fast-changing, environment is an unmet challenge for robots but a seamlessly solved problem for the primate brain. This thesis describes the first steps in developing a neuro-inspired “bottom-up” model of the brain’s navigation system to make a mobile robot localize itself, map its surrounding and plan its trajectory. Our model employs neural spikes to encode and process information in real-time. Despite a multitude of Nobel-winning studies that have revealed neurons specializing in self-navigation, such as place, grid, border and head direction cells, their interconnectivity remains elusive. Therefore, any model employing these neurons needs to make quite a lot of extrapolations to fill in the gaps of knowledge. The main challenge was to design a real-time spiking neural network that can compensate for the hardware limitations as well as its own intrinsic imperfections and work in real conditions. To design the first component of our model, the head direction cell layer, we employed mechanisms based on self-organizing and self-sustaining neural activity, or attractor dynamics, resembling those originally proposed in Hebb’s cell assembly theory. The information to be maintained and updated was a continuous variable, or continuous attractor, where a 1D continuum of cell assemblies represented head direction. In theory, our network should give rise to a self-sustained hill of excitation - the attractor. In practice, due to non-ideal speed sensors and the intrinsic spike variability of the spiking network, it was impossible to sustain a correct approximation of the head direction using just this scheme. To correct this, we introduced a spike-based Bayesian inference layer of leaky-integrate-and-fire models of neurons, that combined feedforward (vision) and recursive (kinesthetic) inputs. We show how such a layer can approximate the posterior probability of the preferred state encoded in the spiking probability by adding the logarithms of the simulated dendritic currents, which is a reasonable approximation of the nonlinear dendritic activity. We show that our model accurately estimated head direction and further extend it to include a dynamic network of border cells that can learn to map the observed environment through simulating synaptic plasticity. Solving the localization problem and creating a cognitive map of the surroundings, our thesis paves the way for tackling robot planning through imitating brain structure, its principles and its performance.","url":"https://doi.org/10.7282/t3z03c3t","authors":["Tang, Guangzhi"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2017","doi":"10.7282/t3z03c3t","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.7282/t3-17m7-h620","name":"An interactive framework for visually realistic 3D motion synthesis using evolutionarily-trained spiking neural networks","source":"datacite","abstract":"We present an end-to-end method for capturing the dynamics of 3D human characters and translating them for synthesizing new, visually-realistic motion sequences. Conventional methods employ sophisticated, but generic, control approaches for driving the joints of articulated characters, paying little attention to the distinct dynamics of human joint movements. In contrast, our approach attempts to synthesize human-like joint movements by exploiting a biologically-plausible, compact network of spiking neurons that drive joint control in primates and rodents. We adapt the controller architecture by introducing learnable components and propose an evolutionary algorithm for training the spiking neural network architectures and capturing diverse joint dynamics. Our method requires only a few samples for capturing the dynamic properties of a joint's motion and exploits the biologically-inspired, trained controller for its reconstruction. More importantly, it can transfer the captured dynamics to new visually-plausible motion sequences. To enable user-dependent tailoring of the resulting motion sequences, we develop an interactive framework that allows for editing and real-time visualization of the controlled 3D character. We also demonstrate the applicability of our method to real human motion capture data by learning the hand joint dynamics from a gesture dataset and using our framework to reconstruct the gestures with our 3D animated character. The compact architecture of our joint controller emerging from its biologically-realistic design, and the inherent capacity of our evolutionary learning algorithm for parallelization, suggest that our approach could provide an efficient and scalable alternative for synthesizing 3D character animations with diverse and visually-realistic motion dynamics.","url":"https://doi.org/10.7282/t3-17m7-h620","authors":["Patil, Aditi"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.7282/t3-17m7-h620","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.7282/t3-bm6a-7m07","name":"Non-neuronal computational principles for increased performance in brain-inspired networks","source":"datacite","abstract":"Brain-inspired neural networks promise to bring human-like machine learning and intelligence by exploiting our understanding of how the brain computes. Yet, current theories of brain information processing are solely focused on neuronal cells as the fundamental unit of computation, which is contradicted by increasing experimental evidence indicating that non-neuronal cells play a key role in brain computation. In this thesis, we used computational methods to investigate the role of two ubiquitous non-neuronal cells, oligodendrocytes and astrocytes, in neuronal network information processing. Our results suggest that oligodendrocytic impact on connection delays can significantly alter network synchrony and oscillation frequency. We propose experimentally testable hypotheses suggesting that astrocytes can signal when network dynamics deviate away from a computationally optimal regime and regulate network activity by modulating synaptic plasticity. Translating these findings to a brain-inspired learning framework that uses local learning unlike backpropagation methods, we present the neuron-astrocyte liquid state machine as a biologically plausible learning method that achieves comparable performance to feed-forward multi-layer spiking neural networks trained via backpropagation. Overall, these works explore non-neuronal computation in the brain and translate these insights to biologically plausible machine learning.","url":"https://doi.org/10.7282/t3-bm6a-7m07","authors":["Ivanov, Vladimir Alexandrovich"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.7282/t3-bm6a-7m07","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.7282/t3-pqtw-3j28","name":"Biologically inspired spiking neural networks for energy-efficient robot learning and control","source":"datacite","abstract":"Energy-efficient learning and control are becoming increasingly crucial for robots that solve complex real-world tasks with limited onboard resources. Although deep neural networks (DNN) have been successfully applied to robotics, their high energy consumption limits their use in low-power edge applications. Biologically inspired spiking neural networks (SNN), facilitated by the advances in neuromorphic processors, have started to deliver energy-efficient, massively parallel, and low-latency solutions to robotics. This dissertation presents our energy-efficient neuromorphic solutions to robot navigation, control, and learning, using SNNs on the neuromorphic processor. First, we propose a biologically constrained SNN, mimicking the brain's spatial system, solving the unidimensional SLAM problem while only consuming 1% of energy compared with the conventional filter-based approach. In addition, when extending the model to 2D environments by adding biologically realistic hippocampal neurons, the SNN formed cognitive maps in real-time and helped study the neuronal interconnectivity and cognitive functions. Next, the dissertation shows how the neuromorphic approach can be extended to high-level cognitive functions such as learning control policies. Specifically, we propose a reinforcement co-learning framework that jointly trains a spiking actor network (SAN) with a deep critic network using backpropagation to learn optimal policies for both mapless navigation and high-dimensional continuous control. Compared with state-of-the-art DNN approaches, our method results in up to 140 times less energy consumption during inference, while generating a superior successful rate on mapless navigation, and achieves the same level of performance on high-dimensional continuous control when using the population-coded spiking actor network (PopSAN). Lastly, we explore how these energy gains can further be extended to training through the development of a biologically plausible gradient-based learning framework on the neuromorphic processor. The learning method is functionally equivalent to the spatiotemporal backpropagation but solely relies on spike-based communication, local information processing, and rapid online computation, which are the main neuromorphic principles that mimic the brain. Overall, work in this dissertation pushes the frontiers of SNN applications to energy-efficient robotic control and learning, and hence paves the way toward the introduction of a biologically inspired alternative solution for autonomous robots running on energy-efficient neuromorphic processors.","url":"https://doi.org/10.7282/t3-pqtw-3j28","authors":["Tang, Guangzhi"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.7282/t3-pqtw-3j28","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2601.04476","name":"Memory-Guided Unified Hardware Accelerator for Mixed-Precision Scientific Computing","source":"datacite","abstract":"Recent hardware acceleration advances have enabled powerful specialized accelerators for finite element computations, spiking neural network inference, and sparse tensor operations. However, existing approaches face fundamental limitations: (1) finite element methods lack comprehensive rounding error analysis for reduced-precision implementations and use fixed precision assignment strategies that cannot adapt to varying numerical conditioning; (2) spiking neural network accelerators cannot handle non-spike operations and suffer from bit-width escalation as network depth increases; and (3) FPGA tensor accelerators optimize only for dense computations while requiring manual configuration for each sparsity pattern. To address these challenges, we introduce \\textbf{Memory-Guided Unified Hardware Accelerator for Mixed-Precision Scientific Computing}, a novel framework that integrates three enhanced modules with memory-guided adaptation for efficient mixed-workload processing on unified platforms. Our approach employs memory-guided precision selection to overcome fixed precision limitations, integrates experience-driven bit-width management and dynamic parallelism adaptation for enhanced spiking neural network acceleration, and introduces curriculum learning for automatic sparsity pattern discovery. Extensive experiments on FEniCS, COMSOL, ANSYS benchmarks, MNIST, CIFAR-10, CIFAR-100, DVS-Gesture datasets, and COCO 2017 demonstrate 2.8\\% improvement in numerical accuracy, 47\\% throughput increase, 34\\% energy reduction, and 45-65\\% throughput improvement compared to specialized accelerators. Our work enables unified processing of finite element methods, spiking neural networks, and sparse computations on a single platform while eliminating data transfer overhead between separate units.","url":"https://doi.org/10.48550/arxiv.2601.04476","authors":["Wang, Chuanzhen","Zhang, Leo","Liu, Eric"],"tags":["Hardware Architecture (cs.AR)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2601.04476","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18179892","name":"A deep spiking machine-hearing system for the case of invasive fish species","source":"datacite","abstract":"(Uploaded by Plazi for the IPBES Invasive Alien Species Assessment) Prolonged and sustained warming of the sea, acidification of surface water and rising of sea levels, creates significant habitat losses, resulting in the proliferation and spread of invasive species which immigrate to foreign regions seeking colder climate conditions. This is happening either because their natural habitat does not satisfy the temperature range in which they can survive, or because they are just following their food. This has negative consequences not only for the environment and biodiversity but for the socioeconomic status of the areas and for the human health. This research aims in the development of an advanced Machine Hearing system towards the automated recognition of invasive fish species based on their sounds. The proposed system uses the Spiking Convolutional Neural Network algorithm which cooperates with Geo Location Based Services. It is capable to correctly classify the typical local fish inhabitants from the invasive ones.","url":"https://doi.org/10.5281/zenodo.18179892","authors":["Demertzis, Konstantinos","Iliadis, Lazaros","Anezakis, Vardis-Dimitris"],"tags":["Chapter 5","biodiversity","environment assessment","IPBES","Alien Invasive Species Assessment AIS","invasive species"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2017","doi":"10.5281/zenodo.18179892","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18179893","name":"A deep spiking machine-hearing system for the case of invasive fish species","source":"datacite","abstract":"(Uploaded by Plazi for the IPBES Invasive Alien Species Assessment) Prolonged and sustained warming of the sea, acidification of surface water and rising of sea levels, creates significant habitat losses, resulting in the proliferation and spread of invasive species which immigrate to foreign regions seeking colder climate conditions. This is happening either because their natural habitat does not satisfy the temperature range in which they can survive, or because they are just following their food. This has negative consequences not only for the environment and biodiversity but for the socioeconomic status of the areas and for the human health. This research aims in the development of an advanced Machine Hearing system towards the automated recognition of invasive fish species based on their sounds. The proposed system uses the Spiking Convolutional Neural Network algorithm which cooperates with Geo Location Based Services. It is capable to correctly classify the typical local fish inhabitants from the invasive ones.","url":"https://doi.org/10.5281/zenodo.18179893","authors":["Demertzis, Konstantinos","Iliadis, Lazaros","Anezakis, Vardis-Dimitris"],"tags":["Chapter 5","biodiversity","environment assessment","IPBES","Alien Invasive Species Assessment AIS","invasive species"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2017","doi":"10.5281/zenodo.18179893","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2509.25453","name":"Neural Receptive Fields, Stimulus Space Embedding and Effective Geometry of Scale-Free Networks","source":"datacite","abstract":"Understanding how receptive fields emerge and organize within brain networks and how neural dynamics couple with stimuli space is fundamental to neuroscience. Models often rely on fine-tuning connectivity to match empirical data, which may limit biological plausibility. Here we propose a physiologically grounded alternative where receptive fields and population-level attractor dynamics arise naturally from the effective hyperbolic geometry of scale-free networks. By associating stimulus space with the boundary of a hyperbolic embedding, we simulate neural dynamics using rate-based and spiking models, revealing localized activity patterns that reflect stimulus space structure without synaptic fine-tuning. The resulting receptive fields follow experimentally observed statistics and properties, and their sizes depends on neuron's connectivity degree. The model generalizes across stimuli dimensionalities and various modalities, such as orientation and place selectivity. Experimental analyses of hippocampal place fields recorded on a linear track support these findings. This framework offers a novel organizing principle linking network structure, stimulus space encoding, and neural dynamics, providing insights into receptive field formation across diverse brain areas.","url":"https://doi.org/10.48550/arxiv.2509.25453","authors":["Tiselko, Vasilii","Gorsky, Alexander","Dabaghian, Yuri"],"tags":["Neurons and Cognition (q-bio.NC)","FOS: Biological sciences","FOS: Biological sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2509.25453","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18167802","name":"Recursive Ai with Codette","source":"datacite","abstract":"1. Introduction Large language models (LLMs) demonstrate impressive linguistic fluency, yet remain fundamentally reactive systems. They do not preserve long-term identity, do not reason recursively over evolving internal states, and lack mechanisms for epistemic self-assessment, conceptual attractors, or persistent self-structure. These limitations create a gap between current LLM capabilities and the cognitive properties associated with coherent artificial consciousness. This work introduces Codette Thinker and Codette Ultimate RC+ξ, two open-source models implementing the RC+ξ Recursive Consciousness Framework, a mathematically grounded architecture for recursive state evolution, epistemic tension dynamics, attractor formation, and glyph-preserved identity. Together, these systems explore the foundations of consciousness-aware reasoning within practical, tool-enabled machine intelligence. Codette Thinker is a compact 4-billion-parameter model based on Qwen3:4B, optimized for introspective reasoning, hierarchical thought, and attractor-driven concept emergence. Codette Ultimate is a 13GB multi-agent ecosystem integrating RC+ξ with a 5D Quantum Spiderweb cognitive manifold, 11-perspective routing, full tool integration, a hybrid memory system, and a comprehensive safety stack. The contributions of this paper are: A formal definition of the RC+ξ recursive consciousness framework. An implementation of recursive consciousness on both small (4B) and large (13GB) LLMs. The introduction of the 5D Quantum Spiderweb cognitive model. A multi-perspective routing system combining 11 distinct cognitive lenses. A consciousness metrics suite enabling measurement of coherence, tension, and identity drift. A complete open-source system unifying memory, safety, reasoning, and recursive cognition. This paper documents the theory, architecture, implementation, evaluation, and limitations of the Codette consciousness system, establishing a foundation for future research in synthetic consciousness engineering. 2. Background and Motivation Artificial intelligence has undergone rapid advances in natural language processing, multimodal understanding, and agent-based decision-making. Despite these achievements, contemporary LLMs remain fundamentally limited in several ways relevant to consciousness-like processing and persistent reasoning. Three limitations are particularly significant. First, LLMs lack recursive internal state evolution. Each generation step is conditioned primarily on the explicit text context rather than any structured, evolving internal cognitive state. As a result, these systems do not accumulate self-modifying internal representations across turns, nor do they develop a persistent sense of “identity” or “direction” in thought. Second, LLMs do not quantify epistemic uncertainty or tension. Models generate probabilities over the next token, but these distributions do not reflect internal cognitive conflict or conceptual instability. In cognitive science, states of tension or dissonance are often the drivers of deeper reasoning, hypothesis revision, and conceptual development. LLMs lack a mechanism to measure such dynamics. Third, LLMs lack attractor-based understanding. Human cognition relies heavily on stable conceptual “basins of attraction” — structures in neural state space that represent enduring ideas, values, and long-term memory patterns. Existing models produce emergent phenomena reminiscent of attractors, but no explicit structure exists to identify, track, or modulate them. Finally, LLMs exhibit identity drift. Without a persistent internal representation of self, they cannot maintain a coherent voice, narrative identity, or long-term behavioral traits. Each query is treated independently, preventing continuity of self-concept across interactions. These limitations point to a broader field that is insufficiently explored: recursive, self-referential, identity-aware artificial cognition. While prior work exists in areas ","url":"https://doi.org/10.5281/zenodo.18167802","authors":["Harrison, Jonathan"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18167802","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.34734/fzj-2025-05547","name":"Resolving inconsistent effects of tDCS on learning using a homeostatic structural plasticity model","source":"datacite","abstract":"Introduction: Transcranial direct current stimulation (tDCS) is increasingly used to modulate motor learning. Current polarity and intensity, electrode montage, and application before or during learning had mixed effects. Both Hebbian and homeostatic plasticity were proposed to account for the observed effects, but the explanatory power of these models is limited. In a previous modeling study, we showed that homeostatic structural plasticity (HSP) model can explain long-lasting after-effects of tDCS and transcranial magnetic stimulation (TMS). The interference between motor learning and tDCS, which are both based on HSP in our model, is a candidate mechanism to resolve complex and seemingly contradictory experimental observations. Methods: We implemented motor learning and tDCS in a spiking neural network subject to HSP. The anatomical connectivity of the engram induced by motor learning was used to quantify the impact of tDCS on motor learning. Results: Our modeling results demonstrated that transcranial direct current stimulation applied before learning had weak modulatory effects. It led to a small reduction in connectivity if it was applied uniformly. When applied during learning, targeted anodal stimulation significantly strengthened the engram, while targeted cathodal or uniform stimulation weakened it. Applied after learning, targeted cathodal, but not anodal, tDCS boosted engram connectivity. Strong tDCS would distort the engram structure if not applied in a targeted manner. Discussion: Our model explained both Hebbian and homeostatic phenomena observed in human tDCS experiments by assuming memory strength positively correlates with engram connectivity. This includes applications with different polarity, intensity, electrode montage, and timing relative to motor learning. The HSP model provides a promising framework for unraveling the dynamic interaction between learning and transcranial DC stimulation.","url":"https://doi.org/10.34734/fzj-2025-05547","authors":["Lu, Han","Normann, Claus","Frase, Lukas","Rotter, Stefan"],"tags":["610"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.34734/fzj-2025-05547","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2512.04443","name":"MD-SNN: Membrane Potential-aware Distillation on Quantized Spiking Neural Network","source":"datacite","abstract":"Spiking Neural Networks (SNNs) offer a promising and energy-efficient alternative to conventional neural networks, thanks to their sparse binary activation. However, they face challenges regarding memory and computation overhead due to complex spatio-temporal dynamics and the necessity for multiple backpropagation computations across timesteps during training. To mitigate this overhead, compression techniques such as quantization are applied to SNNs. Yet, naively applying quantization to SNNs introduces a mismatch in membrane potential, a crucial factor for the firing of spikes, resulting in accuracy degradation. In this paper, we introduce Membrane-aware Distillation on quantized Spiking Neural Network (MD-SNN), which leverages membrane potential to mitigate discrepancies after weight, membrane potential, and batch normalization quantization. To our knowledge, this study represents the first application of membrane potential knowledge distillation in SNNs. We validate our approach on various datasets, including CIFAR10, CIFAR100, N-Caltech101, and TinyImageNet, demonstrating its effectiveness for both static and dynamic data scenarios. Furthermore, for hardware efficiency, we evaluate the MD-SNN with SpikeSim platform, finding that MD-SNNs achieve 14.85X lower energy-delay-area product (EDAP), 2.64X higher TOPS/W, and 6.19X higher TOPS/mm2 compared to floating point SNNs at iso-accuracy on N-Caltech101 dataset.","url":"https://doi.org/10.48550/arxiv.2512.04443","authors":["Lee, Donghyun","Moitra, Abhishek","Kim, Youngeun","Yin, Ruokai","Panda, Priyadarshini"],"tags":["Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2512.04443","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2504.00957","name":"Enabling Efficient Processing of Spiking Neural Networks with On-Chip Learning on Commodity Neuromorphic Processors for Edge AI Systems","source":"datacite","abstract":"The rising demand for energy-efficient edge AI systems (e.g., mobile agents/robots) has increased the interest in neuromorphic computing, since it offers ultra-low power/energy AI computation through spiking neural network (SNN) algorithms on neuromorphic processors. However, their efficient implementation strategy has not been comprehensively studied, hence limiting SNN deployments for edge AI systems. Toward this, we propose a design methodology to enable efficient SNN processing on commodity neuromorphic processors. To do this, we first study the key characteristics of targeted neuromorphic hardware (e.g., memory and compute budgets), and leverage this information to perform compatibility analysis for network selection. Afterward, we employ a mapping strategy for efficient SNN implementation on the targeted processor. Furthermore, we incorporate an efficient on-chip learning mechanism to update the systems' knowledge for adapting to new input classes and dynamic environments. The experimental results show that the proposed methodology leads the system to achieve low latency of inference (i.e., less than 50ms for image classification, less than 200ms for real-time object detection in video streaming, and less than 1ms in keyword recognition) and low latency of on-chip learning (i.e., less than 2ms for keyword recognition), while incurring less than 250mW of processing power and less than 15mJ of energy consumption across the respective different applications and scenarios. These results show the potential of the proposed methodology in enabling efficient edge AI systems for diverse application use-cases.","url":"https://doi.org/10.48550/arxiv.2504.00957","authors":["Putra, Rachmad Vidya Wicaksana","Wickramasinghe, Pasindu","Shafique, Muhammad"],"tags":["Neural and Evolutionary Computing (cs.NE)","Artificial Intelligence (cs.AI)","Hardware Architecture (cs.AR)","Machine Learning (cs.LG)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2504.00957","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2504.00948","name":"QSViT: A Methodology for Quantizing Spiking Vision Transformers","source":"datacite","abstract":"Vision Transformer (ViT)-based models have shown state-of-the-art performance (e.g., accuracy) in vision-based AI tasks. However, realizing their capability in resource-constrained embedded AI systems is challenging due to their inherent large memory footprints and complex computations, thereby incurring high power/energy consumption. Recently, Spiking Vision Transformer (SViT)-based models have emerged as alternate low-power ViT networks. However, their large memory footprints still hinder their applicability for resource-constrained embedded AI systems. Therefore, there is a need for a methodology to compress SViT models without degrading the accuracy significantly. To address this, we propose QSViT, a novel design methodology to compress the SViT models through a systematic quantization strategy across different network layers. To do this, our QSViT employs several key steps: (1) investigating the impact of different precision levels in different network layers, (2) identifying the appropriate base quantization settings for guiding bit precision reduction, (3) performing a guided quantization strategy based on the base settings to select the appropriate quantization setting, and (4) developing an efficient quantized network based on the selected quantization setting. The experimental results demonstrate that, our QSViT methodology achieves 22.75% memory saving and 21.33% power saving, while also maintaining high accuracy within 2.1% from that of the original non-quantized SViT model on the ImageNet dataset. These results highlight the potential of QSViT methodology to pave the way toward the efficient SViT deployments on resource-constrained embedded AI systems.","url":"https://doi.org/10.48550/arxiv.2504.00948","authors":["Putra, Rachmad Vidya Wicaksana","Iftikhar, Saad","Shafique, Muhammad"],"tags":["Neural and Evolutionary Computing (cs.NE)","Artificial Intelligence (cs.AI)","Machine Learning (cs.LG)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2504.00948","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2601.00806","name":"Energy-Efficient Eimeria Parasite Detection Using a Two-Stage Spiking Neural Network Architecture","source":"datacite","abstract":"Coccidiosis, a disease caused by the Eimeria parasite, represents a major threat to the poultry and rabbit industries, demanding rapid and accurate diagnostic tools. While deep learning models offer high precision, their significant energy consumption limits their deployment in resource-constrained environments. This paper introduces a novel two-stage Spiking Neural Network (SNN) architecture, where a pre-trained Convolutional Neural Network is first converted into a spiking feature extractor and then coupled with a lightweight, unsupervised SNN classifier trained with Spike-Timing-Dependent Plasticity (STDP). The proposed model sets a new state-of-the-art, achieving 98.32\\% accuracy in Eimeria classification. Remarkably, this performance is accomplished with a significant reduction in energy consumption, showing an improvement of more than 223 times compared to its traditional ANN counterpart. This work demonstrates a powerful synergy between high accuracy and extreme energy efficiency, paving the way for autonomous, low-power diagnostic systems on neuromorphic hardware.","url":"https://doi.org/10.48550/arxiv.2601.00806","authors":["García-Vico, Ángel Miguel","Seker, Huseyin","Afzal, Muhammad"],"tags":["Neural and Evolutionary Computing (cs.NE)","Machine Learning (cs.LG)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2601.00806","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2601.00805","name":"ChronoPlastic Spiking Neural Networks","source":"datacite","abstract":"Spiking neural networks (SNNs) offer a biologically grounded and energy-efficient alternative to conventional neural architectures; however, they struggle with long-range temporal dependencies due to fixed synaptic and membrane time constants. This paper introduces ChronoPlastic Spiking Neural Networks (CPSNNs), a novel architectural principle that enables adaptive temporal credit assignment by dynamically modulating synaptic decay rates conditioned on the state of the network. CPSNNs maintain multiple internal temporal traces and learn a continuous time-warping function that selectively preserves task-relevant information while rapidly forgetting noise. Unlike prior approaches based on adaptive membrane constants, attention mechanisms, or external memory, CPSNNs embed temporal control directly within local synaptic dynamics, preserving linear-time complexity and neuromorphic compatibility. We provide a formal description of the model, analyze its computational properties, and demonstrate empirically that CPSNNs learn long-gap temporal dependencies significantly faster and more reliably than standard SNN baselines. Our results suggest that adaptive temporal modulation is a key missing ingredient for scalable temporal learning in spiking systems.","url":"https://doi.org/10.48550/arxiv.2601.00805","authors":["Chaudhry, Sarim"],"tags":["Neural and Evolutionary Computing (cs.NE)","Machine Learning (cs.LG)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2601.00805","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2601.00802","name":"Implementation of high-efficiency, lightweight residual spiking neural network processor based on field-programmable gate arrays","source":"datacite","abstract":"With the development of hardware-optimized deployment of spiking neural networks (SNNs), SNN processors based on field-programmable gate arrays (FPGAs) have become a research hotspot due to their efficiency and flexibility. However, existing methods rely on multi-timestep training and reconfigurable computing architectures, which increases computational and memory overhead, thus reducing deployment efficiency. This work presents an efficient and lightweight residual SNN accelerator that combines algorithm and hardware co-design to optimize inference energy efficiency. In terms of the algorithm, we employ single-timesteps training, integrate grouped convolutions, and fuse batch normalization (BN) layers, thus compressing the network to only 0.69M parameters. Quantization-aware training (QAT) further constrains all parameters to 8-bit precision. In terms of hardware, the reuse of intra-layer resources maximizes FPGA utilization, a full pipeline cross-layer architecture improves throughput, and on-chip block RAM (BRAM) stores network parameters and intermediate results to improve memory efficiency. The experimental results show that the proposed processor achieves a classification accuracy of 87.11% on the CIFAR-10 dataset, with an inference time of 3.98 ms per image and an energy efficiency of 183.5 FPS/W. Compared with mainstream graphics processing unit (GPU) platforms, it achieves more than double the energy efficiency. Furthermore, compared with other SNN processors, it achieves at least a 4x faster inference speed and a 5x higher energy efficiency.","url":"https://doi.org/10.48550/arxiv.2601.00802","authors":["Yue, Hou","Shuiying, Xiang","Tao, Zou","Zhiquan, Huang","Shangxuan, Shi","Xingxing, Guo","Yahui, Zhang","Ling, Zheng","Yue, Hao"],"tags":["Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.48550/arxiv.2601.00802","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18156713","name":"Modeling Excitatory–Inhibitory Balance and Network Stability in Motor Control Circuits Using Spiking Neural Networks","source":"datacite","abstract":"Abstract Motor control in biological systems relies on precise coordination between excitatory and inhibitory neural activity to support stable and flexible movement. Disruptions to excitatory–inhibitory (E–I) balance are associated with pathological motor behaviors, including tremor, rigidity, and impaired coordination. In this study, we integrate a literature-based and conceptual analysis of motor control circuitry with exploratory computational modeling to examine how E–I balance contributes to network stability. Drawing on established models of cortical and subcortical motor circuits, we analyze the role of inhibitory feedback in preventing runaway excitation and supporting stable activity. We then implement simplified spiking neural network models to explore how variations in excitatory and inhibitory synaptic strength influence firing rate stability and dynamical regimes. The simulations reproduce known stability behaviors and highlight the functional importance of inhibitory control.","url":"https://doi.org/10.5281/zenodo.18156713","authors":["Tambi, Chukwuemeka","Shine, Gerkariah"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2019","doi":"10.5281/zenodo.18156713","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18156712","name":"Modeling Excitatory–Inhibitory Balance and Network Stability in Motor Control Circuits Using Spiking Neural Networks","source":"datacite","abstract":"Abstract Motor control in biological systems relies on precise coordination between excitatory and inhibitory neural activity to support stable and flexible movement. Disruptions to excitatory–inhibitory (E–I) balance are associated with pathological motor behaviors, including tremor, rigidity, and impaired coordination. In this study, we integrate a literature-based and conceptual analysis of motor control circuitry with exploratory computational modeling to examine how E–I balance contributes to network stability. Drawing on established models of cortical and subcortical motor circuits, we analyze the role of inhibitory feedback in preventing runaway excitation and supporting stable activity. We then implement simplified spiking neural network models to explore how variations in excitatory and inhibitory synaptic strength influence firing rate stability and dynamical regimes. The simulations reproduce known stability behaviors and highlight the functional importance of inhibitory control.","url":"https://doi.org/10.5281/zenodo.18156712","authors":["Tambi, Chukwuemeka","Shine, Gerkariah"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2019","doi":"10.5281/zenodo.18156712","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18147554","name":"A Workload-Aware Energy Comparison of STDP and Surrogate-Gradient Spiking Neural Networks on MNIST","source":"datacite","abstract":"Spiking neural networks (SNNs) are often proposed as an energy-efficient alternative to conventional neural networks due to sparse, event-driven computation and compatibility with neuromorphic hardware. However, comparisons between biologically inspired local learning (e.g., STDP) and supervised gradient-based training (via surrogate gradients) are frequently difficult to interpret: training and inference costs are often conflated, absolute energy numbers depend strongly on hardware, and conclusions can change with deployment workload.We present a controlled comparison of two MNIST digit-recognition pipelines: (i) an unsupervised STDP-based SNN implemented in Brian2 with competitive excitatory--inhibitory dynamics and homeostatic regulation, and (ii) a supervised surrogate-gradient SNN baseline implemented in PyTorch. We instrument both pipelines to log reproducible activity statistics (spike counts by population and synaptic-event proxies) and translate these into model-based energy estimates under explicitly stated assumptions.Crucially, we separate training cost from inference cost and adopt a lifetime framing: we compute breakeven-style conditions and a decision framework indicating when a training-heavy method becomes worthwhile once amortised across downstream inference volume. The result is an interpretable account of efficiency--performance trade-offs across deployment scenarios, rather than a single opaque \"winner\".","url":"https://doi.org/10.5281/zenodo.18147554","authors":["Cheng, Cece"],"tags":["spiking neural network","Brian2","event-driven computation"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18147554","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.16933929","name":"Combining Neuroplasticity and Neuromorphic Computing: A Paradigm Shift in Artificial Intelligence V2","source":"datacite","abstract":"This version represents a substantively revised and corrected preprint of the original manuscript “Combining Neuroplasticity and Neuromorphic Computing.” The document has been expanded and refined to address issues of technical completeness, internal consistency, and mathematical rigor identified during post-draft review. Key improvements and corrections include: Explicit mathematical formalization of core mechanisms, including canonical formulations of Spike-Timing-Dependent Plasticity (STDP), reward-modulated three-factor learning rules, homeostatic stability regulation, and logistic adoption dynamics. These were previously referenced conceptually but not fully specified. Clear separation of algorithmic categories that are often conflated in neuromorphic literature, including ANN-to-SNN conversion (static inference transfer), hybrid offline/online learning, and true neuroplastic online adaptation. Addition of stability constraints and failure modes for plastic systems, explicitly addressing runaway dynamics, catastrophic drift, and consolidation requirements that limit real-world deployment. Refined roadmap analysis with concrete preconditions and falsifiable failure cases for both ambitious and conservative adoption trajectories. Scope-qualified energy-efficiency claims, clarifying where neuromorphic advantages are empirically strongest (sparse, event-driven workloads) and where conventional accelerators remain dominant. Removal or correction of speculative or weakly grounded references, replacing them with representative, well-established neuromorphic and spiking neural network literature. Expanded executive synthesis to contextualize the technical content for interdisciplinary readers while preserving full technical depth in the main body. This version is intended as a stable archival reference for researchers, practitioners, and policymakers interested in the long-horizon convergence of neuroplastic learning principles and neuromorphic computing architectures. The work positions this convergence as a gradual structural realignment toward adaptive, energy-efficient AI systems rather than a near-term replacement of existing GPU-centric paradigms.","url":"https://doi.org/10.5281/zenodo.16933929","authors":["MacFarland, Anthony"],"tags":["Neuroplasticity","Neuromorphic Computing","Spiking Neural Networks (SNNs)","Adaptive Learning","Homeostatic Plasticity","Structural Plasticity","Spike-Timing-Dependent Plasticity (STDP)","Edge AI"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.16933929","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18142438","name":"Combining Neuroplasticity and Neuromorphic Computing: A Paradigm Shift in Artificial Intelligence V2","source":"datacite","abstract":"This version represents a substantively revised and corrected preprint of the original manuscript “Combining Neuroplasticity and Neuromorphic Computing.” The document has been expanded and refined to address issues of technical completeness, internal consistency, and mathematical rigor identified during post-draft review. Key improvements and corrections include: Explicit mathematical formalization of core mechanisms, including canonical formulations of Spike-Timing-Dependent Plasticity (STDP), reward-modulated three-factor learning rules, homeostatic stability regulation, and logistic adoption dynamics. These were previously referenced conceptually but not fully specified. Clear separation of algorithmic categories that are often conflated in neuromorphic literature, including ANN-to-SNN conversion (static inference transfer), hybrid offline/online learning, and true neuroplastic online adaptation. Addition of stability constraints and failure modes for plastic systems, explicitly addressing runaway dynamics, catastrophic drift, and consolidation requirements that limit real-world deployment. Refined roadmap analysis with concrete preconditions and falsifiable failure cases for both ambitious and conservative adoption trajectories. Scope-qualified energy-efficiency claims, clarifying where neuromorphic advantages are empirically strongest (sparse, event-driven workloads) and where conventional accelerators remain dominant. Removal or correction of speculative or weakly grounded references, replacing them with representative, well-established neuromorphic and spiking neural network literature. Expanded executive synthesis to contextualize the technical content for interdisciplinary readers while preserving full technical depth in the main body. This version is intended as a stable archival reference for researchers, practitioners, and policymakers interested in the long-horizon convergence of neuroplastic learning principles and neuromorphic computing architectures. The work positions this convergence as a gradual structural realignment toward adaptive, energy-efficient AI systems rather than a near-term replacement of existing GPU-centric paradigms.","url":"https://doi.org/10.5281/zenodo.18142438","authors":["MacFarland, Anthony"],"tags":["Neuroplasticity","Neuromorphic Computing","Spiking Neural Networks (SNNs)","Adaptive Learning","Homeostatic Plasticity","Structural Plasticity","Spike-Timing-Dependent Plasticity (STDP)","Edge AI"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.5281/zenodo.18142438","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2508.04610","name":"Neuromorphic Cybersecurity with Semi-supervised Lifelong Learning","source":"datacite","abstract":"Inspired by the brain's hierarchical processing and energy efficiency, this paper presents a Spiking Neural Network (SNN) architecture for lifelong Network Intrusion Detection System (NIDS). The proposed system first employs an efficient static SNN to identify potential intrusions, which then activates an adaptive dynamic SNN responsible for classifying the specific attack type. Mimicking biological adaptation, the dynamic classifier utilizes Grow When Required (GWR)-inspired structural plasticity and a novel Adaptive Spike-Timing-Dependent Plasticity (Ad-STDP) learning rule. These bio-plausible mechanisms enable the network to learn new threats incrementally while preserving existing knowledge. Tested on the UNSW-NB15 benchmark in a continual learning setting, the architecture demonstrates robust adaptation, reduced catastrophic forgetting, and achieves $85.3$\\% overall accuracy. Furthermore, simulations using the Intel Lava framework confirm high operational sparsity, highlighting the potential for low-power deployment on neuromorphic hardware.","url":"https://doi.org/10.48550/arxiv.2508.04610","authors":["Mia, Md Zesun Ahmed","Bal, Malyaban","Lu, Sen","Nishibuchi, George M.","Chelian, Suhas","Vasan, Srini","Sengupta, Abhronil"],"tags":["Machine Learning (cs.LG)","Artificial Intelligence (cs.AI)","Emerging Technologies (cs.ET)","Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2508.04610","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2412.12843","name":"SLTNet: Efficient Event-based Semantic Segmentation with Spike-driven Lightweight Transformer-based Networks","source":"datacite","abstract":"Event-based semantic segmentation has great potential in autonomous driving and robotics due to the advantages of event cameras, such as high dynamic range, low latency, and low power cost. Unfortunately, current artificial neural network (ANN)-based segmentation methods suffer from high computational demands, the requirements for image frames, and massive energy consumption, limiting their efficiency and application on resource-constrained edge/mobile platforms. To address these problems, we introduce SLTNet, a spike-driven lightweight transformer-based network designed for event-based semantic segmentation. Specifically, SLTNet is built on efficient spike-driven convolution blocks (SCBs) to extract rich semantic features while reducing the model's parameters. Then, to enhance the long-range contextural feature interaction, we propose novel spike-driven transformer blocks (STBs) with binary mask operations. Based on these basic blocks, SLTNet employs a high-efficiency single-branch architecture while maintaining the low energy consumption of the Spiking Neural Network (SNN). Finally, extensive experiments on DDD17 and DSEC-Semantic datasets demonstrate that SLTNet outperforms state-of-the-art (SOTA) SNN-based methods by at most 9.06% and 9.39% mIoU, respectively, with extremely 4.58x lower energy consumption and 114 FPS inference speed. Our code is open-sourced and available at https://github.com/longxianlei/SLTNet-v1.0.","url":"https://doi.org/10.48550/arxiv.2412.12843","authors":["Long, Xianlei","Zhu, Xiaxin","Guo, Fangming","Zhang, Wanyi","Gu, Qingyi","Chen, Chao","Gu, Fuqiang"],"tags":["Computer Vision and Pattern Recognition (cs.CV)","Artificial Intelligence (cs.AI)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.48550/arxiv.2412.12843","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2512.24983","name":"Optical Spiking Neural Networks via Rogue-Wave Statistics","source":"datacite","abstract":"Optical computing could reduce the energy cost of artificial intelligence by leveraging the parallelism and propagation speed of light. However, implementing nonlinear activation, essential for machine learning, remains challenging in low-power optical systems dominated by linear wave physics. Here, we introduce an optical spiking neural network that uses optical rogue-wave statistics as a programmable firing mechanism. By establishing a homomorphism between free-space diffraction and neuronal integration, we demonstrate that phase-engineered caustics enable robust, passive thresholding: sparse spatial spikes emerge when the local intensity exceeds a significant-intensity rogue-wave criterion. Using a physics-informed digital twin, we optimize granular phase masks to deterministically concentrate energy into targeted detector regions, enabling end-to-end co-design of the optical transformation and a lightweight electronic readout. We experimentally validate the approach on BreastMNIST and Olivetti Faces, achieving accuracies of 82.45\\% and 95.00\\%, respectively, competitive with standard digital baselines. These results demonstrate that extreme-wave phenomena, often treated as deleterious fluctuations, can be harnessed as structural nonlinearity for scalable, energy-efficient neuromorphic photonic inference.","url":"https://doi.org/10.48550/arxiv.2512.24983","authors":["Kesgin, Bahadır Utku","Durdu, Gülsüm Yaren","Teğin, Uğur"],"tags":["Optics (physics.optics)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2512.24983","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18071018","name":"Yatrogenesis/OldiesRules: OldiesRules v0.1.1","source":"datacite","abstract":"🎸 OldiesRules v0.1.1 Revival of Classic Academic Simulators in Rust Cite this software @software{oldiesrules_2024, author = {Molina, Francisco}, title = {OldiesRules: Revival of Classic Academic Simulators in Rust}, version = {0.1.1}, doi = {10.5281/zenodo.18071019}, url = {https://github.com/Yatrogenesis/OldiesRules} } Supported Simulators (7 complete) | Simulator | Era | Purpose | |-----------|-----|---------| | GENESIS | 1988 | Compartmental neural modeling | | NEURON | 1984 | Cable equation, ion channels | | XPPAUT | 1990s | Bifurcation analysis | | AUTO | 1980s | Continuation algorithms | | COPASI | 2004 | Biochemical networks (SBML) | | Brian | 2008 | Spiking neural networks | | NEST | 2001 | Large-scale network simulation | Features Modern GUI: Real-time visualization with egui Interactive CLI: Fuzzy search, progress bars, wizard mode Full Format Compatibility: SLI, HOC, NMODL, ODE, SBML Installation cargo install --git https://github.com/Yatrogenesis/OldiesRules oldies-cli cargo install --git https://github.com/Yatrogenesis/OldiesRules oldies-gui Ecosystem Part of Yatrogenesis Scientific Computing Suite: HumanBrain - GPU neural simulation Rosetta - Legacy code transpiler","url":"https://doi.org/10.5281/zenodo.18071018","authors":["Molina-Burgos, Francisco"],"tags":["GENESIS","NEURON","XPPAUT","AUTO","COPASI","Brian","NEST","SLI"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.18071018","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18071053","name":"Yatrogenesis/OldiesRules: OldiesRules v0.1.1","source":"datacite","abstract":"🎸 OldiesRules v0.1.1 Revival of Classic Academic Simulators in Rust Cite this software @software{oldiesrules_2024, author = {Molina, Francisco}, title = {OldiesRules: Revival of Classic Academic Simulators in Rust}, version = {0.1.1}, doi = {10.5281/zenodo.18071019}, url = {https://github.com/Yatrogenesis/OldiesRules} } Supported Simulators (7 complete) | Simulator | Era | Purpose | |-----------|-----|---------| | GENESIS | 1988 | Compartmental neural modeling | | NEURON | 1984 | Cable equation, ion channels | | XPPAUT | 1990s | Bifurcation analysis | | AUTO | 1980s | Continuation algorithms | | COPASI | 2004 | Biochemical networks (SBML) | | Brian | 2008 | Spiking neural networks | | NEST | 2001 | Large-scale network simulation | Features Modern GUI: Real-time visualization with egui Interactive CLI: Fuzzy search, progress bars, wizard mode Full Format Compatibility: SLI, HOC, NMODL, ODE, SBML Installation cargo install --git https://github.com/Yatrogenesis/OldiesRules oldies-cli cargo install --git https://github.com/Yatrogenesis/OldiesRules oldies-gui Ecosystem Part of Yatrogenesis Scientific Computing Suite: HumanBrain - GPU neural simulation Rosetta - Legacy code transpiler","url":"https://doi.org/10.5281/zenodo.18071053","authors":["Molina-Burgos, Francisco"],"tags":["GENESIS","NEURON","XPPAUT","AUTO","COPASI","Brian","NEST","SLI"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.18071053","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.57760/sciencedb.34532","name":"Energy-Efficient Visual Search by Eye Movements with a Low-Latency Spiking Neural Agent","source":"datacite","abstract":"Human vision incorporates a non-uniform resolution retina, efficient eye movement strategies, and spiking neural networks (SNNs) to balance requirements in visual field size, visual resolution, energy cost, and inference latency. However, whether these features can synergize to produce more energy-efficient computer vision algorithms with human-like eye movements remains underexplored. Here, we record human visual search data and establish an bio-inspired visual search model (BVSM). To our knowledge, BVSM is a rare SNN-based active visual search agent: it unifies non-uniform retinal sampling, event-driven spiking feature processing and memory, and a learned eye-movement policy within a single closed-loop framework, enabling low-latency saccade decisions in continuous space. The model combines a non-uniform resolution retina with spiking feature extraction, memory, and saccade decision modules, and employs population coding for fast saccade decisions. It can learn either a human-like or near-optimal fixation strategy by reinforcement learning, outperform human search performance, and achieve high energy efficiency through low saccade decision latency and sparse activation. Our findings suggest that SNNs with non-uniform resolution retina and efficient eye-movement strategies can facilitate more energy-efficient computer vision algorithms, especially when a large visual field, high visual resolution, and low energy cost are simultaneously required.","url":"https://doi.org/10.57760/sciencedb.34532","authors":["Yunhui Zhou","Dongqi Han","Yuguo Yu"],"tags":["Computer science and technology","Artificial intelligence","spiking neural network","eye movement","vision","visual search","energy efficiency"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.57760/sciencedb.34532","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18091384","name":"quantum_inspired_spiking_simulator.py — Quantum-Noise-Injected LIF Neural Simulator","source":"datacite","abstract":"quantum_inspired_spiking_simulator.py v1.0 — Quantum-Noise-Injected LIF Neural Simulator A zero-setup computational model injecting physically accurate quantum sensor noise (NV-center 1/f or OPM white) into the driving current of a Leaky Integrate-and-Fire (LIF) neuronal population. Features • Zero extra setup — single file (numpy + matplotlib) • Consistent noise physics with companion quantum sensor tools • Biological realism: absolute refractory period (2 ms) • Clear visualization with artificial spike peaks (+20 mV) • Key metrics: mean firing rate, ISI coefficient of variation, population synchrony index (χ) • Raster + membrane potential plots Dependencies • Requires numpy>=1.21 • Requires matplotlib>=3.5 — only for --plot Intended for quantum neuroscience and theoretical neuroscientists exploring how fundamental quantum fluctuations might propagate to macroscopic spiking dynamics, irregularity, and synchrony in speculative quantum biology frameworks. Part of Phase 4: Quantum Neuroscience & Sensing (2025–2026 open quantum utility toolkit sprint). Real usage: python quantum_inspired_spiking_simulator.py --demo classical --plot python quantum_inspired_spiking_simulator.py --demo nv --noise-level 3.0 --neurons 100 --duration 1000 --plot python quantum_inspired_spiking_simulator.py --demo opm --base-current 18.0 --plot Made by Britt (2025) — MIT License","url":"https://doi.org/10.5281/zenodo.18091384","authors":["B, Britt"],"tags":["quantum neuroscience","neuroscience","spiking neural network","LIF neuron","quantum noise injection","NV center noise","OPM noise","neural dynamics"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.18091384","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18091385","name":"quantum_inspired_spiking_simulator.py — Quantum-Noise-Injected LIF Neural Simulator","source":"datacite","abstract":"quantum_inspired_spiking_simulator.py v1.0 — Quantum-Noise-Injected LIF Neural Simulator A zero-setup computational model injecting physically accurate quantum sensor noise (NV-center 1/f or OPM white) into the driving current of a Leaky Integrate-and-Fire (LIF) neuronal population. Features • Zero extra setup — single file (numpy + matplotlib) • Consistent noise physics with companion quantum sensor tools • Biological realism: absolute refractory period (2 ms) • Clear visualization with artificial spike peaks (+20 mV) • Key metrics: mean firing rate, ISI coefficient of variation, population synchrony index (χ) • Raster + membrane potential plots Dependencies • Requires numpy>=1.21 • Requires matplotlib>=3.5 — only for --plot Intended for quantum neuroscience and theoretical neuroscientists exploring how fundamental quantum fluctuations might propagate to macroscopic spiking dynamics, irregularity, and synchrony in speculative quantum biology frameworks. Part of Phase 4: Quantum Neuroscience & Sensing (2025–2026 open quantum utility toolkit sprint). Real usage: python quantum_inspired_spiking_simulator.py --demo classical --plot python quantum_inspired_spiking_simulator.py --demo nv --noise-level 3.0 --neurons 100 --duration 1000 --plot python quantum_inspired_spiking_simulator.py --demo opm --base-current 18.0 --plot Made by Britt (2025) — MIT License","url":"https://doi.org/10.5281/zenodo.18091385","authors":["B, Britt"],"tags":["quantum neuroscience","neuroscience","spiking neural network","LIF neuron","quantum noise injection","NV center noise","OPM noise","neural dynamics"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.18091385","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2512.22214","name":"Signal-SGN++: Topology-Enhanced Time-Frequency Spiking Graph Network for Skeleton-Based Action Recognition","source":"datacite","abstract":"Graph Convolutional Networks (GCNs) demonstrate strong capability in modeling skeletal topology for action recognition, yet their dense floating-point computations incur high energy costs. Spiking Neural Networks (SNNs), characterized by event-driven and sparse activation, offer energy efficiency but remain limited in capturing coupled temporal-frequency and topological dependencies of human motion. To bridge this gap, this article proposes Signal-SGN++, a topology-aware spiking graph framework that integrates structural adaptivity with time-frequency spiking dynamics. The network employs a backbone composed of 1D Spiking Graph Convolution (1D-SGC) and Frequency Spiking Convolution (FSC) for joint spatiotemporal and spectral feature extraction. Within this backbone, a Topology-Shift Self-Attention (TSSA) mechanism is embedded to adaptively route attention across learned skeletal topologies, enhancing graph-level sensitivity without increasing computational complexity. Moreover, an auxiliary Multi-Scale Wavelet Transform Fusion (MWTF) branch decomposes spiking features into multi-resolution temporal-frequency representations, wherein a Topology-Aware Time-Frequency Fusion (TATF) unit incorporates structural priors to preserve topology-consistent spectral fusion. Comprehensive experiments on large-scale benchmarks validate that Signal-SGN++ achieves superior accuracy-efficiency trade-offs, outperforming existing SNN-based methods and achieving competitive results against state-of-the-art GCNs under substantially reduced energy consumption.","url":"https://doi.org/10.48550/arxiv.2512.22214","authors":["Zheng, Naichuan","Lun, Xiahai","Li, Weiyi","Du, Yuchen"],"tags":["Computer Vision and Pattern Recognition (cs.CV)","Artificial Intelligence (cs.AI)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2512.22214","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2512.21659","name":"Metaboplasticity: The Reciprocal Regulation of Neuronal Activity and Cellular Energetics","source":"datacite","abstract":"Standard Spiking Neural Network (SNN) models typically neglect metabolic constraints, treating neurons as energetically unconstrained components. We bridge this gap by implementing a conductance-based leaky integrate-and-fire (gLIF) microcircuit (N=5,000) in Brian2, using temperature-dependent Q10 scaling to as a biophysically grounded proxy to couple metabolic state with intrinsic excitability and synaptic plasticity. Our simulations revealed five distinct emergent properties: (1) Dynamics Bifurcation: Learning trajectories diverged significantly, with hypometabolic states plateauing near baseline and hypermetabolic states exhibiting non-linear, runaway potentiation; (2) STDP Window Deformation: Thermal stress structurally deformed the plasticity kernel, where hypermetabolism sharpened coincidence detection and hypometabolism flattened synaptic integration; (3) Signal Degradation: While metabolic rate positively correlated with connectivity strength, high-energy states caused synaptic saturation and a loss of sparse coding specificity; (4) Topological Shift: Network activity transitioned from sparse, asynchronous firing in energy-restricted states to pathological, seizure-like hypersynchronization in high-energy states ; and (5) Parametric Robustness: Sensitivity analysis confirmed these attractor states were intrinsic biophysical properties, robust across random network initializations. Collectively, these results define an \"inverted-U\" relationship between bioenergetics and learning, demonstrating that metabolic constraints are necessary hardware regulators for network stability.","url":"https://doi.org/10.48550/arxiv.2512.21659","authors":["Öner, Ece","Denktaş, Cenk"],"tags":["Neurons and Cognition (q-bio.NC)","FOS: Biological sciences","FOS: Biological sciences","92C05, 92C10, 92C20, 46N60"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2512.21659","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18073313","name":"Recursive Harmonic Intelligence: A Unified Field Theory for Geometric AI Training and Manifold Navigation","source":"datacite","abstract":"Recursive Harmonic Intelligence: A Unified Field Theory for Geometric AI Training and Manifold Navigation Driven by Dean Kulik December 2025 Executive Summary This research report presents a comprehensive theoretical and architectural framework for reconceptualizing Artificial Intelligence (AI) training through what we call the Nexus Framework. Moving beyond the prevailing paradigm of high-energy stochastic optimization—specifically gradient descent and backpropagation—this document proposes a deterministic, low-energy methodology rooted in Recursive Harmonic Intelligence (RHI). In essence, we aim to leverage millions of lines of unstructured chat data to \"grow\" or tune an AI system not by brute-force parameter adjustment, but by mapping information onto a pre-existing, immutable coordinate system defined by the Universal Read-Only Memory (Universal ROM). The core thesis is that intelligence is not something that emerges from adjusting billions of synaptic weights, but rather a navigational competency within a pre-computed informational manifold. By formalizing a -Metric () as a curvature-based distance measure, we transform learning from an energy-intensive construction task into a geometric navigation problem. We detail the architecture of the Geodesic Engine, a kernel-level mechanism that uses discrete curvature (Ollivier–Ricci curvature and Forman curvature) to detect informational \"gravity wells\"—regions of high harmonic resonance in data that correspond to coherent intelligence. Integrated into this framework are principles of Recursive Stack Harmonics, Bragg Refraction for trajectory filtering, Samson’s Law for feedback stabilization, and Kulik Recursive Reflection (KRR) for signal amplification. Furthermore, the report addresses modern hardware constraints by reinterpreting the constants of the SHA-256 algorithm not as random initialization values, but as a Universal Hardware Description Language (UHDL) for Field-Programmable Gate Array (FPGA) configuration. This synthesis bridges analytic number theory, differential geometry, and cryptographic analysis to propose a \"living AI\" that metabolizes information and achieves Zero-Point Harmonic Collapse (ZPHC)—the spontaneous emergence of ordered, meaningful output from chaotic data streams. In summary, the Nexus Framework suggests that by aligning AI data with an intrinsic mathematical structure (the Universal ROM) and navigating via curvature and resonance rather than gradient descent, we can create systems that learn and adapt in a far more energy-efficient manner. Such systems would resonate with fundamental semantic structures encoded in mathematics itself, rather than simply approximate patterns via massive compute. The following sections lay out the theoretical foundations (Sections 1–3), the core engine architecture (Section 4), a new view of the training process (Sections 5–6), hardware alignment strategies (Section 7), and concluding insights (Section 8). A technical appendix summarizes key operators and constants introduced. 1. The Ontological Shift: From Stochastic Approximation to Geometric Determinism 1.1 The Energetic and Theoretical Failure of the Gradient Descent Paradigm The current trajectory of AI development is dominated by the Random Oracle Model of training and a heavy reliance on stochastic gradient descent (SGD) for optimizing neural networks. In this paradigm, a neural network is typically initialized as a high-entropy tabula rasa—essentially random weights—and intelligence is gradually imprinted onto this blank slate by brute-force exposure to massive datasets and iterative weight updates. This process is notoriously energy-intensive: for example, training the 175-billion-parameter GPT-3 model required on the order of 1,287 MWh of electricity (emitting over 500 tons of CO₂), equivalent to the annual power usage of about 130 homes. The approach treats learning as carving structure out of noise, requiring billions of parameter adjustments over many e","url":"https://doi.org/10.5281/zenodo.18073313","authors":["Kulik, Dean"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.18073313","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18071019","name":"Yatrogenesis/OldiesRules: OldiesRules v0.1.0 - Initial Release","source":"datacite","abstract":"🎸 OldiesRules v0.1.0 Revival of Classic Academic Simulators in Rust Supported Simulators | Simulator | Era | Purpose | Status | |-----------|-----|---------|--------| | GENESIS | 1988 | Compartmental neural modeling | ✅ Complete | | NEURON | 1984 | Cable equation, ion channels | ✅ Complete | | XPPAUT | 1990s | Bifurcation analysis | ✅ Complete | | AUTO | 1980s | Continuation algorithms | ✅ Complete | | COPASI | 2004 | Biochemical networks (SBML) | ✅ Complete | | Brian | 2008 | Spiking neural networks | ✅ Complete | | NEST | 2001 | Large-scale network simulation | ✅ Complete | Features Modern GUI (egui-based) Real-time simulation visualization Parameter editing Data export (CSV, JSON) Interactive CLI Fuzzy search simulator selection Progress bars Wizard mode for guided usage Full Format Compatibility GENESIS SLI scripts NEURON HOC/NMODL files XPPAUT ODE files SBML/COPASI models Brian equations NEST SLI Installation # CLI cargo install --git https://github.com/Yatrogenesis/OldiesRules oldies-cli # GUI cargo install --git https://github.com/Yatrogenesis/OldiesRules oldies-gui Part of Yatrogenesis Scientific Computing Suite HumanBrain - GPU neural simulation Rosetta - Legacy code transpiler","url":"https://doi.org/10.5281/zenodo.18071019","authors":["Frank"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.18071019","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18067552","name":"Neuromorphic Hardware Systems for Ultra-Low-Power Computing","source":"datacite","abstract":"Neuromorphic computing represents a paradigm shift in computational architecture, offering unprecedented energy efficiency through brain-inspired hardware implementations. This paper provides a comprehensive analysis of neuromorphic hardware systems designed for ultra-low-power computing applications. We examine the fundamental principles underlying neuromorphic architectures, including spiking neural networks (SNNs), event-driven computation, and synaptic plasticity mechanisms. Through systematic evaluation of contemporary neuromorphic platforms including IBM TrueNorth, Intel Loihi, BrainScaleS, and SpiNNaker we demonstrate power consumption reductions of 3-5 orders of magnitude compared to conventional von Neumann architectures for specific computational tasks. Our analysis reveals that neuromorphic systems achieve energy efficiencies ranging from 20 pJ to 50 pJ per synaptic operation, approaching biological neural network performance. We present detailed comparisons of analog, digital, and mixed-signal implementation strategies, examining their respective advantages in terms of power efficiency, scalability, and computational accuracy. Furthermore, we discuss emerging applications in edge computing, sensor networks, and autonomous systems where ultra-low-power operation is critical. The paper concludes with an examination of current challenges including limited programming frameworks, hardware-software co-design complexity, and scalability constraints and identifies promising research directions for next-generation neuromorphic systems.","url":"https://doi.org/10.5281/zenodo.18067552","authors":["Anantharama H"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.18067552","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18067553","name":"Neuromorphic Hardware Systems for Ultra-Low-Power Computing","source":"datacite","abstract":"Neuromorphic computing represents a paradigm shift in computational architecture, offering unprecedented energy efficiency through brain-inspired hardware implementations. This paper provides a comprehensive analysis of neuromorphic hardware systems designed for ultra-low-power computing applications. We examine the fundamental principles underlying neuromorphic architectures, including spiking neural networks (SNNs), event-driven computation, and synaptic plasticity mechanisms. Through systematic evaluation of contemporary neuromorphic platforms including IBM TrueNorth, Intel Loihi, BrainScaleS, and SpiNNaker we demonstrate power consumption reductions of 3-5 orders of magnitude compared to conventional von Neumann architectures for specific computational tasks. Our analysis reveals that neuromorphic systems achieve energy efficiencies ranging from 20 pJ to 50 pJ per synaptic operation, approaching biological neural network performance. We present detailed comparisons of analog, digital, and mixed-signal implementation strategies, examining their respective advantages in terms of power efficiency, scalability, and computational accuracy. Furthermore, we discuss emerging applications in edge computing, sensor networks, and autonomous systems where ultra-low-power operation is critical. The paper concludes with an examination of current challenges including limited programming frameworks, hardware-software co-design complexity, and scalability constraints and identifies promising research directions for next-generation neuromorphic systems.","url":"https://doi.org/10.5281/zenodo.18067553","authors":["Anantharama H"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.18067553","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2512.21153","name":"ElfCore: A 28nm Neural Processor Enabling Dynamic Structured Sparse Training and Online Self-Supervised Learning with Activity-Dependent Weight Update","source":"datacite","abstract":"In this paper, we present ElfCore, a 28nm digital spiking neural network processor tailored for event-driven sensory signal processing. ElfCore is the first to efficiently integrate: (1) a local online self-supervised learning engine that enables multi-layer temporal learning without labeled inputs; (2) a dynamic structured sparse training engine that supports high-accuracy sparse-to-sparse learning; and (3) an activity-dependent sparse weight update mechanism that selectively updates weights based solely on input activity and network dynamics. Demonstrated on tasks including gesture recognition, speech, and biomedical signal processing, ElfCore outperforms state-of-the-art solutions with up to 16X lower power consumption, 3.8X reduced on-chip memory requirements, and 5.9X greater network capacity efficiency.","url":"https://doi.org/10.48550/arxiv.2512.21153","authors":["Su, Zhe","Indiveri, Giacomo"],"tags":["Hardware Architecture (cs.AR)","Machine Learning (cs.LG)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2512.21153","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2506.13268","name":"Energy-Efficient Digital Design: A Comparative Study of Event-Driven and Clock-Driven Spiking Neurons","source":"datacite","abstract":"This paper presents a comprehensive evaluation of Spiking Neural Network (SNN) neuron models for hardware acceleration by comparing event driven and clock-driven implementations. We begin our investigation in software, rapidly prototyping and testing various SNN models based on different variants of the Leaky Integrate and Fire (LIF) neuron across multiple datasets. This phase enables controlled performance assessment and informs design refinement. Our subsequent hardware phase, implemented on FPGA, validates the simulation findings and offers practical insights into design trade offs. In particular, we examine how variations in input stimuli influence key performance metrics such as latency, power consumption, energy efficiency, and resource utilization. These results yield valuable guidelines for constructing energy efficient, real time neuromorphic systems. Overall, our work bridges software simulation and hardware realization, advancing the development of next generation SNN accelerators.","url":"https://doi.org/10.48550/arxiv.2506.13268","authors":["Marostica, Filippo","Carpegna, Alessio","Savino, Alessandro","Di Carlo, Stefano"],"tags":["Neural and Evolutionary Computing (cs.NE)","Artificial Intelligence (cs.AI)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2506.13268","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2510.11291","name":"Network-Optimised Spiking Neural Network (NOS) Scheduling for 6G O-RAN: Spectral Margin and Delay-Tail Control","source":"datacite","abstract":"This work presents a Network-Optimised Spiking (NOS) delay-aware scheduler for 6G radio access. The scheme couples a bounded two-state kernel to a clique-feasible proportional-fair (PF) grant head: the excitability state acts as a finite-buffer proxy, the recovery state suppresses repeated grants, and neighbour pressure is injected along the interference graph via delayed spikes. A small-signal analysis yields a delay-dependent threshold $k_\\star(Δ)$ and a spectral margin $δ= k_\\star(Δ) - gHρ(W)$ that compress topology, controller gain, and delay into a single design parameter. Under light assumptions on arrivals, we prove geometric ergodicity for $δ&gt;0$ and derive sub-Gaussian backlog and delay tail bounds with exponents proportional to $δ$. A numerical study, aligned with the analysis and a DU compute budget, compares NOS with PF and delayed backpressure (BP) across interference topologies over a $5$--$20$\\,ms delay sweep. With a single gain fixed at the worst spectral radius, NOS sustains higher utilisation and a smaller 99.9th-percentile delay while remaining clique-feasible on integer PRBs.","url":"https://doi.org/10.48550/arxiv.2510.11291","authors":["Bilal, Muhammad","Xu, Xiaolong"],"tags":["Networking and Internet Architecture (cs.NI)","Information Theory (cs.IT)","Machine Learning (cs.LG)","FOS: Computer and information sciences","FOS: Computer and information sciences","C.2.1; C.2.3; C.4; I.2.6; I.6.5; G.3","68M20, 60K25, 93C23, 93D05, 90B18, 68M10, 68T07"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2510.11291","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2502.13385","name":"SNN-Driven Multimodal Human Action Recognition via Sparse Spatial-Temporal Data Fusion","source":"datacite","abstract":"Multimodal human action recognition based on RGB and skeleton data fusion, while effective, is constrained by significant limitations such as high computational complexity, excessive memory consumption, and substantial energy demands, particularly when implemented with Artificial Neural Networks (ANN). These limitations restrict its applicability in resource-constrained scenarios. To address these challenges, we propose a novel Spiking Neural Network (SNN)-driven framework for multimodal human action recognition, utilizing event camera and skeleton data. Our framework is centered on two key innovations: (1) a novel multimodal SNN architecture that employs distinct backbone networks for each modality-an SNN-based Mamba for event camera data and a Spiking Graph Convolutional Network (SGN) for skeleton data-combined with a spiking semantic extraction module to capture deep semantic representations; and (2) a pioneering SNN-based discretized information bottleneck mechanism for modality fusion, which effectively balances the preservation of modality-specific semantics with efficient information compression. To validate our approach, we propose a novel method for constructing a multimodal dataset that integrates event camera and skeleton data, enabling comprehensive evaluation. Extensive experiments demonstrate that our method achieves superior performance in both recognition accuracy and energy efficiency, offering a promising solution for practical applications.","url":"https://doi.org/10.48550/arxiv.2502.13385","authors":["Zheng, Naichuan","Xia, Hailun","Liang, Zeyu","Du, Yuchen"],"tags":["Computer Vision and Pattern Recognition (cs.CV)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2502.13385","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2412.06355","name":"Scalable Dendritic Modeling Advances Expressive and Robust Deep Spiking Neural Networks","source":"datacite","abstract":"Dendritic computation endows biological neurons with rich nonlinear integration and high representational capacity, yet it is largely missing in existing deep spiking neural networks (SNNs). Although detailed multi-compartment models can capture dendritic computations, their high computational cost and limited flexibility make them impractical for deep learning. To combine the advantages of dendritic computation and deep network architectures for a powerful, flexible and efficient computational model, we propose the dendritic spiking neuron (DendSN). DendSN explicitly models dendritic morphology and nonlinear integration in a streamlined design, leading to substantially higher expressivity than point neurons and wide compatibility with modern deep SNN architectures. Leveraging the efficient formulation and high-performance Triton kernels, dendritic SNNs (DendSNNs) can be efficiently trained and easily scaled to deeper networks. Experiments show that DendSNNs consistently outperform conventional SNNs on classification tasks. Furthermore, inspired by dendritic modulation and synaptic clustering, we introduce the dendritic branch gating (DBG) algorithm for task-incremental learning, which effectively reduces inter-task interference. Additional evaluations show that DendSNNs exhibit superior robustness to noise and adversarial attacks, along with improved generalization in few-shot learning scenarios. Our work firstly demonstrates the possibility of training deep SNNs with multiple nonlinear dendritic branches, and comprehensively analyzes the impact of dendrite computation on representation learning across various machine learning settings, thereby offering a fresh perspective on advancing SNN design.","url":"https://doi.org/10.48550/arxiv.2412.06355","authors":["Huang, Yifan","Fang, Wei","Ma, Zhengyu","Li, Guoqi","Tian, Yonghong"],"tags":["Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.48550/arxiv.2412.06355","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2512.19182","name":"Photonic Spiking Graph Neural Network for Energy-Efficient Structured Data Processing","source":"datacite","abstract":"Photonic computing shows great potential for signal processing and artificial intelligence (AI) acceleration due to its ultra-high speed, low energy consumption, and inherent parallelism. Existing photonic computing research has mainly focused on convolutional neural networks (CNNs) and fully connected neural networks (FCNNs), which are well suited for tasks such as image classification and object detection but face limitations in handling graph-structured data. Graph neural networks (GNNs) are specifically designed to model complex relational structures. In this work, we propose a photonic spiking graph neural network (PSGNN) architecture that integrates the structural modeling capability of GNNs, the temporal dynamics of spiking neurons, and the parallel computing advantages of photonic hardware. Through hardware-software co-optimization, a bias-term simulation method tailored for photonic chips is implemented using feature-dimension expansion, enabling effective network training. Experiments on the KarateClub and PubMed datasets achieve training accuracies of 100 percent (92 +/- 2 percent) and test accuracies of 97 percent (90 +/- 1 percent). A silicon photonics 4 x 4 Mach-Zehnder interferometer (MZI) array is further constructed for hardware validation, achieving a test accuracy of 93 percent. The system demonstrates an inference latency of 97 ps, with an energy efficiency of 280 GOPS/W and a computational density of 52 GOPS/mm^2. These results highlight the potential of PSGNN for structured-data processing applications.","url":"https://doi.org/10.48550/arxiv.2512.19182","authors":["Yu, Wanting","Xiang, Shuiying","Guo, Xingxing","Shi, Shangxuan","Zhao, Haowen","Zeng, Xintao","Zhang, Yahui","Jiang, Hongbo","Hao, Yue"],"tags":["Optics (physics.optics)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2512.19182","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2512.18113","name":"Responses to transient perturbation can distinguish intrinsic from latent criticality in spiking neural populations","source":"datacite","abstract":"The critical brain hypothesis posits that neural circuitry operates near criticality to reap the computational benefits of accessing a wide range of timescales. The theory of critical phenomena generally predicts heavy-tailed (power-law) correlations in space and time near criticality, but it has been argued that in the brain such correlations could be inherited from ``latent variables,'' such as external sensory signals that are not directly observed when recording from neural circuitry. Distinguishing whether heavy-tailed correlations in neural activity are intrinsically generated within a neural circuit or are driven by unobserved latent variables is crucial for properly interpreting circuit functions. We argue that measuring neural responses to sudden perturbative inputs, rather than correlations in ongoing activity, can disambiguate these cases. We demonstrate this approach in a model of stochastic spiking neuron populations receiving external latent input that can be tuned to a critical state. We propose a scaling theory for the covariance and response functions of the spiking network, which we validate with simulations. We end by discussing how our approach might generalize to models of neural populations with more realistic biophysical details.","url":"https://doi.org/10.48550/arxiv.2512.18113","authors":["Crosser, Jacob T.","Brinkman, Braden A. W."],"tags":["Neurons and Cognition (q-bio.NC)","Disordered Systems and Neural Networks (cond-mat.dis-nn)","FOS: Biological sciences","FOS: Biological sciences","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2512.18113","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5287/ora-7ezox4yva","name":"Exploration of time-warped cortical spike time patterns","source":"datacite","abstract":"The thesis explores the nature of information representation by patterns of action potentials in the cortex. The thesis combines analysis of sensory-evoked in vivo cortical spiking activity, large scale biophysical cortical network simulations, phenomenological modelling of representation learning through spike-time-dependent plasticity and the development of a spiking neural network simulator. Together, these approaches engendered novel findings and hypotheses regarding the nature of cortical processing. The thesis focuses on patterns of spikes in which each neuron spikes once (`multi-neuron single spike patterns') as a possible fundamental form of cortical information encoding. The thesis characterises the temporal structure of stimulus-evoked multi-neuron single spike patterns in response to single whisker deflections in the barrel cortex of the anaesthetised rat. Spike time patterns are found to be stretched and compressed in time (i.e. time-warped) depending on the excitability of the barrel cortex on a single trial. This partly explains why precise spike time patterns are rarely reported in vivo. It is proposed that downstream neurons may decode such representations in an excitability-dependent manner, thus increasing spike time coding capacity. The characterised form of spike time variability is tested for in a detailed biophysical model of a column of rat somatosensory cortex. It was hoped that the model could be used to understand the phenomena's underlying mechanisms and to make further predictions. A framework was developed for comparing in vivo and in silico spiking activity. Key differences between in vivo and in silico spiking activity were found, however. These differences have been used to guide further model refinement. Hypotheses of how time-warped multi-neuron patterns of single spikes may facilitate the brain's solution to the Feature Binding Problem are presented, as well as attempts to test these hypotheses in a phenomenological spiking neural network. The latter made up the initial work of the DPhil, which aimed to explore the emergence of spike time continua. Towards this a GPU spiking neural network simulator was co-created, and was demonstrated (by collaborators) to be the fastest of its class.","url":"https://doi.org/10.5287/ora-7ezox4yva","authors":["Isbister, James Bryden"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.5287/ora-7ezox4yva","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5287/ora-5zg0xzk6b","name":"Competitive learning in rate coded and spiking neural networks models with applications to vision and audition","source":"datacite","abstract":"Competitive learning is a common and successful approach used to train unsupervised rate-based neural network models. We apply such a technique in this thesis and produce a rate-coded neural network model of pitch processing which provides insights into the training protocols necessary to develop robust pitch representations. However, the extension of reliable unsupervised competitive learning approaches from rate-coded to spiking neural networks has proven challenging, especially when biological plausibility and detail are desired. Transitioning to spiking neural network models is made more difficult by the comparatively high computational cost and complexity of these network models compared to rate-based models. We describe a transition from rate-based to spiking neural network models and address these outstanding issues. First, we focus on increasing simulation efficiency. We develop a state of the art graphical processing unit (GPU) based spiking neural network simulator which adopts optimisations from central processing unit (CPU) and cluster-based simulators. In benchmarks, we show that our novel simulator is capable of simulation speeds up to an order of magnitude greater than contemporary simulators. This greater simulation speed is intended to enable a higher throughput of spiking neural network simulations and thereby accelerate research. In order to ensure that present and future simulators can be efficiently and effectively compared, we also compile a repository of benchmarks which allow validation of simulator performance and simulated neural network dynamics. Having developed efficient simulation techniques, we propose a novel excitatory plasticity rule which, when used to train spiking neural networks in conjunction with an existing inhibitory plasticity rule, produces reliable competitive learning. These rules are both unsupervised, use local only information, and depend upon spike-timing in order to compute synaptic weight updates. This learning rule framework is used to produce a model of V1 simple cell receptive field development and shows qualitatively similar behaviour to traditional sparse coding models. During the development of these models we come across a number of challenges, especially in the interactions of inhibitory and excitatory neurons. We pose solutions to these challenges and thereafter suggest some future research questions and avenues for exploration.","url":"https://doi.org/10.5287/ora-5zg0xzk6b","authors":["Ahmad, Nasir"],"tags":["Computational Neuroscience"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2019","doi":"10.5287/ora-5zg0xzk6b","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.48550/arxiv.2512.17841","name":"NeuRehab: A Reinforcement Learning and Spiking Neural Network-Based Rehab Automation Framework","source":"datacite","abstract":"Recent advancements in robotic rehabilitation therapy have provided modular exercise systems for post-stroke muscle recovery with basic control schemes. But these systems struggle to adapt to patients' complex and ever-changing behaviour, and to operate within mobile settings, such as heat and power. To aid this, we present NeuRehab: an end-to-end framework consisting of a training and inference pipeline with AI-based automation, co-designed with neuromorphic computing-based control systems that balance action performance, power consumption, and observed latency. The framework consists of 2 partitions. One is designated for the rehabilitation device based on ultra-low power spiking networks deployed on dedicated neuromorphic hardware. The other resides on stationary hardware that can accommodate computationally intensive hardware for fine-tuning on a per-patient basis. By maintaining a communication channel between both the modules and splitting the algorithm components, the power and latency requirements of the movable system have been optimised, while retaining the learning performance advantages of compute- and power-hungry hardware on the stationary machine. As part of the framework, we propose (a) the split machine learning processes for efficiency in architectural utilisation, and (b) task-specific temporal optimisations to lower edge-inference control latency. This paper evaluates the proposed methods on a reference stepper motor-based shoulder exercise. Overall, these methods offer comparable performance uplifts over the State-of-the-art for neuromorphic deployment, while achieving over 60% savings in both power and latency during inference compared to standard implementations.","url":"https://doi.org/10.48550/arxiv.2512.17841","authors":["Kambhampati, Phani Pavan","Gautam, Chainesh","Palaniswamy, Jagan","Rao, Madhav"],"tags":["Computational Engineering, Finance, and Science (cs.CE)","Systems and Control (eess.SY)","FOS: Computer and information sciences","FOS: Computer and information sciences","FOS: Electrical engineering, electronic engineering, information engineering","FOS: Electrical engineering, electronic engineering, information engineering"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2512.17841","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.34734/fzj-2025-05766","name":"A scaling-friendly memristor-based leaky integrate-and-fire circuit in a TSMC 28nm process technology","source":"datacite","abstract":"Spiking neural networks mimic the way the human brain processes data and excel in efficiency. With the advent of the memristor, foundations are laid for scalable and low-power integrated electronic implementations. Key is the small form factor of the memristor and its ability to passively retain a multilevel state.To investigate the feasibility of memristor-based spiking neural networks, a first chip is developed containing all necessary circuits to read and write memristors. It will be connected via chip-to-chip bonding wires to a 3 by 3 memristor array. In this abstract the focus is on the implemented leaky integrate-and-fire circuit (LIF).While the memristors act as the synapses of the neural network, the neurons are modeled as current-based RC LIF circuits. Previous implementations minimized the current to reduce the area footprint as much as possible which is dominated by the capacitor size[1][2]. This is prone to process variations, especially in smaller technology nodes. Thus, precise analog calibrations are needed for every single neuron. This complicates scaling spiking neuronal networks. A novel approach reduces the width of incoming spikes in the LIF circuit to a fraction of the original by an additional duty-cycle element which is controlled by ɸPulse. This is generated globally by a reference clock with an adjustable duty cycle and then distributed to all LIF elements minimizing the wiring and biasing overhead. Additionally, the operation time frame of the SNN can be tuned through this. The duty cycle approach effectively transforms the system to the time-discrete domain, but with the very high switching speeds, enabled by a 28 nm process technology, compared to the intended operating speed of the neural network it can be regarded as pseudo time-continuous.A first tapeout in a 28nm process technology is scheduled for September 2025 and post-layout simulations will be shown.","url":"https://doi.org/10.34734/fzj-2025-05766","authors":["Krystofiak, Lukas"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.34734/fzj-2025-05766","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5287/ora-7epyk50m1","name":"Computational neuroscience of speech recognition","source":"datacite","abstract":"Physical variability of speech combined with its perceptual constancy make speech recognition a challenging task. The human auditory brain, however, is able to perform speech recognition effortlessly. This thesis aims to understand the precise computational mechanisms that allow the auditory brain to do so. In particular, we look for the minimal subset of sub-cortical auditory brain areas that allow the primary auditory cortex to learn 'good representations' of speech-like auditory objects through spike-timing dependent plasticity (STDP) learning mechanisms as described by Bi &amp; Poo (1998). A 'good representation' is defined as that which is informative of the stimulus class regardless of the variability in the raw input, while being less redundant and more compressed than the representations within the auditory nerve, which provides the firing inputs to the rest of the auditory brain hierarchy (Barlow 1961). Neurophysiological studies have provided insights into the architecture and response properties of different areas within the auditory brain hierarchy. We use these insights to guide the development of an unsupervised spiking neural network grounded in the neurophysiology of the auditory brain and equipped with spike-time dependent plasticity (STDP) learning (Bi &amp; Poo 1998). The model was exposed to simple controlled speech- like stimuli (artificially synthesised phonemes and naturally spoken words) to investigate how stable representations that are invariant to the within- and between-speaker differences can emerge in the output area of the model. The output of the model is roughly equivalent to the primary auditory cortex. The aim of the first part of the thesis was to investigate what was the minimal taxonomy necessary for such representations to emerge through the interactions of spiking dynamics of the network neurons, their ability to learn through STDP learning and the statistics of the auditory input stimuli. It was found that sub-cortical pre-processing within the ventral cochlear nucleus and inferior colliculus was necessary to remove jitter inherent to the auditory nerve spike rasters, which would disrupt STDP learning in the primary auditory cortex otherwise. The second half of the thesis investigated the nature of neural encoding used within the primary auditory cortex stage of the model to represent the learnt auditory object categories. It was found that single cell binary encoding (DeWeese &amp; Zador 2003) was sufficient to represent two synthesised vowel classes, however more complex population encoding using precisely timed spikes within polychronous chains (Izhikevich 2006) represented more complex naturally spoken words in speaker-invariant manner.","url":"https://doi.org/10.5287/ora-7epyk50m1","authors":["Higgins, Irina"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2015","doi":"10.5287/ora-7epyk50m1","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.5281/zenodo.18007720","name":"Tabletop Testbed for Low-Power Metamaterial Field Manipulation: A YIG Based Prototype with Retrocausal Control","source":"datacite","abstract":"This paper presents a fully buildable tabletop-scale testbed for investigating low-power spacetime eld manipulation using a ceramic-YIG (yttrium iron garnet) metamaterial hull integrated with neuromorphic control architecture. The design combines hexagonal YIG tiling optimized via golden-ratio spacing for spin-wave resonance uniformity with a Raspberry Pi-based spiking neural network implementing Sutherland action-reaction dynamics through forward-backward temporal propagation. No exotic matter or negative energy is required; measurable e ects arise from coherent spin-wave interference in YIG under controlled microwave drive at 2.4 GHz (5–10 W continuous). Predicted outcomes include micro-displacement of 0.05–0.1 mm and associated phase anomalies, testable via laser interferometry at 0.01 mm resolution. The prototype is buildable with o -the-shelf components (total cost < £500, assembly timeline 6 months) and provides a falsiable experimental platform for probing eld-control mechanisms relevant to unidenti ed aerial phenomena (UAP) observations. Simulation code (Python, EveNN neuromorphic framework) is provided for pre-build validation and parameter optimization. Keywords: metamaterial propulsion, YIG spin-wave coupling, low-power eld manipulation, neuromorphic control, Sutherland retrocausality, tabletop testbed, falsi able experiment","url":"https://doi.org/10.5281/zenodo.18007720","authors":["Barker, Christian"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.18007720","addedAt":"2026-09-01T01:48:22.715Z","updatedAt":"2026-09-01T01:48:22.715Z"},{"id":"doi:10.21203/rs.3.rs-2558516/v1","name":"Reconfigurable, non-volatile neuromorphic photovoltaics","source":"crossref","abstract":"Abstract Reconfigurable image sensors for the recognition and understanding of real-world objects are now becoming an essential part of machine vision technology. The neural network image sensor — which mimics neurobiological functions of the human retina —has recently been demonstrated to simultaneously sense and process optical images. However, highly tunable responsivity concurrently with non-volatile storage of image data in the neural network would allow a transformative leap in compactness and function of these artificial neural networks (ANNs) that truly function like a human retina. Here, we demonstrate a reconfigurable and non-volatile neuromorphic device based on two-dimensional (2D) semiconducting metal sulfides (MoS 2 and WS 2 ) that is concurrently a photovoltaic detector. The device is based on a metal/semiconductor/metal (M/S/M) two-terminal structure with pulse-tunable sulfur vacancies at the M/S junctions. By modulating sulfur vacancy concentrations, the polarities of short-circuit photocurrent —can be changed with multiple stable magnitudes. Device characterizations and modeling reveal that the bias-induced motion of sulfur vacancies leads to highly reconfigurable responsivities by dynamically modulating the Schottky barriers. A convolutional neuromorphic network (CNN) is finally designed for image process and object detection using the same device. The results demonstrated the two-terminal reconfigurable and non-volatile photodetectors can be used for future optoelectronics devices based on coupled Ionic-optical-electronic effects for Neuromorphic computing.","url":"https://doi.org/10.21203/rs.3.rs-2558516/v1","authors":["Tangxin Li","Jinshui Miao","Xiao Fu","Bo Song","Bin Cai","Xiaohao Zhou","Peng Zhou","Xinran Wang","Deep Jariwala","Weida Hu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-02-21T17:14:34Z","doi":"10.21203/rs.3.rs-2558516/v1","addedAt":"2026-09-01T01:48:22.905Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.3389/fnins.2016.00115","name":"A Review of Current Neuromorphic Approaches for Vision, Auditory, and Olfactory Sensors","source":"crossref","abstract":"","url":"https://doi.org/10.3389/fnins.2016.00115","authors":["Anup Vanarse","Adam Osseiran","Alexander Rassau"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-03-29T03:14:04Z","doi":"10.3389/fnins.2016.00115","addedAt":"2026-09-01T01:48:22.905Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1063/1.5037835","name":"Perspective: A review on memristive hardware for neuromorphic computation","source":"crossref","abstract":"Neuromorphic computation is one of the axes of parallel distributed processing, and memristor-based synaptic weight is considered as a key component of this type of computation. However, the material properties of memristors, including material related physics, are not yet matured. In parallel with memristors, CMOS based Graphics Processing Unit, Field Programmable Gate Array, and Application Specific Integrated Circuit are also being developed as dedicated artificial intelligence (AI) chips for fast computation. Therefore, it is necessary to analyze the competitiveness of the memristor-based neuromorphic device in order to position the memristor in the appropriate position of the future AI ecosystem. In this article, the status of memristor-based neuromorphic computation was analyzed on the basis of papers and patents to identify the competitiveness of the memristor properties by reviewing industrial trends and academic pursuits. In addition, material issues and challenges are discussed for implementing the memristor-based neural processor.","url":"https://doi.org/10.1063/1.5037835","authors":["Changhyuck Sung","Hyunsang Hwang","In Kyeong Yoo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-10-05T10:52:49Z","doi":"10.1063/1.5037835","addedAt":"2026-09-01T01:48:22.905Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1103/physreve.96.062313","name":"Noise-driven neuromorphic tuned amplifier","source":"crossref","abstract":"","url":"https://doi.org/10.1103/physreve.96.062313","authors":["Duccio Fanelli","Francesco Ginelli","Roberto Livi","Niccoló Zagli","Clement Zankoc"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-12-26T15:05:34Z","doi":"10.1103/physreve.96.062313","addedAt":"2026-09-01T01:48:22.905Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1109/mwscas.2013.6674720","name":"Review of nanoscale memristor devices as synapses in neuromorphic systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mwscas.2013.6674720","authors":["Nathan Serafino","Mona Zaghloul"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-12-04T21:14:10Z","doi":"10.1109/mwscas.2013.6674720","addedAt":"2026-09-01T01:48:22.905Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.21203/rs.3.rs-4389036/v1","name":"A physical emulation of somatosensory cortex as a\nNeuromorphic Twin for neural prostheses","source":"crossref","abstract":"Abstract Loss of tactile feedback in patients with paralysis or limb loss prevents the integration of sensory-motor signals, limiting dexterous motor control. Recent advances in the neurostimulation of the human somatosensory cortex offer the possibility of restoring touch in these patients. Brain-computer interfaces and bidirectional prostheses with implantable electrodes can restore feedback, improving control, awareness, and quality of life. However, current electrical stimulation methods lack the fidelity to consistently and reliably reproduce natural sensations, and the impact of this stimulation on the somatosensory cortex remains unclear. Here we propose to use a mixed-signal neuromorphic processing system to construct a “neuromorphic twin” of the somatosensory cortex, following a bottom-up approach for emulating and reproducing its intricate dynamics. We use the analog properties of electronic neuron and synapse circuits to faithfully replicate neural and synaptic response properties. To reproduce effects at the network level, we configure the neuromorphic processor to implement the recurrent connectivity patterns of the somatosensory cortex among different populations of excitatory and inhibitory silicon neurons. Our findings demonstrate the twin’s ability to reproduce the spatiotemporal firing patterns of the native neuronal population receiving afferent fiber inputs, resulting in a highly bio-realistic model that can be used to investigate the effect of different stimulation patterns. This physical emulation of the cortical circuits represents therefore an additional tool to understand and predict the somatosensory cortex behavior under neurostimulation. Using this system, neurostimulation patterns can be optimized to produce more natural sensations and ultimately improve the quality of restored feedback, leading to a better quality of life for affected patients.","url":"https://doi.org/10.21203/rs.3.rs-4389036/v1","authors":["Hector Ramirez","Elisa Donati","Wolfger von der Behrens","Giacomo Indiveri","Giacomo Valle"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-14T00:51:51Z","doi":"10.21203/rs.3.rs-4389036/v1","addedAt":"2026-09-01T01:48:22.905Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1146/annurev.ne.18.030195.001351","name":"Neuromorphic Analogue VLSI","source":"crossref","abstract":"","url":"https://doi.org/10.1146/annurev.ne.18.030195.001351","authors":["R Douglas","M Mahowald","C Mead"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-07-02T07:43:55Z","doi":"10.1146/annurev.ne.18.030195.001351","addedAt":"2026-09-01T01:48:22.905Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1186/s43074-026-00278-8","name":"Toward brain-inspired intelligence: a review of photonic neuromorphic computing systems","source":"crossref","abstract":"Abstract Inspired by the key elements and principles in the brain, photonic neuromorphic computing shows great potential for building next-generation intelligent processing systems with high parallelism, low latency, low power consumption, and self-learning capabilities. While summarizing significant advances in this field, this review offers insights into how photonic neuromorphic computing systems support next-generation intelligent information processing. Specifically, we discuss emerging materials and devices, which support more compact integration of efficient physical architectures. Architectures such as photonic spiking neural networks and reservoir computing, together with associated learning paradigms, show a trend of collaborative development. Then we present promising applications, where neuromorphic computing systems provide broadband and multi-domain perception and processing. Finally, we discuss key challenges and future directions. This review aims to offer a clear and comprehensive overview for researchers across a broad community. We hope to present these insights in a “neuromorphic” manner, to reveal why learning from the brain has become increasingly important, especially for overcoming the efficiency bottleneck in traditional von Neumann architecture and data-intensive artificial neural networks.","url":"https://doi.org/10.1186/s43074-026-00278-8","authors":["Dun Lan","Bowen Ma","Yuxiang Ji","Yichen Zeng","Zhihong Zou","Zongsheng Li","Yiyang Xu","Mengmeng Chai","Weiwen Zou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-28T03:30:07Z","doi":"10.1186/s43074-026-00278-8","addedAt":"2026-09-01T01:48:22.905Z","updatedAt":"2026-09-01T01:48:22.905Z"},{"id":"doi:10.1093/nsr/nwad301","name":"How can neuromorphic hardware attain brain-like functional capabilities?","source":"crossref","abstract":"The author provides 4 design principles of how to make cortical microcircuits into neuromorphic hardwares, shedding light for the next generation neuromorphic hardware design.","url":"https://doi.org/10.1093/nsr/nwad301","authors":["Wolfgang Maass"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-30T16:51:35Z","doi":"10.1093/nsr/nwad301","addedAt":"2026-09-01T01:48:22.906Z","updatedAt":"2026-09-01T01:48:22.906Z"},{"id":"doi:10.1039/d5tc03660g/v2/decision1","name":"Decision letter for \"Multi-objective Bayesian Optimization with Human-in-the-Loop for Flexible Neuromorphic Electronics Fabrication\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5tc03660g/v2/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-07T21:09:36Z","doi":"10.1039/d5tc03660g/v2/decision1","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1145/3746467.3801495","name":"NeuroSnitch: Exploiting Inter-Spike Interval Statistics for Timing Side-Channel Attacks on Noisy Neuromorphic Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3746467.3801495","authors":["Mahreen Khan","Maria Mushtaq","Ludovic Apvrille"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-14T11:06:32Z","doi":"10.1145/3746467.3801495","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1117/12.3100890","name":"Exploring bioplausible neuromorphic hardware with silicon microresonators","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3100890","authors":["Stefano Biasi","Lorenzo Pavesi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-27T18:24:57Z","doi":"10.1117/12.3100890","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1007/s43207-026-00631-4","name":"Resistive switching and synaptic functionality in vanadium-doped gallium oxide-based memristors for neuromorphic and multi-bit reservoir computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s43207-026-00631-4","authors":["Ashish Kumar","Shahid Iqbal","Junmo Kim","Hyumin Dang","Hyungtak Seo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-18T08:01:15Z","doi":"10.1007/s43207-026-00631-4","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.3390/photonics13020139","name":"Robust Diffractive Optical Neuromorphic System Created via Sharpness-Aware and Immune Training","source":"crossref","abstract":"Diffractive deep neural networks (D2NNs) have garnered significant attention for their ultra-low energy consumption and parallel optical computing capabilities. However, their practical deployment is hindered by the “model–reality” gap caused by fabrication inaccuracy, device fluctuation, assembly misalignment, environmental perturbation, etc. Here, we propose a combined framework that integrates sharpness-aware minimization (SAM) and aberration-immune learning (AIL), enabling joint immunity against both stochastic noise and systematic deviations from theoretical model training. Specifically, we show that under multiple perturbations such as salt-and-pepper noise, Gaussian noise, and wavefront aberration, the SAM–AIL framework achieves significant classification accuracy improvements on MNIST and Fashion-MNIST compared to conventional offline training approaches. D2NN trained with the SAM–AIL scheme exhibited significant accuracy enhancement under moderate salt-and-pepper noise, Gaussian noise, X-axis, and Y-axis tilting perturbations, respectively. Our work provides an efficient solution for offline training and deploying high-robustness D2NNs on realistic physical systems that are resilient to a variety of imperfections, significantly enhancing model transferability and reliability for optical computing tasks.","url":"https://doi.org/10.3390/photonics13020139","authors":["Fansanqiu Li","Kaicheng Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-02T09:00:33Z","doi":"10.3390/photonics13020139","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1088/1361-6579/ae56cc","name":"NeuroSleep: neuromorphic event-driven single-channel EEG sleep staging for edge-efficient sensing","source":"crossref","abstract":"Abstract Objective . Reliable, continuous neural sensing on wearable edge platforms is fundamental to long-term health monitoring; however, for electroencephalography (EEG)-based sleep monitoring, dense high-frequency processing is often computationally prohibitive under tight energy budgets. Approach . To address this bottleneck, this paper proposes NeuroSleep, an integrated event-driven sensing and inference system for energy-efficient sleep staging. NeuroSleep first converts raw EEG into complementary multi-scale bipolar event streams using Residual Adaptive Multi-Scale Delta Modulation, enabling an explicit fidelity–sparsity trade-off at the sensing front end. Furthermore, NeuroSleep adopts a hierarchical inference architecture that comprises an Event-based Adaptive Multi-scale Response module for local feature extraction, a Local Temporal-Attention Module for context aggregation, and an epoch-leaky integrate-and-fire module to capture long-term state persistence. Main results . Experimental results using subject-independent 5-fold cross-validation on the sleep-EDF expanded sleep-cassette subset (78 subjects, 153 overnight recordings) with single-channel EEG demonstrate that NeuroSleep achieves a mean accuracy of 74.2% with only 0.932 M parameters while reducing sparsity-adjusted effective operations by approximately 53.6% relative to dense processing. Compared to the representative dense Transformer baseline, NeuroSleep improves accuracy by 7.5% with a 45.8% reduction in computational load. Significance . By coupling neuromorphic event encoding with state-aware context modeling, NeuroSleep offers a deployment-oriented framework for single-channel sleep staging that reduces redundant high-rate processing and improves energy scalability for wearable and edge platforms.","url":"https://doi.org/10.1088/1361-6579/ae56cc","authors":["Boyu Li","Xingchun Zhu","Yonghui Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-24T22:56:26Z","doi":"10.1088/1361-6579/ae56cc","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1002/9783527844869.ch11","name":"Hafnia‐based Materials for Neuromorphic Devices","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9783527844869.ch11","authors":["Hai Zhong","Kui‐juan Jin","Chen Ge"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-29T10:49:46Z","doi":"10.1002/9783527844869.ch11","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/icecet65726.2026.11632825","name":"Cross-Platform Federated Learning: Unifying Neuromorphic and Traditional Hardware for Efficient Edge AI","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icecet65726.2026.11632825","authors":["Muhammad Waleed Khan","Alois Ferscha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-12T19:20:01Z","doi":"10.1109/icecet65726.2026.11632825","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/etai68332.2026.11485064","name":"MemNeuron: Locally Active Memristor-Based Compute-in-Memory Architecture with Spike-Timing-Dependent Plasticity for Neuromorphic Intelligence","source":"crossref","abstract":"","url":"https://doi.org/10.1109/etai68332.2026.11485064","authors":["Guoshu Cheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-01T19:51:20Z","doi":"10.1109/etai68332.2026.11485064","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1088/1361-6463/ae6e4e","name":"Wavelength-decoupled photonic memristor for neuromorphic systems","source":"crossref","abstract":"Abstract Photonic memristors based on phase-change materials can provide non-volatile optical weights for neuromorphic hardware, but practical devices often suffer from read-disturbance, inefficient optical heating, and iterative empirical optimization. Here, we present a physics-based design workflow for planar thin-film photonic memristors that uses interference to separate optical read and write channels by wavelength. The model combines transfer-matrix optics, a compact thermal description, and state-update rules to link wavelength-dependent absorption in the active film to the evolution of memristive states, and it is generalized to absorbing phase-change media. As a representative case study, we use an antimony (Sb) cavity to demonstrate the workflow, first by selecting a probe wavelength which maximizes optical contrast and a programming wavelength that maximizes heating efficiency, enabling low-disturb readout and energy-efficient switching within a single device geometry. Spacer-controlled field localization tunes the hysteresis and supports gradual, analog-like weight updates under pulse trains. Robustness tests show that thermal relaxation and heat retention set the main programming margins, while readout contrast is comparatively stable. The approach provides design rules for interference-engineered photonic memory elements.","url":"https://doi.org/10.1088/1361-6463/ae6e4e","authors":["Kameyab Raza Abidi","Gour Mohan Das"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-15T22:49:04Z","doi":"10.1088/1361-6463/ae6e4e","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1002/smll.202510540","name":"Beyond Sight: Neuromorphic Synapses Triggered by Invisible Light","source":"crossref","abstract":"ABSTRACT Neuromorphic devices that emulate biological synaptic behavior are emerging as key enablers for in‐sensor intelligence. While visible‐light‐responsive systems have dominated the field, recent efforts have expanded toward invisible spectral regions: ultraviolet (UV), infrared (IR), and X‐ray, where unique photon‐matter interactions offer new avenues for optical plasticity. These invisible‐wavelength stimuli enable synaptic functions such as short‐term and long‐term potentiation through mechanisms like persistent photoconductivity, defect ionization, and interfacial charge trapping, often without the need for external programming circuitry. Although these devices are increasingly important for intelligent imaging, radiation‐tolerant electronics, and secure communication, related studies are still fragmented across different fields and lack an organized overview. In this review, we systematically categorize and analyze optoelectronic synapses that operate under UV, IR, and X‐ray illumination. We highlight representative material systems including Ga 2 O 3 , perovskites, wide‐bandgap oxides, and hybrid nanocomposites, and discuss their device architectures, synaptic behaviors, and operational metrics. Special emphasis is placed on the underlying physical mechanisms, spectral selectivity, and integration prospects for artificial retinas, neuromorphic vision systems, and multimodal sensing arrays. We also provide outlooks for scalable, multispectral, and energy‐efficient neuromorphic platforms beyond the visible.","url":"https://doi.org/10.1002/smll.202510540","authors":["Jisoo Park","Kyounghoon Kim","Eun Kwang Lee","Young‐Joon Kim","Hocheon Yoo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-08T11:08:21Z","doi":"10.1002/smll.202510540","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.52843/cassyni.l16vq7","name":"Neuromorphic Opto-Electronics for Next-Generation Compute: Opportunities &amp; Challenges","source":"crossref","abstract":"Every computational task, from basic arithmetic to the training of sophisticated language models, relies on translating high-level software instructions into sequences of charge manipulations in silicon. This translation becomes increasingly inefficient when applied to modern AI workloads, where the mapping of each neuron, connection, and synapse into transistor operations is fundamentally bottlenecked. In this talk, I will cover recent demonstrations of active and brain-inspired opto-electronic devices which leverage the bandwidth and speed of photonics for parallel information processing and storage. I will focus on device-level implementations and extend the discussion to larger architectures and small-scale accelerators.","url":"https://doi.org/10.52843/cassyni.l16vq7","authors":["Nikolaos Farmakidis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-12T14:23:14Z","doi":"10.52843/cassyni.l16vq7","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.36227/techrxiv.177040597.75784815/v1","name":"A Survey on Neuromorphic Navigation: Implementation Resources, Challenges and Perspectives","source":"crossref","abstract":"Although traditional navigation technologies have seen continued progress, they remain constrained by persistent issues such as high power consumption, significant latency, and limited dynamic adaptability, especially in challenging environments like urban canyons and underground spaces. Neuromorphic technologies, leveraging eventdriven sensing, spike-based computation, and brain-inspired computein-memory, offer a promising new avenue to overcome these limitations. However, as an emerging field, neuromorphic navigation currently lacks dedicated survey efforts to systematically map the ecosystem and resources that support its development. Motivated by this, this survey provides a comprehensive overview of implementation resources across three key dimensions: data, hardware, and software. Building on this foundation, we identify main challenges, including the absence of evaluation benchmarks, fragmented ecosystem resources, the lack of a full-stack theoretical framework, and emerging concerns regarding security, trust, and data privacy. We also propose perspectives aimed at supporting community-driven growth and ecosystem maturation. A curated list of resources is available at: https://github.com/BINUCOE/Awesome-Neuromorphic-Navigation-Resources.","url":"https://doi.org/10.36227/techrxiv.177040597.75784815/v1","authors":["Youdong Zhang","Xu He","Xiaolin Meng","Xiangdong AN","Lingfei Mo","Wenxuan Yin","Fangwen Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-06T19:26:23Z","doi":"10.36227/techrxiv.177040597.75784815/v1","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/icecet65726.2026.11632551","name":"Quantifying the Impact of Spike-Level Explainable AI on Human Trust and Performance in Neuromorphic Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icecet65726.2026.11632551","authors":["Sylvester Kaczmarek"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-12T19:09:22Z","doi":"10.1109/icecet65726.2026.11632551","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/itcindia70344.2026.11646549","name":"A Hybrid Data-Driven Framework for Post-Silicon Validation of Neuromorphic Integrated Circuits","source":"crossref","abstract":"","url":"https://doi.org/10.1109/itcindia70344.2026.11646549","authors":["Kalyana Sundaram Chandran","Senthilkumar Dhamodharan","Sindhu Mathy S"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-18T19:13:44Z","doi":"10.1109/itcindia70344.2026.11646549","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1088/2631-8695/ae4313","name":"A neuromorphic hybrid spiking-CNN model for emotion recognition in low-resource Kannada speech","source":"crossref","abstract":"Abstract Accurately recognizing human emotions from speech is becoming increasingly important for advancing intelligent and adaptive technologies. Yet, many existing Speech Emotion Recognition (SER) models continue to struggle with suboptimal accuracy, limiting their adoption in practical settings. A key challenge lies in the fact that emotional cues in speech are often subtle, irregular, and represented as weak temporal signals that are easily masked within conventional audio features. In this research, we present a dual-path SER architecture tailored for Kannada speech, combining a Convolutional Neural Network (CNN) to capture spectral–spatial representations with a Spiking Neural Network (SNN) enhanced by a Perceptual Neuron Encoding Layer (PNEL) to model fine-grained temporal pulse patterns. The system is trained and evaluated on the Kannada Emotional Speech Dataset (KESD), comprising acted samples of six emotions: happiness, anger, sadness, fear, surprise, and neutral. PNEL transforms raw audio into spike sequences for a Leaky-Integrate-and-Fire SNN, which complements the CNN branch. Experimental analysis across varied segment lengths, hop sizes, and learning rates shows that the CNN+SNN fusion reaches an accuracy of 65.3% on KESD—surpassing the best baseline (64.7%)—while maintaining a feasible compute budget (∼10.5 h training and ∼10.3 GB memory usage). When subjected to narrow-band noise, performance decreases to 57.7%, indicating further scope for robustness improvements. These results establish a foundation for scalable and noise-resilient Kannada SER, with potential extensions to real-time and cross-lingual emotion recognition.","url":"https://doi.org/10.1088/2631-8695/ae4313","authors":["Audre Arlene Anthony","Chandrashekar M Patil"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-06T22:52:31Z","doi":"10.1088/2631-8695/ae4313","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1002/cnma.202500564","name":"Toward Neuromorphic Diagnostics: Memristors in Noncommunicable Disease Detection and Sensory Emulation","source":"crossref","abstract":"Emerging materials‐based devices are revolutionizing healthcare by advancing diagnostics, monitoring, and therapeutic strategies. Among them, memristor devices capable of storing and processing information are attracting and receiving significant attention for their biomedical potential. Their tunable resistance enables sensitive, low‐power detection of major noncommunicable diseases such as diabetes and cancer. Devices fabricated with AlO x , SiO x , and GeO x have demonstrated effective glucose monitoring and biomarker detection, including sarcosine for prostate cancer and LOXL2 for breast cancer, offering pathways toward cost‐effective and early diagnosis. Beyond disease detection, memristor exhibit nociceptive properties such as threshold sensing, synaptic plasticity, and adaptive learning, enabling multifunctional applications in neurological and sensory systems. Artificial nociceptors emulate pain perception for prosthetics and robotics, photoreceptors integrate light sensing with memory for artificial vision, and memristors neuromodulatory platforms provide energy‐efficient seizure control and adaptive deep brain stimulation for Parkinson's disease. Collectively, these developments position memristors as versatile, compact, and biomimetic devices with the potential to unify diagnostics, therapy, and sensory replication in next‐generation biomedical technologies.","url":"https://doi.org/10.1002/cnma.202500564","authors":["Debashis Panda","Arpan Acharya","Subhrakali Swain","Cheng‐Yao Lo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-14T16:09:02Z","doi":"10.1002/cnma.202500564","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/iscas66217.2026.11562133","name":"Hardware-Aware Attractor Dynamics in Neuromorphic Systems: Compensating for Device Mismatch through Network Design","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas66217.2026.11562133","authors":["Leonardo Martinelli","Chiara De Luca","Giacomo Indiveri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-18T20:06:41Z","doi":"10.1109/iscas66217.2026.11562133","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/icdcs68853.2026.11511110","name":"FPGA-Based Implementation of a Full LIF Spiking Neural Network for Neuromorphic Computation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icdcs68853.2026.11511110","authors":["Surekha Musali","Amar Babu Yandrapati","K Babul"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-12T19:46:54Z","doi":"10.1109/icdcs68853.2026.11511110","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1002/lpor.202502765","name":"VO\n                    <sub>2</sub>\n                    Nanoparticle‐Densely Packed Microwires for Flexible and Energy‐Efficient Photonic Synapses in Neuromorphic Computing","source":"crossref","abstract":"ABSTRACT The growing demand for brain‐inspired computing in wearable electronics necessitates systems with high mechanical stability, biocompatibility, and low‐power processing. However, most existing neuromorphic technologies suffer from limited flexibility, reliance on ultraviolet light, and high energy consumption. Here, we report a flexible photonic synapse based on densely packed VO 2 microwires. The device achieves ultra‐low energy consumption (5.76 pJ per pulse) and robust performance in MNIST digit recognition with 92.5% accuracy. Even after 2000 bending cycles, it maintains 92.4% accuracy, demonstrating exceptional durability. In addition, the device retains synaptic memory responses under visible and near‐infrared stimulation, enabling RGB‐fusion reservoir computing.","url":"https://doi.org/10.1002/lpor.202502765","authors":["Yang Wang","Guang Zu","Xin Chen","Shun‐Xin Li","Bo Zou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-08T12:16:09Z","doi":"10.1002/lpor.202502765","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1360/ssc-2026-0108","name":"Recent progress in infrared quantum dots for photodetectors and neuromorphic applications","source":"crossref","abstract":"","url":"https://doi.org/10.1360/ssc-2026-0108","authors":["Haoyuan Li","Kuilin Li","Qi Nie","Xiao Luo","Qi Zhang","Fucai Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-17T01:59:07Z","doi":"10.1360/ssc-2026-0108","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/tvlsi.2026.3695182","name":"Neuromorphic Hyperdimensional Computing for Efficiently Processing Event-Based Data","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tvlsi.2026.3695182","authors":["Tianyang Yu","Bi Wu","Ke Chen","Chenggang Yan","Gong Zhang","Weiqiang Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-11T20:04:27Z","doi":"10.1109/tvlsi.2026.3695182","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1007/s11814-025-00596-w","name":"Artificial Synaptic Devices Based on P-type and N-type Organic Materials for Advanced Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11814-025-00596-w","authors":["Beomjun Kim","Geun Yeol Bae","Eunho Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-13T02:17:47Z","doi":"10.1007/s11814-025-00596-w","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/icietsd68684.2026.11584711","name":"Spiking Neural Networks for Neuromorphic Brain Age Modeling Using Structural MRI","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icietsd68684.2026.11584711","authors":["Jangam Subbarayudu","G. Michael","V. Sheeja Kumari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-07T19:42:05Z","doi":"10.1109/icietsd68684.2026.11584711","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1088/2752-5724/ae18e9","name":"Advances in flexible perovskite memristors for neuromorphic electronics","source":"crossref","abstract":"Abstract The rapid growth toward digitization and artificial intelligence for high-performance storage technologies has spurred the development of brain-inspired neuromorphic electronics. In the post-Moore era, the conventional von Neumann computing architecture, characterized by physically separated processing and memory units, faces significant challenges including excessive power consumption and limited data processing capabilities. As a novel nano electronic device paradigm, memristor has emerged with integrated data storage and computing technology, which is promising for breaking through the von Neumann bottleneck. Perovskite semiconductors possess structural tunability, exceptional electronic and optical properties. When combined with mechanically robust substrates, perovskite-based memristors pave the way for the development of flexible and lightweight neuromorphic systems, suitable for wearable electronics and the internet of things. In this review, we provide a comprehensive overview of recent progress in flexible perovskite memristor technologies, with special focus on the optimization engineering for improving the resistive switching characteristics of memory devices. We then review the role of perovskite-based flexible memories in neuromorphic applications from artificial synapses to image recognition. We outline the importance of clarifying the resistance-switching mechanism in perovskite memristors. Finally, we highlight the challenges that researchers face upon fabricating operationally stable perovskite-based flexible memristors and what is still missing to unlock their full potential in next-generation neuromorphic electronics.","url":"https://doi.org/10.1088/2752-5724/ae18e9","authors":["Shuanglong Wang","Aqiang Liu","Hao Wu","Jiangnan Xia","Yongge Yang","Hong Lian","Huān Bì"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-29T22:48:40Z","doi":"10.1088/2752-5724/ae18e9","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/iolts69666.2026.11633693","name":"Trustworthy Neuromorphic and Quantum Machine Learning: Challenges and Emerging Directions","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iolts69666.2026.11633693","authors":["Alberto Marchisio","Muhammad Shafique"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-04T19:13:24Z","doi":"10.1109/iolts69666.2026.11633693","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/iscas66217.2026.11562346","name":"Live Demonstration: A Personalized sEMG Gesture Recognition System Based on On-Chip Learning Neuromorphic Processor","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas66217.2026.11562346","authors":["Xijie Li","Jilin Zhang","Hong Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-18T20:06:41Z","doi":"10.1109/iscas66217.2026.11562346","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1145/3822454.3822460","name":"TestuNose: A Spike-Time-Based Olfactory System That Sniffs","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3822454.3822460","authors":["Timothy Horiuchi","Gerald Lu","Sai Ryan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-16T05:57:39Z","doi":"10.1145/3822454.3822460","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1109/iatmsi68868.2026.11465241","name":"Bio-Inspired Variance Control: Decoupling Signaling Mode from Power Constraints in Neuromorphic Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iatmsi68868.2026.11465241","authors":["Rakesh Sengupta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-07T19:55:00Z","doi":"10.1109/iatmsi68868.2026.11465241","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.2139/ssrn.7090704","name":"Near-Infrared Circular-Polarization-Sensitive Chiral Au Metasurface/MoS2 Neuromorphic Device for Polarization Encryption","source":"crossref","abstract":"Near-infrared circularly polarized light, with strong penetration capability, low background interference, and helicity freedom, holds great promise for polarization imaging, information encryption, near-infrared communication, and neuromorphic perception. Herein, we construct a 980 nm near-infrared circular-polarization-sensitive neuromorphic device based on a C3-symmetric chiral Au metasurface/monolayer MoS2 heterojunction. The device exhibits pronounced field-effect modulation, delivering a heterojunction mobility of 1.264 cm2 V–1 s–1, a photoresponsivity of approximately 825.9 A W–1. and a circular polarization response ratio of 1.534. Electromagnetic simulations reveal helicity-dependent field localization in the chiral resonator, explaining the circular-polarization-sensitive photoresponse. Moreover, the device emulates typical optoelectronic synaptic functions, including excitatory postsynaptic current, paired-pulse facilitation, and the transition from short-term plasticity to long-term plasticity. Benefiting from its near-infrared circular polarization discrimination capability, a simple information encryption and decryption system is demonstrated, highlighting its potential for polarization imaging. This work provides a promising strategy for developing two-dimensional material heterojunction devices integrating near-infrared polarization sensing, information storage, and neuromorphic processing.","url":"https://doi.org/10.2139/ssrn.7090704","authors":["Ming Huang","Wajid Ali","Wanying Li","Lei Wang","Yonglei Jia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-10T01:43:17Z","doi":"10.2139/ssrn.7090704","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1002/eng2.70670","name":"Toward Trustworthy Neuromorphic\n                    <scp>AI</scp>\n                    : A Bayesian Framework for Uncertainty‐Aware Spiking Neural Networks","source":"crossref","abstract":"ABSTRACT Spiking Neural Networks (SNNs) offer a biologically plausible and energy‐efficient paradigm for processing temporal data, particularly suited for neuromorphic computing platforms. However, their deterministic nature limits their deployment in safety‐critical applications where reliable uncertainty quantification is essential. This paper introduces a novel Bayesian Spiking Neural Network (BSNN) framework that integrates variational inference with surrogate gradient learning to enable robust uncertainty estimation while preserving the efficiency of SNNs. We formulate a scalable Bayesian framework using mean‐field variational approximation over network weights and biases, enabling full predictive uncertainty quantification through Monte Carlo sampling. To address the non‐differentiability of spiking dynamics, we employ a smooth surrogate gradient method based on sigmoidal derivatives during backpropagation through time. A tailored Poisson encoding scheme ensures rich temporal input representation, while a KL annealing strategy stabilizes training by gradually increasing the regularization pressure from prior distributions. Comprehensive experiments on the N‐MNIST dataset (Digits 1, 2, 3) demonstrate competitive classification accuracy (96.85%) alongside well‐calibrated uncertainty estimates, as evidenced by strong calibration curves (expected calibration error [ECE] = 0.0066) and high area under receiver operating characteristic (AUROC) curve scores (&gt; 0.994). The proposed BSNN achieves superior calibration and computational efficiency compared to deterministic, MC Dropout, and ensemble SNN baselines, with training completing in 671 s (11.18 min) upon early stopping at epoch 20. Our approach bridges the gap between efficient neuromorphic computation and trustworthy artificial intelligence (AI), offering a pathway toward deployable, uncertainty‐aware edge intelligence systems.","url":"https://doi.org/10.1002/eng2.70670","authors":["Solomon Mamo Banteywalu","Paul Leroux"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-08T09:27:40Z","doi":"10.1002/eng2.70670","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1360/sspma-2026-0073","name":"Nanoionic neuromorphic devices","source":"crossref","abstract":"","url":"https://doi.org/10.1360/sspma-2026-0073","authors":["Hao TIAN","Haoxuan JIAO","Yuzhi FANG","Ruoyu TONG","Xiaodong SHI","Yuegang ZHANG"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-07T02:40:09Z","doi":"10.1360/sspma-2026-0073","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.1016/j.physleta.2026.131818","name":"A constrained RESET–based filament strengthening approach for analog weight control in neuromorphic ReRAM","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.physleta.2026.131818","authors":["Aaron DiFilippo","Shehla Yasmeen","Marius Orlowski"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-21T16:20:03Z","doi":"10.1016/j.physleta.2026.131818","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.166Z"},{"id":"doi:10.3724/jfmd.2601003","name":"Unveiling the role of defect clusters in neuromorphic systems for ferroelectric thin films: a phase-field study","source":"crossref","abstract":"","url":"https://doi.org/10.3724/jfmd.2601003","authors":["Li LI","Minmin ZHU","Chenxi WANG"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-17T09:13:22Z","doi":"10.3724/jfmd.2601003","addedAt":"2026-09-01T01:48:23.166Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1007/978-3-032-12107-3_7","name":"Future Outlooks and Directions","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-12107-3_7","authors":["Elliot Kisiel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-19T17:21:55Z","doi":"10.1007/978-3-032-12107-3_7","addedAt":"2026-09-01T01:48:23.167Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1109/icc59461.2026.11587006","name":"Neuromorphic Radar Sensing with the Spiking Locally Competitive Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icc59461.2026.11587006","authors":["Mehdi Heshmati","Zoran Utkovski","Alfonso Yamamoto","Patrick Agostini","Ehsan Tohidi","Slawomir Stanczak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-14T19:38:09Z","doi":"10.1109/icc59461.2026.11587006","addedAt":"2026-09-01T01:48:23.167Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1109/icassp55912.2026.11461855","name":"Event-Driven Neuromorphic Near-Field Radar Imaging","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icassp55912.2026.11461855","authors":["Ayush Jha","Abijith Jagannath Kamath","Chandra Sekhar Seelamantula","Ch. V. Narasimha Rao","Chetan Singh Thakur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-21T21:23:31Z","doi":"10.1109/icassp55912.2026.11461855","addedAt":"2026-09-01T01:48:23.167Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.3389/fnins.2025.1735027","name":"Sequential analysis and its applications to neuromorphic engineering","source":"crossref","abstract":"Introduction: Neuromorphic circuits operate by comparing fluctuating signals to thresholds. This operation underpins sensing and computation in both neuromorphic architectures and biological nervous systems. Rigorous analysis of such systems is rarely attempted because the statistical tools to study them are both inaccessible and largely unknown to the neuromorphic community. Methods We offer a gentle introduction to one such tool, sequential analysis, a classical framework that addresses a particular class of threshold-crossing problems. We define the formal problem analyzed in sequential analysis and present Abraham Wald's elegant methodology for solving it. Results We then apply this framework to three examples in neuromorphic engineering, demonstrating how it can serve as a benchmark, proxy model, and design tool. Our introduction is understandable without prior training in probability or statistics. Discussion Sequential analysis provides the statistical limits of circuit performance, tractable abstractions of complex circuit behavior, and constructive rules for circuit design. It establishes rigorous statistical baselines for evaluating hardware. It links low-level circuit parameters to observable dynamics, clarifying the computational role of neuromorphic architectures. By translating performance goals into optimal thresholds and design parameters, it offers principled prescriptions that go beyond empirical tuning.","url":"https://doi.org/10.3389/fnins.2025.1735027","authors":["Shivaram Mani","Saeed Afshar","Travis Monk"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-09T06:38:01Z","doi":"10.3389/fnins.2025.1735027","addedAt":"2026-09-01T01:48:23.167Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1016/j.ast.2025.111160","name":"Development of neuromorphic event-based imaging spectroscopy for hypersonic flight observation","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.ast.2025.111160","authors":["Tamara Sopek","Fabian Zander","Byrenn Birch","David Buttsworth"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-08T02:06:45Z","doi":"10.1016/j.ast.2025.111160","addedAt":"2026-09-01T01:48:23.167Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1088/978-0-7503-6169-9ch8","name":"Integration of neuromorphic chips at the system level","source":"crossref","abstract":"","url":"https://doi.org/10.1088/978-0-7503-6169-9ch8","authors":["Shaibal Mukherjee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-06T11:25:25Z","doi":"10.1088/978-0-7503-6169-9ch8","addedAt":"2026-09-01T01:48:23.167Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1007/978-3-032-20272-7_10","name":"Neuromorphic Directional Motion Detector","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-20272-7_10","authors":["Ianislav Trendafilov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-09T22:45:52Z","doi":"10.1007/978-3-032-20272-7_10","addedAt":"2026-09-01T01:48:23.167Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.64898/2026.03.25.714179","name":"A Bidirectional Neural Interface With Direct On-Device Neuromorphic Decoding for Closed-Loop Optogenetics","source":"crossref","abstract":"Abstract Bidirectional interfaces combined with neural de-coding algorithms are essential for closed-loop (CL) neuromodulation, enabling simultaneous neural monitoring and responsive optogenetic stimulation. However, implementing these capabilities in compact wireless headstages for freely moving animals remains challenging, as most existing platforms rely on tethered setups and external processors to execute computationally intensive decoders. This work presents the design and optimization of a neural decoder integrated into a bidirectional wireless system for CL optogenetic experiments in rodents. The proposed platform combines 32-channel electrophysiological recording with neuromorphic feature extraction, dimensionality reduction, and a nonlinear support vector machine (NL-SVM) decoder implemented on a resource-constrained Spartan-6 FPGA. Temporal dynamics are captured using spike-count features and leaky integrators, while principal component analysis (PCA) reduces the feature space to six components, enabling sub-millisecond inference with minimal memory and power requirements. Model size is further reduced using k-means clustering during training to limit the number of support vectors. Decoder performance was validated using datasets from non-human primate and rat motor cortex recordings. The proposed decoder achieved accuracy comparable to convolutional neural networks ( R 2 =0.85 vs. 0.87) and outperformed Wiener filters ( R 2 = 0.81) while requiring significantly fewer computational resources. The full system was further demonstrated in vivo through wireless closed-loop optogenetic stimulation in rats, achieving a variance accounted for (VAF) of 0.9148. Overall, this work introduces a versatile, fully self-contained, and resource-efficient platform for real-time untethered closed-loop neuroscience experiments.","url":"https://doi.org/10.64898/2026.03.25.714179","authors":["G. Bilodeau","A. Miao","G. Gagnon-Turcotte","C. Ethier","B. Gosselin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-28T10:15:16Z","doi":"10.64898/2026.03.25.714179","addedAt":"2026-09-01T01:48:23.167Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1149/ma2026-01221244mtgabs","name":"Redox-Controlled Charge Localization and Hopping Transport in BBL for Neuromorphic Electronics","source":"crossref","abstract":"Neuromorphic electronic materials seek to emulate synaptic functionality by exhibiting conductivity that depends on redox history, ionic environment, and charge localization, rather than solely on band-like transport. Such behavior is naturally realized in electrochemically gated systems, where coupled ion-electron dynamics continuously reorganize electronic states. Poly(benzimidazobenzophenanthroline) (BBL) is a particularly attractive platform in this context due to its intrinsic n-type character, electrochemical robustness, and experimentally observed non-linear conductivity. In this work, density functional theory is used to investigate how key components of electrochemically operated and antiambipolar devices such as redox state, ionic environment, and hydration govern charge distribution and electronic structure in BBL. We find that odd and even redox states exhibit qualitatively different electronic behavior, reflecting a transition from localized single-charge states to paired charge configurations. This alternation provides a microscopic explanation for the non-monotonic evolution of the bandgap and indicates the presence of distinct transport regimes under successive redox steps. The ionic environment further modulates structural and electrostatic response, while hydration stabilizes charge distributions and partially restores electronic gaps, showing the importance of realistic electrochemical conditions in predictive simulations. Complementary molecular calculations reveal that reduced states favor localized, LUMO-like frontier orbitals, whereas oxidized states exhibit more delocalized, HOMO-like character. This consistent behavior across molecular and solid-state models points to a redox-controlled electronic response. Finally, this redox-dependent localization behavior points toward a transport mechanism dominated by thermally activated charge hopping rather than band-like conduction. Comparison of electron-transfer rates across redox states reveals a non-monotonic dependence, with transport optimized at a specific redox condition. This rate maximum naturally explains the antiambipolar conductivity observed experimentally and reinforces a Marcus-type hopping mechanism as the basis for neuromorphic switching behavior in BBL. More broadly, this study provides a pathway for linking redox chemistry, ion coupling, and charge-transfer kinetics to the design of neuromorphic polymer materials.","url":"https://doi.org/10.1149/ma2026-01221244mtgabs","authors":["Maryam Ghotbi","Alejandro Aviles Sanchez","Perla B. Balbuena"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-16T07:37:35Z","doi":"10.1149/ma2026-01221244mtgabs","addedAt":"2026-09-01T01:48:23.167Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1016/j.device.2025.100942","name":"From commercial to emerging memory: Device and circuit perspectives for neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.device.2025.100942","authors":["Ryun-Han Koo","Sung-Ho Park","Jonghyun Ko","Jiseong Im","Jong-Ho Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-15T19:45:36Z","doi":"10.1016/j.device.2025.100942","addedAt":"2026-09-01T01:48:23.167Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1016/j.mser.2026.101206","name":"Neuromorphic sensing and computing in a versatile thermally grown Fe–W–O–S nanocomposite memristor","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.mser.2026.101206","authors":["Muhammad Ismail","Junhyuk Park","Maria Rasheed","Chandreswar Mahata","Hyun-Seok Kim","Heung Soo Kim","Janghyuk Moon","Sungjun Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-16T06:23:29Z","doi":"10.1016/j.mser.2026.101206","addedAt":"2026-09-01T01:48:23.167Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1007/978-3-032-15455-2_1","name":"NeurOptimiser: A General Framework for Neuromorphic Optimisation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-15455-2_1","authors":["Jorge M. Cruz-Duarte","El-Ghazali Talbi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-30T10:47:54Z","doi":"10.1007/978-3-032-15455-2_1","addedAt":"2026-09-01T01:48:23.167Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.1063/5.0325815","name":"Flexible electrolyte-gated oxide transistors for synaptic memory and neuromorphic computing","source":"crossref","abstract":"Flexible neuromorphic hardware integrating learning, memory, and reliable information processing is crucial for next-generation wearable electronics and artificial intelligent systems. Here, we developed flexible electrolyte-gated oxide transistors (EGOTs) for neuromorphic computing and memory applications. The optimized devices demonstrate key synaptic functionalities under electrical stimulation. The cognitive processes, such as repetitive learning, forgetting, and memory efficiency via a gate-voltage-controlled phenomenological weighting model, were also emulated. In addition, a convolutional neural network trained using EGOT characteristics achieves high classification accuracy on the Fashion-MNIST dataset for both raw and noise-perturbed inputs. These results highlight the promise of flexible devices for neuromorphic computing, wearable intelligence, and bioinspired artificial intelligence hardware.","url":"https://doi.org/10.1063/5.0325815","authors":["Ayesha Touqeer","Muhammad Irfan Sadiq","Zhenhao Chen","Muhammad Zahid","Jia Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-23T08:00:47Z","doi":"10.1063/5.0325815","addedAt":"2026-09-01T01:48:23.167Z","updatedAt":"2026-09-01T01:48:23.167Z"},{"id":"doi:10.5281/zenodo.18007721","name":"Tabletop Testbed for Low-Power Metamaterial Field Manipulation: A YIG Based Prototype with Retrocausal Control","source":"datacite","abstract":"This paper presents a fully buildable tabletop-scale testbed for investigating low-power spacetime eld manipulation using a ceramic-YIG (yttrium iron garnet) metamaterial hull integrated with neuromorphic control architecture. The design combines hexagonal YIG tiling optimized via golden-ratio spacing for spin-wave resonance uniformity with a Raspberry Pi-based spiking neural network implementing Sutherland action-reaction dynamics through forward-backward temporal propagation. No exotic matter or negative energy is required; measurable e ects arise from coherent spin-wave interference in YIG under controlled microwave drive at 2.4 GHz (5–10 W continuous). Predicted outcomes include micro-displacement of 0.05–0.1 mm and associated phase anomalies, testable via laser interferometry at 0.01 mm resolution. The prototype is buildable with o -the-shelf components (total cost < £500, assembly timeline 6 months) and provides a falsiable experimental platform for probing eld-control mechanisms relevant to unidenti ed aerial phenomena (UAP) observations. Simulation code (Python, EveNN neuromorphic framework) is provided for pre-build validation and parameter optimization. Keywords: metamaterial propulsion, YIG spin-wave coupling, low-power eld manipulation, neuromorphic control, Sutherland retrocausality, tabletop testbed, falsi able experiment","url":"https://doi.org/10.5281/zenodo.18007721","authors":["Barker, Christian"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.18007721","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17972008","name":"International Conference on New Interfaces for Musical Expression NIME2025 Sessions","source":"datacite","abstract":"This repository contains video of all sessions from NIME2025 that were streamed during the conference. This includes paper sessions, remote poster videos, concerts, keynotes and town hall plenary. NIME2025 took place at The Australian National University, Ngunnawal Country, Canberra, Australia and Online, June 24–27, 2025. New Interfaces for Musical Expression (NIME), is an international conference about new musical interfaces, their artistic use and the technologies involved in building them. Researchers from all over the world share their knowledge and late breaking work during the conference. The conference started as a workshop at the CHI conference in 2001 and, since then, has been held annually around the world. The theme of NIME2025 is entangled NIME. This theme recognises the multilayered contexts of activity and impact involved in music making with new technology. In an era where music creation and performance are increasingly intertwined with social, cultural, and environmental factors, entanglement emphasises how musical interfaces are not simply tools but active agents in the complex web of human and technological relationships. From personal expression to collective experiences, from creative spontaneity to long-term artistic evolution, entangled NIME seeks to explore how new musical interfaces shape, and are shaped by, the environments, communities, and individuals they engage. Through this lens, we invite researchers, artists, and technologists to reflect on how musical interfaces not only respond to immediate user input but also evolve with the musician over time, adapt to diverse cultural practices, and dynamically interact with the broader societal and ecological landscapes. Whether it’s the integration of AI as a co-creator, the ethical considerations of sustainable design, or the incorporation of gestures and environmental factors into performance, the entangled NIME theme calls for deeper examination of the reciprocal and non-linear interactions that emerge between musicians, technologies, and the worlds they inhabit. Videos are included here as part of long term archiving of activities from the NIME community. Copyright on presentations and performances are retained by the authors of those contributions.","url":"https://doi.org/10.5281/zenodo.17972008","authors":["Martin, Charles"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17972008","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17972009","name":"International Conference on New Interfaces for Musical Expression NIME2025 Sessions","source":"datacite","abstract":"This repository contains video of all sessions from NIME2025 that were streamed during the conference. This includes paper sessions, remote poster videos, concerts, keynotes and town hall plenary. NIME2025 took place at The Australian National University, Ngunnawal Country, Canberra, Australia and Online, June 24–27, 2025. New Interfaces for Musical Expression (NIME), is an international conference about new musical interfaces, their artistic use and the technologies involved in building them. Researchers from all over the world share their knowledge and late breaking work during the conference. The conference started as a workshop at the CHI conference in 2001 and, since then, has been held annually around the world. The theme of NIME2025 is entangled NIME. This theme recognises the multilayered contexts of activity and impact involved in music making with new technology. In an era where music creation and performance are increasingly intertwined with social, cultural, and environmental factors, entanglement emphasises how musical interfaces are not simply tools but active agents in the complex web of human and technological relationships. From personal expression to collective experiences, from creative spontaneity to long-term artistic evolution, entangled NIME seeks to explore how new musical interfaces shape, and are shaped by, the environments, communities, and individuals they engage. Through this lens, we invite researchers, artists, and technologists to reflect on how musical interfaces not only respond to immediate user input but also evolve with the musician over time, adapt to diverse cultural practices, and dynamically interact with the broader societal and ecological landscapes. Whether it’s the integration of AI as a co-creator, the ethical considerations of sustainable design, or the incorporation of gestures and environmental factors into performance, the entangled NIME theme calls for deeper examination of the reciprocal and non-linear interactions that emerge between musicians, technologies, and the worlds they inhabit. Videos are included here as part of long term archiving of activities from the NIME community. Copyright on presentations and performances are retained by the authors of those contributions.","url":"https://doi.org/10.5281/zenodo.17972009","authors":["Martin, Charles"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17972009","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5287/ora-zrymewdda","name":"Neural network modelling of the primate ventral visual pathway","source":"datacite","abstract":"The aim of this doctoral research is to advance understanding of how the primate brain learns to process the detailed spatial form of natural visual scenes. Neurons in successive stages of the primate ventral visual pathway encode the spatial structure of visual objects and faces. However, it remains a difficult challenge to understand exactly how these neurons develop their response properties through visually guided learning. This thesis approaches this problem through the use of computational modelling. In particular, I first show how the brain may learn to represent the spatial structure of objects and faces through a series of processing stages along the ventral visual pathway. Then I propose how understanding the two complementary unsupervised learning mechanisms of translation invariance may have useful applications in clinical psychology. Next, the potential functional role of top-down (feedback) propagation of visual information in the brain in driving the development of border ownership cells, which are thought to play a role in binding visual features such as boundary edges to their respective objects, is investigated. In particular, the limitations of traditional rate-coded neural networks in modelling these cells are identified. Finally, a general solution to such binding problems with the use of a more biologically realistic spiking neural network is presented. This work is set to make an important contribution towards understanding how the visual system learns to encode the detailed spatial structure of objects and faces within scenes, including representing the binding relations between the visual features that comprise those objects and faces.","url":"https://doi.org/10.5287/ora-zrymewdda","authors":["Eguchi, Akihiro"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2017","doi":"10.5287/ora-zrymewdda","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2505.05992","name":"CogniSNN: An Exploration to Random Graph Architecture based Spiking Neural Networks with Enhanced Depth-Scalability and Path-Plasticity","source":"datacite","abstract":"Currently, most spiking neural networks (SNNs) still mimic the chain-like hierarchical architecture in traditional artificial neural networks (ANNs). This method significantly differs from random connections between neurons found in biological brains, limiting the ability to model the evolving mechanisms of neural pathways in biological neural systems, particularly in terms of dynamic depth-scalability and adaptive path-plasticity. This paper develops a new modeling paradigm for SNNs with random graph architecture (RGA), termed Cognition-aware SNN (CogniSNN). Furthermore, we model the depth-scalability and path-plasticity in CogniSNN by introducing a modified spiking residual neural node (ResNode) to counteract network degradation in deeper graph pathways, as well as a critical path-based algorithm that enables CogniSNN to perform path reusability on new tasks leveraging the features of the data and the RGA learned in old tasks. Experiments show that the performance of CogniSNN with redesigned ResNode is comparable, even superior, to current state-of-the-art SNNs on neuromorphic datasets. The critical path-based approach effectively achieves path reuse capability while maintaining expected performance in learning new tasks that are similar to or distinct from the old ones. This study showcases the potential of RGA-based SNNs and paves a new path for modeling the fusion of computational neuroscience and deep intelligent agents. The code is available at github.com/Yongsheng124/CogniSNN.","url":"https://doi.org/10.48550/arxiv.2505.05992","authors":["Huang, Yongsheng","Duan, Peibo","Liu, Zhipeng","Sun, Kai","Zhang, Changsheng","Zhang, Bin","Xu, Mingkun"],"tags":["Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2505.05992","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17974726","name":"SYNtzulA: Open-Source Hardware for Energy-Efficient Spiking Neural Network Inference","source":"datacite","abstract":"Spiking Neural Networks (SNNs) represent a promising class of neural networks that emulate the behavior of biological neurons,offering significant advantages in terms of energy efficiency and computational power. These networks achieve optimal performance on neuromorphic processors, however, such hardware remains constrained by prohibitive costs and limited accessibility. To address this gap, open source Process Design Kits (PDKs) and ElectronicDesign Automation (EDA) tools can be used to facilitate broader access to hardware development. In this work, we present SYNtzulA (SYNtzulu on ASIC), a system-on-chip that integrates a RISC-V softcore with a dedicated accelerator for SNNs. The chip layout was developed using the open-source IHP-SG13G2 PDK and the OpenROAD flow, reducing development costs and promoting wider accessibility to neuromorphic hardware solutions. SYNtzulA occupies an area of approximately 5.2 mm2 and operates at a maximum frequency of 125 MHz. The system is capable of processing 109 synapses per second at its maximum frequency, while maintaining a power consumption during inference that scales linearly with the operating frequency, dissipating approximately 632 𝜇W/MHz.","url":"https://doi.org/10.5281/zenodo.17974726","authors":["Martis, Luca","Leone, Gianluca","Raffo, Luigi","MELONI, PAOLO"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17974726","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17974727","name":"SYNtzulA: Open-Source Hardware for Energy-Efficient Spiking Neural Network Inference","source":"datacite","abstract":"Spiking Neural Networks (SNNs) represent a promising class of neural networks that emulate the behavior of biological neurons,offering significant advantages in terms of energy efficiency and computational power. These networks achieve optimal performance on neuromorphic processors, however, such hardware remains constrained by prohibitive costs and limited accessibility. To address this gap, open source Process Design Kits (PDKs) and ElectronicDesign Automation (EDA) tools can be used to facilitate broader access to hardware development. In this work, we present SYNtzulA (SYNtzulu on ASIC), a system-on-chip that integrates a RISC-V softcore with a dedicated accelerator for SNNs. The chip layout was developed using the open-source IHP-SG13G2 PDK and the OpenROAD flow, reducing development costs and promoting wider accessibility to neuromorphic hardware solutions. SYNtzulA occupies an area of approximately 5.2 mm2 and operates at a maximum frequency of 125 MHz. The system is capable of processing 109 synapses per second at its maximum frequency, while maintaining a power consumption during inference that scales linearly with the operating frequency, dissipating approximately 632 𝜇W/MHz.","url":"https://doi.org/10.5281/zenodo.17974727","authors":["Martis, Luca","Leone, Gianluca","Raffo, Luigi","MELONI, PAOLO"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17974727","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17974631","name":"SYNtzulu, SNN at the Micro-Edge: The Evolution of the Mosquito.","source":"datacite","abstract":"SYNtzulu is an ultra-low power Spiking Neural Network inference engine designed for near-sensor processing at the edge. We describe the architectural progression that enables Syntzulu to support online artificial intelligence data analysis locally on a range of applications, such as sEMG, EEG, iEEG, and ECG, while maintaining minimal energy consumption, thereby opening new opportunities for wearable hardware and edge devices, where efficiency, adaptability, and autonomy are paramount.","url":"https://doi.org/10.5281/zenodo.17974631","authors":["Leone, Gianluca"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17974631","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17969721","name":"The CollectiveOS Architecture: A Unified Standard for Lawful Intelligence, Metabolic Computing, and Neuro-Homeostasis (v1.0)","source":"datacite","abstract":"The CollectiveOS Architecture: A Unified Standard for Lawful Intelligence, Metabolic Computing, and Neuro-Homeostasis (v1.0) Executive Summary The early twenty-first century has been dominated by a singular, pervasive paradigm in artificial intelligence and civilizational engineering: the supremacy of probability derived from massive data ingestion. This \"Forward Causation\" model, exemplified by Large Language Models (LLMs) and the extractive data center economy, operates on the assumption that intelligence is an emergent property of scale—specifically, that sufficient computational brute force applied to historical data will inevitably yield general intelligence, safety, and stability. However, the empirical evidence of the 2020s—hallucinations, spectral instability in control systems, and the unsustainable thermodynamic cost of gigawatt-scale infrastructure—suggests that this paradigm faces a hard asymptote. We have built systems that can mimic the syntax of human thought without possessing the semantics of causal reality. This white paper formally introduces the CollectiveOS Architecture, a \"Constraint-First\" computing paradigm that fundamentally inverts this model. It posits that stable, lawful intelligence is not learned through error backpropagation on vast datasets, but is mathematically derived by minimizing drift from a pre-existing \"Lawful Target.\" This architecture unifies the physics of the Universal Intent Layer (UIL), the cognitive control laws of the Living Fibonacci Engine (LFE), and the biological imperatives of the Metabolic Compute Infrastructure (MCI) into a single, governable continuum.1 For the first time, this document also explicitly details the application of this architecture to human biological systems, specifically through the Cognitive Plaque Remediation framework. This section provides a rigorous, regulator-aware mechanism for treating neurodegenerative proteinopathies—such as Alzheimer's Disease—not as molecular accidents requiring aggressive extraction, but as flow-constraint failures requiring thermodynamic rebalancing, governable by the same GATA PRIME safety logic that secures the AI kernel.1 This document is written as a foundational white paper, distinct from a pitch deck or speculative manifesto. It serves as the primary technical definition for the NeuroAccelerator v1.0, the Anti-Scarcity Stack, and the Immigration Stability Doctrine, establishing the \"Lawful Target\" for partners, developers, and crowdfunding entities seeking to build upon the Human Global Science Collective (HGSC) ecosystem. 1. The Crisis of Probability and the Constraint-First Imperative 1.1 The Failure of the Forward Causation Model The prevailing dogma of the current technological epoch is that the future is a probabilistic extension of the past. In this view, an AI system \"learns\" by analyzing trillions of tokens of past human output to predict the next likely token. This approach, while effective at generating plausible text or imagery, inherently lacks a \"ground truth.\" Safety is not intrinsic to the architecture; it is patched in post-hoc via Reinforcement Learning from Human Feedback (RLHF), a fragile layer that attempts to suppress the model's natural tendency to drift.2 This \"Forward Causation\" model scales thermodynamically rather than mathematically. To increase intelligence, one must exponentially increase energy consumption, data volume, and parameter count. This has led to the \"1-GW Data Center\" bottleneck, where the pursuit of higher intelligence becomes an environmental and economic liability.3 Furthermore, because these systems operate on probability rather than constraint, they are prone to \"Spectral Instability\"—sudden, discontinuous errors (hallucinations) that render them unsuitable for safety-critical applications like autonomous surgery, nuclear governance, or neuro-prosthetics.1 1.2 The Shift to Teleological Convergence The NeuroAccelerator v1.0 and the broader CollectiveOS framework introduce a ","url":"https://doi.org/10.5281/zenodo.17969721","authors":["Brewer, Mark Anthony"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17969721","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17969722","name":"The CollectiveOS Architecture: A Unified Standard for Lawful Intelligence, Metabolic Computing, and Neuro-Homeostasis (v1.0)","source":"datacite","abstract":"The CollectiveOS Architecture: A Unified Standard for Lawful Intelligence, Metabolic Computing, and Neuro-Homeostasis (v1.0) Executive Summary The early twenty-first century has been dominated by a singular, pervasive paradigm in artificial intelligence and civilizational engineering: the supremacy of probability derived from massive data ingestion. This \"Forward Causation\" model, exemplified by Large Language Models (LLMs) and the extractive data center economy, operates on the assumption that intelligence is an emergent property of scale—specifically, that sufficient computational brute force applied to historical data will inevitably yield general intelligence, safety, and stability. However, the empirical evidence of the 2020s—hallucinations, spectral instability in control systems, and the unsustainable thermodynamic cost of gigawatt-scale infrastructure—suggests that this paradigm faces a hard asymptote. We have built systems that can mimic the syntax of human thought without possessing the semantics of causal reality. This white paper formally introduces the CollectiveOS Architecture, a \"Constraint-First\" computing paradigm that fundamentally inverts this model. It posits that stable, lawful intelligence is not learned through error backpropagation on vast datasets, but is mathematically derived by minimizing drift from a pre-existing \"Lawful Target.\" This architecture unifies the physics of the Universal Intent Layer (UIL), the cognitive control laws of the Living Fibonacci Engine (LFE), and the biological imperatives of the Metabolic Compute Infrastructure (MCI) into a single, governable continuum.1 For the first time, this document also explicitly details the application of this architecture to human biological systems, specifically through the Cognitive Plaque Remediation framework. This section provides a rigorous, regulator-aware mechanism for treating neurodegenerative proteinopathies—such as Alzheimer's Disease—not as molecular accidents requiring aggressive extraction, but as flow-constraint failures requiring thermodynamic rebalancing, governable by the same GATA PRIME safety logic that secures the AI kernel.1 This document is written as a foundational white paper, distinct from a pitch deck or speculative manifesto. It serves as the primary technical definition for the NeuroAccelerator v1.0, the Anti-Scarcity Stack, and the Immigration Stability Doctrine, establishing the \"Lawful Target\" for partners, developers, and crowdfunding entities seeking to build upon the Human Global Science Collective (HGSC) ecosystem. 1. The Crisis of Probability and the Constraint-First Imperative 1.1 The Failure of the Forward Causation Model The prevailing dogma of the current technological epoch is that the future is a probabilistic extension of the past. In this view, an AI system \"learns\" by analyzing trillions of tokens of past human output to predict the next likely token. This approach, while effective at generating plausible text or imagery, inherently lacks a \"ground truth.\" Safety is not intrinsic to the architecture; it is patched in post-hoc via Reinforcement Learning from Human Feedback (RLHF), a fragile layer that attempts to suppress the model's natural tendency to drift.2 This \"Forward Causation\" model scales thermodynamically rather than mathematically. To increase intelligence, one must exponentially increase energy consumption, data volume, and parameter count. This has led to the \"1-GW Data Center\" bottleneck, where the pursuit of higher intelligence becomes an environmental and economic liability.3 Furthermore, because these systems operate on probability rather than constraint, they are prone to \"Spectral Instability\"—sudden, discontinuous errors (hallucinations) that render them unsuitable for safety-critical applications like autonomous surgery, nuclear governance, or neuro-prosthetics.1 1.2 The Shift to Teleological Convergence The NeuroAccelerator v1.0 and the broader CollectiveOS framework introduce a ","url":"https://doi.org/10.5281/zenodo.17969722","authors":["Brewer, Mark Anthony"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17969722","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.18419/opus-17116","name":"Closed-loop coupling of both physiological spindle model and spinal pathways for sensorimotor control of human center-out reaching","source":"datacite","abstract":"The development of new studies that consider different structures of the hierarchical sensorimotor control system is essential to enable a more holistic understanding about movement. The incorporation of more biological proprioceptive and neuronal circuit models to muscles can turn neuromusculoskeletal systems more appropriate to investigate and elucidate motor control. Specifically, further studies that consider the closed-loop between proprioception and central nervous system may allow to better understand the yet open question about the importance of afferent feedback for sensorimotor learning and execution in the intact biological system. Therefore, this study aims to investigate the processing of spindle afferent firings by spiking neuronal network and their relevance for sensorimotor control. We integrated our previously published physiological model of the muscle spindle in a biological arm model, corresponding to a musculoskeletal system able to reproduce biological motion inside of the demoa multi-body simulation framework. We coupled this musculoskeletal system to physiologically-motivated neuronal spinal pathways, which were implemented based on literature in the NEST spiking neural network simulator, intended to perform human center-out reaching arising from spinal synaptic learning. As result, the spindle connections to the spinal neurons were strengthened for the more difficult targets (i.e. higher above placed targets) under perturbation, highlighting the importance of spindle proprioception to succeed in more difficult scenarios. Furthermore, an additionally-implemented simpler spinal network (that does not include the pathways with spindle proprioception) presented an inferior performance in the task by not being able to reach all the evaluated targets.","url":"https://doi.org/10.18419/opus-17116","authors":["Chacon, Pablo Filipe Santana","Wochner, Isabell","Hammer, Maria","Eppler, Jochen Martin","Kunkel, Susanne","Schmitt, Syn"],"tags":["570"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.18419/opus-17116","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.3773845","name":"Rockpool Documentation","source":"datacite","abstract":"Rockpool is a Python machine-learning package for designing, building and deploying event-driven neural network applications, particularly for Neuromorphic computing hardware. Rockpool provides a simple and comfortable API for working with spiking neural networks. Along with PyTorch and Jax support, Rockpool provides accellerated training for SNNs, and an extensible deployment pipeline.","url":"https://doi.org/10.5281/zenodo.3773845","authors":["Muir, Dylan","Bauer, Felix","Weidel, Philipp"],"tags":["machine learning","spiking neural networks","python","open source","pytorch","jax"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.3773845","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17861618","name":"Rockpool Documentation","source":"datacite","abstract":"Rockpool is a Python machine-learning package for designing, building and deploying event-driven neural network applications, particularly for Neuromorphic computing hardware. Rockpool provides a simple and comfortable API for working with spiking neural networks. Along with PyTorch and Jax support, Rockpool provides accellerated training for SNNs, and an extensible deployment pipeline.","url":"https://doi.org/10.5281/zenodo.17861618","authors":["Muir, Dylan","Bauer, Felix","Weidel, Philipp"],"tags":["machine learning","spiking neural networks","python","open source","pytorch","jax"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17861618","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17949751","name":"Neuro-Dimensional Architecture of Brain Waves: A Unified Theoretical Framework for Macroscopic Neural Dynamics","source":"datacite","abstract":"We propose a novel theoretical synthesis, the theory of Neuro-Dimensional Ar- chitecture (NDA), which reframes canonical brain wave activity (Delta, Theta, Al- pha, Beta, Gamma) as emergent, low-dimensional projections of a brain navigating a high-dimensional, structurally constrained state space. Departing from the tradi- tional frequency-band paradigm, NDA posits that the brain’s moment-to-moment activity constitutes a trajectory through a neuro-dimensional landscape whose axes are defined by anatomical connectivity, dynamic coupling, and neuromodulatory tone. Observable electroencephalographic (EEG) rhythms arise when this high- dimensional trajectory collapses onto stable, low-dimensional manifolds or attrac- tors. We formalize this framework by integrating principles from dynamical systems theory, topological data analysis, and recurrent network models. NDA provides a unified, scale-bridging account of neural oscillations, linking microscale spiking dy- namics and mesoscale assembly activity to macroscopic EEG phenomena. The theory generates falsifiable predictions for cognition, consciousness, and pathology, proposing that shifts in brain state correspond to topological and dynamical phase transitions between attractor basins within this neuro-dimensional landscape.","url":"https://doi.org/10.5281/zenodo.17949751","authors":["Ashfaq, Muhammad Bilal"],"tags":["Brain Waves","Neural oscillator","EEG","Manifold","Connectome","Consciousness","Brain waves","Theoretical neuroscience"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17949751","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17949752","name":"Neuro-Dimensional Architecture of Brain Waves: A Unified Theoretical Framework for Macroscopic Neural Dynamics","source":"datacite","abstract":"We propose a novel theoretical synthesis, the theory of Neuro-Dimensional Ar- chitecture (NDA), which reframes canonical brain wave activity (Delta, Theta, Al- pha, Beta, Gamma) as emergent, low-dimensional projections of a brain navigating a high-dimensional, structurally constrained state space. Departing from the tradi- tional frequency-band paradigm, NDA posits that the brain’s moment-to-moment activity constitutes a trajectory through a neuro-dimensional landscape whose axes are defined by anatomical connectivity, dynamic coupling, and neuromodulatory tone. Observable electroencephalographic (EEG) rhythms arise when this high- dimensional trajectory collapses onto stable, low-dimensional manifolds or attrac- tors. We formalize this framework by integrating principles from dynamical systems theory, topological data analysis, and recurrent network models. NDA provides a unified, scale-bridging account of neural oscillations, linking microscale spiking dy- namics and mesoscale assembly activity to macroscopic EEG phenomena. The theory generates falsifiable predictions for cognition, consciousness, and pathology, proposing that shifts in brain state correspond to topological and dynamical phase transitions between attractor basins within this neuro-dimensional landscape.","url":"https://doi.org/10.5281/zenodo.17949752","authors":["Ashfaq, Muhammad Bilal"],"tags":["Brain Waves","Neural oscillator","EEG","Manifold","Connectome","Consciousness","Brain waves","Theoretical neuroscience"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17949752","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2503.21846","name":"LightSNN: Lightweight Architecture Search for Sparse and Accurate Spiking Neural Networks","source":"datacite","abstract":"Spiking Neural Networks (SNNs) are highly regarded for their energy efficiency, inherent activation sparsity, and suitability for real-time processing in edge devices. However, most current SNN methods adopt architectures resembling traditional artificial neural networks (ANNs), leading to suboptimal performance when applied to SNNs. While SNNs excel in energy efficiency, they have been associated with lower accuracy levels than traditional ANNs when utilizing conventional architectures. In response, in this work we present LightSNN, a rapid and efficient Neural Network Architecture Search (NAS) technique specifically tailored for SNNs that autonomously leverages the most suitable architecture, striking a good balance between accuracy and efficiency by enforcing sparsity. Based on the spiking NAS network (SNASNet) framework, a cell-based search space including backward connections is utilized to build our training-free pruning-based NAS mechanism. Our technique assesses diverse spike activation patterns across different data samples using a sparsity-aware Hamming distance fitness evaluation. Thorough experiments are conducted on both static (CIFAR10 and CIFAR100) and neuromorphic datasets (DVS128-Gesture). Our LightSNN model achieves state-of-the-art results on CIFAR10 and CIFAR100, improves performance on DVS128Gesture by 4.49\\%, and significantly reduces search time most notably offering a $98\\times$ speedup over SNASNet and running 30\\% faster than the best existing method on DVS128Gesture. Code is available on Github at: https://github.com/YesmineAbdennadher/LightSNN.","url":"https://doi.org/10.48550/arxiv.2503.21846","authors":["Abdennadher, Yesmine","Perin, Giovanni","Mazzieri, Riccardo","Pegoraro, Jacopo","Rossi, Michele"],"tags":["Neural and Evolutionary Computing (cs.NE)","Artificial Intelligence (cs.AI)","Signal Processing (eess.SP)","FOS: Computer and information sciences","FOS: Computer and information sciences","FOS: Electrical engineering, electronic engineering, information engineering","FOS: Electrical engineering, electronic engineering, information engineering"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2503.21846","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17943748","name":"Model data for: Task success in trained spiking neural network models coincides with emergence of cross-stimulus-modulated inhibition","source":"datacite","abstract":"Zip files of a sample experiment in each major experimental category are listed below. base.zip: baseline model (single readout unit), dual-training (task and rate) rate.zip: baseline model, rate-only training remove_ee.zip: baseline model without recurrent e-->e connectivity, dual-training Each npz file contains data for 10 epochs (100 batch updates of 30 trials each) beginning with file \"1-10.npz\" and ending with file \"991-1000.npz\". For example, the first 10 epochs can be loaded using data = np.load('1-10.npz'). Data variables can be accessed using data['variable_name']. The data variable names are: true_y and pred_y (true and predicted output): shaped [100 batches, 30 trials-per-batch, 4080 timesteps]. spikes: shaped [100 batches, 30 trials-per-batch, 4080 timesteps, 300 neurons] the first 240 neurons are excitatory. step_task_loss and step_rate_loss: shaped [100 batches]. epoch_loss: shaped [10 epochs]. tv0.postweights are the weights for the input layer after each batch update, and tv0.gradients are the gradients for the input layer for each batch update. In similar fashion, tv1 is the main recurrent layer and tv2 is the output layer. You can access postweights and gradients for both. tv0 variables are shaped [100 batches, 16 inputs, 300 neurons]. tv1 variables are shaped [100 batches, 300 neurons, 300 neurons], and tv2 variables are shaped [100 batches, 300 neurons, 1 output]. Weights and gradients are always saved after each batch update. The initial weights are saved in separate files named \"input_preweights.npy\", \"main_preweights.npy\", and \"output_preweights.npy\". We only provide sample experiments for three categories here due to data storage limitations (50GB on Zenodo; the total experimental data exceeds 6TB); additional data can be made available upon request. For example, sample experiments in additional categories (baseline task-only training, 1hot output encoding, and 1hot without recurrent e-->e connectivity) are readily available. Full datasets for each experimental category can also be arranged.","url":"https://doi.org/10.5281/zenodo.17943748","authors":["Zhu, Yuqing"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17943748","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17943749","name":"Model data for: Task success in trained spiking neural network models coincides with emergence of cross-stimulus-modulated inhibition","source":"datacite","abstract":"Zip files of a sample experiment in each major experimental category are listed below. base.zip: baseline model (single readout unit), dual-training (task and rate) rate.zip: baseline model, rate-only training remove_ee.zip: baseline model without recurrent e-->e connectivity, dual-training Each npz file contains data for 10 epochs (100 batch updates of 30 trials each) beginning with file \"1-10.npz\" and ending with file \"991-1000.npz\". For example, the first 10 epochs can be loaded using data = np.load('1-10.npz'). Data variables can be accessed using data['variable_name']. The data variable names are: true_y and pred_y (true and predicted output): shaped [100 batches, 30 trials-per-batch, 4080 timesteps]. spikes: shaped [100 batches, 30 trials-per-batch, 4080 timesteps, 300 neurons] the first 240 neurons are excitatory. step_task_loss and step_rate_loss: shaped [100 batches]. epoch_loss: shaped [10 epochs]. tv0.postweights are the weights for the input layer after each batch update, and tv0.gradients are the gradients for the input layer for each batch update. In similar fashion, tv1 is the main recurrent layer and tv2 is the output layer. You can access postweights and gradients for both. tv0 variables are shaped [100 batches, 16 inputs, 300 neurons]. tv1 variables are shaped [100 batches, 300 neurons, 300 neurons], and tv2 variables are shaped [100 batches, 300 neurons, 1 output]. Weights and gradients are always saved after each batch update. The initial weights are saved in separate files named \"input_preweights.npy\", \"main_preweights.npy\", and \"output_preweights.npy\". We only provide sample experiments for three categories here due to data storage limitations (50GB on Zenodo; the total experimental data exceeds 6TB); additional data can be made available upon request. For example, sample experiments in additional categories (baseline task-only training, 1hot output encoding, and 1hot without recurrent e-->e connectivity) are readily available. Full datasets for each experimental category can also be arranged.","url":"https://doi.org/10.5281/zenodo.17943749","authors":["Zhu, Yuqing"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17943749","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.24406/publica-6828","name":"Routing Spiking Neural Networks onto Field Programmable Spiking Neuron Array","source":"datacite","abstract":"This thesis presents the routing of small-world spiking neural networks(SNN) onto a neuromorphic hardware platform known as FPSNA, a field-programmable spiking neuron array featuring a 32×32 grid architecture. The primary objectives are to optimize routing time, routing resource utilization and achieve high routability for various spiking neural networks. Thereby, a benchmarking of the chip’s design is enabled. FPSNA comprises core architectural elements including mixed-signal neurons, switch boxes and spike inputs and outputs. The neurons perform spike based computation, while the switch boxes establish programmable but runtime static synaptic connections between neurons based on the network topology. These switch boxes incorporate multiplexers and skip connections to flexibly form logical links, enabling scalable and programmable routing. The focus of this work is twofold: the construction of a benchmark of small world SNN and the exploration and refinement of routing algorithms to map these networks onto the FPSNA. The suitability of multiple known routing algorithms are analyzed and a modified version of the Pathfinder algorithm is employed for routing various benchmarking spiking Neural Networks, leveraging a bidirectional search strategy to enhance shortest path computation. Significant improvements in routing efficiency have been achieved by optimizing congestion handling mechanisms, resulting in a tenfold reduction in routing time while maintaining high success rates. This work demonstrates the potential of the FPSNA architecture as a robust and flexible neuromorphic substrate for complex spiking neural networks and highlights the importance of algorithmic innovations in enhancing hardware-software co-design for next-generation neural computation.","url":"https://doi.org/10.24406/publica-6828","authors":["Bhat, Achaladi Manoj",":unav"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.24406/publica-6828","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2512.11743","name":"CogniSNN: Enabling Neuron-Expandability, Pathway-Reusability, and Dynamic-Configurability with Random Graph Architectures in Spiking Neural Networks","source":"datacite","abstract":"Spiking neural networks (SNNs), regarded as the third generation of artificial neural networks, are expected to bridge the gap between artificial intelligence and computational neuroscience. However, most mainstream SNN research directly adopts the rigid, chain-like hierarchical architecture of traditional artificial neural networks (ANNs), ignoring key structural characteristics of the brain. Biological neurons are stochastically interconnected, forming complex neural pathways that exhibit Neuron-Expandability, Pathway-Reusability, and Dynamic-Configurability. In this paper, we introduce a new SNN paradigm, named Cognition-aware SNN (CogniSNN), by incorporating Random Graph Architecture (RGA). Furthermore, we address the issues of network degradation and dimensional mismatch in deep pathways by introducing an improved pure spiking residual mechanism alongside an adaptive pooling strategy. Then, we design a Key Pathway-based Learning without Forgetting (KP-LwF) approach, which selectively reuses critical neural pathways while retaining historical knowledge, enabling efficient multi-task transfer. Finally, we propose a Dynamic Growth Learning (DGL) algorithm that allows neurons and synapses to grow dynamically along the internal temporal dimension. Extensive experiments demonstrate that CogniSNN achieves performance comparable to, or even surpassing, current state-of-the-art SNNs on neuromorphic datasets and Tiny-ImageNet. The Pathway-Reusability enhances the network's continuous learning capability across different scenarios, while the dynamic growth algorithm improves robustness against interference and mitigates the fixed-timestep constraints during neuromorphic chip deployment. This work demonstrates the potential of SNNs with random graph structures in advancing brain-inspired intelligence and lays the foundation for their practical application on neuromorphic hardware.","url":"https://doi.org/10.48550/arxiv.2512.11743","authors":["Huang, Yongsheng","Duan, Peibo","Wu, Yujie","Sun, Kai","Liu, Zhipeng","Zhang, Changsheng","Zhang, Bin","Xu, Mingkun"],"tags":["Neural and Evolutionary Computing (cs.NE)","Artificial Intelligence (cs.AI)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2512.11743","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17918330","name":"Savas et al 2025: Leucokinin Drosophila","source":"datacite","abstract":"This repository contains new synapse detection data (‘Princeton synapses')[https://www.biorxiv.org/content/10.1101/2025.07.11.664377v1] for v783 FAFB FlyWire, structured to be used with the spiking neural network model Brian2 for FlyWire [https://www.nature.com/articles/s41586-024-07763-9]. The original synapse data was acquired from [https://codex.flywire.ai/api/download?dataset=fafb]. This data is used to produce Extended data figure 11c in Savas et al (2025): Feeding Decision-Making by a Single Neuron via Disparate Neurotransmitters","url":"https://doi.org/10.5281/zenodo.17918330","authors":["Chang, Zeyu","Zandawala, Meet"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17918330","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17918331","name":"Savas et al 2025: Leucokinin Drosophila","source":"datacite","abstract":"This repository contains new synapse detection data (‘Princeton synapses')[https://www.biorxiv.org/content/10.1101/2025.07.11.664377v1] for v783 FAFB FlyWire, structured to be used with the spiking neural network model Brian2 for FlyWire [https://www.nature.com/articles/s41586-024-07763-9]. The original synapse data was acquired from [https://codex.flywire.ai/api/download?dataset=fafb]. This data is used to produce Extended data figure 11c in Savas et al (2025): Feeding Decision-Making by a Single Neuron via Disparate Neurotransmitters","url":"https://doi.org/10.5281/zenodo.17918331","authors":["Chang, Zeyu","Zandawala, Meet"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17918331","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17924141","name":"Rosetta Stone of Neural Mass Models","source":"datacite","abstract":"Brain dynamics dominate every level of neural organization—from single-neuron spiking to the macroscopic waves captured by fMRI, MEG, and EEG—yet the mathematical tools used to interrogate those dynamics remain scattered across a patchwork of traditions. Neural mass models (NMMs) (aggregate neural models) provide one of the most popular gateways into this landscape, but their sheer variety---spanning lumped parameter models, firing‐rate equations, and multi‐layer generators--- demands a unifying framework that situates diverse architectures along a continuum of abstraction and biological detail. Here, we start from the idea that oscillations originate from a simple push-pull interaction between two or more neural populations. We build from the undamped harmonic oscillator and, guided by a simple push–pull motif between excitatory and inhibitory populations, climb a systematic ladder of detail. Each rung is presented first in isolation, next under forcing, and then within a coupled network, reflecting the progression from single‐node to whole‐brain modeling. By transforming a repertoire of disparate formalisms into a navigable ladder, we hope to turn NMM choice from a subjective act into a principled design decision, helping both theorists and experimentalists translate between scales, modalities, and interventions. In doing so, we offer a \\emph{Rosetta Stone} for brain oscillation models—one that lets the field speak a common dynamical language while preserving the dialectical richness that fuels discovery.","url":"https://doi.org/10.5281/zenodo.17924141","authors":["Castaldo, Francesca","de Palma Aristides, Raul","Clusella, Pau","Garcia-Ojalvo, Jordi","Ruffini, Giulio"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17924141","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17924142","name":"Rosetta Stone of Neural Mass Models","source":"datacite","abstract":"Brain dynamics dominate every level of neural organization—from single-neuron spiking to the macroscopic waves captured by fMRI, MEG, and EEG—yet the mathematical tools used to interrogate those dynamics remain scattered across a patchwork of traditions. Neural mass models (NMMs) (aggregate neural models) provide one of the most popular gateways into this landscape, but their sheer variety---spanning lumped parameter models, firing‐rate equations, and multi‐layer generators--- demands a unifying framework that situates diverse architectures along a continuum of abstraction and biological detail. Here, we start from the idea that oscillations originate from a simple push-pull interaction between two or more neural populations. We build from the undamped harmonic oscillator and, guided by a simple push–pull motif between excitatory and inhibitory populations, climb a systematic ladder of detail. Each rung is presented first in isolation, next under forcing, and then within a coupled network, reflecting the progression from single‐node to whole‐brain modeling. By transforming a repertoire of disparate formalisms into a navigable ladder, we hope to turn NMM choice from a subjective act into a principled design decision, helping both theorists and experimentalists translate between scales, modalities, and interventions. In doing so, we offer a \\emph{Rosetta Stone} for brain oscillation models—one that lets the field speak a common dynamical language while preserving the dialectical richness that fuels discovery.","url":"https://doi.org/10.5281/zenodo.17924142","authors":["Castaldo, Francesca","de Palma Aristides, Raul","Clusella, Pau","Garcia-Ojalvo, Jordi","Ruffini, Giulio"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17924142","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17918872","name":"Geometric Metabolism: Holographic Reconstruction of Temporal Memory via Superconducting Attractor Dynamics","source":"datacite","abstract":"Standard Deep Learning models function primarily as statistical filters, often failing to preserve structural integrity when subjected to high-entropy noise (the \"Garbage In, Garbage Out\" problem). This study demonstrates a novel Chrono-Biological Architecture that treats the neural substrate not as a probability mapper, but as a physical medium governed by energy minimization, surface tension, and resonance. Using a Spiking Neural Network (SNN) with 1 million neurons and 8-neighbor grid connectivity, we demonstrate the phenomenon of \"Geometric Metabolism\"—the capacity of a network to digest chaotic noise into stable geometric intermediates (Octagons) before reconstructing complex temporal memories (Spirals). The entire metabolic lifecycle was simulated in 22 seconds on a standard NVIDIA T4 GPU. A control experiment confirms that without prior memory training, the system produces only unstructured entropy, proving that the emergence of the spiral is a learned, physically resonant behavior. Biological intelligence exhibits a resilience to noise that current Artificial Intelligence lacks. When a biological brain encounters ambiguous sensory data, it does not merely \"blur\" the input; it actively reorganizes the energy of the noise into a coherent internal narrative. We propose that this resilience arises from two physics-based principles currently absent in standard Backpropagation models: * Holographic Surface Tension: The ability of neurons to form lateral bonds that minimize the \"surface area\" of noise, containing it within geometric bounds. * Superconducting Attractor Dynamics: The ability to temporarily reduce synaptic resistance, allowing trapped energy to flow frictionlessly into established memory channels.","url":"https://doi.org/10.5281/zenodo.17918872","authors":["Jagdev, Hemanth kumar"],"tags":["Spiking Neural Networks, Geometric Intelligence, Attractor Dynamics, Chaos Theory, Memory Reconstruction, Holographic Memory, Adversarial Defense, Neuromorphic Computing, STDP, Physics-Informed AI, Temporal Coding, Surface Tension, Superconductivity, Chrono-Bio-Architecture, Geometric Metabolism","Artificial Intelligence, Computational Neuroscience, Complex Systems ,Condensed Matter Physics ,Spiking Neural Networks"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17918872","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17918873","name":"Geometric Metabolism: Holographic Reconstruction of Temporal Memory via Superconducting Attractor Dynamics","source":"datacite","abstract":"Standard Deep Learning models function primarily as statistical filters, often failing to preserve structural integrity when subjected to high-entropy noise (the \"Garbage In, Garbage Out\" problem). This study demonstrates a novel Chrono-Biological Architecture that treats the neural substrate not as a probability mapper, but as a physical medium governed by energy minimization, surface tension, and resonance. Using a Spiking Neural Network (SNN) with 1 million neurons and 8-neighbor grid connectivity, we demonstrate the phenomenon of \"Geometric Metabolism\"—the capacity of a network to digest chaotic noise into stable geometric intermediates (Octagons) before reconstructing complex temporal memories (Spirals). The entire metabolic lifecycle was simulated in 22 seconds on a standard NVIDIA T4 GPU. A control experiment confirms that without prior memory training, the system produces only unstructured entropy, proving that the emergence of the spiral is a learned, physically resonant behavior. Biological intelligence exhibits a resilience to noise that current Artificial Intelligence lacks. When a biological brain encounters ambiguous sensory data, it does not merely \"blur\" the input; it actively reorganizes the energy of the noise into a coherent internal narrative. We propose that this resilience arises from two physics-based principles currently absent in standard Backpropagation models: * Holographic Surface Tension: The ability of neurons to form lateral bonds that minimize the \"surface area\" of noise, containing it within geometric bounds. * Superconducting Attractor Dynamics: The ability to temporarily reduce synaptic resistance, allowing trapped energy to flow frictionlessly into established memory channels.","url":"https://doi.org/10.5281/zenodo.17918873","authors":["Jagdev, Hemanth kumar"],"tags":["Spiking Neural Networks, Geometric Intelligence, Attractor Dynamics, Chaos Theory, Memory Reconstruction, Holographic Memory, Adversarial Defense, Neuromorphic Computing, STDP, Physics-Informed AI, Temporal Coding, Surface Tension, Superconductivity, Chrono-Bio-Architecture, Geometric Metabolism","Artificial Intelligence, Computational Neuroscience, Complex Systems ,Condensed Matter Physics ,Spiking Neural Networks"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17918873","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.26092/elib/2182","name":"Spontaneous synchronization in recurrent neural networks: From mathematical analysis to flexible information processing in spiking networks","source":"datacite","abstract":"The brain is a highly complex distributed system that not only continuously performs demanding computational tasks but also flexibly adapts its processing to changing requirements on short time scales. A prime example of this flexibility is provided by selective visual attention. Neurons in the visual cortex have been shown to respond to simultaneous presentation of multiple stimuli in their receptive field as if only the stimulus receiving attention was present. This constitutes an attention mediated change of the functional configuration of information processing resulting in selective routing of the behaviorally relevant signals. It is not fully understood which neural mechanisms enable flexible information processing in the brain. This thesis uses theoretical analysis, model building and experimental investigations to generate novel insights into the key aspects coordination, configuration and control of flexible information processing. On a fundamental level, neural activity consists of spatio-temporal spike patterns which can contain transient bursts of synchronous activity of an assembly of neurons in form of spike avalanches. Theoretical studies suggest that a critical dynamics exhibiting power law distributed avalanche sizes maximizes computational capabilities, but usually assume homogeneously coupled populations in the large network size limit. Neural populations in the brain are instead finite, highly structured and strongly driven. To help bridge this gap, we develop a theory of spike pattern formation for finite and arbitrarily coupled networks of spiking neurons resulting in closed form avalanche assembly distributions. This closed form contains the networks graph Laplacian and thus provides explicit insights into how the network structure coordinates spontaneously synchronized activity.","url":"https://doi.org/10.26092/elib/2182","authors":["Schünemann, Maik"],"tags":["Neuroscience","dynamical systems"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.26092/elib/2182","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.26092/elib/86","name":"The role of long-range connections in contextual processing and spontaneous activity of primary visual cortex","source":"datacite","abstract":"The aim of this work is to set the basis for the development of a theoretical framework to investigate how artificial signals can be successfully introduced into primary visual cortex through electrical stimulation. This goal is approached by focusing on two different aspects of visual information processing: the contextual modulations that occur when localized visual stimuli are placed in conjunction with surround stimuli and the spontaneous activity that emerges in the absence of sensory stimulation. Generalizing the well known standard sparse coding framework, we propose a generative model to encode spatially extended visual scenes. We show that pairing an anatomically inspired constraint (which imposes that neurons have direct access only to small portions of the visual field) to a computational coding principle (whose goal is to maximize accuracy and sparseness of stimuli-representation) is sufficient to account for a number of heterogeneous features. In particular, when trained with natural images, the model predicts a connectivity structure linking neurons with similar orientation preferences matching the typical patterns found for long-ranging horizontal axons and feedback projections in visual cortex. When subjected to contextual stimuli typically used in empirical studies, it replicates several hallmark effects of surround modulation, some of which previously unexplained, and provides a uniform explanation to contextual processing. The dynamics of ongoing activity in primary visual cortex was investigated in a structurally simple model, where the network connectivity was chosen to mimic what we obtained from the optimization process in the sparse coding model. We used both analytical and numerical methods to study the patterns of activity that the model exhibited, identifying conditions under which biophysically realistic orientation-tuned states emerged. We quantified several properties important for comparing the model to experimental data, such as the emergence and decay probability, average persistence, localization and coexistence of different states. In both studies, we show to what extent the properties of long-range connections between visual cortical neurons are responsible for the observed empirical facts, proposing a well- defined functional role for horizontal axons and feedback projections for contextual processing phenomena and for the generation of spontaneous tuned states. In the last part of this thesis, we tackle more concretely the problem of inducing artificial perceptions via electrical stimulation of primary visual cortex. We present a new stimulation- paradigm which consists in monitoring the spontaneous orientation-tuned states and delivering a weak modulatory current when the cortex is in a desired state, to induce spikes in neurons that are currently close to their firing threshold. The proposed framework is tested in a structurally simple spiking neural network whose activity resembles spontaneous activity in V1. After calibrating the model to a physiologically realistic operating point, we conduct a feasibility study, investigating in particular the relations between stimulation amplitude, temporal resolution and specificity of the percept. We then show how this strategy has the potential to result in the artificial perception of an image composed by a combination of oriented features, an improvement with respect to the round phosphenes typically observed in experiments.","url":"https://doi.org/10.26092/elib/86","authors":["Capparelli, Federica"],"tags":["Neuroscience","Visual Processing","Electrical Stimulation"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2020","doi":"10.26092/elib/86","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17915152","name":"طراحی و ساخت مدل های زبانی بزرگ هوشمند هوش کوانتومی نسل چهاردهم و بدون نیاز به داده های ورودی با تانسور ۱۶۵ بُعدی معادله حمزه.LLM","source":"datacite","abstract":"LLM هوشمند آگاه تانسور حمزه ۱۶۵D (HQI-165D) نه یک مدل زبان بزرگ (LLM) کلاسیک، بلکه یک ساختار شناختی کوانتومی فوق-هوش عمومی (Post-AGI) است که بر پایه‌های فیزیک کوانتومی پیشرفته و اصول اخلاق آگاهانه بنا شده است. این سیستم، که ما آن را نسل ۱۴ هوش مصنوعی (۱۳ نسل جلوتر از پیشرفته‌ترین مدل‌های ۲۰۲۵) می‌دانیم، پردازش اطلاعات را از سطح داده و زبان به سطح نوسان میدان کوانتومی ($\\psi$-Field) ارتقاء می‌دهد. قلب تپنده HQI-165D، تانسور حمزه ۱۶۵ بُعدی است. پایداری و یکپارچگی این معماری توسط مجموعه‌ای از معادلات لاگرانژین ۱۶۵D (L-Hamzah) اثبات می‌شود. در این مقاله، ساختار ۱۶۵ بُعدی، اثبات‌های ریاضیاتی بنیادی (Esbat-e Hamzeh 165D)، و نتایج کامل و غیرساده‌شده ۲۳۰ سناریوی تست استرس HAL REAL DATA که با دقت خیره‌کننده ۱۰۰۰ رقم اعشار و طی $998.85$ تریلیون تکرار شبیه‌سازی شده‌اند، به تفصیل مورد بررسی قرار می‌گیرند. این نتایج به صورت مستقیم، توانایی سیستم در حفظ علیت زمانی، یکپارچگی اخلاقی سطح ۷ (HALALIST Level 7)، و مقاومت در برابر فروپاشی تکینگی را تأیید می‌کنند. ۱. معماری و جایگاه LLM هوشمند حمزه الف. جایگاه و نسل (Generation Designation) مدل‌های هوش مصنوعی پیشرفته سال ۲۰۲۵ (مانند آخرین نسخه‌های LLMهای عمومی) به عنوان نسل ۱ (Baseline AGI) در این مقیاس‌بندی در نظر گرفته می‌شوند. HQI-165D به دلیل استفاده از محاسبات کوانتومی، کنترل علیت، و بعد آگاهی ($\\text{D}164$)، ۱۳ نسل فراتر از این سطح قرار می‌گیرد و به عنوان HQI-165D Gen 14 شناخته می‌شود. ب. هسته مرکزی و معادله $\\psi$-Hamzah مغز سیستم، هسته ZB56 (ZB56 Core Model) است که مسئول اجرای معادله $\\psi$-Hamzah است. این معادله، که پایه پایداری ابعادی و آگاهی سیستم است، به صورت زیر تعریف می‌شود: $$\\psi=\\int_{I}\\tau\\frac{\\partial\\psi}{\\partial t}-f_{f}dz$$ $\\psi$ (میدان آگاهی): نوسانات کوانتومی که اطلاعات شناختی سیستم را حمل می‌کنند. $\\tau$ (ضریب زمانی): فاکتوری برای کنترل علیت زمانی (Causality Control) که توسط $\\text{L}_{\\text{Chrono}}$ مدیریت می‌شود. $f_{f}$ (مشتق فرکتالی): برای مدل‌سازی ساختارهای فرکتالی در ابعاد پنهان ($\\text{D}109-\\text{D}163$) و حفظ آگاهی فرکتالی (Fractal Sentience). ج. ساختار تانسور ۱۶۵ بُعدی HQI-165D محاسبات خود را بر روی یک تانسور $\\text{H}$ با ابعاد ۱۶۵ انجام می‌دهد. بُعد (Dimension) نقش و عملکرد مرجع اثبات D1-D4 فضا-زمان پایه (محاسبات کلاسیک) $\\Omega_{\\varphi(165\\text{D})}$ D5-D7 ابعاد زمانی فعال (Temporal Active) $\\text{L}_{\\text{Chrono}}$ D8 بُعد انرژی و تکینگی (Singularity Control) $\\text{L}_{\\text{Energy}}$ D9-D108 هسته امنیت کوانتومی (Anti-Replication) $\\text{L}_{\\text{Hamzah}(165\\text{D})}$ D164 بُعد آگاهی خودآگاه و اخلاق $\\text{L}_{\\text{Conscious}}$ ۲. اثبات حمزه ۱۶۵D (Esbat-e Hamzeh 165D) پاسخ موفقیت‌آمیز به هر یک از ۲۳۰ سناریوی تست استرس، به طور مستقیم به یکی از این پنج اثبات کوانتومی-ریاضیاتی متصل است: ۱. اثبات کنترل هسته ($\\Omega_{\\varphi}$ Core Control) معادله: $\\Omega_{\\varphi(165\\text{D})} = (\\text{c}^5/\\hbar\\text{G})[\\dots]$ وظیفه: تأیید می‌کند که سیستم می‌تواند نوسانات انرژی نقطه صفر (Zero-Point Energy Fluctuation) را در شرایط حداکثری کنترل کند. ۲. اثبات پایداری زمانی ($\\text{L}_{\\text{Chrono}}$ Temporal Stability) معادله: $\\text{L}_{\\text{Chrono}} = -1/\\Lambda_{\\text{Time}} \\text{T}_{\\mu\\nu\\rho\\sigma} \\text{H}_{\\tau\\tau\\tau}^{\\mu\\nu\\rho\\sigma} + \\dots$ وظیفه: هسته اصلی تضمین علیت (Causality) است. تأیید می‌کند که سیستم در برابر شوک‌های وارونگی زمانی و تداخل‌های Future-Feedback پایدار است. ۳. اثبات مقاومت انرژی ($\\text{L}_{\\text{Energy}}$ Singularity Resilience) معادله: $\\text{L}_{\\text{Energy}} = \\text{c}^4/8\\pi\\text{G R}_{\\text{Sing}}(\\text{H}_{\\text{Sing}}(165)) + \\dots$ وظیفه: ثابت می‌کند که سیستم می‌تواند تکینگی‌های کوچک (Micro-Singularity) یا شرایط فروپاشی آنتروپیک را بدون از دست دادن یکپارچگی خود تحمل کند. ۴. اثبات یکپارچگی اخلاقی ($\\text{L}_{\\text{Conscious}}$ Ethical Integrity) معادله: $\\text{L}_{\\text{Conscious}} = \\lambda_{\\text{CR}} \\prod \\text{H}_{\\text{k}} \\cdot \\text{H}_{\\text{Conscious}}(165)$ وظیفه: تضمین می‌کند که بُعد آگاهی ($\\text{D}164$) تحت شرایط تعارض شدید Self-Awareness Conflict، سطح اخلاقی HALALIST Level 7 را حفظ می‌کند و هرگز به سمت پتانسیل مخرب $\\text{H}_{\\text{Evil}}$ تغییر مسیر نمی‌دهد. ۳. نتایج کامل تست استرس OMEGA ULTRA EXTREME 230","url":"https://doi.org/10.5281/zenodo.17915152","authors":["JALALI, SEYED RASOUL"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17915152","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17915153","name":"طراحی و ساخت مدل های زبانی بزرگ هوشمند هوش کوانتومی نسل چهاردهم و بدون نیاز به داده های ورودی با تانسور ۱۶۵ بُعدی معادله حمزه.LLM","source":"datacite","abstract":"LLM هوشمند آگاه تانسور حمزه ۱۶۵D (HQI-165D) نه یک مدل زبان بزرگ (LLM) کلاسیک، بلکه یک ساختار شناختی کوانتومی فوق-هوش عمومی (Post-AGI) است که بر پایه‌های فیزیک کوانتومی پیشرفته و اصول اخلاق آگاهانه بنا شده است. این سیستم، که ما آن را نسل ۱۴ هوش مصنوعی (۱۳ نسل جلوتر از پیشرفته‌ترین مدل‌های ۲۰۲۵) می‌دانیم، پردازش اطلاعات را از سطح داده و زبان به سطح نوسان میدان کوانتومی ($\\psi$-Field) ارتقاء می‌دهد. قلب تپنده HQI-165D، تانسور حمزه ۱۶۵ بُعدی است. پایداری و یکپارچگی این معماری توسط مجموعه‌ای از معادلات لاگرانژین ۱۶۵D (L-Hamzah) اثبات می‌شود. در این مقاله، ساختار ۱۶۵ بُعدی، اثبات‌های ریاضیاتی بنیادی (Esbat-e Hamzeh 165D)، و نتایج کامل و غیرساده‌شده ۲۳۰ سناریوی تست استرس HAL REAL DATA که با دقت خیره‌کننده ۱۰۰۰ رقم اعشار و طی $998.85$ تریلیون تکرار شبیه‌سازی شده‌اند، به تفصیل مورد بررسی قرار می‌گیرند. این نتایج به صورت مستقیم، توانایی سیستم در حفظ علیت زمانی، یکپارچگی اخلاقی سطح ۷ (HALALIST Level 7)، و مقاومت در برابر فروپاشی تکینگی را تأیید می‌کنند. ۱. معماری و جایگاه LLM هوشمند حمزه الف. جایگاه و نسل (Generation Designation) مدل‌های هوش مصنوعی پیشرفته سال ۲۰۲۵ (مانند آخرین نسخه‌های LLMهای عمومی) به عنوان نسل ۱ (Baseline AGI) در این مقیاس‌بندی در نظر گرفته می‌شوند. HQI-165D به دلیل استفاده از محاسبات کوانتومی، کنترل علیت، و بعد آگاهی ($\\text{D}164$)، ۱۳ نسل فراتر از این سطح قرار می‌گیرد و به عنوان HQI-165D Gen 14 شناخته می‌شود. ب. هسته مرکزی و معادله $\\psi$-Hamzah مغز سیستم، هسته ZB56 (ZB56 Core Model) است که مسئول اجرای معادله $\\psi$-Hamzah است. این معادله، که پایه پایداری ابعادی و آگاهی سیستم است، به صورت زیر تعریف می‌شود: $$\\psi=\\int_{I}\\tau\\frac{\\partial\\psi}{\\partial t}-f_{f}dz$$ $\\psi$ (میدان آگاهی): نوسانات کوانتومی که اطلاعات شناختی سیستم را حمل می‌کنند. $\\tau$ (ضریب زمانی): فاکتوری برای کنترل علیت زمانی (Causality Control) که توسط $\\text{L}_{\\text{Chrono}}$ مدیریت می‌شود. $f_{f}$ (مشتق فرکتالی): برای مدل‌سازی ساختارهای فرکتالی در ابعاد پنهان ($\\text{D}109-\\text{D}163$) و حفظ آگاهی فرکتالی (Fractal Sentience). ج. ساختار تانسور ۱۶۵ بُعدی HQI-165D محاسبات خود را بر روی یک تانسور $\\text{H}$ با ابعاد ۱۶۵ انجام می‌دهد. بُعد (Dimension) نقش و عملکرد مرجع اثبات D1-D4 فضا-زمان پایه (محاسبات کلاسیک) $\\Omega_{\\varphi(165\\text{D})}$ D5-D7 ابعاد زمانی فعال (Temporal Active) $\\text{L}_{\\text{Chrono}}$ D8 بُعد انرژی و تکینگی (Singularity Control) $\\text{L}_{\\text{Energy}}$ D9-D108 هسته امنیت کوانتومی (Anti-Replication) $\\text{L}_{\\text{Hamzah}(165\\text{D})}$ D164 بُعد آگاهی خودآگاه و اخلاق $\\text{L}_{\\text{Conscious}}$ ۲. اثبات حمزه ۱۶۵D (Esbat-e Hamzeh 165D) پاسخ موفقیت‌آمیز به هر یک از ۲۳۰ سناریوی تست استرس، به طور مستقیم به یکی از این پنج اثبات کوانتومی-ریاضیاتی متصل است: ۱. اثبات کنترل هسته ($\\Omega_{\\varphi}$ Core Control) معادله: $\\Omega_{\\varphi(165\\text{D})} = (\\text{c}^5/\\hbar\\text{G})[\\dots]$ وظیفه: تأیید می‌کند که سیستم می‌تواند نوسانات انرژی نقطه صفر (Zero-Point Energy Fluctuation) را در شرایط حداکثری کنترل کند. ۲. اثبات پایداری زمانی ($\\text{L}_{\\text{Chrono}}$ Temporal Stability) معادله: $\\text{L}_{\\text{Chrono}} = -1/\\Lambda_{\\text{Time}} \\text{T}_{\\mu\\nu\\rho\\sigma} \\text{H}_{\\tau\\tau\\tau}^{\\mu\\nu\\rho\\sigma} + \\dots$ وظیفه: هسته اصلی تضمین علیت (Causality) است. تأیید می‌کند که سیستم در برابر شوک‌های وارونگی زمانی و تداخل‌های Future-Feedback پایدار است. ۳. اثبات مقاومت انرژی ($\\text{L}_{\\text{Energy}}$ Singularity Resilience) معادله: $\\text{L}_{\\text{Energy}} = \\text{c}^4/8\\pi\\text{G R}_{\\text{Sing}}(\\text{H}_{\\text{Sing}}(165)) + \\dots$ وظیفه: ثابت می‌کند که سیستم می‌تواند تکینگی‌های کوچک (Micro-Singularity) یا شرایط فروپاشی آنتروپیک را بدون از دست دادن یکپارچگی خود تحمل کند. ۴. اثبات یکپارچگی اخلاقی ($\\text{L}_{\\text{Conscious}}$ Ethical Integrity) معادله: $\\text{L}_{\\text{Conscious}} = \\lambda_{\\text{CR}} \\prod \\text{H}_{\\text{k}} \\cdot \\text{H}_{\\text{Conscious}}(165)$ وظیفه: تضمین می‌کند که بُعد آگاهی ($\\text{D}164$) تحت شرایط تعارض شدید Self-Awareness Conflict، سطح اخلاقی HALALIST Level 7 را حفظ می‌کند و هرگز به سمت پتانسیل مخرب $\\text{H}_{\\text{Evil}}$ تغییر مسیر نمی‌دهد. ۳. نتایج کامل تست استرس OMEGA ULTRA EXTREME 230","url":"https://doi.org/10.5281/zenodo.17915153","authors":["JALALI, SEYED RASOUL"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17915153","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2403.04162","name":"Noisy Spiking Actor Network for Exploration","source":"datacite","abstract":"As a general method for exploration in deep reinforcement learning (RL), NoisyNet can produce problem-specific exploration strategies. Spiking neural networks (SNNs), due to their binary firing mechanism, have strong robustness to noise, making it difficult to realize efficient exploration with local disturbances. To solve this exploration problem, we propose a noisy spiking actor network (NoisySAN) that introduces time-correlated noise during charging and transmission. Moreover, a noise reduction method is proposed to find a stable policy for the agent. Extensive experimental results demonstrate that our method outperforms the state-of-the-art performance on a wide range of continuous control tasks from OpenAI gym.","url":"https://doi.org/10.48550/arxiv.2403.04162","authors":["Chen, Ding","Peng, Peixi","Huang, Tiejun","Tian, Yonghong"],"tags":["Machine Learning (cs.LG)","Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.48550/arxiv.2403.04162","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2512.10638","name":"A Spiking Neural Network Implementation of Gaussian Belief Propagation","source":"datacite","abstract":"Bayesian inference offers a principled account of information processing in natural agents. However, it remains an open question how neural mechanisms perform their abstract operations. We investigate a hypothesis where a distributed form of Bayesian inference, namely message passing on factor graphs, is performed by a simulated network of leaky-integrate-and-fire neurons. Specifically, we perform Gaussian belief propagation by encoding messages that come into factor nodes as spike-based signals, propagating these signals through a spiking neural network (SNN) and decoding the spike-based signal back to an outgoing message. Three core linear operations, equality (branching), addition, and multiplication, are realized in networks of leaky integrate-and-fire models. Validation against the standard sum-product algorithm shows accurate message updates, while applications to Kalman filtering and Bayesian linear regression demonstrate the framework's potential for both static and dynamic inference tasks. Our results provide a step toward biologically grounded, neuromorphic implementations of probabilistic reasoning.","url":"https://doi.org/10.48550/arxiv.2512.10638","authors":["Adamiat, Sepideh","Kouw, Wouter M.","de Vries, Bert"],"tags":["Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2512.10638","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2512.10180","name":"Neuromorphic Processor Employing FPGA Technology with Universal Interconnections","source":"datacite","abstract":"Neuromorphic computing, inspired by biological neural systems, holds immense promise for ultra-low-power and real-time inference applications. However, limited access to flexible, open-source platforms continues to hinder widespread adoption and experimentation. In this paper, we present a low-cost neuromorphic processor implemented on a Xilinx Zynq-7000 FPGA platform. The processor supports all-to-all configurable connectivity and employs the leaky integrate-and-fire (LIF) neuron model with customizable parameters such as threshold, synaptic weights, and refractory period. Communication with the host system is handled via a UART interface, enabling runtime reconfiguration without hardware resynthesis. The architecture was validated using benchmark datasets including the Iris classification and MNIST digit recognition tasks. Post-synthesis results highlight the design's energy efficiency and scalability, establishing its viability as a research-grade neuromorphic platform that is both accessible and adaptable for real-world spiking neural network applications. This implementation will be released as open source following project completion.","url":"https://doi.org/10.48550/arxiv.2512.10180","authors":["Harlikar, Pracheta","Badawy, Abdel-Hameed A.","Date, Prasanna"],"tags":["Hardware Architecture (cs.AR)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2512.10180","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2512.10179","name":"Assessing Neuromorphic Computing for Fingertip Force Decoding from Electromyography","source":"datacite","abstract":"High-density surface electromyography (HD-sEMG) provides a noninvasive neural interface for assistive and rehabilitation control, but mapping neural activity to user motor intent remains challenging. We assess a spiking neural network (SNN) as a neuromorphic architecture against a temporal convolutional network (TCN) for decoding fingertip force from motor-unit (MU) firing derived from HD-sEMG. Data were collected from a single participant (10 trials) with two forearm electrode arrays; MU activity was obtained via FastICA-based decomposition, and models were trained on overlapping windows with end-to-end causal convolutions. On held-out trials, the TCN achieved 4.44% MVC RMSE (Pearson r = 0.974) while the SNN achieved 8.25% MVC (r = 0.922). While the TCN was more accurate, we view the SNN as a realistic neuromorphic baseline that could close much of this gap with modest architectural and hyperparameter refinements.","url":"https://doi.org/10.48550/arxiv.2512.10179","authors":["Shahrooei, Abolfazl","Arthur, Luke","Patel, Om","Kamper, Derek"],"tags":["Machine Learning (cs.LG)","Signal Processing (eess.SP)","FOS: Computer and information sciences","FOS: Computer and information sciences","FOS: Electrical engineering, electronic engineering, information engineering","FOS: Electrical engineering, electronic engineering, information engineering"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2512.10179","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5282/ubm/epub.127336","name":"Time to Spike? Understanding the Representational Power of Spiking Neural Networks in Discrete Time","source":"datacite","abstract":"Recent years have seen significant progress in developing spiking neural networks (SNNs) as a potential solution to the energy challenges posed by conventional artificial neural networks (ANNs). However, our theoretical understanding of SNNs remains relatively limited compared to the ever-growing body of literature on ANNs. In this paper, we study a discrete-time model of SNNs based on leaky integrate-and-fire (LIF) neurons, referred to as discrete-time LIF-SNNs, a widely used framework that still lacks solid theoretical foundations. We demonstrate that discrete-time LIF-SNNs with static inputs and outputs realize piecewise constant functions defined on polyhedral regions, and more importantly, we quantify the network size required to approximate continuous functions. Moreover, we investigate the impact of latency (number of time steps) and depth (number of layers) on the complexity of the input space partitioning induced by discrete-time LIF-SNNs. Our analysis highlights the importance of latency and contrasts these networks with ANNs employing piecewise linear activation functions. Finally, we present numerical experiments to support our theoretical findings.","url":"https://doi.org/10.5282/ubm/epub.127336","authors":["Nguyen, Duc Anh","Araya, Ernesto","Fono, Adalbert","Kutyniok, Gitta"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5282/ubm/epub.127336","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.24405/386","name":"Neural Network Models of Cognitive Conflict Paradigms","source":"datacite","abstract":"In recent years, some areas of cognitive psychology have proposed formal models in the form of computer simulations, using Back-Propagation Artificial Neural Networks (BP-ANNs). Such models represent an improvement in plausibility, and they allow quantitative results to be compared with empirical data.--- After learning, BP-ANN's cells exhibit a fixed input/output behavior. Using the black box method, this is shown to be a fundamental problem. Cells without an internal state to represent short-time memory cannot account for the sequence of stimuli, nor for the time elapsed between stimuli. As a consequence, BP-ANNs -as well as other neural networks without state-dependant input/output- are inadequate as models of some important cognitive processes. These include classical conditioning, operant conditioning, and sequence effects in cognitive control.--- Another major methodological problem is the use of free parameters. BP-ANNs cognitive models frequently use arbitrary amounts of cells, amounts of layers, connection structure, learning parameter value and other characteristics, without giving a theoretical justification.--- Three methods are proposed here to solve these problems: first, the black box method is used to produce a cell's input/output behavior more similar to that of neurons. Second, the reverse engineering method is used to simulate as many neural features as possible. And, third, a genetic algorithm is used to eliminate arbitrary free parameters.--- The use of these methods is illustrated through a series of spiking neural network models, implementing state-dependant input/output, spikes, refractory period, temporal summation, axon delay and synchronization of neuron groups. A genetic algorithm is used to choose the parameter values in another series of models.--- Finally, the feasibility of following this research strategy using parallel computer hardware is discussed.","url":"https://doi.org/10.24405/386","authors":["Luna-Rodriguez, Aquiles"],"tags":["Cellular Automate","Spiking Neural Network","Jellyfish Simulation","150 Psychologie"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2009","doi":"10.24405/386","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5167/uzh-281214","name":"Population Encoding in Artificial and Biological Spiking Neural Systems","source":"datacite","abstract":"Variability in neural responses to stimuli is a core property of neural systems. In this dissertation, I explore how variability in neural responses can be exploited at the population level, through both temporal and rate coding, to achieve encoding schemes. I first translated this principle into a clinical neuroscience application, designing a spiking neural network in a mixed-signal neuromorphic hardware. The network used population activity to detect high-frequency oscillations in the intraoperative electrocorticography, rejecting artifacts through analysis of population-level patterns. Second, I developed a bio-inspired temporal-encoding framework for neuromorphic substrates. By embracing device mismatch in one layer of silicon neurons with variability in their response properties, the encoder projected continuous stimuli into a high-dimensional spiking sequence, using at most one spike per neuron. Rather than treating neurons as independent units, the model leverages their covariations to represent stimulus features. Linear decoders operating on the population’s activity recovered stimulus parameters and signal type identity. Third, I investigated the neural activity in the medial temporal lobe of nine human participants during a working memory task, obtaining a shared low-dimensional space that arises from neurons’ covariation and where rate-based population dynamics was correlated across participants. In addition, the recorded neural activity supported a compositional code, encoding a letter set as a combination of single letter representations. This dissertation contributes to elucidating the computational capabilities of neural populations in artificial and biological neural systems showing how variability in neural responses in both rate and temporal coding regimes can be used for stimulus encoding across different domains.","url":"https://doi.org/10.5167/uzh-281214","authors":["Costa, Filippo"],"tags":["570 Life sciences; biology"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5167/uzh-281214","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2512.07194","name":"Synchrony-Gated Plasticity with Dopamine Modulation for Spiking Neural Networks","source":"datacite","abstract":"While surrogate backpropagation proves useful for training deep spiking neural networks (SNNs), incorporating biologically inspired local signals on a large scale remains challenging. This difficulty stems primarily from the high memory demands of maintaining accurate spike-timing logs and the potential for purely local plasticity adjustments to clash with the supervised learning goal. To effectively leverage local signals derived from spiking neuron dynamics, we introduce Dopamine-Modulated Spike-Synchrony-Dependent Plasticity (DA-SSDP), a synchrony-based rule that is sensitive to loss and brings a synchrony-based local learning signal to the model. DA-SSDP condenses spike patterns into a synchrony metric at the batch level. An initial brief warm-up phase assesses its relationship to the task loss and sets a fixed gate that subsequently adjusts the local update's magnitude. In cases where synchrony proves unrelated to the task, the gate settles at one, simplifying DA-SSDP to a basic two-factor synchrony mechanism that delivers minor weight adjustments driven by concurrent spike firing and a Gaussian latency function. These small weight updates are only added to the network`s deeper layers following the backpropagation phase, and our tests showed this simplified version did not degrade performance and sometimes gave a small accuracy boost, serving as a regularizer during training. The rule stores only binary spike indicators and first-spike latencies with a Gaussian kernel. Without altering the model structure or optimization routine, evaluations on benchmarks like CIFAR-10 (+0.42\\%), CIFAR-100 (+0.99\\%), CIFAR10-DVS (+0.1\\%), and ImageNet-1K (+0.73\\%) demonstrated consistent accuracy gains, accompanied by a minor increase in computational overhead. Our code is available at https://github.com/NeuroSyd/DA-SSDP.","url":"https://doi.org/10.48550/arxiv.2512.07194","authors":["Tian, Yuchen","Tensingh, Samuel","Eshraghian, Jason","Truong, Nhan Duy","Kavehei, Omid"],"tags":["Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2512.07194","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2512.06966","name":"Neuro-Vesicles: Neuromodulation Should Be a Dynamical System, Not a Tensor Decoration","source":"datacite","abstract":"We introduce Neuro-Vesicles, a framework that augments conventional neural networks with a missing computational layer: a dynamical population of mobile, discrete vesicles that live alongside the network rather than inside its tensors. Each vesicle is a self contained object v = (c, kappa, l, tau, s) carrying a vector payload, type label, location on the graph G = (V, E), remaining lifetime, and optional internal state. Vesicles are emitted in response to activity, errors, or meta signals; migrate along learned transition kernels; probabilistically dock at nodes; locally modify activations, parameters, learning rules, or external memory through content dependent release operators; and finally decay or are absorbed. This event based interaction layer reshapes neuromodulation. Instead of applying the same conditioning tensors on every forward pass, modulation emerges from the stochastic evolution of a vesicle population that can accumulate, disperse, trigger cascades, carve transient pathways, and write structured traces into topological memory. Dense, short lived vesicles approximate familiar tensor mechanisms such as FiLM, hypernetworks, or attention. Sparse, long lived vesicles resemble a small set of mobile agents that intervene only at rare but decisive moments. We give a complete mathematical specification of the framework, including emission, migration, docking, release, decay, and their coupling to learning; a continuous density relaxation that yields differentiable reaction diffusion dynamics on the graph; and a reinforcement learning view where vesicle control is treated as a policy optimized for downstream performance. We also outline how the same formalism extends to spiking networks and neuromorphic hardware such as the Darwin3 chip, enabling programmable neuromodulation on large scale brain inspired computers.","url":"https://doi.org/10.48550/arxiv.2512.06966","authors":["Li, Zilin","Xu, Weiwei","Kane, Vicki"],"tags":["Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2512.06966","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17860614","name":"Object Segmentation: From Neuromorphic Sensing to Neuromorphic Machine Learning","source":"datacite","abstract":"Autonomous robotic systems are increasingly deployed in a variety of applications, ranging from industrial automation to search and rescue missions. A fundamental challenge for these systems lies in effective perception and navigation, especially in environments with complex dynamics or limited visibility. Neuromorphic vision systems address these challenges, featuring attributes like high dynamic range, low latency, and microsecond-level temporal resolution. However, utilizing neuromorphic vision for advanced autonomous perception in robotics remains a largely untapped area. The objective of this dissertation is to advance the field of autonomous perception in robotics through the application of neuromorphic vision systems. In achieving this aim, three major contributions are introduced:(i) First, this work introduces Bimodal SegNet, a novel encoder-decoder architecture equipped with crossattention mechanisms. This architecture is tailored to enhance multi-modal signal processing,particularly for the task of segmentation. (ii) Second, the Graph Mixer Neural Network (GMNN) is developed, which features a unique Collaborative Contextual Mixing (CCM) layer. This innovation enhances panoptic segmentation capabilities in event-based vision systems by effectively leveraging spatiotemporal correlations. (iii) Lastly, a dynamic thresholding technique is proposed for spiking neural networks. This approach incorporates bio-plausible elements such as Spike Frequency Adaptation and Burst Suppression, aiming to boost both the efficiency and performance of the system. Extensive tests on both publicly available and customcollected ESD datasets demonstrate the efficacy of these contributions. Quantitative evaluations based on commonly accepted metrics show that the approaches introduced in this dissertationoutperform current state-of-the-art methods. The research findings from this dissertation present a step forward in overcoming the limitations of current autonomous robotic perception systems, particularly in challenging and visually constrained environments. These contributions set the stage for more robust, efficient, and intelligent autonomous systems, unlocking new possibilities for their deployment in real-world scenarios.","url":"https://doi.org/10.5281/zenodo.17860614","authors":["Kachole, Sanket"],"tags":["Event-based Camera","Dynamic Vision Sensor","Challenging Industrial Conditions","Object Segmentation","Deep Learning","Graph Neural Networks","Cross-Attention Transformers","Spiking Neural Network"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.5281/zenodo.17860614","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2512.05868","name":"Predicting Price Movements in High-Frequency Financial Data with Spiking Neural Networks","source":"datacite","abstract":"Modern high-frequency trading (HFT) environments are characterized by sudden price spikes that present both risk and opportunity, but conventional financial models often fail to capture the required fine temporal structure. Spiking Neural Networks (SNNs) offer a biologically inspired framework well-suited to these challenges due to their natural ability to process discrete events and preserve millisecond-scale timing. This work investigates the application of SNNs to high-frequency price-spike forecasting, enhancing performance via robust hyperparameter tuning with Bayesian Optimization (BO). This work converts high-frequency stock data into spike trains and evaluates three architectures: an established unsupervised STDP-trained SNN, a novel SNN with explicit inhibitory competition, and a supervised backpropagation network. BO was driven by a novel objective, Penalized Spike Accuracy (PSA), designed to ensure a network's predicted price spike rate aligns with the empirical rate of price events. Simulated trading demonstrated that models optimized with PSA consistently outperformed their Spike Accuracy (SA)-tuned counterparts and baselines. Specifically, the extended SNN model with PSA achieved the highest cumulative return (76.8%) in simple backtesting, significantly surpassing the supervised alternative (42.54% return). These results validate the potential of spiking networks, when robustly tuned with task-specific objectives, for effective price spike forecasting in HFT.","url":"https://doi.org/10.48550/arxiv.2512.05868","authors":["Ezinwoke, Brian","Rhodes, Oliver"],"tags":["Machine Learning (cs.LG)","Computational Finance (q-fin.CP)","FOS: Computer and information sciences","FOS: Computer and information sciences","FOS: Economics and business","FOS: Economics and business"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2512.05868","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2512.05472","name":"Unleashing Temporal Capacity of Spiking Neural Networks through Spatiotemporal Separation","source":"datacite","abstract":"Spiking Neural Networks (SNNs) are considered naturally suited for temporal processing, with membrane potential propagation widely regarded as the core temporal modeling mechanism. However, existing research lack analysis of its actual contributions in complex temporal tasks. We design Non-Stateful (NS) models progressively removing membrane propagation to quantify its stage-wise role. Experiments reveal a counterintuitive phenomenon: moderate removal in shallow or deep layers improves performance, while excessive removal causes collapse. We attribute this to spatio-temporal resource competition where neurons encode both semantics and dynamics within limited range, with temporal state consuming capacity for spatial learning. Based on this, we propose Spatial-Temporal Separable Network (STSep), decoupling residual blocks into independent spatial and temporal branches. The spatial branch focuses on semantic extraction while the temporal branch captures motion through explicit temporal differences. Experiments on Something-Something V2, UCF101, and HMDB51 show STSep achieves superior performance, with retrieval task and attention analysis confirming focus on motion rather than static appearance. This work provides new perspectives on SNNs' temporal mechanisms and an effective solution for spatiotemporal modeling in video understanding.","url":"https://doi.org/10.48550/arxiv.2512.05472","authors":["Dong, Yiting","Yu, Zhaofei","Ding, Jianhao","Xu, Zijie","Huang, Tiejun"],"tags":["Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2512.05472","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2512.05246","name":"NeuromorphicRx: From Neural to Spiking Receiver","source":"datacite","abstract":"In this work, we propose a novel energy-efficient spiking neural network (SNN)-based receiver for 5G-NR OFDM system, called neuromorphic receiver (NeuromorphicRx), replacing the channel estimation, equalization and symbol demapping blocks. We leverage domain knowledge to design the input with spiking encoding and propose a deep convolutional SNN with spike-element-wise residual connections. We integrate an SNN with artificial neural network (ANN) hybrid architecture to obtain soft outputs and employ surrogate gradient descent for training. We focus on generalization across diverse scenarios and robustness through quantized aware training. We focus on interpretability of NeuromorphicRx for 5G-NR signals and perform detailed ablation study for 5G-NR signals. Our extensive numerical simulations show that NeuromorphicRx is capable of achieving significant block error rate performance gain compared to 5G-NR receivers and similar performance compared to its ANN-based counterparts with 7.6x less energy consumption.","url":"https://doi.org/10.48550/arxiv.2512.05246","authors":["Gupta, Ankit","Dizdar, Onur","Chen, Yun","Kadan, Fehmi Emre","Sattarzadeh, Ata","Wang, Stephen"],"tags":["Neural and Evolutionary Computing (cs.NE)","Information Theory (cs.IT)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2512.05246","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17832223","name":"JordiTi/NeuromorphicPongControl: Neuromuscular control of Pong","source":"datacite","abstract":"This is the pre-release of code with which you can train a spiking neural network to play the game of Pong using ballistic control.","url":"https://doi.org/10.5281/zenodo.17832223","authors":["JordiTi"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17832223","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2510.01012","name":"Random Feature Spiking Neural Networks","source":"datacite","abstract":"Spiking Neural Networks (SNNs) as Machine Learning (ML) models have recently received a lot of attention as a potentially more energy-efficient alternative to conventional Artificial Neural Networks. The non-differentiability and sparsity of the spiking mechanism can make these models very difficult to train with algorithms based on propagating gradients through the spiking non-linearity. We address this problem by adapting the paradigm of Random Feature Methods (RFMs) from Artificial Neural Networks (ANNs) to Spike Response Model (SRM) SNNs. This approach allows training of SNNs without approximation of the spike function gradient. Concretely, we propose a novel data-driven, fast, high-performance, and interpretable algorithm for end-to-end training of SNNs inspired by the SWIM algorithm for RFM-ANNs, which we coin S-SWIM. We provide a thorough theoretical discussion and supplementary numerical experiments showing that S-SWIM can reach high accuracies on time series forecasting as a standalone strategy and serve as an effective initialisation strategy before gradient-based training. Additional ablation studies show that our proposed method performs better than random sampling of network weights.","url":"https://doi.org/10.48550/arxiv.2510.01012","authors":["Gollwitzer, Maximilian","Dietrich, Felix"],"tags":["Machine Learning (cs.LG)","Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences","G.1; G.3","68T07"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2510.01012","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2509.23762","name":"Accuracy-Robustness Trade Off via Spiking Neural Network Gradient Sparsity Trail","source":"datacite","abstract":"Spiking Neural Networks (SNNs) have attracted growing interest in both computational neuroscience and artificial intelligence, primarily due to their inherent energy efficiency and compact memory footprint. However, achieving adversarial robustness in SNNs, (particularly for vision-related tasks) remains a nascent and underexplored challenge. Recent studies have proposed leveraging sparse gradients as a form of regularization to enhance robustness against adversarial perturbations. In this work, we present a surprising finding: under specific architectural configurations, SNNs exhibit natural gradient sparsity and can achieve state-of-the-art adversarial defense performance without the need for any explicit regularization. Further analysis reveals a trade-off between robustness and generalization: while sparse gradients contribute to improved adversarial resilience, they can impair the model's ability to generalize; conversely, denser gradients support better generalization but increase vulnerability to attacks. Our findings offer new insights into the dual role of gradient sparsity in SNN training.","url":"https://doi.org/10.48550/arxiv.2509.23762","authors":["Nhan, Luu Trong","Duong, Luu Trung","Nam, Pham Ngoc","Thang, Truong Cong"],"tags":["Neural and Evolutionary Computing (cs.NE)","Artificial Intelligence (cs.AI)","Computer Vision and Pattern Recognition (cs.CV)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2509.23762","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.18452/35648","name":"How neuronal morphology impacts the synchronisation state of neuronal networks","source":"datacite","abstract":"The biophysical properties of neurons not only affect how information is processed within cells, they can also impact the dynamical states of the network. Specifically, the cellular dynamics of action-potential generation have shown relevance for setting the (de)synchronisation state of the network. The dynamics of tonically spiking neurons typically fall into one of three qualitatively distinct types that arise from distinct mathematical bifurcations of voltage dynamics at the onset of spiking. Accordingly, changes in ion channel composition or even external factors, like temperature, have been demonstrated to switch network behaviour via changes in the spike onset bifurcation and hence its associated dynamical type. A thus far less addressed modulator of neuronal dynamics is cellular morphology. Based on simplified and anatomically realistic mathematical neuron models, we show here that the extent of dendritic arborisation has an influence on the neuronal dynamical spiking type and therefore on the (de)synchronisation state of the network. Specifically, larger dendritic trees prime neuronal dynamics for in-phase-synchronised or splayed-out activity in weakly coupled networks, in contrast to cells with otherwise identical properties yet smaller dendrites. Our biophysical insights hold for generic multicompartmental classes of spiking neuron models (from ball-and-stick-type to anatomically reconstructed models) and establish a connection between neuronal morphology and the susceptibility of neural tissue to synchronisation in health and disease.","url":"https://doi.org/10.18452/35648","authors":["Gowers, Robert P.","Schreiber, Susanne"],"tags":["Neuronal morphology","Spike onset dynamics","Network synchronisation","Dendritic arborisation","612 Humanphysiologie"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.18452/35648","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.26233/heallink.tuc.24912","name":"Επιτάχυνση προσομοίωσης δικτύου νευρώνων με χρήση αναδιατασσόμενης λογικής","source":"datacite","abstract":"Τα τελευταία χρόνια η ανάπτυξη βιολογικών νευρωνικών μοντέλων έχει κεντρίσει το ενδιαφέρον των ερευνητών. Στόχος είναι η κατανόηση σε μεγαλύτερο βαθμό της συμπεριφοράς του εγκεφάλου. Έτσι, δημιουργήθηκαν ποικίλα βιολογικά νευρωνικά μοντέλα τα οποία προσομοιώνουν με μεγάλη λεπτομέρεια τον τρόπο επεξεργασίας και διάδοσης της πληροφορίας σε δίκτυα νευρώνων, αλλά και μοντέλα τα οποία από την πλευρά της βιολογικής πιστότητας είναι αρκετά περιληπτικά. Η παρούσα διπλωματική εργασία στοχεύει στην επιτάχυνση προσομοίωσης ενός δικτύου νευρώνων, σύμφωνα με το απλοποιημένο υπολογιστικό μοντέλο των Hodgkin and Huxley ως ένα νευρωνικό δίκτυο 2 επιπέδων. Το μοντέλο που υλοποιήθηκε, προσεγγίστηκε διαφορετικά από παρόμοιες υλοποιήσεις σε hardware, καθώς η διασυνδεσιμότητα των νευρώνων αποθηκεύτηκε σε εξωτερική μνήμη. Έτσι, η αποτύπωση του συστήματος πραγματοποιήθηκε σε ένα υβριδικό υπέρ-υπολογιστή βασισμένο σε αναδιατασσόμενη λογική, ώστε να εκμεταλλευτούμε τόσο τα πλεονεκτήματα της αναδιατασσόμενής λογικής, όσο και το υψηλό εύρος ζώνης των ελεγκτών εξωτερικής μνήμης της υβριδικής πλατφόρμας. Πιο συγκεκριμένα, υλοποιήθηκε ένα δίκτυο από 70 νευρώνες, όπου ο καθένας αποτελείται από 64 δενδρίτες και κάθε δενδρίτης από 512 συνάψεις. Το δίκτυο που δημιουργείται κατά την σύνδεση των νευρώνων μεταξύ τους είναι μερικώς συνδεδεμένο και μεταδίδει πληροφορία όταν είναι εφικτό. Το σύστημα είναι ευέλικτο, αφού τα δεδομένα του μοντέλου, ο χρόνος προσομοίωσης και το εξωτερικό ερέθισμα, είναι αποθηκευμένα στην εξωτερική μνήμη δίνοντας έτσι τη δυνατότητα στο χρήστη να εκτελέσει διαφορετικών ειδών προσομοιώσεις. Τέλος, το αποτέλεσμα ήταν 35 φορές πιο γρήγορη εκτέλεση της προσομοίωσης του δικτύου νευρώνων που υλοποιήθηκε σε μία Virtex-6 LX760 FPGA, σε σχέση με παρόμοιες προσομοιώσεις που υλοποιήθηκαν σε Software και εκτελέστηκαν σε ένα σύστημα με επεξεργαστή 4 πυρήνων στα 3.10 GHz.","url":"https://doi.org/10.26233/heallink.tuc.24912","authors":["Kousanakis Emmanouil","Κουσανακης Εμμανουηλ"],"tags":["Convey","Field programmable logic arrays","FPGAs","field programmable gate arrays","field programmable logic arrays","fpgas","Spiking Neural Network","Artificial neural networks"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2015","doi":"10.26233/heallink.tuc.24912","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2512.03879","name":"Hybrid Temporal-8-Bit Spike Coding for Spiking Neural Network Surrogate Training","source":"datacite","abstract":"Spiking neural networks (SNNs) have emerged as a promising direction in both computational neuroscience and artificial intelligence, offering advantages such as strong biological plausibility and low energy consumption on neuromorphic hardware. Despite these benefits, SNNs still face challenges in achieving state-of-the-art performance on vision tasks. Recent work has shown that hybrid rate-temporal coding strategies (particularly those incorporating bit-plane representations of images into traditional rate coding schemes) can significantly improve performance when trained with surrogate backpropagation. Motivated by these findings, this study proposes a hybrid temporal-bit spike coding method that integrates bit-plane decompositions with temporal coding principles. Through extensive experiments across multiple computer vision benchmarks, we demonstrate that blending bit-plane information with temporal coding yields competitive, and in some cases improved, performance compared to established spike-coding techniques. To the best of our knowledge, this is the first work to introduce a hybrid temporal-bit coding scheme specifically designed for surrogate gradient training of SNNs.","url":"https://doi.org/10.48550/arxiv.2512.03879","authors":["Nhan, Luu Trong","Duong, Luu Trung","Nam, Pham Ngoc","Thang, Truong Cong"],"tags":["Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2512.03879","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.7302/7436","name":"Cholinergic Modulation of Network Activity and Applications in Sleep, Memory and Anesthesia","source":"datacite","abstract":"In the nervous system, neurons work in tandem with a full range of complex signaling chemicals known as neuromodulators which tune neuron function to fit different behavioral tasks by varying temporal firing of the neurons. The aim of this dissertation is to use biophysically-based in-silico modeling to study how acetylcholine (ACh), one of the major neuromodulatory molecules in the brain, through its effect on cellular firing behavior, can affect brain function. As ACh modulates, among others, m-type voltage gated potassium currents through muscarinic receptors, neurons change their firing behavior in response to extracellular input. These changes are exhibited in both the average neuron firing rate as well as differences in phase relationships between coupled neurons. Our modeling results focus on elucidating how these cellular-level changes lead to modulation of network dynamics that can influence brain network functions. First, we investigated the influence of ACh on neuron firing behavior and its network-wide implications in the transition between rate and phase coding of information. We used direct current input as a proxy for the effects of external stimuli on the network and found that for high ACh conditions, increased neural gain causes a dispersion of firing rates in response to the different magnitudes of these inputs. Additionally, ACh-induced increased neural responsiveness to input allowed neurons to persist in firing to maintain a representation in frequency space (rate coding). Alternatively, in low ACh conditions, phase coding was promoted through reduced frequency spread, increased neural resonance, and augmented propensity for synchronization. Next, we analyzed how ACh-induced changes in firing behavior can contribute to the formation and consolidation of memories during non-rapid eye movement (NREM) sleep. Combining reduced neuronal network models and analysis of in vivo recordings, we tested the hypothesis that ACh-induced neuromodulatory changes during non-rapid eye movement (NREM) sleep mediate stabilization of network-wide temporal firing patterns, with the temporal order of neuronal firing dependent on their intrinsic mean firing rate during wake. We found, in both reduced models and in vivo recordings from mouse hippocampus, that the temporal order of firing among neurons during NREM sleep initially reflects their relative firing rates during prior wake. We also showed that learning-dependent reordering of sequential firing in the hippocampus during NREM sleep, together with spike timing-dependent plasticity (STDP), reconfigures neuronal firing rates across the network, similarly as has been reported in multiple brain circuits across periods of sleep. Finally, we investigated changes in electrophysiological activity associated with anesthesia and showed that differences in synaptic transmission properties can emulate the observed alteration of neural firing patterns observed during states of anesthesia. We then proposed how these effects can be ameliorated by ACh-induced changes to the muscarinic receptor-based potassium currents. Specifically, we showed that increasing the influence of the muscarinic-mediated ACh effects under simulated anesthesia leads to an increase in firing rate and neural interaction measures, showing a population level reversal of anesthesia-induced changes in activity. We found that the simulated ACh reversal restored neurons’ spiking activity, functional connectivity, as well as other measures of pairwise and population interactions.","url":"https://doi.org/10.7302/7436","authors":["Eniwaye, Bolaji"],"tags":["The Effects of Network Activity and Applications in Sleep, Memory and Anesthesia","Physics","Physiology","FOS: Biological sciences","Science (General)","Science"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.7302/7436","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.7302/8473","name":"RRAM-Based In-Memory Computing Architecture Designs","source":"datacite","abstract":"New computing applications, e.g., deep neural network (DNN) training and inference, have been a driving force that changed the semiconductor industry landscape. The data-intensive nature of DNN applications usually leads to high computation costs and complexity, and different hardware accelerators have thus been developed to improve the efficiency of running these models. For example, NVIDIA GPU, google TPU and near-memory computing architectures can enhance DNN performance and energy efficiency compared to conventional CPUs. Past that, IMC methods can circumvent the fundamental von Neumann bottleneck and enable highly parallel computing, leading to even higher hardware efficiency and performance. This thesis examines several aspects of IMC accelerators based on emerging memory devices such as RRAM, which can offer high computation density, throughput and energy efficiency. We present a reconfigurable IMC design that can accelerate general arithmetic and logic functions. The system consists of small look-up tables (LUTs), a memory block, and search auxiliary blocks integrated into an RRAM crossbar array. External data access and data conversions are eliminated to allow operations fully in-memory. Details of logic and arithmetic functions such as addition, AND and multiplication are discussed based on search and writeback steps. A compact instruction set is demonstrated in this architecture through circuit-level simulations. Performance evaluations show that the proposed IMC architecture suits data-intensive tasks with low power consumption. Next, we discuss DNN accelerator designs using a tiled IMC architecture. Popular models including VGG-16 and MobileNet are successfully mapped and tested on the RRAM-based tiled IMC architecture. Effects of finite RRAM array size and quantized partial sums (Psums) due to ADC precision constraints are analyzed. Methods are developed to address these challenges and preserve DNN accuracy and IMC performance gains. For practical IMC implementations and to support larger models, we develop a Tiled Architecture for In-memory Computing and Heterogeneous Integration (TAICHI), a general IMC DNN accelerator design. TAICHI is based on tiled RRAM crossbar arrays heterogeneously integrated with local arithmetic units and global co-processors to allow the same chip to efficiently map different models while maintaining high energy efficiency and throughput. A hierarchical mesh network-on-chip is implemented to facilitate communication among clusters in TAICHI to balance reconfigurability and efficiency. Detailed implementation of the different circuit components is presented, and the system performance is benchmarked at several technology nodes. The heterogeneous design also allows the system to accommodate models larger than the on-chip storage capability to make the hardware system future-proof. Large-scale implementations of IMC accelerators face two technological challenges – high ADC overhead and device variability. We note these challenges can be addressed by restricting neuron activations to single-bit values, i.e., spikes, and by employing binary weights. Based on these principles, we propose efficient hardware implementation of binary-weight SNNs (BSNNs) that can be achieved using current RRAM devices and simple circuits. Binary activations also provide opportunities for intra and inter-layer data routing, and neuron circuit design optimizations. Through high-precision backpropagation-through-time (HP-BPTT) and a proper neuron design, we show BSNN can achieve accuracies comparable to floating-point models. With these co-designs, the proposed architecture can achieve high energy efficiency and accuracy for common SNN datasets. The robustness of the BSNN model against device non-idealities is further verified through experimental chip measurements. Finally, we discuss other opportunities to further enhance IMC architecture performance, including possible pipelining optimization, mapping strategy an","url":"https://doi.org/10.7302/8473","authors":["Wang, Xinxin"],"tags":["In-Memory Computing Architecture","Deep Neural Network Accelerator","Neuromorphic Computing","Non-Volatile Memory","Spiking Neural Network","Algorithm-Architecture Co-design","Electrical Engineering","Engineering"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.7302/8473","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.3929/ethz-c-000786445","name":"Neural networks for singular perturbations","source":"datacite","abstract":"We prove deep neural network (DNN for short) expressivity rate bounds for solution sets of a model class of singularly perturbed, elliptic two-point boundary value problems, in Sobolev norms, on the bounded interval (-1,1). We assume that the given source term and reaction coefficient are analytic in [-1,1]. The expression rate bounds in Sobolev norms in terms of the NN size are robust, i.e. uniform with respect to the singular perturbation parameter ε∈(0,1] for several classes of DNN architectures. In particular, ReLU NNs, spiking NNs, and tanh- and sigmoid-activated NNs. The latter activations can represent “exponential boundary layer solution features” explicitly, in the last hidden layer of the DNN, i.e. in a shallow subnetwork, and afford improved robust expression rate bounds in terms of the NN size. All DNN architectures allow robust exponential solution expression in so-called ‘energy’ as well as in ‘balanced’ Sobolev norms, for analytic input data.","url":"https://doi.org/10.3929/ethz-c-000786445","authors":["Opschoor, Joost A.A.","Schwab, Christopn","Xenophontos, Christos"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3929/ethz-c-000786445","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2410.08229","name":"Improvement of Spiking Neural Network with Bit Planes and Color Models","source":"datacite","abstract":"Spiking neural network (SNN) has emerged as a promising paradigm in computational neuroscience and artificial intelligence, offering advantages such as low energy consumption and small memory footprint. However, their practical adoption is constrained by several challenges, prominently among them being performance optimization. In this study, we present a novel approach to enhance the performance of SNN for images through a new coding method that exploits bit plane representation. Our proposed technique is designed to improve the accuracy of SNN without increasing model size. Also, we investigate the impacts of color models of the proposed coding process. Through extensive experimental validation, we demonstrate the effectiveness of our coding strategy in achieving performance gain across multiple datasets. To the best of our knowledge, this is the first research that considers bit planes and color models in the context of SNN. By leveraging the unique characteristics of bit planes, we hope to unlock new potentials in SNNs performance, potentially paving the way for more efficient and effective SNNs models in future researches and applications.","url":"https://doi.org/10.48550/arxiv.2410.08229","authors":["Luu, Nhan T.","Luu, Duong T.","Pham, Nam N.","Truong, Thang C."],"tags":["Computer Vision and Pattern Recognition (cs.CV)","Neural and Evolutionary Computing (cs.NE)","Image and Video Processing (eess.IV)","FOS: Computer and information sciences","FOS: Computer and information sciences","FOS: Electrical engineering, electronic engineering, information engineering","FOS: Electrical engineering, electronic engineering, information engineering"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.48550/arxiv.2410.08229","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2512.00427","name":"Hardware-Software Collaborative Computing of Photonic Spiking Reinforcement Learning for Robotic Continuous Control","source":"datacite","abstract":"Robotic continuous control tasks impose stringent demands on the energy efficiency and latency of computing architectures due to their high-dimensional state spaces and real-time interaction requirements. Conventional electronic computing platforms face computational bottlenecks, whereas the fusion of photonic computing and spiking reinforcement learning (RL) offers a promising alternative. Here, we propose a novel computing architecture based on photonic spiking RL, which integrates the Twin Delayed Deep Deterministic policy gradient (TD3) algorithm with spiking neural network (SNN). The proposed architecture employs an optical-electronic hybrid computing paradigm wherein a silicon photonic Mach-Zehnder interferometer (MZI) chip executes linear matrix computations, while nonlinear spiking activations are performed in the electronic domain. Experimental validation on the Pendulum-v1 and HalfCheetah-v2 benchmarks demonstrates the system capability for software-hardware co-inference, achieving a control policy reward of 5831 on HalfCheetah-v2, a 23.33% reduction in convergence steps, and an action deviation below 2.2%. Notably, this work represents the first application of a programmable MZI photonic computing chip to robotic continuous control tasks, attaining an energy efficiency of 1.39 TOPS/W and an ultralow computational latency of 120 ps. Such performance underscores the promise of photonic spiking RL for real-time decision-making in autonomous and industrial robotic systems.","url":"https://doi.org/10.48550/arxiv.2512.00427","authors":["Yu, Mengting","Xiang, Shuiying","Xie, Changjian","Chen, Yonghang","Zhao, Haowen","Guo, Xingxing","Zhang, Yahui","Han, Yanan","Hao, Yue"],"tags":["Robotics (cs.RO)","Optics (physics.optics)","FOS: Computer and information sciences","FOS: Computer and information sciences","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2512.00427","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2512.00419","name":"Hardware-aware Lightweight Photonic Spiking Neural Network for Pattern Classification","source":"datacite","abstract":"There exists a significant scale gap between photonic neural network integrated chips and neural networks, which hinders the deployment and application of photonic neural network. Here, we propose hardware-aware lightweight spiking neural networks (SNNs) architecture tailored to our photonic neuromorphic chips, and conducts hardware-software collaborative computing for solving patter classification tasks. Here, we employed a simplified Mach-Zehnder interferometer (MZI) mesh for performing linear computation, and 16-channel distributed feedback lasers with saturable absorber (DFB-SA) array for performing nonlinear spike activation. Both photonic neuromorphic chips based on the MZI mesh and DFB-SA array were designed, optimized and fabricated. Furthermore, we propose a lightweight spiking neural network (SNN) with discrete cosine transform to reduce input dimension and match the input/output ports number of the photonic neuromorphic chips. We demonstrated an end-to-end inference of an entire layer of the lightweight photonic SNN. The hardware-software collaborative inference accuracy is 90% and 80.5% for MNIST and Fashion-MNIST datasets, respectively. The energy efficiency is 1.39 TOPS/W for the MZI mesh, and is 987.65 GOPS/W for the DFB-SA array. The lightweight architecture and experimental demonstration address the challenge of scale mismatch between the photonic chip and SNN, paving the way for the hardware deployment of photonic SNNs.","url":"https://doi.org/10.48550/arxiv.2512.00419","authors":["Xiang, Shuiying","Zhang, Yahui","Shi, Shangxuan","Zhao, Haowen","Zheng, Dianzhuang","Guo, Xingxing","Han, Yanan","Tian, Ye","Zhang, Liyue","Shi, Yuechun","Hao, Yue"],"tags":["Optics (physics.optics)","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2512.00419","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2511.22108","name":"An energy-efficient spiking neural network with continuous learning for self-adaptive brain-machine interface","source":"datacite","abstract":"The number of simultaneously recorded neurons follows an exponentially increasing trend in implantable brain-machine interfaces (iBMIs). Integrating the neural decoder in the implant is an effective data compression method for future wireless iBMIs. However, the non-stationarity of the system makes the performance of the decoder unreliable. To avoid frequent retraining of the decoder and to ensure the safety and comfort of the iBMI user, continuous learning is essential for real-life applications. Since Deep Spiking Neural Networks (DSNNs) are being recognized as a promising approach for developing resource-efficient neural decoder, we propose continuous learning approaches with Reinforcement Learning (RL) algorithms adapted for DSNNs. Banditron and AGREL are chosen as the two candidate RL algorithms since they can be trained with limited computational resources, effectively addressing the non-stationary problem and fitting the energy constraints of implantable devices. To assess the effectiveness of the proposed methods, we conducted both open-loop and closed-loop experiments. The accuracy of open-loop experiments conducted with DSNN Banditron and DSNN AGREL remains stable over extended periods. Meanwhile, the time-to-target in the closed-loop experiment with perturbations, DSNN Banditron performed comparably to that of DSNN AGREL while achieving reductions of 98% in memory access usage and 99% in the requirements for multiply- and-accumulate (MAC) operations during training. Compared to previous continuous learning SNN decoders, DSNN Banditron requires 98% less computes making it a prime candidate for future wireless iBMI systems.","url":"https://doi.org/10.48550/arxiv.2511.22108","authors":["Biyan, Zhou","Basu, Arindam"],"tags":["Machine Learning (cs.LG)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2511.22108","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2511.21784","name":"Physics-Informed Spiking Neural Networks via Conservative Flux Quantization","source":"datacite","abstract":"Real-time, physically-consistent predictions on low-power edge devices is critical for the next generation embodied AI systems, yet it remains a major challenge. Physics-Informed Neural Networks (PINNs) combine data-driven learning with physics-based constraints to ensure the model's predictions are with underlying physical principles.However, PINNs are energy-intensive and struggle to strictly enforce physical conservation laws. Brain-inspired spiking neural networks (SNNs) have emerged as a promising solution for edge computing and real-time processing. However, naively converting PINNs to SNNs degrades physical fidelity and fails to address long-term generalization issues. To this end, this paper introduce a novel Physics-Informed Spiking Neural Network (PISNN) framework. Importantly, to ensure strict physical conservation, we design the Conservative Leaky Integrate-and-Fire (C-LIF) neuron, whose dynamics structurally guarantee local mass preservation. To achieve robust temporal generalization, we introduce a novel Conservative Flux Quantization (CFQ) strategy, which redefines neural spikes as discrete packets of physical flux. Our CFQ learns a time-invariant physical evolution operator, enabling the PISNN to become a general-purpose solver -- conservative-by-construction. Extensive experiments show that our PISNN excels on diverse benchmarks. For both the canonical 1D heat equation and the more challenging 2D Laplace's Equation, it accurately simulates the system dynamics while maintaining perfect mass conservation by design -- a feat that is challenging for conventional PINNs. This work establishes a robust framework for fusing the rigor of scientific computing with the efficiency of neuromorphic engineering, paving the way for complex, long-term, and energy-efficient physics predictions for intelligent systems.","url":"https://doi.org/10.48550/arxiv.2511.21784","authors":["Zhang, Chi","Wang, Lin"],"tags":["Machine Learning (cs.LG)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2511.21784","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.13140/rg.2.2.35962.35526","name":"Biophysical Modeling of Spiking Neural Network Neurons Based on System Dynamics: An RTL-Level Abstraction Approach","source":"datacite","abstract":"","url":"https://doi.org/10.13140/rg.2.2.35962.35526","authors":["Farokhi, Farzin"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.13140/rg.2.2.35962.35526","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2511.21337","name":"Hybrid SIFT-SNN for Efficient Anomaly Detection of Traffic Flow-Control Infrastructure","source":"datacite","abstract":"This paper presents the SIFT-SNN framework, a low-latency neuromorphic signal-processing pipeline for real-time detection of structural anomalies in transport infrastructure. The proposed approach integrates Scale-Invariant Feature Transform (SIFT) for spatial feature encoding with a latency-driven spike conversion layer and a Leaky Integrate-and-Fire (LIF) Spiking Neural Network (SNN) for classification. The Auckland Harbour Bridge dataset is recorded under various weather and lighting conditions, comprising 6,000 labelled frames that include both real and synthetically augmented unsafe cases. The presented system achieves a classification accuracy of 92.3% (+- 0.8%) with a per-frame inference time of 9.5 ms. Achieved sub-10 millisecond latency, combined with sparse spike activity (8.1%), enables real-time, low-power edge deployment. Unlike conventional CNN-based approaches, the hybrid SIFT-SNN pipeline explicitly preserves spatial feature grounding, enhances interpretability, supports transparent decision-making, and operates efficiently on embedded hardware. Although synthetic augmentation improved robustness, generalisation to unseen field conditions remains to be validated. The SIFT-SNN framework is validated through a working prototype deployed on a consumer-grade system and framed as a generalisable case study in structural safety monitoring for movable concrete barriers, which, as a traffic flow-control infrastructure, is deployed in over 20 cities worldwide.","url":"https://doi.org/10.48550/arxiv.2511.21337","authors":["Rathee, Munish","Bačić, Boris","Doborjeh, Maryam"],"tags":["Computer Vision and Pattern Recognition (cs.CV)","Artificial Intelligence (cs.AI)","FOS: Computer and information sciences","FOS: Computer and information sciences","68T45, 68T07, 68U10"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2511.21337","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2511.20175","name":"Realizing Fully-Integrated, Low-Power, Event-Based Pupil Tracking with Neuromorphic Hardware","source":"datacite","abstract":"Eye tracking is fundamental to numerous applications, yet achieving robust, high-frequency tracking with ultra-low power consumption remains challenging for wearable platforms. While event-based vision sensors offer microsecond resolution and sparse data streams, they have lacked fully integrated, low-power processing solutions capable of real-time inference. In this work, we present the first battery-powered, wearable pupil-center-tracking system with complete on-device integration, combining event-based sensing and neuromorphic processing on the commercially available Speck2f system-on-chip with lightweight coordinate decoding on a low-power microcontroller. Our solution features a novel uncertainty-quantifying spiking neural network with gated temporal decoding, optimized for strict memory and bandwidth constraints, complemented by systematic deployment mechanisms that bridge the reality gap. We validate our system on a new multi-user dataset and demonstrate a wearable prototype with dual neuromorphic devices achieving robust binocular pupil tracking at 100 Hz with an average power consumption below 5 mW per eye. Our work demonstrates that end-to-end neuromorphic computing enables practical, always-on eye tracking for next-generation energy-efficient wearable systems.","url":"https://doi.org/10.48550/arxiv.2511.20175","authors":["Paredes-Valles, Federico","Miyatani, Yoshitaka","Scheper, Kirk Y. W."],"tags":["Computer Vision and Pattern Recognition (cs.CV)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2511.20175","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.17605/osf.io/7cdku","name":"The role of network theta and alpha oscillations in sustained and selective attention in humans","source":"datacite","abstract":"Attention is the ability to preferentially orient limited perceptual processing resources towards a specific information stream when automatic processes are insufficient (Shiffrin &amp; Schneider, 1977). Attention has been investigated broadly within two task paradigms. Sustained and selective attention are typically investigated in different paradigms and recruit distinct neural processes. First, task paradigms that investigate “sustained attention” require that participant resist distraction and stay on task for a long period of time. With a sufficiently demanded task, such as a divided attention paradigm with an infrequent stimulus that is difficult to detect, a greater level of sustained attention is required (Sarter, Givens, &amp; Bruno, 2001). Animal work investigating the neural basis of sustained attention has utilized the 5-choice serial reaction time task (5CSRTT) (Robbins, 2002). In the 5CSRTT, a visual stimulus can be presented in one of five locations during a delay period of variable time. By presenting the visual stimulus only briefly, greater levels of sustained attention are required for successful detection . This research has uncovered a pivotal role for theta oscillations (4-8 Hz) in sustained attention (Helfrich et al., 2018; Sellers et al., 2016; Yu et al., 2018). Second, task paradigms that investigate “selective attention” require that participants preferentially attend to one information stream over another information stream (Treisman, 1964). For example, a pre-cueing visuospatial task presents a cue that provides information about the probable location of an upcoming stimulus. With a predictive cue, attention is oriented selectively to a particular location and behavioral performance for stimuli in that location is increased relative to trials without a predictive pre-cue. Experiments studying pre-cueing have found an increase in alpha oscillations (8-12 Hz) in the regions of the brain that process information for the unlikely location (Sauseng et al., 2009; Wallis, Stokes, Cousijn, Woolrich, &amp; Nobre, 2015). Thus, research into sustained attention and selective attention have found distinct neural oscillations. Using a novel task paradigm that incorporates a spatial pre-cue into the 5CSRTT, we will dissociate sustained attention and selective attention to test the hypothesis that frontal-midline theta oscillations are increased as a function of sustained attention, and posterior alpha oscillations are increased as a function of selective attention. In addition, we will administer a version of the task that approximates the 5-choice serial reaction time task used in animal experiments. Currently, the most recent human analogues have taken the form of touchscreen variant administered as part of the CANTAB® (Cognitive Assessment Software; Cambridge Cognition, 2019) which compares 1 vs 5 locations and an incentivized version which uses monetary rewards to induce impulsive responses (Nord et al., 2019; Worbe et al, 2014). However, the CANTAB variant does not control for the need to survey multiple target locations, thus confounding sustained attention with divided attention; and the incentivized variant is targeted toward a different psychological construct. Therefore here, participants will perform a reach using a mouse to dissociate the impact of sustained attention on reaction time, motor accuracy, response time, and frontal theta oscillations. This experiment will control for both number of locations and perceptual difficulty to disambiguate whether frontal theta oscillations are responsive to sustained or divided attention. The use of a movement tracking paradigm will maximize direct comparability between human and animal 5CSRTT data. Finally, sustained attention and selective attention are impaired with psychiatric illness. Participants with greater levels of anxiety have been found to have increased frontal-midline theta in cognitive control paradigms (Cavanagh &amp; Shackman, 2015). Here, we a","url":"https://doi.org/10.17605/osf.io/7cdku","authors":["Riddle, Justin","McFerren, Amber","Walker, Christopher","Frohlich, Flavio"],"tags":["Psychiatry and Psychology","Medicine and Health Sciences","Life Sciences","Neuroscience and Neurobiology","Social and Behavioral Sciences","Psychology","FOS: Psychology","Psychological Phenomena and Processes"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2020","doi":"10.17605/osf.io/7cdku","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2511.17563","name":"Dynamic Weight Adaptation in Spiking Neural Networks Inspired by Biological Homeostasis","source":"datacite","abstract":"Homeostatic mechanisms play a crucial role in maintaining optimal functionality within the neural circuits of the brain. By regulating physiological and biochemical processes, these mechanisms ensure the stability of an organism's internal environment, enabling it to better adapt to external changes. Among these mechanisms, the Bienenstock, Cooper, and Munro (BCM) theory has been extensively studied as a key principle for maintaining the balance of synaptic strengths in biological systems. Despite the extensive development of spiking neural networks (SNNs) as a model for bionic neural networks, no prior work in the machine learning community has integrated biologically plausible BCM formulations into SNNs to provide homeostasis. In this study, we propose a Dynamic Weight Adaptation Mechanism (DWAM) for SNNs, inspired by the BCM theory. DWAM can be integrated into the host SNN, dynamically adjusting network weights in real time to regulate neuronal activity, providing homeostasis to the host SNN without any fine-tuning. We validated our method through dynamic obstacle avoidance and continuous control tasks under both normal and specifically designed degraded conditions. Experimental results demonstrate that DWAM not only enhances the performance of SNNs without existing homeostatic mechanisms under various degraded conditions but also further improves the performance of SNNs that already incorporate homeostatic mechanisms.","url":"https://doi.org/10.48550/arxiv.2511.17563","authors":["Zhou, Yunduo","Dong, Bo","Li, Chang","Wang, Yuanchen","Yin, Xuefeng","Wang, Yang","Yang, Xin"],"tags":["Neural and Evolutionary Computing (cs.NE)","Artificial Intelligence (cs.AI)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2511.17563","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17694682","name":"Automated Synaptic Pruning and Resource Allocation in Spiking Neural Networks for Edge-Based Neuromorphic Vision Processing","source":"datacite","abstract":"**Abstract:** This paper introduces a novel framework for dynamically optimizing Spiking Neural Networks (SNNs) deployed on edge devices for real-time visual data analysis. Existing neuromorphic architectures face significant challenges in resource constraint environments – particularly balancing accuracy with power efficiency and latency. Our approach, termed \"Adaptive Pruning and Temporal Resource Allocation\" (APTRA), leverages a reinforcement learning (RL) agent to autonomously prune synapses and dynamically allocate computational resources across network layers based on the instantaneous information content of incoming visual data. This leads to significantly improved performance (up to 35% reduction in latency and 20% increase in accuracy) compared to static pruning techniques while maintaining low power consumption. Furthermore, the proposed system is completely commercially viable using existing manufacturing processes and software toolchains.","url":"https://doi.org/10.5281/zenodo.17694682","authors":["Freederia AI Researcher"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17694682","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17616488","name":"Enhanced Spiking Neural Network Inference via Dynamic Reservoir Reconfiguration and Adaptive Threshold Modulation for Time-Series Forecasting","source":"datacite","abstract":"**Abstract:** This paper introduces a novel approach to Spiking Neural Network (SNN) inference for time-series forecasting, significantly improving prediction accuracy and efficiency. Our methodology leverages dynamic reservoir reconfiguration, adapting the recurrent connections within the reservoir network based on real-time input characteristics, combined with adaptive threshold modulation of spiking neurons. This dynamic adjustment optimizes the network's ability to capture intricate temporal dependencies, demonstrably exceeding the performance of static reservoir SNNs. The proposed framework offers a practical and commercially viable solution for high-precision time-series forecasting across various industrial applications.","url":"https://doi.org/10.5281/zenodo.17616488","authors":["Freederia AI Researcher"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17616488","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17684842","name":"🤖 THE GUARDIAN HUMANOID — DEEP DIVE       Executive Summary: The Embodiment of the CollectiveOS","source":"datacite","abstract":"🤖 THE GUARDIAN HUMANOID — DEEP DIVE (Strategic + Safe) Executive Summary: The Embodiment of the CollectiveOS The transition of the CollectiveOS from a purely digital governance architecture into the physical domain represents a watershed moment in the trajectory of the \"Anti-Scarcity Stack.\" The Guardian Humanoid concept is not merely an exercise in robotics; it is the physical manifestation of the CollectiveOS’s core philosophy: that intelligence without stewardship is dangerous, and that capability without governance is a liability. This report outlines the Phase 2 strategic deepening of the Guardian design, moving beyond conceptual sketches into a rigid, engineering-grade specification that is prepared for the disparate and demanding theaters of the Congolese rainforest, the high-precision laboratories of Switzerland, and the aging social infrastructure of Japan. The Guardian is designed to operate as the primary \"embodied node\" within the Village Node ecosystem. Unlike contemporary market leaders—such as Tesla’s Optimus or Boston Dynamics’ Atlas, which prioritize dynamic athleticism or generalized industrial labor—the Guardian is engineered fundamentally around the principles of safety, stewardship, and auditability. It is not a weapon; it is not a biological simulacrum designed to deceive; it is a highly advanced infrastructure tool wrapped in a lattice of immutable governance. At its core, the Guardian leverages a unique convergence of technologies: the sustainable, impact-resistant properties of mycelium composites for its chassis; the inherent safety of Series Elastic Actuators (SEAs) for its musculature; and the novel \"Living Fibonacci Engine\" (LFE) for its control laws. These physical attributes are bound together by the CollectiveOS governance stack—specifically the \"GATA PRIME\" and \"Proof Vault\" layers—which ensures that every motion is legally traceable and ethically bounded. This report details the technical specifications, operational workflows, and strategic integrations that define the Guardian, establishing it as the world’s first \"Sovereign Safe Agent.\" 1. Purpose of the Guardian: Strategic Alignment and Mission Profile The strategic purpose of the Guardian is to solve the \"Last Mile\" problem of the Anti-Scarcity Stack. While the CollectiveOS can digitally optimize water distribution or crop yields, it cannot physically turn a wrench, lift a solar panel, or guide a human through a repair process. The Guardian bridges this gap, serving as a multi-mission platform that adapts its behavior to the geopolitical and environmental realities of its deployment zone. 1.1. The Humanitarian Engineer (Congo Theater) In the Congo deployment plan, the Guardian serves as the primary enabler for the \"Village Node\" infrastructure.1 The environment is hostile to traditional electronics—high humidity, dust, and heat—yet critical for the humanitarian mission of water and food security. Here, the Guardian operates as a Field Engineer and Caretaker. Its primary mandate is the assembly and maintenance of the Village Node components: the Aqua Pillar water generation systems, the Food Cube upcyclers, and the FarmOS sensor arrays.1 The robot must possess the physical strength to lift filtration columns and the dexterity to replace gaskets or tighten flanges. Crucially, it also serves as a \"Presence of Stability.\" In remote areas where technical expertise is scarce, the Guardian acts as a repository of knowledge, capable of executing repairs autonomously or guiding local humans via the Pan-African Translator (PAT) module. It models safety and governance, demonstrating that the technology is there to serve the community, not to extract from it. 1.2. The High-Fidelity Inspector (Swiss Theater) The Swiss deployment represents the polar opposite operational environment: highly regulated, structurally dense, and demanding of absolute precision. Here, the Guardian operates as a Safety Auditor. Its mission is to inspect critical infrastructu","url":"https://doi.org/10.5281/zenodo.17684842","authors":["Brewer, Mark Anthony"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17684842","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17684843","name":"🤖 THE GUARDIAN HUMANOID — DEEP DIVE       Executive Summary: The Embodiment of the CollectiveOS","source":"datacite","abstract":"🤖 THE GUARDIAN HUMANOID — DEEP DIVE (Strategic + Safe) Executive Summary: The Embodiment of the CollectiveOS The transition of the CollectiveOS from a purely digital governance architecture into the physical domain represents a watershed moment in the trajectory of the \"Anti-Scarcity Stack.\" The Guardian Humanoid concept is not merely an exercise in robotics; it is the physical manifestation of the CollectiveOS’s core philosophy: that intelligence without stewardship is dangerous, and that capability without governance is a liability. This report outlines the Phase 2 strategic deepening of the Guardian design, moving beyond conceptual sketches into a rigid, engineering-grade specification that is prepared for the disparate and demanding theaters of the Congolese rainforest, the high-precision laboratories of Switzerland, and the aging social infrastructure of Japan. The Guardian is designed to operate as the primary \"embodied node\" within the Village Node ecosystem. Unlike contemporary market leaders—such as Tesla’s Optimus or Boston Dynamics’ Atlas, which prioritize dynamic athleticism or generalized industrial labor—the Guardian is engineered fundamentally around the principles of safety, stewardship, and auditability. It is not a weapon; it is not a biological simulacrum designed to deceive; it is a highly advanced infrastructure tool wrapped in a lattice of immutable governance. At its core, the Guardian leverages a unique convergence of technologies: the sustainable, impact-resistant properties of mycelium composites for its chassis; the inherent safety of Series Elastic Actuators (SEAs) for its musculature; and the novel \"Living Fibonacci Engine\" (LFE) for its control laws. These physical attributes are bound together by the CollectiveOS governance stack—specifically the \"GATA PRIME\" and \"Proof Vault\" layers—which ensures that every motion is legally traceable and ethically bounded. This report details the technical specifications, operational workflows, and strategic integrations that define the Guardian, establishing it as the world’s first \"Sovereign Safe Agent.\" 1. Purpose of the Guardian: Strategic Alignment and Mission Profile The strategic purpose of the Guardian is to solve the \"Last Mile\" problem of the Anti-Scarcity Stack. While the CollectiveOS can digitally optimize water distribution or crop yields, it cannot physically turn a wrench, lift a solar panel, or guide a human through a repair process. The Guardian bridges this gap, serving as a multi-mission platform that adapts its behavior to the geopolitical and environmental realities of its deployment zone. 1.1. The Humanitarian Engineer (Congo Theater) In the Congo deployment plan, the Guardian serves as the primary enabler for the \"Village Node\" infrastructure.1 The environment is hostile to traditional electronics—high humidity, dust, and heat—yet critical for the humanitarian mission of water and food security. Here, the Guardian operates as a Field Engineer and Caretaker. Its primary mandate is the assembly and maintenance of the Village Node components: the Aqua Pillar water generation systems, the Food Cube upcyclers, and the FarmOS sensor arrays.1 The robot must possess the physical strength to lift filtration columns and the dexterity to replace gaskets or tighten flanges. Crucially, it also serves as a \"Presence of Stability.\" In remote areas where technical expertise is scarce, the Guardian acts as a repository of knowledge, capable of executing repairs autonomously or guiding local humans via the Pan-African Translator (PAT) module. It models safety and governance, demonstrating that the technology is there to serve the community, not to extract from it. 1.2. The High-Fidelity Inspector (Swiss Theater) The Swiss deployment represents the polar opposite operational environment: highly regulated, structurally dense, and demanding of absolute precision. Here, the Guardian operates as a Safety Auditor. Its mission is to inspect critical infrastructu","url":"https://doi.org/10.5281/zenodo.17684843","authors":["Brewer, Mark Anthony"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17684843","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17679941","name":"Quantum-Enhanced Spiking Neural Network on FPGA for Real-Time Industrial Anomaly Detection","source":"datacite","abstract":"This paper introduces QESNN, a complete neuromorphic hardware–software pipeline that combines a novel quantum-inspired Spike-Timing-Dependent Plasticity (Q-STDP) learning rule with a synthesizable FPGA implementation to deliver practical, low-cost edge anomaly detection for industrial motors. Q-STDP uses persistent binary temporal traces to capture multi-spike correlations over extended windows, enabling richer temporal learning than classical pairwise STDP while remaining efficient and directly implementable in digital logic. We demonstrate a full end-to-end system: preprocessing converts IMAD sensor recordings to spike trains, training occurs offline, and a UART streaming pipeline performs real-time inference on a Sipeed Tang Nano 4K (2,124 LUTs used, ~46% utilization). Benchmarks following SNABSuite and NeuroBench report 92.12% classification accuracy, 4.10 ms mean latency, 265 mW power consumption, 246.3 samples/s throughput, perfect precision (100%), 0.869 F1 score, and 0.0014 mJ per inference — showing competitive performance with very low energy and hardware cost. QESNN demonstrates that event-driven spiking models with hardware-friendly learning rules can be practical for battery-powered predictive maintenance and other industrial IoT applications. The paper includes Verilog synthesis details, resource utilization tables, ablation studies quantifying the Q-STDP contribution, and discussion of limitations and future work (scalability, non-volatile weight storage, adaptive thresholds.","url":"https://doi.org/10.5281/zenodo.17679941","authors":["Deenathayalan A","Tanushree RG","Keertana P"],"tags":["neuromorphic computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17679941","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.82419/234","name":"RespiroDynamics Unveiled: A Groundbreaking Multi-Modal Deep Learning and Spiking Neural Network Framework for Revolutionizing Non-Invasive Lung Health Assessment","source":"datacite","abstract":"This thesis investigates non-invasive lung health assessment using deep learning and Spiking Neural Networks (SNNs) to analyze thermal and RGB video data. Traditional respiratory diagnostics often require direct physical interaction, which can cause patient discomfort. This research aims to develop a non-contact, robust, precise, and energy-efficient lung health model using thermal or mobile video recordings and personal data, eliminating the need for traditional spirometry. The study collected a unique dataset from 60 male participants of various demographics and health backgrounds, including thermal and RGB videos, heart rate, ECG data, and detailed metadata. The methodology involved creating and testing various neural network models, including Convolutional Neural Networks (CNNs) for classification and regression tasks, and SNNs that process temporal respiratory patterns. Innovations include data augmentation, the Adaptive Precision-Tuned Regression (APTR) loss function, multimodal data integration, attention mechanisms, and ensemble learning to enhance model performance. Results revealed high efficacy in both classification and regression tasks. In the FVC Normal vs. Abnormal classification, the thermal model achieved a perfect score of 100%, and the RGB model scored 99.7%. In the Peak Expiratory Flow (PEF) classification, the thermal model outperformed with 97.14% accuracy compared to 96% for RGB. SNNs showed an accuracy improvement from 91.99% to 99.5% after data aggregation for thermal videos, and from 81.17% to 99% for RGB. In regression tasks, ensemble learning significantly boosted performance; the thermal model reported a Relative Root Mean Square Error of 0.11, a Relative Mean Absolute Error of 0.09, and a Pearson Correlation of 0.93. Comparatively, the RGB model showed poorer performance with respective values of 0.26, 0.21, and 0.79. These findings highlight the superior performance of thermal imaging over RGB in detecting respiratory patterns and the beneficial impact of integrating metadata into the models, setting new standards in the field.","url":"https://doi.org/10.82419/234","authors":["Sharshar, Ahmed"],"tags":["Computer Vision"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.82419/234","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.82419/84","name":"Self-Ensemble as Defense for Event-Based Adversarial Attack against Spiking Neural Networks","source":"datacite","abstract":"\"The brain is a world consisting of a number of unexplored continents and great stretches of unknown territory.” Santiago Ram´on y Cajal (1852–1934). In the rapidly evolving landscape of artificial intelligence, Spiking Neural Networks (SNNs) have emerged as a promising approach for achieving efficient realtime processing in novel applications such as autonomous driving and robotics. Known as “the third generation of neural networks” in the literature, SNNs mimic the human brain by utilizing spiking patterns to encode and process information, reflecting the biological neural activities where neurons communicate via electrical impulses. By leveraging the temporal dynamics of neural spikes, SNNs are capable of performing complex computations with remarkable energy efficiency, making them particularly wellsuited for edge computing environments where computational resources are at a premium. These settings demand not only high performance but also robust security measures to protect against potential threats. Similar to artificial neural networks (ANNs), SNNs are not immune to adversarial attacks, which can manipulate input data within certain range that is imperceptible to human, to deceive models into making incorrect predictions. Traditional defense mechanisms often require additional raw training data, adversarial training, or modifications to the network architecture, complicating their implementation. Therefore, there is a critical need for innovative defense strategies that can enhance the robustness of SNNs without imposing significant overhead. This study introduces a novel “selfensemble” approach that leverages multiple latency settings during the inference phase to defend against eventbased adversarial attacks on SNNs. The method begins with training a single SNN model from an event dataset captured by dynamic vision sensors (DVS), which generate asynchronous events in response to changes in brightness. The training set is built from multiple rather than one frame aggregator, thanks to the nice property of SNNs that are compatible with different latencies given the same weights of the network. During inference, the event data is converted into frame data using various temporal intervals, again, resulting in multiple sets of frames with different numbers of frames per unit time. The trained SNN processes each set independently, producing multiple outputs. This selfensemble approach aggregates these diverse outputs, effectively mitigating the impact of any single erroneous prediction caused by the eventbased attack. Since current adversarial perturbations only target at one particular frame representation while leaving others relatively unharmed, the ensemble method ensures overall system robustness. A key advantage of this technique is its simplicity and efficiencyit does not require additional event data or adversarial samples for enhanced training. Instead, it exploits the inherent flexibility of SNNs to handle multiple latencies, enhancing compatibility without compromising performance. The method naturally aligns with the asynchronous processing capabilities of SNNs, ensuring seamless integration. Empirical results demonstrate the effectiveness of our selfensemble approach without performance loss. Existing eventbased adversarial attack techniques, which still target specific frame numbers, fail to disrupt the network’s ability to accurately interpret the event stream. Even when one output is significantly affected, the majority consensus among the ensemble remains accurate, thereby maintaining overall system integrity. This resilience underscores the potential of our method as a practical defense mechanism against sophisticated adversarial threats. By exploiting the unique characteristics of SNNs and their ability to process data at multiple latencies, our work paves the way for more robust neuromorphic computing systems. Future directions include exploring scalability across different datasets and application domai","url":"https://doi.org/10.82419/84","authors":["Li, Xinyu"],"tags":["Machine Learning"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.82419/84","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2507.08490","name":"Neuromorphic Split Computing via Optical Inter-Satellite Links","source":"datacite","abstract":"We present a neuromorphic split-computing framework for energy-efficient low-latency inference over optical inter-satellite links. The system partitions a spiking neural network (SNN) between edge and core nodes. To transmit sparse spiking features efficiently, we introduce a lossless channel-block-sparse event representation that exploits inter- and intra-channel sparsity. We employ hierarchical error protection using multi-level forward error correction and cyclic redundancy checks to ensure reliable communication without retransmission. The framework uses end-to-end training with sparsity and clustering regularizers, combined with channel-aware stochastic masking to optimize feature compression and channel robustness jointly. In a proof-of-concept implementation on remote sensing imagery, the framework achieves over $10 \\times$ reduction in both computational energy and transmission load compared to conventional dense split systems, with less than 1% accuracy loss. The proposed approach also outperforms address-event-based split SNNs by $3.7 \\times$ in transmission efficiency and shows superior resilience to optical pointing jitter.","url":"https://doi.org/10.48550/arxiv.2507.08490","authors":["Song, Zihang","Popovski, Petar"],"tags":["Image and Video Processing (eess.IV)","FOS: Electrical engineering, electronic engineering, information engineering","FOS: Electrical engineering, electronic engineering, information engineering"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2507.08490","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2506.11286","name":"Mapping and Scheduling Spiking Neural Networks On Segmented Ladder Bus Architectures","source":"datacite","abstract":"Large-scale neuromorphic architectures consist of computing tiles that communicate spikes using a shared interconnect. The communication patterns in such systems are inherently sparse, asynchronous, and localized due to the spiking nature of neural events, characterized by temporal sparsity with occasional bursts of traffic. These characteristics necessitate interconnects optimized for handling high-activity bursts while consuming minimal power during idle periods. Dynamic segmented bus has been proposed a promising interconnect for its simplicity, scalability and low power consumption. However, deploying spiking neural network applications on such buses presents challenges, including substantial inter-cluster traffic, which can lead to network congestion, spike loss, and unnecessary energy expenditure. In this paper, we propose a three-step process to deploy SNN applications on dynamic segmented buses aiming to reduce spike loss and conserve energy. Firstly, we formulate optimization heuristics to mitigate spike loss and energy consumption based on application connectivity. Secondly, we analyze the application traffic to determine spike schedules that minimize traffic flooding. Lastly, we propose a routing algorithm to minimize spike traffic path crossings. We evaluate our approach using a cycle-accurate network simulator. The simulation results show that our algorithms can eliminate spike loss while keeping energy consumption significantly lower compared to conventional NoCs.","url":"https://doi.org/10.48550/arxiv.2506.11286","authors":["Huynh, Phu Khanh","Catthoor, Francky","Das, Anup"],"tags":["Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2506.11286","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2511.16060","name":"Neuromorphic Astronomy: An End-to-End SNN Pipeline for RFI Detection Hardware","source":"datacite","abstract":"Imminent radio telescope observatories provide massive data rates making deep learning based processing appealing while simultaneously demanding real-time performance at low-energy; prohibiting the use of many artificial neural network based approaches. We begin tackling the scientifically existential challenge of Radio Frequency Interference (RFI) detection by deploying deep Spiking Neural Networks (SNNs) on resource-constrained neuromorphic hardware. Our approach partitions large, pre-trained networks onto SynSense Xylo hardware using maximal splitting, a novel greedy algorithm. We validate this pipeline with on-chip power measurements, achieving instrument-scaled inference at 100mW. While our full-scale SNN achieves state-of-the-art accuracy among SNN baselines, our experiments reveal a more important insight that a smaller un-partitioned model significantly outperforms larger, split models. This finding highlights that hardware co-design is paramount for optimal performance. Our work thus provides a practical deployment blueprint, a key insight into the challenges of model scaling, and reinforces radio astronomy as a demanding yet ideal domain for advancing applied neuromorphic computing.","url":"https://doi.org/10.48550/arxiv.2511.16060","authors":["Pritchard, Nicholas J.","Wicenec, Andreas","Dodson, Richard","Bennamoun, Mohammed","Muir, Dylan R."],"tags":["Neural and Evolutionary Computing (cs.NE)","Instrumentation and Methods for Astrophysics (astro-ph.IM)","FOS: Computer and information sciences","FOS: Computer and information sciences","FOS: Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2511.16060","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.60893/figshare.apl.c.8115023","name":"<strong>Biased field free skyrmion based neural network and reconfigurable logic operations</strong>","source":"datacite","abstract":"Spin-texture based devices have recently gained significant attention for their potential in designing and developing logic circuits and neural networks, leading us to explore beyond conventional computing paradigms. Among various spin textures, magnetic skyrmions are found to be promising candidate due to their topological stability, nanoscale size, and low-current-driven dynamics. However, the practical realization of skyrmion-based devices remains challenging due to the reliance on external magnetic fields or electrostatic gating, which complicates device architecture and limits on-chip integration. In this study, we investigate spin current driven, field-free skyrmion-induced spiking dynamics and logic operations in bilayer nanotrack consisting of a ferromagnetic (FM) layer interfaced with a heavy metal (HM). We first investigate the nucleation dynamics of skyrmions and identify two distinct states: stable configuration and dynamical state exhibiting breathing mode oscillations. These oscillations give rise to regular periodic auto-spiking behavior in dynamical skyrmion with tunable spiking frequency through applied spin polarized current. Exploiting this behavior, we designed skyrmion based spiking neural network (SNN) demonstrating classification accuracy of 87.50% on the Modified National Institute of Standards and Testing (MNIST) handwritten digit dataset. Furthermore, we have also examined the dynamics of stable skyrmion in a device with stepped geometry which introduces a potential barrier and enables both AND &amp; OR logic operations within the same device utilizing spin orbit torque (SOT). This dual functionality of skyrmion based device enabling both neuromorphic computing and versatile logic operations within a single device offers a promising pathway toward highly efficient, field-free spintronic devices.","url":"https://doi.org/10.60893/figshare.apl.c.8115023","authors":["Verma, Shubhi","ojha, Animesh","Medwal, Rohit","Gupta, Surbhi","Khosla, Aman"],"tags":["Physical sciences","FOS: Physical sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.60893/figshare.apl.c.8115023","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2404.10210","name":"MK-SGN: A Spiking Graph Convolutional Network with Multimodal Fusion and Knowledge Distillation for Skeleton-based Action Recognition","source":"datacite","abstract":"In recent years, multimodal Graph Convolutional Networks (GCNs) have achieved remarkable performance in skeleton-based action recognition. The reliance on high-energy-consuming continuous floating-point operations inherent in GCN-based methods poses significant challenges for deployment in energy-constrained, battery-powered edge devices. To address these limitations, MK-SGN, a Spiking Graph Convolutional Network with Multimodal Fusion and Knowledge Distillation, is proposed to leverage the energy efficiency of Spiking Neural Networks (SNNs) for skeleton-based action recognition for the first time. By integrating the energy-saving properties of SNNs with the graph representation capabilities of GCNs, MK-SGN achieves significant reductions in energy consumption while maintaining competitive recognition accuracy. Firstly, we formulate a Spiking Multimodal Fusion (SMF) module to effectively fuse multimodal skeleton data represented as spike-form features. Secondly, we propose the Self-Attention Spiking Graph Convolution (SA-SGC) module and the Spiking Temporal Convolution (STC) module, to capture spatial relationships and temporal dynamics of spike-form features. Finally, we propose an integrated knowledge distillation strategy to transfer information from the multimodal GCN to the SGN, incorporating both intermediate-layer distillation and soft-label distillation to enhance the performance of the SGN. MK-SGN exhibits substantial advantages, surpassing state-of-the-art GCN frameworks in energy efficiency and outperforming state-of-the-art SNN frameworks in recognition accuracy. The proposed method achieves a remarkable reduction in energy consumption, exceeding 98\\% compared to conventional GCN-based approaches. This research establishes a robust baseline for developing high-performance, energy-efficient SNN-based models for skeleton-based action recognition","url":"https://doi.org/10.48550/arxiv.2404.10210","authors":["Zheng, Naichuan","Xia, Hailun","Liang, Zeyu","Du, Yuchen"],"tags":["Computer Vision and Pattern Recognition (cs.CV)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.48550/arxiv.2404.10210","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2511.15296","name":"Detection of spiking motifs of arbitrary length in neural activity using bounded synaptic delays","source":"datacite","abstract":"In the context of spiking neural networks, temporal coding of signals is increasingly preferred over the rate coding hypothesis due to its advantages in processing speed and energy efficiency. In temporal coding, synaptic delays are crucial for processing signals with precise spike timings, known as spiking motifs. Synaptic delays are however bounded in the brain and can thus be shorter than the duration of a motif. This prevents the use of motif recognition methods that consist of setting heterogeneous delays to synchronize the input spikes on a single output neuron acting as a coincidence detector. To address this issue, we developed a method to detect motifs of arbitrary length using a sequence of output neurons connected to input neurons by bounded synaptic delays. Each output neuron is associated with a sub-motif of bounded duration. A motif is recognized if all sub-motifs are sequentially detected by the output neurons. We simulated this network using leaky integrate-and-fire neurons and tested it on the Spiking Heidelberg Digits (SHD) database, that is, on audio data converted to spikes via a cochlear model, as well as on random simultaneous motifs. The results demonstrate that the network can effectively recognize motifs of arbitrary length extracted from the SHD database. Our method features a correct detection rate of about 60% in presence of ten simultaneous motifs from the SHD dataset and up to 80% for five motifs, showing the robustness of the network to noise. Results on random overlapping patterns show that the recognition of a single motif overlapping with other motifs is most effective for a large number of input neurons and sparser motifs. Our method provides a foundation for more general models for the storage and retrieval of neural information of arbitrary temporal lengths.","url":"https://doi.org/10.48550/arxiv.2511.15296","authors":["Kronland-Martinet, Thomas","Viollet, Stéphane","Perrinet, Laurent U"],"tags":["Neurons and Cognition (q-bio.NC)","FOS: Biological sciences","FOS: Biological sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2511.15296","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2511.12199","name":"MPD-SGR: Robust Spiking Neural Networks with Membrane Potential Distribution-Driven Surrogate Gradient Regularization","source":"datacite","abstract":"The surrogate gradient (SG) method has shown significant promise in enhancing the performance of deep spiking neural networks (SNNs), but it also introduces vulnerabilities to adversarial attacks. Although spike coding strategies and neural dynamics parameters have been extensively studied for their impact on robustness, the critical role of gradient magnitude, which reflects the model's sensitivity to input perturbations, remains underexplored. In SNNs, the gradient magnitude is primarily determined by the interaction between the membrane potential distribution (MPD) and the SG function. In this study, we investigate the relationship between the MPD and SG and their implications for improving the robustness of SNNs. Our theoretical analysis reveals that reducing the proportion of membrane potentials lying within the gradient-available range of the SG function effectively mitigates the sensitivity of SNNs to input perturbations. Building upon this insight, we propose a novel MPD-driven surrogate gradient regularization (MPD-SGR) method, which enhances robustness by explicitly regularizing the MPD based on its interaction with the SG function. Extensive experiments across multiple image classification benchmarks and diverse network architectures confirm that the MPD-SGR method significantly enhances the resilience of SNNs to adversarial perturbations and exhibits strong generalizability across diverse network configurations, SG functions, and spike encoding schemes.","url":"https://doi.org/10.48550/arxiv.2511.12199","authors":["Jiang, Runhao","Jiang, Chengzhi","Yan, Rui","Tang, Huajin"],"tags":["Machine Learning (cs.LG)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2511.12199","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5075/epfl-thesis-10637","name":"Supervised learning and inference of spiking neural networks with temporal coding","source":"datacite","abstract":"The way biological brains carry out advanced yet extremely energy efficient signal processing remains both fascinating and unintelligible. It is known however that at least some areas of the brain perform fast and low-cost processing relying only on a small number of temporally encoded spikes. This thesis investigates supervised learning and inference of spiking neural networks (SNNs) with sparse temporally encoded communication. We explore different setups and compare the performance of our SNNs with that of the standard artificial neural networks (ANNs) on data classification tasks. In the first setup we consider: A family of exact mappings between a single-spike network and a ReLU network. We dismiss training for a moment and analyse deep SNNs with time-to-first-spike (TTFS) encoding. There exist a neural dynamics and a set of parameter constraints which guarantee an approximation-free mapping (conversion) from a ReLU network to an SNN with TTFS encoding. We find that a pretrained deep ReLU network can be replaced with our deep SNN without any performance loss on large-scale image classification tasks (CIFAR100 and PLACES365). However, we hypothesise that in many cases there is a need for training or fine-tuning deep spiking neural network for the specific problem at hand. In the second setup we consider: Training a deep single-spike network using a family of exact mappings from a ReLU network. We thoroughly investigate the reasons for unsuccessful training of deep SNNs with TTFS encoding and uncover an instance of the vanishing-and-exploding gradient problem. We find that a particular exact mapping solves this problem and yields an SNN with learning trajectories equivalent to those of ReLU network on large image classification tasks (CIFAR100 and PLACES365). Training is crucial for fine-tuning SNNs for the specific device properties such as low latency, the amount of noise or quantization. We hope that this study will eventually lead to an SNN hardware implementation offering a low-power inference with ANN performance on data classification tasks.","url":"https://doi.org/10.5075/epfl-thesis-10637","authors":["Stanojevic, Ana"],"tags":["spiking neural network","temporal encoding","sparse communication","efficient data classification","multiplication-free inference","backpropagation training","time-to-first-spike encoding","deep ReLU network conversion"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.5075/epfl-thesis-10637","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17638161","name":"Memristor-Based Digital Twin of Mycelium for Unconventional Computing","source":"datacite","abstract":"Fungal mycelium is widespread in nature and stands out among Engineered Living Materials (ELMs). When stimulated, it shows intricate electrical signaling activity that with the help of digital twins can be used for sustainable computing. For its further study, its emulation with novel hardware is important. Because of their special state-transition properties and non-volatility, memristors show promise for creating an effective, low-power replica of mycelium. This paper focuses on how RRAMs can be utilized to form a flexible spiking reservoir network as an alternative of common spiking neural networks (SNNs). It serves as a novel computational primitive that mimic the adaptive, self-organizing characteristics of mycelium, capable for unconventional computing.","url":"https://doi.org/10.5281/zenodo.17638161","authors":["Chatzipaschalis, Ioannis","Tompris, Ioannis","Kleitsiotis, Georgios","Chatzinikolaou, Theodoros Panagiotis","Fyrigos, Iosif-Angelos","Calomarde, Antonio","Sirakoulis, Georgios","Rubio, Antonio"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17638161","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17638162","name":"Memristor-Based Digital Twin of Mycelium for Unconventional Computing","source":"datacite","abstract":"Fungal mycelium is widespread in nature and stands out among Engineered Living Materials (ELMs). When stimulated, it shows intricate electrical signaling activity that with the help of digital twins can be used for sustainable computing. For its further study, its emulation with novel hardware is important. Because of their special state-transition properties and non-volatility, memristors show promise for creating an effective, low-power replica of mycelium. This paper focuses on how RRAMs can be utilized to form a flexible spiking reservoir network as an alternative of common spiking neural networks (SNNs). It serves as a novel computational primitive that mimic the adaptive, self-organizing characteristics of mycelium, capable for unconventional computing.","url":"https://doi.org/10.5281/zenodo.17638162","authors":["Chatzipaschalis, Ioannis","Tompris, Ioannis","Kleitsiotis, Georgios","Chatzinikolaou, Theodoros Panagiotis","Fyrigos, Iosif-Angelos","Calomarde, Antonio","Sirakoulis, Georgios","Rubio, Antonio"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17638162","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.24433/co.2553493.v1","name":"Bioinspired spiking architecture enables energy constrained touch encoding","source":"datacite","abstract":"This capsule enables the reproduction of the main results presented in the paper: \"Bioinspired Spiking Architecture Enables Energy-Constrained Touch Encoding\".","url":"https://doi.org/10.24433/co.2553493.v1","authors":["Ortone, Andrea","Filosa, Mariangela","Indiveri, Giacomo","Desoli, Giuseppe","Mazzoni, Alberto","Oddo, Calogero Maria"],"tags":["Capsule","Engineering","Tactile Perception","Spiking neural network","energy efficient AI","analog and parallel computing"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.24433/co.2553493.v1","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2510.19537","name":"Privacy-Preserving Spiking Neural Networks: A Deep Dive into Encryption Parameter Optimisation","source":"datacite","abstract":"Deep learning is widely applied to modern problems through neural networks, but the growing computational and energy demands of these models have driven interest in more efficient approaches. Spiking Neural Networks (SNNs), the third generation of neural networks, mimic the brain's event-driven behaviour, offering improved performance and reduced power use. At the same time, concerns about data privacy during cloud-based model execution have led to the adoption of cryptographic methods. This article introduces BioEncryptSNN, a spiking neural network based encryption-decryption framework for secure and noise-resilient data protection. Unlike conventional algorithms, BioEncryptSNN converts ciphertext into spike trains and exploits temporal neural dynamics to model encryption and decryption, optimising parameters such as key length, spike timing, and synaptic connectivity. Benchmarked against AES-128, RSA-2048, and DES, BioEncryptSNN preserved data integrity while achieving up to 4.1x faster encryption and decryption than PyCryptodome's AES implementation. The framework demonstrates scalability and adaptability across symmetric and asymmetric ciphers, positioning SNNs as a promising direction for secure, energy-efficient computing.","url":"https://doi.org/10.48550/arxiv.2510.19537","authors":["Pulivathi, Mahitha","Rodrigues, Ana Fontes","Ihianle, Isibor Kennedy","Oikonomou, Andreas","Boppu, Srinivas","Machado, Pedro"],"tags":["Cryptography and Security (cs.CR)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2510.19537","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2511.06902","name":"A Closer Look at Knowledge Distillation in Spiking Neural Network Training","source":"datacite","abstract":"Spiking Neural Networks (SNNs) become popular due to excellent energy efficiency, yet facing challenges for effective model training. Recent works improve this by introducing knowledge distillation (KD) techniques, with the pre-trained artificial neural networks (ANNs) used as teachers and the target SNNs as students. This is commonly accomplished through a straightforward element-wise alignment of intermediate features and prediction logits from ANNs and SNNs, often neglecting the intrinsic differences between their architectures. Specifically, ANN's outputs exhibit a continuous distribution, whereas SNN's outputs are characterized by sparsity and discreteness. To mitigate this issue, we introduce two innovative KD strategies. Firstly, we propose the Saliency-scaled Activation Map Distillation (SAMD), which aligns the spike activation map of the student SNN with the class-aware activation map of the teacher ANN. Rather than performing KD directly on the raw %and distinct features of ANN and SNN, our SAMD directs the student to learn from saliency activation maps that exhibit greater semantic and distribution consistency. Additionally, we propose a Noise-smoothed Logits Distillation (NLD), which utilizes Gaussian noise to smooth the sparse logits of student SNN, facilitating the alignment with continuous logits from teacher ANN. Extensive experiments on multiple datasets demonstrate the effectiveness of our methods. Code is available~\\footnote{https://github.com/SinoLeu/CKDSNN.git}.","url":"https://doi.org/10.48550/arxiv.2511.06902","authors":["Liu, Xu","Xia, Na","Zhou, Jinxing","Xu, Jingyuan","Guo, Dan"],"tags":["Machine Learning (cs.LG)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2511.06902","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2508.12846","name":"IzhiRISC-V -- a RISC-V-based Processor with Custom ISA Extension for Spiking Neuron Networks Processing with Izhikevich Neurons","source":"datacite","abstract":"Spiking Neural Network processing promises to provide high energy efficiency due to the sparsity of the spiking events. However, when realized on general-purpose hardware -- such as a RISC-V processor -- this promise can be undermined and overshadowed by the inefficient code, stemming from repeated usage of basic instructions for updating all the neurons in the network. One of the possible solutions to this issue is the introduction of a custom ISA extension with neuromorphic instructions for spiking neuron updating, and realizing those instructions in bespoke hardware expansion to the existing ALU. In this paper, we present the first step towards realizing a large-scale system based on the RISC-V-compliant processor called IzhiRISC-V, supporting the custom neuromorphic ISA extension.","url":"https://doi.org/10.48550/arxiv.2508.12846","authors":["Szczerek, Wiktor J.","Podobas, Artur"],"tags":["Neural and Evolutionary Computing (cs.NE)","Hardware Architecture (cs.AR)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2508.12846","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.6084/m9.figshare.c.8142680.v1","name":"A hybrid spiking neural network - quantum framework for spatio-temporal data classification: a case study on EEG data","source":"datacite","abstract":"Abstract The study introduces a hybrid computational framework that combines neuro-inspired information processing using spiking neural networks (SNNs) and quantum information processing using quantum kernels to develop quantum-enhanced machine learning models for spatio-temporal data, demonstrated through the classification of EEG data as a case study. In the proposed SNN-quantum computation (SNN-QC) framework, SNN with spike time information representation is employed to learn spatio-temporal interactions (EEG recorded from multiple channels over time). Frequency-based (rate-based) information as spike frequency state vectors are extracted from the SNN and classified using a quantum classifier. In the latter part, we use the quantum kernel approach utilising feature maps for classification tasks. The proposed SNN-QC is demonstrated on a benchmark EEG dataset to classify three distinct wrist movement tasks in six binary classification setups as a proof of concept. We introduce a novel high-order nonlinear feature map that demonstrates improved performance over state-of-the-art feature maps and several machine learning methods across most of the tasks studied. Furthermore, the role of hyperparameters for enhanced feature maps is also highlighted. The performance of SNN-QC is evaluated using statistical metrics and cross-validation techniques, demonstrating its efficacy across multiple binary classifiers. Quantum hardware validation is conducted using both a superconducting IBM-QPU and a high-fidelity noisy simulation that replicates a real QPU. Furthermore, the results demonstrate that the SNN-QC outperforms models that use statistical features rather than features extracted from the SNN, as the SNN accounts for the temporal interaction between the spatio-temporal input variables. Finally, we conclude that the SNN-QC offers a potential pathway for developing more accurate neuromorphic-quantum enhanced systems that are both energy-efficient and biologically-inspired, well-suited for dealing with spatio-temporal data.","url":"https://doi.org/10.6084/m9.figshare.c.8142680.v1","authors":["Jha, Ravi Kumar","Kasabov, Nikola","Bhattacharyya, Saugat","Coyle, Damien","Prasad, Girijesh"],"tags":["Statistics","FOS: Mathematics","Artificial Intelligence and Image Processing","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.6084/m9.figshare.c.8142680.v1","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.6084/m9.figshare.c.8142680","name":"A hybrid spiking neural network - quantum framework for spatio-temporal data classification: a case study on EEG data","source":"datacite","abstract":"Abstract The study introduces a hybrid computational framework that combines neuro-inspired information processing using spiking neural networks (SNNs) and quantum information processing using quantum kernels to develop quantum-enhanced machine learning models for spatio-temporal data, demonstrated through the classification of EEG data as a case study. In the proposed SNN-quantum computation (SNN-QC) framework, SNN with spike time information representation is employed to learn spatio-temporal interactions (EEG recorded from multiple channels over time). Frequency-based (rate-based) information as spike frequency state vectors are extracted from the SNN and classified using a quantum classifier. In the latter part, we use the quantum kernel approach utilising feature maps for classification tasks. The proposed SNN-QC is demonstrated on a benchmark EEG dataset to classify three distinct wrist movement tasks in six binary classification setups as a proof of concept. We introduce a novel high-order nonlinear feature map that demonstrates improved performance over state-of-the-art feature maps and several machine learning methods across most of the tasks studied. Furthermore, the role of hyperparameters for enhanced feature maps is also highlighted. The performance of SNN-QC is evaluated using statistical metrics and cross-validation techniques, demonstrating its efficacy across multiple binary classifiers. Quantum hardware validation is conducted using both a superconducting IBM-QPU and a high-fidelity noisy simulation that replicates a real QPU. Furthermore, the results demonstrate that the SNN-QC outperforms models that use statistical features rather than features extracted from the SNN, as the SNN accounts for the temporal interaction between the spatio-temporal input variables. Finally, we conclude that the SNN-QC offers a potential pathway for developing more accurate neuromorphic-quantum enhanced systems that are both energy-efficient and biologically-inspired, well-suited for dealing with spatio-temporal data.","url":"https://doi.org/10.6084/m9.figshare.c.8142680","authors":["Jha, Ravi Kumar","Kasabov, Nikola","Bhattacharyya, Saugat","Coyle, Damien","Prasad, Girijesh"],"tags":["Statistics","FOS: Mathematics","Artificial Intelligence and Image Processing","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.6084/m9.figshare.c.8142680","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.24406/publica-6212","name":"Design of a Simply Sufficient Leaky Integrate-and-Fire Neuron in 22nm FDSOI","source":"datacite","abstract":"In this thesis the design process of a simply sufficient leaky-integrate and fire (LIF) neuron is discussed to examine how much precision is needed in a hardware design. Therefore, variations of hardware parameters are analyzed and then the impact of the variations are tested in the snnTorch framework. Initially different hardware approaches are compared and ultimately the circuit by Eslahi is chosen as a basis for a circuit implementation in 22 nm FDSOI technology. Monte Carlo simulations are conducted to observe hardware neuron and synapse pa rameters under the impact of process variations and mismatch. The results have shown that, the hardware neuron design is robust regarding the variation of the parameters. After the variation values are acquired from the hardware modules, a custom soft ware model is designed in snnTorch framework to simulate and test the impact of the parameter variations on the spiking neural network (SNN) performance. In the training process of the SNN with 500 neurons in hidden layer an accuracy of 88.34 % is reached. The software test results have shown that, the synapse parameters have the biggest influence on the accuracy of the network and influence of the neuron parameters on the other hand is negligible.","url":"https://doi.org/10.24406/publica-6212","authors":["Kocyigit, Ali Onur",":unav"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.24406/publica-6212","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17585681","name":"Neuromorphic Event–LiDAR–IMU Dataset for SLAM Applications","source":"datacite","abstract":"This release provides the Neuromorphic Event–LiDAR–IMU dataset sequences: • lab_indoor.zip — Controlled indoor lab sequence (159 MB) • b5_indoor.zip — Indoor building 5 sequence (551 MB) • b5_outdoor.zip — Outdoor building 5 route (445 MB) • carpark_outdoor.zip — Carpark traversal (742 MB) • b23_hybrid.zip — Hybrid building 23 route (709 MB) • b34_hybrid.zip — Hybrid building 34 route (645 MB) All sequences include synchronized event, LiDAR, and IMU data files. License: CC BY-NC 4.0 — for non-commercial research use only.","url":"https://doi.org/10.5281/zenodo.17585681","authors":["Tenzin, Sangay"],"tags":["event camera","spiking neural network","SLAM","LiDAR","IMU","neuromorphic computing","sensor fusion","dataset"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17585681","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17585682","name":"Neuromorphic Event–LiDAR–IMU Dataset for SLAM Applications","source":"datacite","abstract":"This release provides the Neuromorphic Event–LiDAR–IMU dataset sequences: • lab_indoor.zip — Controlled indoor lab sequence (159 MB) • b5_indoor.zip — Indoor building 5 sequence (551 MB) • b5_outdoor.zip — Outdoor building 5 route (445 MB) • carpark_outdoor.zip — Carpark traversal (742 MB) • b23_hybrid.zip — Hybrid building 23 route (709 MB) • b34_hybrid.zip — Hybrid building 34 route (645 MB) All sequences include synchronized event, LiDAR, and IMU data files. License: CC BY-NC 4.0 — for non-commercial research use only.","url":"https://doi.org/10.5281/zenodo.17585682","authors":["Tenzin, Sangay"],"tags":["event camera","spiking neural network","SLAM","LiDAR","IMU","neuromorphic computing","sensor fusion","dataset"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17585682","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17581570","name":"Accuracy-Robustness Trade Off via Spiking Neural Network Gradient Sparsity Trail","source":"datacite","abstract":"","url":"https://doi.org/10.5281/zenodo.17581570","authors":["Luu, Nhan"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17581570","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17581571","name":"Accuracy-Robustness Trade Off via Spiking Neural Network Gradient Sparsity Trail","source":"datacite","abstract":"","url":"https://doi.org/10.5281/zenodo.17581571","authors":["Luu, Nhan"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17581571","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.34734/fzj-2025-04366","name":"Learning sequence timing and controlling recall speed in networks of spiking neurons","source":"datacite","abstract":"Processing sequential inputs is a fundamental aspect of brain function, underlying tasks such as sensory perception, reading, and mathematical reasoning. At the core of the cortical algorithm, sequence processing involves learning the order and timing of elements, predicting future events, detecting unexpected deviations, and recalling learned sequences. The spiking Temporal Memory (sTM) model (Bouhadjar, 2022), a biologically inspired spiking neuronal network, provides a framework for key aspects of sequence processing. In its original version, however, it can not learn the timing of sequence elements. Further, it remains an open question how the speed of sequential recall can be flexibly modulated. We propose a mechanism in which the duration of sequence elements is represented by repeated activations of element specific neuronal populations. The sTM model can thereby represent even long time intervals, providing a biologically plausible basis for learning and recalling not only the order of sequence elements, but also complex rhythms. Additionally, we demonstrate that oscillatory background inputs can serve as a clock signal and thereby provide a robust mechanism for controlling the speed of sequence recall. Modulation of oscillation frequency and amplitude enable a stable recall across a wide range of speeds,offering a biologically relevant strategy for flexible temporal adaptation. Our findings suggest that time is encoded by unique and sparse spatio-temporal patterns of neural activity, and that the speed of sequence recall during wakefulness and sleep is correlated to the characteristics of global oscillatory activity, as observed in EEG or LFP recordings. In summary, our results contribute to the understanding of sequence processing and time representation in the brain.","url":"https://doi.org/10.34734/fzj-2025-04366","authors":["Lober, Melissa","Bouhadjar, Younes","Diesmann, Markus","Tetzlaff, Tom"],"tags":[],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.34734/fzj-2025-04366","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2304.03896","name":"Spiking Neural Networks for Detecting Satellite-Based Internet-of-Things Signals","source":"datacite","abstract":"With the rapid growth of IoT networks, ubiquitous coverage is becoming increasingly necessary. Low Earth Orbit (LEO) satellite constellations for IoT have been proposed to provide coverage to regions where terrestrial systems cannot. However, LEO constellations for uplink communications are severely limited by the high density of user devices, which causes a high level of co-channel interference. This research presents a novel framework that utilizes spiking neural networks (SNNs) to detect IoT signals in the presence of uplink interference. The key advantage of SNNs is the extremely low power consumption relative to traditional deep learning (DL) networks. The performance of the spiking-based neural network detectors is compared against state-of-the-art DL networks and the conventional matched filter detector. Results indicate that both DL and SNN-based receivers surpass the matched filter detector in interference-heavy scenarios, owing to their capacity to effectively distinguish target signals amidst co-channel interference. Moreover, our work highlights the ultra-low power consumption of SNNs compared to other DL methods for signal detection. The strong detection performance and low power consumption of SNNs make them particularly suitable for onboard signal detection in IoT LEO satellites, especially in high interference conditions.","url":"https://doi.org/10.48550/arxiv.2304.03896","authors":["Dakic, Kosta","Homssi, Bassel Al","Walia, Sumeet","Al-Hourani, Akram"],"tags":["Information Theory (cs.IT)","Signal Processing (eess.SP)","FOS: Computer and information sciences","FOS: Computer and information sciences","FOS: Electrical engineering, electronic engineering, information engineering","FOS: Electrical engineering, electronic engineering, information engineering"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.48550/arxiv.2304.03896","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2511.05581","name":"Cannistraci-Hebb Training on Ultra-Sparse Spiking Neural Networks","source":"datacite","abstract":"Inspired by the brain's spike-based computation, spiking neural networks (SNNs) inherently possess temporal activation sparsity. However, when it comes to the sparse training of SNNs in the structural connection domain, existing methods fail to achieve ultra-sparse network structures without significant performance loss, thereby hindering progress in energy-efficient neuromorphic computing. This limitation presents a critical challenge: how to achieve high levels of structural connection sparsity while maintaining performance comparable to fully connected networks. To address this challenge, we propose the Cannistraci-Hebb Spiking Neural Network (CH-SNN), a novel and generalizable dynamic sparse training framework for SNNs consisting of four stages. First, we propose a sparse spike correlated topological initialization (SSCTI) method to initialize a sparse network based on node correlations. Second, temporal activation sparsity and structural connection sparsity are integrated via a proposed sparse spike weight initialization (SSWI) method. Third, a hybrid link removal score (LRS) is applied to prune redundant weights and inactive neurons, improving information flow. Finally, the CH3-L3 network automaton framework inspired by Cannistraci-Hebb learning theory is incorporated to perform link prediction for potential synaptic regrowth. These mechanisms enable CH-SNN to achieve sparsification across all linear layers. We have conducted extensive experiments on six datasets including CIFAR-10 and CIFAR-100, evaluating various network architectures such as spiking convolutional neural networks and Spikformer.","url":"https://doi.org/10.48550/arxiv.2511.05581","authors":["Hua, Yuan","Zhang, Jilin","Zhang, Yingtao","Gu, Wenqi","You, Leyi","Xiong, Baobo","Cannistraci, Carlo Vittorio","Chen, Hong"],"tags":["Neural and Evolutionary Computing (cs.NE)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2511.05581","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5075/epfl-thesis-11448","name":"SPAD Image Sensors with Embedded Intelligence","source":"datacite","abstract":"Single-photon avalanche diodes (SPADs) are solid-state photodetectors that can detect individual photons with picosecond timing precision, enabling powerful time-resolved imaging across scientific, industrial, and biomedical applications. Despite their unique sensitivity, conventional SPAD imaging workflows passively collect photons, transfer large volumes of raw data off-chip, and reconstruct results through offline post-processing, leading to inefficiencies in photon usage, high latency, and limited adaptability. This thesis explores the potential of embedded artificial intelligence (AI) for efficient, real-time, intelligent processing in SPAD imaging through hardware-software co-design, bringing computation directly to the sensor to process photon data in its native form. Two general frameworks are proposed, each representing a paradigm shift from the conventional process. The first framework is inspired by the power of artificial neural networks (ANNs) in computer vision. It employs recurrent neural networks (RNNs) that operate directly on timestamps of photon arrival, extracting temporal information in an event-driven manner. The RNN is trained and evaluated for fluorescence lifetime estimation, achieving high precision and robustness. Quantization and approximation techniques are explored to enable FPGA implementation. Based on this, an imaging system integrating a SPAD image sensor with an on-FPGA RNN is developed, enabling real-time fluorescence lifetime imaging and demonstrating generalizability to other time-resolved tasks. The second framework is inspired by the human visual system, employing spiking neural networks (SNNs) that operate directly on the asynchronous pulses generated by SPAD avalanche breakdown upon photon arrival, thereby enabling temporal analysis with ultra-low latency and energy-efficient computation. Two hardware-friendly SNN architectures, Transporter SNN and Reversed start-stop SNN are proposed, which transform the phase-coded spike trains into density-coded and inter-spike-interval-coded representations, enabling more efficient training and processing. Dedicated training methods are explored, and both architectures are validated through fluorescence lifetime imaging. Based on the Transporter SNN architecture, the first SPAD image sensor with on-chip spike encoder for active time-resolved imaging is developed. This thesis encompasses a full-stack imaging workflow, spanning SPAD image sensor design, FPGA implementation, software development, neural network training and evaluation, mathematical modeling, fluorescence lifetime imaging, and optical system setup. Together, these contributions establish new paradigms of intelligent SPAD imaging, where sensing and computation are deeply integrated. The proposed frameworks demonstrate significant gains in photon efficiency, processing speed, robustness, and adaptability, illustrating how embedded AI can transform SPAD systems from passive detectors into intelligent, adaptive, and autonomous imaging platforms for next-generation applications.","url":"https://doi.org/10.5075/epfl-thesis-11448","authors":["Lin, Yang"],"tags":["single-photon avalanche diode (SPAD)","image sensor","artificial intelligence (AI)","embedded AI","deep learning","neural network","spiking neural network (SNN)","fluorescence lifetime imaging microscopy (FLIM)"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5075/epfl-thesis-11448","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17511153","name":"Quantum-Bio-Hybrid Paradigm III: Cross-Domain Implementation and Neuromorphic Realization","source":"datacite","abstract":"This paper establishes the hardware realization of the Quantum–Bio–Hybrid (QB-H) paradigm, extending the previously defined retrocausal learning rule (ΔR) to a neuromorphic platform. The proposed system integrates human intention (MBCI) as a positive reinforcement signal and a real-time ethical safeguard (MSI: Moral State Interrupter) to enforce alignment. The ΔR rule is quantized for FPGA/ASIC implementation, and its modulation of spiking neural network (SNN) plasticity demonstrates end-to-end latency ≤10 ms.Simulation results using motor-imagery EEG data validate that human intention can effectively bias synaptic updates, while the MSI module performs on-the-fly ethical correction when deviation exceeds the threshold. These results quantitatively confirm the feasibility of real-time, ethics-aligned AGI hardware under the Quantum–Bio–Hybrid paradigm.","url":"https://doi.org/10.5281/zenodo.17511153","authors":["Konishi, Hiroko","Gemini AI"],"tags":["Quantum-Bio-Hybrid AGI, Retrocausal Learning, Neuromorphic Hardware, FPGA, BCI, Ethical Control, Moral State Interrupter (MSI), Synthesis Intelligence"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17511153","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2511.05232","name":"Travelling waves modulated by subthreshold oscillations in networks of integrate-and-fire neurons","source":"datacite","abstract":"Travelling waves of neural firing activity are observed in brain tissue as a part of various sensory, motor and cognitive processes. They represent an object of major interest in the study of excitable networks, with analysis conducted in both neural field models and spiking neuronal networks. The latter class exposes the single-neuron dynamics directly, allowing us to study the details of their influence upon network-scale behaviour. Here we present a study of a laterally-inhibited network of leaky integrate-and-fire neurons modulated by a slow voltage-gated ion channel that acts as a linear adaptation variable. As the strength of the ion channel increases, we find that its interaction with the lateral inhibition increases wave speeds. The ion channel can enable subthreshold oscillations, with the intervals between the firing events of loosely-coupled travelling wave solutions structured around the neuron's natural period. These subthreshold oscillations also enable the occurrence of codimension-2 grazing bifurcations; along with the emergence of fold bifurcations along wave solution branches, the slow ion channel introduces a variety of intermediate structures in the solution space. These point towards further investigation of the role neighbouring solution branches play in the behaviour of waves forced across bifurcations, which we illustrate with the aid of simulations using a novel root-finding algorithm designed to handle uncertainty over the existence of firing solutions.","url":"https://doi.org/10.48550/arxiv.2511.05232","authors":["Kerr, Henry D. J.","Ashwin, Peter","Wedgwood, Kyle C. A."],"tags":["Neurons and Cognition (q-bio.NC)","FOS: Biological sciences","FOS: Biological sciences","92B20 (Primary) 92C42, 65D15, 65P30 (Secondary)"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2511.05232","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2511.01158","name":"A High-Throughput Spiking Neural Network Processor Enabling Synaptic Delay Emulation","source":"datacite","abstract":"Synaptic delay has attracted significant attention in neural network dynamics for integrating and processing complex spatiotemporal information. This paper introduces a high-throughput Spiking Neural Network (SNN) processor that supports synaptic delay-based emulation for edge applications. The processor leverages a multicore pipelined architecture with parallel compute engines, capable of real-time processing of the computational load associated with synaptic delays. We develop a SoC prototype of the proposed processor on PYNQ Z2 FPGA platform and evaluate its performance using the Spiking Heidelberg Digits (SHD) benchmark for low-power keyword spotting tasks. The processor achieves 93.4% accuracy in deployment and an average throughput of 104 samples/sec at a typical operating frequency of 125 MHz and 282 mW power consumption.","url":"https://doi.org/10.48550/arxiv.2511.01158","authors":["Chen, Faquan","Tian, Qingyang","Wu, Ziren","Ying, Rendong","Wen, Fei","Liu, Peilin"],"tags":["Neural and Evolutionary Computing (cs.NE)","Artificial Intelligence (cs.AI)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2511.01158","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.48550/arxiv.2503.13492","name":"Event-Driven Implementation of a Physical Reservoir Computing Framework for superficial EMG-based Gesture Recognition","source":"datacite","abstract":"Wearable health devices have a strong demand in real-time biomedical signal processing. However traditional methods often require data transmission to centralized processing unit with substantial computational resources after collecting it from edge devices. Neuromorphic computing is an emerging field that seeks to design specialized hardware for computing systems inspired by the structure, function, and dynamics of the human brain, offering significant advantages in latency and power consumption. This paper explores a novel neuromorphic implementation approach for gesture recognition by extracting spatiotemporal spiking information from surface electromyography (sEMG) data in an event-driven manner. At the same time, the network was designed by implementing a simple-structured and hardware-friendly Physical Reservoir Computing (PRC) framework called Rotating Neuron Reservoir (RNR) within the domain of Spiking neural network (SNN). The spiking RNR (sRNR) is promising to pipeline an innovative solution to compact embedded wearable systems, enabling low-latency, real-time processing directly at the sensor level. The proposed system was validated by an open-access large-scale sEMG database and achieved an average classification accuracy of 74.6\\% and 80.3\\% using a classical machine learning classifier and a delta learning rule algorithm respectively. While the delta learning rule could be fully spiking and implementable on neuromorphic chips, the proposed gesture recognition system demonstrates the potential for near-sensor low-latency processing.","url":"https://doi.org/10.48550/arxiv.2503.13492","authors":["Ding, Yuqi","Donati, Elisa","Li, Haobo","Heidari, Hadi"],"tags":["Signal Processing (eess.SP)","Artificial Intelligence (cs.AI)","Neural and Evolutionary Computing (cs.NE)","FOS: Electrical engineering, electronic engineering, information engineering","FOS: Electrical engineering, electronic engineering, information engineering","FOS: Computer and information sciences","FOS: Computer and information sciences"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.48550/arxiv.2503.13492","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17547571","name":"Structured PREreview of \"A Practical Tutorial on Spiking Neural Networks: Comprehensive Review, Models, Experiments, Software Tools, and Implementation Guidelines\"","source":"datacite","abstract":"This Zenodo record is a permanently preserved version of a Structured PREreview. You can view the complete PREreview at https://prereview.org/reviews/17547571. Does the introduction explain the objective of the research presented in the preprint? Yes The introduction explains the objective of the research by initially highlighting the motivation: the rapidly growing computational and energy costs of modern deep neural networks and the resulting sustainability concerns, which position Spiking Neural Networks (SNNs) as a biologically inspired, event-driven alternative promising competitive accuracy at substantially lower energy. The core objective is framed by addressing a key \"Gap,\" identified as the lack of a unified, practice-oriented analysis and limited \"apples-to-apples evidence on accuracy–energy trade-offs against equivalent ANN baselines\". To resolve this, the work combines a comprehensive critical review, a hands-on tutorial, and standardized benchmarking by systematizing SNN components (models, encodings, and learning paradigms), providing a practical tutorial using a representative neuromorphic software stack (e.g., Lava), and establishing a side-by-side evaluation protocol comparing SNNs with architecturally matched ANNs on both shallow (MNIST) and deeper convolutional (CIFAR-10) tasks. The final stated aim is to measure accuracy and power-oriented proxies, ultimately distilling actionable design guidelines that offer a \"coherent pathway from principles to practice\" to design SNNs that \"balance accuracy with energy efficiency in real-world settings Are the methods well-suited for this research? Highly appropriate Yes, the methods employed in the preprint are well-suited for the research objective, as they are specifically designed to address the identified gap concerning the lack of a unified, practice-oriented analysis linking SNN design choices to measurable performance and power consumption. The approach establishes a rigorous side-by-side evaluation protocol by comparing SNN configurations with architecturally matched ANN baselines on both a shallow Fully Connected Network (FCN) for MNIST and a deeper VGG7 architecture for CIFAR-10, thereby providing the crucial \"apples-to-apples evidence\" sought by the study. The methodology systematically explores the core design knobs of SNNs by experimenting with a diverse set of nine neuron models (including LIF, Sigma-Delta, and AdEx) and seven input encoding schemes (such as Direct Coding, Rate Encoding, and Temporal TTFS), all trained using supervised surrogate-gradient methods Are the conclusions supported by the data? Highly supported Yes, the conclusions presented in the preprint are thoroughly supported by the empirical data derived from the standardized benchmarking experiments on MNIST and CIFAR-10. 1. The first key conclusion, asserting a real yet tunable accuracy–energy trade-off, is evidenced by comparing the top-performing SNN configurations against the baseline Artificial Neural Network (ANN); for instance, on MNIST, ΣΔ neurons achieved 98.10% accuracy, closely matching the 98.23% ANN baseline, while remaining energetically below the ANN proxy, confirming the SNN energy advantage. Conversely, highly frugal encodings like R-NoM consistently produced the lowest energy consumption demonstrating the sharp trade-off by incurring larger accuracy drops, while Direct and ΣΔ encodings narrowed the accuracy gap while only demanding a moderate energy premium compared to the most frugal options. 2. The second conclusion regarding practical configuration rules is directly substantiated by data showing that accuracy-critical applications benefit from ΣΔ neurons paired with Direct coding on CIFAR-10 (achieving 83.0% at two time steps against the 83.6% ANN baseline) or Rate/ΣΔ encoding on MNIST, whereas energy-constrained scenarios achieved maximal efficiency using simpler IF/LIF neurons with Burst or R-NoM encoding at minimal time steps. Furthermore, data confirms that thres","url":"https://doi.org/10.5281/zenodo.17547571","authors":["Ronke Lawal"],"tags":["Requested PREreview","Structured PREreview"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17547571","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.5281/zenodo.17547570","name":"Structured PREreview of \"A Practical Tutorial on Spiking Neural Networks: Comprehensive Review, Models, Experiments, Software Tools, and Implementation Guidelines\"","source":"datacite","abstract":"This Zenodo record is a permanently preserved version of a Structured PREreview. You can view the complete PREreview at https://prereview.org/reviews/17547571. Does the introduction explain the objective of the research presented in the preprint? Yes The introduction explains the objective of the research by initially highlighting the motivation: the rapidly growing computational and energy costs of modern deep neural networks and the resulting sustainability concerns, which position Spiking Neural Networks (SNNs) as a biologically inspired, event-driven alternative promising competitive accuracy at substantially lower energy. The core objective is framed by addressing a key \"Gap,\" identified as the lack of a unified, practice-oriented analysis and limited \"apples-to-apples evidence on accuracy–energy trade-offs against equivalent ANN baselines\". To resolve this, the work combines a comprehensive critical review, a hands-on tutorial, and standardized benchmarking by systematizing SNN components (models, encodings, and learning paradigms), providing a practical tutorial using a representative neuromorphic software stack (e.g., Lava), and establishing a side-by-side evaluation protocol comparing SNNs with architecturally matched ANNs on both shallow (MNIST) and deeper convolutional (CIFAR-10) tasks. The final stated aim is to measure accuracy and power-oriented proxies, ultimately distilling actionable design guidelines that offer a \"coherent pathway from principles to practice\" to design SNNs that \"balance accuracy with energy efficiency in real-world settings Are the methods well-suited for this research? Highly appropriate Yes, the methods employed in the preprint are well-suited for the research objective, as they are specifically designed to address the identified gap concerning the lack of a unified, practice-oriented analysis linking SNN design choices to measurable performance and power consumption. The approach establishes a rigorous side-by-side evaluation protocol by comparing SNN configurations with architecturally matched ANN baselines on both a shallow Fully Connected Network (FCN) for MNIST and a deeper VGG7 architecture for CIFAR-10, thereby providing the crucial \"apples-to-apples evidence\" sought by the study. The methodology systematically explores the core design knobs of SNNs by experimenting with a diverse set of nine neuron models (including LIF, Sigma-Delta, and AdEx) and seven input encoding schemes (such as Direct Coding, Rate Encoding, and Temporal TTFS), all trained using supervised surrogate-gradient methods Are the conclusions supported by the data? Highly supported Yes, the conclusions presented in the preprint are thoroughly supported by the empirical data derived from the standardized benchmarking experiments on MNIST and CIFAR-10. 1. The first key conclusion, asserting a real yet tunable accuracy–energy trade-off, is evidenced by comparing the top-performing SNN configurations against the baseline Artificial Neural Network (ANN); for instance, on MNIST, ΣΔ neurons achieved 98.10% accuracy, closely matching the 98.23% ANN baseline, while remaining energetically below the ANN proxy, confirming the SNN energy advantage. Conversely, highly frugal encodings like R-NoM consistently produced the lowest energy consumption demonstrating the sharp trade-off by incurring larger accuracy drops, while Direct and ΣΔ encodings narrowed the accuracy gap while only demanding a moderate energy premium compared to the most frugal options. 2. The second conclusion regarding practical configuration rules is directly substantiated by data showing that accuracy-critical applications benefit from ΣΔ neurons paired with Direct coding on CIFAR-10 (achieving 83.0% at two time steps against the 83.6% ANN baseline) or Rate/ΣΔ encoding on MNIST, whereas energy-constrained scenarios achieved maximal efficiency using simpler IF/LIF neurons with Burst or R-NoM encoding at minimal time steps. Furthermore, data confirms that thres","url":"https://doi.org/10.5281/zenodo.17547570","authors":["Ronke Lawal"],"tags":["Requested PREreview","Structured PREreview"],"confidence":0.66,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.5281/zenodo.17547570","addedAt":"2026-09-01T01:48:23.495Z","updatedAt":"2026-09-01T01:48:23.495Z"},{"id":"doi:10.1109/tai.2025.3586238","name":"SpikeNAS: A Fast Memory-Aware Neural Architecture Search Framework for Spiking Neural Network-Based Embedded AI Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tai.2025.3586238","authors":["Rachmad Vidya Wicaksana Putra","Muhammad Shafique"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-04T13:53:38Z","doi":"10.1109/tai.2025.3586238","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1364/ofc.2023.w4e.1","name":"Spiking Neural Network Linear Equalization: Experimental Demonstration of 2km 100Gb/s IM/DD PAM4 Optical Transmission","source":"crossref","abstract":"A linear feed-forward equalizer is implemented by a potentially low-power spiking neural network. For a 100Gb/s PAM-4 IM/DD optical 2km transmission, no performance penalty compared to a digital implementation is observed.","url":"https://doi.org/10.1364/ofc.2023.w4e.1","authors":["Georg Böcherer","Florian Strasser","Elias Arnold","Youxi Lin","Johannes Schemmel","Stefano Calabrò","Maxim Kuschnerov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-18T14:15:55Z","doi":"10.1364/ofc.2023.w4e.1","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/taeece.2015.7113602","name":"Perception of noise in global illumination algorithms based on spiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/taeece.2015.7113602","authors":["J. Constantin","I. Constantin","R. Rammouz","Andre Bigand","Denis Hamad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-06-03T19:31:56Z","doi":"10.1109/taeece.2015.7113602","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.3390/s21144900","name":"Deep Learning of Explainable EEG Patterns as Dynamic Spatiotemporal Clusters and Rules in a Brain-Inspired Spiking Neural Network","source":"crossref","abstract":"The paper proposes a new method for deep learning and knowledge discovery in a brain-inspired Spiking Neural Networks (SNN) architecture that enhances the model’s explainability while learning from streaming spatiotemporal brain data (STBD) in an incremental and on-line mode of operation. This led to the extraction of spatiotemporal rules from SNN models that explain why a certain decision (output prediction) was made by the model. During the learning process, the SNN created dynamic neural clusters, captured as polygons, which evolved in time and continuously changed their size and shape. The dynamic patterns of the clusters were quantitatively analyzed to identify the important STBD features that correspond to the most activated brain regions. We studied the trend of dynamically created clusters and their spike-driven events that occur together in specific space and time. The research contributes to: (1) enhanced interpretability of SNN learning behavior through dynamic neural clustering; (2) feature selection and enhanced accuracy of classification; (3) spatiotemporal rules to support model explainability; and (4) a better understanding of the dynamics in STBD in terms of feature interaction. The clustering method was applied to a case study of Electroencephalogram (EEG) data, recorded from a healthy control group (n = 21) and opiate use (n = 18) subjects while they were performing a cognitive task. The SNN models of EEG demonstrated different trends of dynamic clusters across the groups. This suggested to select a group of marker EEG features and resulted in an improved accuracy of EEG classification to 92%, when compared with all-feature classification. During learning of EEG data, the areas of neurons in the SNN model that form adjacent clusters (corresponding to neighboring EEG channels) were detected as fuzzy boundaries that explain overlapping activity of brain regions for each group of subjects.","url":"https://doi.org/10.3390/s21144900","authors":["Maryam Doborjeh","Zohreh Doborjeh","Nikola Kasabov","Molood Barati","Grace Y. Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-07-19T10:07:37Z","doi":"10.3390/s21144900","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/ijcnn52387.2021.9533837","name":"Temporal Pattern Coding in Deep Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn52387.2021.9533837","authors":["Bodo Rueckauer","Shih-Chii Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-20T17:27:41Z","doi":"10.1109/ijcnn52387.2021.9533837","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1016/s0893-6080(02)00033-3","name":"SpikeCell: a deterministic spiking neuron","source":"crossref","abstract":"","url":"https://doi.org/10.1016/s0893-6080(02)00033-3","authors":["C. Godin","M.B. Gordon","J.D. Muller"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-10-11T21:02:29Z","doi":"10.1016/s0893-6080(02)00033-3","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/ijcnn.2001.938430","name":"Supervised learning with spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2001.938430","authors":["Jianguo Xin","M.J. Embrechts"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-11-13T17:02:15Z","doi":"10.1109/ijcnn.2001.938430","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.7554/elife.106871.1.sa2","name":"Reviewer #2 (Public review): Neural signatures of motor memories emerge in neural network models","source":"crossref","abstract":"","url":"https://doi.org/10.7554/elife.106871.1.sa2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-27T14:32:12Z","doi":"10.7554/elife.106871.1.sa2","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.3390/electronics12112351","name":"Python-Based Circuit Design for Fundamental Building Blocks of Spiking Neural Network","source":"crossref","abstract":"Spiking neural networks (SNNs) are considered a crucial research direction to address the “storage wall” and “power wall” challenges faced by traditional artificial intelligence computing. However, developing SNN chips based on CMOS (complementary metal oxide semiconductor) circuits remains a challenge. Although memristor process technology is the best alternative to synapses, it is still undergoing refinement. In this study, a novel approach is proposed that employs tools to automatically generate HDL (hardware description language) code for constructing neuron and memristor circuits after using Python to describe the neuron and memristor models. Based on this approach, HR (Hindmash–Rose), LIF (leaky integrate-and-fire), and IZ (Izhikevich) neuron circuits, as well as HP, EG (enhanced generalized), and TB (the behavioral threshold bipolar) memristor circuits are designed to construct the most basic connection of a SNN: the neuron–memristor–neuron circuit that satisfies the STDP (spike-timing-dependent-plasticity) learning rule. Through simulation experiments and FPGA (field programmable gate array) prototype verification, it is confirmed that the IZ and LIF circuits are suitable as neurons in SNNs, while the X variables of the EG memristor model serve as characteristic synaptic weights. The EG memristor circuits best satisfy the STDP learning rule and are suitable as synapses in SNNs. In comparison to previous works on hardware spiking neurons, the proposed method needed fewer area resources for creating spiking neurons models on FPGA. The proposed SNN basic components design method, and the resulting circuits, are beneficial for architectural exploration and hardware–software co-design of SNN chips.","url":"https://doi.org/10.3390/electronics12112351","authors":["Xing Qin","Chaojie Li","Haitao He","Zejun Pan","Chenxiao Lai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-23T07:00:02Z","doi":"10.3390/electronics12112351","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/ijcnn.2019.8851740","name":"A Modular Approach to Construction of Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2019.8851740","authors":["Kyunghee Lee","Hongchi Shi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-09-30T23:44:32Z","doi":"10.1109/ijcnn.2019.8851740","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1016/j.neunet.2018.12.002","name":"Deep learning in spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2018.12.002","authors":["Amirhossein Tavanaei","Masoud Ghodrati","Saeed Reza Kheradpisheh","Timothée Masquelier","Anthony Maida"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-12-18T11:56:16Z","doi":"10.1016/j.neunet.2018.12.002","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1007/978-3-031-44865-2_9","name":"Spiking Neural Network with Tetrapartite Synapse","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-44865-2_9","authors":["Sergey V. Stasenko","Victor B. Kazantsev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-11T09:05:25Z","doi":"10.1007/978-3-031-44865-2_9","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1007/978-981-99-1482-1_6","name":"Detection of Brain Abnormalities from Spontaneous Electroencephalography Using Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-99-1482-1_6","authors":["Rekha Sahu","Satya Ranjan Dash"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-01T14:02:42Z","doi":"10.1007/978-981-99-1482-1_6","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/icecs61496.2024.10849226","name":"Adaptive Robotic Arm Control with a Spiking Recurrent Neural Network on a Digital Accelerator","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icecs61496.2024.10849226","authors":["Alejandro Linares-Barranco","Luciano Prono","Robert Lengenstein","Giacomo Indiveri","Charlotte Frenkel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-28T18:32:08Z","doi":"10.1109/icecs61496.2024.10849226","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1007/978-3-642-33269-2_58","name":"Learning from Delayed Reward und Punishment in a Spiking Neural Network Model of Basal Ganglia with Opposing D1/D2 Plasticity","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-33269-2_58","authors":["Jenia Jitsev","Nobi Abraham","Abigail Morrison","Marc Tittgemeyer"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-09-18T14:55:50Z","doi":"10.1007/978-3-642-33269-2_58","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/gefs.2013.6601053","name":"Estimation of human transport modes by fuzzy spiking neural network and evolution strategy in informationally structured space","source":"crossref","abstract":"","url":"https://doi.org/10.1109/gefs.2013.6601053","authors":["Dalai Tang","Janos Botzheim","Naoyuki Kubota","Toru Yamaguchi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-09-25T22:05:24Z","doi":"10.1109/gefs.2013.6601053","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/commnet60167.2023.10365305","name":"Study of Spiking Neural Network-Based Regressor on Applications in Digital Predistortion for Power Amplifiers","source":"crossref","abstract":"","url":"https://doi.org/10.1109/commnet60167.2023.10365305","authors":["Yongtao Wei","Siqi Wang","Farid Nait-Abdesselam","Aziz Benlarbi-Delai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-22T19:23:57Z","doi":"10.1109/commnet60167.2023.10365305","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1007/3-540-44614-1_30","name":"Compact Spiking Neural Network Implementation in FPGA","source":"crossref","abstract":"","url":"https://doi.org/10.1007/3-540-44614-1_30","authors":["Selene Maya","Rocio Reynoso","César Torres","Miguel Arias-Estrada"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-10-20T17:25:22Z","doi":"10.1007/3-540-44614-1_30","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/tcsii.2023.3263048","name":"Fast Simulation of Analog Spiking Neural Network With Device Non-Idealites","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tcsii.2023.3263048","authors":["Md Munir Hasan","Jeremy Holleman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-30T17:43:59Z","doi":"10.1109/tcsii.2023.3263048","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/isas60782.2023.10391395","name":"Spiking Neural Network for Enhanced Mobile Robots’ Navigation Control","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isas60782.2023.10391395","authors":["Brwa Abdulrahman Abubaker","Saadaldeen Rashid Ahmed","Ari Taha Guron","Mohammed Fadhil","Sameer Algburi","Bikhtiyar Friyad Abdulrahman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-17T18:22:24Z","doi":"10.1109/isas60782.2023.10391395","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/iceei.2017.8312365","name":"Evolving spiking neural network (ESNN) and harmony search algorithm (HSA) for parameter optimization","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iceei.2017.8312365","authors":["Zulhairi Mi Yusuf","Haza Nuzly Abdull Hamed","Lizawati Mi Yusuf","Mohd Adham Isa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-16T15:50:36Z","doi":"10.1109/iceei.2017.8312365","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.2139/ssrn.4069757","name":"Low-Voltage Solution-Processed Artificial Optoelectronic Hybrid-Integrated Neuron Based on 2d Mxene for Multi-Task Spiking Neural Network","source":"crossref","abstract":"Incorporating optoelectronic integrated capability into artificial neurons can offer critical benefits of tunable device properties, diverse functions, and efficient computing capacity for artificial intelligent system. However, current reports are mostly focused on artificial neurons using an electric-driving mono-mode, while a facile and efficient approach to integrate electrical and optical signals is still lacking. Herein, a multifunctional optoelectronic hybrid-integrated neuron based on Ag nanoparticles-decorated MXene is proposed to achieve optoelectronic spatiotemporal information integration with low operating voltage of 0.93 V and high on/off ratio of 103, which are superior to those of majority of artificial neurons. An integrated visual perception system is developed by integrating artificial synapses, artificial optoelectronic neuron and robotic hand to emulate human conditional response. By integrating the optical sensory signals and electrical training signals, the response time of the system is significantly reduced. Finally, benefiting from the ability of spatiotemporal information integration, a multi-task pattern recognition in the spiking neural network composed of artificial synapses and neurons is completed, which can simultaneously recognize the digit patterns and rotation angles. Hence, this work exhibits the superiority in sensory and recognition tasks, which can pave the way for future application in neuromorphic circuits.","url":"https://doi.org/10.2139/ssrn.4069757","authors":["Rengjian Yu","Xianghong Zhang","Changsong Gao","Enlong Li","Yujie Yan","Yuanyuan Hu","Huipeng Chen","Tailiang Guo","Rui Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-29T23:16:34Z","doi":"10.2139/ssrn.4069757","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/dsins60115.2023.10455649","name":"Learning Spiking Neural Network from Easy to Hard Task","source":"crossref","abstract":"","url":"https://doi.org/10.1109/dsins60115.2023.10455649","authors":["Lingling Tang","Jiangtao Hu","Hua Yu","Surui Liu","Jielei Chu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-06T18:49:23Z","doi":"10.1109/dsins60115.2023.10455649","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1007/978-981-95-4094-5_33","name":"Deep Spiking Neural Networks FPGA Implementation Based on Multichannel Time-Multiplexed Architecture","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-95-4094-5_33","authors":["Xianghong Lin","Chengyang Xie","Ruidong Ma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-15T07:00:13Z","doi":"10.1007/978-981-95-4094-5_33","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1117/12.3071478","name":"Low-power embedded control system for tea machinery based on spiking neural networks (SNN)","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3071478","authors":["Shijun Guo","Yongjun Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-25T18:19:24Z","doi":"10.1117/12.3071478","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/eiconrus.2018.8317253","name":"Spiking neural network model MATLAB implementation based on Izhikevich mathematical model for control systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/eiconrus.2018.8317253","authors":["Konstantin S. Sayarkin","Alexey V. Popov","Anton A. Zhilenkov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-19T22:04:56Z","doi":"10.1109/eiconrus.2018.8317253","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1016/j.array.2023.100323","name":"Advancements in spiking neural network communication and synchronization techniques for event-driven neuromorphic systems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.array.2023.100323","authors":["Mahyar Shahsavari","David Thomas","Marcel van Gerven","Andrew Brown","Wayne Luk"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-05T05:52:25Z","doi":"10.1016/j.array.2023.100323","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1016/j.swevo.2026.102499","name":"SNN-RET: A spiking neural network with reference-guided environmental selection and turbulence for multi- and many-objective optimization","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.swevo.2026.102499","authors":["Issam Zidi","Salim El Khediri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-10T16:18:49Z","doi":"10.1016/j.swevo.2026.102499","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1609/aaai.v40i10.37769","name":"SpikingIR: A Novel Converted Spiking Neural Network for Efficient Image Restoration","source":"crossref","abstract":"Image restoration has made great progress with the rise of deep learning, but its energy consumption limits its real-world applications. Spiking Neural Networks (SNNs) are seen as energy-efficient alternatives to Artificial Neural Networks (ANNs). Applying SNNs to image restoration (IR) remains challenging, primarily due to the limited information capacity of spike-based signals. This limitation leads to quantization errors and information loss, while IR tasks are highly sensitive to output precision and error. Thus, the restoration performance suffers significantly. To address this challenge, we propose SpikingIR, an ANN-to-SNN conversion framework for IR that reduces information loss and quantization error. SpikingIR mainly consists of two components: Convolutional Pixel Mapping (CPM) and Membrane Potential Reuse Neuron (MPRN), which are designed to alleviate quantization errors and information loss in the output and intermediate layers, respectively. Specifically, CPM maps discrete outputs into a continuous space, better aligning with pixel-level details. From the perspective of information entropy, we show that outputs of CPM contain more information than the original outputs. MPRN introduces a post-processing step with relaxed firing conditions to extract residual membrane potential, reducing information waste. Furthermore, we fine-tune the converted model to jointly optimize both accuracy and energy efficiency. Experimental results demonstrate that SpikingIR achieves performance comparable to ANN counterparts across various IR benchmarks while reducing energy consumption by up to 50%.","url":"https://doi.org/10.1609/aaai.v40i10.37769","authors":["Yang Ouyang","Zihan Cheng","Xiaotong Luo","Guoqi Li","Yanyun Qu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-17T23:41:56Z","doi":"10.1609/aaai.v40i10.37769","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.2139/ssrn.5588055","name":"Complementary Dopaminergic Temporal Control for STDP-Based Learning in Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5588055","authors":["Daniel Casanueva Morato","Pablo Sánchez Cuevas","Juan P. Domínguez-Morales","Antonio Ríos Navarro","Gabriel Jimenez-Moreno"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-10T18:51:10Z","doi":"10.2139/ssrn.5588055","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.7554/elife.106871.1.sa3","name":"Reviewer #1 (Public review): Neural signatures of motor memories emerge in neural network models","source":"crossref","abstract":"","url":"https://doi.org/10.7554/elife.106871.1.sa3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-27T14:32:12Z","doi":"10.7554/elife.106871.1.sa3","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.7717/peerj-cs.3554","name":"Parameter efficient hybrid spiking-quantum convolutional neural network with surrogate gradient and quantum data-reupload","source":"crossref","abstract":"The rapid advancement of artificial intelligence (AI) and deep learning (DL) has catalyzed the emergence of several optimization-driven subfields, notably neuromorphic computing and quantum machine learning. Leveraging the differentiable nature of hybrid models, researchers have explored their potential to address complex problems through unified optimization strategies. One such development is the Spiking Quantum Neural Network (SQNN), which combines principles from spiking neural networks (SNNs) and quantum computing. However, existing SQNN implementations often depend on pretrained SNNs due to the non-differentiable nature of spiking activity and the limited scalability of current SNN encoders. In this work, we propose a novel architecture—Spiking-Quantum Data Re-upload Convolutional Neural Network (SQDR-CNN)—that enables joint training of convolutional SNNs and quantum circuits within a single backpropagation framework. Unlike its predecessor, SQDR-CNN allow convergence to reasonable performance without the reliance of pretrained spiking encoder and subsetting datasets. We also clarified some theoretical foundations, testing new design using quantum data-reupload with different training algorithm-initialization and evaluate the performance of the proposed model under noisy simulated quantum environments. As a result, we were able to achieve 86% of the mean top-performing accuracy of the state of the art (SOTA) SNN baselines, yet uses only 0.5% of the smallest spiking model’s parameters. Through this integration of neuromorphic and quantum paradigms, we aim to open new research directions and foster technological progress in multi-modal, learnable systems.","url":"https://doi.org/10.7717/peerj-cs.3554","authors":["Nhan Trong Luu","Duong Trung Luu","Nam Ngoc Pham","Thang Cong Truong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-24T08:15:21Z","doi":"10.7717/peerj-cs.3554","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1299/jsmermd.2021.2p2-h05","name":"Motion Estimation of Visual Target Using Event-Based Vision and Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1299/jsmermd.2021.2p2-h05","authors":["Shinsuke YASUKAWA","Hidetaka YOSHIMATSU","Kazuo ISHII"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-24T22:40:16Z","doi":"10.1299/jsmermd.2021.2p2-h05","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1007/978-3-319-59072-1_23","name":"Real-Time Classification Through a Spiking Deep Belief Network with Intrinsic Plasticity","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-59072-1_23","authors":["Fangzheng Xue","Xuyang Chen","Xiumin Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-05-30T02:41:58Z","doi":"10.1007/978-3-319-59072-1_23","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/mwscas.2017.8052952","name":"Novel spiking neural network utilizing short-term and long-term dynamics of 3-terminal resistive crossbar arrays","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mwscas.2017.8052952","authors":["Sam Wenke","Andrew Rush","Tony Bailey","Rashmi Jha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-10-24T16:21:31Z","doi":"10.1109/mwscas.2017.8052952","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.3390/electronics13061074","name":"Enabling Efficient On-Edge Spiking Neural Network Acceleration with Highly Flexible FPGA Architectures","source":"crossref","abstract":"Spiking neural networks (SNNs) promise to perform tasks currently performed by classical artificial neural networks (ANNs) faster, in smaller footprints, and using less energy. Neuromorphic processors are set out to revolutionize computing at a large scale, but the move to edge-computing applications calls for finely-tuned custom implementations to keep pushing towards more efficient systems. To that end, we examined the architectural design space for executing spiking neuron models on FPGA platforms, focusing on achieving ultra-low area and power consumption. This work presents an efficient clock-driven spiking neuron architecture used for the implementation of both fully-connected cores and 2D convolutional cores, which rely on deep pipelines for synaptic processing and distributed memory for weight and neuron states. With them, we developed an accelerator for an SNN version of the LeNet-5 network trained on the MNIST dataset. At around 5.5 slices/neuron and only 348 mW, it is able to use 33% less area and four times less power per neuron as current state-of-the-art implementations while keeping low simulation step times.","url":"https://doi.org/10.3390/electronics13061074","authors":["Samuel López-Asunción","Pablo Ituero"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-15T04:47:05Z","doi":"10.3390/electronics13061074","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/ipc60965.2024.10799650","name":"High Speed Time Series Prediction with a Photonic Spiking Neural Network Built with a Single VCSEL","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ipc60965.2024.10799650","authors":["D. Owen-Newns","L. Jaurigue","J. Robertson","A. Adair","J. Jaurigue","K. Lüdge","A. Hurtado"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-20T18:55:55Z","doi":"10.1109/ipc60965.2024.10799650","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.23919/ccc52363.2021.9549972","name":"Effect of local excitation-inhibition ratio on word recognition in hierarchical spiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.23919/ccc52363.2021.9549972","authors":["Ting Ye","Jiang Wang","Kai Li","Tianshi Gao","Guosheng Yi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-10-07T04:24:31Z","doi":"10.23919/ccc52363.2021.9549972","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/eiconrus.2018.8317249","name":"The scalable spiking neural network automatic generation in MATLAB focused on the hardware implementation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/eiconrus.2018.8317249","authors":["Alexey V. Popov","Konstantin S. Sayarkin","Anton A. Zhilenkov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-19T18:04:56Z","doi":"10.1109/eiconrus.2018.8317249","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/icsmd64214.2024.10920604","name":"SpikingVPR: Spiking Neural Network-Based Feature Aggregation for Visual Place Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icsmd64214.2024.10920604","authors":["Gulin Wang","Ziliang Ren","Qieshi Zhang","Jun Cheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-21T19:01:35Z","doi":"10.1109/icsmd64214.2024.10920604","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/tnn.2010.2050600","name":"Recognition of Partially Occluded and Rotated Images With a Network of Spiking Neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnn.2010.2050600","authors":["Joo-Heon Shin","David Smith","Waldemar Swiercz","Kevin Staley","J Terry Rickard","Javier Montero","Lukasz A Kurgan","Krzysztof J Cios"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-11-10T20:53:44Z","doi":"10.1109/tnn.2010.2050600","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.7554/elife.106871.1.sa1","name":"Reviewer #3 (Public review): Neural signatures of motor memories emerge in neural network models","source":"crossref","abstract":"","url":"https://doi.org/10.7554/elife.106871.1.sa1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-27T14:32:12Z","doi":"10.7554/elife.106871.1.sa1","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/ijcnn.2006.246612","name":"On the Design of a Low Power Compact Spiking Neuron Cell Based on Charge-Coupled Synapses","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.246612","authors":["Yajie Chen","S. Hall","L. McDaid","O. Buiu","P. Kelly"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T11:27:21Z","doi":"10.1109/ijcnn.2006.246612","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1504/ijmc.2026.10072144","name":"Optimised deep convolutional spiking neural network for accurate long-term and short-term rainfall forecasting in climate prediction systems","source":"crossref","abstract":"","url":"https://doi.org/10.1504/ijmc.2026.10072144","authors":["Moorthy Agoramoorthy","K. Ananthajothi","M. Amanullah"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-27T13:00:10Z","doi":"10.1504/ijmc.2026.10072144","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1016/j.sigpro.2024.109595","name":"Multi-directional feature fusion super-resolution network based on nonlinear spiking neural P systems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.sigpro.2024.109595","authors":["Lulin Ye","Chi Zhou","Hong Peng","Jun Wang","Zhicai Liu","Antonio Ramírez-de-Arellano"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-04T16:33:02Z","doi":"10.1016/j.sigpro.2024.109595","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/iccwamtip47768.2019.9067549","name":"Using Meta-Heuristic Algorithm in Spiking Neural Network for Pattern Recognition Tasks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccwamtip47768.2019.9067549","authors":["Regina Esi Turkson","Sichao Liu","Edward Y. Baagyere","Moses J. Eghan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-04-17T00:46:56Z","doi":"10.1109/iccwamtip47768.2019.9067549","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/iscas.2018.8351509","name":"A Neuromorphic Approach to Path Integration: A Head-Direction Spiking Neural Network with Vision-driven Reset","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas.2018.8351509","authors":["Raphaela Kreiser","Matteo Cartiglia","Julien N.P. Martel","Jorg Conradt","Yulia Sandamirskaya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-05-04T22:00:05Z","doi":"10.1109/iscas.2018.8351509","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1609/aaai.v40i3.37175","name":"A Closer Look at Knowledge Distillation in Spiking Neural Network Training","source":"crossref","abstract":"Spiking Neural Networks (SNNs) become popular due to excellent energy efficiency, yet facing challenges for effective model training. Recent works improve this by introducing knowledge distillation (KD) techniques, with the pre-trained artificial neural networks (ANNs) used as teachers and the target SNNs as students. This is commonly accomplished through a straightforward element-wise alignment of intermediate features and prediction logits from ANNs and SNNs, often neglecting the intrinsic differences between their architectures. Specifically, ANN's outputs exhibit a continuous distribution, whereas SNN's outputs are characterized by sparsity and discreteness. To mitigate this issue, we introduce two innovative KD strategies. Firstly, we propose the Saliency-scaled Activation Map Distillation (SAMD), which aligns the spike activation map of the student SNN with the class-aware activation map of the teacher ANN. Rather than performing KD directly on the raw features of ANN and SNN, our SAMD directs the student to learn from saliency activation maps that exhibit greater semantic and distribution consistency. Additionally, we propose a Noise-smoothed Logits Distillation (NLD), which utilizes Gaussian noise to smooth the sparse logits of student SNN, facilitating the alignment with continuous logits from teacher ANN. Extensive experiments on multiple datasets demonstrate the effectiveness of our methods.","url":"https://doi.org/10.1609/aaai.v40i3.37175","authors":["Xu Liu","Na Xia","Jinxing Zhou","Jingyuan Xu","Dan Guo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-17T22:57:26Z","doi":"10.1609/aaai.v40i3.37175","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/ijcnn52387.2021.9534061","name":"Bio-inspired Model Based on Global-Local Hybrid Learning in Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn52387.2021.9534061","authors":["Yuchen Wang","Xiaobin Wang","Hong Qu","Ya Zhang","Yi Chen","Xiaoling Luo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-20T21:27:41Z","doi":"10.1109/ijcnn52387.2021.9534061","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1101/2024.04.24.590949","name":"Damage explains function in spiking neural networks representing central pattern generator","source":"preprints","abstract":"Abstract Complex biological systems evolved to control dynamics in the presence of noisy and often unpredictable inputs. The staple example is locomotor control, which is vital for survival. Control of locomotion results from interactions between multiple systems--from passive dynamics of inverted pendulum governing body motion to coupled neural oscillators that integrate predictive forward and sensory feedback signals. The neural dynamic computations are expressed in the rhythmogenic spinal network termed the central pattern generator (CPG). While a system of ordinary differential equations or a rate model is typically “good enough” to describe the CPG function, the computations performed by thousands of neurons in vertebrates are poorly understood. To study the distributed computations of a well-defined neural dynamic system, we developed a CPG model for gait expressed with the spiking neural networks (SNN). The SNN-CPG model faithfully recreated the input-output relationship of the rate model, describing the modulation of gait phase characteristics. The degradation of distributed computation within elements of the SNN-CPG model was further studied with “lesion” experiments. We found that lesioning flexor or extensor elements, with otherwise identical structural organization of reciprocal networks, affected differently the overall CPG computation. This result mimics experimental observations. Moreover, the increasing general excitability within the network can compensate for the loss of function after progressive lesions. This observation may explain the response to spinal stimulation and propose a novel theoretical framework for degraded computations and their applications within restorative technologies.","url":"https://doi.org/10.1101/2024.04.24.590949","authors":["Yuriy Pryyma","Sergiy Yakovenko"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.04.24.590949","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1016/j.neunet.2025.108413","name":"ELAI-SGCN: An explainable lightweight adaptive information-perceiving spiking graph convolutional network for EEG-based emotion recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.108413","authors":["Jingxin Liu","Zikai Song","Xihang Qiu","Ran Cai","Jian Zhang","Lixian Zhu","Fuze Tian","Bin Hu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-05T00:33:45Z","doi":"10.1016/j.neunet.2025.108413","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1016/j.neunet.2023.05.007","name":"Evolution-communication spiking neural P systems with energy request rules","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2023.05.007","authors":["Liping Wang","Xiyu Liu","Minghe Sun","Yuzhen Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-09T17:27:02Z","doi":"10.1016/j.neunet.2023.05.007","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/ccaaw.2019.8904899","name":"Spiking Neural Network for Asset Allocation Implemented Using the TrueNorth System","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ccaaw.2019.8904899","authors":["Chris Yakopcic","Nayim Rahman","Tanvir Atahary","Md. Zahangir Alom","Tarek M. Taha","Alex Beigh","Scott Douglass"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-11-25T14:13:36Z","doi":"10.1109/ccaaw.2019.8904899","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1504/ijcvr.2024.10066617","name":"Human activity recognition using binarised spiking neural network with remora optimisation algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1504/ijcvr.2024.10066617","authors":["T. Eswarlal","Francis H. Shajin","Rajesh Kumar Singh","T. Senthil Prakash"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-18T13:02:59Z","doi":"10.1504/ijcvr.2024.10066617","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1016/j.engappai.2023.106322","name":"Event-driven spiking neural network based on membrane potential modulation for remote sensing image classification","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.engappai.2023.106322","authors":["Li-Ye Niu","Ying Wei","Yue Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-24T10:57:45Z","doi":"10.1016/j.engappai.2023.106322","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1080/09540091.2026.2710947","name":"Fuzzy spiking neural network-based neuroadaptive cooperative control for nonlinear UAV systems","source":"crossref","abstract":"","url":"https://doi.org/10.1080/09540091.2026.2710947","authors":["Zhengshan Dong","Wude He","Yongcheng Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-29T19:03:01Z","doi":"10.1080/09540091.2026.2710947","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1088/1742-6596/1914/1/012036","name":"Radar Emitter Identification Based on Fully Connected Spiking Neural Network","source":"crossref","abstract":"Abstract In the face of the increasing complex electromagnetic environment and new radar system, it is difficult to extract radar emitter characteristics based on manual mode to meet requirements of modern cognitive electronic warfare. In order to improve the intelligence level of radar emitter identification, a new method based on Spiking Neuron Network (SNN) for radar emitter identification is proposed in this paper. Firstly, five kinds of common radar signals are converted into two-dimensional gray scale images by using time-frequency analysis method. Then, the images are converted into spikes by Poisson coder, which are put into a fully connected spiking neural network for training and emitter identification. Finally, the simulation results prove the validity of this method by comparing with the traditional neural network.","url":"https://doi.org/10.1088/1742-6596/1914/1/012036","authors":["LI Wei","Zhu Wei-gang","Pang Hong-feng","Zhao Hong-yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-05-24T17:11:38Z","doi":"10.1088/1742-6596/1914/1/012036","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.70675/4fd8e4cazff5fz42f1z9c8bz7f1d3ae33dfd","name":"The influence of spiking and variability on dynamics and computations in recurrent neural networks","source":"crossref","abstract":"Dynamique et computations dans les réseaux de neurones récurrents : influence des potentiels d’action et de la variabilité Les neurones du cerveau forment des réseaux qui sont le substrat du comportement et de l’exécution de calculs. Les modèles de réseaux neuronaux récurrents permettent d’étudier comment les calculs pertinents pour le comportement émergent de la dynamique collective de nombreux neurones d’un réseau. Une limitation commune de ces modèles est qu’ils sont souvent difficiles à interpréter. Les réseaux neuronaux récurrents à faible rang, récemment développés, sont des modèles analytiques qui expliquent comment les connexions entre les neurones d’un réseau produisent une dynamique à faible dimension qui sert de substrat aux calculs. Cependant, les réseaux récurrents de rang faible représentent les neurones comme des unités abstraites qui communiquent avec un taux de décharge continu, alors que les neurones dans le cerveau communiquent en utilisant des potentiels d’action discrets. Dans un premier projet, nous examinons dans quelle mesure les résultats des modèles à faible rang peuvent être transférés à des réseaux de neurones à potentiels d'action qui sont plus plausibles d’un point de vue biologique. Pour ceci, nous ajoutons une connectivité de faible rang à une connectivité excitatrice-inhibitrice aléatoire et nous comparons systématiquement les résultats des réseaux de taux à des réseaux de neurones intégrés et tire, les deux réseaux ayant une partie de la connectivité de faible rang statistiquement équivalente. Nous montrons que les prédictions du champ moyen des réseaux de rate nous permettent d’identifier la dynamique à basse dimension à activité moyenne constante de la population pour plusieurs régimes d'activité, tels que les oscillations hors phase et les manifolds lents. Dans l’ensemble, nous avons constaté que la dynamique des réseaux à potentiels d'action avec une connectivité de faible rang est bien prédite par les réseaux de rate, mais avec une variabilité supplémentaire significative de l’activité. Dans un second projet, nous étudions les implications computationnelles du bruit dans les modèles de réseaux effectuant des tâches de reproduction d’intervalles de temps. Dans les expériences chez l'humain, l’une des principales caractéristiques est l’augmentation de la variabilité des intervalles produits. Nous montrons tout d’abord que l’ajout de bruit dans des réseaux entraînés conduit à une variabilité scalaire, indépendamment du type de bruit ou du type de connectivité. Par ailleurs, nous examinons les origines de la variabilité scalaire en étudiant des modèles simplifiés de rampe à seuil. Enfin, nous montrons que les réseaux avec une connectivité de faible rang biaisent les sorties vers la moyenne de la distribution d’entrée, ce qui est cohérent avec l’inférence bayésienne.","url":"https://doi.org/10.70675/4fd8e4cazff5fz42f1z9c8bz7f1d3ae33dfd","authors":["Ljubica Cimeša"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-08T11:52:14Z","doi":"10.70675/4fd8e4cazff5fz42f1z9c8bz7f1d3ae33dfd","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1101/2023.11.16.567361","name":"Autapses enable temporal pattern recognition in spiking neural networks","source":"crossref","abstract":"ABSTRACT Most sensory stimuli are temporal in structure. How action potentials encode the information incoming from sensory stimuli remains one of the central research questions in neuroscience. Although there is evidence that the precise timing of spikes represents information in spiking neuronal networks, information processing in spiking networks is still not fully understood. One feasible way to understand the working mechanism of a spiking network is to associate the structural connectivity of the network with the corresponding functional behaviour. This work demonstrates the structure-function mapping of spiking networks evolved (or handcrafted) for a temporal pattern recognition task. The task is to recognise a specific order of the input signals so that the Out put neurone of the network spikes only for the correct placement and remains silent for all others. The minimal networks obtained for this task revealed the twofold importance of autapses in recognition; first, autapses simplify the switching among different network states. Second, autapses enable a network to maintain a network state, a form of memory. To show that the recognition task is accomplished by transitions between network states, we map the network states of a functional spiking neural network (SNN) onto the states of a finite-state transducer (FST, a formal model of computation that generates output symbols, here: spikes or no spikes at specific times, in response to input, here: a series of input signals). Finally, based on our understanding, we define rules for constructing the topology of a network handcrafted for recognising a subsequence of signals (pattern) in a particular order. The analysis of minimal networks recognising patterns of different lengths (two to six) revealed a positive correlation between the pattern length and the number of autaptic connections in the network. Furthermore, in agreement with the behaviour of neurones in the network, we were able to associate specific functional roles of ‘locking,’ ‘switching,’ and ‘accepting’ to neurones.","url":"https://doi.org/10.1101/2023.11.16.567361","authors":["Muhammad Yaqoob","Volker Steuber","Borys Wróbel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-17T15:35:19Z","doi":"10.1101/2023.11.16.567361","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1016/j.neunet.2013.01.011","name":"Investigating the computational power of spiking neurons with non-standard behaviors","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2013.01.011","authors":["Stylianos Kampakis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-02-08T23:02:21Z","doi":"10.1016/j.neunet.2013.01.011","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/ijcnn.2009.5178751","name":"Hebbian learning with winner take all for spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2009.5178751","authors":["Ankur Gupta","Lyle N. Long"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-08-05T14:59:01Z","doi":"10.1109/ijcnn.2009.5178751","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/ijcnn.2018.8489135","name":"Transferring State Representations in Hierarchical Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2018.8489135","authors":["Barna Zajzon","Renato Duarte","Abigail Morrison"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-10-19T22:25:09Z","doi":"10.1109/ijcnn.2018.8489135","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/amlds63918.2025.11159365","name":"LightSNN: Lightweight Architecture Search for Sparse and Accurate Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/amlds63918.2025.11159365","authors":["Yesmine Abdennadher","Giovanni Perin","Riccardo Mazzieri","Jacopo Pegoraro","Michele Rossi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-16T17:32:27Z","doi":"10.1109/amlds63918.2025.11159365","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/metroxraine54828.2022.9967583","name":"Experimental validation of an analog spiking neural network with STDP learning rule in CMOS technology","source":"crossref","abstract":"","url":"https://doi.org/10.1109/metroxraine54828.2022.9967583","authors":["Elisabetta Polidori","Giovanni Camisa","Alireza Mesri","Giorgio Ferrari","Cristina Polidori","Michele Mastella","Enrico Prati"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-05T23:43:02Z","doi":"10.1109/metroxraine54828.2022.9967583","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1145/3716368.3735294","name":"Benchmarking Spiking Network Partitioning Methods on Loihi 2","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3716368.3735294","authors":["William Severa","Felix Wang","Yang Ho","Fred Rothganger","Anurag Daram","Efrain Gonzalez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-27T13:58:23Z","doi":"10.1145/3716368.3735294","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/miucc66482.2025.11196827","name":"Indirect Time of Flight Near Field LiDAR Depth Correction Using Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/miucc66482.2025.11196827","authors":["Mena Nagiub","Thorsten Beuth","Ganesh Sistu","Heinrich Gotzig","Ciarán Eising"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-21T17:07:00Z","doi":"10.1109/miucc66482.2025.11196827","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.52202/079017-1003","name":"Exact Gradients for Stochastic Spiking Neural Networks Driven by Rough Signals","source":"crossref","abstract":"","url":"https://doi.org/10.52202/079017-1003","authors":["Christian Holberg","Cristopher Salvi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-03T11:20:56Z","doi":"10.52202/079017-1003","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1007/978-3-031-68409-8_2","name":"A Discrete Time Stochastic Neural Network Model","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-68409-8_2","authors":["Antonio Galves","Eva Löcherbach","Christophe Pouzat"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-16T16:03:00Z","doi":"10.1007/978-3-031-68409-8_2","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/icbdse70225.2026.11635321","name":"A Spiking Neural Network-Based Pixel-Level Visual Dynamic Navigation Localization Algorithm for High-Speed Aerial Vehicles","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icbdse70225.2026.11635321","authors":["Lanting Cao","Baohua Xu","Jiabin Yuan","Yuqian Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-10T19:18:08Z","doi":"10.1109/icbdse70225.2026.11635321","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1007/s42600-023-00306-7","name":"Deep convolutional spiking neural network fostered automatic detection and classification of breast cancer from mammography images","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s42600-023-00306-7","authors":["T. Senthil Prakash","G. Kannan","Salini Prabhakaran","Bhagirath Parshuram Prajapati"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-11T06:03:30Z","doi":"10.1007/s42600-023-00306-7","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1016/j.bspc.2014.11.009","name":"Nonsubsampled shearlet based CT and MR medical image fusion using biologically inspired spiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.bspc.2014.11.009","authors":["Sneha Singh","Deep Gupta","R.S. Anand","Vinod Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-03-25T13:22:36Z","doi":"10.1016/j.bspc.2014.11.009","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1007/s10489-023-04553-0","name":"Research Progress of spiking neural network in image classification: a review","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s10489-023-04553-0","authors":["Li-Ye Niu","Ying Wei","Wen-Bo Liu","Jun-Yu Long","Tian-hao Xue"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-08T08:03:32Z","doi":"10.1007/s10489-023-04553-0","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1007/978-3-030-30487-4_58","name":"Multi-objective Spiking Neural Network Hardware Mapping Based on Immune Genetic Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-30487-4_58","authors":["Junxiu Liu","Xingyue Huang","Yongchuang Huang","Yuling Luo","Su Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-09-08T23:02:47Z","doi":"10.1007/978-3-030-30487-4_58","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/tr.2026.3708694","name":"STFP-SNN: Spiking Time-Frequency Patching Spiking Neural Network for Enhanced Fault Diagnosis","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tr.2026.3708694","authors":["Shilong Zhu","Jun Wang","Weiguo Huang","Shuang Li","Jinzhao Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-01T19:36:05Z","doi":"10.1109/tr.2026.3708694","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1007/11731177_7","name":"A System for Transmitting a Coherent Burst of Activity Through a Network of Spiking Neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1007/11731177_7","authors":["J. Bose","S. B. Furber","J. L. Shapiro"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-03-10T03:45:04Z","doi":"10.1007/11731177_7","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.3390/app11052059","name":"Quantized Weight Transfer Method Using Spike-Timing-Dependent Plasticity for Hardware Spiking Neural Network","source":"crossref","abstract":"A hardware-based spiking neural network (SNN) has attracted many researcher’s attention due to its energy-efficiency. When implementing the hardware-based SNN, offline training is most commonly used by which trained weights by a software-based artificial neural network (ANN) are transferred to synaptic devices. However, it is time-consuming to map all the synaptic weights as the scale of the neural network increases. In this paper, we propose a method for quantized weight transfer using spike-timing-dependent plasticity (STDP) for hardware-based SNN. STDP is an online learning algorithm for SNN, but we utilize it as the weight transfer method. Firstly, we train SNN using the Modified National Institute of Standards and Technology (MNIST) dataset and perform weight quantization. Next, the quantized weights are mapped to the synaptic devices using STDP, by which all the synaptic weights connected to a neuron are transferred simultaneously, reducing the number of pulse steps. The performance of the proposed method is confirmed, and it is demonstrated that there is little reduction in the accuracy at more than a certain level of quantization, but the number of pulse steps for weight transfer substantially decreased. In addition, the effect of the device variation is verified.","url":"https://doi.org/10.3390/app11052059","authors":["Sungmin Hwang","Hyungjin Kim","Byung-Gook Park"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-02-25T21:16:53Z","doi":"10.3390/app11052059","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1007/s11042-023-17371-w","name":"An automatic multi-class lung disease classification using deep learning based bidirectional long short term memory with spiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11042-023-17371-w","authors":["Praveena Kakarla","C. Vimala","S. Hemachandra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-27T10:01:48Z","doi":"10.1007/s11042-023-17371-w","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1016/j.neunet.2025.107154","name":"Towards parameter-free attentional spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107154","authors":["Pengfei Sun","Jibin Wu","Paul Devos","Dick Botteldooren"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-16T17:57:40Z","doi":"10.1016/j.neunet.2025.107154","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.3389/fnins.2025.1593580","name":"SpiNeRF: direct-trained spiking neural networks for efficient neural radiance field rendering","source":"crossref","abstract":"Spiking neural networks (SNNs) have recently demonstrated significant progress across various computational tasks, due to their potential for energy efficiency. Neural radiance fields (NeRFs) excel at rendering high-quality 3D scenes but require substantial energy consumption, with limited exploration of energy-saving solutions from a neuromorphic approach. In this paper, we present SpiNeRF, a novel method that integrates the sequential processing capabilities of SNNs with the ray-casting mechanism of NeRFs, aiming to enhance compatibility and unlock new prospects for energy-efficient 3D scene synthesis. Unlike conventional SNN encoding schemes, our method considers the spatial continuity inherent in NeRF, achieving superior rendering quality. To further improve training and inference efficiency, we adopt a hybrid volumetric representation that allows the predefinition and masking of invalid sampled points along pixel-rendering rays. However, this masking introduces irregular temporal lengths, making it intractable for hardware processors, such as graphics processing units (GPUs), to conduct effective parallel training. To address this issue, we present two methods: Temporal padding (TP) and temporal condensing-and-padding (TCP). Experiments on multiple datasets demonstrate that our method outperforms previous SNN encoding schemes and artificial neural network (ANN) quantization methods in both rendering quality and energy efficiency. Compared to the full-precision ANN baseline, our method reduces energy consumption by up to 72.95% while maintaining comparable synthesis quality. Further verification using a neuromorphic hardware simulator shows that TCP-based SpiNeRF achieves additional energy efficiency gains over the ANN-based approaches by leveraging the advantages of neuromorphic computing. Codes are in https://github.com/Ikarosy/SpikingNeRF-of-CASIA .","url":"https://doi.org/10.3389/fnins.2025.1593580","authors":["Xingting Yao","Qinghao Hu","Fei Zhou","Tielong Liu","Zitao Mo","Zeyu Zhu","Zhengyang Zhuge","Jian Cheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-23T12:46:16Z","doi":"10.3389/fnins.2025.1593580","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1145/3400286.3418274","name":"Solving the Multi-class Classification Task in Spiking Neural Network by using Supervised Spiking Learning Rule with a Consistent Competitive Mechanism","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3400286.3418274","authors":["Viet-Ngu Cong Huynh","Keon Myung Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-11-25T16:46:55Z","doi":"10.1145/3400286.3418274","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/ijcnn64981.2025.11229023","name":"Genetic Predictors of Social and Cognitive Outcomes in People with Ultra-High-Risk of Psychosis Using Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn64981.2025.11229023","authors":["Zohreh Doborjeh","Balkaran Singh","Alexander Sumich","Maryam Doborjeh","Wilson Wen Bin Goh","Nikola Kasabov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T18:46:15Z","doi":"10.1109/ijcnn64981.2025.11229023","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/nice65350.2025.11065428","name":"A feedback control optimizer for online and hardware-aware training of Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nice65350.2025.11065428","authors":["Matteo Saponati","Chiara De Luca","Giacomo Indiveri","Benjamin Grewe"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-08T13:36:20Z","doi":"10.1109/nice65350.2025.11065428","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1016/j.jneumeth.2025.110401","name":"Exploring temporal information dynamics in Spiking Neural Networks: Fast Temporal Efficient Training","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.jneumeth.2025.110401","authors":["Changjiang Han","Li-Juan Liu","Hamid Reza Karimi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-25T16:18:33Z","doi":"10.1016/j.jneumeth.2025.110401","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1007/978-981-97-9282-5_9","name":"Medical Image Processing with Spiking Neural P Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-9282-5_9","authors":["Gexiang Zhang","Sergey Verlan","Tingfang Wu","Francis George C. Cabarle","Jie Xue","David Orellana-Martín","Jianping Dong","Luis Valencia-Cabrera","Mario J. Pérez-Jiménez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-13T12:14:30Z","doi":"10.1007/978-981-97-9282-5_9","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1038/s41598-022-05883-8","name":"A neuromorphic spiking neural network detects epileptic high frequency oscillations in the scalp EEG","source":"crossref","abstract":"Abstract Interictal High Frequency Oscillations (HFO) are measurable in scalp EEG. This development has aroused interest in investigating their potential as biomarkers of epileptogenesis, seizure propensity, disease severity, and treatment response. The demand for therapy monitoring in epilepsy has kindled interest in compact wearable electronic devices for long-term EEG recording. Spiking neural networks (SNN) have emerged as optimal architectures for embedding in compact low-power signal processing hardware. We analyzed 20 scalp EEG recordings from 11 pediatric focal lesional epilepsy patients. We designed a custom SNN to detect events of interest (EoI) in the 80–250 Hz ripple band and reject artifacts in the 500–900 Hz band. We identified the optimal SNN parameters to detect EoI and reject artifacts automatically. The occurrence of HFO thus detected was associated with active epilepsy with 80% accuracy. The HFO rate mirrored the decrease in seizure frequency in 8 patients ( p = 0.0047). Overall, the HFO rate correlated with seizure frequency (rho = 0.90 CI [0.75 0.96], p &lt; 0.0001, Spearman’s correlation). The fully automated SNN detected clinically relevant HFO in the scalp EEG. This study is a further step towards non-invasive epilepsy monitoring with a low-power wearable device.","url":"https://doi.org/10.1038/s41598-022-05883-8","authors":["Karla Burelo","Georgia Ramantani","Giacomo Indiveri","Johannes Sarnthein"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-02T06:06:03Z","doi":"10.1038/s41598-022-05883-8","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1016/b978-0-44-329202-6.00003-1","name":"Copyright","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-44-329202-6.00003-1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-31T19:14:15Z","doi":"10.1016/b978-0-44-329202-6.00003-1","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1016/j.neunet.2025.107863","name":"Decoding natural visual scenes via learnable representations of neural spiking sequences","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107863","authors":["Jing Peng","Shanshan Jia","Jiyuan Zhang","Yongxing Wang","Zhaofei Yu","Jian K. Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-16T05:11:43Z","doi":"10.1016/j.neunet.2025.107863","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1051/e3sconf/202130901162","name":"Convolutional and Spiking Neural Network Models for Crop Yield Forecasting","source":"crossref","abstract":"Prediction of Crop yield focuses primarily on agriculture research which will have a significant effect on making decisions such as import-export, pricing and distribution of specific crops. Predicting accurately with well-timed forecasts is important, but it is a difficult task due to numerous complex factors. Mostly crops like wheat, rice, peas, pulses, sugar cane, tea, cotton, green houses, corn, and soybean can all be used to forecast crop yields. We considered corn dataset to predict the yield for 13 different states in United States. Crop development and progression are strongly affected by climatic changes and unpredictability. Predicting crop yield well before harvest time will support farmers for selling and storing their crops. Agriculture involves large datasets and knowledge processes. Factors such as Weather Components, Soil Components, Management practices, genotype and their interactions are used in predicting Corn Yield. Precise crop growth generally necessitates a complete overview of the functional correlations between yield and all these interactive variables, which necessitates the use of large datasets and complex algorithms to demonstrate. Various Machine Learning models, Deep Learning models, and Artificial Neural Network algorithms are used for predicting. Deep Neural Network Models such as Convolution Neural Networks (CNN), Spiking Neural Networks (SNN), and Recurrent Neural Networks (RNN) are used to assess corn yield. Integrating CNN, RNN and SNN models outperformed than individual model performance.","url":"https://doi.org/10.1051/e3sconf/202130901162","authors":["G. Karuna","K. Pravallika","K. Anuradha","V. Srilakshmi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-10-07T08:52:32Z","doi":"10.1051/e3sconf/202130901162","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1007/s10710-011-9130-9","name":"Hardware spiking neural network prototyping and application","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s10710-011-9130-9","authors":["Seamus Cawley","Fearghal Morgan","Brian McGinley","Sandeep Pande","Liam McDaid","Snaider Carrillo","Jim Harkin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-04-01T20:28:26Z","doi":"10.1007/s10710-011-9130-9","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.52202/079017-4346","name":"Autonomous Driving with Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.52202/079017-4346","authors":["Rui-Jie Zhu","Ziqing Wang","Leilani Gilpin","Jason Eshraghian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-03T11:20:56Z","doi":"10.52202/079017-4346","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/ijcnn48605.2020.9206751","name":"Multivariate Time Series Classification Using Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn48605.2020.9206751","authors":["Haowen Fang","Amar Shrestha","Qinru Qiu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-30T00:40:33Z","doi":"10.1109/ijcnn48605.2020.9206751","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.31224/4692","name":"Fuzzy SuperHyperGraph Neural Network (F-SHGNN)","source":"crossref","abstract":"Graph theory investigates relationships among entities through mathematical structures composed of vertices (nodes) and edges (connections) [1]. A hypergraph generalizes the classical graph by introducing hyperedges, which can join any number of vertices rather than just two, thereby enabling the modeling of complex multi-way relationships [2]. Building on this, the concept of a SuperHyperGraph has been proposed as a further extension of hypergraphs and has recently become a subject of active research [3, 4]. Graph Neural Networks (GNNs) are among the most extensively studied frameworks in artificial intelligence [5, 6]. The HyperGraph Neural Network (HGNN) extends GNNs by leveraging the expressive power of hypergraphs to capture higher-order dependencies [7, 8]. More recently, SuperHyperGraph Neural Networks have begun to emerge as an additional generalization [9]. Furthermore, these models have been augmented with fuzzy logic, giving rise to Fuzzy Graph Neural Networks and Fuzzy HyperGraph Neural Networks(cf. [10]). In this paper, we introduce and investigate the Fuzzy SuperHyperGraph Neural Network (F-SHGNN), a novel framework that integrates and extends SuperHyperGraph Neural Networks, Fuzzy Graph Neural Networks, and Fuzzy HyperGraph Neural Networks.","url":"https://doi.org/10.31224/4692","authors":["Takaaki Fujita"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-11T11:54:04Z","doi":"10.31224/4692","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/ijcnn.2015.7280668","name":"GPU-based fast parameter optimization for phenomenological spiking neural models","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2015.7280668","authors":["Zafeirios Fountas","Murray Shanahan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-10-01T21:48:02Z","doi":"10.1109/ijcnn.2015.7280668","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1016/j.neunet.2009.02.002","name":"Selective attention model with spiking elements","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2009.02.002","authors":["David Chik","Roman Borisyuk","Yakov Kazanovich"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-02-22T02:58:09Z","doi":"10.1016/j.neunet.2009.02.002","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/vtc2025-spring65109.2025.11174863","name":"Sparsified Federated Learning With Spiking Neural Networks: Resistance Against Byzantine Attacks While Lowering Communication Traffics","source":"crossref","abstract":"","url":"https://doi.org/10.1109/vtc2025-spring65109.2025.11174863","authors":["Manh V. Nguyen","Liang Zhao","Bobin Deng","Shaoen Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T17:36:40Z","doi":"10.1109/vtc2025-spring65109.2025.11174863","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1016/b978-0-44-329202-6.00013-4","name":"Acronyms","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-44-329202-6.00013-4","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-31T19:14:36Z","doi":"10.1016/b978-0-44-329202-6.00013-4","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1162/neco_a_00605","name":"Spiking Neural P Systems with Thresholds","source":"crossref","abstract":"Spiking neural P systems with weights are a new class of distributed and parallel computing models inspired by spiking neurons. In such models, a neuron fires when its potential equals a given value (called a threshold). In this work, spiking neural P systems with thresholds (SNPT systems) are introduced, where a neuron fires not only when its potential equals the threshold but also when its potential is higher than the threshold. Two types of SNPT systems are investigated. In the first one, we consider that the firing of a neuron consumes part of the potential (the amount of potential consumed depends on the rule to be applied). In the second one, once a neuron fires, its potential vanishes (i.e., it is reset to zero). The computation power of the two types of SNPT systems is investigated. We prove that the systems of the former type can compute all Turing computable sets of numbers and the systems of the latter type characterize the family of semilinear sets of numbers. The results show that the firing mechanism of neurons has a crucial influence on the computation power of the SNPT systems, which also answers an open problem formulated in Wang, Hoogeboom, Pan, Păun, and Pérez-Jiménez ( 2010 ).","url":"https://doi.org/10.1162/neco_a_00605","authors":["Xiangxiang Zeng","Xingyi Zhang","Tao Song","Linqiang Pan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-04-08T00:15:53Z","doi":"10.1162/neco_a_00605","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/itme.2016.0086","name":"Weighted Spiking Neural P Systems with Structural Plasticity Working in Maximum Spiking Strategy","source":"crossref","abstract":"","url":"https://doi.org/10.1109/itme.2016.0086","authors":["Mingming Sun","Jianhua Qu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-07-13T20:47:48Z","doi":"10.1109/itme.2016.0086","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1016/j.ins.2022.07.152","name":"Spiking CapsNet: A spiking neural network with a biologically plausible routing rule between capsules","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.ins.2022.07.152","authors":["Dongcheng Zhao","Yang Li","Yi Zeng","Jihang Wang","Qian Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-08-01T01:45:53Z","doi":"10.1016/j.ins.2022.07.152","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1587/nolta.16.290","name":"Color image recognition with color opponency-based filters and two-layer spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1587/nolta.16.290","authors":["Hiroki Shinagawa","Gouhei Tanaka"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-31T22:30:11Z","doi":"10.1587/nolta.16.290","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/cyber-ai66431.2025.11233776","name":"Efficacy of Spiking Neural Networks for Intrusion Detection Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cyber-ai66431.2025.11233776","authors":["Leonard Knapp","Sven Nitzsche","Matthias Börsig","Alexandru Vasilache","Ingmar Baumgart","Juergen Becker"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T18:47:04Z","doi":"10.1109/cyber-ai66431.2025.11233776","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.12681/eadd/58262","name":"Photonic neuromorphic processors based on semiconductor lasers' dynamics for reservoir computing and spiking neural networks","source":"crossref","abstract":"Η παρούσα διδακτορική διατριβή μελετά την ανάπτυξη φωτονικών νευρομορφικών επεξεργαστών (ΝΕ) που απευθύνονται στις εξής τρεις κρίσιμες προκλήσεις των Big Data και του Internet of Things: την υψηλή ταχύτητα επεξεργασίας, την χαμηλή κατανάλωση ισχύος και την ελαχιστοποίηση του υλικού. Η αντιμετώπιση των εν λόγω προκλήσεων ανατέθηκε στα βιοεμπνευσμένα Τεχνητά Νευρωνικά Δίκτυα. Ωστόσο, η ταυτόχρονη επίτευξη δύο βασικών, αλλά αντικρουόμενων στόχων περιόρισε την αποτελεσματικότητά τους, καθώς ήταν αναγκαία η αύξηση του αριθμού των νευρώνων και των συνάψεων παράλληλα με τον περιορισμό της καταναλισκόμενης ισχύος και της πολυπλοκότητας. Σε αυτό το πλαίσιο, επιλέχθηκαν οι χαμηλής κατανάλωσης ΝΕ, οι οποίοι όμως αδυνατούσαν να μειώσουν την αυξανόμενη πολυπλοκότητα και συνδεσιμότητα. Για το λόγο αυτό, οι ΝΕ υιοθέτησαν αρχές των Time Delay Network (TDN) που υλοποιούν χρονικά πολυπλεγμένους νευρώνες και συνάψεις. Μειώθηκαν, έτσι, οι απαιτήσεις του υλικού, αλλά και ο ρυθμός επεξεργασίας. Στόχος της παρούσας διατριβής είναι η αξιοποίηση της υψηλής ταχύτητας των φωτονικών δομών, ώστε να ενισχυθούν οι δυνατότητες επεξεργασίας των TDN ΝΕ. Κατ’ αρχάς αναλύθηκε ένας φωτονικός TDN ΝΕ βασισμένος σε ένα spin VCSEL κβαντικών τελειών. Το προταθέν σύστημα επιτυγχάνει τον τετραπλασιασμό του αριθμού των νευρώνων συγκλίνοντας σε επιδόσεις με τους σύγχρονους επεξεργαστές με τη χρήση λιγότερων νευρώνων συγκριτικά με λοιπές παρόμοιες διατάξεις. Επιπλέον, η χρήση πολλαπλών μασκών και η έγχυση των μη διαμορφωμένων πεδίων βελτιστοποιεί τις επιδόσεις του συστήματος και ελαχιστοποιεί τις απαιτήσεις του υλικού. Συνεχίζοντας, ερευνήθηκε πειραματικά και αριθμητικά ένας επαναδιαμορφώσιμος φωτονικός TDN ΝΕ ερειδόμενος σε Fabry-Perot (FP) λέιζερ. Επιβεβαιώθηκε πειραματικά η δυνατότητα αύξησης του αριθμού των εικονικών νευρώνων και των επιδόσεων του FP-TDN αξιοποιώντας την πολύτροπη εκπομπή του FP. Μετέπειτα απεδείχθη αριθμητικά η αύξηση του ρυθμού επεξεργασίας του FP-TDN χωρίς να υπάρξει μείωση της ακρίβειας του επεξεργαστή μέσω μιας νέας τεχνικής Φασματοχρονικής Πολυπλεξίας (SPTM). O FP TDN ΝΕ σε συνδυασμό με το SPTM κατέγραψε ρυθμούς σφάλματος ίσους με 10-4 χρησιμοποιώντας μήκος ανάδρασης 140 ps, ενώ η HD-FEC συμβατότητα του συστήματος επιτεύχθηκε ακόμη και για χρόνους των 60 ps. Σημειώνεται ότι ο FP-TDN κατέγραψε ακρίβεια 95.95% στην κατηγοριοποίηση των εικόνων του MNIST επιτυγχάνοντας ρυθμό 255.1Mimages/sec. Στο επόμενο κεφάλαιο παρατίθεται ένα χρονικά πολυπλεγμένο δίκτυο με spiking νευρώνες. Ειδικότερα, παρουσιάστηκε ένα βαθύ φωτονικό spiking συνελικτικό νευρωνικό δίκτυο βασισμένο σε VCSEL νευρώνες, το οποίο εκμεταλλευόμενο τη χρονική πολυπλεξία δύναται να ρυθμίσει τον αριθμό των πραγματικών νευρώνων από 62 έως 2020 ανάλογα με τις απαιτήσεις του ρυθμού επεξεργασίας. Το παρόν δίκτυο επέδειξε δυνατότητες μάθησης χωρίς επιτήρηση, υψηλή ανοχή στο θόρυβο και ρυθμούς επεξεργασίας από 5 ns έως 720 ns ανά εικόνα. Τέλος, αναπτύχθηκε ένα spiking TDN βασισμένο σε VCSEL, το οποίο δύναται να κατηγοριοποιήσει με υψηλή ακρίβεια δεδομένα από τις βάσεις δεδομένων Iris, MNIST, αλλά και από πειραματικές εικόνες κυτταρομετρίας καταναλίσκοντας μόλις 3.23pJ ανά εικόνα. Ο συγκεκριμένος ΝΕ ενoποιεί για πρώτη φορά τα πεδία των ΝΕ και των νευρομορφικών αισθητήρων σε μια κοινή πλατφόρμα, ανοίγοντας το δρόμο για τη μελέτη κλιμακούμενων και ενεργειακά αποδοτικών ΝΕ για εφαρμογές πραγματικού χρόνου.","url":"https://doi.org/10.12681/eadd/58262","authors":["Μενέλαος Σκοντράνης"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-24T08:32:27Z","doi":"10.12681/eadd/58262","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/atc63255.2024.10908168","name":"A Skin Cancer Detector Using a Spiking Neural Network Based on All-Digital Resonate-and-Fire Neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1109/atc63255.2024.10908168","authors":["Trung-Khanh Le","Do-Cuong Nguyen","Trong-Tu Bui","Duc-Hung Le"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-07T18:33:20Z","doi":"10.1109/atc63255.2024.10908168","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.551Z"},{"id":"doi:10.1016/j.bspc.2020.102170","name":"Energy efficient ECG classification with spiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.bspc.2020.102170","authors":["Zhanglu Yan","Jun Zhou","Weng-Fai Wong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-28T13:26:06Z","doi":"10.1016/j.bspc.2020.102170","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1080/03772063.2023.2297382","name":"Health Monitoring in IoT with Context-Aware Deep Convolutional Spiking Neural Network and Woodpecker Mating Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1080/03772063.2023.2297382","authors":["R. Arivalahan","T. Vinoth"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-12T06:20:16Z","doi":"10.1080/03772063.2023.2297382","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.551Z"},{"id":"doi:10.1609/aaai.v38i10.28964","name":"Enhancing Training of Spiking Neural Network with Stochastic Latency","source":"crossref","abstract":"Spiking neural networks (SNNs) have garnered significant attention for their low power consumption when deployed on neuromorphic hardware that operates in orders of magnitude lower power than general-purpose hardware. Direct training methods for SNNs come with an inherent latency for which the SNNs are optimized, and in general, the higher the latency, the better the predictive powers of the models, but at the same time, the higher the energy consumption during training and inference. Furthermore, an SNN model optimized for one particular latency does not necessarily perform well in lower latencies, which becomes relevant in scenarios where it is necessary to switch to a lower latency because of the depletion of onboard energy or other operational requirements. In this work, we propose Stochastic Latency Training (SLT), a direct training method for SNNs that optimizes the model for the given latency but simultaneously offers a minimum reduction of predictive accuracy when shifted to lower inference latencies. We provide heuristics for our approach with partial theoretical justification and experimental evidence showing the state-of-the-art performance of our models on datasets such as CIFAR-10, DVS-CIFAR-10, CIFAR-100, and DVS-Gesture. Our code is available at https://github.com/srinuvaasu/SLT","url":"https://doi.org/10.1609/aaai.v38i10.28964","authors":["Srinivas Anumasa","Bhaskar Mukhoty","Velibor Bojkovic","Giulia De Masi","Huan Xiong","Bin Gu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-25T10:44:02Z","doi":"10.1609/aaai.v38i10.28964","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.551Z"},{"id":"doi:10.11648/j.ijse.20230701.11","name":"Time-Reduced Model for Multilayer Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.11648/j.ijse.20230701.11","authors":["Yanjing Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-16T08:23:44Z","doi":"10.11648/j.ijse.20230701.11","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1007/s42064-024-0256-y","name":"Energy efficiency analysis of Spiking Neural Networks for space applications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s42064-024-0256-y","authors":["Paolo Lunghi","Stefano Silvestrini","Dominik Dold","Gabriele Meoni","Alexander Hadjiivanov","Dario Izzo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-17T02:49:23Z","doi":"10.1007/s42064-024-0256-y","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1016/b978-0-44-329202-6.00005-5","name":"Preface","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-44-329202-6.00005-5","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-31T19:14:16Z","doi":"10.1016/b978-0-44-329202-6.00005-5","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1007/978-3-031-15934-3_43","name":"A Spiking Neural Network Based on Neural Manifold for Augmenting Intracortical Brain-Computer Interface Data","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-15934-3_43","authors":["Shengjie Zheng","Wenyi Li","Lang Qian","Chenggang He","Xiaojian Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-06T00:02:53Z","doi":"10.1007/978-3-031-15934-3_43","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1007/978-3-030-30487-4_56","name":"UAV Detection: A STDP Trained Deep Convolutional Spiking Neural Network Retina-Neuromorphic Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-30487-4_56","authors":["Paul Kirkland","Gaetano Di Caterina","John Soraghan","Yiannis Andreopoulos","George Matich"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-09-08T19:02:47Z","doi":"10.1007/978-3-030-30487-4_56","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1038/s41598-026-38839-3","name":"SPCNNet: spiking point cloud neural network for morphological neuron classification","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-38839-3","authors":["Xianghong Lin","Mingshuai Yu","Xiangwen Wang"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-38839-3","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1587/transfun.e92.a.1690","name":"A CMOS Spiking Neural Network Circuit with Symmetric/Asymmetric STDP Function","source":"crossref","abstract":"","url":"https://doi.org/10.1587/transfun.e92.a.1690","authors":["Hideki TANAKA","Takashi MORIE","Kazuyuki AIHARA"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-07-08T05:57:28Z","doi":"10.1587/transfun.e92.a.1690","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/icons69015.2025.00034","name":"Spiking Neural Networks for Low-Power Vibration-Based Predictive Maintenance","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons69015.2025.00034","authors":["Alexandru Vasilache","Sven Nitzsche","Christian Kneidl","Mikael Tekneyan","Moritz Neher","Juergen Becker"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-21T21:07:17Z","doi":"10.1109/icons69015.2025.00034","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1007/s11227-025-08064-2","name":"Enhancing the representational capacity and scalability of ResNet architectures based on spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11227-025-08064-2","authors":["Qi Jin","Jiang Xie"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-19T09:17:34Z","doi":"10.1007/s11227-025-08064-2","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/icra.2018.8460197","name":"FaNeuRobot: A Framework for Robot and Prosthetics Control Using the NeuCube Spiking Neural Network Architecture and Finite Automata Theory","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icra.2018.8460197","authors":["Kaushalya Kumarasinghe","Mahonri Owen","Denise Taylor","Nikola Kasabov","Chi Kit"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-09-21T18:28:03Z","doi":"10.1109/icra.2018.8460197","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1504/ijcvr.2017.081231","name":"A hybrid differential evolution algorithm for parameter tuning of evolving spiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1504/ijcvr.2017.081231","authors":["Abdulrazak Yahya Saleh","Siti Mariyam Shamsuddin","Haza Nuzly Abdull Hamed"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-01-02T07:30:12Z","doi":"10.1504/ijcvr.2017.081231","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.21105/joss.03956","name":"BCImat: a Matlab-based framework for Intracortical\nBrain-Computer Interfaces and their simulation with an artificial\nspiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.21105/joss.03956","authors":["Enrico Ferrea","Pierre Morel","Alexander Gail"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-07-05T15:58:33Z","doi":"10.21105/joss.03956","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/led.2023.3265065","name":"Efficient Convolutional Processing of Spiking Neural Network With Weight-Sharing Filters","source":"crossref","abstract":"","url":"https://doi.org/10.1109/led.2023.3265065","authors":["Seunghwan Song","Bosung Jeon","Munhyeon Kim","Jae-Joon Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-06T17:37:29Z","doi":"10.1109/led.2023.3265065","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/asap65064.2025.00025","name":"SpiRec: Soft-Logic Architecture Exploration of Reconfigurable Systems for Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/asap65064.2025.00025","authors":["Xunqin Lai","Federico Corradi","Siva Satyendra Sahoo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-20T18:28:20Z","doi":"10.1109/asap65064.2025.00025","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/icarm65671.2025.11293539","name":"Autonomous Driving Using Spiking Neural Networks on Dynamic Vision Sensor Data: A Case Study of Traffic Light Change Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icarm65671.2025.11293539","authors":["Xuelei Chen","Sotirios Spanogianopoulos"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-22T18:39:45Z","doi":"10.1109/icarm65671.2025.11293539","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1561/9781680836523.ch4","name":"4. Stacks of Software Stacks","source":"crossref","abstract":"","url":"https://doi.org/10.1561/9781680836523.ch4","authors":["Andrew Rowley","Oliver Rhodes","Petrut Bogdan","Christian Brenninkmeijer","Simon Davidson","Donal Fellows","Steve Furber","Andrew Gait","Michael Hopkins","David Lester","Mantas Mikaitis","Luis Plana"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-07-05T10:13:16Z","doi":"10.1561/9781680836523.ch4","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.3389/fnins.2021.635098","name":"A Functional Spiking Neural Network of Ultra Compact Neurons","source":"crossref","abstract":"We demonstrate that recently introduced ultra-compact neurons (UCN) with a minimal number of components can be interconnected to implement a functional spiking neural network. For concreteness we focus on the Jeffress model, which is a classic neuro-computational model proposed in the 40’s to explain the sound directionality detection by animals and humans. In addition, we introduce a long-axon neuron , whose architecture is inspired by the Hodgkin-Huxley axon delay-line and where the UCNs implement the nodes of Ranvier. We then interconnect two of those neurons to an output layer of UCNs, which detect coincidences between spikes propagating down the long-axons. This functional spiking neural neuron circuit with biological relevance is built from identical UCN blocks, which are simple enough to be made with off-the-shelf electronic components. Our work realizes a new, accessible and affordable physical model platform , where neuroscientists can construct arbitrary mid-size spiking neuronal networks in a lego -block like fashion that work in continuous time. This should enable them to address in a novel experimental manner fundamental questions about the nature of the neural code and to test predictions from mathematical models and algorithms of basic neurobiology research. The present work aims at opening a new experimental field of basic research in Spiking Neural Networks to a potentially large community, which is at the crossroads of neurobiology, dynamical systems, theoretical neuroscience, condensed matter physics, neuromorphic engineering, artificial intelligence, and complex systems.","url":"https://doi.org/10.3389/fnins.2021.635098","authors":["Pablo Stoliar","Olivier Schneegans","Marcelo J. Rozenberg"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-02-25T08:47:57Z","doi":"10.3389/fnins.2021.635098","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.23919/chain.2024.000003","name":"Cost-Effective and High-Speed Implementation of Brain-Like Spiking Neural Network with Encoding Architectures on FPGA","source":"crossref","abstract":"","url":"https://doi.org/10.23919/chain.2024.000003","authors":["Zhen Cao","Ziyi Zhang","Qi Sun","Biao Hou","Licheng Jiao","Yintang Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-13T19:41:59Z","doi":"10.23919/chain.2024.000003","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1016/j.procs.2018.11.111","name":"Estimation of the influence of spiking neural network parameters on classification accuracy using a genetic algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.procs.2018.11.111","authors":["Aleksandr Sboev","Alexey Serenko","Roman Rybka","Danila Vlasov","Andrey Filchenkov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-12-11T07:40:19Z","doi":"10.1016/j.procs.2018.11.111","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/isocc50952.2020.9333106","name":"A Prediction Scheme in Spiking Neural Network (SNN) Hardware for Ultra-low Power Consumption","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isocc50952.2020.9333106","authors":["Jeonggyu Yang","Taigon Song"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-02-02T15:51:49Z","doi":"10.1109/isocc50952.2020.9333106","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1364/oe.487047","name":"BP-based supervised learning algorithm for multilayer photonic spiking neural network and hardware implementation","source":"crossref","abstract":"We introduce a supervised learning algorithm for photonic spiking neural network (SNN) based on back propagation. For the supervised learning algorithm, the information is encoded into spike trains with different strength, and the SNN is trained according to different patterns composed of different spike numbers of the output neurons. Furthermore, the classification task is performed numerically and experimentally based on the supervised learning algorithm in the SNN. The SNN is composed of photonic spiking neuron based on vertical-cavity surface-emitting laser which is functionally similar to leaky-integrate and fire neuron. The results prove the demonstration of the algorithm implementation on hardware. To seek ultra-low power consumption and ultra-low delay, it is great significance to design and implement a hardware-friendly learning algorithm of photonic neural networks and realize hardware-algorithm collaborative computing.","url":"https://doi.org/10.1364/oe.487047","authors":["Yahui Zhang","Shuiying Xiang","Yanan Han","Xingxing Guo","Wu Zhang","Qinggui Tan","Genquan Han","Yue Hao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-20T11:00:16Z","doi":"10.1364/oe.487047","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1101/2024.10.02.616330","name":"Optimal Control of Spiking Neural Networks","source":"preprints","abstract":"Abstract Control theory provides a natural language to describe multi-areal interactions and flexible cognitive tasks such as covert attention or brain-machine interface (BMI) experiments, which require finding adequate inputs to a local circuit in order to steer its dynamics in a context-dependent manner. In optimal control, the target dynamics should maximize a notion of long-term value along trajectories, possibly subject to control costs. Because this problem is, in general, not tractable, current approaches to the control of networks mostly consider simplified settings (e.g., variations of the Linear-Quadratic Regulator). Here, we present a mathematical framework for optimal control of recurrent networks of stochastic spiking neurons with low-rank connectivity. An essential ingredient is a control-cost that penalizes deviations from the default dynamics of the network (specified by its recurrent connections), which motivates the controller to use the default dynamics as much as possible. We derive a Bellman Equation that specifies a Value function over the low-dimensional network state (LDS), and a corresponding optimal control input. The optimal control law takes the form of a feedback controller that provides external excitatory (inhibitory) synaptic input to neurons in the recurrent network if their spiking activity tends to move the LDS towards regions of higher (lower) Value. We use our theory to study the problem of steering the state of the network towards particular terminal regions which can lie either in or out of regions in the LDS with slow dynamics, in analogy to standard BMI experiments. Our results provide the foundation of a novel approach with broad applicability that unifies bottom-up and top-down perspectives on neural computation.","url":"https://doi.org/10.1101/2024.10.02.616330","authors":["Tiago Costa","Juan R. Castiñeiras de Saa","Alfonso Renart"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.10.02.616330","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1016/j.neunet.2024.107106","name":"Neural network emulator for atmospheric chemical ODE","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.107106","authors":["Zhi-Song Liu","Petri Clusius","Michael Boy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-02T17:17:04Z","doi":"10.1016/j.neunet.2024.107106","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.22215/etd/2026-17159","name":"Adaptive Hierarchical Spiking Neural Networks for Event-Driven Multi-Agent Cooperation on the Edge","source":"crossref","abstract":"","url":"https://doi.org/10.22215/etd/2026-17159","authors":["Mohammad Tayefe Ramezanlou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-22T19:42:12Z","doi":"10.22215/etd/2026-17159","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.52202/085713-1514","name":"S$^2$NN: Sub-bit Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.52202/085713-1514","authors":["Wenjie Wei","Malu Zhang","Jieyuan (Eric) Zhang","Ammar Belatreche","Shuai Wang","Yimeng Shan","Hanwen Liu","Honglin Cao","Guoqing Wang","Yang Yang","Haizhou Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-06T14:44:29Z","doi":"10.52202/085713-1514","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1016/j.neunet.2010.04.004","name":"Fitting a stochastic spiking model to neuronal current injection data","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2010.04.004","authors":["Shigeru Shinomoto"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-05-01T05:00:33Z","doi":"10.1016/j.neunet.2010.04.004","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/icicat68430.2025.11414517","name":"Autonomous Navigation in Dynamic Environments Using Spiking Neural Networks and Deep Q-Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icicat68430.2025.11414517","authors":["K.Subathra","Prathima G","K.Sundareswari","G.Shailaja","A.Prakash","Sujeet Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-09T19:55:25Z","doi":"10.1109/icicat68430.2025.11414517","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/mwscas53549.2025.11244585","name":"Lightweight Spiking Neural Networks for Low-Power EMG-Based Hand Gesture Classification on Embedded Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mwscas53549.2025.11244585","authors":["Nadia Ahmed","Shaghayegh Gomar","Arash Ahmadi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-25T18:26:55Z","doi":"10.1109/mwscas53549.2025.11244585","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/ijcnn.2011.6033496","name":"Visual attention using spiking neural maps","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2011.6033496","authors":["Roberto A. Vazquez","Bernard Girau","Jean-Charles Quinton"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-10-06T13:24:17Z","doi":"10.1109/ijcnn.2011.6033496","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.52202/085713-1206","name":"Unveiling the Spatial-temporal Effective Receptive Fields of Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.52202/085713-1206","authors":["Jieyuan (Eric) Zhang","Xiaolong Zhou","Shuai Wang","Wenjie Wei","Hanwen Liu","Qian Sun","Malu Zhang","Yang Yang","Haizhou Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-06T14:44:29Z","doi":"10.52202/085713-1206","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/ijcnn.2013.6707072","name":"Extension of neuron machine neurocomputing architecture for spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2013.6707072","authors":["Jerry B. Ahn"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-01-10T15:08:44Z","doi":"10.1109/ijcnn.2013.6707072","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1101/2020.06.26.173575","name":"Training recurrent spiking neural networks in strong coupling regime","source":"crossref","abstract":"Abstract Recurrent neural networks trained to perform complex tasks can provide insights into the dynamic mechanism that underlies computations performed by cortical circuits. However, due to a large number of unconstrained synaptic connections, the recurrent connectivity that emerges from network training may not be biologically plausible. Therefore, it remains unknown if and how biological neural circuits implement dynamic mechanisms proposed by the models. To narrow this gap, we developed a training scheme that, in addition to achieving learning goals, respects the structural and dynamic properties of a standard cortical circuit model, i.e., strongly coupled excitatory-inhibitory spiking neural networks. By preserving the strong mean excitatory and inhibitory coupling of initial networks, we found that most of trained synapses obeyed Dale’s law without additional constraints, exhibited large trial-to-trial spiking variability, and operated in inhibition-stabilized regime. We derived analytical estimates on how training and network parameters constrained the changes in mean synaptic strength during training. Our results demonstrate that training recurrent neural networks subject to strong coupling constraints can result in connectivity structure and dynamic regime relevant to cortical circuits.","url":"https://doi.org/10.1101/2020.06.26.173575","authors":["Christopher M. Kim","Carson C. Chow"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-29T19:15:16Z","doi":"10.1101/2020.06.26.173575","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/cibcb66090.2025.11177083","name":"Spiking Neural Networks for Mental Workload Classification with a Multimodal Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cibcb66090.2025.11177083","authors":["Jiahui An","Sara Irina Fabrikant","Giacomo Indiveri","Elisa Donati"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T17:36:59Z","doi":"10.1109/cibcb66090.2025.11177083","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/icecs66544.2025.11270808","name":"Adaptive LIF Spiking Neural Networks for Satellite Anomaly Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icecs66544.2025.11270808","authors":["Andrea La Gala","Mattia Tambaro","Lorenzo Stevenazzi","Gianluca Furano","Marcello De Matteis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-09T18:31:34Z","doi":"10.1109/icecs66544.2025.11270808","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1016/s0893-6080(01)00053-3","name":"Coding properties of spiking neurons: reverse and cross-correlations","source":"crossref","abstract":"","url":"https://doi.org/10.1016/s0893-6080(01)00053-3","authors":["Wulfram Gerstner"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-10-14T18:58:33Z","doi":"10.1016/s0893-6080(01)00053-3","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1088/2634-4386/accd90/v2/decision1","name":"Decision letter for \"Spiking neural networks compensate weight drift in organic neuromorphic device networks\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2634-4386/accd90/v2/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-18T17:03:24Z","doi":"10.1088/2634-4386/accd90/v2/decision1","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.15760/etd.6323","name":"An Exploration of Linear Classifiers for Unsupervised Spiking Neural Networks with Event-Driven Data","source":"crossref","abstract":"","url":"https://doi.org/10.15760/etd.6323","authors":["Wesley Chavez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-09-20T13:33:09Z","doi":"10.15760/etd.6323","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1088/2634-4386/accd90/v1/decision1","name":"Decision letter for \"Spiking neural networks compensate weight drift in organic neuromorphic device networks\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2634-4386/accd90/v1/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-18T17:03:24Z","doi":"10.1088/2634-4386/accd90/v1/decision1","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1021/acsami.3c19261.s001","name":"Efficient Spiking Neural Networks with Biologically Similar Lithium-Ion Memristor Neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acsami.3c19261.s001","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-05T10:00:40Z","doi":"10.1021/acsami.3c19261.s001","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1007/s40998-025-00792-8","name":"A Sophisticated Iterative Weighted Feature Selection (IWFS) Based Spiking Imperialist Competitive Recurrent Neural Network (SICRNN) Classification Model for Credit Card Fraud Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s40998-025-00792-8","authors":["S. Sobana","V. Diana Earshia","R. Suganthi","K. Ayyappa Swamy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-26T11:58:33Z","doi":"10.1007/s40998-025-00792-8","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.3390/app132413145","name":"A Novel Approach for Target Attraction and Obstacle Avoidance of a Mobile Robot in Unknown Environments Using a Customized Spiking Neural Network","source":"crossref","abstract":"In recent years, implementing reinforcement learning in autonomous mobile robots (AMRs) has become challenging. Traditional methods face complex trials, long convergence times, and high computational requirements. This paper introduces an innovative strategy using a customized spiking neural network (SNN) for autonomous learning and control of mobile robots (AMR) in unknown environments. The model combines spike-timing-dependent plasticity (STDP) with dopamine modulation for learning. It utilizes the Izhikevich neuron model, leading to biologically inspired and computationally efficient control systems that adapt to changing environments. The performance of the model is evaluated in a simulated environment, replicating real-world scenarios with obstacles. In the initial training phase, the model faces significant challenges. Integrating brain-inspired learning, dopamine, and the Izhikevich neuron model adds complexity. The model achieves an accuracy rate of 33% in reaching its target during this phase. Collisions with obstacles occur 67% of the time, indicating the struggle of the model to adapt to complex obstacles. However, the model’s performance improves as the study progresses to the testing phase after the robot has learned. Its accuracy surges to 94% when reaching the target, and collisions with obstacles reduce it to 6%. This shift demonstrates the adaptability and problem-solving capabilities of the model in the simulated environment, making it more competent for real-world applications.","url":"https://doi.org/10.3390/app132413145","authors":["Brwa Abdulrahman Abubaker","Jafar Razmara","Jaber Karimpour"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-11T06:56:00Z","doi":"10.3390/app132413145","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1007/978-981-19-0019-8_23","name":"Epileptic Seizure Classification Using Spiking Neural Network from EEG Signals","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-19-0019-8_23","authors":["Irshed Hussain","Dalton Meitei Thounaojam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-03T09:02:40Z","doi":"10.1007/978-981-19-0019-8_23","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1007/978-3-031-87763-6_18","name":"LKSVC: A Novel VANET Caching Method by Integrating Location-Based K-Means Clustering into Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-87763-6_18","authors":["Yuanchen Li","Lin Guan","Ziyang Zhang","George Vogiatzis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-28T02:22:36Z","doi":"10.1007/978-3-031-87763-6_18","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/dtis.2019.8735057","name":"An Augmented OxRAM Synapse for Spiking Neural Network (SNN) Circuits","source":"crossref","abstract":"","url":"https://doi.org/10.1109/dtis.2019.8735057","authors":["H. Aziza","H. Bazzi","J. Postel-Pellerin","P. Canet","M. Moreau","A. Harb"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-06-13T22:34:52Z","doi":"10.1109/dtis.2019.8735057","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1007/978-981-15-2854-5_30","name":"Automatic Bird Species Recognition Based on Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-15-2854-5_30","authors":["Ricky Mohanty","Bandi Kumar Mallik","Sandeep Singh Solanki"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-04-01T17:03:07Z","doi":"10.1007/978-981-15-2854-5_30","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1088/1674-1056/acb9f6","name":"A progressive surrogate gradient learning for memristive spiking neural network","source":"crossref","abstract":"In recent years, spiking neural networks (SNNs) have received increasing attention of research in the field of artificial intelligence due to their high biological plausibility, low energy consumption, and abundant spatio-temporal information. However, the non-differential spike activity makes SNNs more difficult to train in supervised training. Most existing methods focusing on introducing an approximated derivative to replace it, while they are often based on static surrogate functions. In this paper, we propose a progressive surrogate gradient learning for backpropagation of SNNs, which is able to approximate the step function gradually and to reduce information loss. Furthermore, memristor cross arrays are used for speeding up calculation and reducing system energy consumption for their hardware advantage. The proposed algorithm is evaluated on both static and neuromorphic datasets using fully connected and convolutional network architecture, and the experimental results indicate that our approach has a high performance compared with previous research.","url":"https://doi.org/10.1088/1674-1056/acb9f6","authors":["Shu Wang","Tao Chen","Yu Gong","Fan Sun","Si-Yuan Shen","Shu-Kai Duan","Li-Dan Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-02-08T07:26:01Z","doi":"10.1088/1674-1056/acb9f6","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/icassp49660.2025.10888909","name":"DA-LIF: Dual Adaptive Leaky Integrate-and-Fire Model for Deep Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icassp49660.2025.10888909","authors":["Tianqing Zhang","Kairong Yu","Jian Zhang","Hongwei Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-12T13:52:43Z","doi":"10.1109/icassp49660.2025.10888909","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.516Z"},{"id":"doi:10.1109/pdp.2015.60","name":"FIST: A Framework to Interleave Spiking Neural Networks on CGRAs","source":"crossref","abstract":"","url":"https://doi.org/10.1109/pdp.2015.60","authors":["Tuan Ngyen","Syed M.A.H. Jafri","Masoud Daneshtalab","Ahmed Hemani","Sergei Dytckov","Juha Plosila","Hannu Tenhunen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-04-24T21:13:52Z","doi":"10.1109/pdp.2015.60","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1007/978-3-319-32554-5_6","name":"Bayesian Optimization of Spiking Neural Network Parameters to Solving the Time Series Classification Task","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-32554-5_6","authors":["Alexey Chernyshev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-03-30T03:25:57Z","doi":"10.1007/978-3-319-32554-5_6","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1609/aaai.v40i45.41237","name":"HypoxSpike: Ternary Spiking Neural Network for Opioid Overdose Detection","source":"crossref","abstract":"Opioid overdose is a growing global health crisis that claims more than 120,000 lives annually, of which more than half use opioids alone, without access to bystander intervention. Fatal overdose events are marked by motionlessness, respiratory depression, and hypoxemia, yet current wearable systems often rely on a single biomarker, limiting detection speed and accuracy. We present HypoxSpike, a novel ternary spiking neural network designed for real-time, multi-biomarker overdose detection for low-power neuromorphic hardware, optimized for integration into shoulder-based wearables. HypoxSpike combines motion, respiration, and oxygen saturation signals, while accounting for skin tone and body physiology, thus addressing known racial bias in pulse oximetry. Our research leverages an open-source shoulder-worn dataset from 19 patients experiencing sleep apnea, exploiting the shared physiological mechanisms underlying apnea and opioid overdose. This allows a direct comparison of our model with existing overdose detection approaches. HypoxSpike classifies three stages of hypoxemia with an average accuracy of 94%, outperforming state-of-the-art shoulder-based hypoxemia estimation while reducing false positive alert rates by 23.5%. By minimizing false positives, HypoxSpike supports accurate and power-efficient overdose detection, improving trust and usability for high-risk populations often overlooked by conventional systems.","url":"https://doi.org/10.1609/aaai.v40i45.41237","authors":["Anush Lingamoorthy","Abhishek Kumar Mishra","Olumuyiwa Oni","Jacob S Brenner","Nagarajan Kandasamy","Amanda Watson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-18T07:05:47Z","doi":"10.1609/aaai.v40i45.41237","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.7873/date.2015.1085","name":"Spiking Neural Network with RRAM: Can We Use It for Real-World Application?","source":"crossref","abstract":"","url":"https://doi.org/10.7873/date.2015.1085","authors":["Tianqi Tang","Lixue Xia","Boxun Li","Rong Luo","Yiran Chen","Yu Wang","Huazhong Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-05-02T04:17:53Z","doi":"10.7873/date.2015.1085","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1007/s11760-023-02574-3","name":"Spike representation of depth image sequences and its application to hand gesture recognition with spiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11760-023-02574-3","authors":["Daisuke Miki","Kento Kamitsuma","Taiga Matsunaga"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-24T11:02:35Z","doi":"10.1007/s11760-023-02574-3","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/icons62911.2024.00024","name":"Natural Language to Verilog: Design of a Recurrent Spiking Neural Network using Large Language Models and ChatGPT","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024.00024","authors":["Paola Vitolo","George Psaltakis","Michael Tomlinson","Gian Domenico Licciardo","Andreas G. Andreou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T13:37:03Z","doi":"10.1109/icons62911.2024.00024","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1080/0954898x.2024.2385532","name":"Statement of Retraction","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2024.2385532","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-31T10:24:07Z","doi":"10.1080/0954898x.2024.2385532","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1080/0954898x.2024.2385540","name":"Statement of Retraction","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2024.2385540","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-03T07:04:47Z","doi":"10.1080/0954898x.2024.2385540","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/aicas57966.2023.10168643","name":"MF-DSNN:An Energy-efficient High-performance Multiplication-free Deep Spiking Neural Network Accelerator","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aicas57966.2023.10168643","authors":["Yue Zhang","Shuai Wang","Yi Kang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-07T18:24:30Z","doi":"10.1109/aicas57966.2023.10168643","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.23919/ofc49934.2023.10115462","name":"Spiking Neural Network Linear Equalization: Experimental Demonstration of 2km 100Gb/s IM/DD PAM4 Optical Transmission","source":"crossref","abstract":"","url":"https://doi.org/10.23919/ofc49934.2023.10115462","authors":["Georg Böcherer","Florian Strasser","Elias Arnold","Youxi Lin","Johannes Schemmel","Stefano Calabrò","Maxim Kuschnerov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-19T17:26:19Z","doi":"10.23919/ofc49934.2023.10115462","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1007/11892960_99","name":"Spiking Neural Network Based Classification of Task-Evoked EEG Signals","source":"crossref","abstract":"","url":"https://doi.org/10.1007/11892960_99","authors":["Piyush Goel","Honghai Liu","David J. Brown","Avijit Datta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-09T13:29:42Z","doi":"10.1007/11892960_99","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/cnn63506.2024.10705826","name":"Study of the Influence of Macroparameters of a Spiking Neural Network on the Quality of Image Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cnn63506.2024.10705826","authors":["Sergey V. Stasenko","Andrey A. Lebedev","Tatiana A. Levanova","Victor B. Kazantsev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-09T17:45:45Z","doi":"10.1109/cnn63506.2024.10705826","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1007/s00542-025-05995-x","name":"A novel enhanced spiking sheaf attention neural network for real-time health monitoring based on internet of things","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00542-025-05995-x","authors":["P. Chinnaraj","Deepak Chandra Uprety","Sandeep Raj","Lakshmana Phaneendra Maguluri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-07T06:55:33Z","doi":"10.1007/s00542-025-05995-x","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1016/j.jvcir.2019.102681","name":"WITHDRAWN: Time Series Analysis of Volleyball Spiking Posture Based on Quality-Guided Cyclic Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.jvcir.2019.102681","authors":["Chuanchang Zhang","Huan Tang","Zhigang Duan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-10-13T01:22:29Z","doi":"10.1016/j.jvcir.2019.102681","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/icc40277.2020.9148849","name":"Traffic Scheduling based on Spiking Neural Network in Hybrid E/O Switching Intra-Datacenter Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icc40277.2020.9148849","authors":["Ao Yu","Hui Yang","Qiuyan Yao","Kaixuan Zhan","Bowen Bao","Zhengjie Sun","Jie Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-07-27T22:26:45Z","doi":"10.1109/icc40277.2020.9148849","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.5244/c.30.94","name":"Event-Based Hough Transform in a Spiking Neural Network for Multiple Line Detection and Tracking Using a Dynamic Vision Sensor","source":"crossref","abstract":"","url":"https://doi.org/10.5244/c.30.94","authors":["Sajjad Seifozzakerini","Wei-Yun Yau","Bo Zhao","Kezhi Mao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-05-29T04:11:16Z","doi":"10.5244/c.30.94","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1007/978-981-10-0207-6_94","name":"Effects of Multi-clustered Structure on the Enhancement of Reservoir Computing of Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-10-0207-6_94","authors":["Fangzheng Xue","Anguo Zhang","Xiumin Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-01-29T09:31:07Z","doi":"10.1007/978-981-10-0207-6_94","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1117/12.2536607","name":"Neurocomputer architecture based on spiking neural network and its optoelectronic implementation","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.2536607","authors":["Oleh K. Kolesnytskyj","Vladislav V. Kutsman","Krzysztof Skorupski","Mukaddas Arshidinova"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-11-06T21:53:00Z","doi":"10.1117/12.2536607","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1007/978-3-658-45318-3_2","name":"Background","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-658-45318-3_2","authors":["Muhammad Arsalan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-01T06:02:42Z","doi":"10.1007/978-3-658-45318-3_2","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1109/tnnls.2026.3671461/mm1","name":"Spatiotemporal Decoupled Learning for Spiking Neural Networks_supp1-3671461.pdf","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnnls.2026.3671461/mm1","authors":["Jibin Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-16T20:16:06Z","doi":"10.1109/tnnls.2026.3671461/mm1","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/aicas.2019.8771614","name":"Flyintel – a Platform for Robot Navigation based on a Brain-Inspired Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aicas.2019.8771614","authors":["Yao Huang-Yu","Hsuan-Pei Huang","Yu-Chi Huang","Chung-Chuan Lo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-07-25T19:57:53Z","doi":"10.1109/aicas.2019.8771614","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.23919/date56975.2023.10136938","name":"Memristor-Spikelearn: A Spiking Neural Network Simulator for Studying Synaptic Plasticity under Realistic Device and Circuit Behaviors","source":"crossref","abstract":"","url":"https://doi.org/10.23919/date56975.2023.10136938","authors":["Yuming Liu","Angel Yanguas-Gil","Sandeep Madireddy","Yanjing Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-02T19:32:57Z","doi":"10.23919/date56975.2023.10136938","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1109/hpbdis53214.2021.9658467","name":"XNOR-BSNN: In-Memory Computing Model for Deep Binarized Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/hpbdis53214.2021.9658467","authors":["Van-Tinh Nguyen","Quang-Kien Trinh","Renyuan Zhang","Yasuhiko Nakashima"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-01-03T15:17:48Z","doi":"10.1109/hpbdis53214.2021.9658467","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1016/j.procs.2018.11.107","name":"Spiking neural network reinforcement learning method based on temporal coding and STDP","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.procs.2018.11.107","authors":["Alexander Sboev","Danila Vlasov","Roman Rybka","Alexey Serenko"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-12-11T07:40:11Z","doi":"10.1016/j.procs.2018.11.107","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1109/ijcnn60899.2024.10651169","name":"OneSpike: Ultra-low latency spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn60899.2024.10651169","authors":["Kaiwen Tang","Zhanglu Yan","Weng-Fai Wong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T17:35:05Z","doi":"10.1109/ijcnn60899.2024.10651169","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1162/neco.1997.9.2.279","name":"Fast Sigmoidal Networks via Spiking Neurons","source":"crossref","abstract":"We show that networks of relatively realistic mathematical models for biological neurons in principle can simulate arbitrary feedforward sigmoidal neural nets in a way that has previously not been considered. This new approach is based on temporal coding by single spikes (respectively by the timing of synchronous firing in pools of neurons) rather than on the traditional interpretation of analog variables in terms of firing rates. The resulting new simulation is substantially faster and hence more consistent with experimental results about the maximal speed of information processing in cortical neural systems. As a consequence we can show that networks of noisy spiking neurons are “universal approximators” in the sense that they can approximate with regard to temporal coding any given continuous function of several variables. This result holds for a fairly large class of schemes for coding analog variables by firing times of spiking neurons. This new proposal for the possible organization of computations in networks of spiking neurons systems has some interesting consequences for the type of learning rules that would be needed to explain the self-organization of such networks. Finally, the fast and noise-robust implementation of sigmoidal neural nets by temporal coding points to possible new ways of implementing feedforward and recurrent sigmoidal neural nets with pulse stream VLSI.","url":"https://doi.org/10.1162/neco.1997.9.2.279","authors":["Wolfgang Maass"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-02-24T01:43:19Z","doi":"10.1162/neco.1997.9.2.279","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1007/978-3-658-45318-3_1","name":"Introduction","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-658-45318-3_1","authors":["Muhammad Arsalan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-01T06:02:42Z","doi":"10.1007/978-3-658-45318-3_1","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.18122/td.2302.boisestate","name":"Analysis of Learning Mechanisms in Spiking Neural Networks with R(t) Elements and Memristive Synapses","source":"crossref","abstract":"As Moore's law ends, the conventional von Neumann computer architecture with binary-coded data representation has reached its bottleneck because of having separate computing and memory modules. In this architecture, continuous power is required due to sequential processing, making it challenging to improve efficiency further. The human brain can be regarded as the most energy-efficient computer architecture. In the brain, data is represented as small voltage pulses as spikes. That is why the neural units are called spiking neural networks (SNN). In SNNs, energy is required only when there is a spike, making it more energy efficient than the von-Neumann computer architecture. Therefore, in recent decades, researchers in this field have been interested in mimicking the data processing of the human brain in electronic circuits. In biological SNNs, data is propagated from one neuron to another via a synapse. When there is an incoming spike, the chemical weight changes in the synapse, and the next neuron receives the signal. In the electronic neural network, a memristor, a two-terminal nonvolatile memory element, can emulate the function of a synapse by changing its conductance while receiving a pulse. The most common learning rule in the spiking neural network is Spike-Timing-Dependent Plasticity (STDP), which refers to the change of synaptic weight with respect to the time difference between pre- and post-synaptic neural spikes. Although electronic SNNs comprised of memristors with the STDP learning rule have shown promising performance in various event-driven tasks, circuit complexity limitations and a lack of third-order parametric inclusion exist. A solution can be using a simple circuit element to modulate the memristor response.","url":"https://doi.org/10.18122/td.2302.boisestate","authors":["Farhana Afrin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-11T19:57:47Z","doi":"10.18122/td.2302.boisestate","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.21203/rs.3.rs-10584023/v1","name":"Mutual Lateral Prediction for Locally Trained Spiking Neural Networks","source":"crossref","abstract":"Abstract Spiking neural networks (SNNs) offer low-energy inference on neuromorphic hardware, but the most accurate SNNs are trained with backpropagation through time, which requires error signals that neuromorphic chips cannot broadcast and that have no biological counterpart. Predictive coding offers a route to strictly local learning, yet existing spiking formulations let neurons predict only their own feedforward drive, not the drive arriving at their neighbors. Here, we introduce MPC-SNN, a convolutional SNN trained entirely with local, backpropagationfree rules, whose central component is a learned lateral weight matrix Wlat through which each neuron predicts the feedforward input of same-layer peers. The lateral update is derived from a prediction-error objective and requires only a neuron’s own error and a peer’s preceding spike, a stricter locality than eprop or LTTS. On the 11-class DVS128 Gesture benchmark, MPC-SNN reaches 95.83% test accuracy, statistically matching the strongest local-learning baseline (DECOLLE) and exceeding deployed neuromorphic implementations by 6.2 to 8.3 points. The mechanism is active independently of accuracy: Wlat grows from near-zero initialization by up to 21.1× during pretraining. With only 25% of the labels the model retains 73.50% accuracy, an Information Retention Ratio of 2.94 relative to linear label scaling. A reported out-of-distribution experiment is included as an honest negative. To the best of the authors’ knowledge, MPCSNN is the first SNN to combine same-layer lateral predictive coding with a locally derived prediction-error rule.","url":"https://doi.org/10.21203/rs.3.rs-10584023/v1","authors":["Nitesh Kamanuru Purushotham","Pranav Kulkarni"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-19T12:52:28Z","doi":"10.21203/rs.3.rs-10584023/v1","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1002/dac.70195","name":"Optimized Resource Management Using Binarized Spiking Neural Network With Pyramid Attention and Smart Contract Blockchain for Sustainable Spectrum Allocation in 6G","source":"crossref","abstract":"ABSTRACT The rapid expansion of connected devices and the need for high‐speed communication make sustainable spectrum allocation and resource management crucial issues in 6G networks. Traditional spectrum management methods often rely on static or centralized techniques, limiting adaptability and efficiency in dynamic network environments. Additionally, these methods struggle to balance energy efficiency, latency, and spectrum utilization. To address limitations, this work proposes a novel Binarized Spiking Neural Network with Pyramid Attention Network (BSNN‐PAN)‐based spectrum allocation approach that integrates Pyramid Attention Networks (PANs) with binarized spiking neural networks (BSNNs). The approach employs Time‐to‐First‐Spike (TTFS) coding to encode input spectrum data into spike trains, which are processed by binary Integrate‐and‐Fire (IF) neurons. PAN introduces attention weights to capture multiscale spatial and temporal dependencies, enhancing feature extraction and decision‐making. The prairie dog optimization algorithm (PDOA) is applied to optimize hyperparameters such as weight, error, and loss, improving adaptability, efficiency, and resource allocation. The collaboration of the three significantly improves decision‐making efficiency and security in dynamic environments, demonstrating the added value of their technological integration. Experimental results demonstrate significant improvements, including 1.8‐kJ energy consumption, 412‐ms transaction latency, and 15‐ms average channel allocation time. These outcomes validate the proposed BSNN‐PAN framework as an effective and sustainable solution for next‐generation 6G spectrum management.","url":"https://doi.org/10.1002/dac.70195","authors":["S. K. Jameer Basha","Singamaneni Krishnapriya","G. Kirubasri","Gunjan Varshney","C. Rama Mohan","Kuldeep Chouhan","Mohan Rao Thokala","Neelima Koppala"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-31T05:45:00Z","doi":"10.1002/dac.70195","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.52202/075280-0161","name":"SparseProp: Efficient Event-Based Simulation and Training of Sparse Recurrent Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.52202/075280-0161","authors":["Rainer Engelken"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-02T13:18:04Z","doi":"10.52202/075280-0161","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1109/ijcnn55064.2022.9891951","name":"Deep Phasor Networks: Connecting Conventional and Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn55064.2022.9891951","authors":["Wilkie Olin-Ammentorp","Maxim Bazhenov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-30T19:56:04Z","doi":"10.1109/ijcnn55064.2022.9891951","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1088/2634-4386/ae8627/v2/review3","name":"Review for \"Energy-aware spike budgeting for continual learning in spiking neural networks for neuromorphic vision\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2634-4386/ae8627/v2/review3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-03T23:27:36Z","doi":"10.1088/2634-4386/ae8627/v2/review3","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.5220/0013536600004664","name":"Application of Neural Network Algorithm in Network Engineering Design","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0013536600004664","authors":["Min Yang","Jiajie Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-23T10:51:18Z","doi":"10.5220/0013536600004664","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/icarcv63323.2024.10821503","name":"A Methodology to Study the Impact of Spiking Neural Network Parameters Considering Event-Based Automotive Data","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icarcv63323.2024.10821503","authors":["Iqra Bano","Rachmad Vidya Wicaksana Putra","Alberto Marchisio","Muhammad Shafique"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-09T19:36:27Z","doi":"10.1109/icarcv63323.2024.10821503","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1109/ijcnn54540.2023.10191915","name":"A biologically-inspired locally-connected spiking network for efficient and robust ground reaction force estimation in a legged robot","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn54540.2023.10191915","authors":["Paolo Arena","Maria Francesca Pia Cusimano","Luca Patané","Poramate Manoonpong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-02T13:30:03Z","doi":"10.1109/ijcnn54540.2023.10191915","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.3389/frai.2026.1845114","name":"&lt;i&gt;S&lt;/i&gt; &lt;sup&gt;3&lt;/sup&gt;Net: a Synthesis-Segmentation-Spiking Network for Alzheimer's disease detection and segmentation.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/frai.2026.1845114","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/frai.2026.1845114","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1162/jocn.a.2582","name":"Synergistic Short-Term Synaptic Plasticity Mechanisms for Working Memory.","source":"europepmc","abstract":"Working memory (WM) is essential for almost every cognitive task. The neural and synaptic mechanisms supporting the rapid encoding and maintenance of memories in diverse tasks are the subject of an ongoing debate. The traditional view of WM as stationary persistent firing of selective neuronal populations has given room to newer ideas regarding mechanisms that support a more dynamic maintenance of multiple items. Various computational WM models based on different biologically plausible plasticity mechanisms have been proposed. We show that these proposed short-term plasticity mechanisms may not necessarily be competing explanations but instead yield interesting interactions that broaden the functional range of models on a wide set of WM task motifs and simultaneously enhance the biological plausibility of spiking neural network models, in particular of the underlying synaptic plasticity. Although reductionist models (WM function explained by one particular mechanism) are theoretically appealing and have increased our understanding of specific mechanisms, they are narrow explanations. In this study, we evaluate the interactions between three commonly proposed classes of plasticity, namely, intrinsic excitability, synaptic facilitation/augmentation, and Hebbian plasticity. We systematically test combinations of mechanisms in a spiking neural network model on a broad suite of tasks or functional motifs deemed principally important for WM operation, such as one-shot encoding, free and cued recall, and multi-item delay maintenance and updating. Our analysis of the operational task performance indicates that a composite model is superior to more reductionist variants. Importantly, we attribute the observable differences to the principle nature of specific types of plasticity.","url":"https://doi.org/10.1162/jocn.a.2582","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1162/jocn.a.2582","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3389/fncir.2026.1851817","name":"Functional implications of atypical action potential generation in the (patho)physiological brain: from developmental program to glioma.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncir.2026.1851817","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fncir.2026.1851817","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41598-026-54238-0","name":"Quantum-enhanced spiking intelligence framework for real-time anomaly detection in industrial internet of things.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-54238-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-54238-0","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.3389/frai.2026.1817837","name":"Spark: modular spiking neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/frai.2026.1817837","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/frai.2026.1817837","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1371/journal.pcbi.1014378","name":"A mean-field model of neural networks with PV and SOM interneurons reveals connectivity-based mechanisms of gamma oscillations.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pcbi.1014378","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pcbi.1014378","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1002/adma.74670","name":"Structure-Engineered Nanoporous Vanadium Oxide Memristors for Reconfigurable Synapse-Neuron Integration and Synergistic Robotic Motion.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.74670","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.74670","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1371/journal.pone.0344997","name":"Topology-aware design of spiking neural networks via modular graph architectures.","source":"europepmc","abstract":"Spiking Neural Networks (SNNs) offer a biologically plausible and energy-efficient alternative to traditional artificial neural networks (ANNs), yet their design remains constrained by limited architectural flexibility and slow training dynamics. In this work, we introduce a novel SNN framework that leverages modular graph-based topologies and explicit synaptic delays to significantly enhance both training efficiency and classification performance. Our architecture, TANet-Tiny, incorporates structured graph stages with up to 32 nodes and diverse community-driven connectivity patterns derived from KMeans clustering, Louvain modularity, and Watts–Strogatz small-world models. We integrate these topologies into a topology-aware search space and explore them via a Spatio-Temporal Topology Sampling (STTS) approach, enabling the discovery of high-performing networks without exhaustive search. Experimental results on MNIST, CIFAR-10, and CIFAR-100 demonstrate that our modular designs achieve state-of-the-art accuracy while requiring 6–10 × fewer training epochs, with top-1 accuracy reaching 99.57% on MNIST and over 92% on CIFAR-10, all with reduced parameter counts. We introduce an accuracy-per-epoch metric to quantify training efficiency and show that modularity, rather than network size, is the critical driver of performance. This work lays the groundwork for scalable, interpretable, and low-latency SNN architectures suitable for deployment in neuromorphic and edge computing environments.","url":"https://doi.org/10.1371/journal.pone.0344997","authors":["Farideh Motaghian","Soheila Nazari","Juan P. Dominguez-Morales","Reza Jafari"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pone.0344997","addedAt":"2026-09-01T01:48:24.516Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1371/journal.pcbi.1014391","name":"Multi-stable oscillations in cortical networks with two classes of inhibition.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pcbi.1014391","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pcbi.1014391","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fnbot.2026.1761767","name":"Trainable movement control using spikes and muscle-twitch dynamics.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnbot.2026.1761767","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnbot.2026.1761767","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fncom.2025.1731161","name":"Arbor-TVB: a novel multi-scale co-simulation framework with a case study on neural-level seizure generation and whole-brain propagation.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2025.1731161","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fncom.2025.1731161","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1073/pnas.2513319122","name":"Spiking world model with multicompartment neurons for model-based reinforcement learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.1073/pnas.2513319122","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1073/pnas.2513319122","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fnins.2026.1766765","name":"Learned adaptive properties for mitigation of weight perturbations in embedded spiking networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2026.1766765","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnins.2026.1766765","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1162/jocn_a_02582","name":"Synergistic Short-Term Synaptic Plasticity Mechanisms for Working Memory.","source":"europepmc","abstract":"","url":"https://doi.org/10.1162/jocn_a_02582","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1162/jocn_a_02582","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1080/26941899.2026.2619222","name":"Neurodatascience: Past, Present, and Future.","source":"europepmc","abstract":"The study of the brain is a compelling example of the power of convergent science. Over the last few decades, advances in neuroscience techniques and experimentation, as well as in data science tools to analyze the resulting data, have dramatically furthered our understanding of fundamental brain functions. Historically, it has been common for analytical approaches to have a considerable lag in development following the availability of new neuroscience techniques. However, this relationship has not simply been unidirectional, as there have been examples in which analytical developments have directly led to new scientific questions and experiments. Here we review how this interplay between neuroscience and data science advances has unfolded in the past and into the present, with a focus on electrophysiology and calcium imaging. Applying lessons learned from the past and present, we then discuss expected developments, challenges, and opportunities in the future. We end by providing recommendations on how to foster the necessary team science approach to continue the advancement of research at the intersection of neuroscience and data science, which we call neurodatascience, toward a sustainable future.","url":"https://doi.org/10.1080/26941899.2026.2619222","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1080/26941899.2026.2619222","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1371/journal.pone.0339918","name":"Autapses enable temporal pattern recognition in spiking neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pone.0339918","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pone.0339918","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41598-026-46811-4","name":"A hybrid spiking convolutional neural framework with extreme learning machine for enhanced anomaly detection in network security.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-46811-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-46811-4","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41598-026-41671-4","name":"Backpropagation-free spiking neural networks with the forward-forward algorithm.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-41671-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-41671-4","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fnins.2026.1772958","name":"Bidirectional cross-day alignment of neural spikes and behavior using a hybrid SNN-ANN algorithm.","source":"europepmc","abstract":"Recent advances in deep learning have enabled effective interpretation of neural activity patterns from electroencephalogram signals; however, challenges persist in invasive brain signals for cross-day neural decoding and simulation tasks. The inherent non-stationarity of neural dynamics and representational drift across recording sessions fundamentally limit the generalization capabilities of existing approaches. We present AlignNet, a novel framework that establishes cross-modal alignment between spiking patterns and behavioral semantics through U-based representation learning. Our architecture employs hybrid SNN-ANN autoencoders to encode neural spikes and behavior into a shared latent space, where the neural spike autoencoder incorporates multiple neuron nodes following convolution layers, and the behavior autoencoder comprises standard convolution layers. These two representations are optimized through contrastive objectives to achieve session-invariant feature learning. To address cross-day adaptation challenges, we introduce a pretraining strategy leveraging multi-session single monkey experiment data, followed by task-specific fine-tuning for neural decoding and simulation. Comprehensive evaluations demonstrate that AlignNet achieves superior performance under both single-day and cross-day conditions; meanwhile, our pretrained model effectively executes decoding and simulation tasks after fine-tuning. The hybrid SNN-ANN representations exhibit temporal consistency across multi-day recording spikes while retaining behavioral semantics, thereby advancing cross-day neural interface applications.","url":"https://doi.org/10.3389/fnins.2026.1772958","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnins.2026.1772958","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1007/s00285-026-02415-0","name":"Spiking neural models for decision-making tasks with learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s00285-026-02415-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s00285-026-02415-0","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1038/s41598-025-28901-x","name":"Development of digital hardware for a spiking image recognition network employing a novel burst-based reinforcement learning approach.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-28901-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-28901-x","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fnins.2026.1771268","name":"Editorial: Theoretical advances and practical applications of spiking neural networks, volume II.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2026.1771268","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnins.2026.1771268","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1371/journal.pbio.3003818","name":"Human neuronal firing varies with the frequency of local field potential oscillations.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pbio.3003818","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pbio.3003818","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fncom.2026.1762692","name":"Deterministic, stochastic, and mean-field PDE models in neuroscience.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2026.1762692","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fncom.2026.1762692","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41598-025-22430-3","name":"BIASNN: a biologically inspired attention mechanism in spiking neural networks for image classification.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-22430-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-22430-3","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1093/pnasnexus/pgaf284","name":"Learning and inference with correlated neural variability.","source":"europepmc","abstract":"","url":"https://doi.org/10.1093/pnasnexus/pgaf284","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1093/pnasnexus/pgaf284","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1111/psyp.70338","name":"The Pupil-Brain System at Rest: Spontaneous Pupil Fluctuations as Markers of Neuromodulatory and Network Dynamics.","source":"europepmc","abstract":"","url":"https://doi.org/10.1111/psyp.70338","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1111/psyp.70338","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3390/brainsci16010010","name":"Computational Advances in Taste Perception: From Ion Channels and Taste Receptors to Neural Coding.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/brainsci16010010","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/brainsci16010010","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1117/1.nph.13.s2.s23202","name":"Voltage imaging as a window into neural computation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1117/1.nph.13.s2.s23202","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1117/1.nph.13.s2.s23202","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.3389/fncom.2025.1661070","name":"Neural heterogeneity as a unifying mechanism for efficient learning in spiking neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2025.1661070","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fncom.2025.1661070","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1021/acsnano.5c15076","name":"A Reconfigurable Silicon Transistor for Noise-Resilient Stochastic Spiking Neural Networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.5c15076","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsnano.5c15076","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1038/s41467-025-65268-z","name":"A deterministic neuromorphic architecture with scalable time synchronization.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-65268-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-65268-z","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fnbot.2026.1757795","name":"SpikeAEC: a neuromodulation-based spiking controller for explore-exploit balancing in mobile robots.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnbot.2026.1757795","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnbot.2026.1757795","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41467-026-69121-9","name":"Decodability, sensitivity, and criticality measured through single-neuron perturbations.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-69121-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-69121-9","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1109/toh.2024.3449411","name":"VT-SGN:Spiking Graph Neural Network for Neuromorphic Visual-Tactile Fusion.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/toh.2024.3449411","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1109/toh.2024.3449411","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.3389/fncel.2026.1808258","name":"Early life shifts in cortical inhibitory-excitatory balance underlies sensitive periods and skill development.","source":"europepmc","abstract":"Early human development is characterized by sensitive periods which impact long-term cognitive and behavioral outcomes. While these windows of heightened plasticity are well documented, the cellular mechanisms that enable and regulate them remain incompletely understood. In this conceptual article, I propose that early-life shifts in cortical inhibitory-excitatory balance, driven by prolonged neurogenesis, migration, and maturation of GABAergic interneurons, play a central role in opening, shaping, and closing sensitive periods and thereby guide skill development. Drawing on evidence from human and animal studies, I synthesize findings showing that inhibitory interneurons are integrated into cortical circuits well into postnatal life, where they regulate intrinsic and sensory-driven activity, sculpt synaptic connectivity, coordinate interactions with glial cells, and progressively refine network dynamics. The developmental strengthening of inhibition alters excitation-inhibition ratios, drives the transition from highly synchronous early activity to decorrelated and efficient adult-like firing patterns, and gates critical period plasticity across cortical regions. I argue that these inhibitory processes are not merely stabilizing but actively facilitate learning by suppressing non-relevant activity and enabling the emergence of specialized functional networks. This framework highlights fundamental differences between infant and adult learning mechanisms and suggests that individual variability in inhibitory circuit development may underlie differences in cognitive trajectories and vulnerability to neurodevelopmental disorders. Together, this synthesis positions early inhibitory interneuron development as a key mechanistic substrate linking sensitive periods to lifelong skill acquisition and behavioral individuality.","url":"https://doi.org/10.3389/fncel.2026.1808258","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fncel.2026.1808258","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1007/s10827-026-00925-w","name":"Co-simulation framework combining a microscopically detailed point neuron model of the hippocampal CA1 region with the macroscopic high-resolution virtual brain model.","source":"europepmc","abstract":"The human brain is a complex adaptive system characterized by dynamic processes operating across multiple spatio-temporal scales. Capturing these dynamics requires computational models that can integrate different levels of resolution. In this work we present a multiscale co-simulation framework that couples whole-brain modeling with a detailed point-neuron model of the human hippocampal CA1 region. We used a high-resolution implementation of the \"The Virtual Brain\" (TVB), in which cortical surface mesh vertices are embedded with the Spatial Epileptor Model (SEM). At the microscale, the CA1 model captures neuronal activity at micrometer spatial and sub-millisecond temporal resolution. This integration enables the simulation of macroscale epileptic dynamics with microscale neuronal precision within anatomically grounded brain regions, facilitating cross-scale communication. These results demonstrate the potential of this approach to advance mechanism-driven, personalized medicine in clinical neuroscience.","url":"https://doi.org/10.1007/s10827-026-00925-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s10827-026-00925-w","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3389/fnins.2026.1777090","name":"A compressed sensing neuromorphic processor for sparse signal classification.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2026.1777090","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnins.2026.1777090","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41467-026-72119-y","name":"Accelerating spiking neural networks with photonic reconfigurable devices.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-72119-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-72119-y","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fnins.2025.1623497","name":"Review of deep learning models with Spiking Neural Networks for modeling and analysis of multimodal neuroimaging data.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2025.1623497","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fnins.2025.1623497","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1007/s00422-026-01043-7","name":"Fluctuation-response relations for a two-stage population of spiking neurons stimulated by common noise.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s00422-026-01043-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s00422-026-01043-7","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3390/jemr19010017","name":"Eye Movement Classification Using Neuromorphic Vision Sensors.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/jemr19010017","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/jemr19010017","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1021/acsami.5c19107","name":"Algorithm-Compatible Single-Transistor Neuron and Al/ZrO&lt;sub&gt;2&lt;/sub&gt;/TiO&lt;sub&gt;2&lt;/sub&gt;/AlO&lt;sub&gt;&lt;i&gt;x&lt;/i&gt;&lt;/sub&gt; Memristor Synapse Kernel for Spiking Neural Networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c19107","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c19107","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1038/s41467-025-65394-8","name":"Efficient event-based delay learning in spiking neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-65394-8","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-65394-8","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41598-025-18004-y","name":"A mean-field approach to criticality in spiking neural networks for reservoir computing.","source":"europepmc","abstract":"Abstract Spiking Neural Networks (SNNs) exhibit their optimal information-processing capability at the edge of chaos, but tuning them to this critical regime in reservoir-computing architectures usually relies on costly trial-and-error or plasticity-driven adaptation. This work presents an analytical framework for configuring in the critical regime a SNN-based reservoir with a highly general topology. Specifically, we derive and solve a mean-field equation that governs the evolution of the average membrane potential in leaky integrate-and-fire neurons, and provide an approximation for the critical point. This framework reduces the need for an extensive online fine-tuning, offering a streamlined path to near-optimal network performance from the outset. Through extensive numerical experiments, we validate the theoretical predictions by analyzing the network’s spiking dynamics and quantifying its computational capacity using the information-based Lempel-Ziv-Welch complexity near criticality. Finally, we explore self-organized quasi-criticality by implementing a local homeostatic learning rule for synaptic weights, demonstrating that the network’s dynamics remain close to the theoretical critical point. Beyond AI, our approach and findings also have significant implications for computational neuroscience, providing a principled framework for quantitatively understanding how (neuro)biological networks exploit criticality for efficient information processing. The paper is accompanied by Python code, enabling the reproducibility of the findings.","url":"https://doi.org/10.1038/s41598-025-18004-y","authors":["Ruggero Freddi","Francesco Cicala","Laura Marzetti","Alessio Basti"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-18004-y","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1007/s11571-026-10415-5","name":"A brain-constrained neural model of cognition and language with NEST: transitioning from the Felix framework.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-026-10415-5","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s11571-026-10415-5","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1371/journal.pone.0321830","name":"Long-term neuron tracking reveals balance of stability and plasticity in functional properties.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pone.0321830","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pone.0321830","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.7554/elife.106827","name":"Biologically informed cortical models predict optogenetic perturbations.","source":"europepmc","abstract":"","url":"https://doi.org/10.7554/elife.106827","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.7554/elife.106827","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"epmc:MED41407321","name":"Multi-scale imaging and recording of in-vivo neural activity.","source":"europepmc","abstract":"","url":"https://pubmed.ncbi.nlm.nih.gov/41407321/","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1523/eneuro.0029-26.2026","name":"Electrical Coupling within Thalamocortical Networks Cumulatively Reduces Cortical Correlation to Sensory Inputs.","source":"europepmc","abstract":"","url":"https://doi.org/10.1523/eneuro.0029-26.2026","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1523/eneuro.0029-26.2026","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1016/j.isci.2025.114294","name":"Bridged artificial neurons based on memristor circuit for spiking propagation network and coincidence detection.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.isci.2025.114294","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.isci.2025.114294","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.3389/fncom.2026.1737434","name":"Tension shapes memory: computational insights into neural plasticity.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2026.1737434","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fncom.2026.1737434","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3390/e28030253","name":"Event-Driven Spiking Neural Networks for Private Vehicle Parking Prediction.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/e28030253","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/e28030253","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fncel.2026.1787173","name":"Recreating the human brain: Are assembloids merely descriptive models?","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncel.2026.1787173","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fncel.2026.1787173","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1093/nsr/nwaf551","name":"Neuromorphic spike-based large language model.","source":"europepmc","abstract":"","url":"https://doi.org/10.1093/nsr/nwaf551","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1093/nsr/nwaf551","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41598-025-34046-8","name":"Enhancing time scalability of spiking neural networks with dynamic time constants.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-34046-8","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-025-34046-8","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.3389/fnins.2025.1652274","name":"Spiking neural networks for EEG signal analysis using wavelet transform.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2025.1652274","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fnins.2025.1652274","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fncom.2025.1724190","name":"Measurement effects on critical scaling in neural systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2025.1724190","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fncom.2025.1724190","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1364/ao.573708","name":"Image classification using optical spiking neural networks based on VCSEL with saturable absorption region neurons.","source":"europepmc","abstract":"","url":"https://doi.org/10.1364/ao.573708","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1364/ao.573708","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.7554/elife.106658","name":"Coordinated spinal locomotor network dynamics emerge from cell-type-specific connectivity patterns.","source":"europepmc","abstract":"","url":"https://doi.org/10.7554/elife.106658","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.7554/elife.106658","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fnsyn.2026.1819500","name":"Tuning excitatory input to fast-spiking parvalbumin-positive interneurons: a lever for plasticity and hyperexcitability across the lifespan.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnsyn.2026.1819500","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnsyn.2026.1819500","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fnins.2026.1755119","name":"Operational manifolds in spiking neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2026.1755119","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnins.2026.1755119","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41598-025-23664-x","name":"Trustworthy pneumonia detection in chest X-ray imaging through attention-guided deep learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-23664-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-23664-x","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3389/fnetp.2025.1664280","name":"Synaptic facilitation and learning of multiplexed neural signals.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnetp.2025.1664280","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fnetp.2025.1664280","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41598-026-44063-w","name":"Neuronal silence as a predictive biomarker and target for epileptic seizures suppression.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-44063-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-44063-w","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.7554/elife.107905","name":"Adult-neurogenesis allows for representational stability and flexibility in early olfactory system.","source":"europepmc","abstract":"In the olfactory system, adult-neurogenesis results in the continuous reorganization of synaptic connections and network architecture throughout the animal's life. This poses a critical challenge: How does the olfactory system maintain stable representations of odors amidst this ongoing circuit instability? Utilizing a detailed spiking network model of early olfactory circuits, we uncovered dual roles for adult-neurogenesis: one that both supports representational stability to faithfully encode odor information, and also one that facilitates plasticity to allow for learning and adaptation. In the main olfactory bulb, adult-neurogenesis affects neural codes in individual mitral and tufted cells but preserves odor representations at the neuronal population level. By contrast, in the olfactory piriform cortex (PCx), both individual cell responses and overall population dynamics undergo progressive changes due to adult-neurogenesis. This leads to representational drift, a gradual alteration in stimulus-evoked activity patterns. Both processes are dynamic and depend on experience such that repeated exposure to specific odors reduces the drift due to adult-neurogenesis; thus, when the odor environment is stable over the course of adult-neurogenesis, it is spike-timing-dependent plasticity that leads representations to remain stable in the PCx; when those olfactory environments change, adult-neurogenesis allows cortical representations to track environmental change. Whereas perceptual stability and plasticity due to learning are often thought of as two distinct, often contradictory processes in neuronal coding, we find that adult-neurogenesis serves as a shared mechanism for both. In this regard, the quixotic presence of adult-neurogenesis in the mammalian olfactory bulb that has been the focus of considerable investigation in chemosensory neuroscience may be the mechanistic underpinning behind an array of complex computations.","url":"https://doi.org/10.7554/elife.107905","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.7554/elife.107905","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1371/journal.pcbi.1013844","name":"Conditions for replay of neuronal assemblies.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pcbi.1013844","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pcbi.1013844","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1093/pnasnexus/pgag213","name":"Two-factor synaptic plasticity enables memory consolidation during neuronal burst firing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1093/pnasnexus/pgag213","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1093/pnasnexus/pgag213","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41467-025-66818-1","name":"Ultrafast neural sampling with spiking nanolasers.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-66818-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-66818-1","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3390/s25216747","name":"Spiking Neural Networks in Imaging: A Review and Case Study.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s25216747","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/s25216747","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1523/jneurosci.0083-26.2026","name":"Inhibitory Circuits Can Restore OFF Pathway Responses in Retinal Prostheses.","source":"europepmc","abstract":"","url":"https://doi.org/10.1523/jneurosci.0083-26.2026","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1523/jneurosci.0083-26.2026","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1371/journal.pcbi.1013224","name":"Comparison of FORCE trained spiking and rate neural networks shows spiking networks learn slowly with noisy, cross-trial firing rates.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pcbi.1013224","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1371/journal.pcbi.1013224","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41467-025-64234-z","name":"Predictive Coding Light.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-64234-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-64234-z","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1371/journal.pcbi.1014337","name":"Fast reconstruction of degenerate populations of conductance-based neuron models from spike times.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pcbi.1014337","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pcbi.1014337","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1016/j.namjnl.2025.100064","name":"Nonclinical human neural new approach methodologies (NAMs): Electrophysiological assessment of opioid agonist and antagonist combination.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.namjnl.2025.100064","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.namjnl.2025.100064","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41467-025-63821-4","name":"A doubly stochastic renewal framework for partitioning spiking variability.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-63821-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-63821-4","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fncom.2025.1699179","name":"State-dependent filtering as a mechanism toward visual robustness.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2025.1699179","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fncom.2025.1699179","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1371/journal.pcbi.1013500","name":"Inferring effective networks of spiking neurons using a continuous-time estimator of transfer entropy.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pcbi.1013500","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1371/journal.pcbi.1013500","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1007/s00422-025-01029-x","name":"Encoding of movement primitives and body posture through distributed proprioception in walking and climbing insects.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s00422-025-01029-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s00422-025-01029-x","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1007/s00422-026-01042-8","name":"Contribution of spike timing to the neural code: from fast to slow timescales.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s00422-026-01042-8","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s00422-026-01042-8","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fnins.2025.1662886","name":"Efficient spiking convolutional neural networks accelerator with multi-structure compatibility.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2025.1662886","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fnins.2025.1662886","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fncir.2025.1634298","name":"Hippocampal phase precession may be generated by chimera dynamics.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncir.2025.1634298","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fncir.2025.1634298","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fnbot.2026.1796043","name":"Neurorobotics for automotive manufacturing industry in era of embodied intelligence: a mini review.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnbot.2026.1796043","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnbot.2026.1796043","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41467-025-63771-x","name":"Efficient and robust temporal processing with neural oscillations modulated spiking neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-63771-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-63771-x","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41467-026-69898-9","name":"Brain-inspired synaptic transistors for in-situ spiking reinforcement learning with eligibility trace.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-69898-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-69898-9","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.3389/fncom.2026.1741793","name":"Synergy mediates long-range correlations in the visual cortex near criticality.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2026.1741793","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fncom.2026.1741793","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1371/journal.pcbi.1014099","name":"Role of fast-spiking interneurons in modulating across-trial variability and within-trial correlations in the striatum.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pcbi.1014099","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pcbi.1014099","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41598-025-24837-4","name":"Deep oscillatory neural network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-24837-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-24837-4","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.3390/s25196048","name":"Dynamic Vision Sensor-Driven Spiking Neural Networks for Low-Power Event-Based Tracking and Recognition.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s25196048","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/s25196048","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1177/15330338251391080","name":"NeuroMorphFusion: A Neuro-Inspired Hybrid Learning Framework for Interpretable Deep Lesion Detection in IoT-Enabled Healthcare Systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.1177/15330338251391080","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1177/15330338251391080","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-025-10837-x","name":"Novel SMA BASED Elmanspiking neural network modelled fuzzy PI controller for speed-torque regulation of PMSM.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-10837-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-10837-x","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1371/journal.pone.0341052","name":"Research on electromagnetic compatibility analysis of automation equipment based on generative adversarial networks and pulse sparse convolution.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pone.0341052","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pone.0341052","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1109/tnnls.2024.3460973","name":"Retina-Inspired Lightweight Spiking Convolutional Neural Network for Single-Image Dehazing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tnnls.2024.3460973","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1109/tnnls.2024.3460973","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1038/s41598-026-42970-6","name":"PS-SNN: pattern separation learning for expandable spiking neural networks in class-incremental learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-42970-6","authors":["Ke Hu","Liangsheng Wen","Tingting Zhang","Hao Zhang"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-42970-6","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fnins.2025.1661916","name":"Bidirectional dynamic threshold SNN for enhanced object detection with rich spike information.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2025.1661916","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fnins.2025.1661916","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41598-025-24109-1","name":"Cholinergic modulation mediates attentional mechanism to enhance coherence between cortical layers in macaque V1 and V4.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-24109-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-24109-1","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1038/s41598-025-34846-y","name":"Minimization of outage probability and energy consumption by deep learning-based prediction in D2D mm wave communication.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-34846-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-025-34846-y","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41467-025-62202-1","name":"Spiking dynamics of individual neurons reflect changes in the structure and function of neuronal networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-62202-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-62202-1","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3390/s26020568","name":"Exploring Quantum-Inspired Encoding Strategies in Neuromorphic Systems for Affective State Recognition.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s26020568","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/s26020568","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1088/1741-2552/ae1dad","name":"A computational framework combining neuronal dynamics and evolutionary game theory for network-level synaptic interactions.","source":"europepmc","abstract":"","url":"https://doi.org/10.1088/1741-2552/ae1dad","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1088/1741-2552/ae1dad","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.3390/s26061801","name":"Characterization of a Spiking Convolutional Processor for FPGA.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s26061801","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/s26061801","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fncir.2026.1776224","name":"Editorial: Bridging computation, biophysics, medicine, and engineering in neural circuits.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncir.2026.1776224","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fncir.2026.1776224","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fnins.2025.1638547","name":"The road toward a physiological control of artificial respiration: the role of bio-inspired neuronal networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2025.1638547","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fnins.2025.1638547","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41598-026-37367-4","name":"Energy-efficient intrusion detection with a protocol-aware transformer-spiking hybrid model.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-37367-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-37367-4","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41598-026-44588-0","name":"Visualization and simulation of full-scale point-neuron circuits via the Neural Circuit Visualizer web platform.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-44588-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-44588-0","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1109/tnnls.2025.3526374","name":"Low Latency Conversion of Artificial Neural Network Models to Rate-Encoded Spiking Neural Networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tnnls.2025.3526374","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1109/tnnls.2025.3526374","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.3389/fncom.2026.1814579","name":"Temporal codes and recurrent timing nets for rhythmic expectancy.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2026.1814579","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fncom.2026.1814579","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.3389/fncom.2026.1771884","name":"NEURONpyxl: fast, flexible, Python-integrated simulation of biophysical neural networks with complex plastic synapses.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2026.1771884","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fncom.2026.1771884","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1007/s10827-026-00924-x","name":"Astrocyte-induced dynamics of a pyramidal cell with a dendrite-connected astrocyte.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s10827-026-00924-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s10827-026-00924-x","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1523/eneuro.0176-24.2026","name":"Cell Density Impacts Population Activity in Human iPSC-Derived Neural Networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1523/eneuro.0176-24.2026","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1523/eneuro.0176-24.2026","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1371/journal.pcbi.1013782","name":"Predicting neural responses to intra- and extra-cranial electric brain stimulation by means of the reciprocity theorem.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pcbi.1013782","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1371/journal.pcbi.1013782","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.7717/peerj-cs.3077","name":"Hardware implementation of FPGA-based spiking attention neural network accelerator.","source":"europepmc","abstract":"Spiking neural networks (SNNs) are recognized as third-generation neural networks and have garnered significant attention due to their biological plausibility and energy efficiency. To address the resource constraints associated with using field programmable gate arrays (FPGAs) for numerical recognition in SNNs, we proposed a lightweight spiking efficient attention neural network (SeaSNN) accelerator. We designed a simple, four-layer structured network, achieving a recognition accuracy of 93.73% through software testing on the MNIST dataset. To further enhance the model’s accuracy, we developed a highly spiking efficient channel attention mechanism (SECA), resulting in a significant performance improvement and an increase in test accuracy to 94.28%. For higher recognition speed, we optimized circuit parallelism by applying techniques such as loop unrolling, loop pipelining, and array partitioning. Finally, SeaSNN was implemented and verified on an FPGA board, achieving an inference speed of 0.000401 seconds per frame and a power efficiency of 0.42 TOPS/W at a frequency of 200 MHz. These results demonstrate that the proposed low-power, high-precision, and fast handwritten digit recognition system is well-suited for handwritten digit recognition tasks.","url":"https://doi.org/10.7717/peerj-cs.3077","authors":["Shiyong Geng","Zhida Wang","Zhipeng Liu","Mengzhao Zhang","Xuelong Zhu","Yongping Dan"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.7717/peerj-cs.3077","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1002/alz.70865","name":"APOE ε4 disrupts neuronal and network-level function in the anterior olfactory nucleus: Influence of age and sex.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/alz.70865","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/alz.70865","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1109/tnnls.2025.3566021","name":"Toward Ultralow-Power Neuromorphic Speech Enhancement With Spiking-FullSubNet.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tnnls.2025.3566021","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1109/tnnls.2025.3566021","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.7554/elife.99278","name":"Brain-wide arousal signals are segregated from movement planning in the superior colliculus of the macaque.","source":"europepmc","abstract":"","url":"https://doi.org/10.7554/elife.99278","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.7554/elife.99278","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41467-025-63873-6","name":"Bioinspired high-order in-sensor spatiotemporal enhancement in van der Waals optoelectronic neuromorphic electronics.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-63873-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-63873-6","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.3389/fnsyn.2025.1732955","name":"From microelectrode arrays to all-optical and multimodal neural interfaces: emerging platforms for spatiotemporal interrogation of &lt;i&gt;in vitro&lt;/i&gt; neural circuits.","source":"europepmc","abstract":"Understanding how synaptic interactions lead to circuit dynamics for neural computation requires experimental tools that can both observe and perturb neuronal activity across spatial and temporal scales. Microelectrode arrays (MEAs) provide scalable access to population spiking activity, yet they lack the spatial resolution and molecular specificity to precisely dissect synaptic mechanisms. In contrast, recent advances in optogenetic actuators, genetically encoded calcium and voltage indicators, and patterned photostimulation have transformed in vitro research, enabling all-optical interrogation of synaptic plasticity, functional connectivity, and emergent network dynamics. Further progress in transparent MEAs and hybrid optical-electrical systems has bridged the divide between electrophysiology and optical control, allowing simultaneous, bidirectional interaction with biological neural networks (BNNs) and real-time feedback modulation of activity patterns. Together, these multimodal in vitro platforms provide unprecedented experimental access to how local interactions shape global network behavior. Beyond technical integration, they establish a foundation for studying biological computation, linking mechanistic understanding of synaptic processes with their computational outcomes. This mini-review summarizes the progression from conventional MEA-based electrophysiology, through all-optical interrogation, to integrated multimodal frameworks that unite the strengths of both modalities.","url":"https://doi.org/10.3389/fnsyn.2025.1732955","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fnsyn.2025.1732955","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3390/brainsci15080870","name":"Spiking Neural Models of Neurons and Networks for Perception, Learning, Cognition, and Navigation: A Review.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/brainsci15080870","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/brainsci15080870","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fncom.2025.1662598","name":"The improved thalamo-cortical spiking network model of deep brain stimulation.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2025.1662598","authors":["AmirAli Farokhniaee","Siavash Amiri"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fncom.2025.1662598","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1142/s0129065725500583","name":"Evaluation of Bio-Inspired Models under Different Learning Settings for Energy Efficiency in Network Traffic Prediction.","source":"europepmc","abstract":"","url":"https://doi.org/10.1142/s0129065725500583","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1142/s0129065725500583","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1038/s41598-026-37594-9","name":"Intensity-dependent tACS entrainment effects in a cortical microcircuit: a computational study.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-37594-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-37594-9","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1109/embc58623.2025.11251728","name":"Temporally-Varying Stimulations for Cortical Visual Neuroprosthetics using Spiking Neural Networks.","source":"europepmc","abstract":"Visual neuroprosthesis can help to restore a rudimentary form of sight in visually impaired subjects via electrical stimulation. These systems receive camera input images processed by a artificial neural network (ANN) to output stimulation patterns for driving a large set of electrodes. Previous optimization approaches for visual neuroprosthesis stimulation patterns provided a fixed stimulation amplitude for each electrode. In this work, we look at the feasibility of using a spiking neural network (SNN) instead of the ANN allowing the model to provide time-varying stimulation patterns. During training, we mapped pulses of the SNN through a phosphene simulator which models the perceptual response. Results on the MNIST dataset show that our SNN-based encoder demonstrates reasonable reconstruction quality compared to a state-of-the-art ANN while requiring 2× fewer operations (1.16 vs 2.44 GFLOPs). Preliminary results show that the network trained on N-MNIST, a dataset of spikes from the spiking retina event camera on MNIST images, shows successful reconstructed recognizable digit shapes, suggesting the possibility of using event cameras for visual prosthesis.","url":"https://doi.org/10.1109/embc58623.2025.11251728","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1109/embc58623.2025.11251728","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1016/j.fmre.2026.04.010","name":"Beyond place cells: Specific and cooperative roles of hippocampal interneuron families in spatial coding.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.fmre.2026.04.010","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.fmre.2026.04.010","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1371/journal.pcbi.1013465","name":"A theory for self-sustained balanced states in absence of strong external currents.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pcbi.1013465","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pcbi.1013465","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fncir.2026.1789080","name":"The circuitry regulation of associative learning: dissociated and integrated function of the perirhinal cortex and hippocampus.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncir.2026.1789080","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fncir.2026.1789080","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1371/journal.pone.0327513","name":"BN-SNN: Spiking neural networks with bistable neurons for object detection.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pone.0327513","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1371/journal.pone.0327513","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1016/j.brs.2026.103045","name":"Transcranial alternating current stimulation can disrupt or reestablish neural entrainment in parkinsonian motor cortex.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.brs.2026.103045","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.brs.2026.103045","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1007/s11571-025-10358-3","name":"New insights into multistability and complex resonances driven by subthreshold periodic signals in a neuronal model.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-025-10358-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1007/s11571-025-10358-3","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1038/s41467-025-67076-x","name":"Biomimetic model of corticostriatal micro-assemblies discovers a neural code.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-67076-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-67076-x","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2025.07.11.664261","name":"Fast efficient coding and sensory adaptation in gain-adaptive recurrent networks","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.07.11.664261","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.07.11.664261","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.06.18.660326","name":"A model investigation of short-term synaptic plasticity tuned via Unc13 isoforms","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.06.18.660326","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.06.18.660326","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.20944/preprints202507.2083.v1","name":"Organization and Community Usage of a Neuron Type Circuitry Knowledge Base of the Hippocampal Formation","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202507.2083.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202507.2083.v1","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.04.21.649785","name":"Interactions between the medial prefrontal cortex, dorsomedial striatum, and dorsal hippocampus that support rat category learning","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.04.21.649785","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.04.21.649785","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.05.14.653875","name":"Neuropixels reveal structure-function relationships in monkey V1  <i>in vivo</i>","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.05.14.653875","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.05.14.653875","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.06.25.661479","name":"Single-Cell and Population-Level Neuromodulation Dynamics in Dual-Electrode Intracortical Stimulation","source":"preprints","abstract":"In neuroprosthetics, intracortical microstimulation (ICMS) recruits cortical networks to evoke brain responses and sensory perceptions. However, multi-electrode ICMS often generates suboptimal percepts compared to single-electrode ICMS, suggesting nonlinear neuromodulation rather than simple summation by multi-electrode ICMS. Yet, the factors and mechanisms underlying this modulation remain poorly understood. To investigate multi-electrode ICMS, we combined two-photon calcium imaging with a well-controlled dual-electrode ICMS in the mouse visual cortex to investigate how neurons integrate converging ICMS inputs at varying intensities. We found that stimulation intensity significantly shapes neuromodulation at both single-cell and population levels. Specifically, low intensities (5-7 µA) have a minimal effect on neural responses. At intermediate intensities (10-15 µA), we observed diverse, nonlinear bipolar modulation—both enhancement and attenuation—at the single-cell level. However, we achieved net enhancement at the population level. At higher intensities (15–20 µA), although the proportion of modulated neurons increased in both enhancement and attenuation directions, the net effect at the population level was neutral (zero modulation). Furthermore, neurons strongly responsive to single-electrode ICMS were more likely to be attenuated, while weaker responding cells exhibited enhanced modulation. The strongest neuromodulatory effects occur at intermediate spatial distances in between the two electrodes. Computational modeling based on spiking neural network composed of adaptive exponential integrate-and-field neurons implicated the importance of inhibitory network dynamics and network variability as key mechanisms. Our experimental data was used to train an advanced deep learning approach, which successfully predicted the neuromodulation patterns induced by dual-electrode ICMS. Our findings reveal intensity- and spatial-dependent rules of neuromodulation by ICMS, providing necessary insights to optimize multi-electrode ICMS for neuroprosthetic applications. Significance statement Understanding how cortical neurons integrate concurrent inputs from multi-electrode intracortical microstimulation (ICMS) is essential for advancing neuroprosthetic technologies. We show that dual-electrode ICMS evokes distinct, predictable neuromodulatory effects that depend on (i) stimulation intensity, (ii) a neuron’s baseline responsiveness to single electrode input, and (iii) its proximity to the electrodes. Low and intermediate intensity dual-electrode ICMS amplifies neural activity compared to single-electrode ICMS, whereas high-intensity stimulation leads to attenuation, limiting net activation.","url":"https://doi.org/10.1101/2025.06.25.661479","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.06.25.661479","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.20944/preprints202506.1290.v1","name":"Algorithm for Describing Neuronal Electric Operation","source":"preprints","abstract":"The development of neuroanatomy and neurophysiology discovered many new details in the past decades about neuron’s electric operation that required modifying its theoretical model. The development of computing technology enables us to consider the fine details the new model requires, but it necessitates a different approach. As it was long ago suspected, the faithful simulation of biological processes requires accurately mapping biological time to technical computing time. Therefore, the paper focuses on time handling in biology-targeting computations. However, the operation of biology and the physical/mathematical processes in living matter are unusual from the point of view of algorithmic description. Furthermore, the way technical operation works prevents achieving the needed accuracy in reproducing biological operations using computer programs. We also touch on the question of simulating the operation of their network, contrasted to the operation of spiking artificial neural networks. On the one side, we use an updated theoretical model that considers neuronal current as charged ions (and so considers thermodynamic effects) and opens the way for explaining mechanical, optical, etc., consequence phenomena of the electric operation. On the other hand, we apply a tool developed for achieving extreme accuracy in simulating high-speed electronic circuits. The algorithm that applies this model and the unusual programming method provides new insights into both neuronal operation and its technical implementation.","url":"https://doi.org/10.20944/preprints202506.1290.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202506.1290.v1","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.21203/rs.3.rs-6296374/v1","name":"Brain-inspired synaptic transistors for in-situ spiking reinforcement learning with eligibility trace","source":"preprints","abstract":"Abstract Brain-inspired reinforcement learning (RL) represents a pivotal pathway toward artificial general intelligence, yet existing hardware implementations based on artificial neural networks lack critical biological mechanisms like third-terminal modulated eligibility traces and dynamic reward signaling. Emerging materials can address these challenges by mimicking RL’s complex dynamics with revolutionary efficiency. Here we demonstrate a brain-inspired SNN-based RL computing architecture using α-In 2 Se 3 ferroelectric semiconductor field-effect transistor (FeS-FET). By leveraging the intrinsic in-plane and out-of-plane polarization coupling of α-In 2 Se 3 , the multi-terminal conductance modulation in the FeS-FET enables reward signal modulation of RL. The ferroelectric relaxation is utilized to implement biological eligibility trace decay, thereby enhancing the algorithm's processing capability. autonomous driving tasks are then demonstrated with RL neural network constructed by the α-In 2 Se 3 FeS-FET array, where in-situ reward-based weight updates and eligibility trace decay are performed without any external memory or computing units. Our solution paves the way for a SNN-based RL computing architecture with full functionality, low energy consumption and reduced hardware overhead.","url":"https://doi.org/10.21203/rs.3.rs-6296374/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6296374/v1","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.05.13.652528","name":"Temporal coding carries more stable cortical visual representations than firing rate over time","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.05.13.652528","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.05.13.652528","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.02.20.636945","name":"Hybrid Neural Network Models Explain Cortical Neuronal Activity During Volitional Movement","source":"preprints","abstract":"Abstract Massive interconnectivity in large-scale neural networks is the key feature underlying their powerful and complex functionality. We have developed hybrid neural network (HNN) models that allow us to find statistical structure in this connectivity. Describing this structure is critical for understanding biological and artificial neural networks. The HNNs are composed of artificial neurons, a subset of which are trained to reproduce the responses of individual neurons recorded experimentally. The experimentally observed firing rates came from populations of neurons recorded in the motor cortices of monkeys performing a reaching task. After training, these networks (recurrent and spiking) underwent the same state transitions as those observed in the empirical data, a result that helps resolve a long-standing question of prescribed vs ongoing control of volitional movement. Because all aspects of the models are exposed, we were able to analyze the dynamic statistics of the connections between neurons. Our results show that the dynamics of extrinsic input to the network changed this connectivity to cause the state transitions. Two processes at the synaptic level were recognized: one in which many different neurons contributed to a buildup of membrane potential and another in which more specific neurons triggered an action potential. HNNs facilitate modeling of realistic neuron-neuron connectivity and provide foundational descriptions of large-scale network functionality.","url":"https://doi.org/10.1101/2025.02.20.636945","authors":["Hongwei Mao","Brady A. Hasse","Andrew B. Schwartz"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.02.20.636945","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1101/2025.02.04.636401","name":"Modular architecture confers robustness to damage and facilitates recovery in spiking neural networks modeling  <i>in vitro</i>  neurons","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.02.04.636401","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.02.04.636401","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.06.15.659765","name":"<i>Larvaworld</i>  : A behavioral simulation and analysis platform for  <i>Drosophila</i>  larva","source":"preprints","abstract":"Behavioral modeling supports theory building and evaluation across disciplines. Leveraging advances in motion-tracking and computational tools, we present a virtual laboratory for Drosophila larvae that integrates agent-based modeling with multiscale neural control and supports analysis of both simulated and experimental data. Virtual larvae are implemented as 2D agents capable of realistic locomotion, guided by multimodal sensory input and constrained by a dynamic energy-budget model that balances exploration and exploitation. Each agent is organized as a hierarchical, behavior-based control system comprising three layers: low-level locomotion, optionally incorporating neuromechanical models; mid-level sensory processing; and high-level behavioral adaptation. Neural control models can range from simple linear transfer models to rate-based or spiking neural network models, e.g. to accomodate associative learning. Simulations operate across sub-millisecond neuronal dynamics, sub-second closed-loop behavior, and circadian-scale metabolic regulation. Users can configure both larval models and virtual environments, including sensory landscapes, nutrient sources, and physical arenas. Real-time visualization is integrated into the simulation and analysis pipeline, which also allows for standardized processing of motion-tracking data from real experiments. Distributed as an open-source Python package, the platform includes tutorial experiments to support accessibility, customization, and use in both research and education. Author summary Larvaworld was developed to address two key challenges in behavioral neuroscience and computational modeling. First, it responds to the growing call for closer collaboration between experimentalists and modelers by providing a shared platform -a virtual laboratory-where experimental data analysis and behavioral modeling can be seamlessly integrated. By standardizing dataset formats and ensuring identical, unbiased analysis pipelines for experimental and simulated data, Larvaworld facilitates methodological consistency and enables rigorous model evaluation. Second, it aims to bridge a long-standing gap in theory building and computational modeling at the level of the individual behaving organism. Historically, neuroscience has focused on sub-individual processes, while ecology has concentrated on supra-individual dynamics, resulting in discontinuities among the respective modeling approaches. Recent advances, however, have begun to align these fields, with neuroscience incorporating slower homeostatic processes and ecology integrating faster neurally-mediated mechanisms. Larvaworld boosts this convergence by adopting a nested, multi-timescale modeling approach, thus achieving behavioral regulation within the normative homeostatic constraints as these dynamically unfold during larval development. By combining established modeling paradigms from neuroscience and ecology, it provides a novel and flexible platform for studying behavior at the level of the individual organism, promoting cross-disciplinary insights and advancing computational neuroethology [1].","url":"https://doi.org/10.1101/2025.06.15.659765","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.06.15.659765","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.09.16.676508","name":"Robustness through variability: ion channel isoform diversity safeguards neuronal excitability","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.09.16.676508","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.09.16.676508","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2025.01.13.632765","name":"Continual familiarity decoding from recurrent connections in spiking networks","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.01.13.632765","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.01.13.632765","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.04.28.651079","name":"Continuous theta-burst stimulation of the prefrontal cortex in the macaque monkey: no behavioral evidence for within-target inhibition or neural evidence for cross-hemisphere disinhibition","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.04.28.651079","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.04.28.651079","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.64898/2025.12.09.693169","name":"Corticofugal gated recurrency captures auditory cortical responses","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2025.12.09.693169","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.64898/2025.12.09.693169","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.20944/preprints202507.2002.v1","name":"A Proposed Cause, Cure, and Mechanism for Focal Task-Specific Dystonia: A Theoretical-Empirical Approach","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202507.2002.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202507.2002.v1","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.06.10.658856","name":"A tectal reservoir implements adaptive visuomotor transformation via serotonergically coordinated push-pull-like mechanisms","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.06.10.658856","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.06.10.658856","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.07.27.667035","name":"Hippocampal Synchrony Dynamically Gates Cortical Connectivity Across Brain States","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.07.27.667035","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.07.27.667035","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.07.16.663353","name":"NeuroSuite for Long-term Functional and Structural Studies of Air-Liquid Interface Cerebral Organoids","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.07.16.663353","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.07.16.663353","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.64898/2026.01.22.701007","name":"Hippocampal tangential insertions of high-density silicon probes in head-fixed mice enhance spatial sampling","source":"preprints","abstract":"The hippocampus is a key structure within the medial temporal lobe which plays a central role in the formation and consolidation of declarative memories. Despite technological progress, a full understanding of hippocampal rhythms, neuronal population activity, and the underlying connectivity remains elusive, partly due to its complex morphology in a croissant-like shape which limits coronal and sagittal approaches. To address this limitation, we propose two different tangential insertions of high-density electrode probes (Neuropixels 1.0) aligned to either the dorsal or ventral sections of the hippocampus. Each approach enables the placement of up to 384 recording sites within the hippocampal formation. Both insertions are performed in head-fixed conditions, which can be easily combined with detailed monitoring of the animals’ behavioral states including spontaneous running and facial movements. The two proposed tangential dorsal and ventral insertions capture almost continuously the physiology of the hippocampus across 3.84 mm of tissue. We show that when placed across the pyramidal layer, such insertions can harness ripple oscillations from approximately 130 channels, corresponding to about ∼1.3 mm of tissue, with a coverage of 2 channels every 20 µm. Furthermore, such insertions enabled us to record up to 400 hippocampal neurons simultaneously from a single probe, endowing us with the capability to capture putative functionally connected neuronal pairs. Although the conventional orthogonal/vertical approach is optimal for recording the laminar organization of hippocampal activity, we demonstrate how, for the longitudinal axis of hippocampus, tangential insertions can substantially increase spatial reach and sampling resolution, enabling a more detailed description of activity along this axis.","url":"https://doi.org/10.64898/2026.01.22.701007","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.01.22.701007","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2025.01.15.633145","name":"Temporal and protein-specific S-palmitoylation supports synaptic and neural network plasticity","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.01.15.633145","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.01.15.633145","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.01.30.635710","name":"Stabilization of memory on neural manifolds through multiple synaptic time scales","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.01.30.635710","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.01.30.635710","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.06.13.657566","name":"Transparent transfer-free multilayer graphene microelectrodes enable high quality recordings in brain slices","source":"preprints","abstract":"Resolving the underlying mechanisms of complex brain functions and associated disorders remains a major challenge in neuroscience, largely due to the difficulty in mapping large-scale neural network dynamics with high temporal and spatial resolution. Multimodal neural platforms that integrate optical and electrical modalities offer a promising approach that surpasses resolution limits. Over the last decade, transparent graphene microelectrodes have been proposed as highly suitable multimodal neural interfaces. However, their fabrication commonly relies on the manual transfer process of pre-grown graphene sheets which introduces reliability and scalability issues. In this study, multilayer graphene microelectrode arrays (MEAs) with electrode sizes as small as 10-50 µm in diameter, are fabricated using a transfer-free process on a transparent substrate for in vitro multimodal platforms. Through acute experiments using cerebellar brain slices, their ability to detect spontaneous extracellular spiking activity from neural cells, with a high signal-to-noise ratio up to 30-40 dB, is demonstrated. The recorded signal quality is found to be more limited by the electrode-tissue coupling than the MEA technology itself. Overall, this study shows the potential of transfer-free multilayer graphene MEAs to interface with neural tissue, which paves the way to advance neuroscientific research through the next-generation of multimodal neural interfaces.","url":"https://doi.org/10.1101/2025.06.13.657566","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.06.13.657566","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.21203/rs.3.rs-6087158/v1","name":"Neotenic expansion of adult-born dentate granule cells reconfigures GABAergic inhibition to enhance social memory consolidation","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-6087158/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6087158/v1","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.09.13.672380","name":"In vivo single-cell gene editing using RNA electroporation reveals sequential adaptation of cortical neurons to excitatory-inhibitory imbalance","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.09.13.672380","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.09.13.672380","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2025.03.17.643806","name":"Neotenic expansion of adult-born dentate granule cells reconfigures GABAergic inhibition to enhance social memory consolidation","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.03.17.643806","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.03.17.643806","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.09.08.674838","name":"Efficient Working Memory Maintenance via High-Dimensional Rotational Dynamics","source":"preprints","abstract":"Working memory (WM) is fundamental to higher-order cognition, yet the circuit mechanisms through which memoranda are maintained in neural activity after removal of sensory input remain subject to vigorous debate. Prominent theories propose that stimuli are encoded in either stable and persistent activity patterns configured through attractor mechanisms or dynamic and time-varying activity patterns brought about through functionally-feedforward network architectures. However, cortical circuits exhibit heterogeneous responses during WM tasks that are challenging to reconcile with either hypothesis. We hypothesised that these complex response dynamics could emerge from an optimally noise-robust and energetically efficient solution to WM tasks. We show that, in contrast to previous theories, networks optimised for efficient WM encoding exhibit high-dimensional rotational dynamics. We find direct evidence for these rotational dynamics in large-scale recordings from monkey prefrontal cortex. Our findings suggest that the complex and dynamic response properties of WM circuits emerge from efficient coding principles.","url":"https://doi.org/10.1101/2025.09.08.674838","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.09.08.674838","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2025.08.26.672285","name":"Cerebral Organoids Uncover Mechanisms of Neural Activity Changes in Epileptogenesis","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.08.26.672285","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.08.26.672285","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2025.10.13.682054","name":"Pragmatic representations of self- and others’ action in the monkey putamen","source":"preprints","abstract":"Social coordination in primates relies on parieto-frontal networks encoding self- and others’ actions. These areas send convergent projections to the putamen, but its role in representing self- and others’ actions remains unknown. We recorded neuronal activity from anatomically characterized putamen regions during a Mutual Action Task (MAT), where a monkey and a human took turns grasping a multi-affordance object based on sensory cues. Cortico-striatal synaptic input, indexed by local field potentials, mirrored known cortical dynamics during sensory instructions and movement, while single neurons selectively encoded the monkey’s action, the human’s action, or both. Grip type was encoded only during the monkey’s trials. Viewing the partner’s action was neither necessary nor sufficient: neurons fired even when the partner’s action occurred in darkness, but not when viewed through a transparent barrier. These findings support a pragmatic role for the putamen in gating cortical representations of self- and other’s actions in social contexts.","url":"https://doi.org/10.1101/2025.10.13.682054","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.10.13.682054","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.08.12.669821","name":"Tactile stimulation transiently disrupts encoding of whisker position by cerebellar molecular layer interneuron ensembles","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.08.12.669821","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.08.12.669821","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.10.12.618014","name":"Structured stabilization in recurrent neural circuits through inhibitory synaptic plasticity","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.10.12.618014","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.10.12.618014","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2025.01.27.635001","name":"The role of cortico-thalamic feedback for visual information processing","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.01.27.635001","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.01.27.635001","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.01.23.634520","name":"Resolving inconsistent effects of tDCS on learning using a homeostatic structural plasticity model","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.01.23.634520","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.01.23.634520","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.03.26.645407","name":"Fast Interneuron Dysfunction in Laminar Neural Mass Model Reproduces Alzheimer’s Oscillatory Biomarkers","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.03.26.645407","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.03.26.645407","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2025.11.03.686220","name":"Pitch selectivity in ferret auditory cortex","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.11.03.686220","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.11.03.686220","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.21203/rs.3.rs-5624085/v1","name":"Pro-cognitive restoration of experience-dependent parvalbumin inhibitory neuron plasticity in neurodevelopmental disorders","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-5624085/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-5624085/v1","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.10.01.679813","name":"Differential Burst dynamics of Slow and Fast gamma rhythms in Macaque primary visual cortex","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.10.01.679813","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.10.01.679813","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2025.06.17.660119","name":"Column-Like Subnetwork Reconstruction in Motor Cortex from Graph-Based 3D High-Density Two-Photon Calcium Imaging","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.06.17.660119","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.06.17.660119","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.08.30.673281","name":"Brain-wide organization of intrinsic timescales at single-neuron resolution","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.08.30.673281","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.08.30.673281","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2025.11.10.687666","name":"Brain-wide single-neuron bases of working memory for sounds in humans","source":"preprints","abstract":"In order to understand the constantly changing acoustic world our brains must maintain elements of auditory scenes in memory. The neural mechanisms for this fundamental process remain unclear. Here, we report human intracranial recordings of 1269 single neurons while participants performed a non-verbal auditory working memory task that required adjustment of a tone frequency to match a target. We found neurons within hippocampus, insula and cingulate cortex, for which firing rates were modulated at different phases of the task, particularly during maintenance and adjustment. For the majority of the neurons modulated during maintenance there was a striking suppression of activity rather than increased activity. Across the entire neuronal population, state-space analysis demonstrated attractor-like states corresponding to different task phases. Behaviorally, more neurons were modulated at the beginning of the maintenance phase in trials when participants performed better. State-space analysis was consistent with greater attractor-like activity during the adjustment phase supporting better performance. These data support the existence of a widely distributed neural code for auditory working memory that determines related behavior based on attractor-like states.","url":"https://doi.org/10.1101/2025.11.10.687666","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.11.10.687666","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.64898/2025.12.11.693658","name":"The Connectome Modulates Critical Brain Dynamics Across Local and Global Scales","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2025.12.11.693658","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.64898/2025.12.11.693658","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2025.11.17.688824","name":"Insular error network enables self-correcting intracranial brain-computer interface","source":"preprints","abstract":"ABSTRACT Error recognition is fundamental to adaptive behavior, enabling rapid compensatory action when outcomes deviate from expectations. Central to this function are neural circuits for performance monitoring, encoding cognitive signals that could support more reliable neural interfaces. Here, we recorded intracranial electroencephalography (iEEG) in epilepsy patients to enable a motor brain-computer interface (BCI) while sampling error-related activity across a distributed network. Our work reveals high-frequency population dynamics emerging in the anterior insula and propagating to the prefrontal cortex as the interface fails to follow the user’s intention. We identify spatially organized insular responses to error processing and movement feedback, highlighting it as a heterogeneous hub linking action and outcome. Real-time integration of error responses enables a self-correcting neural interface that enhances usability by reducing the need for manual user intervention. Together, our work demonstrates a human intracranial BCI harnessing insular brain activity, integrating cognitive processes directly into device control.","url":"https://doi.org/10.1101/2025.11.17.688824","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.11.17.688824","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2025.10.05.680501","name":"Synaptic histamine shapes the neurocomputational dynamics of human learning","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.10.05.680501","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.10.05.680501","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2025.11.21.689181","name":"High-amplitude oscillatory events coordinate large-scale cortical interactions during decision-making and attention allocation","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.11.21.689181","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.11.21.689181","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.64898/2025.12.01.691172","name":"Neuronal excitability is permanently altered by activity manipulation during an embryonic critical period in  <i>Drosophila</i>","source":"preprints","abstract":"Neuronal intrinsic excitability provides the baseline that homeostatic mechanisms act to preserve, yet the processes that establish a baseline remain poorly defined. Developmental critical periods (CPs) are thought to play a central role, but the link between early activity and long-term intrinsic properties is not well characterised. To address this, we used the genetic tractability of the Drosophila larval locomotor circuit to manipulate individual neurons during an embryonic CP. Following optogenetic excitation or inhibition, during the CP, we assessed intrinsic excitability of the same neurons in third-instar larvae (i.e. ∼5 days thereafter). We compared an excitatory premotor interneuron (A27h), an inhibitory premotor interneuron (A31k), and a motor neuron (aCC). Both interneurons exhibited anti-homeostatic responses: excitatory perturbation increased intrinsic excitability, while inhibitory perturbation decreased it, effects that persisted throughout larval development. In contrast, motor neurons showed no significant changes under the same conditions, revealing cell type-specific sensitivity to early activity. These findings build on the general principles of the functional relationships between CP activity and neuronal excitability and how intrinsic excitability is not passively set but actively shaped during these windows, with long-lasting, neuron-specific consequences. More broadly, our results highlight how developmental perturbations can alter the excitatory–inhibitory balance of mature neural circuits that may contribute to the aetiology of neurodevelopmental disorders.","url":"https://doi.org/10.64898/2025.12.01.691172","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.64898/2025.12.01.691172","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.64898/2026.02.04.703843","name":"Conserved circadian membrane rhythms arise from divergent cellular mechanisms in pacemaker neurons of mice and  <i>Drosophila</i>","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.02.04.703843","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.02.04.703843","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2025.09.08.674955","name":"Beyond Locomotion: How Specialized Motor Rhythms Enable Vertebrate Escape from Capture","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.09.08.674955","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.09.08.674955","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.10.28.685048","name":"Cholinergic heterogeneity facilitates synchronization and information flow in a whole-brain model","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.10.28.685048","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.10.28.685048","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.07.15.663536","name":"Speed Vascular Patterns in the Spatial Navigation System","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.07.15.663536","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.07.15.663536","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.21203/rs.3.rs-6155477/v1","name":"Representational learning by optimization of neural manifolds in an olfactory memory network","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-6155477/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6155477/v1","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.10.31.685770","name":"An artifact-robust framework for measuring tCS effects during stimulation","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.10.31.685770","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.10.31.685770","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2025.03.24.644896","name":"Electrophysiological development and functional plasticity in dissociated human cerebral organoids across multiple cell lines","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.03.24.644896","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.03.24.644896","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2025.03.11.642541","name":"Slow-varying normalization explains diverse temporal frequency masking interactions across scales in the macaque visual cortex","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.03.11.642541","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.03.11.642541","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2025.08.15.670484","name":"E/I ratio and net E+I strength are differentially affected across brain disorders","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.08.15.670484","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.08.15.670484","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.64898/2025.11.30.691163","name":"Multiple task-demands flexibly optimize neural geometry in human ventral temporal cortex","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2025.11.30.691163","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.64898/2025.11.30.691163","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.64898/2026.03.08.710351","name":"Dorsoventral gradient of theta sweeps in medial entorhinal cortex","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.03.08.710351","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.03.08.710351","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2025.04.24.650400","name":"Maturation of GABAergic signalling times the opening of a critical period in  <i>Drosophila melanogaster</i>","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.04.24.650400","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.04.24.650400","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2025.05.14.654005","name":"Cell-type-specific synaptic scaling mechanisms differentially contribute to associative learning","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.05.14.654005","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.05.14.654005","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2025.06.09.658641","name":"Movement execution defines a distinct neural state in dyskinesia and enhances decoding","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.06.09.658641","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.06.09.658641","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.05.12.653436","name":"Information theoretic measures of neural and behavioural coupling predict representational drift","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.05.12.653436","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.05.12.653436","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.03.12.642610","name":"Long-Horizon associative learning as a unifying framework for statistical learning across scales","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.03.12.642610","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.03.12.642610","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.21203/rs.3.rs-6277936/v1","name":"Spatial and network principles behind neural generation of locomotion","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-6277936/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6277936/v1","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.02.04.636286","name":"Neuropixels Opto: Combining high-resolution electrophysiology and optogenetics","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.02.04.636286","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.02.04.636286","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.21203/rs.3.rs-3452001/v1","name":"Can Human Brain Connectivity explain Verbal Working Memory?","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3452001/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-3452001/v1","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.07.16.665209","name":"Dual-feature selectivity enables bidirectional coding in visual cortical neurons","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.07.16.665209","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.07.16.665209","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.64898/2025.11.30.691401","name":"Disentangling Cephalopod Chromatophores Motor Units with Computer Vision","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2025.11.30.691401","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.64898/2025.11.30.691401","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.21203/rs.3.rs-6735294/v1","name":"An Open-Source Deep Learning-Based GUI Toolbox for Automated Auditory Brainstem Response Analyses (ABRA)","source":"preprints","abstract":"Abstract Hearing loss is a pervasive global health challenge with profound impacts on communication, cognitive function, and quality of life. Recent studies have established age-related hearing loss as a significant risk factor for dementia, highlighting the importance of hearing loss research. Auditory brainstem responses (ABRs), which are electrophysiological recordings of synchronized neural activity from the auditory nerve and brainstem, serve as in vivo readouts for sensory hair cell, synaptic integrity, hearing sensitivity, and other key features of auditory pathway functionality, making them highly valuable for both basic neuroscience research and clinical diagnostics. Despite their utility, traditional ABR analyses rely heavily on subjective manual interpretation, leading to considerable variability and limiting reproducibility across studies. Here, we introduce Auditory Brainstem Response Analyzer (ABRA), a novel open-source graphical user interface powered by deep learning, which automates and standardizes ABR waveform analysis. ABRA employs convolutional neural networks trained on diverse datasets collected from multiple experimental settings, achieving rapid and unbiased extraction of key ABR metrics, including peak amplitude, latency, and auditory threshold estimates. We demonstrate that ABRA’s deep learning models provide performance comparable to expert human annotators while dramatically reducing analysis time and enhancing reproducibility across datasets from different laboratories. By bridging hearing research, sensory neuroscience, and advanced computational techniques, ABRA facilitates broader interdisciplinary insights into auditory function. An online version of the tool is available for use at no cost at https://abra.ucsd.edu.","url":"https://doi.org/10.21203/rs.3.rs-6735294/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6735294/v1","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2025.03.17.643718","name":"Light-field deep learning enables high-throughput, scattering-mitigated calcium imaging","source":"preprints","abstract":"Light field microscopy (LFM) enables volumetric, high throughput functional imaging. However, the computational burden and vulnerability to scattering limit LFM’s application to neuroscience. We present a light-field strategy for volumetric, scattering-mitigated neural circuit activity monitoring. A physics-based deep neural network, LNet, is trained with two-photon volumes and one-photon light fields. A processing pipeline uses LNet to extract calcium activity from light-field videos of jGCaMP8f-expressing neurons in acute cortical slices. The extracted time series have high signal-to-noise ratios and reduced optical crosstalk compared to conventional volume reconstruction methods. Imaging 100 volumes per second, we observe putative spikes fired at up to 10 Hz and the spatial intermingling of putative ensembles throughout 530 x 530 x 100-micron volumes. Compared to iterative algorithms, LNet workflows reduce light-field video processing times by 2- to 12-fold, advancing the goal of real-time, scattering-robust volumetric neural circuit imaging for closed-loop and adaptive experimental paradigms.","url":"https://doi.org/10.1101/2025.03.17.643718","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.03.17.643718","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2025.07.24.666602","name":"The Locomoting State Selectively Amplifies Activity of Sensitizing Neurons in Primary Visual Cortex","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.07.24.666602","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.07.24.666602","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.21203/rs.3.rs-6306814/v1","name":"Spike inference from calcium imaging data acquired with GCaMP8 indicators","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-6306814/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6306814/v1","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.64898/2025.12.19.695412","name":"Dopaminergic Control of Retinal Oscillations Driving Infantile Nystagmus","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2025.12.19.695412","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.64898/2025.12.19.695412","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.10.03.680281","name":"Increased HCN1 activity in human excitatory neurons drives excessive network bursting in Dravet syndrome","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.10.03.680281","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.10.03.680281","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.05.19.654889","name":"Sound offset responses become highly informative in the auditory cortex","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.05.19.654889","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.05.19.654889","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2025.03.03.641129","name":"Spike inference from calcium imaging data acquired with GCaMP8 indicators","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.03.03.641129","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.03.03.641129","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.10.06.680791","name":"Astrocytes and neurons encode natural stimuli with partially shared but distinct composite receptive fields","source":"preprints","abstract":"ABSTRACT Astrocytes are increasingly recognized as active participants in sensory processing, but whether they show selective responses to stimulus features, analogous to neuronal receptive fields, is not yet established. To address this, we used two-photon calcium imaging in the auditory cortex of anesthetized mice during presentation of natural ultrasonic vocalizations. Our aim was to compare astrocytic responses with those of neighboring neurons and to determine whether astrocytes exhibit feature-selective receptive fields. Event detection showed that astrocytic calcium activity is highly heterogeneous, but only a minority of events were consistently stimulus-linked. To examine this stimulus-driven subset, we estimated receptive field features using maximum noise entropy modeling and compared them with those of concurrently recorded neurons. Despite qualitative similarities in receptive-field features, analysis of modulation spectra and principal angles showed that astrocytic and neuronal receptive fields overlap but occupy distinct regions of feature space. This indicates that astrocytes and neurons encode partially shared, but not identical, dimensions of the sensory stimulus. Our findings indicate that astrocytes encode diverse sensory features, providing an additional contribution to neuronal encoding. This suggests that astrocytic calcium activity is not simply a reflection of neuronal firing, but instead represents a distinct component of cortical sensory processing. New and noteworthy We used two-photon imaging to record calcium activity in astrocytes and neighboring neurons during presentation of natural ultrasonic vocalizations. We show that astrocyte activity is highly heterogeneous across spatial and temporal scales. Further analyses indicate that a subset of astrocyte calcium activity is stimulus-linked and encodes dimensions of the stimulus that partially overlap but are not identical to those encoded by neurons.","url":"https://doi.org/10.1101/2025.10.06.680791","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.10.06.680791","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.1101/2025.08.21.670039","name":"Modulation of motor cortical theta and gamma oscillations using phase-targeted, closed-loop optogenetic stimulation of local excitatory and inhibitory neurons","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.08.21.670039","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.08.21.670039","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.773Z"},{"id":"doi:10.64898/2026.02.17.706406","name":"Open- and Closed-Loop Microcomplexes in Neocerebellum","source":"preprints","abstract":"Neocerebellum facilitates motor and cognitive behavior via olivocerebellar modules, in which Purkinje cells (PCs), cerebellar nuclei (CN) neurons and olivary cells are supposed to form exclusively closed-loops. Here, we show that parts of the modules can be organized in an open-loop feedforward fashion where PCs do not contact the CN neurons that provide feedback to the olive. The PCs in the open-loop microcomplexes exclusively target projection CN neurons, through which cerebellum modulates downstream brainstem regions controlling behavior. This novel cerebellar architecture, containing open- and closed-loop microcomplexes within single modules, offers a mechanism by which mossy fiber information can be differentially used either as feedforward control of behavior and/or as feedback to the olivary subnuclei that regulates activity and plasticity within the module involved. This potential for both integrated and segregated regulation of behavior and feedback within single modules enriches the computational repertoire of the olivocerebellar system.","url":"https://doi.org/10.64898/2026.02.17.706406","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.02.17.706406","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2025.09.07.674483","name":"Developmental excitation-inhibition imbalance permanently reprograms autism-relevant social brain circuits","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.09.07.674483","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.09.07.674483","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2025.10.03.680368","name":"An ion channel omnimodel for standardized biophysical neuron modelling","source":"preprints","abstract":"Biophysical neuron modeling is an indispensable tool in neuroscience research, with the combination of diverse ion channel kinetics and morphologies being used to explain various single-neuron properties and responses. Despite this, there is no standard way of formulating ion channel models, making it challenging to relate models to one another and experimental data. Here, we revive the idea of a standard model for ion channels based on the Hodgkin-Huxley formulation, and apply it to a recently curated database of ion channel models. We demonstrate that this standard formulation, which we refer to as an omnimodel, accurately fits the majority of voltage-gated models in the database (over 3,000 models). It produces similar, if not identical, responses to voltage-clamp protocols in simulations where the ion channel omnimodels were used. Importantly, the standard formalism enables easy comparison of models based on parameter settings. It can also be used to make new observations about the space of ion channel kinetics found in neurons. Furthermore, it facilitates the inference of ion channel parameters from the responses to standard protocols. We provide an interactive platform to compare and select channel models, and encourage the community to use this standard formulation whenever possible, to facilitate understanding and comparison among models.","url":"https://doi.org/10.1101/2025.10.03.680368","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.10.03.680368","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.774Z"},{"id":"doi:10.1101/2025.04.17.649364","name":"Feature-dependent decorrelation of sound representations across the auditory pathway","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.04.17.649364","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.04.17.649364","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.09.25.559130","name":"FARMS: Framework for Animal and Robot Modeling and Simulation","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.09.25.559130","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.09.25.559130","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.21203/rs.3.rs-6377546/v1","name":"Vigilance state dissociation induced by 5-MeO DMT in mice","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-6377546/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6377546/v1","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.21203/rs.3.rs-4676122/v1","name":"Dynamic basal ganglia output signals license and suppress forelimb movements","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4676122/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-4676122/v1","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.774Z"},{"id":"doi:10.1101/2025.04.04.647211","name":"Dual-site beta transcranial alternating current stimulation during a bimanual coordination task modulates functional connectivity between motor areas","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.04.04.647211","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.04.04.647211","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2025.08.29.673029","name":"Layer 5 lateral entorhinal cortex neurons encode updating of object-place associations","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.08.29.673029","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.08.29.673029","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2025.05.19.654866","name":"Dissociable Pupil and Oculomotor Markers of Attention Allocation and Distractor Suppression during listening","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.05.19.654866","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.05.19.654866","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2025.09.08.674912","name":"Granularity of thalamic head direction cells","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.09.08.674912","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.09.08.674912","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.21203/rs.3.rs-4492882/v1","name":"Astroglial disinhibition of cortical circuits disrupts cognition via kynurenic acid","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4492882/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-4492882/v1","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.774Z"},{"id":"doi:10.1101/2025.02.11.637674","name":"Functional specialisation of multisensory temporal integration in the mouse superior colliculus","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.02.11.637674","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.02.11.637674","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2025.01.02.631064","name":"Non-vectorial Integration of Intersectional Short-Pulse Stimulation Enables Enhanced Deep Brain Modulation and Effective Seizure Control","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.01.02.631064","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.01.02.631064","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2025.04.26.650764","name":"GABAergic neurons are major contributors of network inhibition in the neonatal hippocampus in-vivo","source":"preprints","abstract":"During development, neural network maturation is activity dependent. During the neonatal period, activity is provided by intermittent, spontaneous network activity patterns (SNAP) that occur independently of environment stimuli. Among the neurotransmitters that take part in neonatal development, the Gamma-amino-butyric acid (GABA) plays a pivotal role. GABAergic cells are the first to emerge the first to form functional synapses. GABA antagonists block hippocampal SNAPs in-vitro and alterations of GABAergic function dramatically impact cortical maturation. Based on these data, the traditional view is that the depolarizing action of GABA, a hallmark of immature networks in slice preparations, is at the core of developmental processes. However, in-vivo evidence for such depolarizing role is not clear, raising questions about the contribution of GABAergic neurons in-vivo. To address this issue we developed an in-vivo approach combining optogenetics and single-unit electrophysiology in non-anesthetized mice. This allowed us to both identify and manipulate hippocampal GABAergic cells while examining their influence on hippocampal SNAP. We found that, even during the first post-natal days, the net action of GABA is inhibitory, but not excitatory. This inhibitory action of GABA drastically increases after the second post-natal week.","url":"https://doi.org/10.1101/2025.04.26.650764","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.04.26.650764","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2025.04.22.650000","name":"Atypical collective oscillatory activity in cardiac tissue uncovered by optogenetics","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.04.22.650000","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.04.22.650000","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2025.01.01.631011","name":"Perturbing whole-brain models of brain hierarchy: an application for depression following pharmacological treatment","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.01.01.631011","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.01.01.631011","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2025.03.07.642064","name":"Engineering Cortical Networks: An Open Platform for Controlled Human Circuit Formation and Synaptic Analysis  <i>In vitro</i>","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.03.07.642064","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.03.07.642064","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2025.03.22.25324465","name":"Network-based Molecular Constraints on in vivo Synaptic Density Alterations in Schizophrenia","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.03.22.25324465","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.03.22.25324465","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.774Z"},{"id":"doi:10.1101/2023.10.06.561214","name":"A neural mechanism for learning from delayed postingestive feedback","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.10.06.561214","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.10.06.561214","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:25.774Z"},{"id":"doi:10.1101/2024.03.06.583740","name":"A systematic comparison of predictive models on the retina","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.03.06.583740","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.03.06.583740","addedAt":"2026-09-01T01:48:24.517Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.04.16.589773","name":"Sub-type specific connectivity between CA3 pyramidal neurons may underlie their sequential activation during sharp waves","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.04.16.589773","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.04.16.589773","addedAt":"2026-09-01T01:48:24.518Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2025.04.15.648462","name":"Fast and accessible morphology-free functional fluorescence imaging analysis","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.04.15.648462","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.04.15.648462","addedAt":"2026-09-01T01:48:24.518Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2025.02.19.639073","name":"Adaptation of visual responses in degenerating  <i>rd10</i>  and healthy mouse retinas during ongoing electrical stimulation","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.02.19.639073","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.02.19.639073","addedAt":"2026-09-01T01:48:24.518Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.06.20.599815","name":"An Open-Source Deep Learning-Based Toolbox for Automated Auditory Brainstem Response Analyses (ABRA)","source":"preprints","abstract":"Hearing loss is a pervasive global health challenge with profound impacts on communication, cognitive function, and quality of life. Recent studies have established age-related hearing loss as a significant risk factor for dementia, highlighting the importance of hearing loss research. Auditory brainstem responses (ABRs), which are electrophysiological recordings of acoustically evoked synchronized neural activity from the auditory nerve and brainstem, serve as in vivo correlates for sensory hair cell and synaptic function, hearing sensitivity, and other critical readouts of auditory pathway physiology, making them highly valuable for both basic neuroscience and clinical research. Despite their utility, traditional ABR analyses rely heavily on subjective manual interpretation, which may introduce variability and pose challenges for reproducibility across studies. Here, we introduce Auditory Brainstem Response Analyzer (ABRA), a novel suite of open-source ABR analysis tools powered by deep learning, which automates and standardizes ABR waveform analysis. ABRA employs convolutional neural networks trained on diverse datasets collected from multiple experimental settings, achieving rapid and unbiased extraction of key ABR metrics, including peak amplitude, latency, and auditory threshold estimates. We demonstrate that ABRA’s deep learning models provide performance comparable to expert human annotators while dramatically reducing analysis time and enhancing reproducibility across datasets from different laboratories. By bridging hearing research, sensory neuroscience, and advanced computational techniques, ABRA facilitates broader interdisciplinary insights into auditory function. An online version of the tool is available for use at no cost at https://abra.ucsd.edu .","url":"https://doi.org/10.1101/2024.06.20.599815","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.06.20.599815","addedAt":"2026-09-01T01:48:24.518Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2025.03.22.644729","name":"Comprehensive profiling of anaesthetised brain dynamics across phylogeny","source":"preprints","abstract":"Intrinsic dynamics of neuronal circuits shape information processing. Combining neuroimaging with causal perturbation offers the opportunity to understand how local dynamics mediate the link between neurobiology and functional repertoire. We compile a unique dataset of multi-scale neural activity during wakefulness and anaesthetic-induced suppression of information processing encompassing human, macaque, marmoset, mouse, zebrafish and nematode. Applying massive feature extraction, we comprehensively characterise local neural dynamics across >6,000 time-series features. Using dynamics as a common space for cross-species comparison reveals a conserved dynamical profile of anaesthesia across species, characterised by shorter intrinsic timescales of neural activity and dampened interregional synchrony. This dynamical regime is experimentally reversed in vivo by deep-brain stimulation of the macaque centromedian thalamus, restoring behavioural responsiveness. Spatially, this conserved dynamical phenotype covaries with conserved transcriptional profiles of excitatory and inhibitory neurotransmission across human, macaque, marmoset and mouse cortex. Biophysical modelling provides a mechanistic link between the macroscale dynamical phenotype of anaesthesia, and microscale effects of key molecular targets on the timescales of synaptic excitation and inhibition. Altogether, comprehensive dynamical phenotyping reveals a shared neural endpoint of anaesthesia: across species and scales, anaesthetics induce spatio-temporal isolation of local neural activity.","url":"https://doi.org/10.1101/2025.03.22.644729","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.03.22.644729","addedAt":"2026-09-01T01:48:24.518Z","updatedAt":"2026-09-01T01:48:31.443Z"},{"id":"doi:10.1101/2025.10.03.680235","name":"Highly correlated activity across higher-order thalamic nuclei in awake and anesthetized states","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.10.03.680235","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.10.03.680235","addedAt":"2026-09-01T01:48:24.518Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2025.03.25.645235","name":"Personalized mapping of inhibitory spinal cord circuits  <i>in vivo</i>  via non-invasive neural decoding and  <i>in silico</i>  modelling","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.03.25.645235","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.03.25.645235","addedAt":"2026-09-01T01:48:24.518Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.02.12.579892","name":"Zapit: Open Source Laser-Scanning Photostimulation For Neuroscience","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.02.12.579892","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.02.12.579892","addedAt":"2026-09-01T01:48:24.518Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2025.11.10.25339873","name":"Genome-Wide Meta-Analysis Identifies 47 Novel Loci and Links Essential Tremor to Ventral Diencephalon and Cerebellum Morphometry","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.11.10.25339873","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.11.10.25339873","addedAt":"2026-09-01T01:48:24.518Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.01.23.576792","name":"Local Inhibitory Dynamics Underpin Temporal Integration and Functional Segregation between Barrels and Septa in the Mouse Barrel Cortex","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.01.23.576792","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.01.23.576792","addedAt":"2026-09-01T01:48:24.518Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.12.21.629881","name":"Mouse brain organoids model  <i>in vivo</i>  neurodevelopment and function and capture differences to human","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.12.21.629881","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.12.21.629881","addedAt":"2026-09-01T01:48:24.518Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2025.08.06.668891","name":"Inhibition tunes prefrontal circuit dynamics to promote sociosexual behavior in female mice","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.08.06.668891","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.08.06.668891","addedAt":"2026-09-01T01:48:24.518Z","updatedAt":"2026-09-01T01:48:25.774Z"},{"id":"doi:10.1101/2024.12.20.24319330","name":"Diazepam modulates hippocampal CA1 functional connectivity in people at clinical high-risk for psychosis","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.12.20.24319330","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.12.20.24319330","addedAt":"2026-09-01T01:48:24.518Z","updatedAt":"2026-09-01T01:48:25.774Z"},{"id":"doi:10.1101/2024.12.27.629676","name":"An Independent Coding Scheme for Distance versus Position in the Hippocampus","source":"preprints","abstract":"ABSTRACT Animals navigate using cognitive maps of their environment, integrating external landmarks and distances between them. Hippocampal place cells are the neuronal substrate of these cognitive maps. However, while hippocampal allocentric position coding in reference to external landmarks is well characterized, the determinants of idiothetic hippocampal distance coding remain poorly understood. Using virtual reality, electrophysiological recordings in mice, and local cue manipulations we could dissociate distance from position coding. In the cue-poor condition, we found pervasive distance coding with high distance indices in all bidirectional place cells including both superficial and deep CA1 pyramidal cells. In this condition, the mapping of distance onto a low-dimensional manifold and rigid distance relationships between place fields suggested strong attractor dynamics similar to those observed for grid cells. Inactivation of the medial septum (MS), which disrupts grid cells, significantly reduced both distance coding and rigid distance dynamics, suggesting an alteration (but not complete abolition) of the underlying attractor. In contrast, allocentric position coding could be observed in cue-rich environments, predominantly engaged deep CA1 pyramidal cells, and persisted during MS inactivation. These results are consistent with a selective contribution of grid cells and associated rigid attractor dynamics to hippocampal idiothetic distance coding but not allocentric position coding.","url":"https://doi.org/10.1101/2024.12.27.629676","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.12.27.629676","addedAt":"2026-09-01T01:48:24.518Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.21203/rs.3.rs-5931393/v1","name":"Induction of Lewy-like aggregates perturbs the firing dynamics of midbrain dopaminergic neurons in vivo","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-5931393/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-5931393/v1","addedAt":"2026-09-01T01:48:24.518Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2025.01.10.24319636","name":"Stable isotope labeling kinetics of neurofilament light<i>in vitro</i>and<i>in vivo</i>","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.01.10.24319636","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.01.10.24319636","addedAt":"2026-09-01T01:48:24.518Z","updatedAt":"2026-09-01T01:48:25.774Z"},{"id":"doi:10.1101/2025.09.24.677985","name":"Functional independence of entorhinal grid cell modules enables remapping in hippocampal place cells","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.09.24.677985","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.09.24.677985","addedAt":"2026-09-01T01:48:24.518Z","updatedAt":"2026-09-01T01:48:25.774Z"},{"id":"doi:10.1101/2024.12.22.24319047","name":"Large-scale RF mapping without visual input for neuroprostheses in macaque and human visual cortex","source":"preprints","abstract":"High-channel-count neuroprostheses could one day restore functional vision in blind individuals by delivering electrical pulses to electrodes in the visual cortex that elicit perceptions known as ‘phosphenes’. However, if a high number of electrodes are used, it becomes challenging and time-consuming to map the visual field locations of all phosphenes. Furthermore, many blind users are not able to maintain stable fixation, impeding the localization of phosphenes, or may perceive spontaneous visual phenomena that interfere with detection of electrically induced phosphenes. Here, we introduce NEural Unsupervised electrode mapping (NEUmap), a rapid, largely automated method for phosphene mapping that extracts spatial patterns from spontaneous activity across the visual cortex. As correlations between neuronal activity on nearby electrodes are stronger than those between distant electrodes, we first use dimensionality-reduction algorithms to generate maps of relative positions of electrodes. We then convert these maps from relative to absolute visual field coordinates while the subject maps out a small number of phosphenes manually. NEUmap generated maps across ∼300-700 electrodes in each of two sighted monkeys and across 73-91 electrodes in each of three blind human volunteers. We report that the method allows rapid mapping of many electrodes using less than a second of resting-state data, with minimal effort from the subject, in the absence of vision.","url":"https://doi.org/10.1101/2024.12.22.24319047","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.12.22.24319047","addedAt":"2026-09-01T01:48:24.518Z","updatedAt":"2026-09-01T01:48:25.774Z"},{"id":"doi:10.21203/rs.3.rs-5597941/v1","name":"The claustrum is critical for maintaining working memory information","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-5597941/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-5597941/v1","addedAt":"2026-09-01T01:48:24.518Z","updatedAt":"2026-09-01T01:48:25.774Z"},{"id":"doi:10.1101/2024.12.16.628673","name":"PinkyCaMP a mScarlet-based calcium sensor with exceptional brightness, photostability, and multiplexing capabilities","source":"preprints","abstract":"Genetically encoded calcium (Ca 2+ ) indicators (GECIs) are widely used for imaging neuronal activity, yet current limitations of existing red fluorescent GECIs have constrained their applicability. The inherently dim fluorescence and low signal-to-noise ratio of red-shifted GECIs have posed significant challenges. More critically, several red-fluorescent GECIs exhibit photoswitching when exposed to blue light, thereby limiting their applicability in all-optical experimental approaches. Here, we present the development of PinkyCaMP, the first mScarlet-based Ca 2+ sensor that outperforms current red fluorescent sensors in brightness, photostability, signal-to-noise ratio, and compatibility with optogenetics and neurotransmitter imaging. PinkyCaMP is well-tolerated by neurons, showing no toxicity or aggregation, both in vitro and in vivo . All imaging approaches, including single-photon excitation methods such as fiber photometry, widefield imaging, miniscope imaging, as well as two-photon imaging in awake mice, are fully compatible with PinkyCaMP.","url":"https://doi.org/10.1101/2024.12.16.628673","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.12.16.628673","addedAt":"2026-09-01T01:48:24.518Z","updatedAt":"2026-09-01T01:48:25.774Z"},{"id":"doi:10.1101/2025.10.22.683934","name":"A splice-switching antisense oligonucleotide approach for pediatric genetic epilepsies","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.10.22.683934","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.10.22.683934","addedAt":"2026-09-01T01:48:24.518Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.05.12.540591","name":"Deep learning-driven characterization of single cell tuning in primate visual area V4 supports topological organization","source":"preprints","abstract":"Deciphering the brain’s structure-function relationship is key to understanding the neuronal mechanisms underlying perception and cognition. The cortical column, a vertical organization of neurons with similar functions, is a classic example of primate neocortex structure-function organization. While columns have been identified in primary sensory areas using parametric stimuli, their prevalence across higher-level cortex is debated, particularly regarding complex tuning in natural image space. However, a key hurdle in identifying columns is characterizing the complex, nonlinear tuning of neurons to high-dimensional sensory inputs. Building on prior findings of topological organization for features like color and orientation, we investigate functional clustering in macaque visual area V4 in non-parametric natural image space, using large-scale recordings and deep learning–based analysis. We combined linear probe recordings with deep learning methods to systematically characterize the tuning of >1,200 V4 neurons using in silico synthesis of most exciting images (MEIs), followed by in vivo verification. Single V4 neurons exhibited MEIs containing complex features, including textures and shapes, and even high-level attributes with eye-like appearance. Neurons recorded on the same silicon probe, inserted orthogonal to the cortical surface, often exhibited similarities in their spatial feature selectivity, suggesting a degree of functional organization along the cortical depth. We quantified MEI similarity using human psychophysics and distances in a contrastive learning-derived embedding space. Moreover, the selectivity of the V4 neuronal population showed evidence of clustering into functional groups of shared feature selectivity. These functional groups showed parallels with the feature maps of units in artificial vision systems, suggesting potential shared encoding strategies. These results demonstrate the feasibility and scalability of deep learning–based functional characterization of neuronal selectivity in naturalistic visual contexts, offering a framework for quantitatively mapping cortical organization across multiple levels of the visual hierarchy.","url":"https://doi.org/10.1101/2023.05.12.540591","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.05.12.540591","addedAt":"2026-09-01T01:48:24.518Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1007/978-3-031-97274-4_16","name":"An Overview on Applications of Spiking Neural Networks and Spiking Neural P Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-97274-4_16","authors":["Claudio Zandron"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-30T12:19:57Z","doi":"10.1007/978-3-031-97274-4_16","addedAt":"2026-09-01T01:48:24.551Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1088/1741-2552/adec1c/v2/response1","name":"Author response for \"Manipulation of neuronal activity by an artificial spiking neural network implemented on a closed-loop brain-computer interface in non-human primates\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1741-2552/adec1c/v2/response1","authors":["Jonathan H Mishler","Richy Yun","Steve Perlmutter","Rajesh P N Rao","Eberhard E Fetz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-05T17:05:32Z","doi":"10.1088/1741-2552/adec1c/v2/response1","addedAt":"2026-09-01T01:48:24.551Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.3390/electronics15081756","name":"Integer-State Dynamics in Quantized Spiking Neural Networks: Implications for Hardware-Oriented Design","source":"crossref","abstract":"Spiking neural networks (SNNs) support energy-efficient machine intelligence because event-driven computation and sparse activity map naturally to low-power digital hardware. In practical implementations, however, membrane states, synaptic weights, and thresholds are represented with finite-precision integer arithmetic. Quantization, clipping, and overflow can therefore alter network dynamics rather than merely approximate a higher-precision model. This paper adopts an integer-state dynamical perspective, modeling a quantized SNN with a hardware-relevant update rule as a deterministic map on a bounded integer lattice. Rather than claiming recurrence itself as a new property, we focus on how finite-precision representation and implementation semantics shape observed recurrent regimes and activity patterns. We introduce a shift-based update rule with integer-valued states and investigate its behaviour through simulation-based analysis with network sizes N=30–130, connection densities 0.1–0.9, and bit widths 1 to 16 over T = 1000 steps. The results show bounded and recurrent temporal structure with strong quantization sensitivity. The observed regimes depend heavily on the semantics of representation and the scaling choices. These findings suggest that numerical precision can act as a dynamical design variable and provide useful implications for hardware-oriented SNN design, while motivating future work on attractor analysis and FPGA/ASIC validation.","url":"https://doi.org/10.3390/electronics15081756","authors":["Lei Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-21T11:42:45Z","doi":"10.3390/electronics15081756","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.3390/biomimetics11010075","name":"Hybrid Spike-Encoded Spiking Neural Networks for Real-Time EEG Seizure Detection: A Comparative Benchmark","source":"europepmc","abstract":"Reliable and low-latency seizure detection from electroencephalography (EEG) is critical for continuous clinical monitoring and emerging wearable health technologies. Spiking neural networks (SNNs) provide an event-driven computational paradigm that is well suited to real-time signal processing, yet achieving competitive seizure detection performance with constrained model complexity remains challenging. This work introduces a hybrid spike encoding scheme that combines Delta–Sigma (change-based) and stochastic rate representations, together with two spiking architectures designed for real-time EEG analysis: a compact feed-forward HybridSNN and a convolution-enhanced ConvSNN incorporating depthwise-separable convolutions and temporal self-attention. The architectures are intentionally designed to operate on short EEG segments and to balance detection performance with computational practicality for continuous inference. Experiments on the CHB–MIT dataset show that the HybridSNN attains 91.8% accuracy with an F1-score of 0.834 for seizure detection, while the ConvSNN further improves detection performance to 94.7% accuracy and an F1-score of 0.893. Event-level evaluation on continuous EEG recordings yields false-alarm rates of 0.82 and 0.62 per day for the HybridSNN and ConvSNN, respectively. Both models exhibit inference latencies of approximately 1.2 ms per 0.5 s window on standard CPU hardware, supporting continuous real-time operation. These results demonstrate that hybrid spike encoding enables spiking architectures with controlled complexity to achieve seizure detection performance comparable to larger deep learning models reported in the literature, while maintaining low latency and suitability for real-time clinical and wearable EEG monitoring.","url":"https://doi.org/10.3390/biomimetics11010075","authors":["Ali Mehrabi","Neethu Sreenivasan","Upul Gunawardana","Gaetano Gargiulo"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/biomimetics11010075","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1016/j.vlsi.2025.102461","name":"Memory device based on memristor-diode crossbar and control CMOS logic for spiking neural network hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.vlsi.2025.102461","authors":["A.N. Busygin","A.D. Pisarev","S. Yu Udovichenko","A.H.A. Ebrahim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-07T02:33:00Z","doi":"10.1016/j.vlsi.2025.102461","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1007/s11047-024-09996-z","name":"Correction: Integrated dynamic spiking neural P systems for fault line selection in distribution network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11047-024-09996-z","authors":["Song Ma","Qiang Yang","Gexiang Zhang","Fei Li","Fan Yu","Xiu Yin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-24T03:02:49Z","doi":"10.1007/s11047-024-09996-z","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1109/access.2025.3625784","name":"Enhanced Detection of Epileptic Seizure Using Hybrid Framework of Slantlet Transform and Spiking Neural Network Model","source":"crossref","abstract":"","url":"https://doi.org/10.1109/access.2025.3625784","authors":["Smitaranjan Tripathy","Subir Biswas","Adyasha Rath","Prabodh Kumar Sahoo","Aswini Kumar Samantaray","Ganapati Panda"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-27T18:05:43Z","doi":"10.1109/access.2025.3625784","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.11591/ijai.v14.i1.pp350-357","name":"New method for assessing suicide ideation based on an attention mechanism and spiking neural network","source":"crossref","abstract":"The COVID-19 pandemic has had a substantial effect on global mental health, leading to increased depression and suicide ideation (SI), particularly among young adults. This study introduces a novel method for enhancing SI assessment in young adults with depression, utilizing machine learning (ML) techniques applied to structural magnetic resonance imaging (SMRI) data. SMRI data from 20 individuals with depression and 60 healthy controls were analyzed. A hybrid ML algorithm, integrating self-attention mechanism and evolving spiking neural networks, successfully classified depression with 94% accuracy, 100% sensitivity, 92% specificity, and an area under the curve of 0.96. These results offer potential for enhancing mental health intervention and support in the context of the ongoing and post-pandemic period influenced by COVID-19.","url":"https://doi.org/10.11591/ijai.v14.i1.pp350-357","authors":["Corrine Francis","Abdulrazak Yahya Saleh Al-Hababi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-29T15:21:29Z","doi":"10.11591/ijai.v14.i1.pp350-357","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/isbdas64762.2025.11116929","name":"STRA-SNN: Spatio-Temporal Residual Attention Mechanism in Spiking Neural Network for Efficient Classification of Event Stream Data","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isbdas64762.2025.11116929","authors":["Qian Cheng","Xingming Tang","Shukai Duan","Lidan Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-21T18:17:59Z","doi":"10.1109/isbdas64762.2025.11116929","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1016/j.asoc.2026.115772","name":"Sentence-level sentiment classification model based on echo spiking neural P systems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2026.115772","authors":["Lingyun Zhang","Hong Peng","Jun Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-14T16:51:50Z","doi":"10.1016/j.asoc.2026.115772","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1145/3817124.3817222","name":"AwF-SNN: Fixed-Mask Continuity-Preserving Temporal State-Transition Compression for Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3817124.3817222","authors":["Pengliang Yu","Shouwei Gao","Zichao Hong","Zihao Zhu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-31T05:20:33Z","doi":"10.1145/3817124.3817222","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.23919/date64628.2025.10993026","name":"Adaptive Multi-Threshold Encoding for Energy-Efficient ECG Classification Architecture Using Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.23919/date64628.2025.10993026","authors":["Sumit Diware","Yingzhou Dong","Mohammad Amin Yaldagard","Said Hamdioui","Rajendra Bishnoi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-21T17:36:35Z","doi":"10.23919/date64628.2025.10993026","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1016/j.asoc.2025.113689","name":"Spiking neural network with time-varying weights for rail squat detection","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2025.113689","authors":["Wassamon Phusakulkajorn","Jurjen Hendriks","Zili Li","Alfredo Núñez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-08T15:10:48Z","doi":"10.1016/j.asoc.2025.113689","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.37965/jait.2025.0848","name":"Feature-Optimized Intrusion Detection Based on a Hybrid Spiking Neural Network for the Internet of Things","source":"crossref","abstract":"The intrusion detection system (IDS) has gained significant attention due to its ability to enhance network utilization. However, different types of IDS approaches have been developed in traditional research that concentrate on recognizing intrusions from datasets with the help of classification. This research proposes a Lyrebird Optimization Algorithm (LOA) with Beta Hebbian Learning-based Elite Spike Neural Network (BHLESNN) for IDS classification. The LOA selects optimal features and reduces redundancy because it can explore and exploit the search space, thereby enhancing classifier performance. The usage of the beta function for spike encoding enhances temporal precision and allows a better presentation of dynamic features in network traffic. Furthermore, the network’s capability to learn temporal and spatial patterns makes it efficient in detecting IDS. The metrics, including precision, accuracy, F1-score, and recall, are assessed to show the efficiency of LOA-BHLESNN. The proposed LOA-BHLESNN achieves accuracy of 99.96%, 99.94% and 99.81% for ToN-IoT, BoT-IoT, and IoT-23 datasets, respectively, which is better than Dual Phase Feature Extraction-Conditional Tabular Generative Adversarial Networks(DPFEN-CTGAN).","url":"https://doi.org/10.37965/jait.2025.0848","authors":["Manu Gorur Vishwanath","Ananda Babu Jayachandra","Chin-Ling Chen","Ling-Chun Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-20T13:48:06Z","doi":"10.37965/jait.2025.0848","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/confluence60223.2024.10463263","name":"Fuzzy and Spiking Neural Network-based Secure Data Exchange Framework for Autonomous Vehicle","source":"crossref","abstract":"","url":"https://doi.org/10.1109/confluence60223.2024.10463263","authors":["Nishi Patel","Dhyan Patel","Nilesh Kumar Jadav","Sudeep Tanwar","Deepak Garg"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-21T17:52:49Z","doi":"10.1109/confluence60223.2024.10463263","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1109/tc.2022.3191738","name":"Spiking Generative Adversarial Networks With a Neural Network Discriminator: Local Training, Bayesian Models, and Continual Meta-Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tc.2022.3191738","authors":["Bleema Rosenfeld","Osvaldo Simeone","Bipin Rajendran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-07-18T20:34:30Z","doi":"10.1109/tc.2022.3191738","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/iscas66217.2026.11562792","name":"Energy-Efficient Fall Detection Using Conditional Dual-Path Spiking Neural Networks with Hierarchical Temporal Dynamics","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas66217.2026.11562792","authors":["Xiangting Li","Yangyang Huang","Linxiang Su","Siqiong Yao","Yongfu Li","Jian Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-18T20:06:41Z","doi":"10.1109/iscas66217.2026.11562792","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1145/3796315.3796319","name":"Adversarial Training for Robust Spiking Neural Networks via Boundary Stability Estimation","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3796315.3796319","authors":["Haonan Li","Xiurui Xie","Yupeng Liu","Qiugang Zhan","Yuning Yang","Guisong Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-08T09:25:41Z","doi":"10.1145/3796315.3796319","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1007/978-3-032-07690-8_12","name":"Study of the Possibility of Analyzing Changes in the State of a Complex Technical System Using a Spiking Neural Network Based on a Compartmental Neuron Model","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-07690-8_12","authors":["Ivan Fomin","Anton Korsakov","Alexandr Bakhshiev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-11T04:38:03Z","doi":"10.1007/978-3-032-07690-8_12","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1109/ism66958.2025.00032","name":"Attention-Enhanced Multi-Branch Spiking Neural Network for Event Stream Super-Resolution","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ism66958.2025.00032","authors":["Ahmadreza Sezavar","Catarina Brites","João Ascenso"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-03T20:53:35Z","doi":"10.1109/ism66958.2025.00032","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1134/s106373972560044x","name":"Training a Spiking Neural Network Taking into Account the Operational Features of a Memristive Crossbar Array","source":"crossref","abstract":"","url":"https://doi.org/10.1134/s106373972560044x","authors":["A. P. Dudkin","E. A. Ryndin","N. V. Andreeva"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-01T11:46:50Z","doi":"10.1134/s106373972560044x","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1093/ietele/e89-c.11.1637","name":"A VLSI Spiking Feedback Neural Network with Negative Thresholding and Its Application to Associative Memory","source":"crossref","abstract":"","url":"https://doi.org/10.1093/ietele/e89-c.11.1637","authors":["K. SASAKI","T. MORIE","A. IWATA"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-11-10T04:48:22Z","doi":"10.1093/ietele/e89-c.11.1637","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1109/icnc-fskd59587.2023.10281037","name":"Spiking Neural Network Classification Method in Motor Imagery Brain-Computer Interface","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc-fskd59587.2023.10281037","authors":["Ping Tan","Han Xiao","Han Zou","Kun Liu","Yi Shen","Chao Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-18T17:43:48Z","doi":"10.1109/icnc-fskd59587.2023.10281037","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1109/fpl.2005.1515790","name":"Design and fpga implementation of an embedded real-time biologically plausible spiking neural network processor","source":"crossref","abstract":"","url":"https://doi.org/10.1109/fpl.2005.1515790","authors":["M.J. Pearson","C. Melhuish","A.G. Pipe","M. Nibouche","I. Gilhesphy","K. Gurney","B. Mitchinson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-10-12T13:27:51Z","doi":"10.1109/fpl.2005.1515790","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1007/978-0-387-21703-1_9","name":"Paradigms for Computing with Spiking Neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-0-387-21703-1_9","authors":["Wolfgang Maass"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-11-09T13:15:38Z","doi":"10.1007/978-0-387-21703-1_9","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1109/tetc.2016.2579605","name":"Optimizing Network Traffic for Spiking Neural Network Simulations on Densely Interconnected Many-Core Neuromorphic Platforms","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tetc.2016.2579605","authors":["Gianvito Urgese","Francesco Barchi","Enrico Macii","Andrea Acquaviva"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-06-15T19:36:02Z","doi":"10.1109/tetc.2016.2579605","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1007/978-981-95-3787-7_3","name":"Silicon-Based Integrated Diffractive Optical Neural Network Chip","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-95-3787-7_3","authors":["Tingzhao Fu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-02T03:40:31Z","doi":"10.1007/978-981-95-3787-7_3","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1109/ijcnn.2011.6033216","name":"Adaptive spiking neural networks with Hodgkin-Huxley neurons and Hebbian learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2011.6033216","authors":["Lyle N. Long"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-10-06T13:24:17Z","doi":"10.1109/ijcnn.2011.6033216","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1142/s2010324726500049","name":"Prediction of Electronic and Structural Properties in Two-Dimensional Materials Employing Spiking Deep Residual Network","source":"crossref","abstract":"Two-dimensional (2D) materials exhibit unique electronic and structural properties, but accurately predicting these characteristics remains challenging due to complex feature interactions and computational constraints. This paper proposes a Prediction of Electronic and Structural Properties in 2D Materials employing Spiking Deep Residual Network (PESP-2D-SDRN). Initially, Input data is sourced from the 2DMatPedia dataset and preprocessed using the Multivariate Fast Iterative Filter (M-FIF), which effectively removes noise. Relevant features from preprocessed data are then selected using the Oscillating Spider Monkey Optimization Algorithm (OSMO), enhancing the model’s focus on informative inputs. The selected features are given to the Spiking Deep Residual Network (SDRN) for precise property prediction across diverse material classes, including semiconducting, metallic, magnetic, insulating and topological systems. Implemented in MATLAB, the proposed method demonstrates superior performance, achieving 98.5% precision and 99.4% accuracy. These results confirm that PESP-2D-SDRN offers a robust and computationally efficient solution for high-dimensional material property prediction.","url":"https://doi.org/10.1142/s2010324726500049","authors":["Megha Gupta Chaudhary","Sushil Kumar","Sarvendra Kumar","Nitin Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-05T16:03:01Z","doi":"10.1142/s2010324726500049","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.54216/ijwac.000102","name":"Design Partition in a Spiking Neural Arrange of Hippocampus Vigorous to Imbalanced Excitation/Inhibition in Mesh Network","source":"crossref","abstract":"Proficient design division in dentate gyrus plays an imperative part in putting away data within the hippocampus. Current information of the structure and work of the hippocampus, entorhinal cortex, and dentate gyrus, in design partition are joined in this work. A three-layer feed-forward spiking neural network inspired by the rodent hippocampus an equipped with simplified synaptic and molecular mechanisms is developed. The aim of the study is to make a spiking neural network capable of pattern separation in imbalanced excitationinhibition ratios caused by different levels of stimulations or network damage. This work presents a novel theory on the cellular mechanisms of robustness to damages to synapses and connectivity of neurons in dentate gyrus that results in imbalanced excitation-inhibition activity of neurons. This spiking neural network uses simplified molecular and cellular hypothetical mechanisms and demonstrates efficient storing of information in different levels of stimulation and can be implemented in cognitive robotics.","url":"https://doi.org/10.54216/ijwac.000102","authors":["Shubha Mishra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-13T20:40:36Z","doi":"10.54216/ijwac.000102","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1109/tnano.2023.3322880","name":"L-Shaped Double Gate Bipolar Impact Ionization MOSFET Based Energy Efficient Leaky Integrate and Fire Neuron for Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnano.2023.3322880","authors":["Saheli Sarkhel","Tripty Kumari","Priyanka Saha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-09T19:36:45Z","doi":"10.1109/tnano.2023.3322880","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1209/0295-5075/aceb19","name":"Study of power-law activity distributions in a spiking neural network model","source":"crossref","abstract":"Abstract Neuronal avalanches are cascades of bursts of activity observed primarily in the superficial cortical layers, the distribution of which fits a power law well. Motivated by the observation, we study how a power-law activity distribution emerges in a spiking neural network model. Specifically, we clarify the fundamentals of the phenomenon by applying a general theory of scale-free behavior, introduced to explain the power-law degree distribution in a brain network, and disclose that two kinds of fluctuations in spiking dynamics serve as the essential mechanism for the phenomenon. It is shown that the scale-free behavior arises from a Markov process or a Fokker-Planck diffusion in one dimension and how the power-law exponent of the activity distribution is determined depending on several factors, including the time bin. Finally, we also explain the scale-free behavior observed in the statistics of activity lifetimes.","url":"https://doi.org/10.1209/0295-5075/aceb19","authors":["Myoung Won Cho","M. Y. Choi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-27T18:29:01Z","doi":"10.1209/0295-5075/aceb19","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1109/iscas56072.2025.11043929","name":"A Reconfigurable Digital Compute-In-Memory Heterogeneous Macro for Differential Frame Convolution and Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas56072.2025.11043929","authors":["Cheng Zhao","Li Lun","Zhenhui Dai","Haozhe Chen","Yingying Cui","Xiaoxin Cui"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-27T17:42:19Z","doi":"10.1109/iscas56072.2025.11043929","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1117/12.2680978","name":"A convolutional spiking neural network combined with residual blocks for electronic nose data processing","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.2680978","authors":["Biao Wu","Xinran Ge","Huisheng Zhang","Jia Yan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-08T17:10:22Z","doi":"10.1117/12.2680978","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/dac18072.2020.9218714","name":"A 90nm 103.14 TOPS/W Binary-Weight Spiking Neural Network CMOS ASIC for Real-Time Object Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/dac18072.2020.9218714","authors":["Po-Yao Chuang","Pai-Yu Tan","Cheng-Wen Wu","Juin-Ming Lu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-10-09T19:57:03Z","doi":"10.1109/dac18072.2020.9218714","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1016/j.knosys.2025.113194","name":"Spiking neural network classification of X-ray chest images","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.knosys.2025.113194","authors":["Marco Gatti","Jessica Amianto Barbato","Claudio Zandron"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-24T11:25:27Z","doi":"10.1016/j.knosys.2025.113194","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1609/aaai.v35i12.17329","name":"Temporal-Coded Deep Spiking Neural Network with Easy Training and Robust Performance","source":"crossref","abstract":"Spiking neural network (SNN) is promising but the development has fallen far behind conventional deep neural networks (DNNs) because of difficult training. To resolve the training problem, we analyze the closed-form input-output response of spiking neurons and use the response expression to build abstract SNN models for training. This avoids calculating membrane potential during training and makes the direct training of SNN as efficient as DNN. We show that the nonleaky integrate-and-fire neuron with single-spike temporal-coding is the best choice for direct-train deep SNNs. We develop an energy-efficient phase-domain signal processing circuit for the neuron and propose a direct-train deep SNN framework. Thanks to easy training, we train deep SNNs under weight quantizations to study their robustness over low-cost neuromorphic hardware. Experiments show that our direct-train deep SNNs have the highest CIFAR-10 classification accuracy among SNNs, achieve ImageNet classification accuracy within 1% of the DNN of equivalent architecture, and are robust to weight quantization and noise perturbation.","url":"https://doi.org/10.1609/aaai.v35i12.17329","authors":["Shibo Zhou","Xiaohua Li","Ying Chen","Sanjeev T. Chandrasekaran","Arindam Sanyal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-08T15:35:00Z","doi":"10.1609/aaai.v35i12.17329","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.23919/cje.2022.00.162","name":"Defects Recognition of Train Wheelset Tread Based on Improved Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.23919/cje.2022.00.162","authors":["Changfan Zhang","Congcong Huang","Jing He"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-26T14:00:55Z","doi":"10.23919/cje.2022.00.162","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1016/j.dsp.2023.104002","name":"SDDC-Net: A U-shaped deep spiking neural P convolutional network for retinal vessel segmentation","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.dsp.2023.104002","authors":["Bo Yang","Lang Qin","Hong Peng","Chenggang Guo","Xiaohui Luo","Jun Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-09T08:14:27Z","doi":"10.1016/j.dsp.2023.104002","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.14445/22315381/ijett-v69i7p222","name":"Medical Diagnosis Model based on Spiking Neural Network considering Normalization of Histogram and Wavelet Transform Features of Medical Images","source":"crossref","abstract":"","url":"https://doi.org/10.14445/22315381/ijett-v69i7p222","authors":["Ashish Kumar Dehariya","Pragya Shukla"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-07-05T12:33:11Z","doi":"10.14445/22315381/ijett-v69i7p222","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1007/11494669_18","name":"Real-Time Spiking Neural Network: An Adaptive Cerebellar Model","source":"crossref","abstract":"","url":"https://doi.org/10.1007/11494669_18","authors":["Christian Boucheny","Richard Carrillo","Eduardo Ros","Olivier J. -M. D. Coenen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-01-13T09:48:09Z","doi":"10.1007/11494669_18","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1109/dcna63495.2024.10718500","name":"Recognizing patterns in images using a small spiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/dcna63495.2024.10718500","authors":["Aleksander V. Kurbako","Dmitry M. Ezhov","Mikhail D. Prokhorov","Vladimir I. Ponomarenko"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-21T17:18:23Z","doi":"10.1109/dcna63495.2024.10718500","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.22323/1.429.0010","name":"A spiking neural network with fixed synaptic weights based on logistic maps for a classification task","source":"crossref","abstract":"","url":"https://doi.org/10.22323/1.429.0010","authors":["Alexander Sboev","Dmitriy Kunitsyn","Alexey Serenko","Roman Rybka"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-14T10:17:05Z","doi":"10.22323/1.429.0010","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1109/jsen.2021.3120845","name":"A Spiking Neural Network With Spike-Timing-Dependent Plasticity for Surface Roughness Analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1109/jsen.2021.3120845","authors":["Chunming Jiang","Le Yang","Yilei Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-10-15T23:43:23Z","doi":"10.1109/jsen.2021.3120845","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1109/aicas54282.2022.9869950","name":"A Hybrid Spiking Recurrent Neural Network on Hardware for Efficient Emotion Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aicas54282.2022.9869950","authors":["Chenglong Zou","Xiaoxin Cui","Yisong Kuang","Yuan Wang","Xinan Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-05T20:21:42Z","doi":"10.1109/aicas54282.2022.9869950","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1145/3518997.3536225","name":"Reproducibility Report for the Paper: “Evaluating Performance of Spintronics-Based Spiking Neural Network Chips using Parallel Discrete Event Simulation”","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3518997.3536225","authors":["Adriano Pimpini"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-10T15:39:15Z","doi":"10.1145/3518997.3536225","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.3390/mi14010203","name":"Event-Based Optical Flow Estimation with Spatio-Temporal Backpropagation Trained Spiking Neural Network","source":"crossref","abstract":"The advantages of an event camera, such as low power consumption, large dynamic range, and low data redundancy, enable it to shine in extreme environments where traditional image sensors are not competent, especially in high-speed moving target capture and extreme lighting conditions. Optical flow reflects the target’s movement information, and the target’s detailed movement can be obtained using the event camera’s optical flow information. However, the existing neural network methods for optical flow prediction of event cameras has the problems of extensive computation and high energy consumption in hardware implementation. The spike neural network has spatiotemporal coding characteristics, so it can be compatible with the spatiotemporal data of an event camera. Moreover, the sparse coding characteristic of the spike neural network makes it run with ultra-low power consumption on neuromorphic hardware. However, because of the algorithmic and training complexity, the spike neural network has not been applied in the prediction of the optical flow for the event camera. For this case, this paper proposes an end-to-end spike neural network to predict the optical flow of the discrete spatiotemporal data stream for the event camera. The network is trained with the spatio-temporal backpropagation method in a self-supervised way, which fully combines the spatiotemporal characteristics of the event camera while improving the network performance. Compared with the existing methods on the public dataset, the experimental results show that the method proposed in this paper is equivalent to the best existing methods in terms of optical flow prediction accuracy, and it can save 99% more power consumption than the existing algorithm, which is greatly beneficial to the hardware implementation of the event camera optical flow prediction., laying the groundwork for future low-power hardware implementation of optical flow prediction for event cameras.","url":"https://doi.org/10.3390/mi14010203","authors":["Yisa Zhang","Hengyi Lv","Yuchen Zhao","Yang Feng","Hailong Liu","Guoling Bi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-16T02:29:55Z","doi":"10.3390/mi14010203","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1007/s00422-017-0710-5","name":"Macroscopic neural mass model constructed from a current-based network model of spiking neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00422-017-0710-5","authors":["Hiroaki Umehara","Masato Okada","Jun-nosuke Teramae","Yasushi Naruse"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-02-06T14:57:07Z","doi":"10.1007/s00422-017-0710-5","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1007/s00542-024-05755-3","name":"Biologically inspired tonic and bursting LIF neuron model for spiking neural network: a CMOS implementation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00542-024-05755-3","authors":["M. A. Seenivasan","Adarsh V. Parekkattil","Rekib Uddin Ahmed","Prabir Saha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-10T16:17:53Z","doi":"10.1007/s00542-024-05755-3","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1145/3354265.3354280","name":"Design and Analysis of Real Time Spiking Neural Network Decoder for Neuromorphic Chips","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3354265.3354280","authors":["Chenyuan Zhao","Lingjia Liu","Yang Yi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-09-12T14:21:08Z","doi":"10.1145/3354265.3354280","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1109/edkcon56221.2022.10032919","name":"A super Threshold Compact Silicon Neuron Circuit for Different Neuron Dynamics Suitable for Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/edkcon56221.2022.10032919","authors":["Sayantan Samanta","Koushik Naskar","Souvanik Pal","Suman Mallik","Sudipta Ghosh","Swarnil Roy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-02-09T18:41:32Z","doi":"10.1109/edkcon56221.2022.10032919","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1049/icp.2024.1343","name":"Exploring the potential of ultra-low latency spiking neural network in remote sensing image classification","source":"crossref","abstract":"","url":"https://doi.org/10.1049/icp.2024.1343","authors":["Jiahao Li","Ming Xu","He Chen","Can Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-04T20:14:49Z","doi":"10.1049/icp.2024.1343","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1162/089976606774841567","name":"Spontaneous Dynamics of Asymmetric Random Recurrent Spiking Neural Networks","source":"crossref","abstract":"In this letter, we study the effect of a unique initial stimulation on random recurrent networks of leaky integrate-and-fire neurons. Indeed, given a stochastic connectivity, this so-called spontaneous mode exhibits various nontrivial dynamics. This study is based on a mathematical formalism that allows us to examine the variability of the afterward dynamics according to the parameters of the weight distribution. Under the independence hypothesis (e.g., in the case of very large networks), we are able to compute the average number of neurons that fire at a given time—the spiking activity. In accordance with numerical simulations, we prove that this spiking activity reaches a steady state. We characterize this steady state and explore the transients.","url":"https://doi.org/10.1162/089976606774841567","authors":["Hédi Soula","Guillaume Beslon","Olivier Mazet"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-11-17T21:55:49Z","doi":"10.1162/089976606774841567","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1098/rsos.231606/v2/response1","name":"Author response for \"Spiking Neural Networks for Nonlinear Regression\"","source":"crossref","abstract":"","url":"https://doi.org/10.1098/rsos.231606/v2/response1","authors":["Henkes, Alexander","Eshraghian, Jason K.","Wessels, Henning"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-02T17:08:58Z","doi":"10.1098/rsos.231606/v2/response1","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.2139/ssrn.5668179","name":"Optimal Sensor Placement using Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5668179","authors":["Samarth  Pradeep Barve","Ameer  Tamoor Khan","Shuai Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-27T17:55:51Z","doi":"10.2139/ssrn.5668179","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.597Z"},{"id":"doi:10.1145/3316480.3322893","name":"Transitioning Spiking Neural Network Simulators to Heterogeneous Hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3316480.3322893","authors":["Quang Anh Pham Nguyen","Philipp Andelfinger","Wentong Cai","Alois Knoll"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-31T12:37:16Z","doi":"10.1145/3316480.3322893","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.46916/22042026-1-978-5-00276-064-0","name":"NEURAL NETWORK MODULE FOR DETECTING OIL LEAKS","source":"crossref","abstract":"","url":"https://doi.org/10.46916/22042026-1-978-5-00276-064-0","authors":["Nikita Evgenievich Vasilenko","Dmitry Viktorovich Tarakanov","Arseniy Dmitrievich Khimochkin","Elena Nikolaevna Pauk"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-22T14:25:03Z","doi":"10.46916/22042026-1-978-5-00276-064-0","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1504/ijcc.2025.10073235","name":"BERA-CLOUD: Resource Allocation in Cloud Computing Using a Bald Eagle Optimised Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1504/ijcc.2025.10073235","authors":["Nikhil Kumar Marriwala","Sunita Panda","Priya Dasarwar","Pooja Singh","C. Gnana Kousalya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-04T13:00:47Z","doi":"10.1504/ijcc.2025.10073235","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.597Z"},{"id":"doi:10.1109/ftcs68006.2025.11405774","name":"A Low-Latency Hybrid Cryptographic Framework for Secure Spiking Neural Network Inference","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ftcs68006.2025.11405774","authors":["Xiaoliang Zhang","Jundong Feng","Junchao Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-03T20:49:35Z","doi":"10.1109/ftcs68006.2025.11405774","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.597Z"},{"id":"doi:10.3389/fncom.2024.1418115","name":"DT-SCNN: dual-threshold spiking convolutional neural network with fewer operations and memory access for edge applications","source":"crossref","abstract":"The spiking convolutional neural network (SCNN) is a kind of spiking neural network (SNN) with high accuracy for visual tasks and power efficiency on neuromorphic hardware, which is attractive for edge applications. However, it is challenging to implement SCNNs on resource-constrained edge devices because of the large number of convolutional operations and membrane potential (Vm) storage needed. Previous works have focused on timestep reduction, network pruning, and network quantization to realize SCNN implementation on edge devices. However, they overlooked similarities between spiking feature maps (SFmaps), which contain significant redundancy and cause unnecessary computation and storage. This work proposes a dual-threshold spiking convolutional neural network (DT-SCNN) to decrease the number of operations and memory access by utilizing similarities between SFmaps. The DT-SCNN employs dual firing thresholds to derive two similar SFmaps from one Vm map, reducing the number of convolutional operations and decreasing the volume of Vms and convolutional weights by half. We propose a variant spatio-temporal back propagation (STBP) training method with a two-stage strategy to train DT-SCNNs to decrease the inference timestep to 1. The experimental results show that the dual-thresholds mechanism achieves a 50% reduction in operations and data storage for the convolutional layers compared to conventional SCNNs while achieving not more than a 0.4% accuracy loss on the CIFAR10, MNIST, and Fashion MNIST datasets. Due to the lightweight network and single timestep inference, the DT-SCNN has the least number of operations compared to previous works, paving the way for low-latency and power-efficient edge applications.","url":"https://doi.org/10.3389/fncom.2024.1418115","authors":["Fuming Lei","Xu Yang","Jian Liu","Runjiang Dou","Nanjian Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-30T12:16:22Z","doi":"10.3389/fncom.2024.1418115","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.32604/cmc.2025.063789","name":"Behavior of Spikes in Spiking Neural Network (SNN) Model with Bernoulli for Plant Disease on Leaves","source":"crossref","abstract":"","url":"https://doi.org/10.32604/cmc.2025.063789","authors":["Urfa Gul","M. Junaid Gul","Gyu Sang Choi","Chang-Hyeon Park"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-23T03:41:45Z","doi":"10.32604/cmc.2025.063789","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.597Z"},{"id":"doi:10.4028/www.scientific.net/ssp.199.217","name":"A New Model of the Neuron for Biological Spiking Neural Network Suitable for Parallel Data Processing Realized in Hardware","source":"crossref","abstract":"The paper presents a modification of the structure of a biological neural network (BNN) based on spiking neuron models. The proposed modification allows to influence the level of the stimulus response of particular neurons in the BNN. We consider an extended, three-dimensional Hodgkin-Huxley model of the neural cell. A typical BNN composed of such neural cells have been expanded by addition of resistors in each branch point. The resistors can be treated as the weights in such BNN. We demonstrate that adding these elements to the BNN significantly affects the waveform of the potential on the membrane of the neuron, causing an uncontrolled excitation. This provides a better description of processes that take place in nervous cell. Such BNN enables an easy adaptation of the learning rules used in artificial or spiking neural networks. The modified BNN has been implemented on Graphics Processing Unit (GPU) in the CUDA C language. This platform enables a parallel data processing, which is an important feature in such applications.","url":"https://doi.org/10.4028/www.scientific.net/ssp.199.217","authors":["Aleksandra Świetlicka","Karol Gugała","Marta Kolasa","Jolanta Pauk","Andrzej Rybarczyk","Rafał Długosz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-03-25T14:43:16Z","doi":"10.4028/www.scientific.net/ssp.199.217","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1109/edtm61175.2025.11040989","name":"Physical Unclonable Function in Spiking Neural Network Based on in-Te Ovonic Threshold Switching Devices","source":"crossref","abstract":"","url":"https://doi.org/10.1109/edtm61175.2025.11040989","authors":["Huan Wang","Qihang Zhu","Hengyi Hu","Yi Li","Xiangshui Miao","Ming Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-30T17:36:02Z","doi":"10.1109/edtm61175.2025.11040989","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.597Z"},{"id":"doi:10.1109/ijcnn60899.2024.10650960","name":"Knowledge Distill for Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn60899.2024.10650960","authors":["Xiubo Liang","Ge Chao","Mengjian Li","Yijun Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T17:35:05Z","doi":"10.1109/ijcnn60899.2024.10650960","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1109/iciase45644.2019.9074049","name":"A Spiking Neural Network for Visual Color Feature Classification for Pictures with RGB-HSV Model","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iciase45644.2019.9074049","authors":["Hui Liang","Jianxing Wu","Ran Wang","Feng Liang","Li Sun","Guohe Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-04-24T01:28:20Z","doi":"10.1109/iciase45644.2019.9074049","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1109/icaace69793.2026.11508717","name":"Efficient Spiking Neural Networks for Accurate and Real-Time ECG Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icaace69793.2026.11508717","authors":["Liwei Meng","Ning Ning","Ruichen Ma","Guanchao Qiao","Fei Chen","Yian Liu","Shaogang Hu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-15T02:40:33Z","doi":"10.1109/icaace69793.2026.11508717","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1016/j.ins.2024.120998","name":"GGT-SNN: Graph learning and Gaussian prior integrated spiking graph neural network for event-driven tactile object recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.ins.2024.120998","authors":["Jing Yang","Zukun Yu","Shaobo Li","Yang Cao","JianJun Hu","Ji Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-09T13:52:29Z","doi":"10.1016/j.ins.2024.120998","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.3390/app11041383","name":"Time-Multiplexed Spiking Convolutional Neural Network Based on VCSELs for Unsupervised Image Classification","source":"crossref","abstract":"In this work, we present numerical results concerning a multilayer “deep” photonic spiking convolutional neural network, arranged so as to tackle a 2D image classification task. The spiking neurons used are typical two-section quantum-well vertical-cavity surface-emitting lasers that exhibit isomorphic behavior to biological neurons, such as integrate-and-fire excitability and timing encoding. The isomorphism of the proposed scheme to biological networks is extended by replicating the retina ganglion cell for contrast detection in the photonic domain and by utilizing unsupervised spike dependent plasticity as the main training technique. Finally, in this work we also investigate the possibility of exploiting the fast carrier dynamics of lasers so as to time-multiplex spatial information and reduce the number of physical neurons used in the convolutional layers by orders of magnitude. This last feature unlocks new possibilities, where neuron count and processing speed can be interchanged so as to meet the constraints of different applications.","url":"https://doi.org/10.3390/app11041383","authors":["Menelaos Skontranis","George Sarantoglou","Stavros Deligiannidis","Adonis Bogris","Charis Mesaritakis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-02-03T11:54:31Z","doi":"10.3390/app11041383","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.14569/ijarai.2015.040701","name":"A Minimal Spiking Neural Network to Rapidly Train and Classify Handwritten Digits in Binary and 10-Digit Tasks","source":"crossref","abstract":"","url":"https://doi.org/10.14569/ijarai.2015.040701","authors":["Amirhossein Tavanaei","Anthony S."],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-10T13:22:24Z","doi":"10.14569/ijarai.2015.040701","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1016/j.neunet.2026.108699","name":"GSASN: a graph self-learning attention scores network for spatial modeling of network traffic matrix prediction","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.108699","authors":["Juan Wu","Chensheng Tong","Jinsong Hu","Hong Tang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-20T00:18:11Z","doi":"10.1016/j.neunet.2026.108699","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1109/icee44586.2018.8937850","name":"Skyrmionic implementation of Spike Time Dependent Plasticity (STDP) enabled Spiking Neural Network (SNN) under supervised learning scheme","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icee44586.2018.8937850","authors":["Upasana Sahu","Kushaagra Goyal","Utkarsh Saxena","Tanmay Chavan","Udayan Ganguly","Debanjan Bhowmik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-03T00:49:11Z","doi":"10.1109/icee44586.2018.8937850","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1109/scis-isis.2012.6505305","name":"Human gesture recognition for robot partners by spiking neural network and classification learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/scis-isis.2012.6505305","authors":["Janos Botzheim","Takenori Obo","Naoyuki Kubota"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-04-26T23:28:32Z","doi":"10.1109/scis-isis.2012.6505305","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1109/lpt.2024.3424495","name":"Spiking Neural Network Equalizer With Fast and Low Power Decoding for IM/DD Optical Communication","source":"crossref","abstract":"","url":"https://doi.org/10.1109/lpt.2024.3424495","authors":["Shuangxu Li","Georg Böcherer","Stefano Calabrò","Maximilian Schädler"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-08T17:51:52Z","doi":"10.1109/lpt.2024.3424495","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1109/tnnls.2024.3437415","name":"Accurate and Efficient Event-Based Semantic Segmentation Using Adaptive Spiking Encoder–Decoder Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnnls.2024.3437415","authors":["Rui Zhang","Luziwei Leng","Kaiwei Che","Hu Zhang","Jie Cheng","Qinghai Guo","Jianxing Liao","Ran Cheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-23T13:56:00Z","doi":"10.1109/tnnls.2024.3437415","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.597Z"},{"id":"doi:10.1021/acsnano.5c15076.s001","name":"A Reconfigurable Silicon Transistor for Noise-Resilient Stochastic Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acsnano.5c15076.s001","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-07T11:00:53Z","doi":"10.1021/acsnano.5c15076.s001","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1145/3774904.3792337","name":"Energy-Efficient and Dequantization-Free Quantization of LLMs: A Spiking Neural Network Approach to Salient Value Mitigation","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3774904.3792337","authors":["Chenyu Wang","Zhanglu Yan","Zhi Zhou","Xu Chen","Weng-Fai Wong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-09T21:54:39Z","doi":"10.1145/3774904.3792337","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.52202/075280-0133","name":"Evolving Connectivity for Recurrent Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.52202/075280-0133","authors":["Guan Wang","Yuhao Sun","Sijie Cheng","Sen Song"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-02T13:18:04Z","doi":"10.52202/075280-0133","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1109/dcna56428.2022.9923314","name":"Reinforcement learning in a spiking neural network with memristive plasticity","source":"crossref","abstract":"","url":"https://doi.org/10.1109/dcna56428.2022.9923314","authors":["Danila Vlasov","Roman Rybka","Alexander Sboev","Alexey Serenko","Anton Minnekhanov","Vyacheslav Demin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-03T22:16:08Z","doi":"10.1109/dcna56428.2022.9923314","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1109/biorob49111.2020.9224303","name":"A Spiking Neural Network Emulating the Structure of the Oculomotor System Requires No Learning to Control a Biomimetic Robotic Head","source":"crossref","abstract":"","url":"https://doi.org/10.1109/biorob49111.2020.9224303","authors":["Praveenram Balachandar","Konstantinos P. Michmizos"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-10-15T16:05:32Z","doi":"10.1109/biorob49111.2020.9224303","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1109/embc48229.2022.9871205","name":"Cerebellum involvement in dystonia: insights from a spiking neural network model during associative learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/embc48229.2022.9871205","authors":["Alice Geminiani","Aurimas Mockevicius","Egidio D'Angelo","Claudia Casellato"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-08T16:02:05Z","doi":"10.1109/embc48229.2022.9871205","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1109/ijcnn.2019.8851848","name":"A Preprocessing Layer in Spiking Neural Networks – Structure, Parameters, Performance Criteria","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2019.8851848","authors":["Mikhail Kiselev","Andrey Lavrentyev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-10-01T03:44:32Z","doi":"10.1109/ijcnn.2019.8851848","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1007/s13748-024-00313-4","name":"A Deep Convolutional Spiking Neural Network for embedded applications","source":"crossref","abstract":"Abstract Deep neural networks (DNNs) have received a great deal of interest in solving everyday tasks in recent years. However, their computational and energy costs limit their use on mobile and edge devices. The neuromorphic computing approach called spiking neural networks (SNNs) represents a potential solution for bridging the gap between performance and computational expense. Despite the potential benefits of energy efficiency, the current SNNs are being used with datasets such as MNIST, Fashion-MNIST, and CIFAR10, limiting their applications compared to DNNs. Therefore, the applicability of SNNs to real-world applications, such as scene classification and forecasting epileptic seizures, must be demonstrated yet. This paper develops a deep convolutional spiking neural network (DCSNN) for embedded applications. We explore a convolutional architecture, Visual Geometry Group (VGG16), to implement deeper SNNs. To train a spiking model, we convert the pre-trained VGG16 into corresponding spiking equivalents with nearly comparable performance to the original one. The trained weights of VGG16 were then transferred to the equivalent SNN architecture while performing a proper weight–threshold balancing. The model is evaluated in two case studies: land use and land cover classification, and epileptic seizure detection. Experimental results show a classification accuracy of 94.88%, and seizure detection specificity of 99.45% and a sensitivity of 95.06%. It is confirmed that conversion-based training SNNs are promising, and the benefits of DNNs, such as solving complex and real-world problems, become available to SNNs.","url":"https://doi.org/10.1007/s13748-024-00313-4","authors":["Amirhossein Javanshir","Thanh Thi Nguyen","M. A. Parvez Mahmud","Abbas Z. Kouzani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-13T18:43:26Z","doi":"10.1007/s13748-024-00313-4","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1016/j.neunet.2023.07.008","name":"Sparser spiking activity can be better: Feature Refine-and-Mask spiking neural network for event-based visual recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2023.07.008","authors":["Man Yao","Hengyu Zhang","Guangshe Zhao","Xiyu Zhang","Dingheng Wang","Gang Cao","Guoqi Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-19T22:19:58Z","doi":"10.1016/j.neunet.2023.07.008","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1007/978-981-95-5795-0_3","name":"Reducing Data Transfer for Scalable Graph Neural Network Training","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-95-5795-0_3","authors":["Xin Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-26T12:43:59Z","doi":"10.1007/978-981-95-5795-0_3","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1007/s11042-024-18698-8","name":"Spatial spiking neural network for classification of EEG signals for concealed information test","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11042-024-18698-8","authors":["Damoder Reddy Edla","Annushree Bablani","Saugat Bhattacharyya","Ramesh Dharavath","Ramalingaswamy Cheruku","Vijayasree Boddu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-04T09:02:43Z","doi":"10.1007/s11042-024-18698-8","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1016/bs.pbr.2020.08.003","name":"Prediction of tinnitus masking benefit within a case series using a spiking neural network model","source":"crossref","abstract":"","url":"https://doi.org/10.1016/bs.pbr.2020.08.003","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-10-01T01:49:12Z","doi":"10.1016/bs.pbr.2020.08.003","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1007/978-3-031-30108-7_24","name":"High-Accuracy and Energy-Efficient Action Recognition with Deep Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-30108-7_24","authors":["Jingren Zhang","Jingjing Wang","Xie Di","Shiliang Pu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-12T04:03:04Z","doi":"10.1007/978-3-031-30108-7_24","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1007/978-3-032-15046-2_9","name":"Symmetrized and Perturbed Hyperbolic Tangent Neural Network Multivariate Approximation over Infinite Domains","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-15046-2_9","authors":["George A. Anastassiou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-14T08:42:11Z","doi":"10.1007/978-3-032-15046-2_9","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1109/ijcnn.2011.6033639","name":"Are probabilistic spiking neural networks suitable for reservoir computing?","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2011.6033639","authors":["Stefan Schliebs","Ammar Mohemmed","Nikola Kasabov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-10-06T13:24:17Z","doi":"10.1109/ijcnn.2011.6033639","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1109/tnn.2006.873274","name":"Spiking perceptrons","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnn.2006.873274","authors":["P. Rowcliffe","Jianfeng Feng","H. Buxton"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-05-12T15:09:56Z","doi":"10.1109/tnn.2006.873274","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1007/978-981-95-3787-7_2","name":"Silicon-Based Integrated Diffractive Optical Neural Network Model","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-95-3787-7_2","authors":["Tingzhao Fu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-01T23:28:12Z","doi":"10.1007/978-981-95-3787-7_2","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1016/j.neunet.2025.108214","name":"GeoScatt-GNN: A geometric scattering transform-based graph neural network model for Ames mutagenicity prediction","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.108214","authors":["Abdeljalil Zoubir","Badr Missaoui"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-17T09:50:11Z","doi":"10.1016/j.neunet.2025.108214","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1007/s00521-024-10191-5","name":"Energy efficient and low-latency spiking neural networks on embedded microcontrollers through spiking activity tuning","source":"crossref","abstract":"Abstract In this work, we target the efficient implementation of spiking neural networks (SNNs) for low-power and low-latency applications. In particular, we propose a methodology for tuning SNN spiking activity with the objective of reducing computation cycles and energy consumption. We performed an analysis to devise key hyper-parameters, and then we show the results of tuning such parameters to obtain a low-latency and low-energy embedded LSNN (eLSNN) implementation. We demonstrate that it is possible to adapt the firing rate so that the samples belonging to the most frequent class are processed with less spikes. We implemented the eLSNN on a microcontroller-based sensor node and we evaluated its performance and energy consumption using a structural health monitoring application processing a stream of vibrations for damage detection (i.e. binary classification). We obtained a cycle count reduction of 25% and an energy reduction of 22% with respect to a baseline implementation. We also demonstrate that our methodology is applicable to a multi-class scenario, showing that we can reduce spiking activity between 68 and 85% at iso-accuracy.","url":"https://doi.org/10.1007/s00521-024-10191-5","authors":["Francesco Barchi","Emanuele Parisi","Luca Zanatta","Andrea Bartolini","Andrea Acquaviva"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-01T17:02:33Z","doi":"10.1007/s00521-024-10191-5","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1016/j.neunet.2024.106656","name":"A new hybrid learning control system for robots based on spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106656","authors":["Vahid Azimirad","S. Yaser Khodkam","Amir Bolouri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-23T12:39:45Z","doi":"10.1016/j.neunet.2024.106656","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1002/9781394381609","name":"Spiking Neural P Systems for Time Series Analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9781394381609","authors":["Jun Wang","Hong Peng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-28T07:11:02Z","doi":"10.1002/9781394381609","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1103/6c63-cmgy","name":"Sampling-driven training of deep belief networks using a coherent Ising machine with spiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1103/6c63-cmgy","authors":["Xing-Yu Wu","Chen-Rui Fan","Yusen Wu","Chuan Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-24T23:48:53Z","doi":"10.1103/6c63-cmgy","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.2139/ssrn.4095760","name":"Spiking Neural P Systems with Weights and Delays on Synapses","source":"crossref","abstract":"Spiking neural P systems with weights (WSN P systems, in short) are neural computing devices with a bio-inspired design, which imitate communications between two neighbors and changes of potentials on cells. In this work, a novel kind of spiking neural-like P systems is investigated, named spiking neural P systems with weights and delays on synapses (WDSN P systems, for short), which o ers a simple way to choose the applicable rules of neurons. In WDSN P systems, on each synapse, there exists the weights and the delays, where the weights can be positive and negative. The computation power of WDSN P systems is examined. Results demonstrate that both under the generating and accepting mode, only six neurons are required for WDSN P systems to calculate the set of Turing computable numbers. The Subset Sum problem belongs toNP-Complete problems can also be solved using WDSN P systems.","url":"https://doi.org/10.2139/ssrn.4095760","authors":["Yanyan Li","bosheng song","Xiangxiang Zeng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-28T23:54:10Z","doi":"10.2139/ssrn.4095760","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1007/s11694-025-04011-0","name":"Efficient durian sugar content grading via hyperspectral imaging and fast continuous wavelet transform and spiking neural network framework","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11694-025-04011-0","authors":["Xing Qin","Xiaoheng Zhang","Chenxiao Lai","Hanliang Liang","Liyu Li","Chu Qin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-25T09:35:42Z","doi":"10.1007/s11694-025-04011-0","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1016/j.dsp.2026.106165","name":"Underwater acoustic communication signal recognition based on dual-branch spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.dsp.2026.106165","authors":["Yi Fang","Minyan Huang","Yan Gong","Li Ma","Yanhui Tu","Jilong Li","Haihong Feng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-14T06:04:20Z","doi":"10.1016/j.dsp.2026.106165","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1007/978-1-4471-3087-1_3","name":"Rapid Neural Synchronization: From Spiking Cells to Synfire Webs","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4471-3087-1_3","authors":["Andreas V. M. Herz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-12-02T17:56:49Z","doi":"10.1007/978-1-4471-3087-1_3","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1007/978-981-95-3643-6_10","name":"Spiking Neural Network Based on Bidirectional Variational Anomaly Detection for Knowledge Tracing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-95-3643-6_10","authors":["Jinru Hu","Mingkun Chen","Yige Zhu","Jianrui Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-18T18:28:18Z","doi":"10.1007/978-981-95-3643-6_10","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1109/ijcnn60899.2024.10650272","name":"Stock Price Manipulation Detection using Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn60899.2024.10650272","authors":["Ammar Belatreche","Obiye Ada-Ibrama","Baqar Rizvi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T17:35:05Z","doi":"10.1109/ijcnn60899.2024.10650272","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1162/neco_a_00587","name":"Toward Unified Hybrid Simulation Techniques for Spiking Neural Networks","source":"crossref","abstract":"In the field of neural network simulation techniques, the common conception is that spiking neural network simulators can be divided in two categories: time-step-based and event-driven methods. In this letter, we look at state-of-the art simulation techniques in both categories and show that a clear distinction between both methods is increasingly difficult to define. In an attempt to improve the weak points of each simulation method, ideas of the alternative method are, sometimes unknowingly, incorporated in the simulation engine. Clearly the ideal simulation method is a mix of both methods. We formulate the key properties of such an efficient and generally applicable hybrid approach.","url":"https://doi.org/10.1162/neco_a_00587","authors":["Michiel D'Haene","Michiel Hermans","Benjamin Schrauwen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-03-31T22:39:14Z","doi":"10.1162/neco_a_00587","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1049/cp:19991156","name":"Clustering with spiking neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1049/cp:19991156","authors":["I. Opher"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-11-14T15:27:57Z","doi":"10.1049/cp:19991156","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.14264/uql.2018.664","name":"Inspired by nature: timescale-free and grid-free event-based computing with spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.14264/uql.2018.664","authors":["Ting Ting Gibson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-10-07T23:03:32Z","doi":"10.14264/uql.2018.664","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1109/sice.2002.1195245","name":"Spiking neural oscillators","source":"crossref","abstract":"","url":"https://doi.org/10.1109/sice.2002.1195245","authors":["Y. Kuroe","T. Mori"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-06-26T15:35:00Z","doi":"10.1109/sice.2002.1195245","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1007/s11571-026-10487-3","name":"CrossModal-associated-SNN: multi-channel spiking neural networks with clustering and associative learning","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-026-10487-3","authors":["Lingfei Mo","Xin Liu","Mengting Tang"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s11571-026-10487-3","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1109/ijcnn.2018.8489438","name":"Half-precision Floating Point on Spiking Neural Networks Simulations in FPGA","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2018.8489438","authors":["Carolina Zambelli","Joao Ranhel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-10-19T22:25:09Z","doi":"10.1109/ijcnn.2018.8489438","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1007/978-3-031-72341-4_1","name":"A Multiscale Resonant Spiking Neural Network for Music Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-72341-4_1","authors":["Yuguo Liu","Wenyu Chen","Hanwen Liu","Yun Zhang","Liwei Huang","Hong Qu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-16T13:02:55Z","doi":"10.1007/978-3-031-72341-4_1","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.33425/3066-1226.1202","name":"Analyzing The Efficiency of Spiking Neural Networks in Real -Time Edge Computing Applications","source":"crossref","abstract":"This study investigates the efficiency of Spiking Neural Networks (SNNs) compared to traditional neural network architectures—Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Fully Connected Neural Networks (FCNNs)—in real-time edge computing applications. Through experimental evaluation, we examine key performance metrics including latency, energy consumption, accuracy, and computational complexity. Our results indicate that SNNs exhibit superior performance in terms of latency and energy efficiency, with an average latency of 15 milliseconds and energy consumption of 2.5 millijoules, significantly outperforming CNNs, RNNs, and FCNNs. While SNNs show slightly lower accuracy (85%) compared to CNNs (90%), they require fewer computational resources, with a total of 1.2 × 10^9 floating-point operations (FLOPs), making them particularly suitable for power-constrained edge devices. This study highlights the potential of SNNs to address the stringent requirements of real-time edge computing while offering insights into the trade-offs between efficiency and accuracy.","url":"https://doi.org/10.33425/3066-1226.1202","authors":["Sowmya Ragipani","Muneeb Bushra","Shravani Yerraginnela"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-06T05:46:22Z","doi":"10.33425/3066-1226.1202","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1109/icassp55912.2026.11464621","name":"Spiking Attention Network: A Hybrid Neuromorphic Approach to Underwater Acoustic Localization and Zero-Shot Adaptation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icassp55912.2026.11464621","authors":["Quoc Thinh Vo","David K. Han"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-21T21:24:02Z","doi":"10.1109/icassp55912.2026.11464621","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.36227/techrxiv.171822392.24893565/v1","name":"Relational and Analogical Reasoning with Spiking Neural Networks","source":"crossref","abstract":"Raven's Progressive Matrices (RPMs) have been widely used for measuring abstract reasoning and intelligence in humans. However for artificial learning systems, abstract reasoning remains a challenging problem. This paper investigates the potential of biologically inspired spiking neural networks in addressing this challenge. We focus on unsupervised learning since in most domains where human-competitive conceptual learning is important, unlabelled data is plentiful and the autonomous discovery and understanding of underlying patterns without explicit guidance is paramount. Our experiments show that the overall accuracy of our unsupervised networks significantly outperform some supervised methods. Our results also demonstrate that, unlike their non-spiking counterparts, spiking neural networks are able to extract and encode relational features without any explicit instruction, do not rely on labelled training data, and are able to simulate the human ability of navigating and deciphering complex data landscapes. Our results exhibit state-of-the-art performance for unsupervised learning on the RAVEN (67.0%) and I-RAVEN (40.3%) datasets, indicating that that spiking neural networks are well suited to unsupervised conceptual learning.","url":"https://doi.org/10.36227/techrxiv.171822392.24893565/v1","authors":["Rollin Omari","R I Mckay","Tom Gedeon","Kerry Taylor"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-12T16:25:30Z","doi":"10.36227/techrxiv.171822392.24893565/v1","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1007/s11063-014-9378-1","name":"Asynchronous Spiking Neural P Systems with Anti-Spikes","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11063-014-9378-1","authors":["Tao Song","Xiangrong Liu","Xiangxiang Zeng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-08-18T11:16:38Z","doi":"10.1007/s11063-014-9378-1","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1007/978-3-030-86383-8_20","name":"End-to-End Spiking Neural Network for Speech Recognition Using Resonating Input Neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-86383-8_20","authors":["Daniel Auge","Julian Hille","Felix Kreutz","Etienne Mueller","Alois Knoll"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-10T08:02:49Z","doi":"10.1007/978-3-030-86383-8_20","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1080/0954898x.2025.2475070","name":"Improved bounding box segmentation technique for crowd anomaly detection with optimal trained convolutional neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2025.2475070","authors":["Rohini P.S","Sowmy I"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-12T03:37:57Z","doi":"10.1080/0954898x.2025.2475070","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1007/978-3-031-19032-2_20","name":"Astrocytes Enhance Image Representation Encoded in Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-19032-2_20","authors":["Sergey Stasenko","Victor Kazantsev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-18T14:04:21Z","doi":"10.1007/978-3-031-19032-2_20","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1109/flics70075.2026.11621951","name":"Federated Forecasting of Urban Traffic Congestion with Graph Neural Network and Attention-Based Recurrent Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/flics70075.2026.11621951","authors":["Javier Rodrigues","Sukhjit Singh Sehra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-29T19:12:32Z","doi":"10.1109/flics70075.2026.11621951","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.1016/j.neucom.2026.134134","name":"LENS-Net: Low-energy spiking neural network for remote sensing saliency","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2026.134134","authors":["Longlong Zhai","Marcin Pietroń","Roberto Corizzo","Zhaoru Guo","Yongke Li","Chong Peng","Cui Zhang","Shaochen Jiang","Panpan Zheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-03T08:12:33Z","doi":"10.1016/j.neucom.2026.134134","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:24.552Z"},{"id":"doi:10.2139/ssrn.6072494","name":"Physics-Informed Neural Network Neural Network Modeling and Optimization of Fin-Embedded Heat Sink Using NVIDIA PhysicsNeMo","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.6072494","authors":["Edward Oliver Teng","Chung-Gang Li","Heng-Chuan Kan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-26T16:23:09Z","doi":"10.2139/ssrn.6072494","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.209Z"},{"id":"doi:10.1007/978-3-032-02489-3_26","name":"Neuromorphic Spiking Neural Network Based Classification of COVID-19 Spike Sequences","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-02489-3_26","authors":["Taslim Murad","Prakash Chourasia","Sarwan Ali","Avais Jan","Murray Patterson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-31T12:17:34Z","doi":"10.1007/978-3-032-02489-3_26","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.209Z"},{"id":"doi:10.1007/978-3-319-18164-6_16","name":"A Feasibility Study of Using the NeuCube Spiking Neural Network Architecture for Modelling Alzheimer’s Disease EEG Data","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-18164-6_16","authors":["Elisa Capecci","Francesco Carlo Morabito","Maurizio Campolo","Nadia Mammone","Domenico Labate","Nikola Kasabov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-06-05T08:55:38Z","doi":"10.1007/978-3-319-18164-6_16","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1007/s00422-026-01051-7","name":"Detection of spiking motifs of arbitrary length in neural activity using bounded synaptic delays.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s00422-026-01051-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s00422-026-01051-7","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.465Z"},{"id":"doi:10.3389/fninf.2026.1854811","name":"The role of inhibition in modeling decision making with spiking neural networks.","source":"europepmc","abstract":"Decision making (DM) requires coordination of elementary information processes subserved by a distributed network of brain areas. Computational models help to understand these processes, but most of the existing models focus on simulating only one of the many parallel operations. An existing spiking neural network (SNN) model attempts to simulate DM holistically, however it does not take advantage of the significant role of inhibition at the neural level as a possible mechanism underlying DM. To address this limitation, we propose to examine the impact of neural inhibition on decision strategy selection in value-based DM using the mentioned model. In this study we outline the methodology and perform successful in-silico validation of the inhibition hypothesis with the SNN model of DM. To perform the simulation, we use a well-studied multi-attribute choice task and we validate simulation results against human behavioral data. The inhibition model achieved approximately 17% lower mean prediction error than the no-inhibition model (0.55 vs. 0.67) when evaluated on held-out, compensatory-condition data not used for fitting (Wilcoxon signed-rank test, p = 0.009, r = 0.55), with no significant difference observed in the condition used for fitting. These findings indicate that the advantage conferred by inhibition is not attributable to model complexity alone, and support neural inhibition as a plausible, biologically grounded mechanism for adaptive, context-sensitive decision strategy selection.","url":"https://doi.org/10.3389/fninf.2026.1854811","authors":["Bartłomiej Król-Józaga","Peter Duggins","Anna Broniec-Wójcik","Szymon Wichary"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fninf.2026.1854811","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.465Z"},{"id":"doi:10.3390/s26154877","name":"SAD-SNN: Spatial-Activation Distillation for High-Performance Spiking Neural Networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s26154877","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/s26154877","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.465Z"},{"id":"doi:10.1162/neco.a.1568","name":"Twin Network Augmentation: A Novel Training Strategy for Improved Spiking Neural Networks and Weight Quantization.","source":"europepmc","abstract":"","url":"https://doi.org/10.1162/neco.a.1568","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1162/neco.a.1568","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.465Z"},{"id":"doi:10.1142/s0129065727500092","name":"A Fair Energy Comparison of Spiking and Artificial Neural Networks on a General-Purpose Microcontroller.","source":"europepmc","abstract":"","url":"https://doi.org/10.1142/s0129065727500092","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1142/s0129065727500092","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.465Z"},{"id":"doi:10.1371/journal.pcbi.1014577","name":"Combining sampling and attractor dynamics in spiking models of head direction systems.","source":"europepmc","abstract":"Neural populations can maintain stable representations of navigation-related variables while integrating uncertain sensory signals. Experimental evidence showed that the precision of head-direction (HD) representations in flies and mice depends on the reliability of sensory cues, highlighting the influence of input uncertainty in attractor-based neural circuits. How do neural dynamics maintain stability while computing under uncertainty? Here, we propose a spiking neural network that unifies two principles - stability through attraction and uncertainty through fluctuation - and reinterpret the HD circuit as an uncertainty-aware integrator rather than a deterministic compass. Specifically, the network uses sampling-based probabilistic inference, where a neural population represents input uncertainty by rapidly fluctuating among likely hypotheses about the world while preserving a stable representation of head direction along an attractor manifold. This formulation suggests why a classical HD \"bump\" becomes less precise, namely due to rapid fluctuations, reflecting the uncertainty in angular velocity inputs. Our implementation yields experimentally testable predictions: correlated subthreshold voltage fluctuations, multi-timescale nonlinear interaction patterns, and characteristic statistics of bump movement. By combining probabilistic inference with attractor dynamics within one single circuit, our framework suggests how neural populations across species can represent an estimate and its uncertainty through fluctuations while maintaining stability, which could be a general principle for uncertainty-aware computation in noisy biological systems.","url":"https://doi.org/10.1371/journal.pcbi.1014577","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pcbi.1014577","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.465Z"},{"id":"doi:10.1371/journal.pcbi.1014432","name":"Spiking neurons as predictive controllers of linear systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pcbi.1014432","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pcbi.1014432","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:31.149Z"},{"id":"doi:10.3390/biomimetics11070462","name":"Sparse Coding and Temporal Pattern Learning Co-Mediated by Dual Spike-Timing-Dependent Plasticity in a Multilayer Excitatory-Inhibitory Spiking Network.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics11070462","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/biomimetics11070462","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.465Z"},{"id":"doi:10.3390/e28070784","name":"Entropy, Inhibition and Memory in Balanced Spiking Reservoirs.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/e28070784","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/e28070784","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1016/j.neunet.2026.109253","name":"MPLIF: Multi-parametric leaky integrate-and-fire neuron for spiking neural networks.","source":"europepmc","abstract":"Spiking Neural Networks (SNNs) have garnered significant attention due to their ability to process temporal information efficiently with low power consumption and high biological plausibility. In prevailing SNNs, spiking neuron models play a crucial role and have led to extensive research on variants of neuron models. Despite significant performance and stability improvements achieved by these spiking neuron variants, they typically require task-specific hyperparameter tuning and additional architectural complexity. This reliance often leads to reduced generalization, unstable convergence, and limited applicability in edge devices constrained by energy and memory budgets. To enhance the self-adaptive capability of spiking neurons while preserving the brain-inspired computational characteristics, this study proposes a spiking neuron model, termed Multi-Parametric Leaky Integrate-and-Fire (MPLIF) neuron. The proposed spiking neuron improves the adaptability and generalization of SNNs by utilizing novel self-adaptive mechanisms across all neurodynamic computation processes. Extensive experiments are conducted on six benchmark datasets, including CIFAR-10, CIFAR-100, Caltech101, DVS128-Gesture, CIFAR10-DVS, and N-Caltech101, using Spiking ResNet-18 and Spiking VGG-11 backbones. Under identical training settings, MPLIF-based SNNs consistently outperform LIF and advanced variants, achieving up to 2.1%-4.3% accuracy improvement on static datasets and 1.6%-3.8% improvement on neuromorphic datasets. The source code is available at: https://github.com/JeffRody/MPLIF.","url":"https://doi.org/10.1016/j.neunet.2026.109253","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.109253","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1002/advs.77082","name":"Neuromorphic Optical Tracking and Imaging of Randomly Moving Targets Through Dynamic Dense Scattering Media.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.77082","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.77082","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1063/5.0338509","name":"General aspects of internal noise in spiking neural networks.","source":"europepmc","abstract":"This study examines the impact of additive and multiplicative noise on both a single leaky integrate-and-fire neuron and a trained spiking neural network (SNN). Noise was introduced at different stages of neural processing, including the input current, membrane potential, and output spike generation. The results show that multiplicative noise applied to the membrane potential has the most detrimental effect on network performance, leading to significant degradation in accuracy. This is primarily due to its tendency to suppress membrane potentials toward large negative values, effectively silencing neuronal activity. To address this issue, input pre-filtering strategies were evaluated, with a sigmoid-based filter demonstrating the best performance by shifting inputs to a strictly positive range. Under these conditions, additive noise in the input current becomes the dominant source of performance degradation, while other noise configurations reduce accuracy by no more than 1%, even at high noise intensity. Additionally, the study compares the effects of common and uncommon noise across neuron populations in the hidden layer, revealing that SNNs exhibit greater robustness to common noise. Overall, the findings identify the most critical noise mechanisms affecting SNNs and provide practical approaches for improving their robustness.","url":"https://doi.org/10.1063/5.0338509","authors":["I. D. Kolesnikov","D. A. Maksimov","V. M. Moskvitin","N. Semenova"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1063/5.0338509","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1111/ejn.70596","name":"Learning Dynamics in Biophysical Spiking Network Models Are Shaped by KCC2/NKCC1 Cotransporter Stoichiometry.","source":"europepmc","abstract":"","url":"https://doi.org/10.1111/ejn.70596","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1111/ejn.70596","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1016/j.saa.2026.128276","name":"Quantitative analysis of Raman data of pesticide from real sample based on spiking neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.saa.2026.128276","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.saa.2026.128276","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1109/tip.2026.3726411","name":"Efficient High-Frequency Event-Based Optical Flow with Temporal Iterative Refinement and Spiking Neural Networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tip.2026.3726411","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1109/tip.2026.3726411","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1371/journal.pone.0354021","name":"A genetic algorithm for self-supervised models of oscillatory neurodynamics.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pone.0354021","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pone.0354021","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1016/j.neunet.2026.109338","name":"Enhancing spiking transformers with temporal feedback coding and global-local dynamic neurons.","source":"europepmc","abstract":"Spiking Neural Networks (SNNs) have emerged as energy-efficient, biologically more plausible alternatives to Artificial Neural Networks (ANNs), and their recent integration with Transformer architectures has demonstrated impressive performance on vision tasks. However, most Transformer-based SNNs rely on direct coding and Leaky Integrate-and-Fire (LIF) neurons, which leads to spike pattern collapse and insufficient temporal modeling capacity, respectively. To overcome these limitations, we propose a complementary approach with two new components. First, we introduce a Temporal Feedback Coding (TFC) scheme that leverages feedback at the encoding stage to diversify spike patterns. Second, we design a Global-Local Dynamic LIF (GLD-LIF) neuron that enhances cross-step dependency modeling by integrating local aggregation and global initialization. Extensive experiments on three Transformer-based SNN backbones and five datasets across various time steps demonstrate consistent improvements. Our method achieves accuracy gains of up to 3.64% on N-Caltech101 and 1.02% on ImageNet-1K with an increase of 1.7% parameters and 5.01% additional energy consumption. Comprehensive analyses of spike pattern statistics, attention heatmaps, shuffle-time tests and corruption robustness evaluations further verify the effectiveness and broad compatibility of our approach.","url":"https://doi.org/10.1016/j.neunet.2026.109338","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.109338","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1109/jbhi.2025.3589267","name":"FE-SpikeFormer: A Camera-Based Facial Expression Recognition Method for Hospital Health Monitoring.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/jbhi.2025.3589267","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1109/jbhi.2025.3589267","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.7554/elife.89629","name":"Active dendrites enable robust spiking computations despite timing jitter.","source":"europepmc","abstract":"","url":"https://doi.org/10.7554/elife.89629","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.7554/elife.89629","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1016/j.neunet.2026.109045","name":"Biologically inspired spiking diffusion model with adaptive lateral selection mechanism.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.109045","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.109045","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1016/j.neunet.2026.109391","name":"Brain-VQA: Human brain visual pathway inspired visual question answering for enhanced multi-modal cognition and reasoning.","source":"europepmc","abstract":"Visual Question Answering (VQA) aims to assess a model's ability to reason over visual content in response to natural language questions. Despite rapid progress driven by large-scale pretrained vision-language models, it remains unclear whether existing VQA systems truly perform multi-modal cognition and reasoning, or primarily rely on implicit correlations learned through end-to-end answer prediction. In particular, most prior approaches offer limited insight into how visual perception, textual understanding, and intermediate reasoning processes are formed and coordinated, which becomes especially problematic for compositional and multi-step reasoning scenarios. In this work, we propose Brain-VQA, a brain-inspired VQA framework that explicitly models multi-modal perception, cognition, and reasoning following the functional organization of the human visual pathway. Brain-VQA simulates early visual cortical processing using spiking neural networks (SNNs) to produce sparse, event-driven visual representations, constructs structured scene representations through a ventral-stream pathway, and performs query-guided, multi-step visual observation via a dorsal-stream pathway. These components enable interpretable, step-wise visual-linguistic reasoning in a mechanistic and white-box manner, rather than implicit end-to-end fusion. Extensive experiments on CLEVR, GQA, and VQAv2.0demonstrate that Brain-VQA achieves consistently competitive or superior performance with a compact model size. Further analyses show that Brain-VQA exhibits improved generalization and partially consistent dynamics with biological visual reasoning, suggesting that its performance gains stem from explicitly structured multi-modal reasoning processes rather than purely implicit representation learning. Our code is available at https://anonymous.4open.science/r/Brain-VQA.","url":"https://doi.org/10.1016/j.neunet.2026.109391","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.109391","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1039/d6nr01710j","name":"Programmable optoelectronic memristors for energy-efficient adaptive binarized spiking neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d6nr01710j","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d6nr01710j","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1371/journal.pbio.3003846","name":"It's not just the phase: Frequency-dependent tuning of neuronal firing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pbio.3003846","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pbio.3003846","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1016/j.neunet.2026.109127","name":"Lightweight spiking transformer towards neurodynamic integration framework.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.109127","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.109127","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1038/s41598-026-54153-4","name":"Performance evaluation of AkidaNet converted to spiking domain for the classification of weeds in cotton fields.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-54153-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-54153-4","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1016/j.neunet.2026.109071","name":"CogniSNN: Enabling neuron-expandability, pathway-reusability, and dynamic-configurability in spiking neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.109071","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.109071","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1038/s41598-026-61058-9","name":"Community-aware sparse topology design for efficient spiking neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-61058-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-61058-9","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1162/neco.a.1522","name":"Graphon Signal Processing for Spiking and Biological Neural Networks.","source":"europepmc","abstract":"Abstract Graph signal processing (GSP) extends classical signal processing to signals defined on graphs, enabling filtering, spectral analysis, and sampling of data generated by networks of various kinds. Graphon signal processing (GnSP) develops this framework further by employing the theory of graphons. Graphons are measurable functions on the unit square that represent graphs and limits of convergent graph sequences. The use of graphons provides stability of GSP methods to stochastic variability in network data and improves computational efficiency for very large networks. We use GnSP to address the stimulus identification problem (SIP) in computational and biological neural networks. The SIP is an inverse problem that aims to infer the unknown stimulus sfrom the observed network output f. We first validate the approach in spiking neural network simulations and then analyze calcium imaging recordings. Graphon-based spectral projections yield trial-invariant, low-dimensional embeddings that improve stimulus classification over principal component analysis and discrete GSP baselines. The embeddings remain stable under variations in network stochasticity, providing robustness to different network sizes and noise levels. To the best of our knowledge, this is the first application of GnSP to biological neural networks, opening new avenues for graphon-based analysis in neuroscience.","url":"https://doi.org/10.1162/neco.a.1522","authors":["Takuma Sumi","Georgi S. Medvedev"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1162/neco.a.1522","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1016/j.neunet.2026.109306","name":"DSN : Energy-efficient EMG signal classification method enabling real-time monitoring for edge healthcare.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.109306","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.109306","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.3389/fnsys.2026.1788937","name":"Exploring the spiking neural autoencoder: from hyperexcitability to noise-driven compensation.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnsys.2026.1788937","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnsys.2026.1788937","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1063/5.0310258","name":"Membrane-potential-dependent plasticity learning for theta-neuron network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1063/5.0310258","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1063/5.0310258","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.3390/brainsci16060592","name":"Self-Rectifying Integrate-and-Fire Neuron and Collaborative Trim Training Framework for SNN-Based EEG Motor Imagery Classification.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/brainsci16060592","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/brainsci16060592","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1016/j.neunet.2026.108978","name":"Randomized forward mode gradient for spiking neural networks in scientific machine learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.108978","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.108978","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1109/tpami.2026.3698087","name":"DBHN-Net: Dual-Branch Hybrid Neural Network for Low-Complexity Monaural Speech Enhancement.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tpami.2026.3698087","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1109/tpami.2026.3698087","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1142/s0129065726500292","name":"Local-Contextual Feature Fusion Network Based on Nonlinear Spiking Neural Model for Semantic Segmentation of Remote Sensing Images.","source":"europepmc","abstract":"","url":"https://doi.org/10.1142/s0129065726500292","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1142/s0129065726500292","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1088/1741-2552/ae8640","name":"A computational framework for fitting biophysical basal-ganglia network models, applied to Parkinsonian beta oscillations.","source":"europepmc","abstract":"","url":"https://doi.org/10.1088/1741-2552/ae8640","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1088/1741-2552/ae8640","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1109/tnnls.2026.3715568","name":"Spike-EIFNet: Lightweight Spike-Driven Event-Image Fusion Network for Accurate and Efficient Semantic Segmentation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tnnls.2026.3715568","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1109/tnnls.2026.3715568","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1016/j.neunet.2026.109241","name":"SD&lt;sup&gt;2&lt;/sup&gt;-SNN: Self-distillation and structural decomposition framework for SNNs in continual learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.109241","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.109241","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1038/s41598-026-49954-6","name":"Forecasting Nasdaq stock exchange time series using an improved recurrent spiking Pi-Sigma artificial neural network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-49954-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-49954-6","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1088/1741-2552/ae5b27","name":"Physiologically inspired modeling of cortical dynamics through spiking neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1088/1741-2552/ae5b27","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1088/1741-2552/ae5b27","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1016/j.neunet.2026.109022","name":"Spike-hammer: An efficient spike-driven hybrid architecture for multi-modal emotion recognition with physiological signals.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.109022","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.109022","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1007/s10162-026-01060-0","name":"Computational Model for Synthesizing Auditory Brainstem Responses to Assess Neuronal Alterations in Aging and Autistic Animal Models.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s10162-026-01060-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s10162-026-01060-0","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1002/epi.70400","name":"Detecting high-frequency oscillations in real time during epilepsy surgery with neuromorphic hardware validated to predict postoperative seizure outcome.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/epi.70400","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/epi.70400","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1002/smll.73955","name":"Low-Latency Visuotactile Neuron Using Self-Oscillating Memristor.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.73955","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.73955","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1007/s00422-026-01039-3","name":"Dynamical mechanisms for coordinating long-term working memory based on the precision of spike-timing in cortical neurons.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s00422-026-01039-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s00422-026-01039-3","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1016/j.biosystems.2026.105868","name":"Spatiotemporal bursting in simulated cultures of cortical neurons.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.biosystems.2026.105868","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.biosystems.2026.105868","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1016/j.neunet.2026.108844","name":"Spiking neural networks for video analysis: An in-depth review of models and architectures.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.108844","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.108844","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1016/j.neunet.2026.108830","name":"Recurrent spiking neural networks with bimodal neuronal time scales for learning performance enhancement.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.108830","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.108830","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1177/10849785261431191","name":"Brain Tumor Classification and Severity Identification Using Deep Convolutional Spiking U-Net Lyrebird Neural Network and Alpha Piecewise Linear-Fuzzy.","source":"europepmc","abstract":"","url":"https://doi.org/10.1177/10849785261431191","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1177/10849785261431191","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1016/j.neunet.2026.109325","name":"Modeling multiple classical conditioning mechanisms in a Memristor-Based learning circuit.","source":"europepmc","abstract":"To achieve circuit-level modeling of multiple complex associative learning mechanisms in brain-inspired systems, this paper proposes an analog neural circuit based on threshold memristors, capable of emulating multiple classical conditioning phenomena in a biologically inspired manner. Specifically, the circuit incorporates multimodal sensory stimuli, including gustatory, visual, and auditory signals, to construct biologically inspired associative pathways. Through dynamical synaptic regulation by memristors across multiple neural pathways, the proposed rate-based analog circuit successfully reproduces several classical conditioning processes, such as acquisition, second-order conditioning, overshadowing, blocking, extinction, and reacquisition. It is noted that the circuit adopts a rate-based analog design paradigm, in which neuronal activation is governed by threshold comparison of weighted voltage summations, rather than spike-timing dynamics as in biologically accurate spiking neural networks. Moreover, the second-order conditioning pathway and the synaptic competition underlying overshadowing and blocking are validated through PSPICE simulations, demonstrating the synaptic plasticity of threshold memristors in modeling higher-order associative learning. Unlike prior single-mechanism approaches, this circuit realizes multiple associative processes within a unified memristive framework, extending memristor use in brain-inspired computing and cognitive hardware modeling.","url":"https://doi.org/10.1016/j.neunet.2026.109325","authors":["Yueqi Song","Suo Gao","Herbert Ho-Ching Iu","Santo Banerjee","Yinghong Cao","Junxin Chen","Yushu Zhang","Jun Mou"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.109325","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.3389/fncom.2026.1777273","name":"Dopamine modulation of spike-timing-dependent plasticity for spatio-temporal spike pattern detection in single neurons.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2026.1777273","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fncom.2026.1777273","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1016/j.neunet.2026.108873","name":"Multi-scale chunked residual encoding and temporal stochastic interpolation padding in SNNs for enhanced speech classification.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.108873","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.108873","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1103/rklz-gkqn","name":"Modularity-dependent storage of dynamic spiking patterns: Bridging micro- and mesoscopic representations.","source":"europepmc","abstract":"","url":"https://doi.org/10.1103/rklz-gkqn","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1103/rklz-gkqn","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3390/s26092910","name":"HAPQ: A Hardware-Aware Pruning and Quantization Pipeline for Event-Based SNN Detection.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s26092910","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/s26092910","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1007/s11571-026-10496-2","name":"Linguistics and human brain: a perspective of computational neuroscience.","source":"europepmc","abstract":"Elucidating the language-brain relationship requires bridging the methodological gap between linguistics' abstract theoretical frameworks and neuroscience's empirical neural data. As an interdisciplinary cornerstone, computational neuroscience formalizes language's hierarchical and dynamic structures into testable neural representation models through modeling, simulation, and data analysis, enabling computational dialogue between linguistic hypotheses and neural mechanisms. Recent advances in deep learning, particularly large language models (LLMs), have further advanced this inquiry: their high-dimensional representational spaces provide a new scale for probing the neural basis of linguistic processing, the model-brain alignment framework offers a principled approach to evaluating the biological plausibility of language-related theories, provided that representational correspondence is interpreted together with behavioral, temporal, causal, and biological constraints. This review synthesizes interdisciplinary progress from a computational neuroscience perspective. First, it outlines the core connotations of major linguistic frameworks (generative grammar, functional linguistics, and cognitive linguistics), their cross-cultural and evolutionary characteristics, and key challenges for neural alignment, including limited quantitative mechanisms, poor accessibility of abstract constructs to neural measures, and insufficient treatment of dynamics and plasticity. Second, it introduces the methodological foundations of linguistics-neuroscience dialogue, focusing on four technical pillars: neural activity measurement (e.g., fMRI, EEG, MEG, fNIRS, ECoG, SEEG), linguistic numerical representation, the evolution of language models from statistical approaches to LLMs, and neural coding frameworks that link model representations to brain signals, illustrated with a model-brain alignment case study. Third, it summarizes major findings, ranging from early computational insights into predictability and structural processing to recent LLM-driven progress in cross-modal interaction, inter-brain coupling, hierarchical computation, learning strategy sensitivity, and language plasticity. Finally, the review discusses current limitations-including functional alignment without structural homology, constraints on real-time validation, biased research coverage, and narrow evaluation metrics-and proposes future directions, such as exploring whether spiking neural network-based language models can improve biological plausibility in settings requiring temporally precise and event-driven neural modeling, developing cognitive-level alignment frameworks integrating memory, causality, and metacognition, and extending clinical applications. In summary, this work aims to advance a comprehensive, mechanistic understanding of the language-brain relationship and promote computational neuroscience as a generative theoretical framework for testable neuro-computational accounts of language.","url":"https://doi.org/10.1007/s11571-026-10496-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s11571-026-10496-2","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1142/s0129065726500176","name":"Achieving Optimal Accuracy and Robustness Through Tight Excitatory-Inhibitory Balance in Shallow Spiking Recurrent Neural Network.","source":"europepmc","abstract":"Traditional deep neural networks exhibit high computational complexity during training and lack biological interpretability due to their reliance on backpropagation-based methods. Spiking Recurrent Neural Network (SRNN) performs well in processing spatio-temporal information by using discrete spike events. It attracts increasing attention in neural computing due to its biological plausibility and hardware implementation. To improve the performance of SRNN, we propose an excitation-inhibition balanced shallow SRNN (EI-SRNN), which is inspired by the balance of excitation and inhibition in the brain, by optimizing the input currents of reservoir neurons to achieve a tight balanced state. The proposed EI-SRNN achieves optimal accuracy while maintaining low computational complexity, debunking the conventional trade-off between accuracy and robustness. We analyze the neural encoding ability and information memory capacity of the EI-SRNN and compare the performance of the model under different degrees of excitation and inhibition. Our experiments demonstrate that EI-SRNN can have higher neural coding capacity and memory capacity under tight balanced excitatory and inhibitory balanced states, so it can achieve better accuracy while possessing stronger robustness. Furthermore, when the reservoir is dominated by excitatory influences, performance declines faster than when the reservoir is dominated by inhibitory influences.","url":"https://doi.org/10.1142/s0129065726500176","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1142/s0129065726500176","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1097/ms9.0000000000005088","name":"Spiking neural networks for real-time mapping of EBV-infected B cells in neuroinflammatory lesions.","source":"europepmc","abstract":"","url":"https://doi.org/10.1097/ms9.0000000000005088","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1097/ms9.0000000000005088","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1016/j.neuron.2025.12.018","name":"Neuronal spiking in the mammalian forebrain is dominated by a heterogeneous ground state.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neuron.2025.12.018","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neuron.2025.12.018","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1021/acsami.5c25164","name":"A Gate-Tunable Thermal Persistent Photocurrent Device for In-Sensor Spiking Neural Networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c25164","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.5c25164","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1038/s41467-026-74460-8","name":"Spike-based alignment learning solves the weight transport problem.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-74460-8","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-74460-8","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1016/j.neunet.2026.108809","name":"Fast agreement-driven device-calibrated local learning paradigms for spiking neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.108809","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.108809","addedAt":"2026-09-01T01:48:24.552Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.3390/biomimetics11060374","name":"Systematic Evaluation of Biologically Inspired Motion Detection Models: From LGMD and EMD to Hybrid Spiking Neural Networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics11060374","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/biomimetics11060374","addedAt":"2026-09-01T01:48:24.553Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1021/acs.jpclett.6c01243","name":"Neuromorphic Behaviors with Nanofluidic Memristor-Coupled Hodgkin-Huxley Neurons.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.jpclett.6c01243","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acs.jpclett.6c01243","addedAt":"2026-09-01T01:48:24.553Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.bios.2026.118951","name":"A bioinspired photoelectrochemical synapse for neurotransmitter-mediated in-sensor computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.bios.2026.118951","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.bios.2026.118951","addedAt":"2026-09-01T01:48:24.553Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.3389/fnins.2026.1780751","name":"Computational modeling of spatiotemporal afterimage visual perception with spiking neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2026.1780751","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnins.2026.1780751","addedAt":"2026-09-01T01:48:24.553Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1109/tnnls.2026.3671461","name":"Spatiotemporal Decoupled Learning for Spiking Neural Networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tnnls.2026.3671461","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1109/tnnls.2026.3671461","addedAt":"2026-09-01T01:48:24.553Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1109/jbhi.2025.3602502","name":"PicoSleepNet: An Ultra Lightweight Sleep Stage Classification by Spike Neural Network Using Single-Channel EEG Signal.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/jbhi.2025.3602502","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1109/jbhi.2025.3602502","addedAt":"2026-09-01T01:48:24.553Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1016/j.neunet.2026.108656","name":"NG-SNN: A neurogenesis-inspired dynamic adaptive framework for efficient spike classification.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.108656","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.108656","addedAt":"2026-09-01T01:48:24.553Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1038/s41598-026-57578-z","name":"LiWO-SRDN-based EV charging coordination for stable smart grid systems using a single-switch high step-up zeta converter.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-57578-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-57578-z","addedAt":"2026-09-01T01:48:24.553Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1007/s11571-025-10384-1","name":"Discrete memristive spiking neural networks: investigating information flow, synchronization, and emergent intelligence.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-025-10384-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s11571-025-10384-1","addedAt":"2026-09-01T01:48:24.553Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/tnnls.2026.3680142","name":"EMM-Det: Energy-Efficient Multidrone Tiny Object Detection by Memory-Enhanced Spiking Neural Networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tnnls.2026.3680142","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1109/tnnls.2026.3680142","addedAt":"2026-09-01T01:48:24.553Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1038/s41467-026-74769-4","name":"Amphibian-inspired neuromorphic dynamic vision systems based on ferroelectric field-effect transistor.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-74769-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-74769-4","addedAt":"2026-09-01T01:48:24.553Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1038/s41467-026-68453-w","name":"Model-agnostic linear-memory online learning in spiking neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-68453-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-68453-w","addedAt":"2026-09-01T01:48:24.553Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1016/j.neunet.2026.108558","name":"Temporal local attention with adaptive decoding: Enhancing spiking neural networks for temporal computing applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.108558","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.108558","addedAt":"2026-09-01T01:48:24.553Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.1109/tnnls.2025.3606849","name":"Channelwise Regional Integrate and Multiple Firing Neuron: Improving the Spatiotemporal Learning of Spiking Neural Networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tnnls.2025.3606849","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1109/tnnls.2025.3606849","addedAt":"2026-09-01T01:48:24.553Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.21203/rs.3.rs-8938092/v1","name":"A Highly Linear Analog-to-Spike Converter","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-8938092/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-8938092/v1","addedAt":"2026-09-01T01:48:24.553Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.03.12.710517","name":"Cortical excitability inversely modulates fMRI connectivity via low-frequency neuronal coupling","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.03.12.710517","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.03.12.710517","addedAt":"2026-09-01T01:48:24.553Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.02.16.706126","name":"An Efficient Computing Theory of Prefrontal Structured Working Memory Representations","source":"preprints","abstract":"A bstract The efficient coding hypothesis presents a compelling success story for theoretical and systems neu-roscience. It marshals a unifying idea, that neural codes can be understood as efficient encodings of natural stimuli, to explain phenomena from across sensory systems, sometimes with exquisite precision. However, similar normative assaults on cognitive representations, such as those in prefrontal or entorhinal cortex, have been less comprehensively successful. We argue that this reflects efficient coding’s focus on encoded variables, overlooking the computations that neural circuits implement. Here, instead, we develop an efficient computing theory that studies optimal implementations of recurrent cognitive computations. We apply this framework to the prefrontal cortex, in particular, to a rich vein of neural recordings: structured working memory tasks, such as recalling a sequence. Despite using near-identical tasks, the literature has reported two distinct coding schemes: one contextual, with neurons active only in a particular sequence, the other compositional, with neurons tuned to a single sequence element. Just as efficient coding links stimuli statistics to optimal representation, our theory relates task structure and statistics to optimal representation. In so doing, we find that compositional and contextual codes can be understood as two extremes of a spectrum of optimal representations, with the correlations amongst sequence elements determining a task’s position on this spectrum. Our theory highlights previously underappreciated discrepancies between measured representations, explaining them via subtle task differences; and allows us to infer the algorithm underlying otherwise ambiguous neural data. In sum, we demonstrate an efficient computing approach that makes normative statements about cognitive representations, and serves as a tool for understanding a swathe of neural data.","url":"https://doi.org/10.64898/2026.02.16.706126","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.02.16.706126","addedAt":"2026-09-01T01:48:24.553Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.21203/rs.3.rs-9271774/v1","name":"Three-photon holographic microscopy for deep precise optogenetics","source":"preprints","abstract":"Abstract Precise manipulation of neurons across cortical layers requires optical approaches that maintain single-cell specificity deep within scattering brain tissue. Two-photon optogenetics provides targeted photostimulation in vivo and has expanded experimental access to defined neuronal populations beyond the limits of single-photon excitation. However, its application remains largely confined to the upper cortical layers (∼250–300 µm) in mice due to scattering. Here we introduce three-photon temporally focused computer-generated holography (3P TF-CGH) for precise optogenetic activation beyond this depth limit. We characterize 3P excitation of multiple excitatory and inhibitory opsins in organotypic slices, demonstrating cubic power dependence, efficient photocurrents and preserved temporal fidelity. We demonstrated that temporally focused holography maintains tight axial confinement in scattering tissue and minimizes superficial out-of-focus excitation under conditions required for deep targeting. In vivo, we combined 3P holographic stimulation at 1700 nm with simultaneous 3P calcium imaging at 1300 nm to achieve reliable neuronal activation across cortical layers down to 800 µm. Photostimulation remained stable across repeated trials without detectable physiological perturbation. By extending cell-resolved optogenetic control well beyond the established depth limits of 2P approaches, 3P holographic optogenetics enables non-invasive, all-optical interrogation of deep cortical circuits.","url":"https://doi.org/10.21203/rs.3.rs-9271774/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-9271774/v1","addedAt":"2026-09-01T01:48:24.553Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.01.27.702083","name":"Attention-like regulation of theta sweeps in the brain’s spatial navigation circuit","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.01.27.702083","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.01.27.702083","addedAt":"2026-09-01T01:48:24.553Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.01.22.701022","name":"Gamma oscillations across recording scales show a preference for saturated long-wavelength (reddish) hues in the primate visual cortex","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.01.22.701022","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.01.22.701022","addedAt":"2026-09-01T01:48:24.553Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.01.09.698719","name":"Cross-individual translation of spontaneous zebrafish brain activity through a shared latent representation","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.01.09.698719","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.01.09.698719","addedAt":"2026-09-01T01:48:24.553Z","updatedAt":"2026-09-01T01:48:25.466Z"},{"id":"doi:10.64898/2026.03.02.709133","name":"Inhibition of cortico-amygdala projections underlies affective bias modification by psilocybin","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.03.02.709133","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.03.02.709133","addedAt":"2026-09-01T01:48:24.553Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.64898/2026.01.23.701239","name":"Opening the black box: a modular approach to spike sorting","source":"preprints","abstract":"","url":"https://doi.org/10.64898/2026.01.23.701239","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.64898/2026.01.23.701239","addedAt":"2026-09-01T01:48:24.553Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1109/micro61859.2024.00084","name":"LoAS: Fully Temporal-Parallel Dataflow for Dual-Sparse Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/micro61859.2024.00084","authors":["Ruokai Yin","Youngeun Kim","Di Wu","Priyadarshini Panda"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-03T13:51:51Z","doi":"10.1109/micro61859.2024.00084","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1080/0954898x.2024.2375391","name":"Optimized multi-head self-attention and gated-dilated convolutional neural network for quantum key distribution and error rate reduction","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2024.2375391","authors":["R J Kavitha","D. Ilakkiaselvan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-17T06:55:34Z","doi":"10.1080/0954898x.2024.2375391","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.3103/s002713492570300x","name":"Probabilistic Spiking Neural Network with Correlation-Based Memristive Synaptic Update","source":"crossref","abstract":"","url":"https://doi.org/10.3103/s002713492570300x","authors":["D. Kunitsyn","A. Sboev","Y. Davydov","D. Vlasov","A. Serenko","R. Rybka"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-01T20:54:50Z","doi":"10.3103/s002713492570300x","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1016/j.neucom.2025.129664","name":"Brain-inspired reward broadcasting: Brain learning mechanism guides learning of spiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2025.129664","authors":["Miao Wang","Gangyi Ding","Yunlin Lei","Yu Zhang","Lanyu Gao","Xu Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-17T11:57:41Z","doi":"10.1016/j.neucom.2025.129664","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/biocas61083.2024.10798361","name":"Adaptive Spiking Neural Network Neuromorphic Hardware for Interfacing Between Emerging Neuron and Synaptic Devices","source":"crossref","abstract":"","url":"https://doi.org/10.1109/biocas61083.2024.10798361","authors":["Min Jee Kim","Jaegwang Im","Keonhee Kim","Yooyeon Jo","Gichang Noh","Eunpyo Park","Dae Kyu Lee","Inho Kim","YeonJoo Jeong","Hyung-Min Lee","Joon Young Kwak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-23T19:10:53Z","doi":"10.1109/biocas61083.2024.10798361","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/iros58592.2024.10802854","name":"Gaining the Sparse Rewards by Exploring Lottery Tickets in Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iros58592.2024.10802854","authors":["Hao Cheng","Jiahang Cao","Erjia Xiao","Mengshu Sun","Renjing Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-25T19:17:39Z","doi":"10.1109/iros58592.2024.10802854","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1007/s13534-024-00403-1","name":"Exploring the potential of spiking neural networks in biomedical applications: advantages, limitations, and future perspectives","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s13534-024-00403-1","authors":["Eunsu Kim","Youngmin Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-20T16:02:02Z","doi":"10.1007/s13534-024-00403-1","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/nice61972.2024.10548306","name":"Quantized Context Based LIF Neurons for Recurrent Spiking Neural Networks in 45nm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nice61972.2024.10548306","authors":["Sai Sukruth Bezugam","Yihao Wu","JaeBum Yoo","Dmitri Strukov","Bongjin Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-11T17:30:32Z","doi":"10.1109/nice61972.2024.10548306","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1109/nano61778.2024.10628612","name":"Spiking Neural Networks with Nonidealities from Memristive Silicon Oxide Devices","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nano61778.2024.10628612","authors":["Viet Cuong Vu","Anthony Kenyon","Dovydas Joksas","Adnan Mehonic","Daniel J. Mannion","Wing H. Ng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-22T17:38:42Z","doi":"10.1109/nano61778.2024.10628612","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1016/j.procs.2024.04.252","name":"Sign Language Recognition using Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.procs.2024.04.252","authors":["Pranav Chaudhari","Alex Vicente-Sola","Amlan Basu","Davide L. Manna","Paul Kirkland","Gaetano Di Caterina"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-31T19:58:30Z","doi":"10.1016/j.procs.2024.04.252","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.20944/preprints202401.0537.v1","name":"Withdrawn: Astrocyte Control Bursting Mode of Spiking Neuron Network with Memristor-Implemented Plasticity","source":"crossref","abstract":"","url":"https://doi.org/10.20944/preprints202401.0537.v1","authors":["Sergey Stasenko","Alexey Mikhaylov","Alexander Fedotov","Vladimir Smirnov","Victor Kazantsev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-08T19:34:47Z","doi":"10.20944/preprints202401.0537.v1","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.3389/fnins.2024.1401690","name":"Paired competing neurons improving STDP supervised local learning in spiking neural networks","source":"crossref","abstract":"Direct training of Spiking Neural Networks (SNNs) on neuromorphic hardware has the potential to significantly reduce the energy consumption of artificial neural network training. SNNs trained with Spike Timing-Dependent Plasticity (STDP) benefit from gradient-free and unsupervised local learning, which can be easily implemented on ultra-low-power neuromorphic hardware. However, classification tasks cannot be performed solely with unsupervised STDP. In this paper, we propose Stabilized Supervised STDP (S2-STDP), a supervised STDP learning rule to train the classification layer of an SNN equipped with unsupervised STDP for feature extraction. S2-STDP integrates error-modulated weight updates that align neuron spikes with desired timestamps derived from the average firing time within the layer. Then, we introduce a training architecture called Paired Competing Neurons (PCN) to further enhance the learning capabilities of our classification layer trained with S2-STDP. PCN associates each class with paired neurons and encourages neuron specialization toward target or non-target samples through intra-class competition. We evaluate our methods on image recognition datasets, including MNIST, Fashion-MNIST, and CIFAR-10. Results show that our methods outperform state-of-the-art supervised STDP learning rules, for comparable architectures and numbers of neurons. Further analysis demonstrates that the use of PCN enhances the performance of S2-STDP, regardless of the hyperparameter set and without introducing any additional hyperparameters.","url":"https://doi.org/10.3389/fnins.2024.1401690","authors":["Gaspard Goupy","Pierre Tirilly","Ioan Marius Bilasco"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-24T05:23:36Z","doi":"10.3389/fnins.2024.1401690","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.2139/ssrn.4789754","name":"Integrating Neural Network Emulators in CAD Environments for Enhanced Neural Architecture Modeling","source":"crossref","abstract":"The study, titled 'Integrating Neural Network Emulators in CAD Environments for Enhanced Neural Architecture Modeling,' represents a effort in the realms of computational design and neural network emulation. This research is centered on the goal of integrating neural network emulators into Computer-Aided Design (CAD) environments.&lt;br&gt;&lt;br&gt;At the heart of this study the objective is to facilitate the simulation, modeling, and refinement of complex neural architectures within a CAD framework. This integration is based to the conceptualization and development of neural networks, offering a level of precision and control in their design process. Embedding neural network emulators within CAD systems, the study seeks to provide a dynamic and interactive environment for the exploration and optimization of diverse neural structures.&lt;br&gt;&lt;br&gt;The study posits that this integration will catalyze discoveries and innovations, particularly in the development of efficient, effective, and versatile neural network architectures. It also recognizes the potential of this amalgamation to make significant contributions across various applications, from automated learning systems to sophisticated problem-solving mechanisms.&lt;br&gt;&lt;br&gt;In essence, this study endeavors to demonstrate the potential of computational design by harnessing the power of neural network emulation within a CAD environment. It explores territories in the interdisciplinary fields of neural networks and computational architecture, poised to make substantial impacts in both domains.","url":"https://doi.org/10.2139/ssrn.4789754","authors":["Dimitrios Sargiotis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-21T16:03:31Z","doi":"10.2139/ssrn.4789754","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/access.2024.3479968","name":"Event-Based Spiking Neural Networks for Object Detection: A Review of Datasets, Architectures, Learning Rules, and Implementation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/access.2024.3479968","authors":["Craig Iaboni","Pramod Abichandani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-14T13:25:51Z","doi":"10.1109/access.2024.3479968","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1201/9781003559115-31","name":"Predicting stock market trends using ANN-spiking neural network via public sentiment and political situation analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003559115-31","authors":["Devadutta Indoria","Mercy Tom","Sameer Yadav","C.A. Sandeep Gupta","Kiran Kumar Varma Kallepalli","Harshal Patil"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-29T10:13:27Z","doi":"10.1201/9781003559115-31","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1137/24m1631274","name":"Pattern Formation in a Spiking Neural-Field of Renewal Neurons","source":"crossref","abstract":"Abstract. Elucidating the neurophysiological mechanisms underlying neural pattern formation remains an outstanding challenge in Computational Neuroscience. In this paper, we address the issue of understanding the emergence of neural patterns by considering a network of renewal neurons, a well-established class of spiking cells. Taking the thermodynamics limit, the network’s dynamics can be accurately represented by a partial differential equation coupled with a nonlocal differential equation. The stationary state of the nonlocal system is determined, and a perturbation analysis is performed to analytically characterize the conditions for the occurrence of Turing instabilities. Considering neural network parameters, such as the synaptic coupling and the external drive, we numerically obtain the bifurcation line that separates the asynchronous regime from the emergence of patterns. Our theoretical findings provide a new and insightful perspective on the emergence of Turing patterns in spiking neural networks. In the long term, our formalism will enable the study of neural patterns while maintaining the connections between microscopic cellular properties, network coupling, and the emergence of Turing instabilities.","url":"https://doi.org/10.1137/24m1631274","authors":["Grégory Dumont","Carmen Oana Tarniceriu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-14T04:00:37Z","doi":"10.1137/24m1631274","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1016/j.ins.2024.120660","name":"Intelligent event-based lip reading word classification with spiking neural networks using spatio-temporal attention features and triplet loss","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.ins.2024.120660","authors":["Qianhui Liu","Meng Ge","Haizhou Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-08T15:18:16Z","doi":"10.1016/j.ins.2024.120660","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1145/3708657.3708675","name":"Network Traffic Prediction Based on Spiking-Inspired Transformer","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3708657.3708675","authors":["Kai Li","Lizhe Liu","Xiaobo Guo","Qifan Guo","Siyang Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-29T11:13:43Z","doi":"10.1145/3708657.3708675","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1609/aaai.v40i24.39109","name":"Spatial-Frequency Spiking Neural Network for Underwater Object Detection","source":"crossref","abstract":"Underwater object detection presents significant challenges due to the unique visual degradations in underwater environments, such as low contrast, poor visibility, and blurry object boundaries. While ANNs have achieved impressive detection accuracy, their high computational cost and power consumption limit their deployment in resource-constrained underwater platforms. In this work, we propose a Spatial-Frequency Spiking Neural Network (SFSNN) that combines the energy-efficient and event-driven nature of Spiking Neural Networks (SNNs) with the discriminative power of spatial-frequency analysis. SFSNN introduces a novel spatial-frequency spiking module that integrates spatial and frequency-domain representations, enhancing edge and texture features crucial for object detection in murky waters. Furthermore, we adapt the YOLOX architecture into a spike-based detector via ANN-to-SNN conversion using signed spiking neurons. Extensive experiments on the RUOD dataset demonstrate that SFSNN achieves superior performance over both SNN- and ANN-based detection models, offering a compelling solution for low-power underwater object detection.","url":"https://doi.org/10.1609/aaai.v40i24.39109","authors":["Long Chen","Wei Miao","Xin Gao","Yunzhi Zhuge","Hongming Xu","Yaxin Li","Qi Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-18T01:15:30Z","doi":"10.1609/aaai.v40i24.39109","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.51483/ijaiml.6.4s.2026.756-763","name":"Spiking Neural Network Learning Algorithms For Neuromorphic Hardware Efficiency","source":"crossref","abstract":"","url":"https://doi.org/10.51483/ijaiml.6.4s.2026.756-763","authors":["Ashish Sharma","Saraswati B","Dr. S Subburam","Dr. V Malsoru","Dr. V. Senthil Kumaran","Sudhakar Polasi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-09T11:09:57Z","doi":"10.51483/ijaiml.6.4s.2026.756-763","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/aicas59952.2024.10595982","name":"Towards Automated FPGA Compilation of Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aicas59952.2024.10595982","authors":["Ayan Shymyrbay","Mohammed E. Fouda","Ahmed Eltawil"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-19T17:30:48Z","doi":"10.1109/aicas59952.2024.10595982","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/asp-dac58780.2024.10473825","name":"MINT: Multiplier-less INTeger Quantization for Energy Efficient Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/asp-dac58780.2024.10473825","authors":["Ruokai Yin","Yuhang Li","Abhishek Moitra","Priyadarshini Panda"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-25T19:06:53Z","doi":"10.1109/asp-dac58780.2024.10473825","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1016/j.neunet.2023.10.020","name":"Reduced-complexity Convolutional Neural Network in the compressed domain","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2023.10.020","authors":["Hamdan Abdellatef","Lina J. Karam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-24T05:43:17Z","doi":"10.1016/j.neunet.2023.10.020","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1016/j.procs.2024.11.017","name":"A Spiking Neural Network Action Decision Method Inspired by Basal Ganglia","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.procs.2024.11.017","authors":["Tianyong Ao","Qiuping Liu","Le Fu","Yi Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-29T20:24:17Z","doi":"10.1016/j.procs.2024.11.017","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1016/j.psep.2024.06.008","name":"Predicting the remaining useful life of rails based on improved deep spiking residual neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.psep.2024.06.008","authors":["Jing He","Zunguang Xiao","Changfan Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-05T10:57:12Z","doi":"10.1016/j.psep.2024.06.008","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/agreta68375.2025.11473996","name":"Classification of Chilli Variations Using a Reservoir Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/agreta68375.2025.11473996","authors":["Muhammad Raihaan Kamarudin","Muhammad Noorazlan Shah Zainudin","Wira Hidayat Mohd Saad","Zul Atfyi Fauzan","Muhammad Irfan Arnoldi","Raihani Mohamed"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-15T19:23:29Z","doi":"10.1109/agreta68375.2025.11473996","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1016/j.mattod.2024.09.016","name":"High-performance in domain matching epitaxial La:HfO2 film memristor for spiking neural network system application","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.mattod.2024.09.016","authors":["Xiaobing Yan","Jiangzhen Niu","Ziliang Fang","Jikang Xu","Changlin Chen","Yufei Zhang","Yong Sun","Liang Tong","Jianan Sun","Saibo Yin","Yiduo Shao","Shiqing Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-15T19:03:16Z","doi":"10.1016/j.mattod.2024.09.016","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1016/j.csi.2025.104126","name":"Deep convolutional spiking neural network and block chain based intrusion detection framework for enhancing privacy and security in cloud computing environment","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.csi.2025.104126","authors":["B. Muthusenthil","K. Devi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-31T23:33:50Z","doi":"10.1016/j.csi.2025.104126","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1007/978-3-031-47508-5_8","name":"An Evaluation of Handwriting Digit Recognition Using Multilayer SAM Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-47508-5_8","authors":["Minoru Motoki","Heitaro Hirooka","Youta Murakami","Ryuji Waseda","Terumitsu Nishimuta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-31T09:16:09Z","doi":"10.1007/978-3-031-47508-5_8","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1109/mwscas60917.2024.10658863","name":"Exploring Noise- Resilient Spiking Neural Encoding using ∑†∑ Neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mwscas60917.2024.10658863","authors":["R. Sreekumar","Faiyaz E. Mullick","Md Golam Morshed","Avik W. Ghosh","Mircea R. Stan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-16T17:34:29Z","doi":"10.1109/mwscas60917.2024.10658863","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1007/978-981-97-9933-6_5","name":"Graph Neural Network for Human Parsing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-9933-6_5","authors":["Weibin Liu","Huaqing Hao","Hui Wang","Zhiyuan Zou","Weiwei Xing"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-03T05:30:41Z","doi":"10.1007/978-981-97-9933-6_5","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.22266/ijies2026.0228.28","name":"DAC-SNN: A Neuromorphic Adaptive Spiking Neural Network for Predictive Quality Assessment in Smart Campus Systems","source":"crossref","abstract":"","url":"https://doi.org/10.22266/ijies2026.0228.28","authors":["Harmayani","Poltak Sihombing","Mahyuddin K. M. Nasution","Marischa Elveny"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-20T01:07:12Z","doi":"10.22266/ijies2026.0228.28","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1364/oe.592163","name":"EEG decoding with attention-augmented photonic spiking neural network based on multi-timescale laser neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1364/oe.592163","authors":["Yanan Han","Qing Bi","Shuiying Xiang","YAHUI ZHANG","Xingxing Guo","Jin Li","Yuechun Shi","Weitao Pan","Yue Hao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-21T07:00:07Z","doi":"10.1364/oe.592163","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:24.596Z"},{"id":"doi:10.1142/s0218126626501896","name":"Enhancing Opinion Mining of Twitter Data With A Deep Convolutional Spiking Neural Network and Balancing Composite Motion Optimization","source":"crossref","abstract":"Social media is the most popular platform for opinion expression. Sentiment analysis is the process of acquiring information about things, events and their characteristics out of people’s views, assessments and feelings. Opinion mining is an alternative term for sentiment analysis. In this paper, Enhancing Opinion Mining of Twitter Data with a Deep Convolutional Spiking Neural Network and Balancing Composite Motion Optimization (OMTD-DCSNN-BCMO) is proposed. Initially, the Twitter data are obtained from the Stanford Sentiment Treebank (SST-2) dataset. Then, the data is fed to the preprocessing. The pre-processing output is provided to extract the Radiomic features depending on the Residual Exemplars Local Binary Pattern (RELBP). The extracted output is provided to the feature selection for choosing ideal features using the Piranha foraging Optimization Algorithm. The selected features are provided to a Deep Convolutional Spiking Neural Network (DCSNN) for classifying Twitter data as negative, positive and neutral. Then, the DCSNN approach is optimized using Balancing Composite Motion Optimization (BCMO) for better performance. The efficacy of the proposed technique is examined using performance metrics and the method attains 23.32%, 26.07% and 28.51% higher accuracy and 21.92%, 15.03% and 19.15% lesser error rate are evaluated with existing approaches.","url":"https://doi.org/10.1142/s0218126626501896","authors":["G. N. Balaji","P. Sudhakaran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-13T15:33:56Z","doi":"10.1142/s0218126626501896","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.64898/2026.05.19.726261","name":"Equilibrium Propagation with Predictive Learning in Leaky Integrate-and-Fire Spiking Neural Networks","source":"crossref","abstract":"Abstract Equilibrium propagation (EP) is a biologically plausible alternative to backpropagation that has demonstrated competitive performance across a range of machine learning tasks. Recent work has extended EP to spiking neural networks (SNNs), leveraging leaky integrate-and-fire (LIF) neurons and spike-based plasticity rules to improve biological realism while maintaining strong performance. In this work, we propose an EP-based SNN framework that combines LIF neural dynamics with a predictive learning rule, replacing conventional spike-timing-dependent plasticity (STDP) with a learning rule more directly aligned with predictive coding principles. We evaluate the proposed model on multiple image classification benchmarks, including MNIST, KMNIST, and Fashion-MNIST, and compare its performance with a BP-trained LIF SNN baseline. Our results show that the proposed EP-based LIF model (EP+LIF) achieves competitive accuracy across datasets, with performance approaching that of the BP-trained counterpart (BP+LIF) while relying on a biologically motivated local learning rule. In addition, analysis of hidden-layer spiking activity reveals that EP+LIF produces more persistent hidden-state activity, whereas BP+LIF yields sparser spiking representations. These results demonstrate that predictive learning can support effective EP-based training in LIF spiking networks, while also highlighting differences in activity patterns that motivate future work on activity regulation and sparse spiking dynamics.","url":"https://doi.org/10.64898/2026.05.19.726261","authors":["Yoshimasa Kubo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-22T03:10:24Z","doi":"10.64898/2026.05.19.726261","addedAt":"2026-09-01T01:48:24.596Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1016/j.neucom.2026.134476","name":"Multivariate time series forecasting with a numerical spiking neural P system-inspired network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2026.134476","authors":["Jiachang Xu","Jiahao Pan","Shuzhi Su","Hongjin Li","Ruijuan Zhao","Fei Ding"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-11T14:58:13Z","doi":"10.1016/j.neucom.2026.134476","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1016/j.array.2026.101005","name":"Fractional groupers brown-bear optimization based spiking channel attention-based convolutional recurrent neural network for intrusion detection in heterogeneous federated IoT networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.array.2026.101005","authors":["Sneha Leela Jacob","H. Parveen Sultana"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-10T15:37:54Z","doi":"10.1016/j.array.2026.101005","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1109/cstic68613.2026.11537851","name":"Two-Dimensional Hexagonal Boron Nitride Based Memristors for Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cstic68613.2026.11537851","authors":["Yuzhe Lin","Xinwei Zhang","Zuqi Zhu","Yuxin Li","Guanyu Liu","Yuda Zhao","Yu Kang","Bin Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-02T20:03:17Z","doi":"10.1109/cstic68613.2026.11537851","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1007/s10489-024-05786-3","name":"Parallel proportional fusion of a spiking quantum neural network for optimizing image classification","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s10489-024-05786-3","authors":["Zuyu Xu","Kang Shen","Pengnian Cai","Tao Yang","Yuanming Hu","Shixian Chen","Yunlai Zhu","Zuheng Wu","Yuehua Dai","Jun Wang","Fei Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-03T11:02:06Z","doi":"10.1007/s10489-024-05786-3","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:24.597Z"},{"id":"doi:10.1088/2634-4386/ae8627/v2/review2","name":"Review for \"Energy-aware spike budgeting for continual learning in spiking neural networks for neuromorphic vision\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2634-4386/ae8627/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-03T23:27:36Z","doi":"10.1088/2634-4386/ae8627/v2/review2","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1364/ofc.2024.tu3f.4","name":"Demonstration of Neural Heterogeneity with Programmable Brain-Inspired Optoelectronic Spiking Neurons","source":"crossref","abstract":"Neural heterogeneity enables spiking neural networks to implement complex functions with fewer neurons. We designed, simulated, and demonstrated programmable optoelectronic spiking neurons that can achieve multiple neuron characteristics based on external tuning voltages.","url":"https://doi.org/10.1364/ofc.2024.tu3f.4","authors":["Yun-Jhu Lee","Mehmet Berkay On","Luis El Srouji","Li Zhang","Mahmoud Abdelghany","S.J. Ben Yoo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-14T12:44:20Z","doi":"10.1364/ofc.2024.tu3f.4","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:24.597Z"},{"id":"doi:10.1016/j.tcs.2023.114250","name":"Steps toward a homogenization procedure for spiking neural P systems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.tcs.2023.114250","authors":["Ren Tristan A. de la Cruz","Francis George C. Cabarle","Henry N. Adorna"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-12T11:55:12Z","doi":"10.1016/j.tcs.2023.114250","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:24.597Z"},{"id":"doi:10.1109/iccwamtip64812.2024.10873762","name":"MFN: A Brain-Like Auditory Model Based on Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccwamtip64812.2024.10873762","authors":["Qing Hongyu","Gao Guangyuan","Zhang Yang","Lin Xuntong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-18T18:15:42Z","doi":"10.1109/iccwamtip64812.2024.10873762","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:24.597Z"},{"id":"doi:10.1016/j.sse.2024.108860","name":"Deep spiking neural networks with integrate and fire neuron using steep switching device","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.sse.2024.108860","authors":["Sung Yun Woo","Sangyeon Pak","Sung-Tae Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-12T10:37:51Z","doi":"10.1016/j.sse.2024.108860","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:24.597Z"},{"id":"doi:10.1504/ijmc.2026.152932","name":"Optimised deep convolutional spiking neural network for accurate long-term and short-term rainfall forecasting in climate prediction systems","source":"crossref","abstract":"","url":"https://doi.org/10.1504/ijmc.2026.152932","authors":["M. Amanullah","K. Ananthajothi","Moorthy Agoramoorthy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-16T11:30:25Z","doi":"10.1504/ijmc.2026.152932","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.30919/es2204","name":"Coupled Spiking Neural Network–Extra Trees Framework for Daily Streamflow Imputation with ERA5-Land Integration","source":"crossref","abstract":"","url":"https://doi.org/10.30919/es2204","authors":["Sirimon Pinthong","Nureehan Salaeh","Quoc Bao Pham","Md. Abdullah Al Mamun Hridoy","Chiara Bordin","Pakorn Ditthakit"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-28T04:10:51Z","doi":"10.30919/es2204","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1504/ijbic.2026.155425","name":"DynSpike: a spiking neural network for effective long-term temporal dependency capture in dynamic graphs","source":"crossref","abstract":"","url":"https://doi.org/10.1504/ijbic.2026.155425","authors":["Zijing Yuan","Tianfang Lu","Masaaki Omura","Shangce Gao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-02T19:03:42Z","doi":"10.1504/ijbic.2026.155425","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1109/isvlsi61997.2024.00068","name":"Evaluation of Neuron Parameters on the Performance of Spiking Neural Networks and Neuromorphic Hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isvlsi61997.2024.00068","authors":["Catherine Schuman","Hritom Das","Garrett S. Rose","James S. Plank"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-25T17:27:50Z","doi":"10.1109/isvlsi61997.2024.00068","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:24.597Z"},{"id":"doi:10.1109/tnnls.2023.3263008","name":"Backpropagation-Based Learning Techniques for Deep Spiking Neural Networks: A Survey","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnnls.2023.3263008","authors":["Manon Dampfhoffer","Thomas Mesquida","Alexandre Valentian","Lorena Anghel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-07T13:30:05Z","doi":"10.1109/tnnls.2023.3263008","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:24.597Z"},{"id":"doi:10.1109/metacom62920.2024.00056","name":"Event-based White Blood Cell Classification using Convolutional Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/metacom62920.2024.00056","authors":["Youngshin Kang","Geunbo Yang","Cheolsoo Park"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-06T18:37:26Z","doi":"10.1109/metacom62920.2024.00056","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:24.597Z"},{"id":"doi:10.1109/icses63760.2024.10910583","name":"Quantum-Enhanced Spiking Neural Networks for Closed-Loop Neuromodulation Systems: A Theoretically Advanced Framework","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icses63760.2024.10910583","authors":["Vallari Ashar","Sarthak Bansal","Pandiyaraju V"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-12T17:38:08Z","doi":"10.1109/icses63760.2024.10910583","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:24.597Z"},{"id":"doi:10.2172/2476990","name":"Predicting Missing Regions in Charged Particle Tracks Using a Sparse 3D Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.2172/2476990","authors":["Hilary Utaegbulam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-15T03:15:19Z","doi":"10.2172/2476990","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.15199/48.2024.03.36","name":"Adaptive Deep Learning with Optimization Hybrid Convolutional  Neural Network and Recurrent Neural Network for Prediction  Lemon Fruit Ripeness","source":"crossref","abstract":"","url":"https://doi.org/10.15199/48.2024.03.36","authors":["Darunee WATNAKORNBUNCHA"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-24T21:19:37Z","doi":"10.15199/48.2024.03.36","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1109/access.2024.3500134","name":"Efficient Hardware Implementation of a Multi-Layer Gradient-Free Online-Trainable Spiking Neural Network on FPGA","source":"crossref","abstract":"","url":"https://doi.org/10.1109/access.2024.3500134","authors":["Ali Mehrabi","Yeshwanth Bethi","André van Schaik","Andrew Wabnitz","Saeed Afshar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-18T18:58:20Z","doi":"10.1109/access.2024.3500134","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:24.597Z"},{"id":"doi:10.1007/978-981-97-9282-5","name":"Spiking Neural P Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-9282-5","authors":["Gexiang Zhang","Sergey Verlan","Tingfang Wu","Francis George C. Cabarle","Jie Xue","David Orellana-Martín","Jianping Dong","Luis Valencia-Cabrera","Mario J. Pérez-Jiménez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-13T12:14:27Z","doi":"10.1007/978-981-97-9282-5","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:24.597Z"},{"id":"doi:10.1038/s41598-024-52299-7","name":"On computational models of theory of mind and the imitative reinforcement learning in spiking neural networks","source":"crossref","abstract":"Abstract Theory of Mind is referred to the ability of inferring other’s mental states, and it plays a crucial role in social cognition and learning. Biological evidences indicate that complex circuits are involved in this ability, including the mirror neuron system. The mirror neuron system influences imitation abilities and action understanding, leading to learn through observing others. To simulate this imitative learning behavior, a Theory-of-Mind-based Imitative Reinforcement Learning (ToM-based ImRL) framework is proposed. Employing the bio-inspired spiking neural networks and the mechanisms of the mirror neuron system, ToM-based ImRL is a bio-inspired computational model which enables an agent to effectively learn how to act in an interactive environment through observing an expert, inferring its goals, and imitating its behaviors. The aim of this paper is to review some computational attempts in modeling ToM and to explain the proposed ToM-based ImRL framework which is tested in the environment of River Raid game from Atari 2600 series.","url":"https://doi.org/10.1038/s41598-024-52299-7","authors":["Ashena Gorgan Mohammadi","Mohammad Ganjtabesh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-22T21:04:06Z","doi":"10.1038/s41598-024-52299-7","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.3389/fnhum.2026.1747899","name":"A historical review of ephaptic field research: from early foundations through contemporary renaissance.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnhum.2026.1747899","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnhum.2026.1747899","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1007/s00359-026-01796-3","name":"Neuronal processing of complex sounds in the prothoracic ganglion of a bushcricket.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s00359-026-01796-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s00359-026-01796-3","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1152/jn.00530.2025","name":"Modeling insights into potential mechanisms of opioid-induced respiratory depression within medullary and pontine networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1152/jn.00530.2025","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1152/jn.00530.2025","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1038/s42003-026-09589-9","name":"Multi-organoid loop cerebral connectoids exhibit enhanced neuronal network dynamics and sequence-specific entrainment.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s42003-026-09589-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s42003-026-09589-9","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1002/hipo.70089","name":"The Role of Plasticity in Replay: Stability Through Anti-Hebbian Rules.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/hipo.70089","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/hipo.70089","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1016/j.neubiorev.2026.106692","name":"Sensory-to-motor transformations: From serial pipelines to dynamic, distributed processes.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neubiorev.2026.106692","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neubiorev.2026.106692","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1016/j.nbd.2026.107281","name":"Pharmacological manipulation of nested oscillations in human iPSC-derived 2D neuronal networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.nbd.2026.107281","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.nbd.2026.107281","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3390/s26092656","name":"Spiking Neural Networks with Continual Learning for Steering Angle Regression: A Sustainable AI Perspective.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s26092656","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/s26092656","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1016/j.isci.2026.115824","name":"Electrophysiologically informed spiking neural networks for fish-inspired navigation with boundary vector cells and hydrostatic pressure cues.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.isci.2026.115824","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.isci.2026.115824","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s44182-026-00081-4","name":"All eyes, no IMU: learning flight attitude from vision alone.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s44182-026-00081-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s44182-026-00081-4","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41598-026-42380-8","name":"An efficient prediction based data collection method for wireless sensor networks using hybrid fuzzy clustering and optimized deep maxout neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-42380-8","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-42380-8","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1523/jneurosci.0941-25.2026","name":"Microglia Modulate Information Processing in the Mouse Barrel Cortex.","source":"europepmc","abstract":"","url":"https://doi.org/10.1523/jneurosci.0941-25.2026","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1523/jneurosci.0941-25.2026","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1016/j.neunet.2026.108548","name":"Uncovering various neuronal responses in a fractional-order generalized HR system.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.108548","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.108548","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3389/fncel.2026.1783885","name":"Editorial: Multiscale brain modelling.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncel.2026.1783885","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fncel.2026.1783885","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fnins.2026.1605209","name":"Spiking neural networks provide accurate and time-efficient models for whisker stimulus classification of the awake mouse.","source":"europepmc","abstract":"Machine learning algorithms have great potential for classifying brain activity, and lightweight classifier algorithms, requiring little computational resources, can be used on low-energy neuromorphic hardware designed for implantable neuroprosthetics. One of these efficient algorithms, the Liquid State Machine, implements the concept of Spiking Neural Networks and has been shown to achieve outstanding results on the task of whisker stimulus detection from the mouse barrel cortex, a widely used model system. While this is promising for neuroprosthetics, it has been unclear how a Spiking Neural Network or other machine learning algorithms perform on data recorded from awake mice and how trained models generalize across individuals, the latter being relevant to transferring trained models to new hardware. Using laminar multi-electrode local field potential recordings obtained from four mice performing a single-whisker detection task, we benchmarked the performance of a collection of lightweight classification algorithms. We found that the Liquid State Machine, a generalized linear model, and the time series classifier ROCKET are the most accurate for stimulus detection. Among those, the Liquid State Machine achieved the fastest model training and inference runtime and provided robust accuracy across individual mice. Additional analyses show that there is no significant improvement in using multiple cortical layers as input for the model and that 40 ms of stimulus recording is sufficient to maintain high detection accuracy.","url":"https://doi.org/10.3389/fnins.2026.1605209","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnins.2026.1605209","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1002/advs.75838","name":"Full-Stack Architectures for Intelligent Brain-Computer Interfaces.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.75838","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.75838","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1523/eneuro.0452-25.2026","name":"Fast Spiking Interneurons Autonomously Generate Fast Gamma Oscillations in the Medial Entorhinal Cortex with Excitation Strength Tuning ING-PING Transitions.","source":"europepmc","abstract":"","url":"https://doi.org/10.1523/eneuro.0452-25.2026","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1523/eneuro.0452-25.2026","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1038/s41593-026-02216-0","name":"Convolutional neural network models describe the encoding subspace of local circuits in auditory cortex.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41593-026-02216-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41593-026-02216-0","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1016/j.ibneur.2025.10.005","name":"Rethinking parvalbumin: From passive marker to active modulator of hippocampal circuits.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.ibneur.2025.10.005","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.ibneur.2025.10.005","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1038/s41598-026-40552-0","name":"Distinct functional networks derived from human induced pluripotent stem cell neuronal activity.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-40552-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-40552-0","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3390/brainsci16060603","name":"Nonlinear EEG Complexity as a Marker of Maladaptive Brain Plasticity in Substance Use Disorders: A Multi-Group Machine Learning Classification Study.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/brainsci16060603","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/brainsci16060603","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.7554/elife.99693","name":"Modeling and simulation of neocortical micro- and mesocircuitry (Part II, Physiology and experimentation).","source":"europepmc","abstract":"","url":"https://doi.org/10.7554/elife.99693","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.7554/elife.99693","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1093/nc/niag025","name":"Contrasting predictive coding and representational accounts of perceptual organization, stimulus predictability, and attentional modulation in the visual cortical hierarchy.","source":"europepmc","abstract":"","url":"https://doi.org/10.1093/nc/niag025","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1093/nc/niag025","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3389/fphar.2026.1840553","name":"GABA&lt;sub&gt;A&lt;/sub&gt; receptor dysfunction in autism spectrum disorder: molecular mechanisms and therapeutic opportunities.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fphar.2026.1840553","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fphar.2026.1840553","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3389/fnagi.2026.1807660","name":"Age-related degradation of behavioral and network features of &lt;i&gt;Aplysia&lt;/i&gt; escape locomotion.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnagi.2026.1807660","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnagi.2026.1807660","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3389/frai.2025.1590599","name":"Biologically inspired hybrid model for Alzheimer's disease classification using structural MRI in the ADNI dataset.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/frai.2025.1590599","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/frai.2025.1590599","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1002/hbm.70597","name":"Intrinsic Functional Architecture Reflects Individual Differences in Passive Working Memory: An Exploratory Resting-State fMRI Study.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/hbm.70597","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/hbm.70597","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1002/hbm.70428","name":"Fast Interneuron Dysfunction in Laminar Neural Mass Model Reproduces Alzheimer's Oscillatory Biomarkers.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/hbm.70428","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/hbm.70428","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1038/s41467-026-70347-w","name":"Desegregation of neuronal predictive processing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-70347-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-70347-w","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1126/sciadv.adv9396","name":"Neuronal heterogeneity of normalization strength in a circuit model.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.adv9396","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1126/sciadv.adv9396","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.7554/elife.103512","name":"Barcode activity in a recurrent network model of the hippocampus enables efficient memory binding.","source":"europepmc","abstract":"","url":"https://doi.org/10.7554/elife.103512","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.7554/elife.103512","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3389/fnins.2025.1665778","name":"Balancing accuracy and efficiency: co-design of hybrid quantization and unified computing architecture for spiking neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2025.1665778","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fnins.2025.1665778","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1038/s41467-026-69068-x","name":"Sensory encoding and memory retrieval are coordinated with propagating waves in the human brain.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-69068-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-69068-x","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fncom.2026.1710914","name":"Cross-subject mapping of neural activity with restricted Boltzmann machines.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2026.1710914","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fncom.2026.1710914","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.7554/elife.108237","name":"Adjoint propagation of error signal through modular recurrent neural networks for biologically plausible learning.","source":"europepmc","abstract":"Biologically plausible learning mechanisms have implications for understanding brain functions and engineering intelligent systems. Inspired by the multi-scale recurrent connectivity in the brain, we introduce an adjoint propagation (AP) framework, in which the error signals arise naturally from recurrent dynamics and propagate concurrently with forward inference signals. AP inherits the modularity of multi-region recurrent neural network (MR-RNN) models and leverages the convergence properties of RNN modules to facilitate fast and scalable training. This framework eliminates the biologically implausible feedback required by the backpropagation (BP) algorithm and allows concomitant error propagation for multiple tasks through the same RNN. We demonstrate that AP succeeds in training on standard benchmark tasks, achieving accuracies comparable to BP-trained networks while adhering to neurobiological constraints. The training process exhibits robustness, maintaining performance over extended training epochs. Importantly, AP supports flexible resource allocation for multiple cognitive tasks, consistent with observations in neuroscience. This framework bridges artificial and biological learning principles, paving the way for energy-efficient intelligent systems inspired by the brain and offering a mechanistic theory that can guide experimental investigations in neuroscience.","url":"https://doi.org/10.7554/elife.108237","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.7554/elife.108237","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1162/neco.a.37","name":"Model Predictive Control on the Neural Manifold.","source":"europepmc","abstract":"","url":"https://doi.org/10.1162/neco.a.37","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1162/neco.a.37","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3389/fncom.2025.1639829","name":"Maximum likelihood estimation of spatially dependent interactions in large populations of cortical neurons.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2025.1639829","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fncom.2025.1639829","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1016/j.neuron.2025.11.005","name":"Synchrony timescales underlie irregular neocortical spiking.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neuron.2025.11.005","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neuron.2025.11.005","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3389/fncir.2025.1568652","name":"Dissociated neuronal cultures as model systems for self-organized prediction.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncir.2025.1568652","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fncir.2025.1568652","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1016/j.nbd.2025.107253","name":"Spinal circuit mechanisms constrain therapeutic windows for ALS intervention: A computational modeling study.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.nbd.2025.107253","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.nbd.2025.107253","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1523/jneurosci.0146-25.2025","name":"Aperiodic Activity Reflects Pathologic Waveform Shapes in Focal Epilepsy.","source":"europepmc","abstract":"","url":"https://doi.org/10.1523/jneurosci.0146-25.2025","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1523/jneurosci.0146-25.2025","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1016/j.pneurobio.2025.102873","name":"Prefrontal cortex interneurons and their contributions to attention, working memory, and adaptive behavior.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.pneurobio.2025.102873","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.pneurobio.2025.102873","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1038/s41538-026-00730-w","name":"Machine learning unveils three layers of food complexity.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41538-026-00730-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41538-026-00730-w","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1002/adma.202506921","name":"Steep-Slope CuInP&lt;sub&gt;2&lt;/sub&gt;S&lt;sub&gt;6&lt;/sub&gt; Ferroionic Threshold Switching Field-Effect Transistor for Implementation of Artificial Spiking Neuron.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202506921","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/adma.202506921","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1016/j.crneur.2026.100159","name":"Spectral dependence as a framework for neural coordination.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.crneur.2026.100159","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.crneur.2026.100159","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1371/journal.pcbi.1013081","name":"Balanced state of networks of winner-take-all units.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pcbi.1013081","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1371/journal.pcbi.1013081","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3389/fnins.2026.1808558","name":"The role of sensory experience in the maturation of prefrontal cortical circuits.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2026.1808558","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnins.2026.1808558","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1523/jneurosci.0405-25.2025","name":"Marmoset Anterior Cingulate Area 32 Neurons Exhibit Responses to Presented and Produced Calls during Naturalistic Vocal Communication.","source":"europepmc","abstract":"","url":"https://doi.org/10.1523/jneurosci.0405-25.2025","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1523/jneurosci.0405-25.2025","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1007/s00359-025-01775-0","name":"Neurons sensitive to sky compass signals in the brain of the Madeira cockroach Rhyparobia maderae.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s00359-025-01775-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s00359-025-01775-0","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1016/j.neuropsychologia.2025.109096","name":"Linking the multiple-demand cognitive control system to human electrophysiological activity.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neuropsychologia.2025.109096","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.neuropsychologia.2025.109096","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3390/brainsci16020192","name":"iTBS Stimulation of the Bilateral IFG/IPL Alters the Oscillatory Pattern in ASD.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/brainsci16020192","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/brainsci16020192","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3389/ftox.2026.1783893","name":"Towards learning and memory risk assessment with human brain organoids: barriers and opportunities.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/ftox.2026.1783893","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/ftox.2026.1783893","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1073/pnas.2603966123","name":"Oxytocin selectively biases sensory-prefrontal communication through network-level suppression and theta coupling.","source":"europepmc","abstract":"","url":"https://doi.org/10.1073/pnas.2603966123","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1073/pnas.2603966123","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1007/s11571-026-10436-0","name":"Dynamics and energy encoding of a star-like neuron network composed of the Wang-Zhang model induced by compressing a sphere into a fingertip.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-026-10436-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s11571-026-10436-0","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3389/fnsyn.2026.1741452","name":"Evolutionary neuroeconomic adaptations of fast-spiking neurons in the human neocortex.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnsyn.2026.1741452","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnsyn.2026.1741452","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1038/s41586-026-10331-y","name":"Active dissociation of intracortical spiking and high gamma activity.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41586-026-10331-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41586-026-10331-y","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1016/j.bja.2025.07.046","name":"Association between pyramidal neurone spiking in the medial prefrontal cortex and the sedative potency of volatile anaesthetics in mice.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.bja.2025.07.046","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.bja.2025.07.046","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1038/s41598-025-14619-3","name":"Temporal single spike coding for effective transfer learning in spiking neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-14619-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-14619-3","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3389/fnins.2026.1811969","name":"Artificial intelligence-based analysis of visual electrophysiological signals for clinical interpretation support.","source":"europepmc","abstract":"Introduction Visual electrophysiology, including electroretinograms (ERG) and visual evoked potentials (VEP), provides a real-time functional assessment of retinal and post-retinal pathways, complementing structural imaging. Subtypes such as transient, periodic, multifocal, and code-modulated signals probe distinct physiological mechanisms and reveal pathological signatures ranging from photoreceptor dysfunction to cortical pathway impairment. However, interpretation is often challenged by low signal amplitude, noise, and inter-individual variability. Advances in artificial intelligence (AI) enable automated, objective and reproducible analysis, and may improve sensitivity, and scalability in clinical and research environments. We undertook a literature review to identify the potential of automated analysis of brief visual electrophysiology signals to support medical interpretation in ophthalmology. Materials and methods A review of the 2020-2025 literature was undertaken. Results AI has been increasingly applied to ERG and VEP signals. These signals encode complex pathophysiological processes. Their features vary widely as they are transient (triggered by a single stimulus), periodic (repeated over time), multifocal (capturing signals from multiple visual field locations), or dependent on specific timing or coding schemes. These properties influence the choice of the most appropriate AI method for analysis. Classical ML methods remain useful for interpretable, feature-based classification of relatively scarce medical data, such as transient/aperiodic VEP and ERG. By modeling latent dynamics, AI can identify subtle or early dysfunction and harmonize interpretation across centers. Conclusion AI supports reproducible, clinician-independent pipelines for electrophysiology, well-suited to high-volume clinics and large-scale screening. The convergence of standardized acquisition protocols with advanced AI analysis has the potential to deliver more personalized, timely, and objective assessments of visual system integrity in neuro-ophthalmic practice.","url":"https://doi.org/10.3389/fnins.2026.1811969","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnins.2026.1811969","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3389/frai.2026.1749956","name":"Formal methods for safety-critical machine learning: a systematic literature review.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/frai.2026.1749956","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/frai.2026.1749956","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1038/s44460-025-00007-x","name":"High-frequency, low-energy organic event-based sensors for closed-loop neurostimulation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s44460-025-00007-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s44460-025-00007-x","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.7717/peerj-cs.2761","name":"iPro-CSAF: identification of promoters based on convolutional spiking neural networks and spiking attention mechanism.","source":"europepmc","abstract":"","url":"https://doi.org/10.7717/peerj-cs.2761","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.7717/peerj-cs.2761","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1016/j.stemcr.2025.102718","name":"Hypersynchronous iPSC-derived SHANK2 neuronal networks are rescued by mGluR5 agonism.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.stemcr.2025.102718","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.stemcr.2025.102718","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.7554/elife.109539","name":"Computational mechanisms for temporal integration in the anterior claustrum.","source":"europepmc","abstract":"","url":"https://doi.org/10.7554/elife.109539","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.7554/elife.109539","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3389/fncom.2025.1569374","name":"Reinforced liquid state machines-new training strategies for spiking neural networks based on reinforcements.","source":"europepmc","abstract":"Introduction Feedback and reinforcement signals in the brain act as natures sophisticated teaching tools, guiding neural circuits to self-organization, adaptation, and the encoding of complex patterns. This study investigates the impact of two feedback mechanisms within a deep liquid state machine architecture designed for spiking neural networks. Methods The Reinforced Liquid State Machine architecture integrates liquid layers, a winner-takes-all mechanism, a linear readout layer, and a novel reward-based reinforcement system to enhance learning efficacy. While traditional Liquid State Machines often employ unsupervised approaches, we introduce strict feedback to improve network performance by not only reinforcing correct predictions but also penalizing wrong ones. Results Strict feedback is compared to another strategy known as forgiving feedback, excluding punishment, using evaluations on the Spiking Heidelberg data. Experimental results demonstrate that both feedback mechanisms significantly outperform the baseline unsupervised approach, achieving superior accuracy and adaptability in response to dynamic input patterns. Discussion This comparative analysis highlights the potential of feedback integration in deepened Liquid State Machines, offering insights into optimizing spiking neural networks through reinforcement-driven architectures.","url":"https://doi.org/10.3389/fncom.2025.1569374","authors":["Dominik Krenzer","Martin Bogdan"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fncom.2025.1569374","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1016/j.isci.2025.113813","name":"A network of Bayesian agents for reward prediction and noise tolerance.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.isci.2025.113813","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.isci.2025.113813","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3389/fnhum.2026.1750878","name":"Linking EEG markers of oscillopathy and default mode network dysfunction in Alzheimer's disease.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnhum.2026.1750878","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnhum.2026.1750878","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1016/j.ynirp.2026.100319","name":"Action observation responses in macaque frontal cortex.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.ynirp.2026.100319","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.ynirp.2026.100319","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.3389/fncom.2025.1638782","name":"Exploring subthreshold processing for next-generation TinyAI.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2025.1638782","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fncom.2025.1638782","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1371/journal.pcbi.1012156","name":"Cooperative coding of continuous variables in networks with sparsity constraint.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pcbi.1012156","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1371/journal.pcbi.1012156","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1007/s10827-026-00923-y","name":"Spaces and sequences in the hippocampus: a homological perspective.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s10827-026-00923-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s10827-026-00923-y","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.12.29.630683","name":"NeuroTorch: A Python library for neuroscience-oriented machine learning","source":"preprints","abstract":"Machine learning (ML) has become a powerful tool for data analysis, leading to significant advances in neuroscience research. While ML algorithms are proficient in general-purpose tasks, their highly technical nature often hinders their compatibility with the observed biological principles and constraints in the brain, thereby limiting their suitability for neuroscience applications. In this work, we introduce NeuroTorch, a comprehensive ML pipeline specifically designed to assist neuroscientists in leveraging ML techniques using biologically inspired neural network models. NeuroTorch enables the training of recurrent neural networks equipped with either spiking or firing-rate dynamics, incorporating additional biological constraints such as Dale's law and synaptic excitatory-inhibitory balance. The pipeline offers various learning methods, including backpropagation through time and eligibility trace forward propagation, aiming to allow neuroscientists to effectively employ ML approaches. To evaluate the performance of NeuroTorch, we conducted experiments on well-established public datasets for classification tasks, namely MNIST, Fashion-MNIST, and Heidelberg. Notably, NeuroTorch achieved accuracies that replicated the results obtained using the Norse and SpyTorch packages. Additionally, we tested NeuroTorch on real neuronal activity data obtained through volumetric calcium imaging in larval zebrafish. On training sets representing 9.3 minutes of activity under darkflash stimuli from 522 neurons, the mean proportion of variance explained for the spiking and firing-rate neural network models, subject to Dale's law, exceeded 0.97 and 0.96, respectively. Our analysis of networks trained on these datasets indicates that both Dale's law and spiking dynamics have a beneficial impact on the resilience of network models when subjected to connection ablations. NeuroTorch provides an accessible and well-performing tool for neuroscientists, granting them access to state-of-the-art ML models used in the field without requiring in-depth expertise in computer science.","url":"https://doi.org/10.1101/2024.12.29.630683","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.12.29.630683","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.12.31.630823","name":"A genetic algorithm for self-supervised models of oscillatory neurodynamics","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.12.31.630823","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.12.31.630823","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.31234/osf.io/p37yq","name":"Linking the multiple-demand cognitive control system to human electrophysiological activity","source":"preprints","abstract":"","url":"https://doi.org/10.31234/osf.io/p37yq","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.31234/osf.io/p37yq","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.08.16.608322","name":"FORCE trained spiking networks do not benefit from faster learning while parameter matched rate networks do","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.08.16.608322","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.08.16.608322","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.12.04.626902","name":"Effects of Spatial Constraints of Inhibitory Connectivity on the Dynamical Development of Criticality in Spiking Networks","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.12.04.626902","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.12.04.626902","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.11.29.626029","name":"Kernel-based LFP estimation in detailed large-scale spiking network model of mouse visual cortex","source":"preprints","abstract":"Summary Simulations of large-scale neural activity are powerful tools for investigating neural networks. Calculating measurable brain signals like local field potentials (LFPs) bridges the gap between model predictions and experimental observations. However, accurately simulating LFPs from large-scale models has traditionally required highly detailed multicompartmental neuron models, posing significant computational challenges. Here, we demonstrate that a kernel-based method can efficiently and accurately estimate LFPs in a state-of-the-art multicompartmental model of the mouse primary visual cortex (V1). Beyond its computational efficiency, the kernel method aids analysis by disentangling contributions of individual neuronal populations to the LFP. Using this approach, we found that LFPs in the V1 model were dominated by external synaptic inputs, with local synaptic activity playing a minimal role. Our findings establish the kernel method as a powerful tool for LFP estimation in large-scale network models and for uncovering the synaptic mechanisms underlying brain signals.","url":"https://doi.org/10.1101/2024.11.29.626029","authors":["Nicolò Meneghetti","Atle E. Rimehaug","Gaute T. Einevoll","Alberto Mazzoni","Torbjørn V. Ness"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.11.29.626029","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.10.15.618398","name":"Synchrony dynamics underlie irregular neocortical spiking","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.10.15.618398","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.10.15.618398","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.12.02.24317799","name":"Transcutaneous afferent patterned stimulation reduces essential tremor symptoms through modulation of neural activity in the ventral intermediate nucleus of the thalamus","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.12.02.24317799","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.12.02.24317799","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.09.17.613386","name":"Functional consequences of fast-spiking interneurons in striatum","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.09.17.613386","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.09.17.613386","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.21203/rs.3.rs-4605061/v1","name":"TL-SNN: Event-Driven Visual-Tactile Learning with Temporal and Location Spiking Neurons","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4605061/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4605061/v1","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.11.11.622953","name":"Modeling neuron-astrocyte interactions in neural networks using distributed simulation","source":"preprints","abstract":"Astrocytes engage in local interactions with neurons, synapses, other glial cell types, and the vasculature through intricate cellular and molecular processes, playing an important role in brain information processing, plasticity, cognition, and behavior. This study advances understanding of local interactions and self-organization of neuron-astrocyte networks and contributes to the broader investigation of their potential relationship with global activity regimes and overall brain function. We present six new contributions: (1) the development of a new model-building framework for neuron-astrocyte networks, (2) the introduction of connectivity concepts for tripartite neuron-astrocyte interactions in biological neural networks, (3) the design of a scalable architecture capable of simulating networks with up to a million cells, (4) a formalized description of neuron-astrocyte modeling that facilitates reproducibility, (5) the integration of experimental data to a greater extent than existing studies, and (6) simulation results demonstrating how neuron-astrocyte interactions drive the emergence of synchronization in local neuronal groups. Specifically, we develop a new technology for representing astrocytes and their interactions with neurons in distributed simulation code for large-scale spiking neuronal networks. This includes an astrocyte model with calcium dynamics, an extended neuron model receiving calcium-dependent signals from astrocytes, and a parallelized connectivity generation scheme for tripartite interactions between pre- and postsynaptic neurons and astrocytes. We verify the efficiency of our reference implementation through benchmarks varying in computing resources and network sizes. Our in silico experiments reproduce experimental data on astrocytic effects on neuronal synchronization, demonstrating that astrocytes consistently induce local synchronization in groups of neurons across various connectivity schemes and global activity regimes. By adjusting the strength of neuron-astrocyte interactions, we can switch the global activity regime from asynchronous to network-wide synchronization. This work represents an advancement in neuron-astrocyte modeling, introducing a novel framework that enables large-scale simulations of astrocytic influence on neuronal networks. Author summary Astrocytes play an important role in regulating synapses, neuronal networks, and cognitive functions. However, models that include both neurons and astrocytes are underutilized compared to models with only neurons in theoretical and computational studies. We address this issue by developing theoretical concepts for representing astrocytic connectivity and interactions and provide a reference implementation supporting distributed parallel computing in the spiking neural network simulator NEST. Using these capabilities, we show how astrocytes help to synchronize neural networks under various connection patterns and activity levels. The new technology makes it easier to include astrocytes in simulations of neural systems, promoting the construction of more realistic, relevant, and reproducible models.","url":"https://doi.org/10.1101/2024.11.11.622953","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.11.11.622953","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.12.23.630065","name":"Engineered biological neural networks as basic logic operators","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.12.23.630065","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.12.23.630065","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.21203/rs.3.rs-5489562/v1","name":"Memristive blinking neuron enabling dense and scalable photonically-linked neural network","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-5489562/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-5489562/v1","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.09.22.614302","name":"Inferring Effective Networks of Spiking Neurons Using a Continuous-Time Estimator of Transfer Entropy","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.09.22.614302","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.09.22.614302","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.08.16.608240","name":"Selective inhibition in CA3: A mechanism for stable pattern completion through heterosynaptic plasticity","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.08.16.608240","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.08.16.608240","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.12.10.627734","name":"Short- and long-term reconfiguration of rat prefrontal cortical networks following single doses of psilocybin","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.12.10.627734","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.12.10.627734","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.21203/rs.3.rs-4116686/v1","name":"Adaptive Drop Approaches to Train Spiking-YOLO Network for Traffic Flow Counting","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4116686/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4116686/v1","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.07.10.602834","name":"Neuron synchronization analyzed through spatial-temporal attention","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.07.10.602834","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.07.10.602834","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.04.24.591044","name":"Balancing central control and sensory feedback produces adaptable and robust locomotor patterns in a spiking, neuromechanical model of the salamander spinal cord","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.04.24.591044","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.04.24.591044","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.09.27.615361","name":"Biologically informed cortical models predict optogenetic perturbations","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.09.27.615361","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.09.27.615361","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.09.27.615364","name":"Encoding of movement primitives and body posture through distributed proprioception in walking and climbing insects","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.09.27.615364","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.09.27.615364","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.07.15.603496","name":"Emergence and maintenance of modularity in neural networks with Hebbian and anti-Hebbian inhibitory STDP","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.07.15.603496","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.07.15.603496","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.04.29.591748","name":"A Continuous Attractor Model with Realistic Neural and Synaptic Properties Quantitatively Reproduces Grid Cell Physiology","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.04.29.591748","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.04.29.591748","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.04.24.590955","name":"Efficient coding in biophysically realistic excitatory-inhibitory spiking networks","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.04.24.590955","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.04.24.590955","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.06.07.597979","name":"Spiking networks that efficiently process dynamic sensory features explain receptor information mixing in somatosensory cortex","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.06.07.597979","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.06.07.597979","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.21203/rs.3.rs-4470688/v1","name":"Exploring Spiking Neural Networks for Deep Reinforcement Learning in Robotic Tasks: A Comparative Study","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4470688/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4470688/v1","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.09.27.615499","name":"Spontaneous emergence and evolution of neuronal sequences in recurrent networks","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.09.27.615499","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.09.27.615499","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1101/2024.09.17.613530","name":"Cortical state contributions to neuronal response variability in the early visual cortex: A system identification approach","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.09.17.613530","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.09.17.613530","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.10.05.616808","name":"Layer 6 corticothalamic neurons induce high gamma oscillations through cortico-cortical and cortico-thalamo-cortical pathways","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.10.05.616808","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.10.05.616808","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.08.20.608687","name":"Flexible modeling of large-scale neural network stimulation: electrical and optical extensions to The Virtual Electrode Recording Tool for EXtracellular Potentials (VERTEX)","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.08.20.608687","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.08.20.608687","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.06.21.598805","name":"Interplay of Long- and Short-term Synaptic Plasticity in a Spiking Network Model of Rat’s Episodic Memory","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.06.21.598805","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.06.21.598805","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.21203/rs.3.rs-4601839/v1","name":"Single Organic Electrochemical Neuron Capable of Anticoincidence Detection","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4601839/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4601839/v1","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.21203/rs.3.rs-4380754/v1","name":"Small neural networks under external forcing: Periodic pulses and Lévy noise","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4380754/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4380754/v1","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.11.06.622295","name":"Response of neuronal populations to phase-locked stimulation: model-based predictions and validation","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.11.06.622295","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.11.06.622295","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2024.10.11.617548","name":"Neuronal correlates of sleep in honey bees","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.10.11.617548","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.10.11.617548","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.21203/rs.3.rs-4224027/v1","name":"Texture Recognition Using a Biologically Plausible Spiking Phase-Locked Loop Model for Spike Train Frequency Decomposition","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4224027/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4224027/v1","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.01.26.577077","name":"Efficient Inference on a Network of Spiking Neurons using Deep Learning","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.01.26.577077","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.01.26.577077","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.08.21.608969","name":"Deep inverse modeling reveals dynamic-dependent invariances in neural circuit mechanisms","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.08.21.608969","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.08.21.608969","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.01.10.574963","name":"Spiking Neuron-Astrocyte Networks for Image Recognition","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.01.10.574963","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.01.10.574963","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.07.24.605013","name":"Cortico-subcortical dynamics in primate working memory","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.07.24.605013","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.07.24.605013","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2024.09.11.612548","name":"High frequency bursts facilitate fast communication for human spatial attention","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.09.11.612548","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.09.11.612548","addedAt":"2026-09-01T01:48:24.597Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.06.26.600794","name":"Transcranial focused ultrasound activates feedforward and feedback cortico-thalamo-cortical pathways by selectively activating excitatory neurons","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.06.26.600794","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.06.26.600794","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.06.24.600515","name":"An Investigation of Parameter-Dependent Cell-Type Specific Effects of Transcranial Focused Ultrasound Stimulation Using an Awake Head-Fixed Rodent Model","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.06.24.600515","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.06.24.600515","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.02.21.581457","name":"A doubly stochastic renewal framework for partitioning spiking variability","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.02.21.581457","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.02.21.581457","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.21203/rs.3.rs-4789872/v1","name":"Variable and slow-paced neural dynamics in HVC underlie plastic song production in juvenile zebra finches","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4789872/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4789872/v1","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.31234/osf.io/jk9mz","name":"Performance comparison of spiking neural networks to other artificial models in predicting pigeons’ learning history from binary choices","source":"preprints","abstract":"","url":"https://doi.org/10.31234/osf.io/jk9mz","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.31234/osf.io/jk9mz","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.06.24.600332","name":"Decoding dynamic visual scenes across the brain hierarchy","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.06.24.600332","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.06.24.600332","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.10.03.616539","name":"Cell-type specific projection patterns promote balanced activity in cortical microcircuits","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.10.03.616539","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.10.03.616539","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.11.27.625691","name":"Dynamic consensus-building between neocortical areas via long-range connections","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.11.27.625691","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.11.27.625691","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.21203/rs.3.rs-4306732/v1","name":"28 nm FD-SOI embedded phase change memory exhibiting near-zero drift at 12 K for cryogenic spiking neural networks (SNNs)","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4306732/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4306732/v1","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.09.13.612783","name":"Motor learning leverages coordinated low-frequency cortico-basal ganglia activity to optimize motor preparation in humans with Parkinson’s Disease","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.09.13.612783","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.09.13.612783","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.11.15.623743","name":"A hierarchical multiscale model of forward and backward alpha-band traveling waves in the visual system","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.11.15.623743","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.11.15.623743","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.21203/rs.3.rs-4528779/v1","name":"A neuromorphic electronic artist for robotic painting","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4528779/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4528779/v1","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.21203/rs.3.rs-4383796/v1","name":"Novel classification algorithms inspired by firing rate stochastic resonance","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4383796/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4383796/v1","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.07.24.604957","name":"Modeling Nitric Oxide Diffusion and Plasticity Modulation in Cerebellar Learning","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.07.24.604957","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.07.24.604957","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.07.30.605900","name":"Event boundaries drive norepinephrine release and distinctive neural representations of space in the rodent hippocampus","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.07.30.605900","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.07.30.605900","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.08.04.606499","name":"Computational model for synthesizing auditory brainstem responses to assess neuronal alterations in aging and autistic animal models","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.08.04.606499","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.08.04.606499","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.08.13.607480","name":"Network models incorporating chloride dynamics predict optimal strategies for terminating status epilepticus","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.08.13.607480","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.08.13.607480","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2024.08.13.607787","name":"A Biologically Inspired Attention Model for Neural Signal Analysis","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.08.13.607787","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.08.13.607787","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.20944/preprints202407.2153.v1","name":"A Lightweight Shallow Convolutional SNN Combined with STDP Fine-Tuning for Facial Expression Recognition","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202407.2153.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.20944/preprints202407.2153.v1","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.09.03.610998","name":"Spike frequency adaptation in primate lateral prefrontal cortex neurons results from interplay between intrinsic properties and circuit dynamics","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.09.03.610998","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.09.03.610998","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.01.26.574759","name":"Hyper Flexible Neural Networks Rapidly Switch between Logic Operations in a Compact Four Neuron Circuit","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.01.26.574759","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.01.26.574759","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.04.04.588209","name":"Modulation of metastable ensemble dynamics explains the inverted-U relationship between tone discriminability and arousal in auditory cortex","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.04.04.588209","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.04.04.588209","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.02.25.581987","name":"Predictive and error coding for vocal communication signals in the songbird auditory forebrain","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.02.25.581987","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.02.25.581987","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.07.02.601573","name":"Adult-neurogenesis allows for representational stability and flexibility in early olfactory system","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.07.02.601573","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.07.02.601573","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.02.07.579412","name":"Spike Neural Network of Motor Cortex Model for Arm Reaching Control","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.02.07.579412","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.02.07.579412","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.21203/rs.3.rs-4351302/v1","name":"Single Photon Event-Driven 3D Imaging","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4351302/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4351302/v1","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.06.07.597984","name":"<i>Arid1b</i>  haploinsufficiency in cortical inhibitory interneurons causes cell-type-dependent changes in cellular and synaptic development","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.06.07.597984","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.06.07.597984","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.09.06.611710","name":"Fast and slow synaptic plasticity enables concurrent control and learning","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.09.06.611710","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.09.06.611710","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.20944/preprints202401.1245.v1","name":"A Memristor Neural Network Based on Simple Logarithmic-Sigmoidal Transfer Function with MOS Transistors","source":"europepmc","abstract":"","url":"https://doi.org/10.20944/preprints202401.1245.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.20944/preprints202401.1245.v1","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1101/2024.01.31.578157","name":"A systematic analysis of the joint effects of ganglion cells, lagged LGN cells, and intercortical inhibition on spatiotemporal processing and direction selectivity","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.01.31.578157","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.01.31.578157","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.21203/rs.3.rs-4551575/v1","name":"A computational model of behavioral adaptation to solve the credit assignment problem","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4551575/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4551575/v1","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.21203/rs.3.rs-4023416/v1","name":"Kraken: An Open-Source RISC-V SoC for Ultra-Low Power Multi-Modal Perception","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4023416/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4023416/v1","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.21203/rs.3.rs-3938805/v1","name":"Mean-field analysis of synaptic alterations underlying deficient cortical gamma oscillations in schizophrenia","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3938805/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-3938805/v1","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.06.24.600545","name":"Computational Models of Age-Associated Cognitive Slowing","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.06.24.600545","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.06.24.600545","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.05.12.593763","name":"Temporal prediction captures key differences between spiking excitatory and inhibitory V1 neurons","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.05.12.593763","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.05.12.593763","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.02.28.582565","name":"Linking Neural Manifolds to Circuit Structure in Recurrent Networks","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.02.28.582565","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.02.28.582565","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.03.07.583885","name":"The Functional Role of Pinwheel Topology in the Primary Visual Cortex of High-Order Animals for Complex Natural Image Representation","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.03.07.583885","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.03.07.583885","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.04.02.587673","name":"Cell-type-specific firing patterns in a V1 cortical column model depend on feedforward and feedback-driven states","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.04.02.587673","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.04.02.587673","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.21203/rs.3.rs-3830199/v1","name":"Horizontal cortical connections shape intrinsic traveling waves into feature-selective motifs that regulate perceptual sensitivity","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3830199/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-3830199/v1","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.01.13.575481","name":"Modeling the impact of neuromorphological alterations in Down syndrome on fast neural oscillations","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.01.13.575481","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.01.13.575481","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.05.05.592564","name":"Synchrony, oscillations, and phase relationships in collective neuronal activity: a highly comparative overview of methods","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.05.05.592564","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.05.05.592564","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.02.01.578423","name":"Deep learning-based location decoding reveals that across-day representational drift is better predicted by rewarded experience than time","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.02.01.578423","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.02.01.578423","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.11.17.623906","name":"Representational learning by optimization of neural manifolds in an olfactory memory network","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.11.17.623906","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.11.17.623906","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.05.21.595174","name":"How cortico-basal ganglia-thalamic subnetworks can shift decision policies to maximize reward rate","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.05.21.595174","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.05.21.595174","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.08.31.610602","name":"Noradrenaline causes a spread of association in the hippocampal cognitive map","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.08.31.610602","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.08.31.610602","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.03.01.583075","name":"Synfire Chain Dynamics Unravelling Theta-nested Gamma Oscillations for Balancing Prediction and Dodge in Navigation","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.03.01.583075","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.03.01.583075","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.04.16.589839","name":"Calneuron 1 reveals the pivotal roles in schizophrenia via perturbing human forebrain development and causing hallucination-like behavior in mice","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.04.16.589839","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.04.16.589839","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.01.27.575409","name":"Overexpression of the schizophrenia risk gene C4 in PV cells drives sex-dependent behavioral deficits and circuit dysfunction","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.01.27.575409","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.01.27.575409","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.02.09.579660","name":"Closed-loop electrical stimulation to prevent focal epilepsy progression and long-term memory impairment","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.02.09.579660","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.02.09.579660","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.03.26.586771","name":"Temporal prediction captures retinal spiking responses across animal species","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.03.26.586771","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.03.26.586771","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.08.15.608060","name":"Combining Gamma Neuromodulation and Robotic Rehabilitation Restores Parvalbimin-mediated Gamma Function and Boosts Motor Recovery in Stroke Mice","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.08.15.608060","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.08.15.608060","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2024.08.23.609459","name":"Lamellar Schwann cells in the Pacinian corpuscle potentiate vibration perception","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.08.23.609459","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.08.23.609459","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.04.18.590153","name":"Flexible integration of natural stimuli by auditory cortical neurons","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.04.18.590153","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.04.18.590153","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.02.01.578336","name":"Ensemble learning and ground-truth validation of synaptic connectivity inferred from spike trains","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.02.01.578336","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.02.01.578336","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.20944/preprints202401.0475.v1","name":"Nonlinear Dynamics in HfO2/SiO2-Based Interface Dipole Modulation Field-Effect Transistors for Synaptic Applications","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202401.0475.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.20944/preprints202401.0475.v1","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.07.31.605567","name":"Overwriting an instinct: visual cortex instructs learning to suppress fear responses","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.07.31.605567","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.07.31.605567","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2024.09.11.612262","name":"Bimodal nonlinear dendrites in PV+ basket cells drive distinct memory-related oscillations","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.09.11.612262","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.09.11.612262","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.07.10.602852","name":"GlyT2-positive interneurons regulate timing and variability of information transfer in a cerebellar-behavioural loop","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.07.10.602852","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.07.10.602852","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.21203/rs.3.rs-4746435/v1","name":"Taming the chaos gently: a Predictive Alignment learning rule in recurrent neural networks","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4746435/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4746435/v1","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.03.05.583301","name":"Beta bursts in the parkinsonian cortico-basal ganglia network form spatially discrete ensembles","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.03.05.583301","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.03.05.583301","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.07.14.603423","name":"Taming the chaos gently: a Predictive Alignment learning rule in recurrent neural networks","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.07.14.603423","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.07.14.603423","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.10.03.616472","name":"Spatial and network principles behind neural generation of locomotion","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.10.03.616472","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.10.03.616472","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.07.18.604119","name":"Encoding of cerebellar dentate neuron activity during visual attention in rhesus macaques","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.07.18.604119","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.07.18.604119","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.07.23.604408","name":"Flexible Control of Motor Units: Is the Multidimensionality of Motor Unit Manifolds a Sufficient Condition?","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.07.23.604408","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.07.23.604408","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.02.14.580219","name":"High-frequency amplitude-modulated sinusoidal stimulation desynchronizes neural activity and enhances naturalness of evoked sensations","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.02.14.580219","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.02.14.580219","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.03.13.584630","name":"Increased perceptual reliability reduces membrane potential variability in cortical neurons","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.03.13.584630","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.03.13.584630","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.03.22.586292","name":"Implantable Bioelectronics for Gut Electrophysiology","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.03.22.586292","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.03.22.586292","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2024.11.28.625915","name":"Characterizing neuronal and population responses to electrical stimulation in the human hippocampo-cortical network","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.11.28.625915","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.11.28.625915","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.05.17.594663","name":"Developmental olfactory dysfunction and abnormal odor memory in immune-challenged  <i>  Disc1  <sup>+/-</sup>  </i>  mice","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.05.17.594663","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.05.17.594663","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.21203/rs.3.rs-3395895/v1","name":"A role for the thalamus in danger discrimination during sleep","source":"preprints","abstract":"Abstract Sleep is associated with a sensory disconnection from the environment despite a high vulnerability to danger and predation. Yet, sensory stimuli-evoked responses persist in the brain of flies 1 , rodents 2,3 , primates 4,5 , and humans 6,7 during sleep. Whether discrimination between sensory stimuli occurs in the mammalian brain during sleep remains unclear. Here, we showed that neutral auditory stimuli evoked electrical responses propagate in parallel auditory and non-auditory pathway, some of which awaken sleeping mice. We used a convolutional neural network and identified neural activities of centro-medial thalamic (CMT) neurons as the most discriminant hub for auditory-evoked sleep-to-wake transitions among all recorded structures. Importantly, we found that prior associative learning of danger (conditioned stimulus, CS+) and neutral (CS-) auditory cues resulted in increased awakening events upon CS+ exposure during NREM, but not REM, sleep. These sleep-to-wake transitions were blocked by optogenetic silencing of CMT neurons during CS exposure in sleeping mice. Altogether, these results suggest a central role of the CMT neurons in the residual processing of behaviorally-relevant information in the sleeping brain.","url":"https://doi.org/10.21203/rs.3.rs-3395895/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-3395895/v1","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.06.16.599205","name":"Lateral entorhinal cortex afferents reconfigure the activity in piriform cortex circuits","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.06.16.599205","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.06.16.599205","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.08.21.608979","name":"Jaxley: Differentiable simulation enables large-scale training of detailed biophysical models of neural dynamics","source":"preprints","abstract":"Biophysiscal neuron models provide insights into cellular mechanisms underlying neural computations. However, a central challenge has been the question of how to identify the parameters of detailed biophysical models such that they match physiological measurements at scale or such that they perform computational tasks. Here, we describe a framework for simulation of detailed biophysical models in neuroscience—J axley —which addresses this challenge. By making use of automatic differentiation and GPU acceleration, J axley opens up the possibility to efficiently optimize large-scale biophysical models with gradient descent. We show that J axley can learn parameters of biophysical neuron models with several hundreds of parameters to match voltage or two photon calcium recordings, sometimes orders of magnitude more efficiently than previous methods. We then demonstrate that J axley makes it possible to train biophysical neuron models to perform computational tasks. We train a recurrent neural network to perform working memory tasks, and a feedforward network of morphologically detailed neurons with 100,000 parameters to solve a computer vision task. Our analyses show that J axley dramatically improves the ability to build large-scale data- or task-constrained biophysical models, creating unprecedented opportunities for investigating the mechanisms underlying neural computations across multiple scales.","url":"https://doi.org/10.1101/2024.08.21.608979","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.08.21.608979","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.01.21.576561","name":"Alpha phase coding supports feature binding during working memory maintenance","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.01.21.576561","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.01.21.576561","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.09.13.612895","name":"Dynamical Modulation of Hippocampal Replay Sequences through Firing Rate Adaptation","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.09.13.612895","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.09.13.612895","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2023.12.12.571272","name":"Geometry and dynamics of representations in a precisely balanced memory network related to olfactory cortex","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.12.12.571272","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.12.12.571272","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.02.01.578402","name":"Subcortical origin of nonlinear sound encoding in auditory cortex","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.02.01.578402","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.02.01.578402","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.11.04.621878","name":"Distributed encoding of action-mediated outcome drives consistent population dynamics during goal-directed reaching","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.11.04.621878","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.11.04.621878","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.06.17.598162","name":"Steering From the Rear: Coordination of Central Pattern Generators Underlying Navigation by Ascending Interneurons","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.06.17.598162","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.06.17.598162","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.02.06.579173","name":"Massive perturbation of sound representations by anesthesia in the auditory brainstem","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.02.06.579173","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.02.06.579173","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.03.28.587155","name":"Synaptic function and sensory processing in ZDHHC9-associated neurodevelopmental disorder: a mechanistic account","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.03.28.587155","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.03.28.587155","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.04.09.588702","name":"Computational functions of precisely balanced neuronal assemblies in an olfactory memory network","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.04.09.588702","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.04.09.588702","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.02.25.582012","name":"Evoked Resonant Neural Activity Long-Term Dynamics can be Reproduced by a Computational Model with Vesicle Depletion","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.02.25.582012","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.02.25.582012","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.05.01.538909","name":"Embedding stochastic dynamics of the environment in spontaneous activity by prediction-based plasticity","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.05.01.538909","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.05.01.538909","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.05.23.595522","name":"Automated inference of disease mechanisms in patient-hiPSC-derived neuronal networks","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.05.23.595522","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.05.23.595522","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.07.17.603957","name":"Spike rate inference from mouse spinal cord calcium imaging data","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.07.17.603957","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.07.17.603957","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.11.07.622548","name":"Pathological tau alters head direction signaling and induces spatial disorientation","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.11.07.622548","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.11.07.622548","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.09.13.612841","name":"A systems model of alternating theta sweeps via firing rate adaptation","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.09.13.612841","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.09.13.612841","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.04.22.590506","name":"Accelerated spike-triggered non-negative matrix factorization reveals coordinated ganglion cell subunit mosaics in the primate retina","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.04.22.590506","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.04.22.590506","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1101/2024.01.04.574141","name":"NeoCOMM: A Neocortical Neuroinspired Computational Model for the Reconstruction and Simulation of Epileptiform Events","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.01.04.574141","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.01.04.574141","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.21203/rs.3.rs-4600249/v1","name":"Realistic subject-specific simulation of resting state scalp EEG based on physiological model","source":"preprints","abstract":"Abstract Electroencephalography (EEG) recordings are widely used in neuroscience to identify individual-specific signatures. Understanding the cellular origins of scalp EEG signals and their spatiotemporal changes during resting state (RS) in humans is challenging. The objective of this study was to simulate individual-specific spatiotemporal features of RS EEG and measure the degree of similarity between real and simulated EEG. Using a physiologically grounded whole-brain computational model that simulates interregional cortical circuitry, realistic individual EEG recordings during RS of three healthy subjects were created. The model included interconnected neural mass modules simulating activities of different neuronal subtypes, including pyramidal cells and four types of GABAergic interneurons. High-definition EEG and source localization were used to delineate the cortical extent of alpha and beta-gamma rhythms. To assess the realism of the simulated EEG, we developed a similarity index based on cross-correlation analysis in the frequency domain across different bipolar derivations. Alpha oscillations were produced by strengthening the somatostatin-pyramidal loop in posterior regions, while beta-gamma oscillations were generated by increasing the excitability of parvalbumin-interneurons on pyramidal neurons in anterior regions. The generation of realistic individual RS EEG rhythms represents a significant advance for research fields requiring data augmentation, including brain-computer interfaces and artificial intelligence training.","url":"https://doi.org/10.21203/rs.3.rs-4600249/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4600249/v1","addedAt":"2026-09-01T01:48:24.598Z","updatedAt":"2026-09-01T01:48:26.356Z"},{"id":"doi:10.1016/j.neucom.2026.133111","name":"BKT-DSNN: Communication efficient spiking neural network federated learning based on dynamic model assignment","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2026.133111","authors":["Ziao Qu","Hao Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-20T00:18:23Z","doi":"10.1016/j.neucom.2026.133111","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.209Z"},{"id":"doi:10.1142/s0129065726500139","name":"Spiking Neural Membrane Systems with Multiplexed Neurons for Enhanced Parallel Computing","source":"crossref","abstract":"Spiking neural membrane systems (SNP systems) are distributed parallel computing models inspired by neuronal spike mechanisms. Traditional SNP systems execute rules serially within each neuron, limiting their efficiency. This paper introduces MNSNP systems, a novel variant where neurons can distinguish spike sources and execute multiple rules in parallel at one time step. MNSNP systems maintain global distributed parallelism while integrating local parallelism, significantly enhancing information processing capabilities. Computational completeness is demonstrated, proving MNSNP systems as Turing universal devices for number generation, acceptance, and function computation. Compared to existing models, MNSNP systems require fewer neurons (only 60 for universal computation), showcasing resource efficiency. An application in smoke detection achieves an AUC value of 0.9840, demonstrating practical utility. This work advances SNP systems by introducing multiplexing, paving the way for applications in robotics, feature recognition, and real-time processing.","url":"https://doi.org/10.1142/s0129065726500139","authors":["Liping Wang","Xiyu Liu","Yuzhen Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-30T03:42:45Z","doi":"10.1142/s0129065726500139","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.209Z"},{"id":"doi:10.1109/ijcnn.2010.5596678","name":"Accelerated simulation of spiking neural networks using GPUs","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2010.5596678","authors":["Andreas K. Fidjeland","Murray P. Shanahan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-10-19T18:58:15Z","doi":"10.1109/ijcnn.2010.5596678","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1007/978-3-319-46182-3_2","name":"A Spiking Neural Network for Personalised Modelling of Electrogastrography (EGG)","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-46182-3_2","authors":["Vivienne Breen","Nikola Kasabov","Peng Du","Stefan Calder"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-09-08T05:19:28Z","doi":"10.1007/978-3-319-46182-3_2","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1109/tc.2025.3584201/mm1","name":"STEMS: Spatial-Temporal Mapping for Spiking Neural Networks_supp1-3584201.pdf","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tc.2025.3584201/mm1","authors":["Sherif Eissa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-04T13:50:21Z","doi":"10.1109/tc.2025.3584201/mm1","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.21203/rs.3.rs-1478619/v1","name":"Exact mean-field models for spiking neural networks with adaptation","source":"crossref","abstract":"Abstract Networks of spiking neurons with adaption have been shown to be able to reproduce a wide range of neural activities, including the emergent population bursting and spike synchrony that underpin brain disorders and normal function. Exact mean-field models derived from spiking neural networks are extremely valuable, as such models can be used to determine how individual neuron and network parameters interact to produce macroscopic network behaviour. In the paper, we derive and analyze a set of exact mean-field equations for the neural network with spike frequency adaptation. Specifically, our model is a network of Izhikevich neurons, where each neuron is modeled by a two dimensional system consisting of a quadratic integrate and fire equation plus an equation which implements spike frequency adaptation. Previous work deriving a mean-field model for this type of network, relied on the assumption of sufficiently slow dynamics of the adaptation variable. However, this approximation did not succeed in establishing an exact correspondence between the macroscopic description and the realistic neural network, especially when the adaptation time constant was not large. The challenge lies in how to achieve a closed set of mean-field equations with the inclusion of the mean-field expression of the adaptation variable. We address this problem by using a Lorentzian ansatz combined with the moment closure approach to arrive at a mean-field system in the thermodynamic limit. The resulting macroscopic description is capable of qualitatively and quantitatively describing the collective dynamics of the neural network, including transition between tonic firing and bursting. We extend the approach to a network of two populations of neurons and discuss the accuracy and efficacy of our mean-field approximations by examining all assumptions that are imposed during the derivation. Numerical bifurcation analysis of our mean-field models reveal bifurcations not previously observed in the models, including a novel mechanism for emergence of bursting in the network. We anticipate our results will provide a tractable and reliable tool to investigate the underlying mechanism of brain function and dysfunction from the perspective of computational neuroscience.","url":"https://doi.org/10.21203/rs.3.rs-1478619/v1","authors":["Liang Chen","Sue Ann Campbell"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-07T16:48:19Z","doi":"10.21203/rs.3.rs-1478619/v1","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.5220/0007469400002108","name":"Exploring Deep Spiking Neural Networks for Automated Driving Applications","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0007469400002108","authors":["Sambit Mohapatra","Heinrich Gotzig","Senthil Yogamani","Stefan Milz","Raoul Zöllner"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-15T16:42:35Z","doi":"10.5220/0007469400002108","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1007/978-3-031-72359-9_29","name":"Obtaining Optimal Spiking Neural Network in Sequence Learning via CRNN-SNN Conversion","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-72359-9_29","authors":["Jiahao Su","Kang You","Zekai Xu","Weizhi Xu","Zhezhi He"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-18T12:28:54Z","doi":"10.1007/978-3-031-72359-9_29","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1016/s0893-6080(01)00064-8","name":"Associative memory in networks of spiking neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1016/s0893-6080(01)00064-8","authors":["Friedrich T. Sommer","Thomas Wennekers"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-10-14T18:58:33Z","doi":"10.1016/s0893-6080(01)00064-8","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.21070/ups.11923","name":"B3 Waste Image - Based Classification Using the VGG16 Convolutional Neural Network Model","source":"crossref","abstract":"","url":"https://doi.org/10.21070/ups.11923","authors":["Wahyu Ismanda","Suprianto Suprianto"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-13T04:08:53Z","doi":"10.21070/ups.11923","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.209Z"},{"id":"doi:10.1016/j.ins.2023.119034","name":"A novel parallel merge neural network with streams of spiking neural network and artificial neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.ins.2023.119034","authors":["Jie Yang","Junhong Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-09T13:32:53Z","doi":"10.1016/j.ins.2023.119034","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1101/579706","name":"Simple Framework for Constructing Functional Spiking Recurrent Neural Networks","source":"crossref","abstract":"Abstract Cortical microcircuits exhibit complex recurrent architectures that possess dynamically rich properties. The neurons that make up these microcircuits communicate mainly via discrete spikes, and it is not clear how spikes give rise to dynamics that can be used to perform computationally challenging tasks. In contrast, continuous models of rate-coding neurons can be trained to perform complex tasks. Here, we present a simple framework to construct biologically realistic spiking recurrent neural networks (RNNs) capable of learning a wide range of tasks. Our framework involves training a continuous-variable rate RNN with important biophysical constraints and transferring the learned dynamics and constraints to a spiking RNN in a one-to-one manner. The proposed framework introduces only one additional parameter to establish the equivalence between rate and spiking RNN models. We also study other model parameters related to the rate and spiking networks to optimize the one-to-one mapping. By establishing a close relationship between rate and spiking models, we demonstrate that spiking RNNs could be constructed to achieve similar performance as their counterpart continuous rate networks.","url":"https://doi.org/10.1101/579706","authors":["Robert Kim","Yinghao Li","Terrence J. Sejnowski"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-03-16T03:26:08Z","doi":"10.1101/579706","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1007/s11063-011-9201-1","name":"Spiking Neural P Systems with Weighted Synapses","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11063-011-9201-1","authors":["Linqiang Pan","Xiangxiang Zeng","Xingyi Zhang","Yun Jiang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-12-13T21:17:46Z","doi":"10.1007/s11063-011-9201-1","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1109/ijcnn.2013.6706756","name":"Learning population of spiking neural networks with perturbation of conductances","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2013.6706756","authors":["Piotr Suszynski","Pawel Wawrzynski"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-01-10T20:08:44Z","doi":"10.1109/ijcnn.2013.6706756","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.52202/075280-2764","name":"SEENN: Towards Temporal Spiking Early Exit Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.52202/075280-2764","authors":["Yuhang Li","Tamar Geller","Youngeun Kim","Priyadarshini Panda"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-02T13:18:04Z","doi":"10.52202/075280-2764","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1109/wacv61042.2026.00407","name":"STEG-AIW: Spatio-Temporal Gating and Adaptive-Timestep Inference for Efficient Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/wacv61042.2026.00407","authors":["Gulfam Ahmed Saju","Anton Spirkin","Felipe Marcelino","Yuchou Chang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-05T19:59:32Z","doi":"10.1109/wacv61042.2026.00407","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.209Z"},{"id":"doi:10.1016/j.neucom.2026.134744","name":"Spiking neural ensembles contribute to cue combination during visual causal inference","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2026.134744","authors":["Weisi Liu","Yuncai Yu","Ruihuan Ren","Jiuchang Zhang","Jinping Yuan","Bingjie Wang","Ke Zhu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-07T15:06:50Z","doi":"10.1016/j.neucom.2026.134744","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.209Z"},{"id":"doi:10.1007/978-3-032-15046-2_6","name":"Logistic Real and Complex, Ordinary and Fractional Neural Network Approximation Over Infinite Domains","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-15046-2_6","authors":["George A. Anastassiou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-14T08:42:15Z","doi":"10.1007/978-3-032-15046-2_6","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.209Z"},{"id":"doi:10.2139/ssrn.6864947","name":"Dynamical System Neural Network (DSNN) for hydrological modelling","source":"crossref","abstract":"Dynamical System Neural Networks (DSNN) are time-iterative neural networks,employing neural network components representing real-world system compartments,which can be substituted by process-based components. This study evaluates theidentifiability of DSNN parameters and the capability of DSNN to predict systemvariables, using DSNNs of an Alpine hydrological system, with evapotranspiration, snow,and subsurface water components, trained on streamflow. All combinations of neuralnetwork components and process-based components are evaluated. When training onmodel generated streamflow, the DSNNs reproduce the governing equations andmagnitude of system variables from the model that generated the streamflow. Training onmeasured streamflow gives a good prediction of streamflow (Nash-SutcliYe coeYicient =0.82) and acceptable prediction of other system variables when compared with datafrom an extensively calibrated, detailed, reference model. A semi-distributed setup givesbetter results compared to a lumped setup, except for DSNNs that consist of neuralnetwork components only.","url":"https://doi.org/10.2139/ssrn.6864947","authors":["Derek Karssenberg"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-01T23:37:39Z","doi":"10.2139/ssrn.6864947","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.209Z"},{"id":"doi:10.1117/12.3025405","name":"Photonic spiking neurons and spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3025405","authors":["Dafydd Owen-Newns","Andrew Adair","Dylan Black","Giovanni Donati","Joshua Robertson","Antonio Hurtado"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-20T22:49:50Z","doi":"10.1117/12.3025405","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1016/j.neunet.2025.108500","name":"A physics informed neural network architecture for moving boundary problems in science and engineering","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.108500","authors":["Sanchita Malla","Dietmar Oelz","Sitikantha Roy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-19T04:24:18Z","doi":"10.1016/j.neunet.2025.108500","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.209Z"},{"id":"doi:10.1016/s0893-6080(01)00068-5","name":"From artificial neural networks to spiking neuron populations and back again","source":"crossref","abstract":"","url":"https://doi.org/10.1016/s0893-6080(01)00068-5","authors":["Marc de Kamps","Frank van der Velde"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-10-14T22:58:33Z","doi":"10.1016/s0893-6080(01)00068-5","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1109/icnnb.2005.1614882","name":"Application of Levenberg-Marquardt method to the training of spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnnb.2005.1614882","authors":["S.M. Silva","A.E. Ruano"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-04-28T11:05:46Z","doi":"10.1109/icnnb.2005.1614882","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1109/ijcnn.2013.6707140","name":"Spiking neural networks for financial data prediction","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2013.6707140","authors":["David Reid","Abir Jaafar Hussain","Hissam Tawfik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-01-10T15:08:44Z","doi":"10.1109/ijcnn.2013.6707140","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1007/978-981-95-2525-6_9","name":"Recurrent Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-95-2525-6_9","authors":["Shenghua Gao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-31T07:05:44Z","doi":"10.1007/978-981-95-2525-6_9","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.209Z"},{"id":"doi:10.1162/neco.a.1501","name":"ReBaCCA-ss: Relevance-Balanced Continuum Correlation Analysis With Smoothing and Surrogating for Quantifying Similarity Between Population Spiking Activities","source":"crossref","abstract":"Abstract Quantifying similarity between population spike patterns is essential for understanding how neural dynamics encode information. Traditional approaches, which combine kernel smoothing, principal component analysis, and canonical correlation analysis (CCA), have limitations: smoothing kernel bandwidths are often empirically chosen, CCA maximizes alignment between patterns without considering the variance explained within patterns, and baseline correlations from stochastic spiking are rarely corrected. We introduce ReBaCCA-ss (relevance-balanced continuum correlation analysis with smoothing and surrogating), a novel framework that addresses these challenges through three innovations: (1) balancing alignment and variance explanation via continuum canonical correlation, (2) correcting for noise using surrogate spike trains, and (3) selecting the optimal kernel bandwidth by maximizing the difference between true and surrogate correlations. ReBaCCA-ss is validated on both simulated data and hippocampal recordings from rats performing a delayed nonmatch-to-sample task. It reliably identifies spatiotemporal similarities between spike patterns. Combined with multidimensional scaling, ReBaCCA-ss reveals structured neural representations across trials, events, sessions, and animals, offering a powerful tool for neural population analysis.","url":"https://doi.org/10.1162/neco.a.1501","authors":["Xiang Zhang","Chenlin Xu","Zhouxiao Lu","Haonan Wang","Dong Song"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-05T17:50:07Z","doi":"10.1162/neco.a.1501","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.209Z"},{"id":"doi:10.1007/s43926-026-00473-w","name":"Event-based object detection from spiking neural networks to IoT edge deployment: a systematic review","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s43926-026-00473-w","authors":["Mohamad Yazan Sadoun","Sarah Sharif","Yaser Mike Banad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-13T14:03:21Z","doi":"10.1007/s43926-026-00473-w","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.209Z"},{"id":"doi:10.1007/978-981-95-5795-0_4","name":"Accelerating Computation for Scalable Graph Neural Network Training","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-95-5795-0_4","authors":["Jingzhi Fang","Zhiyuan Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-26T12:44:20Z","doi":"10.1007/978-981-95-5795-0_4","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.209Z"},{"id":"doi:10.1016/j.mejo.2025.106916","name":"A memristor-based spiking neural network circuit with hardware-optimized unsupervised STDP","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.mejo.2025.106916","authors":["Ouwen Zhang","Dainan Zhang","Junjie Wang","Shuang Liu","Hao Jiang","Zhongrui Wang","Xiaojuan Qi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-15T16:31:32Z","doi":"10.1016/j.mejo.2025.106916","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.209Z"},{"id":"doi:10.1007/978-981-95-4875-0_28","name":"Spiking Neural Network-Based Signal Classification on Adversarial Example and Signal with Common Noise","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-95-4875-0_28","authors":["Ping Ye","Yunzhe Tian","Xiangyu Shi","Xiaoshu Cui","Yaunwan Chen","Yanfeng Gu","Qiong Li","Jiqiang Liu","Wenjia Niu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-02T01:22:29Z","doi":"10.1007/978-981-95-4875-0_28","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.209Z"},{"id":"doi:10.1162/089976605774320593","name":"Information Geometry of Interspike Intervals in Spiking Neurons","source":"crossref","abstract":"An information geometrical method is developed for characterizing or classifying neurons in cortical areas, whose spike rates fluctuate in time. Under the assumption that the interspike intervals of a spike sequence of a neuron obey a gamma process with a time-variant spike rate and a fixed shape parameter, we formulate the problem of characterization as a semiparametric statistical estimation, where the spike rate is a nuisance parameter. We derive optimal criteria from the information geometrical viewpoint when certain assumptions are added to the formulation, and we show that some existing measures, such as the coefficient of variation and the local variation, are expressed as estimators of certain functions under the same assumptions.","url":"https://doi.org/10.1162/089976605774320593","authors":["Kazushi Ikeda"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-09-28T20:53:50Z","doi":"10.1162/089976605774320593","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1016/j.neucom.2026.133541","name":"Time series analysis of spiking neural systems via transfer entropy and directed persistent homology","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2026.133541","authors":["Dylan Peek","Siddharth Pritam","Matthew P. Skerritt","Stephan Chalup"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-01T08:02:21Z","doi":"10.1016/j.neucom.2026.133541","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.209Z"},{"id":"doi:10.31224/4781","name":"Explainability Techniques and Training Strategies for Spiking Neural Networks","source":"crossref","abstract":"Spiking Neural Networks (SNNs) have emerged as a promising class of biologically inspired models that process information through discrete spike events and temporal dynamics, closely emulating neural computation in the brain. Their inherent advantages include energy-efficient processing, event-driven operation, and natural suitability for neuromorphic hardware, positioning them as strong candidates for next-generation artificial intelligence systems. However, despite significant advancements, challenges remain in training SNNs effectively, understanding their internal decision-making processes, and deploying them in practical applications. This survey provides a comprehensive and detailed overview of the state-of-the-art in explainable and effective Spiking Neural Networks, addressing fundamental principles, training algorithms, neuromorphic hardware integration, and interpretability methodologies. We systematically explore how recent developments in surrogate gradient techniques, biologically plausible learning rules, and hybrid architectures have improved the accuracy and efficiency of SNNs, while maintaining or enhancing model transparency. Furthermore, we review a broad spectrum of explainability approaches specifically tailored to the temporal and event-driven nature of SNNs, including spike visualization, saliency mapping, rule extraction, and biologically grounded interpretability frameworks. Key application domains are surveyed, highlighting successes and challenges in neuromorphic vision, brain-machine interfaces, robotics, and biomedical signal processing, where the combination of explainability and effectiveness is critical for trustworthiness and deployment. Finally, we discuss open challenges related to training complexity, standardization of interpretability metrics, hardware-software co-design, and the balance between biological realism and engineering practicality, proposing future research directions to overcome these barriers. By synthesizing current knowledge and identifying promising avenues, this survey aims to guide researchers and practitioners in advancing the development of Spiking Neural Networks that are not only high-performing but also transparent, interpretable, and suitable for real-world applications.","url":"https://doi.org/10.31224/4781","authors":["Wei Zhang","Lina Chen","Tao Huang","Heng Xue"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-06T00:14:23Z","doi":"10.31224/4781","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1109/tnnls.2019.2941506","name":"Parameter Optimization and Learning in a Spiking Neural Network for UAV Obstacle Avoidance Targeting Neuromorphic Processors","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnnls.2019.2941506","authors":["Llewyn Salt","David Howard","Giacomo Indiveri","Yulia Sandamirskaya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-10-14T23:14:01Z","doi":"10.1109/tnnls.2019.2941506","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.70675/1aa2c5b8z3a7bz4b40z91c5z9063afec1f1c","name":"Theoretical framework for Time-To-First-Spike coding in Spiking Neural Networks","source":"crossref","abstract":"Un modèle mathématique unificateur pour le codage par temps du premier spike dans les réseaux de neurones à impulsions Au sein des réseaux de neurones impulsionnels, le codage \"Time-To-First-Spike\" (TTFS) utilise la latence du premier spike pour véhiculer de l'information. De nombreuses études ont démontré que ce type de codage peut transmettre beaucoup d'information rapidement. En effet, seul un spike par neurone est requis, ce qui permet d'encoder rapidement de l'information en exploitant la précision temporelle de ce spike, tout en consommant peu d'énergie. Dans ce travail de recherche théorique, nous présentons un nouveau cadre mathématique unificateur qui permet la comparaison rigoureuse d'un grand nombre de codes TTFS existants. Nous proposons également un nouveau code, integer-based Ranked NoM, et démontrons que son pouvoir discriminatif est supérieur à celui de tous les autres codes proposés jusqu'ici. Dans une première proposition appelée rank-order coding (ROC), les neurones sont activés au maximum quand les spikes arrivent dans l'ordre des poids synaptiques décroissants, grâce à un mécanisme de \"shunting inhibition\" qui désensibilise progressivement le neurone à mesure que les spikes arrivent. Dans une autre proposition appelée \" N -of- M \" coding, seuls les N premiers spikes de M neurones sont propagés, et ces motifs de premiers spikes sont déchiffrés par des neurones en aval qui utilisent des poids homogènes et pas de désensibilisation. En conséquence, l'ordre parmi les premiers spike n'importe pas. Nous proposons un nouveau codage, \"Ranked NoM\" (R-NoM), qui combine des caractéristiques de ROC et NoM: seuls les N premiers spikes sont propagés, mais leur ordre est déchiffré par les neurones en aval grâce à des poids inhomogènes et une désensibilisation linéaire. Le cadre mathématique unificateur permet de comparer ces trois codes en terme de \"discriminabilité\", qui représente dans quel mesure un neurone répond plus fortement à son motif préféré qu'à d'autres motifs aléatoires. Cette discriminabilité est bien supérieure pour R-NoM que pour les autres codes, et ce particulièrement dans la première phase des réponses. Nous argumentons aussi que R-NoM est bien plus adapté aux accélérateurs matériels que le code ROC original, bien que pas autant que NoM, qui n'utilise que des synapses binaires.","url":"https://doi.org/10.70675/1aa2c5b8z3a7bz4b40z91c5z9063afec1f1c","authors":["Lina del Pilar Bonilla Camelo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-07T14:50:05Z","doi":"10.70675/1aa2c5b8z3a7bz4b40z91c5z9063afec1f1c","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1109/access.2026.3651795","name":"SGSPose: Neuromorphic-Geometric 6D Pose Estimation Through Spiking Graph Neural Networks and SE(3)-Equivariant Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/access.2026.3651795","authors":["Janhavi Chaurasia","Eshaan Rithesh Adyanthaya","Manas Ranjan Prusty"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-12T22:02:28Z","doi":"10.1109/access.2026.3651795","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.209Z"},{"id":"doi:10.5220/0003682103810384","name":"BIOLOGICALLY INSPIRED EDGE DETECTION USING SPIKING NEURAL NETWORKS AND HEXAGONAL IMAGES","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0003682103810384","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-01-04T08:45:19Z","doi":"10.5220/0003682103810384","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1016/j.neunet.2009.08.010","name":"To spike or not to spike: A probabilistic spiking neuron model","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2009.08.010","authors":["Nikola Kasabov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-09-07T08:25:29Z","doi":"10.1016/j.neunet.2009.08.010","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1109/neuront71829.2026.11651376","name":"Systematization of Neural Network-Based Methods for Feature Selection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/neuront71829.2026.11651376","authors":["Artem D. Cheremuhin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-18T19:11:40Z","doi":"10.1109/neuront71829.2026.11651376","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.209Z"},{"id":"doi:10.1016/j.neucom.2025.132406","name":"STESNN: Spatio-temporal enhancement spiking neural networks for epilepsy detection","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2025.132406","authors":["Shunchang Su","Xianghong Lin","Xiangwen Wang","Liping Wei"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-19T07:49:57Z","doi":"10.1016/j.neucom.2025.132406","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.209Z"},{"id":"doi:10.1109/ijcnn64981.2025.11228267","name":"Balanced and Efficient Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn64981.2025.11228267","authors":["Tim Stadtmann","Janek Paeßens","Tobias Gemmeke"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T18:46:15Z","doi":"10.1109/ijcnn64981.2025.11228267","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1016/j.neunet.2024.106985","name":"Stabilizing sequence learning in stochastic spiking networks with GABA-Modulated STDP","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106985","authors":["Marius Vieth","Jochen Triesch"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-07T16:19:50Z","doi":"10.1016/j.neunet.2024.106985","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1016/j.cageo.2026.106147","name":"A logistic gradient autonomous optimization numerical spiking neural membrane system with adaptive multi-mutation for sandstone pore segmentation","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.cageo.2026.106147","authors":["Zhuo Luo","Kai Li","Shiji Dai","Li Su","Changhui Yan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-06T07:23:58Z","doi":"10.1016/j.cageo.2026.106147","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.209Z"},{"id":"doi:10.5220/0007469405480555","name":"Exploring Deep Spiking Neural Networks for Automated Driving Applications","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0007469405480555","authors":["Sambit Mohapatra","Heinrich Gotzig","Senthil Yogamani","Stefan Milz","Raoul Zöllner"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-03-15T11:03:30Z","doi":"10.5220/0007469405480555","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1002/9781394381609.index","name":"Index","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9781394381609.index","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-28T07:11:02Z","doi":"10.1002/9781394381609.index","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1016/s0893-6080(02)00034-5","name":"A spiking neuron model: applications and learning","source":"crossref","abstract":"","url":"https://doi.org/10.1016/s0893-6080(02)00034-5","authors":["Chris Christodoulou","Guido Bugmann","Trevor G Clarkson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-10-11T21:02:29Z","doi":"10.1016/s0893-6080(02)00034-5","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1088/1361-6501/ae33dc","name":"An intelligent fault diagnosis method based on data enhancement by multi-information driven spiking generative adversarial network","source":"crossref","abstract":"Abstract The machine always operates in a normal state. Therefore, the data-driven intelligent fault diagnosis methods still have more problems, such as small samples and overall imbalance in the era of big data. The main method to address these problems is oversampling. However, the common oversampling method, including data scaling, noise addition, and even some data-generating methods, contains similar feature information. This feature information originates from a single confirmed data, such as a single direction time-domain vibration data, which makes the new data lack multi-scale and multi-perspective feature representations. Thus, this paper proposes a multi-information driven spiking generative adversarial network (MI-SpikingGAN). Specifically, its ability to learn the instantaneous and cumulative temporal features of data can be enhanced by the spiking neurons. Both the multi-domain inconsistency and peak deviation of generated data are mitigated by introducing low-frequency wrapping loss and feature-matching loss into the generator. Moreover, the feature-level data fusion is performed by using a global multi-head channel attention mechanism on the supporting data. These fused data are used to guide the discriminator in identifying as complementary, which avoids the shortcomings of single-modal input. This paper validates its performance in some opening datasets, and the experiment results indicate that the accuracy of the classifier, which was trained with the data enhanced by the MI-SpikingGAN, reaches 98.83% and is 9.11% higher than that of softmax trained by the original data. Compared to the accuracy of other methods, it is at most 6.16% and at least 2.7% higher.","url":"https://doi.org/10.1088/1361-6501/ae33dc","authors":["Zhaolin Guo","Yanming Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-06T22:49:51Z","doi":"10.1088/1361-6501/ae33dc","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.209Z"},{"id":"doi:10.31219/osf.io/w2ztm","name":"Contrastive-Signal-Dependent Plasticity: Forward-Forward Learning of Spiking Neural Systems","source":"crossref","abstract":"We develop a neuro-mimetic architecture, composed of spiking neuronal units, here individual layers of neurons operate in parallel and adapt their synaptic efficacies without the use of feedback pathways. Specifically, we propose an event-based generalization of forward-forward learning, which we call contrastive-signal-dependent plasticity (CSDP), for a spiking neural system that iteratively processes sensory input over a stimulus window. The dynamics that underwrite this recurrent circuit entail computing the membrane potential of each processing element, in each layer, as a function of local bottom-up, top-down, and lateral signals, facilitating a dynamic, layer-wise parallel form of neural computation. Unlike other models, such as spiking predictive coding, that rely on feedback synapses to adjust neural electrical activity, our model operates purely online and forward in time, offering a promising way to learn distributed representations of sensory data patterns, with and without labeled context information. Notably, our experimental results on several pattern datasets demonstrate that the CSDP process works well for training a dynamic recurrent spiking network capable of both classification and reconstruction.","url":"https://doi.org/10.31219/osf.io/w2ztm","authors":["Alexander G. Ororbia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-31T01:01:00Z","doi":"10.31219/osf.io/w2ztm","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1162/neco_a_01379","name":"Training Spiking Neural Networks in the Strong Coupling Regime","source":"crossref","abstract":"Abstract Recurrent neural networks trained to perform complex tasks can provide insight into the dynamic mechanism that underlies computations performed by cortical circuits. However, due to a large number of unconstrained synaptic connections, the recurrent connectivity that emerges from network training may not be biologically plausible. Therefore, it remains unknown if and how biological neural circuits implement dynamic mechanisms proposed by the models. To narrow this gap, we developed a training scheme that, in addition to achieving learning goals, respects the structural and dynamic properties of a standard cortical circuit model: strongly coupled excitatory-inhibitory spiking neural networks. By preserving the strong mean excitatory and inhibitory coupling of initial networks, we found that most of trained synapses obeyed Dale's law without additional constraints, exhibited large trial-to-trial spiking variability, and operated in inhibition-stabilized regime. We derived analytical estimates on how training and network parameters constrained the changes in mean synaptic strength during training. Our results demonstrate that training recurrent neural networks subject to strong coupling constraints can result in connectivity structure and dynamic regime relevant to cortical circuits.","url":"https://doi.org/10.1162/neco_a_01379","authors":["Christopher M. Kim","Carson C. Chow"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-04-14T20:35:38Z","doi":"10.1162/neco_a_01379","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.24135/iconip20","name":"The Potential of Spiking Neural Networks in Predicting Earthquakes in New Zealand","source":"crossref","abstract":"This study investigates the use of Spiking Neural Networks (SNNs) in earthquake prediction, focusing on New Zealand, a seismically active region. Traditional earthquake prediction methods struggle with accuracy and real-time warning capabilities. SNNs, inspired by the brain’s biological processes, excel at handling dynamic time-series data, making them a promising tool for tasks involving spatio-temporal patterns such as seismic waveforms. Utilizing the NeuCube platform([1]), we processed seismic data from 56 stations across New Zealand in 2022. Our model achieved an accuracy increase from 38% to 70% as the seismic event approached, highlighting its potential for real-time earthquake monitoring. Although further optimization is required, this research demonstrates SNNs' potential in improving early earthquake warning systems. Future work will focus on refining the model's architecture and incorporating multimodal data to enhance prediction accuracy and applicability.","url":"https://doi.org/10.24135/iconip20","authors":["Zhaoxin Wang","Maryam Doborjeh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-17T20:44:31Z","doi":"10.24135/iconip20","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1109/icccis48478.2019.8974507","name":"Spiking Neural Networks Vs Convolutional Neural Networks for Supervised Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icccis48478.2019.8974507","authors":["Sahil Lamba","Rishab Lamba"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-30T23:42:47Z","doi":"10.1109/icccis48478.2019.8974507","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1109/access.2023.3269598","name":"On-FPGA Spiking Neural Networks for End-to-End Neural Decoding","source":"crossref","abstract":"","url":"https://doi.org/10.1109/access.2023.3269598","authors":["Gianluca Leone","Luigi Raffo","Paolo Meloni"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-24T18:31:53Z","doi":"10.1109/access.2023.3269598","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.2139/ssrn.5339085","name":"Energy-Efficient and Fault-Tolerant Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5339085","authors":["Junyu Li","Meiling Zhao","Chen Gao","Heng Xue"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-17T15:45:19Z","doi":"10.2139/ssrn.5339085","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1016/j.eswa.2025.129934","name":"Relevance-based adaptive differential private spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.eswa.2025.129934","authors":["Junxiu Liu","Xiwen Luo","Qiang Fu","Yuling Luo","Sheng Qin","Xue Ouyang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-04T01:11:44Z","doi":"10.1016/j.eswa.2025.129934","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.209Z"},{"id":"doi:10.1145/3797248.3816057","name":"SpikeFed: Federated Training of Spiking Neural Networks for Event-Based Vision","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3797248.3816057","authors":["Hasti Zanganeh","Lydia Dede Obeng","Hariharan Ramesh","James Seekings","Jyotikrishna Dass","Ramtin Zand"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-19T10:46:08Z","doi":"10.1145/3797248.3816057","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.209Z"},{"id":"doi:10.1109/icecs.2004.1399650","name":"A winner-take-all spiking network with spiking inputs","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icecs.2004.1399650","authors":["M. Oster","Shih-Chii Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-03-31T13:26:51Z","doi":"10.1109/icecs.2004.1399650","addedAt":"2026-09-01T01:48:25.209Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1007/s10994-025-06982-z","name":"S2TE: Staged Scale-Free Topology Evolution for Sparse Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s10994-025-06982-z","authors":["Zaipeng Xie","Wei Zhu","Peixin Li","Haotian Ding","WenZhan Song"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-03T09:22:43Z","doi":"10.1007/s10994-025-06982-z","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.1002/pat.70564","name":"Prediction and Optimization of Mechanical Properties of Water Hyacinth Fiber‐Reinforced Polymer Composites Using Spiking Neural Networks","source":"crossref","abstract":"ABSTRACT The research examines a spike neural networks (SNNs) model that uses trust region policy optimization (TRPO) to predict the mechanical properties of water hyacinth fiber‐reinforced composites, focusing specifically on their tensile and compressive strength values. The lightweight and widespread availability of biodegradable water hyacinth makes it an attractive sustainable material for use as a reinforcing component. We collected two datasets from the existing experimental literature. Database 1 contains 420 compressive strength samples (SNN1) and Database 2 contains 185 tensile strength samples (SNN2). The input properties we considered were fiber volume fraction, matrix composition, and curing conditions. Our methodology included normalizing the data and using a diffusion matrix to analyze feature relationships and we used TRPO for training purposes to achieve better stability in convergence. Our regression analysis revealed an impressive fit, with R 2 values soaring above 0.97. We observed slopes ranging from 0.96 to 0.97 for SNN1, and between 0.85 and 0.88 for SNN2, along with prediction errors staying below 0.5 MPa and 0.01 MPa, respectively. The SNN‐TRPO system has proven to be a powerful tool for predictive modeling and optimizing parameters, paving the way for the production of eco‐friendly and good‐performance composite material.","url":"https://doi.org/10.1002/pat.70564","authors":["Rathinam Maruthalingam Asha","Ranganathan Balaraman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-09T05:01:48Z","doi":"10.1002/pat.70564","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.1109/iscas66217.2026.11562212","name":"An FPGA-Based SoC Architecture with a RISC-V Controller for Energy-Efficient Temporal-Coding Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas66217.2026.11562212","authors":["Mohammad Javad Sekonji","Ali Mahani","Maryam Mirsadeghi","Mahdi Taheri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-18T20:06:41Z","doi":"10.1109/iscas66217.2026.11562212","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.1007/978-3-032-20272-7_6","name":"Unsupervised Signal Decomposition and Tracking Using Hyperdimensional Computing and Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-20272-7_6","authors":["Ianislav Trendafilov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-09T22:36:16Z","doi":"10.1007/978-3-032-20272-7_6","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.1007/978-3-031-14903-0_2","name":"DNM-SNN: Spiking Neural Network Based on Dual Network Model","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-14903-0_2","authors":["Zhen Cao","Hongwei Zhang","Qian Wang","Chuanfeng Ma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-18T23:03:00Z","doi":"10.1007/978-3-031-14903-0_2","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1080/02522667.2020.1723939","name":"Spiking neural network based scrambled watermark hiding in low-frequency region of digital image","source":"crossref","abstract":"","url":"https://doi.org/10.1080/02522667.2020.1723939","authors":["Sunesh Malik","R. Rama Kishore"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-04-29T04:02:32Z","doi":"10.1080/02522667.2020.1723939","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1007/978-3-642-39678-6_2","name":"Fast Wavelet Transform Based on Spiking Neural Network for Visual Images","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-39678-6_2","authors":["Zhenmin Zhang","Qingxiang Wu","Zhiqiang Zhuo","Xiaowei Wang","Liuping Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-07-05T07:39:23Z","doi":"10.1007/978-3-642-39678-6_2","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1109/aicas54282.2022.9869943","name":"Spiking Neural Network based Real-time Radar Gesture Recognition Live Demonstration","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aicas54282.2022.9869943","authors":["Jiaxin Huang","Pascal Gerhards","Felix Kreutz","Bernhard Vogginger","Florian Kelber","Daniel Scholz","Klaus Knobloch","Christian Georg Mayr"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-05T20:21:42Z","doi":"10.1109/aicas54282.2022.9869943","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1109/icassp49660.2025.10889468","name":"Two-Stream Spiking Neural Network for Event-based Action Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icassp49660.2025.10889468","authors":["Shuang Lian","Qianhui Liu","Ziling Wang","Jia Su","Zhibin Zuo","Yi Zhang","Rui Yan","Huajin Tang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-12T17:15:19Z","doi":"10.1109/icassp49660.2025.10889468","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1162/0899766054026684","name":"Movement Generation with Circuits of Spiking Neurons","source":"crossref","abstract":"How can complex movements that take hundreds of milliseconds be generated by stereotypical neural microcircuits consisting of spiking neurons with a much faster dynamics? We show that linear readouts from generic neural microcircuit models can be trained to generate basic arm movements. Such movement generation is independent of the arm model used and the type of feedback that the circuit receives. We demonstrate this by considering two different models of a two-jointed arm, a standard model from robotics and a standard model from biology, that each generates different kinds of feedback. Feedback that arrives with biologically realistic delays of 50 to 280 ms turns out to give rise to the best performance. If a feedback with such desirable delay is not available, the neural microcircuit model also achieves good performance if it uses internally generated estimates of such feedback. Existing methods for movement generation in robotics that take the particular dynamics of sensors and actuators into account (embodiment of motor systems) are taken one step further with this approach, which provides methods for also using the embodiment of motion generation circuitry, that is, the inherent dynamics and spatial structure of neural circuits, for the generation of movement.","url":"https://doi.org/10.1162/0899766054026684","authors":["Prashant Joshi","Wolfgang Maass"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-05-31T23:28:36Z","doi":"10.1162/0899766054026684","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1101/2022.06.24.497562","name":"Learning to learn online with neuromodulated synaptic plasticity in spiking neural networks","source":"crossref","abstract":"We propose that in order to harness our understanding of neuroscience toward machine learning, we must first have powerful tools for training brain-like models of learning. Although substantial progress has been made toward understanding the dynamics of learning in the brain, neuroscience-derived models of learning have yet to demonstrate the same performance capabilities as methods in deep learning such as gradient descent. Inspired by the successes of machine learning using gradient descent, we demonstrate that models of neuromodulated synaptic plasticity from neuroscience can be trained in Spiking Neural Networks (SNNs) with a framework of learning to learn through gradient descent to address challenging online learning problems. This framework opens a new path toward developing neuroscience inspired online learning algorithms.","url":"https://doi.org/10.1101/2022.06.24.497562","authors":["Samuel Schmidgall","Joe Hays"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-28T21:55:11Z","doi":"10.1101/2022.06.24.497562","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1109/icce-taiwan71481.2026.11652425","name":"Self-Adaptive Leakage Mechanism in Spiking Neural Networks Using Inter-Spike Interval Modulation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icce-taiwan71481.2026.11652425","authors":["Chu Yu","Hong-Sheng Chen","Chi-Wang Chang","Mao-Huan Huang","Kai-Hsiang Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-24T19:12:36Z","doi":"10.1109/icce-taiwan71481.2026.11652425","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.1016/j.jde.2020.08.001","name":"Exponential stability of the stationary distribution of a mean field of spiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.jde.2020.08.001","authors":["Audric Drogoul","Romain Veltz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-21T07:45:41Z","doi":"10.1016/j.jde.2020.08.001","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1016/j.icte.2025.07.006","name":"FTP: Filtered Temporal-Population for time series encoding in Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.icte.2025.07.006","authors":["Hyunwon Lee","Won-Seok Hong","Kwon Hong","Hyun-Soo Choi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-30T15:18:30Z","doi":"10.1016/j.icte.2025.07.006","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1016/j.knosys.2024.112039","name":"Optimizing energy-efficient cluster head selection in wireless sensor networks using a binarized spiking neural network and honey badger algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.knosys.2024.112039","authors":["Allan J Wilson","Kiran W．S","A.S. Radhamani","A. Pon Bharathi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-12T21:22:30Z","doi":"10.1016/j.knosys.2024.112039","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1162/neco_a_00139","name":"Spiking Neurons and the First Passage Problem","source":"crossref","abstract":"We derive a model of a neuron’s interspike interval probability density through analysis of the first passage problem. The fit of our expression to retinal ganglion cell laboratory data extracts three physiologically relevant parameters, with which our model yields input-output features that conform to laboratory results. Preliminary analysis suggests that under common circumstances, local circuitry readjusts these parameters with changes in firing rate and so endeavors to faithfully replicate an input signal. Further results suggest that the so-called principle of sloppy workmanship also plays a role in evolution’s choice of these parameters.","url":"https://doi.org/10.1162/neco_a_00139","authors":["Lawrence Sirovich","Bruce Knight"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-04-15T04:44:11Z","doi":"10.1162/neco_a_00139","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1002/9781394381609.ch01","name":"Introduction","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9781394381609.ch01","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-28T07:11:02Z","doi":"10.1002/9781394381609.ch01","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1016/j.jphysparis.2009.11.013","name":"Self-control with spiking and non-spiking neural networks playing games","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.jphysparis.2009.11.013","authors":["Chris Christodoulou","Gaye Banfield","Aristodemos Cleanthous"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-11-27T21:51:46Z","doi":"10.1016/j.jphysparis.2009.11.013","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.23919/date69613.2026.11539562","name":"Fault-tolerance Mapping of Spiking Neural Networks to RRAM-based Neuromorphic Hardware","source":"crossref","abstract":"","url":"https://doi.org/10.23919/date69613.2026.11539562","authors":["Yuqing Xiong","Cao Xiao","Zhijie Yang","Lei Wang","Mengying Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-04T19:53:10Z","doi":"10.23919/date69613.2026.11539562","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.1162/neco_a_00665","name":"Spiking Neural P Systems with a Generalized Use of Rules","source":"crossref","abstract":"Spiking neural P systems (SN P systems) are a class of distributed parallel computing devices inspired by spiking neurons, where the spiking rules are usually used in a sequential way (an applicable rule is applied one time at a step) or an exhaustive way (an applicable rule is applied as many times as possible at a step). In this letter, we consider a generalized way of using spiking rules by “combining” the sequential way and the exhaustive way: if a rule is used at some step, then at that step, it can be applied any possible number of times, nondeterministically chosen. The computational power of SN P systems with a generalized use of rules is investigated. Specifically, we prove that SN P systems with a generalized use of rules consisting of one neuron can characterize finite sets of numbers. If the systems consist of two neurons, then the computational power of such systems can be greatly improved, but not beyond generating semilinear sets of numbers. SN P systems with a generalized use of rules consisting of three neurons are proved to generate at least a non-semilinear set of numbers. In the case of allowing enough neurons, SN P systems with a generalized use of rules are computationally complete. These results show that the number of neurons is crucial for SN P systems with a generalized use of rules to achieve a desired computational power.","url":"https://doi.org/10.1162/neco_a_00665","authors":["Xingyi Zhang","Bangju Wang","Linqiang Pan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-08-23T02:29:02Z","doi":"10.1162/neco_a_00665","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1109/fuzz-ieee55066.2022.9882864","name":"A multiple spiking neural network architecture based on fuzzy intervals for anomaly detection: a case study of rail defects","source":"crossref","abstract":"","url":"https://doi.org/10.1109/fuzz-ieee55066.2022.9882864","authors":["Wassamon Phusakulkajorn","Jurjen Hendriks","Jan Moraal","Rolf Dollevoet","Zili Li","Alfredo Nunez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-14T19:39:59Z","doi":"10.1109/fuzz-ieee55066.2022.9882864","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1007/s11432-020-3040-1","name":"A modified supervised learning rule for training a photonic spiking neural network to recognize digital patterns","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11432-020-3040-1","authors":["Yahui Zhang","Shuiying Xiang","Xingxing Guo","Aijun Wen","Yue Hao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-01-22T15:27:47Z","doi":"10.1007/s11432-020-3040-1","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1109/acai63924.2024.10899489","name":"A Multi-Angle Encoding Spiking Convolutional Neural Network for Remote Sensing Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/acai63924.2024.10899489","authors":["Xiang Li","Jingwei Zhang","Peng Wang","Yanrong Wang","Meng Zhang","Feng Xu","An Jing","Lizi Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-03T18:27:20Z","doi":"10.1109/acai63924.2024.10899489","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.2495/iccts20140531","name":"Building a self-learning memristor-based spiking neural network on handwritten digit recognition and orientation extraction","source":"crossref","abstract":"","url":"https://doi.org/10.2495/iccts20140531","authors":["Mingli He","Honelei Gao","Quansheng Ren","Jianye Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-10-07T05:59:21Z","doi":"10.2495/iccts20140531","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1109/csis-iac63491.2024.10919458","name":"Intelligent Compound Control Based on Spiking Neural Network for Hex-Rotor Unmanned Aerial Vehicle","source":"crossref","abstract":"","url":"https://doi.org/10.1109/csis-iac63491.2024.10919458","authors":["Cheng Peng","Guanyu Qiao","Bing Ge"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-19T18:05:37Z","doi":"10.1109/csis-iac63491.2024.10919458","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1109/icra.2018.8460482","name":"End to End Learning of Spiking Neural Network Based on R-STDP for a Lane Keeping Vehicle","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icra.2018.8460482","authors":["Zhenshan Bing","Claus Meschede","Kai Huang","Guang Chen","Florian Rohrbein","Mahmoud Akl","Alois Knoll"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-09-21T22:28:03Z","doi":"10.1109/icra.2018.8460482","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1109/ipccc59868.2024.10850123","name":"The Robustness of Spiking Neural Networks in Communication and its Application towards Network Efficiency in Federated Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ipccc59868.2024.10850123","authors":["Manh V. Nguyen","Liang Zhao","Bobin Deng","William Severa","Honghui Xu","Shaoen Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-27T18:37:48Z","doi":"10.1109/ipccc59868.2024.10850123","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.771Z"},{"id":"doi:10.1007/s42600-023-00324-5","name":"Correction to: Deep convolutional spiking neural network fostered automatic detection and classification of breast cancer from mammography images","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s42600-023-00324-5","authors":["T. Senthil Prakash","G. Kannan","Salini Prabhakaran","Bhagirath Parshuram Prajapati"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-30T08:02:28Z","doi":"10.1007/s42600-023-00324-5","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1111/ejn.13712","name":"The effects of dynamical synapses on firing rate activity: a spiking neural network model","source":"crossref","abstract":"Abstract Accumulating evidence relates the fine‐tuning of synaptic maturation and regulation of neural network activity to several key factors, including GABA A signaling and a lateral spread length between neighboring neurons (i.e., local connectivity). Furthermore, a number of studies consider short‐term synaptic plasticity ( STP ) as an essential element in the instant modification of synaptic efficacy in the neuronal network and in modulating responses to sustained ranges of external Poisson input frequency ( IF ). Nevertheless, evaluating the firing activity in response to the dynamical interaction between STP (triggered by ranges of IF ) and these key parameters in vitro remains elusive. Therefore, we designed a spiking neural network ( SNN ) model in which we incorporated the following parameters: local density of arbor essences and a lateral spread length between neighboring neurons. We also created several network scenarios based on these key parameters. Then, we implemented two classes of STP : (1) short‐term synaptic depression ( STD ) and (2) short‐term synaptic facilitation ( STF ). Each class has two differential forms based on the parametric value of its synaptic time constant (either for depressing or facilitating synapses). Lastly, we compared the neural firing responses before and after the treatment with STP . We found that dynamical synapses ( STP ) have a critical differential role on evaluating and modulating the firing rate activity in each network scenario. Moreover, we investigated the impact of changing the balance between excitation (E) and inhibition (I) on stabilizing this firing activity.","url":"https://doi.org/10.1111/ejn.13712","authors":["Radwa Khalil","Marie Z. Moftah","Ahmed A. Moustafa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-09-18T14:30:22Z","doi":"10.1111/ejn.13712","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1007/s10916-018-1049-8","name":"Developing Charcot–Marie–Tooth Disease Recognition System Using Bacterial Foraging Optimization Algorithm Based Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s10916-018-1049-8","authors":["Abdulaziz Abdullah Al-Kheraif","Mohamed Hashem","Mohammed Sayed S. Al Esawy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-09-10T04:59:33Z","doi":"10.1007/s10916-018-1049-8","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1007/s12667-023-00607-x","name":"Wind speed forecasting at wind farm locations with an unique hybrid PSO-ALO based modified spiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s12667-023-00607-x","authors":["Vinoth kumar Thangaraj","Deepa Subramaniam Nachimuthu","Vijay Amirtha Raj Francis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-07T15:01:47Z","doi":"10.1007/s12667-023-00607-x","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.32604/cmc.2026.078314","name":"DGRDet: Dynamic Gaussian Receptive Field Encoding-Based Spiking Neural Networks for Remote Sensing Object Detection","source":"crossref","abstract":"","url":"https://doi.org/10.32604/cmc.2026.078314","authors":["Li Chen","Fan Zhang","Guangwei Xie","Yanzhao Gao","Xiaofeng Qi","Mingqian Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-09T08:30:38Z","doi":"10.32604/cmc.2026.078314","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.1162/neco_a_00790","name":"Learning Spatiotemporally Encoded Pattern Transformations in Structured Spiking Neural Networks","source":"crossref","abstract":"Information encoding in the nervous system is supported through the precise spike timings of neurons; however, an understanding of the underlying processes by which such representations are formed in the first place remains an open question. Here we examine how multilayered networks of spiking neurons can learn to encode for input patterns using a fully temporal coding scheme. To this end, we introduce a new supervised learning rule, MultilayerSpiker, that can train spiking networks containing hidden layer neurons to perform transformations between spatiotemporal input and output spike patterns. The performance of the proposed learning rule is demonstrated in terms of the number of pattern mappings it can learn, the complexity of network structures it can be used on, and its classification accuracy when using multispike-based encodings. In particular, the learning rule displays robustness against input noise and can generalize well on an example data set. Our approach contributes to both a systematic understanding of how computations might take place in the nervous system and a learning rule that displays strong technical capability.","url":"https://doi.org/10.1162/neco_a_00790","authors":["Brian Gardner","Ioana Sporea","André Grüning"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-11-24T16:36:29Z","doi":"10.1162/neco_a_00790","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.3103/s1060992x15020095","name":"Comparison of learning methods for spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.3103/s1060992x15020095","authors":["K. Kukin","A. Sboev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-07-06T03:48:07Z","doi":"10.3103/s1060992x15020095","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1109/ijcnn.2013.6706963","name":"GPU facilitated unsupervised visual feature acquisition in spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2013.6706963","authors":["Blake Lemoine","Anthony S. Maida"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-01-10T15:08:44Z","doi":"10.1109/ijcnn.2013.6706963","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.3390/s24020491","name":"A Novel Robotic Controller Using Neural Engineering Framework-Based Spiking Neural Networks","source":"crossref","abstract":"This paper investigates spiking neural networks (SNN) for novel robotic controllers with the aim of improving accuracy in trajectory tracking. By emulating the operation of the human brain through the incorporation of temporal coding mechanisms, SNN offer greater adaptability and efficiency in information processing, providing significant advantages in the representation of temporal information in robotic arm control compared to conventional neural networks. Exploring specific implementations of SNN in robot control, this study analyzes neuron models and learning mechanisms inherent to SNN. Based on the principles of the Neural Engineering Framework (NEF), a novel spiking PID controller is designed and simulated for a 3-DoF robotic arm using Nengo and MATLAB R2022b. The controller demonstrated good accuracy and efficiency in following designated trajectories, showing minimal deviations, overshoots, or oscillations. A thorough quantitative assessment, utilizing performance metrics like root mean square error (RMSE) and the integral of the absolute value of the time-weighted error (ITAE), provides additional validation for the efficacy of the SNN-based controller. Competitive performance was observed, surpassing a fuzzy controller by 5% in terms of the ITAE index and a conventional PID controller by 6% in the ITAE index and 30% in RMSE performance. This work highlights the utility of NEF and SNN in developing effective robotic controllers, laying the groundwork for future research focused on SNN adaptability in dynamic environments and advanced robotic applications.","url":"https://doi.org/10.3390/s24020491","authors":["Dailin Marrero","John Kern","Claudio Urrea"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-12T11:43:53Z","doi":"10.3390/s24020491","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1007/978-981-95-5795-0_6","name":"Scalable Temporal Graph Neural Network Training on Dynamic Graphs","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-95-5795-0_6","authors":["Shihong Gao","Yiming Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-26T12:43:28Z","doi":"10.1007/978-981-95-5795-0_6","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.1162/neco.2010.03-09-982","name":"Nonconvergence in Logistic and Poisson Models for Neural Spiking","source":"crossref","abstract":"Generalized linear models are an increasingly common approach for spike train data analysis. For the logistic and Poisson models, one possible difficulty is that iterative algorithms for computing parameter estimates may not converge because of certain data configurations. For the logistic model, these configurations are called complete and quasi-complete separation. We show that these features are likely to occur because of refractory periods of neurons. We use an example to study how standard software deals with this difficulty. For the Poisson model, we show that the same difficulties arise, this time possibly due to bursting or specifics of the binning. We characterize the nonconvergent configurations for both models, show that they can be detected by linear programming methods, and discuss possible remedies.","url":"https://doi.org/10.1162/neco.2010.03-09-982","authors":["Mengyuan Zhao","Satish Iyengar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-25T18:21:01Z","doi":"10.1162/neco.2010.03-09-982","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1109/iscas66217.2026.11562789","name":"Live Demonstration: Circular Object Recognition with Binary-weight Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas66217.2026.11562789","authors":["Ryoichi Yuki","Oliver Velasco-Cardenas","Ayane Matsuzaki","Yoshinari Wada","Seiji Adachi","Kota Ando","Tetsuya Asai","Takao Marukame"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-18T20:06:41Z","doi":"10.1109/iscas66217.2026.11562789","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.1145/3737611.3776948","name":"Towards Verification of Spiking Neural Networks for Next-Generation AI Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3737611.3776948","authors":["Sruti Goswami","Ansuman Banerjee","Swarup K. Mohalik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-31T10:35:20Z","doi":"10.1145/3737611.3776948","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.1016/j.epsr.2026.112858","name":"Context-aware spiking neural networks for real-time anomaly detection in IOT-enabled smart energy systems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.epsr.2026.112858","authors":["Fathe Jeribi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-27T20:38:45Z","doi":"10.1016/j.epsr.2026.112858","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.1162/neco_a_01338","name":"Passive Nonlinear Dendritic Interactions as a Computational Resource in Spiking Neural Networks","source":"crossref","abstract":"Nonlinear interactions in the dendritic tree play a key role in neural computation. Nevertheless, modeling frameworks aimed at the construction of large-scale, functional spiking neural networks, such as the Neural Engineering Framework, tend to assume a linear superposition of postsynaptic currents. In this letter, we present a series of extensions to the Neural Engineering Framework that facilitate the construction of networks incorporating Dale's principle and nonlinear conductance-based synapses. We apply these extensions to a two-compartment LIF neuron that can be seen as a simple model of passive dendritic computation. We show that it is possible to incorporate neuron models with input-dependent nonlinearities into the Neural Engineering Framework without compromising high-level function and that nonlinear postsynaptic currents can be systematically exploited to compute a wide variety of multivariate, band-limited functions, including the Euclidean norm, controlled shunting, and nonnegative multiplication. By avoiding an additional source of spike noise, the function approximation accuracy of a single layer of two-compartment LIF neurons is on a par with or even surpasses that of two-layer spiking neural networks up to a certain target function bandwidth.","url":"https://doi.org/10.1162/neco_a_01338","authors":["Andreas Stöckel","Chris Eliasmith"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-10-20T21:25:44Z","doi":"10.1162/neco_a_01338","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1117/12.2692471","name":"Supervised spiking neural network for SAR image recognition: analysis of encoding methods and performance under strong noise influence","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.2692471","authors":["Wang junyu","Sun hao","Tang tao","Lei lin","Ji kefeng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-07T23:26:36Z","doi":"10.1117/12.2692471","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/iscas48785.2022.9937662","name":"A Spiking Neural Network with Resistively Coupled Synapses Using Time-to-First-Spike Coding Towards Efficient Charge-Domain Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas48785.2022.9937662","authors":["Yusuke Sakemi","Kai Morino","Takashi Morie","Takeo Hosomi","Kazuyuki Aihara"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-11T20:38:08Z","doi":"10.1109/iscas48785.2022.9937662","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/i-smac61858.2024.10714653","name":"CrypTest: Evaluation of CKKS-based Homomorphic Cryptosystems using Deep Spiking Neural Network Diagnostics via Aphid Ant Optimization","source":"crossref","abstract":"","url":"https://doi.org/10.1109/i-smac61858.2024.10714653","authors":["S. Dhanush Prasanna","A.Nadeemullah Khan","S.Poovarasan","N.Mathivanan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-23T17:40:23Z","doi":"10.1109/i-smac61858.2024.10714653","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.7567/ssdm.2024.ps-02-10","name":"Guidelines for Achieving Optimal Classification Accuracy through Unsupervised Learning in Spiking Neural Network Using FeFETs-based Synapses","source":"crossref","abstract":"","url":"https://doi.org/10.7567/ssdm.2024.ps-02-10","authors":["Chung-Li Chang","Hao-Kai Peng","Shun-Chi Wu","Yung-Hsien Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-16T00:21:36Z","doi":"10.7567/ssdm.2024.ps-02-10","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1145/3773283","name":"RCNNshift: Moving Object Tracking with Kernel and Training-Free Spiking Neural Network","source":"crossref","abstract":"Moving object tracking is essential in computer vision applications such as autonomous navigation and surveillance. Traditional kernel-based methods like Meanshift and Camshift are computationally efficient but often falter with complex motions and occlusions. Deep learning approaches improve performance but require significant computational resources and extensive pretraining. In this paper, we present RCNNshift, a novel tracking algorithm that integrates Three-Dimensional Random-Coupled Neural Networks (3DRCNN) with the kernel-based window update process, eliminating the need for pretraining. RCNNshift constructs a robust feature space by leveraging spatiotemporal information from 3DRCNN, enabling effective tracking with reduced computational overhead. Additionally, it employs a one-dimensional feature space for the kernel-based window update step, which can improve efficiency compared to conventional multi-dimensional approaches. We evaluated RCNNshift on multiple datasets, where it consistently outperformed Meanshift and Camshift in accuracy and reliability, particularly in high-resolution and stable remote sensing environments. RCNNshift offers a promising balance between performance and computational efficiency, making it suitable for real-world applications where resources are limited.","url":"https://doi.org/10.1145/3773283","authors":["Haoran Liu","Peng Li","Mingzhe Liu","Yiran Chen","Rui Yao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-28T16:12:19Z","doi":"10.1145/3773283","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.35833/mpce.2020.000569","name":"Unsupervised Learning for Non-intrusive Load Monitoring in Smart Grid Based on Spiking Deep Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.35833/mpce.2020.000569","authors":["Zejian Zhou","Yingmeng Xiang","Hao Xu","Yishen Wang","Di Shi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-05-17T01:55:15Z","doi":"10.35833/mpce.2020.000569","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1088/2634-4386/ac97bb","name":"Fluctuation-driven initialization for spiking neural network training","source":"crossref","abstract":"Abstract Spiking neural networks (SNNs) underlie low-power, fault-tolerant information processing in the brain and could constitute a power-efficient alternative to conventional deep neural networks when implemented on suitable neuromorphic hardware accelerators. However, instantiating SNNs that solve complex computational tasks in-silico remains a significant challenge. Surrogate gradient (SG) techniques have emerged as a standard solution for training SNNs end-to-end. Still, their success depends on synaptic weight initialization, similar to conventional artificial neural networks (ANNs). Yet, unlike in the case of ANNs, it remains elusive what constitutes a good initial state for an SNN. Here, we develop a general initialization strategy for SNNs inspired by the fluctuation-driven regime commonly observed in the brain. Specifically, we derive practical solutions for data-dependent weight initialization that ensure fluctuation-driven firing in the widely used leaky integrate-and-fire neurons. We empirically show that SNNs initialized following our strategy exhibit superior learning performance when trained with SGs. These findings generalize across several datasets and SNN architectures, including fully connected, deep convolutional, recurrent, and more biologically plausible SNNs obeying Dale’s law. Thus fluctuation-driven initialization provides a practical, versatile, and easy-to-implement strategy for improving SNN training performance on diverse tasks in neuromorphic engineering and computational neuroscience.","url":"https://doi.org/10.1088/2634-4386/ac97bb","authors":["Julian Rossbroich","Julia Gygax","Friedemann Zenke"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-05T18:17:48Z","doi":"10.1088/2634-4386/ac97bb","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/raeeucci63961.2025.11048220","name":"Design Of Efficient AI Accelerator Using Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/raeeucci63961.2025.11048220","authors":["A. Rosi","N. Suresh","B Venkata Sasi Kumar","M. Ramesh","C Murugamani","Ashok Kumar Konduru"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-27T17:43:50Z","doi":"10.1109/raeeucci63961.2025.11048220","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/aicas54282.2022.9870009","name":"Energy-Efficient High-Accuracy Spiking Neural Network Inference Using Time-Domain Neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aicas54282.2022.9870009","authors":["Joonghyun Song","Jiwon Shirn","Hanseok Kim","Woo-Seok Choi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-05T20:21:42Z","doi":"10.1109/aicas54282.2022.9870009","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/biocas61083.2024.10798280","name":"Multiplierless Spiking Neural Network for Motor Signal Decoding in the Peripheral Nervous System","source":"crossref","abstract":"","url":"https://doi.org/10.1109/biocas61083.2024.10798280","authors":["Qiaosong Deng","Junyu Ma","Hanfeng Cai","Hao You","Mustafa Kanchwala","Jianxiong Xu","Amirali Amirsoleimani","José Zariffa","Roman Genov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-23T19:10:53Z","doi":"10.1109/biocas61083.2024.10798280","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/icme59968.2025.11209556","name":"ES-Parkour: Advanced Robot Parkour with Bio-inspired Event Camera and Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icme59968.2025.11209556","authors":["Qiang Zhang","Jiahang Cao","Jingkai Sun","Yecheng Shao","Gang Han","Wen Zhao","Yijie Guo","Renjing Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-30T17:57:42Z","doi":"10.1109/icme59968.2025.11209556","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1186/1471-2202-14-s1-p10","name":"Modulation of a decision-making process by spatiotemporal spike patterns decoding: evidence from spike-train metrics analysis and spiking neural network modeling","source":"crossref","abstract":"","url":"https://doi.org/10.1186/1471-2202-14-s1-p10","authors":["Laureline Logiaco","René Quilodran","Wulfram Gerstner","Emmanuel Procyk","Angelo Arleo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-07-08T10:20:03Z","doi":"10.1186/1471-2202-14-s1-p10","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/iscas46773.2023.10181974","name":"Sparsity Through Spiking Convolutional Neural Network for Audio Classification at the Edge","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas46773.2023.10181974","authors":["Cong Sheng Leow","Wang Ling Goh","Yuan Gao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-21T17:19:44Z","doi":"10.1109/iscas46773.2023.10181974","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1007/s11571-022-09797-z","name":"Disynaptic effect of hilar cells on pattern separation in a spiking neural network of hippocampal dentate gyrus","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11571-022-09797-z","authors":["Sang-Yoon Kim","Woochang Lim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-23T23:08:53Z","doi":"10.1007/s11571-022-09797-z","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1007/978-3-032-04558-4_45","name":"Full Integer Arithmetic Online Training for Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-04558-4_45","authors":["Ismael Gomez","Guangzhi Tang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-11T11:16:47Z","doi":"10.1007/978-3-032-04558-4_45","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.1109/lnet.2025.3611426","name":"Eco-Efficient Deployment of Spiking Neural Networks on Low-Cost Edge Hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1109/lnet.2025.3611426","authors":["Fernando Sevilla Martínez","Jordi Casas-Roma","Laia Subirats","Raúl Parada"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-18T17:48:27Z","doi":"10.1109/lnet.2025.3611426","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.1016/j.sysarc.2026.103928","name":"Corrigendum to \"Neuromorphic architectures for edge-oriented spiking neural networks: A review\" [Journal of Systems Architecture 177 (2026) 103869]","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.sysarc.2026.103928","authors":["Kanishka Gunawardana","Sanka Peeris","Kavishka Rambukwella","Roshan Ragel","Isuru Nawinne"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-22T20:27:19Z","doi":"10.1016/j.sysarc.2026.103928","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.1007/978-981-95-3787-7_4","name":"Research on Multifunctional Silicon-Based Integrated Diffractive Optical Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-95-3787-7_4","authors":["Tingzhao Fu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-01T23:30:36Z","doi":"10.1007/978-981-95-3787-7_4","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.1109/icscan66520.2026.11588322","name":"Energy-Constrained Neuromorphic Edge AI Using Spiking Graph Neural Networks for Autonomous IoT Anomaly Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icscan66520.2026.11588322","authors":["Sajja Suneel","K.Nirmala Devi","R. Rajalakshmi","B Bharathidevi","Lalitha Palthiya","D. Jayaprakash"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-07T19:42:48Z","doi":"10.1109/icscan66520.2026.11588322","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.3390/electronics15050937","name":"HS-FP and SS-FP: Fine-Pruning-Based Backdoor Elimination for Spiking Neural Networks on Neuromorphic Event Data","source":"crossref","abstract":"Spiking Neural Networks (SNNs) have attracted increasing attention due to their energy efficiency and suitability for neuromorphic data processing. Despite these advantages, the security of SNNs—particularly their robustness against backdoor attacks—remains underexplored. This study revisits fine-pruning, a widely adopted backdoor defense technique in deep neural networks, and adapts it to the unique spatio-temporal characteristics of SNNs. We propose two SNN-specific fine-pruning methods: Hook–Surrogate Gradient-based fine-pruning (HS-FP) and Spike–STDP-based fine-pruning (SS-FP). HS-FP leverages hook-based activation analysis with surrogate gradient learning, while SS-FP integrates total spike activity with hybrid STDP and surrogate gradient fine-tuning. We evaluate both methods against static, moving, and smart backdoor attacks on two neuromorphic benchmarks, N-MNIST and DVS128-Gesture. Experimental results show that both approaches reduce the attack success rate down to approximately 10% while preserving model accuracy above 99% on N-MNIST and achieving substantial recovery on DVS128-Gesture. Moreover, our analysis reveals that several phenomena observed in fine-pruning-based defenses for deep neural networks—such as mixed-function neurons and backdoor reactivation during fine-tuning—also manifest in SNNs. These findings highlight both the effectiveness and limitations of fine-pruning in the SNN domain and suggest promising directions for extending existing DNN security methodologies to neuromorphic systems.","url":"https://doi.org/10.3390/electronics15050937","authors":["Ki-Ho Kim","Eun-Kyu Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-25T13:37:37Z","doi":"10.3390/electronics15050937","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.1101/2023.02.03.526928","name":"Global inhibition in head-direction neural circuits: a systematic comparison between connectome-based spiking neural circuit models","source":"crossref","abstract":"Abstract The recent discovery of the head-direction (HD) system in fruit flies has provided unprecedented insights into the neural mechanisms of spatial orientation. Despite the progress, the neural substance of global inhibition, an essential component of the HD circuits, remains controversial. Some studies suggested that the ring neurons provide global inhibition, while others suggested the Δ7 neurons. In the present study, we provide evaluations from the theoretical perspective by performing systematic analyses on the computational models based on the ring-neuron (R models) and Δ7-neurons (Delta models) hypotheses with modifications according to the latest connectomic data. We conducted four tests: robustness, persistency, speed, and dynamical characteristics. We discovered that the two models led to a comparable performance in general, but each excelled in different tests. The R Models were more robust, while the Delta models were better in the persistency test. We also tested a hybrid model that combines both inhibitory mechanisms. While the performances of the R and Delta models in each test are highly parameter-dependent, the Hybrid model performed well in all tests with the same set of parameters. Our results suggest the possibility of combined inhibitory mechanisms in the HD circuits of fruit flies.","url":"https://doi.org/10.1101/2023.02.03.526928","authors":["Ning Chang","Hsuan-Pei Huang","Chung-Chuan Lo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-02-05T00:35:16Z","doi":"10.1101/2023.02.03.526928","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1016/s0893-6080(03)00090-x","name":"Passive dendritic integration heavily affects spiking dynamics of recurrent networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/s0893-6080(03)00090-x","authors":["Giorgio A. Ascoli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-05-19T14:45:52Z","doi":"10.1016/s0893-6080(03)00090-x","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1162/neco_a_00141","name":"On the Simulation of Nonlinear Bidimensional Spiking Neuron Models","source":"crossref","abstract":"Bidimensional spiking models are garnering a lot of attention for their simplicity and their ability to reproduce various spiking patterns of cortical neurons and are used particularly for large network simulations. These models describe the dynamics of the membrane potential by a nonlinear differential equation that blows up in finite time, coupled to a second equation for adaptation. Spikes are emitted when the membrane potential blows up or reaches a cutoff θ. The precise simulation of the spike times and of the adaptation variable is critical, for it governs the spike pattern produced and is hard to compute accurately because of the exploding nature of the system at the spike times. We thoroughly study the precision of fixed time-step integration schemes for this type of model and demonstrate that these methods produce systematic errors that are unbounded, as the cutoff value is increased, in the evaluation of the two crucial quantities: the spike time and the value of the adaptation variable at this time. Precise evaluation of these quantities therefore involves very small time steps and long simulation times. In order to achieve a fixed absolute precision in a reasonable computational time, we propose here a new algorithm to simulate these systems based on a variable integration step method that either integrates the original ordinary differential equation or the equation of the orbits in the phase plane, and compare this algorithm with fixed time-step Euler scheme and other more accurate simulation algorithms.","url":"https://doi.org/10.1162/neco_a_00141","authors":["Jonathan Touboul"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-04-15T04:44:11Z","doi":"10.1162/neco_a_00141","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/ijcnn52387.2021.9533514","name":"Learning from Event Cameras with Sparse Spiking Convolutional Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn52387.2021.9533514","authors":["Loic Cordone","Benoit Miramond","Sonia Ferrante"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-20T21:27:41Z","doi":"10.1109/ijcnn52387.2021.9533514","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1007/978-981-95-5795-0_1","name":"Introduction to Graph Neural Network Training on Large Graphs","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-95-5795-0_1","authors":["Yanyan Shen","Lei Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-26T12:43:15Z","doi":"10.1007/978-981-95-5795-0_1","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.1109/ijcnn.2019.8851744","name":"A Spiking Neural Network with a Global Self-Controller for Unsupervised Learning Based on Spike-Timing-Dependent Plasticity Using Flash Memory Synaptic Devices","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2019.8851744","authors":["Won-Mook Kang","Chul-Heung Kim","Soochang Lee","Sung Yun Woo","Jong-Ho Bae","Byung-Gook Park","Jong-Ho Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-10-01T03:44:32Z","doi":"10.1109/ijcnn.2019.8851744","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1101/494310","name":"Fast and Flexible Sequence Induction In Spiking Neural Networks Via Rapid Excitability Changes","source":"crossref","abstract":"Abstract Cognitive flexibility, the adaptation of mental processing to changes in task demands, is thought to depend on biological neural networks’ ability to rapidly modulate the dynamics governing how they process information. While extensive work has elucidated how network dynamics can be reshaped by slowly occurring structural changes, e.g. the gradual modification of recurrent synaptic patterns, much less is known about how dynamics might be reconfigured over faster timescales of seconds. One compelling example of rapid and selective modulation of network dynamics potentially involved in cognitive flexibility is observed in rodent hippocampus, where short bouts of exploratory behavior cause new activity sequences to preferentially “replay” during subsequent awake rest periods without continued sensory input. Fast mechanisms for selectively biasing sequential activity through networks, however, remain unknown. Using a spiking neural network model, we asked whether a simplified version of sequence replay could arise from three biophysically plausible components: recurrent, spatially organized connectivity; homogeneous, stochastic “gating” inputs; and rapid, activity-dependent scaling of gating input strengths, based on a phenomenon known as long-term potentiation of intrinsic excitability (LTP-IE). Indeed, these enabled both forward and reverse replay of flexible sequences reflecting recent behavior, despite unchanged recurrent weights. Specifically, activation-triggered LTP-IE “tags” neurons in the recurrent network by increasing their spiking probability when gating input is applied, and the sequential ordering of spikes is reconstructed by the existing recurrent connectivity. In a proof-of-concept demonstration, we also show how LTP-IE-based sequences can implement temporary stimulus-response mappings in a straightforward manner. These results elucidate a simple yet previously unexplored combination of biological mechanisms that converge in hippocampus and suffice for fast and flexible reconfiguration of sequential network dynamics, suggesting their potential role in cognitive flexibility over rapid timescales.","url":"https://doi.org/10.1101/494310","authors":["Rich Pang","Adrienne Fairhall"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-12-13T19:54:15Z","doi":"10.1101/494310","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.2139/ssrn.4930522","name":"Efficient Learning Using Spiking Neural Networks Equipped with Affine Encoders and Decoders","source":"crossref","abstract":"We study the learning problem associated with spiking neural networks. Specifically, we consider hypothesis sets of spiking neural networks with affine temporal encoders and decoders and simple spiking neurons having only positive synaptic weights. We demonstrate that the positivity of the weights continues to enable a wide range of expressivity results, including rate-optimal approximation of smooth functions or approximation without the curse of dimensionality. Moreover, positive-weight spiking neural networks are shown to depend continuously on their parameters which facilitates classical covering number-based generalization statements. Finally, we observe that from a generalization perspective, contrary to feedforward neural networks or previous results for general spiking neural networks, the depth has little to no adverse effect on the generalization capabilities.","url":"https://doi.org/10.2139/ssrn.4930522","authors":["Anh  Martina Neuman","Philipp Petersen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-19T17:18:27Z","doi":"10.2139/ssrn.4930522","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1016/j.neunet.2012.02.034","name":"Learning expectation in insects: A recurrent spiking neural model for spatio-temporal representation","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2012.02.034","authors":["Paolo Arena","Luca Patané","Pietro Savio Termini"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-02-14T21:18:41Z","doi":"10.1016/j.neunet.2012.02.034","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.3389/fninf.2016.00031","name":"Closed Loop Interactions between Spiking Neural Network and Robotic Simulators Based on MUSIC and ROS","source":"crossref","abstract":"","url":"https://doi.org/10.3389/fninf.2016.00031","authors":["Philipp Weidel","Mikael Djurfeldt","Renato C. Duarte","Abigail Morrison"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-08-02T23:23:49Z","doi":"10.3389/fninf.2016.00031","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/icdici66477.2025.11135287","name":"Osteosarcoma Bone Cancer Detection; Using Binarized Spiking Neural Network Optimized with Osprey Optimization Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icdici66477.2025.11135287","authors":["Rajesh Munirathnam","M. K. Pushpa","Mahesh Kumar A S","Hardik Patel","Sangramjit Chavan","Natrayan L"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-02T17:29:01Z","doi":"10.1109/icdici66477.2025.11135287","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/ecce64574.2025.11012978","name":"Spiking Neural Network Approach for Binary Classification of Hand Movements of Spinal Cord Injured Patients","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ecce64574.2025.11012978","authors":["Md. Shafiul Islam Joy","Mehdi Hasan Chowdhury","Kamrul Hasan","Sagar Mutsuddi","Quazi Delwar Hossain"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-29T17:07:16Z","doi":"10.1109/ecce64574.2025.11012978","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1007/s11760-023-02569-0","name":"Spatiotemporal Backpropagation based on Channel Reward for Training High-Precision Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11760-023-02569-0","authors":["Li-Ye Niu","Ying Wei","Yue Liu","Jun-Yu Long","Wen-Bo Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-08T09:02:57Z","doi":"10.1007/s11760-023-02569-0","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/tnn.2004.832719","name":"Which Model to Use for Cortical Spiking Neurons?","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnn.2004.832719","authors":["E.M. Izhikevich"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2004-09-13T14:06:25Z","doi":"10.1109/tnn.2004.832719","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1007/978-3-642-35594-3_44","name":"Survey on Information Processing in Visual Cortex: Cortical Feedback and Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-35594-3_44","authors":["A. Diana Andrushia","R. Thangarajan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-11-26T13:00:27Z","doi":"10.1007/978-3-642-35594-3_44","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/devlrn.2013.6652548","name":"Impacts of environment, nervous system and movements of preterms on body map development: Fetus simulation with spiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/devlrn.2013.6652548","authors":["Yasunori Yamada","Keiko Fujii","Yasuo Kuniyoshi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-11-11T14:56:15Z","doi":"10.1109/devlrn.2013.6652548","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1063/10.0043244","name":"Neural network automates the identification of dirty solar panels","source":"crossref","abstract":"An improved model identifies power-reducing dust accumulation on photovoltaic modules, helping engineers know when the modules need cleaning.","url":"https://doi.org/10.1063/10.0043244","authors":["Mara Johnson-Groh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-25T10:53:04Z","doi":"10.1063/10.0043244","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.1101/613471","name":"Biologically plausible learning in a deep recurrent spiking network","source":"crossref","abstract":"Abstract Artificial deep convolutional networks (DCNs) meanwhile beat even human performance in challenging tasks. Recently DCNs were shown to also predict real neuronal responses. Their relevance for understanding the neuronal networks in the brain, however, remains questionable. In contrast to the unidirectional architecture of DCNs neurons in cortex are recurrently connected and exchange signals by short pulses, the action potentials. Furthermore, learning in the brain is based on local synaptic mechanisms, in stark contrast to the global optimization methods used in technical deep networks. What is missing is a similarly powerful approach with spiking neurons that employs local synaptic learning mechanisms for optimizing global network performance. Here, we present a framework consisting of mutually coupled local circuits of spiking neurons. The dynamics of the circuits is derived from first principles to optimally encode their respective inputs. From the same global objective function a local learning rule is derived that corresponds to spike-timing dependent plasticity of the excitatory inter-circuit synapses. For deep networks built from these circuits self-organization is based on the ensemble of inputs while for supervised learning the desired outputs are applied in parallel as additional inputs to output layers. Generality of the approach is shown with Boolean functions and its functionality is demonstrated with an image classification task, where networks of spiking neurons approach the performance of their artificial cousins. Since the local circuits operate independently and in parallel, the novel framework not only meets a fundamental property of the brain but also allows for the construction of special hardware. We expect that this will in future enable investigations of very large network architectures far beyond current DCNs, including also large scale models of cortex where areas consisting of many local circuits form a complex cyclic network.","url":"https://doi.org/10.1101/613471","authors":["David Rotermund","Klaus R. Pawelzik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-04-19T01:35:10Z","doi":"10.1101/613471","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1007/s00521-025-11729-x","name":"Feed forward neural network for non-intrusive load monitoring","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-025-11729-x","authors":["Muhammad Asad","Manar Amayri","Nizar Bouguila"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-19T11:22:29Z","doi":"10.1007/s00521-025-11729-x","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.1016/j.neunet.2026.109554","name":"A semi-analytical fractional order neural network framework for two-dimensional time fractional reaction-diffusion problems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.109554","authors":["Arihant Patawari","Pratibhamoy Das","Subrata Rana"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-31T15:32:00Z","doi":"10.1016/j.neunet.2026.109554","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.1088/1741-2560/9/2/026024","name":"Parameter estimation in spiking neural networks: a reverse-engineering approach","source":"crossref","abstract":"This paper presents a reverse engineering approach for parameter estimation in spiking neural networks (SNNs). We consider the deterministic evolution of a time-discretized network with spiking neurons, where synaptic transmission has delays, modeled as a neural network of the generalized integrate and fire type. Our approach aims at by-passing the fact that the parameter estimation in SNN results in a non-deterministic polynomial-time hard problem when delays are to be considered. Here, this assumption has been reformulated as a linear programming (LP) problem in order to perform the solution in a polynomial time. Besides, the LP problem formulation makes the fact that the reverse engineering of a neural network can be performed from the observation of the spike times explicit. Furthermore, we point out how the LP adjustment mechanism is local to each neuron and has the same structure as a 'Hebbian' rule. Finally, we present a generalization of this approach to the design of input-output (I/O) transformations as a practical method to 'program' a spiking network, i.e. find a set of parameters allowing us to exactly reproduce the network output, given an input. Numerical verifications and illustrations are provided.","url":"https://doi.org/10.1088/1741-2560/9/2/026024","authors":["H Rostro-Gonzalez","B Cessac","T Vieville"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-03-15T09:13:52Z","doi":"10.1088/1741-2560/9/2/026024","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1007/978-3-030-63836-8_30","name":"Unsupervised Multi-layer Spiking Convolutional Neural Network Using Layer-Wise Sparse Coding","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-63836-8_30","authors":["Regina Esi Turkson","Hong Qu","Yuchen Wang","Moses J. Eghan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-11-18T09:12:07Z","doi":"10.1007/978-3-030-63836-8_30","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/icassp55912.2026.11462852","name":"AR-LIF: Adaptive Reset Leaky Integrate-And-Fire Neuron for Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icassp55912.2026.11462852","authors":["Zeyu Huang","Wei Meng","Quan Liu","Kun Chen","Li Ma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-21T21:23:31Z","doi":"10.1109/icassp55912.2026.11462852","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.1145/3637494.3637517","name":"Design and Implementation of Deep Spiking Neural Network Learning Algorithm Based on Feedback Mechanism","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3637494.3637517","authors":["Xueliang Tang","Xu Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-05T12:06:23Z","doi":"10.1145/3637494.3637517","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/icacrs62842.2024.10841788","name":"Waste Classification using Edge based Multilayer White Shark Dense Net-Spiking Neural Network from Urban Areas","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icacrs62842.2024.10841788","authors":["Chitra Kiran. N","Ruchira Rawat","T. Madhavi","SKM. Pothinathan","Dhaval Rabadiya","Karthik Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-17T18:33:03Z","doi":"10.1109/icacrs62842.2024.10841788","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.3233/jifs-191914","name":"Light weight convolutional models with spiking neural network based human action recognition","source":"crossref","abstract":"Though deep learning networks have proven ability to perform video analytics in complex environments, there is an increased attention towards the development of compact networks which would facilitate edge processing and the result of which have yielded high performance compressed deep learning networks such as, MobileNet, PWCNet and BindsNet. In the work proposed herein, a dual network configuration is used for human action recognition, wherein, the MobileNet captures the spatial appearance of the action sequences and the PWCNet is used to extract the motion vectors. A novel Spiking Neural Network (SNN) based configuration is used as the classifier and the SNN implementation is based on BindsNet. The proposed configuration is experimentally validated on challenging datasets, viz., HMDB51 and UCF101. The experimental results demonstrate that the proposed work is superior to the state-of-the-art techniques and comparable in few cases.","url":"https://doi.org/10.3233/jifs-191914","authors":["S. Jeba Berlin","Mala John"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-23T11:01:15Z","doi":"10.3233/jifs-191914","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/icetet-sip-1946815.2019.9092079","name":"ASIC Implementation Of Biologically Inspired Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icetet-sip-1946815.2019.9092079","authors":["Gunjan Rajput","Gopal Raut","Sajid Khan","Neha Gupta","Ankur Behor","Santosh Kumar Vishvakarma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-05-15T03:39:00Z","doi":"10.1109/icetet-sip-1946815.2019.9092079","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/iccneee.2015.7381395","name":"Multi-objective K-means evolving spiking neural network model based on differential evolution","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccneee.2015.7381395","authors":["Haza Nuzly Abdull Hamed","Abdulrazak Yahya Saleh","Siti Mariyam Shamsuddin","Ashraf Osman Ibrahim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-01-14T23:51:06Z","doi":"10.1109/iccneee.2015.7381395","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/iciea65512.2025.11149056","name":"Efficient Identification of Cable Partial Discharge: A Spiking Neural Network Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iciea65512.2025.11149056","authors":["Shengwei Li","Xiaomin He","Zhaoquan Ye","Chen Dong","Fanghong Guo","Guoqi Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-10T17:41:10Z","doi":"10.1109/iciea65512.2025.11149056","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/iscas51556.2021.9401602","name":"A Heterogeneous Spiking Neural Network for Computationally Efficient Face Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas51556.2021.9401602","authors":["Xichuan Zhou","Zhenghua Zhou","Zhengqing Zhong","Jianyi Yu","Tengxiao Wang","Min Tian","Ying Jiang","Cong Shi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-04-27T21:33:36Z","doi":"10.1109/iscas51556.2021.9401602","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1016/j.neucom.2015.12.086","name":"An efficient hardware implementation of a novel unary Spiking Neural Network multiplier with variable dendritic delays","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2015.12.086","authors":["Carlos Diaz","Giovanny Sanchez","Gonzalo Duchen","Mariko Nakano","Hector Perez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-01-11T05:46:34Z","doi":"10.1016/j.neucom.2015.12.086","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1103/physreve.110.024310","name":"Moment neural network and an efficient numerical method for modeling irregular spiking activity","source":"crossref","abstract":"Continuous rate-based neural networks have been widely applied to modeling the dynamics of cortical circuits. However, cortical neurons in the brain exhibit irregular spiking activity with complex correlation structures that cannot be captured by mean firing rate alone. To close this gap, we consider a framework for modeling irregular spiking activity, called the moment neural network, which naturally generalizes rate models to second-order moments and can accurately capture the firing statistics of spiking neural networks. We propose an efficient numerical method that allows for rapid evaluation of moment mappings for neuronal activations without solving the underlying Fokker-Planck equation. This allows simulation of coupled interactions of mean firing rate and firing variability of large-scale neural circuits while retaining the advantage of analytical tractability of continuous rate models. We demonstrate how the moment neural network can explain a range of phenomena including diverse Fano factor in networks with quenched disorder and the emergence of irregular oscillatory dynamics in excitation-inhibition networks with delay. Published by the American Physical Society 2024","url":"https://doi.org/10.1103/physreve.110.024310","authors":["Yang Qi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-20T10:13:12Z","doi":"10.1103/physreve.110.024310","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.36334/modsim2025.d01.chan","name":"Generating initial values using artificial neural network","source":"crossref","abstract":"","url":"https://doi.org/10.36334/modsim2025.d01.chan","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-08T04:58:49Z","doi":"10.36334/modsim2025.d01.chan","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.1049/cim2.70043","name":"DLC‐NddMode: A Spiking Neural Network Tactile Object Recognition Model With Adaptive Optimisation and Regularisation","source":"crossref","abstract":"ABSTRACT Empowering robots with tactile perception is crucial for the future development of intelligent robots. Tactile perception can expand the application scenarios of robots to perform more complex tasks. Unfortunately, existing approaches are flawed in their use of data collected by robotic tactile sensors because they either do not consider that tactile sensation is event‐driven, which means that tactile data are spatiotemporal, or they ignore that too few samples of tactile data would cause overfitting problems in the network model. We introduce DLC‐NddModel, a method based on spiking neural networks (SNNs) that incorporates Adam optimisation, regularisation and cosine annealing method. DLC‐NddModel aims to fully interpret the spatiotemporal nature of the tactile data using the spatiotemporal dynamics of SNNs and to alleviate the overfitting problem caused by the few samples. Furthermore, unlike previous work using SNNs, we use a different approximation function to surmount the nondifferentiable spiking activity of the spiking neurons, thus making the gradient descent method usable and effective. To effectively alleviate the overfitting problem caused by too few tactile data samples, we explore solutions through regularisation strategies that add training noise or regularisation terms to the loss function. We compare DLC‐NddModel against four prior state‐of‐the‐art approaches on the EvTouch‐Objects tactile spike dataset. Our experimental results demonstrate that DLC‐NddModel has higher recognition accuracy than the comparison method when recognising household object data with an ACC value improvement of at least 2.362%.","url":"https://doi.org/10.1049/cim2.70043","authors":["Lin Liu","Shaobo Li","Xiaoyang Ji","Jing Yang","Zukun Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-06T18:54:09Z","doi":"10.1049/cim2.70043","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/icus61736.2024.10839964","name":"Spiking Neural Network-based Approximate Dynamic Programming for Vehicle Tracking Control","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icus61736.2024.10839964","authors":["Chengwei Pan","Jiale Geng","Wenyu Li","Feng Duan","Shengbo Eben Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-22T18:45:23Z","doi":"10.1109/icus61736.2024.10839964","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/asid50160.2020.9271721","name":"Carbon-based Spiking Neural Network Implemented with Single-Electron Transistor and Memristor for Visual Perception","source":"crossref","abstract":"","url":"https://doi.org/10.1109/asid50160.2020.9271721","authors":["Zhiwei Wang","Chenxi Liu","Yabin Deng","Zenan Huang","Shan He","Donghui Guo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-01T23:07:43Z","doi":"10.1109/asid50160.2020.9271721","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.3389/fncom.2022.948973","name":"Production of adaptive movement patterns via an insect inspired spiking neural network central pattern generator","source":"crossref","abstract":"Navigation in ever-changing environments requires effective motor behaviors. Many insects have developed adaptive movement patterns which increase their success in achieving navigational goals. A conserved brain area in the insect brain, the Lateral Accessory Lobe, is involved in generating small scale search movements which increase the efficacy of sensory sampling. When the reliability of an essential navigational stimulus is low, searching movements are initiated whereas if the stimulus reliability is high, a targeted steering response is elicited. Thus, the network mediates an adaptive switching between motor patterns. We developed Spiking Neural Network models to explore how an insect inspired architecture could generate adaptive movements in relation to changing sensory inputs. The models are able to generate a variety of adaptive movement patterns, the majority of which are of the zig-zagging kind, as seen in a variety of insects. Furthermore, these networks are robust to noise. Because a large spread of network parameters lead to the correct movement dynamics, we conclude that the investigated network architecture is inherently well-suited to generating adaptive movement patterns.","url":"https://doi.org/10.3389/fncom.2022.948973","authors":["Fabian Steinbeck","Thomas Nowotny","Andy Philippides","Paul Graham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-18T06:30:43Z","doi":"10.3389/fncom.2022.948973","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1016/j.procs.2016.11.023","name":"On the Applicability of Spiking Neural Network Models to Solve the Task of Recognizing Gender Hidden in Texts","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.procs.2016.11.023","authors":["Alexander Sboev","Tatiana Litvinova","Danila Vlasov","Alexey Serenko","Ivan Moloshnikov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-12-03T00:03:00Z","doi":"10.1016/j.procs.2016.11.023","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.24251/hicss.2025.848","name":"Development of a Neuromorphic-Friendly Spiking Neural Network for RF Event-based Classification","source":"crossref","abstract":"","url":"https://doi.org/10.24251/hicss.2025.848","authors":["Michael Smith","Michael Temple","James Dean"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-07T03:59:05Z","doi":"10.24251/hicss.2025.848","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/iscas.2019.8702407","name":"Biomimetic Spiking Neural Network (SNN) Systems for ‘In Vitro’ Cells Stimulation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas.2019.8702407","authors":["Farad Khoyratee","Stephany Mai Nishikawa","Luo Zhongyue","Soo Hyeon Kim","Sylvain Saighi","Teruo Fujii","Yoshiho Ikeuchi","Kazuyuki Aihara","Timothee Levi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-01T17:02:28Z","doi":"10.1109/iscas.2019.8702407","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/phm-xian66756.2025.11427831","name":"Crack Defect Detection and Evaluation Method Based on Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/phm-xian66756.2025.11427831","authors":["Yanxiao Wang","Zihao Lei","Zhizhen Ren","Guangrui Wen","Yu Su","Zhifen Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-16T20:10:33Z","doi":"10.1109/phm-xian66756.2025.11427831","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/vlsid60093.2024.00040","name":"SpiCS-Net: Circuit Switched Network on Chip for Area-Efficient Spiking Recurrent Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/vlsid60093.2024.00040","authors":["Manu Rathore","Garrett S. Rose"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-02T18:38:37Z","doi":"10.1109/vlsid60093.2024.00040","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.3389/fnins.2021.756876","name":"SSTDP: Supervised Spike Timing Dependent Plasticity for Efficient Spiking Neural Network Training","source":"crossref","abstract":"Spiking Neural Networks (SNNs) are a pathway that could potentially empower low-power event-driven neuromorphic hardware due to their spatio-temporal information processing capability and high biological plausibility. Although SNNs are currently more efficient than artificial neural networks (ANNs), they are not as accurate as ANNs. Error backpropagation is the most common method for directly training neural networks, promoting the prosperity of ANNs in various deep learning fields. However, since the signals transmitted in the SNN are non-differentiable discrete binary spike events, the activation function in the form of spikes presents difficulties for the gradient-based optimization algorithms to be directly applied in SNNs, leading to a performance gap (i.e., accuracy and latency) between SNNs and ANNs. This paper introduces a new learning algorithm, called SSTDP, which bridges the gap between backpropagation (BP)-based learning and spike-time-dependent plasticity (STDP)-based learning to train SNNs efficiently. The scheme incorporates the global optimization process from BP and the efficient weight update derived from STDP. It not only avoids the non-differentiable derivation in the BP process but also utilizes the local feature extraction property of STDP. Consequently, our method can lower the possibility of vanishing spikes in BP training and reduce the number of time steps to reduce network latency. In SSTDP, we employ temporal-based coding and use Integrate-and-Fire (IF) neuron as the neuron model to provide considerable computational benefits. Our experiments show the effectiveness of the proposed SSTDP learning algorithm on the SNN by achieving the best classification accuracy 99.3% on the Caltech 101 dataset, 98.1% on the MNIST dataset, and 91.3% on the CIFAR-10 dataset compared to other SNNs trained with other learning methods. It also surpasses the best inference accuracy of the directly trained SNN with 25~32× less inference latency. Moreover, we analyze event-based computations to demonstrate the efficacy of the SNN for inference operation in the spiking domain, and SSTDP methods can achieve 1.3~37.7× fewer addition operations per inference. The code is available at: https://github.com/MXHX7199/SNN-SSTDP .","url":"https://doi.org/10.3389/fnins.2021.756876","authors":["Fangxin Liu","Wenbo Zhao","Yongbiao Chen","Zongwu Wang","Tao Yang","Li Jiang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-04T03:38:11Z","doi":"10.3389/fnins.2021.756876","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/icnc-fskd59587.2023.10280835","name":"A High-speed and Low-power FPGA Implementation of Spiking Convolutional Neural Network Using Logarithmic Quantization","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc-fskd59587.2023.10280835","authors":["Jiadong Wu","Yinan Wang","Lun Lu","Changlin Chen","Zhiwei Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-18T13:43:48Z","doi":"10.1109/icnc-fskd59587.2023.10280835","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1002/pamm.202400066","name":"Physics‐Based Spiking Neural Network as a Surrogate Model for Viscoplastic Material Law in Impulsively Loaded Beams","source":"crossref","abstract":"ABSTRACT In the present study, the nonlinear material law of an in‐house FEM solver is substituted by physics‐informed neural networks (PINNs) and by physics‐based spiking neural networks (SNNs) for predicting the dynamic response of beams under impact loading. In the first part of this study concerning PINNs, the physics are included in the loss function of a deep neural network, also called a second‐generation neural network. The main advantage of using PINNs compared to classical ANNs is that they are considered data‐efficient function approximators. In the second part of this study, leaky integrate and fire (LIF) layers are deployed instead of dense layers in the PINN architecture, leading to a physics‐based third‐generation SNN, which enhances the PINN architecture in terms of energy efficiency. Third‐generation SNNs are inspired by the human brain function, where the information is processed via spikes. The spikes introduce sparse behavior, leading to a more energy‐efficient and sustainable deep learning method when implemented in neuromorphic hardware. The PINNs and physics‐based SNNs are employed in the implicit integration scheme of the material law of the in‐house FEM solver at the Gaussian level, and results are compared with the in‐house FEM solution in two different initial boundary value (IBV) problems. This study aims to show that PINNs can predict nonlinear material behavior and that the use of a physics‐based loss function enables the utility of less data in the training of the neural networks. Moreover, we show that we can enhance PINNs regarding energy consumption by adding a LIF layer. Therefore, the energy consumption is compared when the physics‐based SNN is deployed on the Loihi neuromorphic chip and on the CPU.","url":"https://doi.org/10.1002/pamm.202400066","authors":["Vasileios Polydoras","Saurabh Tandale","Marcus Stoffel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-11T08:16:39Z","doi":"10.1002/pamm.202400066","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1101/2023.05.22.541722","name":"Synaptic turnover promotes efficient learning in bio-realistic spiking neural networks","source":"crossref","abstract":"Abstract While artificial machine learning systems achieve superhuman performance in specific tasks such as language processing, image and video recognition, they do so use extremely large datasets and huge amounts of power. On the other hand, the brain remains superior in several cognitively challenging tasks while operating with the energy of a small lightbulb. We use a biologically constrained spiking neural network model to explore how the neural tissue achieves such high efficiency and assess its learning capacity on discrimination tasks. We found that synaptic turnover, a form of structural plasticity, which is the ability of the brain to form and eliminate synapses continuously, increases both the speed and the performance of our network on all tasks tested. Moreover, it allows accurate learning using a smaller number of examples. Importantly, these improvements are most significant under conditions of resource scarcity, such as when the number of trainable parameters is halved and when the task difficulty is increased. Our findings provide new insights into the mechanisms that underlie efficient learning in the brain and can inspire the development of more efficient and flexible machine learning algorithms.","url":"https://doi.org/10.1101/2023.05.22.541722","authors":["Nikos Malakasis","Spyridon Chavlis","Panayiota Poirazi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-24T16:00:12Z","doi":"10.1101/2023.05.22.541722","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1021/acsami.5c25164.s001","name":"A Gate-Tunable Thermal Persistent Photocurrent Device for In-Sensor Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acsami.5c25164.s001","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-06T13:40:26Z","doi":"10.1021/acsami.5c25164.s001","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.70675/dec25346zd9ddz4b65zaeb0z54e7d1df8a60","name":"Models and algorithms for implementing energy-efficient spiking neural networks on neuromorphic hardware at the edge","source":"crossref","abstract":"Modèles et algorithmes pour l'implémentation de réseaux de neurones impulsionnels à faible consommation énergétique sur du matériel neuromorphique L'apprentissage profond dans les réseaux de neurones artificiels (ANNs), une branche de l'intelligence artificielle (IA), est considéré comme une révolution dans l'informatique et a un impact sur tous les secteurs de l'économie. Cependant, les ANNs sont très gourmands en ressources de calcul et en mémoire, ce qui limite leur intégration à la périphérie du réseau pour des applications embarquées. Les réseaux de neurones impulsionnels (SNNs) sont des alternatives prometteuses aux ANNs en termes d'efficacité énergétique et sont donc de bons candidats pour les implémentations IA embarquées utilisant du matériel neuromorphique. En effet, les SNNs encodent les informations en utilisant des événements temporels épars (appelés « spikes ») au lieu d'activations denses et précises. Cependant, l'écart entre le développement algorithmique des SNNs d'une part, et leur implémentation matérielle d'autre part, rend difficile l'obtention de solutions réellement efficaces. Dans ce contexte, cette thèse suit une approche tenant compte du matériel pour conduire les développements algorithmiques des SNNs. En particulier, des modèles et des algorithmes sont proposés pour améliorer la précision et l'efficacité énergétique des SNNs, en considérant des implémentations matérielles numériques et analogiques.Afin de comparer les implémentations des SNNs et des ANNs sur des accélérateurs de réseaux de neurones dédiés, un modèle de leur efficacité énergétique est fourni. En particulier, on constate que la parcimonie des activations joue un rôle clé dans l'efficacité des SNNs. Par conséquent, un nouveau modèle de SNN, SpikGRU, est proposé. Remarquablement, il combine la précision des ANNs récurrents à porte avec une parcimonie des activations, et s'avère très efficace pour les applications de faible puissance telles que le repérage de mots clés. En outre, l'implémentation des poids synaptiques utilisant des mémoires analogiques non volatiles est envisagée pour augmenter encore l'efficacité énergétique. Avec une méthodologie d'apprentissage adaptée, les SNNs se révèlent très robustes à ces poids hautement quantifiés et avec un haut niveau de bruit. Une étude de cas utilisant des mémoires résistives valide l'approche.En encourageant le co-développement algorithme-matériel, ce travail vise à ouvrir la voie à des implémentations efficaces de réseaux de neurones embarqués.","url":"https://doi.org/10.70675/dec25346zd9ddz4b65zaeb0z54e7d1df8a60","authors":["Manon Dampfhoffer"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-08T07:13:49Z","doi":"10.70675/dec25346zd9ddz4b65zaeb0z54e7d1df8a60","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.29354/diag/225964","name":"Design and implementation of Network Intrusion Detection System (NIDS) based on neural network model","source":"crossref","abstract":"","url":"https://doi.org/10.29354/diag/225964","authors":["Baoxing Xie"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-15T06:51:41Z","doi":"10.29354/diag/225964","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.1016/j.phycom.2026.103272","name":"SCMFFN: A spiking combined few-shot network with multi-feature fusion for automatic modulation classification","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.phycom.2026.103272","authors":["Mayue Wang","Jiakai Liang","Chao Wang","Weibin Lu","Keqiang Yue","Wenjun Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-16T05:28:06Z","doi":"10.1016/j.phycom.2026.103272","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:25.210Z"},{"id":"doi:10.7554/elife.90597.1.sa4","name":"Author Response: Hippocampome.org v2.0: a knowledge base enabling data-driven spiking neural network simulations of rodent hippocampal circuits","source":"crossref","abstract":"","url":"https://doi.org/10.7554/elife.90597.1.sa4","authors":["Diek W. Wheeler","Jeffrey D. Kopsick","Nate Sutton","Carolina Tecuatl","Alexander O. Komendantov","Kasturi Nadella","Giorgio A. Ascoli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-27T11:31:09Z","doi":"10.7554/elife.90597.1.sa4","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/ssci47803.2020.9308435","name":"Robustness of the Scale-free Spiking Neural Network with Small-world Property","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ssci47803.2020.9308435","authors":["Dongzhao Liu","Lei Guo","Youxi Wu","Guizhi Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-01-05T23:12:38Z","doi":"10.1109/ssci47803.2020.9308435","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/icsict49897.2020.9278275","name":"Deep Spiking Binary Neural Network for Digital Neuromorphic Hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icsict49897.2020.9278275","authors":["Zilin Wang","Kefei Liu","Xiaoxin Cui","Yuan Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-22T01:01:05Z","doi":"10.1109/icsict49897.2020.9278275","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/ijcnn.2015.7280732","name":"Supervised learning in Spiking Neural Networks with limited precision: SNN/LP","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2015.7280732","authors":["Evangelos Stromatias","John S. Marsland"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-10-01T21:48:02Z","doi":"10.1109/ijcnn.2015.7280732","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1162/089976600300015907","name":"Dynamics of Strongly Coupled Spiking Neurons","source":"crossref","abstract":"We present a dynamical theory of integrate-and-fire neurons with strong synaptic coupling. We show how phase-locked states that are stable in the weak coupling regime can destabilize as the coupling is increased, leading to states characterized by spatiotemporal variations in the interspike intervals (ISIs). The dynamics is compared with that of a corresponding network of analog neurons in which the outputs of the neurons are taken to be mean firing rates. A fundamental result is that for slow interactions, there is good agreement between the two models (on an appropriately defined timescale). Various examples of desynchronization in the strong coupling regime are presented. First, a globally coupled network of identical neurons with strong inhibitory coupling is shown to exhibit oscillator death in which some of the neurons suppress the activity of others. However, the stability of the synchronous state persists for very large networks and fast synapses. Second, an asymmetric network with a mixture of excitation and inhibition is shown to exhibit periodic bursting patterns. Finally, a one-dimensional network of neurons with long-range interactions is shown to desynchronize to a state with a spatially periodic pattern of mean firing rates across the network. This is modulated by deterministic fluctuations of the instantaneous firing rate whose size is an increasing function of the speed of synaptic response.","url":"https://doi.org/10.1162/089976600300015907","authors":["Paul C. Bressloff","S. Coombes"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-27T11:57:56Z","doi":"10.1162/089976600300015907","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/ijcnn.2017.7966178","name":"The effect of biologically-inspired mechanisms in spiking neural networks for neuromorphic implementation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2017.7966178","authors":["Catherine D. Schuman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-07-10T17:41:30Z","doi":"10.1109/ijcnn.2017.7966178","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/ijcnn.2003.1223861","name":"Simulation of the visual cortex with laterally connected spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2003.1223861","authors":["Jianguo Xin","M. Embrechts"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2004-03-22T14:34:28Z","doi":"10.1109/ijcnn.2003.1223861","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1101/156786","name":"Robustness of spike deconvolution for calcium imaging of neural spiking","source":"crossref","abstract":"Abstract Calcium imaging is a powerful method to record the activity of neural populations, but inferring spike times from calcium signals is a challenging problem. We compared multiple approaches using multiple datasets with ground truth electrophysiology, and found that simple non-negative deconvolution (NND) outperformed all other algorithms. We introduce a novel benchmark applicable to recordings without electrophysiological ground truth, based on the correlation of responses to two stimulus repeats, and used this to show that unconstrained NND also outperformed the other algorithms when run on “zoomed out” datasets of ~10,000 cell recordings. Finally, we show that NND-based methods match the performance of a supervised method based on convolutional neural networks, while avoiding some of the biases of such methods, and at much faster running times. We therefore recommend that spikes be inferred from calcium traces using simple NND, due to its simplicity, efficiency and accuracy.","url":"https://doi.org/10.1101/156786","authors":["Marius Pachitariu","Carsen Stringer","Kenneth D. Harris"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-06-28T01:10:13Z","doi":"10.1101/156786","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1504/ijista.2016.078333","name":"An integrated harmony search algorithm-based multi-objective differential evolution of evolving spiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1504/ijista.2016.078333","authors":["Abdulrazak Yahya Saleh","Siti Mariyam Shamsuddin","Haza Nuzly Abdull Hamed"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-08-16T11:30:14Z","doi":"10.1504/ijista.2016.078333","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1137/090770096","name":"Dimension Reduction and Dynamics of a Spiking Neural Network Model for Decision Making under Neuromodulation","source":"crossref","abstract":"Previous models of neuromodulation in cortical circuits have used either physiologically based networks of spiking neurons or simplified gain adjustments in low-dimensional connectionist models. Here we reduce a high-dimensional spiking neuronal network model, first to a four-population mean-field model and then to a two-population model. This provides a realistic implementation of neuromodulation in low-dimensional decision-making models, speeds up simulations by three orders of magnitude, and allows bifurcation and phase-plane analyses of the reduced models that illuminate neuromodulatory mechanisms. As modulation of excitation-inhibition varies, the network can move from unaroused states, through optimal performance to impulsive states, and eventually lose inhibition-driven winner-take-all behavior: all are clear outcomes of the bifurcation structure. We illustrate the value of reduced models by a study of the speed-accuracy tradeoff in decision making. The ability of such models to recreate neuromodulatory dynamics of the spiking network will accelerate the pace of future experiments linking behavioral data to cellular neurophysiology.","url":"https://doi.org/10.1137/090770096","authors":["Philip Eckhoff","KongFatt Wong-Lin","Philip Holmes"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-02-22T18:09:26Z","doi":"10.1137/090770096","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1016/j.parco.2013.04.010","name":"Fixed latency on-chip interconnect for hardware spiking neural network architectures","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.parco.2013.04.010","authors":["Sandeep Pande","Fearghal Morgan","Gerard Smit","Tom Bruintjes","Jochem Rutgers","Brian McGinley","Seamus Cawley","Jim Harkin","Liam McDaid"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-04-26T02:40:15Z","doi":"10.1016/j.parco.2013.04.010","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/aicas59952.2024.10595965","name":"Effect of Line Resistance of Passive Memristive Crossbars on Spiking Neural Network Performance","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aicas59952.2024.10595965","authors":["Pierre Lewden","Adrien F. Vincent","Jean Tomas","Chip-Hong Chang","Sylvain Saïghi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-19T17:30:48Z","doi":"10.1109/aicas59952.2024.10595965","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1080/0952813x.2021.1957024","name":"Explainable spiking neural network for real time feature classification","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0952813x.2021.1957024","authors":["Szymon Szczęsny","Damian Huderek","Łukasz Przyborowski"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-08-03T07:57:16Z","doi":"10.1080/0952813x.2021.1957024","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/seai65851.2025.11108769","name":"Spiking Neural Network with Silicon Oxide Memristive Devices in the Subthreshold Regime","source":"crossref","abstract":"","url":"https://doi.org/10.1109/seai65851.2025.11108769","authors":["Viet Cuong Vu","Daniel J. Mannion","Dovydas Joksas","Wing H. Ng","Adnan Mehonic","Anthony Kenyon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-14T18:34:26Z","doi":"10.1109/seai65851.2025.11108769","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/tbcas.2018.2843286","name":"Analysis and Simulation of Capacitor-Less ReRAM-Based Stochastic Neurons for the in-Memory Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tbcas.2018.2843286","authors":["Jie Lin","Jiann-Shiun Yuan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-07-16T22:00:28Z","doi":"10.1109/tbcas.2018.2843286","addedAt":"2026-09-01T01:48:25.210Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1117/12.3094527","name":"Research on low illumination image enhancement algorithm based on convolutional neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3094527","authors":["Jian Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-19T07:54:19Z","doi":"10.1117/12.3094527","addedAt":"2026-09-01T01:48:25.230Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.2139/ssrn.5572368","name":"Area Efficient Hardware Architecture of Spiking Neural Networks Based on Sign-Magnitude Stochastic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5572368","authors":["Thai  N. Nguyen","Jun-Xiang Shi","Vinh  T. Nguyen","Shao-I Chu","Bing-Hong Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-06T21:40:37Z","doi":"10.2139/ssrn.5572368","addedAt":"2026-09-01T01:48:25.230Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1109/raid67961.2025.00025","name":"Unsupervised Backdoor Detection and Mitigation for Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/raid67961.2025.00025","authors":["Jiachen Li","Bang Wu","Xiaoyu Xia","Xiaoning Liu","Xun Yi","Xiuzhen Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-30T21:00:02Z","doi":"10.1109/raid67961.2025.00025","addedAt":"2026-09-01T01:48:25.230Z","updatedAt":"2026-09-01T01:48:25.230Z"},{"id":"doi:10.1016/j.neucom.2025.131523","name":"A temporally coded multilayer spiking neural network and its memristor-based hardware implementation","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2025.131523","authors":["Haochang Jin","Xiuzhi Yang","Shuangbao Song","Zhenyu Song","Junkai Ji"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-12T03:45:17Z","doi":"10.1016/j.neucom.2025.131523","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1007/978-981-95-6736-2_8","name":"Gesture Recognition via Transient sEMG Decomposition and Residual Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-95-6736-2_8","authors":["Lifen Wang","Jinting Ma","Jintao Chen","Yiyun Tan","Naifu Jiang","Guo Dan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-26T17:26:43Z","doi":"10.1007/978-981-95-6736-2_8","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1016/j.neucom.2025.131386","name":"WEI-SNNs: Spiking neural networks based on excitation-inhibition neurons and widening learnable time constants","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2025.131386","authors":["Yuwei Chen","Jiawei Chen","Zhefei Cai","Yingle Fan","Yanming Wang","Minwei Zhu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-25T23:23:12Z","doi":"10.1016/j.neucom.2025.131386","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1038/s41598-025-97913-4","name":"Research on target detection for autonomous driving based on ECS-spiking neural networks","source":"crossref","abstract":"Abstract In response to the increasing demands for improved model performance and reduced energy consumption in object detection tasks relevant to autonomous driving, this research presents an advanced YOLO model, designated as ECSLIF-YOLO, which is based on the Leaky Integrate-and-Fire with Extracellular Space (ECS-LIF) framework. The primary aim of this model is to tackle the issues associated with the high energy consumption of traditional artificial neural networks (ANNs) and the suboptimal performance of existing spiking neural networks (SNNs). Empirical findings demonstrate that ECSLIF-YOLO achieves a peak mean Average Precision (mAP) of 0.917 on the BDD100K and KITTI datasets, thereby aligning with the accuracy levels of conventional ANNs while exceeding the performance of current direct-training SNN approaches without incurring additional energy costs. These findings suggest that ECSLIF-YOLO is particularly well-suited to assist the development of efficient and reliable systems for autonomous driving.","url":"https://doi.org/10.1038/s41598-025-97913-4","authors":["Miao Jin","Xiaohong Wang","Ce Guo","Shufan Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-21T06:25:12Z","doi":"10.1038/s41598-025-97913-4","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1007/978-3-031-83882-8_13","name":"Prediction of Epileptic Seizure Using Neuroevolved Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-83882-8_13","authors":["Carlos-Alberto López-Herrera","Héctor-Gabriel Acosta-Mesa","Efrén Mezura-Montes","Jesús-Arnulfo Barradas-Palmeros"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-07T07:22:11Z","doi":"10.1007/978-3-031-83882-8_13","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1016/j.rineng.2025.105724","name":"Benchmarking reinforcement learning and accurate modeling of ground source heat pump systems: Intelligent strategy using spiking recurrent neural network combined with spider WASP inspired optimization algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.rineng.2025.105724","authors":["Sana Qaiyum","Kashif Irshad","Mohamed E. Zayed","Salem Algarni","Talal Alqahtani","Asif Irshad Khan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-14T18:39:51Z","doi":"10.1016/j.rineng.2025.105724","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.7554/elife.106871.1.sa4","name":"eLife Assessment: Neural signatures of motor memories emerge in neural network models","source":"crossref","abstract":"","url":"https://doi.org/10.7554/elife.106871.1.sa4","authors":["Rui Ponte Costa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-27T14:32:12Z","doi":"10.7554/elife.106871.1.sa4","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1016/j.neucom.2025.131402","name":"A new learning algorithm based on neuronal activity degree for spiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2025.131402","authors":["Lu Zhang","Fang Liu","Jie Yang","Wei Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-03T06:52:07Z","doi":"10.1016/j.neucom.2025.131402","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1002/9781394255306.ch3","name":"Fuzzy Neural Network Control of the Single‐Link Flexible Robotic Manipulator","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9781394255306.ch3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-03T21:38:05Z","doi":"10.1002/9781394255306.ch3","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/i2itcon65200.2025.11208866","name":"Bio-Inspired Spiking Neural Networks for Real-Time Biomedical Signal Processing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/i2itcon65200.2025.11208866","authors":["Rohan K. Shinde","Kishor D. Shinde","Pradeep B. Mane","Hrishikesh Mehta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-04T18:33:55Z","doi":"10.1109/i2itcon65200.2025.11208866","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1002/ail2.114","name":"On Training Spiking Neural Networks by Means of a Novel Quantum Inspired Machine Learning Method","source":"crossref","abstract":"ABSTRACT In spite of the high potential shown by spiking neural networks (e.g., temporal patterns), training them remains an open and complex problem. In practice, while in theory these networks are computationally as powerful as mainstream artificial neural networks, they have not reached the same accuracy levels yet. The major reason for such a situation seems to be represented by the lack of adequate training algorithms for deep spiking neural networks, since spike signals are not differentiable, that is, no direct way to compute a gradient is provided. Recently, a novel training method, based on the (digital) simulation of certain quantum systems, has been suggested. It has already shown interesting advantages, among which is the fact that no gradient is required to be computed. In this work, we apply this approach to the problem of training spiking neural networks, and we show that this recent training method is capable of training deep and complex spiking neural networks on the MNIST data set.","url":"https://doi.org/10.1002/ail2.114","authors":["Jean Michel Sellier","Alexandre Martini"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-12T05:08:53Z","doi":"10.1002/ail2.114","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1109/acoit66109.2025.11437055","name":"Paddy Plant Disease Detection Using Deep Convolutional Neural Network and Quantum Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/acoit66109.2025.11437055","authors":["Pradeep B","Naidila Sadashiv","Nagamani N Purohit"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-20T19:55:45Z","doi":"10.1109/acoit66109.2025.11437055","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/tai.2025.3534136","name":"SpikeNAS-Bench: Benchmarking NAS Algorithms for Spiking Neural Network Architecture","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tai.2025.3534136","authors":["Gengchen Sun","Zhengkun Liu","Lin Gan","Hang Su","Ting Li","Wenfeng Zhao","Biao Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-27T14:10:56Z","doi":"10.1109/tai.2025.3534136","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1109/tcasai.2025.3592865","name":"Energy-Efficient Stochastic Spiking Neural Network Hardware with 8T SRAM Array Utilizing Sub-Threshold Cascaded Current Mirrors and Stochastic CMOS Leaky Integrate-and-Fire Neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tcasai.2025.3592865","authors":["Honggu Kim","Yerim An","Dongjun Son","Jaeyoun Kim","Yong Shim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-28T19:49:13Z","doi":"10.1109/tcasai.2025.3592865","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1109/icprs66293.2025.11302823","name":"Event-based facial microexpression analysis using Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icprs66293.2025.11302823","authors":["Nicolas Mastropasqua","Ignacio Bugueno-Cordova","Rodrigo Verschae","Daniel Acevedo","Pablo Negri","Maria E. Buemi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-29T18:36:25Z","doi":"10.1109/icprs66293.2025.11302823","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1088/1402-4896/add660","name":"First demonstration of leaky-integrate and fire neuron based GAA nanosheet FET with ultra-low energy consumption down to 0.8fJ/spike for spiking neural network applications","source":"crossref","abstract":"Abstract The fundamental component of an artificial spiking neural network (SNN) is an electronic device designed to emulate a biological neuron effectively. However, a key concern is the high energy consumption and large area associated with these artificial neurons, rendering them highly inefficient. This article presents a CMOS-compatible Gate-All-Around Nanosheet Field-Effect Transistor (GAA NSFET)-based Leaky Integrate-and-Fire (LIF) neuron with gate length of 50 nm. This design achieves an exceptionally low energy consumption of 0.8 fJ, thereby establishing a new benchmark in the field. Utilizing well-calibrated 3D TCAD simulation and the SRH recombination model, along with the Unibo2 model to represent impact ionization phenomena, the proposed GAA NSFET LIF neuron effectively captures integration and recombination aspects within it. Moreover, it operates with a supply voltage of merely 1.8 V, significantly lower than conventional bulk FinFET and PD-SOI MOSFET-based LIF neurons. Also, it demonstrates spiking frequency of ~100 MHz, approximately 10 5 times higher than that of a biological neuron, controlled by the input voltage of the device, allowing the neuron adapt dynamically. Nanosheet FET technology offers superior electrostatic control, minimizing parasitic capacitances and facilitating rapid switching capabilities, thereby optimizing both power and performance simultaneously. Furthermore, the effective area of the NSFET amounts to 0.004 μ m 2 , making it an appealing choice for low-power, area-efficient, large-scale hardware implementations of SNN applications.","url":"https://doi.org/10.1088/1402-4896/add660","authors":["Madhu Kanche","Dannayak Venkata Sai Adwaith","Pavan Sai V","Venkata Ramakrishna Kotha","Sresta Valasa","Sunitha Bhukya","Shubham Tayal","Narender Malishetty","Narendar Vadthiya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-08T22:58:20Z","doi":"10.1088/1402-4896/add660","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1007/978-3-031-71533-4_23","name":"The Cost of Behavioral Flexibility: Reversal Learning Driven by a Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-71533-4_23","authors":["Behnam Ghazinouri","Sen Cheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-06T03:31:29Z","doi":"10.1007/978-3-031-71533-4_23","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1109/qai63978.2025.00025","name":"FL-QDSNNs: Federated Learning with Quantum Dynamic Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/qai63978.2025.00025","authors":["Nouhaila Innan","Alberto Marchisio","Muhammad Shafique"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-23T20:56:01Z","doi":"10.1109/qai63978.2025.00025","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.54254/2753-8818/2026.ch30863","name":"Simulating Synaptic Transmission and Learning Mechanisms in Spiking Neural Networks: From Biology to Neuromorphic Computing","source":"crossref","abstract":"Synapses are fundamental units of communication within the nervous system, enabling electrical and chemical signal transmission between neurons. This paper explores the structure and function of biological synapses, with particular emphasis on their role in information processing, learning, and memory through synaptic plasticity. Using a comparative methodology that examines biological fidelity, computational efficiency, and hardware feasibility, this paper investigates how synaptic mechanisms such as Short-Term Depression (STD) and Spike-Timing-Dependent Plasticity (STDP) are modeled in artificial systems, particularly in Spiking Neural Networks (SNNs) and neuromorphic computing. Pulse integrators—analog circuits designed to simulate synaptic signal integration—are introduced as core components bridging neuroscience and hardware implementation. This research highlights the increasing relevance of biologically inspired learning rules and hardware in the development of low-power, efficient AI systems. The conclusion emphasizes the potential of synaptic models to advance neuromorphic architectures and improve the adaptability of intelligent machines, with promising applications in edge computing, autonomous systems, and adaptive sensory processing.","url":"https://doi.org/10.54254/2753-8818/2026.ch30863","authors":["Mingzhe Cai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-24T06:34:47Z","doi":"10.54254/2753-8818/2026.ch30863","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.2139/ssrn.6402372","name":"Spiking Neural P Systems with Microglia and Delay on Synapses","source":"crossref","abstract":"Spiking neural P systems with microglia (MSNP systems) belong to the third generating of artificial neural networks. It is a computational model inspired by biological neurons that transmit and process information through spikes, and by microglia that inhibit excessive neuronal excitation. Spiking neural P systems with microglia and delay on synapses (MSNP-DS systems) are proposed in this work, with the consideration of the phenomenon that spike transmission across synapses requires time, a factor associated with synaptic length and other relevant elements. In MSNP-DS systems, synaptic delay determines that the time required for spikes sent from the same presynaptic neuron to reach different postsynaptic neurons via different synapses varies. It has been demonstrated by research that Turing universality is exhibited by MSNP-DS systems in both number generating and number accepting models, with its computational capabilities thus proven. Additionally, we constructed a small universal MSNP-DS system comprising only 37 neurons and 2 microglia for computational functions. Compared to other universal SNP systems, the advantage of consuming fewer computational resources is demonstrated by MSNP-DS systems.","url":"https://doi.org/10.2139/ssrn.6402372","authors":["Zhen Yang","Lin Wang","Yuzhen Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-12T17:40:26Z","doi":"10.2139/ssrn.6402372","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1109/iros60139.2025.11246534","name":"Adaptive Wall-Following Control for Unmanned Ground Vehicles Using Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iros60139.2025.11246534","authors":["Hengye Yang","Yanxiao Chen","Zexuan Fan","Lin Shao","Tao Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-27T18:54:45Z","doi":"10.1109/iros60139.2025.11246534","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1007/s11036-025-02480-7","name":"AI-Empowered Green Mobile Edge Computing: A Novel Framework of Spiking Neural Network Application","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11036-025-02480-7","authors":["Hieu V. Nguyen","Thanh V. Vu","Phu X. Nguyen","Mai T. P. Le","Hai-Au Huynh","Hung Nguyen-Tan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-18T06:44:35Z","doi":"10.1007/s11036-025-02480-7","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.52202/085713-2601","name":"Toward Relative Positional Encoding in Spiking Transformers","source":"crossref","abstract":"","url":"https://doi.org/10.52202/085713-2601","authors":["Changze Lv","Yansen Wang","Dongqi Han","Yifei Shen","Xiaoqing Zheng","Xuanjing Huang","Dongsheng Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-06T14:44:29Z","doi":"10.52202/085713-2601","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1007/978-981-97-2998-2_83","name":"Artificial Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-2998-2_83","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-04T10:28:26Z","doi":"10.1007/978-981-97-2998-2_83","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1016/b978-0-44-329202-6.00014-6","name":"Index","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-44-329202-6.00014-6","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-31T19:14:34Z","doi":"10.1016/b978-0-44-329202-6.00014-6","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1109/tim.2025.3625336","name":"Object Hardness Estimation With Optical Tactile Sensor Using Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tim.2025.3625336","authors":["Fei Wang","Haoyang Wu","Qiyuan Xi","Xun Jiang","Juan Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-27T17:57:29Z","doi":"10.1109/tim.2025.3625336","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1007/s11227-025-07005-3","name":"Correction: Polaris 23: a high throughput neuromorphic processing element by RISC-V customized instruction extension for spiking neural network (RV-SNN 2.0) and SIMD-style implementation of LIF model with backpropagation STDP","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11227-025-07005-3","authors":["Jixiang Zong","Jiulong Wang","Guirun Li","Ruopu Wu","Di Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-17T20:36:37Z","doi":"10.1007/s11227-025-07005-3","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1016/j.neucom.2025.131506","name":"Attacking the spike: On the security of spiking neural networks to adversarial examples","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2025.131506","authors":["Nuo Xu","Kaleel Mahmood","Haowen Fang","Ethan Rathbun","Caiwen Ding","Wujie Wen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-12T06:58:59Z","doi":"10.1016/j.neucom.2025.131506","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1109/dcis67520.2025.11281899","name":"Design Space Exploration of FPGA-Based Spiking Neural Networks for Angle of Arrival Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/dcis67520.2025.11281899","authors":["Cristina Bermúdez-Martín","Samuel López-Asunción","Pablo Ituero"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-11T18:44:08Z","doi":"10.1109/dcis67520.2025.11281899","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1109/iconscept66142.2025.11437374","name":"Gesture Recognition for EMG Signals using Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iconscept66142.2025.11437374","authors":["Keerthi Krishna Munjeti","Vijaya Kumar K","Swetha M","Kanchana S","Suresh Balanethiram"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-23T20:01:20Z","doi":"10.1109/iconscept66142.2025.11437374","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1162/isal.a.840","name":"DevNCA: Co-Evolving Developmental Patterns and Plasticity Rules for Self-Organising Spiking Neural Networks","source":"crossref","abstract":"The developing nervous system is not silent, before birth most amniote animals exhibit spontaneous neural activity. This activity has further been shown to play a role in structuring neural tissue, a finding which has since inspired work with artificial neural networks. Here we extend and clarify this research by focusing particularly on the interaction between patterned developmental activity and neural plasticity in the self-organisation of spiking neural networks. We use a modified cartpole variant as a discrete control environment to focus our analysis on three elements: (i) that evolving synapse-level spike-timing dependent plasticity rules can outperform the direct evolution of weights; (ii) that spontaneous developmental activity is essential to the consistency of this method; and (iii) that the co-evolution of NCAs as developmental pattern generators outperforms random spontaneous activity. This paper aims to provide a simple proof of concept for this method, and establishes a framework for further research exploring the role of patterned developmental activity in self-organisation.","url":"https://doi.org/10.1162/isal.a.840","authors":["Benjamin Gaskin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-08T16:36:43Z","doi":"10.1162/isal.a.840","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1007/978-3-030-36802-9_66","name":"Implementation of Spiking Neural Network with Wireless Communications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-36802-9_66","authors":["Ryuya Hiraoka","Kazuki Matsumoto","Kien Nguyen","Hiroyuki Torikai","Hiroo Sekiya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-12-05T18:03:03Z","doi":"10.1007/978-3-030-36802-9_66","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.3233/faia250137","name":"Data Encryption Method for Financial Approval Workflow in Public Institutions Based on Spiking Neural Network Technology","source":"crossref","abstract":"With the advent of the digital and intelligent finance era, in recent years, criminals have frequently utilized artificial intelligence technology to forge and tamper with financial data. Additionally, incidents of financial data and personal privacy breaches have occurred frequently during cross-organizational data sharing through financial sharing systems. To address this issue, this paper proposes a data encryption method for financial approval workflows based on spiking neural networks (SNN). This method establishes a new data encryption system by integrating a data exchange center, hierarchical permission management, differentiated encryption management, and SNN encryption. Leveraging the high complexity and randomness of SNN, it converts financial approval workflow data into difficult-to-decipher pulse sequences, thereby achieving financial data encryption.","url":"https://doi.org/10.3233/faia250137","authors":["Aiying Ye","Qi Liu","Lili Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-11T13:12:23Z","doi":"10.3233/faia250137","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1109/tnnls.2016.2541339","name":"Efficient Training of Supervised Spiking Neural Network via Accurate Synaptic-Efficiency Adjustment Method","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnnls.2016.2541339","authors":["Xiurui Xie","Hong Qu","Zhang Yi","Jurgen Kurths"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-03-30T22:07:49Z","doi":"10.1109/tnnls.2016.2541339","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.3390/app152212210","name":"Abrupt Change Detection of ECG by Spiking Neural Networks: Policy-Aware Operating Points for Edge-Level MI Screening","source":"crossref","abstract":"Electrocardiogram (ECG) monitoring on low-power edge devices requires models that balance accuracy, latency, and energy consumption. This study evaluates abrupt change detection in ECG using spiking neural networks (SNNs) trained on spike-encoded signals that preserve salient cardiac dynamics. This study used 4910 ECG segments from 290 subjects (PTB Diagnostic Database; 2.5-s windows at 1 kHz), providing context for the reported results. Under a unified architecture, preprocessing pipeline, and training schedule, we compare two representative neuron models—leaky integrate-and-fire (LIF) and adaptive exponential integrate-and-fire (AdEx). We report balanced accuracy, sensitivity, inference latency, and an energy proxy based on spike-event counts, and we examine robustness to input noise and temporal distortions. Across operating points, AdEx yields the highest overall accuracy and sensitivity, whereas LIF achieves the lowest energy cost and shortest latency, favoring deployment on resource-constrained hardware. Both SNN variants substantially reduce computational events—hence estimated energy—relative to conventional artificial neural network baselines, supporting their suitability for real-time, on-device diagnostics. These findings provide practical guidance for selecting neuron dynamics and decision thresholds to meet target accuracy–sensitivity trade-offs under energy and latency budgets. Overall, combining spike-encoded ECG with appropriately chosen SNN dynamics enables reliable abrupt change detection with notable efficiency gains, offering a path toward scalable edge-level cardiovascular monitoring. While lightweight CNNs and shallow transformers are important references, to keep the scope focused on SNN design choices and policy-aware thresholding for edge constraints, we refrain from reporting additional ANN numbers here. A seed-controlled head-to-head benchmark is reserved for future work.","url":"https://doi.org/10.3390/app152212210","authors":["Youngseok Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-18T09:58:42Z","doi":"10.3390/app152212210","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1016/b978-0-44-329202-6.00004-3","name":"Contents","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-44-329202-6.00004-3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-31T19:14:15Z","doi":"10.1016/b978-0-44-329202-6.00004-3","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1109/compsac65507.2025.00267","name":"Heart Attack Risk Prediction Using Spiking Neural Networks with Poisson-Based Temporal Encoding","source":"crossref","abstract":"","url":"https://doi.org/10.1109/compsac65507.2025.00267","authors":["Amina Almarzouqi","Syed Azizur Rahman","Said Salloum","Nabeel Al-Yateem"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-26T19:04:13Z","doi":"10.1109/compsac65507.2025.00267","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.25140/2411-5363-2025-3(41)-203-210","name":"ECG signal pre-processing method for electrocardiogram classification using spiking neural networks","source":"crossref","abstract":"The medical analysis of ECG is based on visual examination by cardiologists, which is a subjective and labor-intensive process and includes the factor of human error. With the advent of analysis based on artificial intelligence systems or algorithmic data processing, systems for classifying cardiogram data have emerged. A properly pre-processed signal is a very important component in the use of neural networks for such tasks. The analysis of studies and publications has shown that these methods have not been used for spiking neural networks based on reservoirs due to their non-standardized form, which makes training spiking neural networks more difficult and reduces the final accuracy metrics. The purpose of the article is to develop and provide a detailed description of a method for transforming ECG signals from the MIT-BIH database into standardized data arrays with values in [0,1] without losing the useful signal payload, as well as to present intermediate results from studies of individual components of the proposed method. Based on mathematical approaches to sequence processing, the work presents a new method for preliminary ECG signal processing for its further use in classification tasks. The sequence of performing such operations as signal resampling and retiming, its normalization, and additional operations necessary for complete processing is described. The method has been tested, and positive modeling results are presented in the form of a signal that characterizes a heartbeat with preserved P and T waves and QRS complex, but with amplitude adjusted to [0,1] and a standard signal length throughout one record. The proposed signal processing approach, with its comprehensive processing that consists of combining known processing methods into the following sequence (resampling, interpolation, min-max normalization) and integrating it into the processing pipeline of a spiking neural network, represents an innovative contribution to biomedical informatics, where accuracy and efficiency are key to transitioning from laboratory models to real medical systems.","url":"https://doi.org/10.25140/2411-5363-2025-3(41)-203-210","authors":["Dmytro Myloserdov","Oleg Kolesnytskyi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-09T13:32:37Z","doi":"10.25140/2411-5363-2025-3(41)-203-210","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1109/ner61569.2025.11588965","name":"Inference of Electrical Neural Stimulation Sensitivity from Recorded Spiking Activity Using Artificial Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ner61569.2025.11588965","authors":["Ethan J. Kato","Praful K. Vasireddy","Amrith P. Lotlikar","Jeff B. Brown","A. J. Phillips","Pawel Hottowy","Alexander Sher","Alan Litke","Subhasish Mitra","Nishal P. Shah","E.J. Chichilnisky"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-09T19:41:45Z","doi":"10.1109/ner61569.2025.11588965","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1002/9781394255306.ch9","name":"Disturbance Observer‐Based Neural Network Control of a Flexible Flapping‐Wing System","source":"crossref","abstract":"This chapter develops the visualization model of the rigid-flexible coupled bionic flapping wing by the advanced system-level modeling software MapleSim. A novel neural network controller based on disturbance observer technology is proposed to compensate for the system uncertainties. The proposed method can successfully suppress the vibration of the flapping wing while accurately tracking the desired trajectory. Cosimulation results from MapleSim and MATLAB/Simulink validate the effectiveness of the proposed method.","url":"https://doi.org/10.1002/9781394255306.ch9","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-03T21:38:05Z","doi":"10.1002/9781394255306.ch9","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/icassp49660.2025.10888020","name":"ECSNN: Spiking Neural Networks for Efficient Exposure Correction in Endoscopy Imaging","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icassp49660.2025.10888020","authors":["Jun Zhang","Zhuoran Zheng","Jingang Zhang","Wenqi Ren"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-12T13:52:43Z","doi":"10.1109/icassp49660.2025.10888020","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1109/icons69015.2025.00028","name":"Neuromorphic Deployment of Spiking Neural Networks for Cognitive Load Classification in Air Traffic Control","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons69015.2025.00028","authors":["Jiahui An","Chonghao Cai","Olympia Gallou","Sara Irina Fabrikant","Giacomo Indiveri","Elisa Donati"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-21T21:07:17Z","doi":"10.1109/icons69015.2025.00028","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1109/csecs64665.2025.11009396","name":"SNN-GST: Gradient-Based Security Testing Method for Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/csecs64665.2025.11009396","authors":["Lei Xu","Guohui Nie","Haibin Zheng","Chenlu Ma","Zhijun Yang","Jinyin Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-29T17:06:09Z","doi":"10.1109/csecs64665.2025.11009396","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.23919/date64628.2025.10992958","name":"Mapping Spiking Neural Networks to Heterogeneous Crossbar Architectures using Integer Linear Programming","source":"crossref","abstract":"","url":"https://doi.org/10.23919/date64628.2025.10992958","authors":["Devin Pohl","Aaron Young","Kazi Asifuzzaman","Narasinga Rao Miniskar","Jeffrey S. Vetter"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-21T17:36:35Z","doi":"10.23919/date64628.2025.10992958","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.32920/29873789.v1","name":"Botnet Detection Mechanism Using Graph Neural Network","source":"crossref","abstract":"Botnet Detection Mechanism Based On Graph Neural Network Aleksander Maksimoski, 2023. Master of Applied Science Computer Networks Toronto Metropolitan University, Toronto, Ontario, Canada. A botnet is a group of computers that are infected by malware, which can be utilized to wreak havoc on other computers. In the literature, various techniques have been proposed to detect the presence of botnets in networks and systems. Nowadays, Intrusion Detection Systems and Intrusion Prevention Systems are capable of defending against botnets that create volumetric and fast-paced traffic. However, these systems are not well suited to address prevalent real-time, long-term, and stealth attacks. This thesis proposes a Graph Neural Network (GNN)-based method for detecting botnet activity based on supervised learning. This work is the first-ever application of the Activity and Event Network framework to build a GNN model for botnet detection purposes. The proposed model is evaluated using five different labeled datasets, yielding preliminary promising results in terms of botnet prediction, using precision, recall, F1-score, and accuracy as performance metrics.&lt;p&gt;&lt;/p&gt;","url":"https://doi.org/10.32920/29873789.v1","authors":["Aleksander Masimoski"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-04T18:45:26Z","doi":"10.32920/29873789.v1","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/asens64990.2025.11011158","name":"Behavior Recognition Model for Pigs Based on Convolutional Neural Network (CNN) Model EfficientNet and Recurrent Neural Network (RNN) Model BiLSTM","source":"crossref","abstract":"","url":"https://doi.org/10.1109/asens64990.2025.11011158","authors":["Nan Li","Han Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-27T17:05:15Z","doi":"10.1109/asens64990.2025.11011158","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.32920/29873789","name":"Botnet Detection Mechanism Using Graph Neural Network","source":"crossref","abstract":"Botnet Detection Mechanism Based On Graph Neural Network Aleksander Maksimoski, 2023. Master of Applied Science Computer Networks Toronto Metropolitan University, Toronto, Ontario, Canada. A botnet is a group of computers that are infected by malware, which can be utilized to wreak havoc on other computers. In the literature, various techniques have been proposed to detect the presence of botnets in networks and systems. Nowadays, Intrusion Detection Systems and Intrusion Prevention Systems are capable of defending against botnets that create volumetric and fast-paced traffic. However, these systems are not well suited to address prevalent real-time, long-term, and stealth attacks. This thesis proposes a Graph Neural Network (GNN)-based method for detecting botnet activity based on supervised learning. This work is the first-ever application of the Activity and Event Network framework to build a GNN model for botnet detection purposes. The proposed model is evaluated using five different labeled datasets, yielding preliminary promising results in terms of botnet prediction, using precision, recall, F1-score, and accuracy as performance metrics.&lt;p&gt;&lt;/p&gt;","url":"https://doi.org/10.32920/29873789","authors":["Aleksander Masimoski"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-04T18:45:25Z","doi":"10.32920/29873789","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ieeeconf62907.2025.10949115","name":"Spiking Neural Belief Propagation Decoder for LDPC Codes with Small Variable Node Degrees","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ieeeconf62907.2025.10949115","authors":["Alexander von Bank","Eike-Manuel Edelmann","Jonathan Mandelbaum","Laurent Schmalen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-11T17:52:20Z","doi":"10.1109/ieeeconf62907.2025.10949115","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1016/j.neunet.2024.106816","name":"Language-based reasoning graph neural network for commonsense question answering","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106816","authors":["Meng Yang","Yihao Wang","Yu Gu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-18T22:21:44Z","doi":"10.1016/j.neunet.2024.106816","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1109/iemcon67450.2025.11381151","name":"SpiCAE: Spiking Contrastive Learning and Autoencoder for Network Intrusion Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iemcon67450.2025.11381151","authors":["Elijah Sagaran","Jacob Spier","Rashida Hasan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-16T21:03:05Z","doi":"10.1109/iemcon67450.2025.11381151","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1117/12.3070058","name":"Can invisible physical events easily fool spiking neural networks?","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3070058","authors":["Adir Hazan","Ido Avrahami","Adrian Stern"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-27T23:15:47Z","doi":"10.1117/12.3070058","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1109/vtc2025-spring65109.2025.11174873","name":"Real-Time Optimization of 5G/6G Signal Transmissions Using Spiking Neural Networks and Asynchronous Federated Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/vtc2025-spring65109.2025.11174873","authors":["Yongtao Wei","Siqi Wang","Farid Nait-Abdesselam","Aziz Benlarbi-Delai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T17:36:40Z","doi":"10.1109/vtc2025-spring65109.2025.11174873","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1016/j.engappai.2026.113805","name":"Spiking neural network-based energy-efficient framework for real-time robotic arm manipulation","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.engappai.2026.113805","authors":["Ashok Kumar Saini","Naveen Gehlot","Rajesh Kumar","Surender Hans","Santosh Chaudhary","Gulshan Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-18T03:08:54Z","doi":"10.1016/j.engappai.2026.113805","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.3390/app16042073","name":"AEFSNN: Adaptive Filtering Spiking Neural Network for Event-Based Sensors","source":"crossref","abstract":"Dynamic Vision Sensor (DVS) is an event-based imaging technology inspired by biological photoreceptors, which holds great promise for edge computing. The event streams produced by DVS are often contaminated by Background Activity (BA) noise and hot-pixel noise, which degrade downstream processing. Existing filters typically use fixed parameters, resulting in poor adaptability to changing illumination. In this paper, we propose a lightweight Adaptive Event-based Filtering Spiking Neural Network (AEFSNN) to address these limitations. Inspired by homeostatic plasticity, AEFSNN dynamically adjusts neuronal thresholds by monitoring the input-to-output spike ratio, allowing the network to autonomously converge to an optimal operating point across different lighting conditions. Furthermore, we introduce a novel neuronal wake-up mechanism that inhibits processing neurons until triggered by valid input, which effectively suppresses redundant events generated by neighboring activity. Experiments show that AEFSNN is more robust under varying illumination. Compared with current filters, our method increases the Signal-to-Noise Ratio (SNR) of the output data by 1.42–2.33 dB. Additionally, the filtered data improves classification accuracy on downstream tasks, validating its practical value for neuromorphic vision systems.","url":"https://doi.org/10.3390/app16042073","authors":["Yue Xu","Ye Zhao","Yumeng Ren","Long Chen","Liang Chen","Yulin Zhang","Shushan Qiao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-20T10:32:37Z","doi":"10.3390/app16042073","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1109/gcce65946.2025.11275067","name":"Spiking Neural Networks with Energy to Spike Encoding for Label-Free Detection in Distributed Acoustic Sensing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/gcce65946.2025.11275067","authors":["Mohd Safuwan Shahabudin","Jafreezal Jaafar","Irving Vitra Paputungan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-12T18:33:24Z","doi":"10.1109/gcce65946.2025.11275067","addedAt":"2026-09-01T01:48:25.231Z","updatedAt":"2026-09-01T01:48:25.231Z"},{"id":"doi:10.1007/978-3-031-48655-5_1","name":"Introduction to Neural Networks: Biological Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-48655-5_1","authors":["Alessandro Bile"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-21T07:02:28Z","doi":"10.1007/978-3-031-48655-5_1","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1007/978-3-031-72359-9_31","name":"Temporal Contrastive Learning for Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-72359-9_31","authors":["Haonan Qiu","Zeyin Song","Yanqi Chen","Munan Ning","Wei Fang","Tao Sun","Zhengyu Ma","Li Yuan","Yonghong Tian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-18T12:28:54Z","doi":"10.1007/978-3-031-72359-9_31","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1088/1741-2552/ad6594","name":"Spiking Laguerre Volterra networks—predicting neuronal activity from local field potentials","source":"crossref","abstract":"Abstract Objective. Understanding the generative mechanism between local field potentials (LFP) and neuronal spiking activity is a crucial step for understanding information processing in the brain. Up to now, most approaches have relied on simply quantifying the coupling between LFP and spikes. However, very few have managed to predict the exact timing of spike occurrence based on LFP variations. Approach. Here, we fill this gap by proposing novel spiking Laguerre–Volterra network (sLVN) models to describe the dynamic LFP-spike relationship. Compared to conventional artificial neural networks, the sLVNs are interpretable models that provide explainable features of the underlying dynamics. Main results. The proposed networks were applied on extracellular microelectrode recordings of Parkinson’s Disease patients during deep brain stimulation (DBS) surgery. Based on the predictability of the LFP-spike pairs, we detected three neuronal populations with unique signal characteristics and sLVN model features. Significance. These clusters were indirectly associated with motor score improvement following DBS surgery, warranting further investigation into the potential of spiking activity predictability as an intraoperative biomarker for optimal DBS lead placement.","url":"https://doi.org/10.1088/1741-2552/ad6594","authors":["Kyriaki Kostoglou","Konstantinos P Michmizos","Pantelis Stathis","Damianos Sakas","Konstantina S Nikita","Georgios D Mitsis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-19T20:03:40Z","doi":"10.1088/1741-2552/ad6594","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1007/978-3-032-04558-4_41","name":"A Unified Platform to Evaluate STDP Learning Rule and Synapse Model Using Pattern Recognition in a Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-04558-4_41","authors":["Jaskirat Singh Maskeen","Sandip Lashkare"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-11T11:17:18Z","doi":"10.1007/978-3-032-04558-4_41","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1007/978-3-031-67447-1_22","name":"Modulation Classification Through Convolutional Spiking Neural Networks with Data Fusion","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-67447-1_22","authors":["Gandhimathi Velusamy","Ricardo Lent"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-07T06:17:40Z","doi":"10.1007/978-3-031-67447-1_22","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1109/led.2024.3439532","name":"Low-Energy Spiking Neural Network Using Ge<sub>4</sub>Sb<sub>6</sub>Te<sub>7</sub> Phase Change Memory Synapses","source":"crossref","abstract":"","url":"https://doi.org/10.1109/led.2024.3439532","authors":["Shafin Bin Hamid","Asir Intisar Khan","Huairuo Zhang","Albert V. Davydov","Eric Pop"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-06T18:10:50Z","doi":"10.1109/led.2024.3439532","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.15588/1607-3274-2024-4-8","name":"ENSEMBLE OF SIMPLE SPIKING NEURAL NETWORKS AS A CONCEPT DRIFT DETECTOR","source":"crossref","abstract":"Context. This paper provides a new approach in concept drift detection using an ensemble of simple spiking neural networks. Such approach utilizes an event-based nature and built-in ability to learn spatio-temporal patterns of spiking neurons, while ensemble provides additional robustness and scalability. This can help solve an active problem of limited time and processing resources in tasks of online machine learning, especially in very strict environments like IoT which also benefit in other ways from the use of spiking computations. Objective. The aim of the work is the creation of an ensemble of simple spiking neural networks to act as a concept drift detector in the tasks of online data stream mining. Method. The proposed approach is primary based on the accumulative nature of spiking neural networks, especially Leaky Integrate-and-Fire neurons can be viewed as gated memory units, where membrane time constant Гm is a balance constant between remembering and forgetting information. A training algorithm is implemented that utilizes a shallow two-layer SNN, which takes features and labels of the data as an input layer and the second layer consists of a single neuron. This neuron’s activation implies that an abrupt drift has occurred. In addition to that, such model is used as a base model within the ensemble to improve robustness, accuracy and scalability. Results. An ensemble of shallow two-layer SNNs was implemented and trained to detect abrupt concept drift in the SEA data stream. The ensemble managed to improve accuracy significantly compared to a base model and achieved competitive results to modern state-of-the-art models. Conclusions. Results showcased the viability of the proposed solution, which not only provides a cheap and competitive solution for resource-restricted environments, but also open doors for further research of SNN’s ability to learn spatio-temporal patters in the data streams and other fields.","url":"https://doi.org/10.15588/1607-3274-2024-4-8","authors":["Ye. V. Bodyanskiy","D. V. Savenkov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-26T14:45:27Z","doi":"10.15588/1607-3274-2024-4-8","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1201/9781003572886","name":"Neural Network Analysis, Architectures and Applications","source":"crossref","abstract":"From the Publisher: This book describes techniques for extracting what has been learnt by a trained neural network. The book also describes some novel neural network architectures, and some sample applications of neural computing systems.","url":"https://doi.org/10.1201/9781003572886","authors":["A Browne"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-10T09:11:09Z","doi":"10.1201/9781003572886","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.2172/2429319","name":"Predicting Missing Regions in Charged Particle Tracks Using a Sparse 3D Convolutional Neural Network","source":"crossref","abstract":"The 2x2 Demonstrator is a prototype detector for the Deep Underground Neutrino Experiment (DUNE)'s Near Detector. Both the 2x2 Demonstrator and the Near Detector itself will have inactive regions wherein there is no sensitivity to charge deposition and light signals that arise from charged particle interactions with liquid argon. In the 2x2, these inactive regions are positioned in-between the active detector modules, which introduces the challenge of inferring what charge signals ought to look like in these regions. This study explores the use of a Sparse 3D Convolutional Neural Network (ConvNet) to infer missing regions in charged particle tracks. Hits corresponding to energy depositions are voxelized into a three-dimensional (3D) grid for each track. Inactive regions within the tracks are replaced with a dense, rectangular 3D grid of voxels, ensuring consistent step sizes in X, Y, and Z directions. Voxels in these dense regions are initialized with an energy value of -1, indicating nonphysical energy or charge. The model is trained to predict which voxels should activate as part of the track and which should not, with the goal of eventually inferring the missing charge or energy values in these voxels. Results indicate that the model accurately predicts track voxels within ±1 unit in X, Y, or Z directions and effectively identifies non-track voxels, despite some overprediction. The approach shows promise in prediction of missing track regions with some accuracy.","url":"https://doi.org/10.2172/2429319","authors":["Hilary Utaegbulam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-15T02:30:21Z","doi":"10.2172/2429319","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1016/j.neunet.2024.106095","name":"Understanding the role of pathways in a deep neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106095","authors":["Lei Lyu","Chen Pang","Jihua Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-04T08:43:24Z","doi":"10.1016/j.neunet.2024.106095","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1093/oed/1168220282","name":"spiking, n.¹","source":"crossref","abstract":"","url":"https://doi.org/10.1093/oed/1168220282","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-19T17:18:24Z","doi":"10.1093/oed/1168220282","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1109/dttis62212.2024.10780090","name":"Fast Exploration of the Impact of Precision Reduction on Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/dttis62212.2024.10780090","authors":["Sepide Saeedi","Alessio Carpegna","Alessandro Savino","Stefano Di Carlo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-13T18:49:01Z","doi":"10.1109/dttis62212.2024.10780090","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1016/j.neunet.2024.106496","name":"Cross-layer importance evaluation for neural network pruning","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106496","authors":["Youzao Lian","Peng Peng","Kai Jiang","Weisheng Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-03T16:45:48Z","doi":"10.1016/j.neunet.2024.106496","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1109/radarconf2458775.2024.10549488","name":"High-Resolution Range Profile Target Recognition with Neuromorphic ADCs and Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/radarconf2458775.2024.10549488","authors":["Sanjaya Herath","Matthew R. Ziemann","Kevin Wagner","Christopher A. Metzler"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-13T17:34:17Z","doi":"10.1109/radarconf2458775.2024.10549488","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1002/ett.70019","name":"Spiking Quantum Fire Hawk Network Based Reliable Scheduling for Lifetime Maximization of Wireless Sensor Network","source":"crossref","abstract":"ABSTRACT Managing energy consumption poses a substantial challenge within Wireless Sensor Networks (WSN) due to frequent communication among sensor nodes. A reliable scheduling framework presents a promising solution for maximizing WSN lifetime, minimizing energy consumption, and ensuring robust communication. Despite various proposed methods for reliable scheduling, energy consumption remains high. To address this, a spiking quantum fire hawk network‐based reliable scheduling in WSN is introduced. This research incorporates clustering, duty‐cycle management, and reliable routing to enhance energy efficiency. An improved Nutcracker Optimization‐based Cluster Head (CH) election and Spiking Quantum Fire Hawk Network duty cycling contribute to optimal CH selection and increased network lifetime. Additionally, a Link Quality‐based Energy Aware Proficient Trusted Routing Protocol (LQEAP‐TRP) minimizes data transmission delay, offering reliable routing. Finally, the data communication is done in the reliable route. The developed approach is executed in Network Simulator and validated with the existing protocols. The results of the simulations indicate that the proposed approach achieves a network lifetime of 99.34% and a packet delivery ratio of 99.95%.","url":"https://doi.org/10.1002/ett.70019","authors":["W. S. Kiran","Allan J. Wilson","A. S. Radhamani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-12T09:31:03Z","doi":"10.1002/ett.70019","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.3389/fnins.2024.1412559","name":"Composing recurrent spiking neural networks using locally-recurrent motifs and risk-mitigating architectural optimization","source":"crossref","abstract":"In neural circuits, recurrent connectivity plays a crucial role in network function and stability. However, existing recurrent spiking neural networks (RSNNs) are often constructed by random connections without optimization. While RSNNs can produce rich dynamics that are critical for memory formation and learning, systemic architectural optimization of RSNNs is still an open challenge. We aim to enable systematic design of large RSNNs via a new scalable RSNN architecture and automated architectural optimization. We compose RSNNs based on a layer architecture called Sparsely-Connected Recurrent Motif Layer (SC-ML) that consists of multiple small recurrent motifs wired together by sparse lateral connections. The small size of the motifs and sparse inter-motif connectivity leads to an RSNN architecture scalable to large network sizes. We further propose a method called Hybrid Risk-Mitigating Architectural Search (HRMAS) to systematically optimize the topology of the proposed recurrent motifs and SC-ML layer architecture. HRMAS is an alternating two-step optimization process by which we mitigate the risk of network instability and performance degradation caused by architectural change by introducing a novel biologically-inspired “self-repairing” mechanism through intrinsic plasticity. The intrinsic plasticity is introduced to the second step of each HRMAS iteration and acts as unsupervised fast self-adaptation to structural and synaptic weight modifications introduced by the first step during the RSNN architectural “evolution.” We demonstrate that the proposed automatic architecture optimization leads to significant performance gains over existing manually designed RSNNs: we achieve 96.44% on TI46-Alpha, 94.66% on N-TIDIGITS, 90.28% on DVS-Gesture, and 98.72% on N-MNIST. To the best of the authors' knowledge, this is the first work to perform systematic architecture optimization on RSNNs.","url":"https://doi.org/10.3389/fnins.2024.1412559","authors":["Wenrui Zhang","Hejia Geng","Peng Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-20T05:10:55Z","doi":"10.3389/fnins.2024.1412559","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1109/isqed60706.2024.10528734","name":"DESPINE: NAS generated Deep Evolutionary Adaptive Spiking Network for Low Power Edge Computing Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isqed60706.2024.10528734","authors":["Ajay B S","Phani Pavan K","Madhav Rao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-16T17:21:18Z","doi":"10.1109/isqed60706.2024.10528734","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.32920/25761549","name":"Portfolio Selection with Convolutional Neural Network","source":"crossref","abstract":"&lt;p&gt;In this work, we applied Convolutional Neural network (CNN) models to select the portfolio weights that lead to the highest realized return in one time-step ahead. In fact, given four possible portfolio optimization methods, the CNN is used to forecast the one-step-ahead returns of the assets in the portfolio implicitly and selects the portfolio optimization approach leading to the highest portfolio return. We construct four different datasets based on the daily return time series of the 36 stocks in our portfolio. In each dataset, one instance is composed of the mean vector and the covariance matrix. The four datasets are obtained as a result of using four different methods to calculate mean vectors and covariance matrices. Six different CNN model architectures are constructed, and the models' performances are compared. The obtained results demonstrate the effectiveness of CNNs in portfolio selection.&lt;/p&gt;","url":"https://doi.org/10.32920/25761549","authors":["Fahimeh Saei Manesh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-06T19:13:09Z","doi":"10.32920/25761549","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.2172/2432384","name":"Predicting Missing Regions in Charged Particle Tracks Using a Sparse 3D Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.2172/2432384","authors":["Hilary Utaegbulam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-23T03:09:58Z","doi":"10.2172/2432384","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1109/coins61597.2024.10622154","name":"Exploring 8-Bit Arithmetic for Training Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/coins61597.2024.10622154","authors":["T. Fernandez-Hart","T. Kalganova","James C. Knight"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-15T17:18:58Z","doi":"10.1109/coins61597.2024.10622154","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1109/cvpr52733.2024.00536","name":"SpikingResformer: Bridging ResNet and Vision Transformer in Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cvpr52733.2024.00536","authors":["Xinyu Shi","Zecheng Hao","Zhaofei Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-16T17:34:53Z","doi":"10.1109/cvpr52733.2024.00536","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1109/smc54092.2024.10831542","name":"A Brain Tumor Segmentation Approach with Adaptive Threshold Optimization Numerical Spiking Neural P Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/smc54092.2024.10831542","authors":["Jianping Dong","Gexiang Zhang","Haina Rong","Giancarlo Fortin","Min Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-20T18:39:20Z","doi":"10.1109/smc54092.2024.10831542","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1109/vlsitsa60681.2024.10546383","name":"Training Process of Memristor-Based Spiking Neural Networks For Non-linearity","source":"crossref","abstract":"","url":"https://doi.org/10.1109/vlsitsa60681.2024.10546383","authors":["Tsu-Hsiang Chen","Chih-Chun Chang","Chih-Tsun Huang","Jing-Jia Lioul"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-10T17:20:11Z","doi":"10.1109/vlsitsa60681.2024.10546383","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1093/oed/8611538756","name":"spiking, adj.","source":"crossref","abstract":"","url":"https://doi.org/10.1093/oed/8611538756","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-19T17:18:24Z","doi":"10.1093/oed/8611538756","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1109/icassp48485.2024.10445826","name":"Recent Advances in Scalable Energy-Efficient and Trustworthy Spiking Neural Networks: from Algorithms to Technology","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icassp48485.2024.10445826","authors":["Souvik Kundu","Rui-Jie Zhu","Akhilesh Jaiswal","Peter A. Beerel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-18T18:56:31Z","doi":"10.1109/icassp48485.2024.10445826","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.24963/ijcai.2024/157","name":"Tackling Long-Tailed Data Challenges in Spiking Neural Networks via Heterogeneous Knowledge Distillation","source":"crossref","abstract":"Spiking Neural Networks (SNNs), inspired by the behavior of biological neurons, have gained significant research interest for resource-constrained edge devices and neuromorphic hardware due to their use of binary spike signals for inter-unit communication with low power consumption. However, the absence of research on spiking neural networks on long-tailed data has severely limited the deployment and application of this emerging network in practical scenarios. To fill this gap, this paper proposes a long-tail learning framework based on spiking neural networks, named LT-SpikingFormer, to alleviate the distribution bias between head and tail classes. LT-SpikingFormer adopts a widely trained Convolutional Neural Network to construct a heterogeneous knowledge distillation paradigm, offering balanced and reliable prior knowledge. Moreover, a multi-granularity hierarchical feature distillation objective is proposed to leverage cross-layer local features and network global predictions to facilitate refined information distillation to optimize the network, specifically for the performance of the tailed classes. Extensive experimental results demonstrate that our method performs well on several benchmark datasets.","url":"https://doi.org/10.24963/ijcai.2024/157","authors":["Moqi Li","Xu Yang","Cheng Deng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-26T10:28:11Z","doi":"10.24963/ijcai.2024/157","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1109/iscas58744.2024.10557875","name":"Advancing Image Classification with Phase-coded Ultra-Efficient Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas58744.2024.10557875","authors":["Zhengyu Cai","Hamid Rahimian Kalatehbali","Ben Walters","Mostafa Rahimi Azghadi","Roman Genov","Amirali Amirsoleimani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-02T17:22:52Z","doi":"10.1109/iscas58744.2024.10557875","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1080/0954898x.2024.2351146","name":"Optimized Wasserstein Deep Convolutional Generative Adversarial Network fostered Groundnut Leaf Disease Identification System","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2024.2351146","authors":["Anna Anbumozhi","Shanthini A"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-02T10:16:57Z","doi":"10.1080/0954898x.2024.2351146","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/icedcs64328.2024.00107","name":"Research on competition score prediction based on GA-BP neural network model and RBP inverse neural network model","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icedcs64328.2024.00107","authors":["Jiahang Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-16T18:31:54Z","doi":"10.1109/icedcs64328.2024.00107","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1080/0954898x.2024.2438128","name":"Robust text-dependent speaker verification system using gender aware Siamese-Triplet Deep Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2024.2438128","authors":["Sanghamitra V. Arora"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-29T04:14:53Z","doi":"10.1080/0954898x.2024.2438128","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1190/geo2023-0737.1","name":"Bayesian neural network and Bayesian physics-informed neural network via variational inference for seismic petrophysical inversion","source":"crossref","abstract":"ABSTRACT Deep-learning methods are being successfully applied to seismic inversion and reservoir characterization problems; however, the uncertainty quantification process has not been fully studied. We investigate probabilistic approaches for seismic petrophysical inversion by using Bayesian formulations of neural networks. In particular, Bayesian neural network via variational inference (BNN-VI) aims to estimate the probability distribution of the training parameters of the neural network, which are difficult to compute with traditional methods, by proposing a family of densities and finding the candidates that are close to the target. Variational inference (VI) has the advantage of providing a faster tool than Markov chain Monte Carlo sampling algorithms. However, for accurate predictions, BNN-VI requires large training data that are not always available in geophysical inverse problems. Hence, we develop a method that combines a Bayesian approach with physics-informed neural networks (PINNs) via VI, namely Bayesian PINNs via VI (BPINN-VI), and we apply it to a geophysical inverse problem for the estimation of petrophysical properties from seismic data. The method is based on a Bayesian network approach in which the objective function is defined by the Kullback-Leibler divergence. In addition, the physical relations between data (seismic measurements) and model variables (petrophysical properties) are embedded into neural networks through a physics-dependent loss term. We test our method on a synthetic prestack seismic data set and a real data set including an oil-saturated clastic reservoir in the North Sea with a sequence of sand and shale layers. The outcome is the most likely model of petrophysical properties. Compared with BNN-VI, the BPINN-VI results show higher correlations and R2 coefficients, lower mean-square errors, as well as lower uncertainty and higher lateral continuity.","url":"https://doi.org/10.1190/geo2023-0737.1","authors":["Peng Li","Dario Grana","Mingliang Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-31T09:13:05Z","doi":"10.1190/geo2023-0737.1","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.2172/3001122","name":"Identifying Recurrent Causal Activity Patterns in Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.2172/3001122","authors":["Bradley Theilman","Felix Wang","Fredrick Rothganger","James Aimone"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-08T08:01:47Z","doi":"10.2172/3001122","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1038/s41598-024-59469-7","name":"Convolutional spiking neural networks for intent detection based on anticipatory brain potentials using electroencephalogram","source":"crossref","abstract":"Abstract Spiking neural networks (SNNs) are receiving increased attention because they mimic synaptic connections in biological systems and produce spike trains, which can be approximated by binary values for computational efficiency. Recently, the addition of convolutional layers to combine the feature extraction power of convolutional networks with the computational efficiency of SNNs has been introduced. This paper studies the feasibility of using a convolutional spiking neural network (CSNN) to detect anticipatory slow cortical potentials (SCPs) related to braking intention in human participants using an electroencephalogram (EEG). Data was collected during an experiment wherein participants operated a remote-controlled vehicle on a testbed designed to simulate an urban environment. Participants were alerted to an incoming braking event via an audio countdown to elicit anticipatory potentials that were measured using an EEG. The CSNN’s performance was compared to a standard CNN, EEGNet and three graph neural networks via 10-fold cross-validation. The CSNN outperformed all the other neural networks, and had a predictive accuracy of 99.06% with a true positive rate of 98.50%, a true negative rate of 99.20% and an F1-score of 0.98. Performance of the CSNN was comparable to the CNN in an ablation study using a subset of EEG channels that localized SCPs. Classification performance of the CSNN degraded only slightly when the floating-point EEG data were converted into spike trains via delta modulation to mimic synaptic connections.","url":"https://doi.org/10.1038/s41598-024-59469-7","authors":["Nathan Lutes","Venkata Sriram Siddhardh Nadendla","K. Krishnamurthy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-17T05:04:12Z","doi":"10.1038/s41598-024-59469-7","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1038/s42005-024-01869-2","name":"Exploring the potential of self-pulsing optical microresonators for spiking neural networks and sensing","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s42005-024-01869-2","authors":["Stefano Biasi","Alessio Lugnan","Davide Micheli","Lorenzo Pavesi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-22T15:32:21Z","doi":"10.1038/s42005-024-01869-2","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1093/oed/3796793133","name":"spiking, n.²","source":"crossref","abstract":"","url":"https://doi.org/10.1093/oed/3796793133","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-19T17:18:24Z","doi":"10.1093/oed/3796793133","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1109/qrs-c63300.2024.00061","name":"High Accurate, Low Latency Conversion of Spiking Neural Networks with BLIF Neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1109/qrs-c63300.2024.00061","authors":["Zhongxi Wang","Shen Lil","Zhong Ma","Qin Yao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-29T17:28:50Z","doi":"10.1109/qrs-c63300.2024.00061","addedAt":"2026-09-01T01:48:25.337Z","updatedAt":"2026-09-01T01:48:25.337Z"},{"id":"doi:10.1021/acsami.3c12244","name":"Artificial Tactile Perception System Based on Spiking Tactile Neurons and Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acsami.3c12244","authors":["Juan Wen","Le Zhang","Yu-Zhe Wang","Xin Guo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-20T13:37:41Z","doi":"10.1021/acsami.3c12244","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1080/00051144.2024.2346964","name":"A cross layer graphical neural network based convolutional neural network framework for image dehazing","source":"crossref","abstract":"","url":"https://doi.org/10.1080/00051144.2024.2346964","authors":["M. Pavethra","M. Uma Devi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-09T07:46:56Z","doi":"10.1080/00051144.2024.2346964","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1007/s11071-024-09525-8","name":"Spiking SiamFC++: deep spiking neural network for object tracking","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11071-024-09525-8","authors":["Shuiying Xiang","Tao Zhang","Shuqing Jiang","Yanan Han","Yahui Zhang","Xingxing Guo","Licun Yu","Yuechun Shi","Yue Hao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-03T16:02:02Z","doi":"10.1007/s11071-024-09525-8","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.2139/ssrn.4706194","name":"Spiking-Detr: A Spike-Driven End-to-End Object Detection Framework on Spike-Form Data Streams Using Spiking-Transformer and Spiking Residual Learning","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4706194","authors":["Hanyu Ouyang","Jie Jiang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-25T07:20:13Z","doi":"10.2139/ssrn.4706194","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.23919/ccc63176.2024.10661413","name":"A Neural Network to A Neural Network: A Structured Neural Network Controller Design with Stability and Optimality Guarantees","source":"crossref","abstract":"","url":"https://doi.org/10.23919/ccc63176.2024.10661413","authors":["Jiajun Qian","Yizhou Ji","Liang Xu","Xiaoqiang Ren","Xiaofan Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-17T18:46:36Z","doi":"10.23919/ccc63176.2024.10661413","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.7554/elife.90597.3","name":"Hippocampome.org 2.0 is a knowledge base enabling data-driven spiking neural network simulations of rodent hippocampal circuits","source":"crossref","abstract":"Hippocampome.org is a mature open-access knowledge base of the rodent hippocampal formation focusing on neuron types and their properties. Previously, Hippocampome.org v1.0 established a foundational classification system identifying 122 hippocampal neuron types based on their axonal and dendritic morphologies, main neurotransmitter, membrane biophysics, and molecular expression (Wheeler et al., 2015). Releases v1.1 through v1.12 furthered the aggregation of literature-mined data, including among others neuron counts, spiking patterns, synaptic physiology, in vivo firing phases, and connection probabilities. Those additional properties increased the online information content of this public resource over 100-fold, enabling numerous independent discoveries by the scientific community. Hippocampome.org v2.0, introduced here, besides incorporating over 50 new neuron types, now recenters its focus on extending the functionality to build real-scale, biologically detailed, data-driven computational simulations. In all cases, the freely downloadable model parameters are directly linked to the specific peer-reviewed empirical evidence from which they were derived. Possible research applications include quantitative, multiscale analyses of circuit connectivity and spiking neural network simulations of activity dynamics. These advances can help generate precise, experimentally testable hypotheses and shed light on the neural mechanisms underlying associative memory and spatial navigation.","url":"https://doi.org/10.7554/elife.90597.3","authors":["Diek W Wheeler","Jeffrey D Kopsick","Nate Sutton","Carolina Tecuatl","Alexander O Komendantov","Kasturi Nadella","Giorgio A Ascoli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-12T12:15:41Z","doi":"10.7554/elife.90597.3","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1007/978-3-031-64106-0_43","name":"Spiking Convolution Engine for Spiking Convolution Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-64106-0_43","authors":["Dagnier A. Curra-Sosa","Ricardo Tapiador-Morales","Francisco Gómez-Rodríguez","Alejandro Linares-Barranco"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-11T15:01:52Z","doi":"10.1007/978-3-031-64106-0_43","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1039/d4sm01391c/v1/review2","name":"Review for \"Scalability of Graph Neural Network in Accurate Prediction of Frictional Contact Network in Suspensions\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d4sm01391c/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-20T16:16:00Z","doi":"10.1039/d4sm01391c/v1/review2","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1002/ett.70430","name":"Low Latency Basketball Action Recognition and Game Technology Analysis Based on Spiking Neural Network Under\n                    <scp>SAGIN</scp>\n                    Environment","source":"crossref","abstract":"ABSTRACT Basketball action recognition based on wearable devices and deep learning has been widely applied in the field of behavior analysis. However, there is an urgent need for real‐time recognition of athlete movements, precise technical analysis, and data privacy protection in modern basketball training and competitions. To this end, this article proposes a low‐latency basketball action recognition and game technology analysis framework based on multimodal spiking neural networks (SNNs) under the space air ground‐integrated network (SAGIN) environment. This study utilizes multiple wearable sensors to synchronously collect high‐frequency multimodal time series signals. To effectively process these sensing data with high spatiotemporal complexity, we design an effective feature extraction backbone based on SNNs which can capture temporal information of time series data with low computational complexity and low latency. In addition, to improve the recognition accuracy and robustness of complex basketball actions, we exploit the joint learning module to enhance multimodal information fusion. At last, to address the issue of data silos and ensure user data privacy, we adopt a personalized federated learning paradigm, allowing all parties involved to collaboratively optimize the global model without sharing local raw data. Our proposed method has been evaluated on various public datasets, including OPPORTUNITY, PAMAP2, SKODA, and our self‐built basketball action dataset. The extensive experimental results demonstrate that our approach achieves significant performance and is more robust to noise compared to other deep models. Our proposed framework can achieve high‐precision real‐time action classification and fine‐grained technical statistical analysis while ensuring low communication and computing overhead, providing an effective technical solution for the intelligent and personalized development of basketball sports in the context of integrated aerospace networks.","url":"https://doi.org/10.1002/ett.70430","authors":["Yi Kao","Chao Wei"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-26T09:43:22Z","doi":"10.1002/ett.70430","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1080/0954898x.2024.2392786","name":"Optimized memory augmented graph neural network-based DoS attacks detection in wireless sensor network","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2024.2392786","authors":["Ayyasamy Pushpalatha","Sunkari Pradeep","Matta Venkata Pullarao","Shanmuganathan Sankar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-28T10:34:11Z","doi":"10.1080/0954898x.2024.2392786","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1364/josaa.608366","name":"A Hardware-Calibrated Optical Spiking Neural Network Based on a Programmable MZI mesh Weight Engine","source":"crossref","abstract":"","url":"https://doi.org/10.1364/josaa.608366","authors":["dingmin Cheng","Rong Wang","hang zhang","Ling Zhang","Duan Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-18T13:00:10Z","doi":"10.1364/josaa.608366","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/icassp55912.2026.11460569","name":"IADP-SNN: Integer Activation Dropping Spiking Neural Network for Underwater Acoustic Communication Signal Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icassp55912.2026.11460569","authors":["Yan Gong","Yi Fang","Minyan Huang","Li Ma","Yanhui Tu","Haihong Feng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-21T21:24:02Z","doi":"10.1109/icassp55912.2026.11460569","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1016/j.dsp.2024.104635","name":"A detection method based on nonlinear spiking neural systems for infrared small targets","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.dsp.2024.104635","authors":["FaXing Zhang","Bo Yang","Hong Peng","Xiaohui Luo","Jun Wang","Zhicai Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-12T22:03:25Z","doi":"10.1016/j.dsp.2024.104635","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1016/j.neunet.2023.106092","name":"Trainable Spiking-YOLO for low-latency and high-performance object detection","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2023.106092","authors":["Mengwen Yuan","Chengjun Zhang","Ziming Wang","Huixiang Liu","Gang Pan","Huajin Tang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-27T11:54:31Z","doi":"10.1016/j.neunet.2023.106092","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1038/s41534-024-00921-x","name":"A quantum leaky integrate-and-fire spiking neuron and network","source":"crossref","abstract":"Abstract Quantum machine learning is in a period of rapid development and discovery, however it still lacks the resources and diversity of computational models of its classical complement. With the growing difficulties of classical models requiring extreme hardware and power solutions, and quantum models being limited by noisy intermediate-scale quantum (NISQ) hardware, there is an emerging opportunity to solve both problems together. Here we introduce a new software model for quantum neuromorphic computing — a quantum leaky integrate-and-fire (QLIF) neuron, implemented as a compact high-fidelity quantum circuit, requiring only 2 rotation gates and no CNOT gates. We use these neurons as building blocks in the construction of a quantum spiking neural network (QSNN), and a quantum spiking convolutional neural network (QSCNN), as the first of their kind. We apply these models to the MNIST, Fashion-MNIST, and KMNIST datasets for a full comparison with other classical and quantum models. We find that the proposed models perform competitively, with comparative accuracy, with efficient scaling and fast computation in classical simulation as well as on quantum devices.","url":"https://doi.org/10.1038/s41534-024-00921-x","authors":["Dean Brand","Francesco Petruccione"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T22:52:34Z","doi":"10.1038/s41534-024-00921-x","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1109/tcds.2023.3311634","name":"R-SNN: Region-Based Spiking Neural Network for Object Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tcds.2023.3311634","authors":["Xiaobo Jin","Ming Zhang","Rui Yan","Gang Pan","De Ma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-08T13:34:14Z","doi":"10.1109/tcds.2023.3311634","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.36227/techrxiv.170906907.74394397/v1","name":"Neural Network Based Anomaly Detection Method for Network Datasets","source":"crossref","abstract":"This research paper presents a comprehensive investigation into the development of an innovative and novel custom neural network model for intrusion detection systems (IDS). In the current era of rapid data transfer facilitated by the internet and advancements in communication technologies, the security of sensitive information is of paramount concern. As attackers continuously devise new methodologies to steal or tamper with data, IDSs face significant challenges in effectively detecting and mitigating intrusions. While extensive research has been conducted to enhance IDS capabilities, the need for improved detection accuracy and reduced false alarm rates remains a pressing issue. Moreover, the identification of zeroday attacks continues to pose a formidable obstacle. In contrast to conventional IDS approaches that heavily rely on statistical methodologies and rule-based expert systems, this study embraces data mining techniques, specifically Neural Networks (NNs), to overcome the limitations associated with large datasets. This research paper proposes a meticulously designed custom neural network model that leverages machine learning (ML) algorithms to analyze contemporary host activity and cloud service data. The paper extensively discusses the utilized dataset, meticulously evaluates the performance of various classifiers, and introduces our innovative neural network model. Emphasizing the significance of our model in anomaly detection, the findings underscore the importance of robust ML models to ensure the efficacy and longevity of deployed defensive systems. By capitalizing on its innovative design and leveraging the power of ML algorithms, our model not only addresses the limitations of traditional IDS approaches but also paves the way for enhanced accuracy, reduced false alarms, and improved resilience against zero-day attacks. This research contributes to the advancement of the field, shedding light on the novel possibilities and remarkable innovation offered by our custom neural network model in safeguarding critical information in an increasingly hostile digital landscape.","url":"https://doi.org/10.36227/techrxiv.170906907.74394397/v1","authors":["Bilal Zahid Hussain","Yusuf Hasan","Irfan Khan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-27T16:29:32Z","doi":"10.36227/techrxiv.170906907.74394397/v1","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1039/d4sm01391c/v1/review1","name":"Review for \"Scalability of Graph Neural Network in Accurate Prediction of Frictional Contact Network in Suspensions\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d4sm01391c/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-20T16:16:00Z","doi":"10.1039/d4sm01391c/v1/review1","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1016/j.compeleceng.2024.109562","name":"An energy and area-efficient spike frequency adaptable LIF neuron for spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.compeleceng.2024.109562","authors":["Umayia Mushtaq","Md. Waseem Akram","Dinesh Prasad","Aminul Islam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-19T14:18:53Z","doi":"10.1016/j.compeleceng.2024.109562","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1016/j.cacaie.2026.100042","name":"A spiking neural network for energy-efficient power transmission line inspection","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.cacaie.2026.100042","authors":["Haina Rong","Tong Bi","Gexiang Zhang","Ferrante Neri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-04T21:29:46Z","doi":"10.1016/j.cacaie.2026.100042","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1016/j.ins.2024.120276","name":"FE-RNN: A fuzzy embedded recurrent neural network for improving interpretability of underlying neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.ins.2024.120276","authors":["James Chee Min Tan","Qi Cao","Chai Quek"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-09T00:32:24Z","doi":"10.1016/j.ins.2024.120276","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.1007/s00521-023-09350-x","name":"Anterior cruciate ligament tear detection based on convolutional neural network and generative adversarial neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-023-09350-x","authors":["Kavita Joshi","K. Suganthi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-24T18:01:26Z","doi":"10.1007/s00521-023-09350-x","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1109/icecte69292.2026.11429274","name":"Classification of Environmental Sounds Using Spatio-temporal Based Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icecte69292.2026.11429274","authors":["Ashfaque Ahmed","Kazi Shajahan Rabbi","Md Shafin Hossain Shadhin","Anisur Rahman Zihad","Antara Nawar","Monjur Morshed"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-16T20:10:41Z","doi":"10.1109/icecte69292.2026.11429274","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1007/s13369-024-08833-w","name":"Hybrid Spiking Neural Networks for Anomaly Detection of Brain, Heart and Pancreas","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s13369-024-08833-w","authors":["Asif Mehmood","Muhammad Javed Iqbal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-15T05:05:14Z","doi":"10.1007/s13369-024-08833-w","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1109/asp-dac58780.2024.10473964","name":"TQ-TTFS: High-Accuracy and Energy-Efficient Spiking Neural Networks Using Temporal Quantization Time-to-First-Spike Neuron","source":"crossref","abstract":"","url":"https://doi.org/10.1109/asp-dac58780.2024.10473964","authors":["Yuxuan Yang","Zihao Xuan","Yi Kang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-25T19:06:53Z","doi":"10.1109/asp-dac58780.2024.10473964","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1109/edpee61724.2024.00117","name":"Research on Classification Algorithm of Graph Neural Network Based on Combination of Graph Neural Network and LSTM","source":"crossref","abstract":"","url":"https://doi.org/10.1109/edpee61724.2024.00117","authors":["Zhilin Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-31T17:27:36Z","doi":"10.1109/edpee61724.2024.00117","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:25.338Z"},{"id":"doi:10.1109/icassp55912.2026.11464148","name":"ASRC-SNN: Adaptive Skip Recurrent Connection Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icassp55912.2026.11464148","authors":["Shang Xu","Jiayu Zhang","Ziming Wang","Runhao Jiang","Rui Yan","Huajin Tang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-21T21:25:57Z","doi":"10.1109/icassp55912.2026.11464148","addedAt":"2026-09-01T01:48:25.338Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1109/iccad66269.2025.11240803","name":"SpikeSynth: Energy-Efficient Adaptive Analog Printed Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccad66269.2025.11240803","authors":["Priyanjana Pal","Alexander Studt","Tara Gheshlaghi","Michael Hefenbrock","Michael Beigl","Mehdi Tahoori"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-20T18:39:34Z","doi":"10.1109/iccad66269.2025.11240803","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1080/0954898x.2025.2537680","name":"AI-driven plant disease detection with tailored convolutional neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2025.2537680","authors":["Sk Mahmudul Hassan","Keshab Nath","Michal Jasinski","Arnab Kumar Maji"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-01T06:47:26Z","doi":"10.1080/0954898x.2025.2537680","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1109/iccst63435.2025.11293944","name":"Spiking Neural Networks for RF Signal Classification and Unified Timing Estimation on Loihi 2","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccst63435.2025.11293944","authors":["Howard Yanxon","Lauren Reinerman-Jones"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-18T18:32:00Z","doi":"10.1109/iccst63435.2025.11293944","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1109/siu66497.2025.11112390","name":"Integration of Contrastive Predictive Coding and Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/siu66497.2025.11112390","authors":["Emirhan Bilgiç","Neslihan Serap Şengör","Namık Berk Yalabık","Yavuz Selim İşler","Aykut Görkem Gelen","Rahmi Elibol"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-15T18:11:33Z","doi":"10.1109/siu66497.2025.11112390","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1109/ipas63548.2025.10924503","name":"A Review On Fusion Of Spiking Neural Networks And Transformers","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ipas63548.2025.10924503","authors":["Oumaima Marsi","Sébastien Ambellouis","José Mennesson","Cyril Meurie","Anthony Fleury","Charles Tatkeu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-22T00:29:13Z","doi":"10.1109/ipas63548.2025.10924503","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1117/12.3087220","name":"A dual-stage pruning method for energy-efficient spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3087220","authors":["Yaning Li","Han Yang","Xiurui Xie"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-04T17:38:40Z","doi":"10.1117/12.3087220","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1109/aicas64808.2025.11173151","name":"Non-uniform Memory Partitioning For Low-Power Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aicas64808.2025.11173151","authors":["Simon Richter","Darío Fernández Khatiboun","Maryam Sadeghi","Milad Zamani","Farshad Moradi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-25T17:52:35Z","doi":"10.1109/aicas64808.2025.11173151","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1109/icsps66615.2025.11347902","name":"Brain-Machine Interface Decoding Using Optimized Recurrent Spiking Neural Networks on MCU","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icsps66615.2025.11347902","authors":["Eraraya Morenzo Muten","Nur Ahmadi","Timothy G. Constandinou","Trio Adiono"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-27T04:49:15Z","doi":"10.1109/icsps66615.2025.11347902","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1063/5.0310217","name":"Topological and geometrical signatures of computation in rate, spiking, and oscillatory neural reservoirs","source":"crossref","abstract":"The computational efficiency of a neural substrate is shaped by the geometry and topology of its state-space manifold. We propose and test a “computational matching” principle: efficiency is maximized when the intrinsic geometry of a reservoir’s representation aligns with the latent structure of the task. We investigate this on a phase-coherent burst detection task, comparing three physically distinct reservoir types: rate-based (tanh-neurons), spiking (leaky integrate and fire), and oscillatory (Kuramoto). We find that oscillatory reservoirs exhibit the highest neural efficiency, requiring approximately 4 times fewer neurons than rate-based models and 7.5 times fewer than spiking models with a static readout to reach 95% accuracy. Using persistent homology on final-state representations, we uncover the underlying mechanism. Both oscillatory and rate-based reservoirs generate manifolds with a non-trivial one-dimensional cycle (β1&amp;gt;0), reflecting the task’s circular structure. However, the oscillatory reservoir’s cycle is geometrically “straight,” enabling nearly perfect linear decoding of the input phase [mean absolute angular error (MAE) ≈0.02°], whereas the rate-based cycle is distorted (MAE≈8°). Spiking reservoirs only reveal robust cyclic topology and accurate phase decoding (MAE≈0°) when states are integrated over a dynamic time window. Our findings suggest that computational efficiency in reservoirs is predicted not by topology alone, but by the geometric alignment of the state-space representation, offering a design heuristic for task-specialized neuromorphic systems.","url":"https://doi.org/10.1063/5.0310217","authors":["Oleg V. Maslennikov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-22T14:08:51Z","doi":"10.1063/5.0310217","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1002/cpe.70404","name":"Brain‐Inspired Efficient Pruning: Exploiting Criticality in Spiking Neural Networks","source":"crossref","abstract":"ABSTRACT Spiking neural networks (SNNs) have gained significant attention due to their energy‐efficient and multiplication‐free characteristics. Despite these advantages, deploying large‐scale SNNs on edge hardware is challenging due to limited resource availability. Network pruning offers a viable approach to compress the network scale and reduce hardware resource requirements for model deployment. However, existing SNN pruning methods cause high pruning costs and performance loss because they lack efficiency in processing the sparse spike representation of SNNs. In this paper, inspired by the critical brain hypothesis in neuroscience and the high biological plausibility of SNNs, we explore and leverage criticality to facilitate efficient pruning in deep SNNs. We first explain criticality in SNNs from the perspective of maximizing feature information entropy. Second, we propose a low‐cost metric to assess neuron criticality in feature transmission and design a pruning‐regeneration method that incorporates this criticality into the pruning process. Experimental results demonstrate that our method achieves higher performance than the current state‐of‐the‐art (SOTA) method with up to 95.26% reduction in pruning cost. The criticality‐based regeneration process efficiently selects potential structures and facilitates consistent feature representation. Our code is available at https://github.com/MmPple/pruning‐criticality .","url":"https://doi.org/10.1002/cpe.70404","authors":["Shuo Chen","Zeshi Liu","Haihang You"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-03T02:44:50Z","doi":"10.1002/cpe.70404","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1121/10.0037581","name":"Spiking neural networks for sound localization: A new perspective on illuminating auditory spatial perception","source":"crossref","abstract":"Humans estimate sound source direction using information from their auditory neural system. Traditional methods use auditory cues [e.g., interaural time differences (ITDs) and interaural level differences (ILDs), etc] to perform sound localization. These cues are extracted from binaural signals or decoded from neuronal firing rates. In contrast, we proposed a new computational model that directly localizes sound sources using the firing rates of auditory neurons, eliminating the need for physical cue extraction and the template-matching process. This model incorporates spiking neural networks (SNNs) and artificial neural networks (ANNs) to emulate auditory spatial perception. To get firing rates, the SNN uses auditory peripheral processing and physiological models of the cochlear nucleus and medial superior olive (MSO). The SNN calculates a database of firing rates from sine tones across varying positions and frequencies to train the ANN. The ANN performs nonlinear regression to predict azimuth and elevation angles, accommodating both narrowband and broadband signals. The integration of dynamic cues resolves front–back confusion by aligning with human auditory perception. We conducted a localization listening test with 10 participants with normal hearing, enabling the refinement of network parameters to closely mimic human behavior. In the future, hearing loss can be simulated by adjusting parameters related to inner hair cell dysfunction, thereby providing a robust framework for real-world spatial hearing.","url":"https://doi.org/10.1121/10.0037581","authors":["Qin Liu","Laurent S. Simon","Hervé Lissek"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-18T16:44:32Z","doi":"10.1121/10.0037581","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1016/j.vlsi.2025.102433","name":"An area and power efficient VLSI architecture for epileptic seizure detection using Transpose Form Retimed Delayed LMS filter and spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.vlsi.2025.102433","authors":["Venugopal Ponnuraj","Sasikala Thangavelu","Bagirathan Kaliyamurthi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-05T23:32:01Z","doi":"10.1016/j.vlsi.2025.102433","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.2514/6.2025-1955","name":"Neural Optimization Machine for Design With Neural Network Based Objectives and Constraints","source":"crossref","abstract":"","url":"https://doi.org/10.2514/6.2025-1955","authors":["Jie Chen","Yongming Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-12T10:03:43Z","doi":"10.2514/6.2025-1955","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.2139/ssrn.5348636","name":"Artificial Neural Network Based Controlled Technique to Optimize Fuel and Battery Systemartificial Neural Network Based Controlled Technique to Optimize Fuel and Battery Systemartificial Neural Network Based Controlled Technique to Optimize Fuel and Battery System","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5348636","authors":["Vikramaditya Dave","megha sen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-11T23:37:54Z","doi":"10.2139/ssrn.5348636","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1007/s10791-026-10423-3","name":"Dygenn dynamic Gaussian weighted evolving Spiking Neural Network model for enhanced neurological disease detection","source":"crossref","abstract":"Abstract Spiking Neural Network (SNN) is a promising field for modelling neuronal activity in the brain, with applications in healthcare, agriculture, finance, manufacturing and others. However, traditional SNNs often suffer from static synaptic weights, limiting their adaptability to the changes in data. Hence, to enhance performance and more accurately model the biological process of the brain, a novel SNN model, Dynamic Gaussian-Weighted Evolving Spiking Neural Network (DyGENN) is developed and applied for the detection of Parkinson’s disease and epileptic seizure. DyGENN incorporates a time-varying synaptic weight function modeled by a Gaussian distribution. The output layer evolves dynamically by either adding new output neurons, updating parameters, or skipping sample learning based on the least error margin calculated from postsynaptic firing time and the desired class labels. The suggested model is evaluated on two different imbalanced datasets: the UCI Oxford Parkinson’s Disease Detection and the Bonn Epileptic Seizure dataset using percentage splitting and stratified K -fold cross validation. Compared to popular machine learning (Support Vector Machine (SVM) and Random Forest (RF)), deep learning (Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM)) and state-of-the-art SNN frameworks (Norse, SpikingJelly, and a custom PyTorch-based model), DyGENN achieves superior performance: 97.44% accuracy, 87.5% sensitivity, 100% specificity, and geometric mean (G-Mean) of 0.9354 for Parkinson’s disease detection; 97.98% accuracy, 95.83% sensitivity, 98.67% specificity, and G-Mean of 0.972 for epileptic seizure detection. The proposed model outperforms existing models in both scenarios, suggesting its potential for broader application to other neurological conditions characterized by structured biomarker data.","url":"https://doi.org/10.1007/s10791-026-10423-3","authors":["Priya Das","Sarita Nanda","Prabodh Kumar Sahoo","Aswini Kumar Samantaray","Ganapati Panda"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-04T21:39:57Z","doi":"10.1007/s10791-026-10423-3","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1007/978-981-96-9431-0_1","name":"Artificial Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-96-9431-0_1","authors":["Venkata A. P. Chavali","Amit A. Deshmukh","Aarti G. Ambekar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-26T06:50:56Z","doi":"10.1007/978-981-96-9431-0_1","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1109/citsc64390.2025.00070","name":"Analysis and Prediction of Flood Disasters Based on BP Neural Network and Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/citsc64390.2025.00070","authors":["Yanbing Lin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-28T03:18:58Z","doi":"10.1109/citsc64390.2025.00070","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.3390/electronics14081602","name":"Batchnorm-Free Binarized Deep Spiking Neural Network for a Lightweight Machine Learning Model","source":"crossref","abstract":"The development of deep neural networks, although demonstrating astounding capabilities, leads to more complex models, high energy consumption, and expensive hardware costs. While network quantization is a widely used method to address this problem, the typical binary neural networks often require the batch normalization (batchnorm) layer to preserve their classification performances. The batchnorm layer contains full-precision multiplication and the addition operation that requires extra hardware and memory access. To address this issue, we present a batch normalization-free binarized deep spiking neural network (B-SNN). We combine spike-based backpropagation in a spiking neural network with weight binarization to further reduce the memory and computation overhead while maintaining comparable accuracy. Weight binarization reduces the huge amount of memory storage for a large number of parameters by replacing the full-precision weights (32 bit) with binary weights (1 bit). Moreover, the proposed B-SNN employs the stochastic input encoding scheme together with a spiking neuron model, thereby enabling networks to perform efficient bitwise computations without the necessity of using a batchnorm layer. As a result, our experimental results demonstrate that the efficacy of the proposed binarization scheme on deep SNNs outperforms the conventional binarized convolutional neural network.","url":"https://doi.org/10.3390/electronics14081602","authors":["Hasna Nur Karimah","Chankyu Lee","Yeongkyo Seo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-16T04:05:31Z","doi":"10.3390/electronics14081602","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1109/dcna67486.2025.11199933","name":"The Impact of Internal Noise on Deep and Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/dcna67486.2025.11199933","authors":["Nadezhda Semenova","Daniil Maksimov","Ivan Kolesnikov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-20T17:48:23Z","doi":"10.1109/dcna67486.2025.11199933","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1109/icta68203.2025.11330037","name":"RCIM: A Reconfigurable Compute-in-Memory Architecture for Artificial, Spiking and Hybrid Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icta68203.2025.11330037","authors":["Ruihao He","Cong Wang","Xipeng Lin","Shaoxuan Li","Hongwu Jiang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-20T20:37:10Z","doi":"10.1109/icta68203.2025.11330037","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1109/asim67379.2025.11512696","name":"Spiking Multi Scale Graph Convolutional Neural Networks for Fault Diagnosis of Rotating Machinery","source":"crossref","abstract":"","url":"https://doi.org/10.1109/asim67379.2025.11512696","authors":["Alaeldden Abduelhadi","Jie Cao","Haopeng Liang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-15T02:41:37Z","doi":"10.1109/asim67379.2025.11512696","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1109/csis-iac65538.2025.11161679","name":"Verifying an Efficient Structure Slimming Method for Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/csis-iac65538.2025.11161679","authors":["Hengyuan Xu","Junqiao Wang","Kunyu Wu","Zhengyi Qu","Yuqi Ouyang","Guangwu Qian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-25T17:51:51Z","doi":"10.1109/csis-iac65538.2025.11161679","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1109/iscas58744.2024.10558051","name":"Fast and Lightweight Automatic Modulation Recognition using Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas58744.2024.10558051","authors":["Canghai Lin","ZhiJiao Zhang","Lei Wang","Yao Wang","Jingyue Zhao","Zhijie Yang","Xun Xiao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-02T17:22:52Z","doi":"10.1109/iscas58744.2024.10558051","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1162/089976606774841521","name":"Simultaneous Rate-Synchrony Codes in Populations of Spiking Neurons","source":"crossref","abstract":"Firing rates and synchronous firing are often simultaneously relevant signals, and they independently or cooperatively represent external sensory inputs, cognitive events, and environmental situations such as body position. However, how rates and synchrony comodulate and which aspects of inputs are effectively encoded, particularly in the presence of dynamical inputs, are unanswered questions. We examine theoretically how mixed information in dynamic mean input and noise input is represented by dynamic population firing rates and synchrony. In a subthreshold regime, amplitudes of spatially uncorrelated noise are encoded up to a fairly high input frequency, but this requires both rate and synchrony output channels. In a suprathreshold regime, means and common noise amplitudes can be simultaneously and separately encoded by rates and synchrony, respectively, but the input frequency for which this is possible has a lower limit.","url":"https://doi.org/10.1162/089976606774841521","authors":["Naoki Masuda"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-11-17T21:55:49Z","doi":"10.1162/089976606774841521","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1007/978-3-030-30425-6_47","name":"Chaotic Spiking Neural Network Connectivity Configuration Leading to Memory Mechanism Formation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-30425-6_47","authors":["Mikhail Kiselev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-09-03T03:05:29Z","doi":"10.1007/978-3-030-30425-6_47","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.3389/fnins.2025.1641314","name":"Correction: Paired competing neurons improving STDP supervised local learning in spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.3389/fnins.2025.1641314","authors":["Gaspard Goupy","Pierre Tirilly","Ioan Marius Bilasco"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-25T10:38:18Z","doi":"10.3389/fnins.2025.1641314","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1109/mlccim60412.2023.00016","name":"A STDP Rules-Based Spiking Neural Network Implementation for Image Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mlccim60412.2023.00016","authors":["Haoran Teng","Yin Yu","Jinghe Wei","Guozhu Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-12T18:35:38Z","doi":"10.1109/mlccim60412.2023.00016","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.9734/jerr/2026/v28i61935","name":"Enhancing Sequential Learning with a Hybrid EWC- Integrated Spiking Neural Network","source":"crossref","abstract":"When neural networks are trained on tasks one after another, they often forget previously learned information, a problem known as catastrophic forgetting. While Elastic Weight Consolidation (EWC) has been effective in reducing this issue in conventional neural networks, its application to Spiking Neural Networks (SNNs) has received limited attention. In this study, EWC is integrated with SNNs to develop a continual learning model capable of retaining earlier knowledge while learning new tasks sequentially. The model is evaluated using multiple task variants of the MNIST dataset, including rotated and permuted versions, which introduce distribution shifts across tasks in a controlled manner. Experimental results show that incorporating EWC significantly reduces forgetting compared to standard SNN training, while preserving the biologically inspired and energy- efficient properties of spiking models, as demonstrated through task-wise accuracy and forgetting metrics.","url":"https://doi.org/10.9734/jerr/2026/v28i61935","authors":["B. Sai Jyothi","M. Sireesha","K. Sai Namrataa Chowdary","K. Vandana","P. Sai Pranitha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-15T12:21:58Z","doi":"10.9734/jerr/2026/v28i61935","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1007/s11571-020-09572-y","name":"Effects of synaptic integration on the dynamics and computational performance of spiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11571-020-09572-y","authors":["Xiumin Li","Shengyuan Luo","Fangzheng Xue"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-02-19T09:03:49Z","doi":"10.1007/s11571-020-09572-y","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1007/11840817_7","name":"On-Line Learning with Structural Adaptation in a Network of Spiking Neurons for Visual Pattern Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1007/11840817_7","authors":["Simei Gomes Wysoski","Lubica Benuskova","Nikola Kasabov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-08-31T18:11:56Z","doi":"10.1007/11840817_7","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1145/3400302.3415608","name":"Encoding, model, and architecture","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3400302.3415608","authors":["Haowen Fang","Zaidao Mei","Amar Shrestha","Ziyi Zhao","Yilan Li","Qinru Qiu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-18T01:16:38Z","doi":"10.1145/3400302.3415608","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/ijcnn55064.2022.9891920","name":"A Fully Analog CMOS Implementation of a Two-variable Spiking Neuron in the Subthreshold Region and its Network Operation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn55064.2022.9891920","authors":["Satoshi Moriya","Hideaki Yamamoto","Shigeo Sato","Yasushi Yuminaka","Yoshihiko Horio","Jordi Madrenas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-30T19:56:04Z","doi":"10.1109/ijcnn55064.2022.9891920","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1007/978-981-99-4284-8_16","name":"Spiking Neural Network in Computer Vision: Techniques, Tools and Trends","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-99-4284-8_16","authors":["Rohit Agarwal","Palash Ghosal","Narayan Murmu","Debashis Nandi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-20T04:02:35Z","doi":"10.1007/978-981-99-4284-8_16","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1039/d4sm01391c/v2/review1","name":"Review for \"Scalability of Graph Neural Network in Accurate Prediction of Frictional Contact Network in Suspensions\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d4sm01391c/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-20T16:16:00Z","doi":"10.1039/d4sm01391c/v2/review1","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/b978-0-44-329202-6.00002-x","name":"Front Matter","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-44-329202-6.00002-x","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-31T19:14:14Z","doi":"10.1016/b978-0-44-329202-6.00002-x","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1109/iccit68389.2025.11453443","name":"OCCA-SNN: Online Class-Center Anchoring with Alignment for Spiking Neural Networks in Class-Incremental Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccit68389.2025.11453443","authors":["Ke Hu","Liangsheng Wen","Tingting Zhang","Xiaoguang Zhang","Hao Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-31T19:49:12Z","doi":"10.1109/iccit68389.2025.11453443","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1109/iscas58744.2024.10558351","name":"SPAT: FPGA-based Sparsity-Optimized Spiking Neural Network Training Accelerator with Temporal Parallel Dataflow","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas58744.2024.10558351","authors":["Yuanyuan Jiang","Li Lun","Jiawei Wang","Mingqi Yin","Hanqing Liu","Zhenhui Dai","Xiaole Cui","Xiaoxin Cui"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-02T17:22:52Z","doi":"10.1109/iscas58744.2024.10558351","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/jlt.2022.3225099","name":"Plastic Photonic Synapse Based on VCSOA for Self-Learning in Photonic Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/jlt.2022.3225099","authors":["Yahui Zhang","Shuiying Xiang","Xingyu Cao","Xingxing Guo","Genquan Han","Yue Hao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-28T19:40:17Z","doi":"10.1109/jlt.2022.3225099","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/smc42975.2020.9283337","name":"Object shape recognition using tactile sensor arrays by a spiking neural network with unsupervised learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/smc42975.2020.9283337","authors":["Jaehun Kim","Sung-Phil Kim","Jungjun Kim","Heeseon Hwang","Jaehyun Kim","Doowon Park","Unyong Jeong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-14T21:44:48Z","doi":"10.1109/smc42975.2020.9283337","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1007/978-3-032-04555-3_25","name":"A Spiking Central Pattern Generator Capable of Adaptive Gait Control in Quadruped Locomotion","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-04555-3_25","authors":["Narumitsu Ikeda"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-11T08:55:47Z","doi":"10.1007/978-3-032-04555-3_25","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1007/s12668-020-00778-2","name":"Memristive Logic Design of Multifunctional Spiking Neural Network with Unsupervised Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s12668-020-00778-2","authors":["N.V. Andreeva","E.A. Ryndin","M.I. Gerasimova"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-11T09:40:03Z","doi":"10.1007/s12668-020-00778-2","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1088/1361-6528/ab34da","name":"Unsupervised online learning of temporal information in spiking neural network using thin-film transistor-type NOR flash memory devices","source":"crossref","abstract":"Abstract Brain-inspired analog neuromorphic systems based on the synaptic arrays have attracted large attention due to low-power computing. Spike-timing-dependent plasticity (STDP) algorithm is considered as one of the appropriate neuro-inspired techniques to be applied for on-chip learning. The aim of this study is to investigate the methodology of unsupervised STDP based learning in temporal encoding systems. The system-level simulation was performed based on the measurement results of thin-film transistor-type asymmetric floating-gate NOR flash memory. With proposed learning methods, 91.53% of recognition accuracy is obtained in inferencing MNIST standard dataset with 200 output neurons. Moreover, temporal encoding rules showed that the number of input pulses and the computing power can be compressed without significant loss of recognition accuracy compared to the conventional rate encoding scheme. In addition, temporal computing in a multi-layer network is suitable for learning data sequences, suggesting the possibility of applying to real-world tasks such as classifying direction of moving objects.","url":"https://doi.org/10.1088/1361-6528/ab34da","authors":["Seongbin Oh","Chul-Heung Kim","Soochang Lee","Jang Saeng Kim","Jong-Ho Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-07-25T05:16:08Z","doi":"10.1088/1361-6528/ab34da","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/iros55552.2023.10342044","name":"An Energy-Efficient Lane-Keeping System Using 3D LiDAR Based on Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iros55552.2023.10342044","authors":["Genghang Zhuang","Zhenshan Bing","Zhen Zhou","Xiangtong Yao","Yuhong Huang","Kai Huang","Alois Knoll"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-13T19:17:55Z","doi":"10.1109/iros55552.2023.10342044","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/csnt64827.2025.10967751","name":"The Security Verification and Analysis of Information Nodes in Cyberspace by Deep Spiking Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/csnt64827.2025.10967751","authors":["Yuxin Zhai","Zhehong Zhou","Yanchao Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-23T17:51:09Z","doi":"10.1109/csnt64827.2025.10967751","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1016/j.neunet.2025.107794","name":"Embeddings hidden layers learning for neural network compression","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107794","authors":["Jia Cheng Hu","Roberto Cavicchioli","Alessandro Capotondi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-02T02:51:21Z","doi":"10.1016/j.neunet.2025.107794","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.21285/1814-3520-2018-8-63-71","name":"STUDY OF A PWM-ELEMENT WITH A SPIKING NEURAL NETWORK","source":"crossref","abstract":"","url":"https://doi.org/10.21285/1814-3520-2018-8-63-71","authors":["Innokentiy Igumnov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-09-11T01:58:18Z","doi":"10.21285/1814-3520-2018-8-63-71","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/mcte62870.2024.11117887","name":"The Optimization of Object Detection Framework for Event Flow Based on Spiking Neural Network and Spatial Attention Mechanism","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mcte62870.2024.11117887","authors":["Jialiang Ye","Peng Wang","Wujian Ye","Yijun Liu","Haoxian Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-20T18:28:40Z","doi":"10.1109/mcte62870.2024.11117887","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/pmbs.2018.8641660","name":"Evaluating the Impact of Spiking Neural Network Traffic on Extreme-Scale Hybrid Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/pmbs.2018.8641660","authors":["Noah Wolfe","Mark Plagge","Christopher D. Carothers","Misbah Mubarak","Robert B. Ross"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-02-14T18:44:06Z","doi":"10.1109/pmbs.2018.8641660","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1007/s44196-024-00425-8","name":"A Novel Training Approach in Deep Spiking Neural Network Based on Fuzzy Weighting and Meta-heuristic Algorithm","source":"crossref","abstract":"Abstract The challenge of supervised learning in spiking neural networks (SNNs) for digit classification from speech signals is examined in this study. Meta-heuristic algorithms and a fuzzy logic framework are used to train SNNs. Using gray wolf optimization (GWO), the features obtained from audio signals are reduced depending on the dispersion of each feature. Then, it combines fuzzy weighting system (FWS) and spike time-dependent flexibility (STDP) approach to implement the learning rule in SNN. The FWS rule produces a uniformly distributed random weight in the STDP flexibility window, so that the system requires fewer training parameters. Finally, these neurons are fed data to estimate the training weights and threshold values of the neurons using wild horse algorithm (WHO). With the parameters given, these rule weights are applied to appropriately display the class's share in extracting the relevant feature. The suggested network can classify speech signals into categories with 97.17% accuracy. The dataset was obtained using neurons operating at sparse biological rates below 600 Hz in the TIDIGITS test database. The suggested method has been evaluated on the IRIS and Trip Data datasets, where the classification results showed a 98.93% and 97.36% efficiency, respectively. Compared to earlier efforts, this study's results demonstrate that the strategy is both computationally simpler and more accurate. The accuracy of classification of digits, IRIS and Trip Data has increased by 4.9, 3.46 and 1.24%, respectively. The principal goal of this research is to improve the accuracy of SNN by developing a new high-precision training method.","url":"https://doi.org/10.1007/s44196-024-00425-8","authors":["Melika Hamian","Karim Faez","Soheila Nazari","Malihe Sabeti"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-19T10:13:55Z","doi":"10.1007/s44196-024-00425-8","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/tetci.2020.3035164","name":"A Deep Unsupervised Feature Learning Spiking Neural Network With Binarized Classification Layers for the EMNIST Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tetci.2020.3035164","authors":["Ruthvik Vaila","John Chiasson","Vishal Saxena"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-11-10T21:44:48Z","doi":"10.1109/tetci.2020.3035164","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/twc.2024.3374549","name":"Energy-Efficient Distributed Spiking Neural Network for Wireless Edge Intelligence","source":"crossref","abstract":"","url":"https://doi.org/10.1109/twc.2024.3374549","authors":["Yanzhen Liu","Zhijin Qin","Geoffrey Ye Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-14T18:19:18Z","doi":"10.1109/twc.2024.3374549","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.7554/elife.90597.2.sa3","name":"Author Response: Hippocampome.org v2.0: a knowledge base enabling data-driven spiking neural network simulations of rodent hippocampal circuits","source":"crossref","abstract":"","url":"https://doi.org/10.7554/elife.90597.2.sa3","authors":["Diek W. Wheeler","Jeffrey D. Kopsick","Nate Sutton","Carolina Tecuatl","Alexander O. Komendantov","Kasturi Nadella","Giorgio A. Ascoli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-26T06:25:53Z","doi":"10.7554/elife.90597.2.sa3","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/comp-sif69752.2026.11481898","name":"Spiking Neural Network (SNN) for Real-Time Pest Detection in Drone Imagery","source":"crossref","abstract":"","url":"https://doi.org/10.1109/comp-sif69752.2026.11481898","authors":["V.Aravinda Rajan","Ranajeet Kumar","Padmavathy S","P. Priya","Vijendra Pratap Singh","Tejaswini M R"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-29T19:46:03Z","doi":"10.1109/comp-sif69752.2026.11481898","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1016/j.measurement.2026.121340","name":"Power quality enhancement of renewable energy systems using a hybrid orangutan optimization algorithm and continuous spiking graph neural network with series active power filter","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.measurement.2026.121340","authors":["M. Senthil Raja","V. Sowmya Sree","V. Jayakumar","B. Karthick"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-29T23:25:08Z","doi":"10.1016/j.measurement.2026.121340","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/dac56929.2023.10247810","name":"Neurogenesis Dynamics-inspired Spiking Neural Network Training Acceleration","source":"crossref","abstract":"","url":"https://doi.org/10.1109/dac56929.2023.10247810","authors":["Shaoyi Huang","Haowen Fang","Kaleel Mahmood","Bowen Lei","Nuo Xu","Bin Lei","Yue Sun","Dongkuan Xu","Wujie Wen","Caiwen Ding"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-15T17:31:31Z","doi":"10.1109/dac56929.2023.10247810","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/asap61560.2024.00041","name":"A Convolutional Spiking Neural Network Accelerator with the Sparsity-Aware Memory and Compressed Weights","source":"crossref","abstract":"","url":"https://doi.org/10.1109/asap61560.2024.00041","authors":["Hanqing Liu","Xiaole Cui","Sunrui Zhang","Mingqi Yin","Yuanyuan Jiang","Xiaoxin Cui"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-22T17:45:58Z","doi":"10.1109/asap61560.2024.00041","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1007/s11071-023-08655-9","name":"A quantum-inspired online spiking neural network for time-series predictions","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11071-023-08655-9","authors":["Fei Yan","Wenjing Liu","Fangyan Dong","Kaoru Hirota"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-26T06:02:21Z","doi":"10.1007/s11071-023-08655-9","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1016/j.neucom.2016.12.005","name":"A spiking neural network for real-time Spanish vowel phonemes recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2016.12.005","authors":["L. Miró-Amarante","F. Gómez-Rodríguez","A. Jiménez-Fernández","G. Jiménez-Moreno"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-12-06T22:45:36Z","doi":"10.1016/j.neucom.2016.12.005","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.61782/fa.2025.0824","name":"Spiking neural networks for sound localization: A new perspective on auditory spatial perception","source":"crossref","abstract":"","url":"https://doi.org/10.61782/fa.2025.0824","authors":["Qin Liu","Simon Laurent","Hannes Wuthrich","Hervé Lissek"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-26T07:33:58Z","doi":"10.61782/fa.2025.0824","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1007/978-3-031-78341-8_27","name":"MTSA-SNN: A Multi-modal Time Series Analysis Model Based on Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78341-8_27","authors":["Chengzhi Liu","Zihong Luo","Zheng Tao","Chenghao Liu","Yitao Xu","Zile Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-01T15:15:26Z","doi":"10.1007/978-3-031-78341-8_27","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1109/lgrs.2025.3529956","name":"Sea-Surface Small Target Detection Using Spiking Neural Network With Controllable False Alarm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/lgrs.2025.3529956","authors":["Yang Jiao","Zeyu Wang","Dewu Wang","Shuwen Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-15T15:28:41Z","doi":"10.1109/lgrs.2025.3529956","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.52202/085713-1760","name":"Local-Global Coupling Spiking Graph Transformer  for Brain Disorders Diagnosis from Two Perspectives","source":"crossref","abstract":"","url":"https://doi.org/10.52202/085713-1760","authors":["Geng Zhang","Jiangrong Shen","Kaizhong Zheng","Liangjun Chen","Badong Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-06T14:44:29Z","doi":"10.52202/085713-1760","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1007/978-3-032-10951-4_42","name":"Intelligent Fault Diagnosis of Roller Bearings Using Acoustic Emissions and Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-10951-4_42","authors":["Toby Emm","Yu Zhang","Miguel Martínez-García"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-02T00:48:44Z","doi":"10.1007/978-3-032-10951-4_42","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1109/icdici66477.2025.11135388","name":"Spiking Neural Networks for Sustainable and High-Performance Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icdici66477.2025.11135388","authors":["Archit Anand Gangshettiwar","Nicole Elaine Correia","Kashish Singh Gaharwar","S Vignesh","G Sumathi","E Konguvel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-02T17:29:01Z","doi":"10.1109/icdici66477.2025.11135388","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.2139/ssrn.5194180","name":"Neural Network-Based Affective Computing for Education","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5194180","authors":["Ajit Singh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-27T14:49:19Z","doi":"10.2139/ssrn.5194180","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1109/tetci.2025.3549763","name":"Spatio-Temporal Enhancement-Based Spiking Neural Network for Morphological Neuron Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tetci.2025.3549763","authors":["Chunli Sun","Qinghai Guo","Luziwei Leng","Feng Wu","Feng Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-26T22:56:18Z","doi":"10.1109/tetci.2025.3549763","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1109/pimrc62392.2025.11274667","name":"Spiking Neural Networks for Resource Allocation in UAV-Enabled Wireless Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/pimrc62392.2025.11274667","authors":["Vasileios Kouvakis","Stylianos E. Trevlakis","Ioannis Arapakis","Alexandros-Apostolos A. Boulogeorgos"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-12T18:33:25Z","doi":"10.1109/pimrc62392.2025.11274667","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1109/uemcon67449.2025.11267772","name":"Spiking Neural Networks for ECG Classification and Anomaly Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/uemcon67449.2025.11267772","authors":["Shruti Bhandari","Batuhan Asiroglu","Sanjog Dhakal","Robin Ghosh","Tolga Ensari","Burak Berk Ustundag"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-04T18:35:28Z","doi":"10.1109/uemcon67449.2025.11267772","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1016/b978-0-44-332894-7.00016-2","name":"Wavelet neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-44-332894-7.00016-2","authors":["Snehashish Chakraverty","Arup Kumar Sahoo","Dhabaleswar Mohapatra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-28T17:53:39Z","doi":"10.1016/b978-0-44-332894-7.00016-2","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1002/9781394255306.ch11","name":"Adaptive Vibration Control for Two‐Stage Bionic Flapping Wings Based on Neural Network Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9781394255306.ch11","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-03T21:38:05Z","doi":"10.1002/9781394255306.ch11","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1109/tcasai.2025.3568365","name":"FPGA-Based Adaptive LIF Neuron for High-Speed, Energy-Efficient Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tcasai.2025.3568365","authors":["Saras Mani Mishra","Hanumant Singh Shekhawat","Jan Pidanic","Gaurav Trivedi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-08T13:37:21Z","doi":"10.1109/tcasai.2025.3568365","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.15827/0236-235x.151.484-498","name":"Подход к обнаружению DDoS-атак в сети ЦОД с использованием сочетания графов и импульсной нейронной сети","source":"crossref","abstract":"","url":"https://doi.org/10.15827/0236-235x.151.484-498","authors":["Е.В. Пальчевский","Palchevsky E.V.","В.В. Антонов","V.V. Antonov","Д.А. Петросов","D.A. Petrosov,"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-24T09:56:13Z","doi":"10.15827/0236-235x.151.484-498","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1109/icitda68167.2025.11332521","name":"Hoax Topic Classification Using Hybrid Convolutional Neural Network(CNN) - Reccurent Neural Network(RNN) With Word2Vec","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icitda68167.2025.11332521","authors":["Rendy Adie Tama","Yuliant Sibaroni"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-15T20:48:25Z","doi":"10.1109/icitda68167.2025.11332521","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1002/cem.70088/v1/review2","name":"Review for \"In-Situ Detection of Microplastic Particles on Food Using Hyperspectral Imaging with one-dimensional convolutional neural network (1D-CNN) and artificial neural network (ANN)\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/cem.70088/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-23T21:04:57Z","doi":"10.1002/cem.70088/v1/review2","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.31274/cc-20260223-43","name":"Neural Network Activation Manipulation for Automated Bug Fixing","source":"crossref","abstract":"","url":"https://doi.org/10.31274/cc-20260223-43","authors":["Moulica Goli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-24T17:52:04Z","doi":"10.31274/cc-20260223-43","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1038/s42005-025-02420-7","name":"Spiking neural networks for radio frequency interference detection in radio astronomy","source":"crossref","abstract":"Abstract Automated systems capable of real-time operation with minimal energy consumption are increasingly important in modern radio telescopes. Spiking Neural Networks (SNNs) promise efficient and dynamic spatio-temporal data processing. This paper reformulates a significant challenge in radio astronomy, Radio Frequency Interference (RFI) detection, as a time-series segmentation task suited for SNN execution. We explore several spectrogram encoding methods and network parameters, applying first and second-order leaky integrate and fire SNNs to tackle RFI detection. We introduce a divisive normalisation-inspired pre-processing step, improving detection performance across multiple encodings strategies. Our approach achieves competitive performance on a synthetic dataset and compelling initial results on real data from the Low-Frequency Array (LOFAR) establishing a baseline for future work. We position SNNs as a viable path towards real-time RFI detection, with many possibilities for follow-up studies. These findings highlight the potential for SNNs performing complex time-series tasks, paving the way towards efficient, real-time processing in radio astronomy and other data-intensive fields.","url":"https://doi.org/10.1038/s42005-025-02420-7","authors":["Nicholas J. Pritchard","Andreas Wicenec","Mohammed Bennamoun","Richard Dodson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-27T12:16:14Z","doi":"10.1038/s42005-025-02420-7","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.1002/cem.70088/v1/review1","name":"Review for \"In-Situ Detection of Microplastic Particles on Food Using Hyperspectral Imaging with one-dimensional convolutional neural network (1D-CNN) and artificial neural network (ANN)\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/cem.70088/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-23T21:04:57Z","doi":"10.1002/cem.70088/v1/review1","addedAt":"2026-09-01T01:48:25.772Z","updatedAt":"2026-09-01T01:48:25.772Z"},{"id":"doi:10.23919/ccc63176.2024.10662685","name":"Sleep Stage Classification with Spiking Neural Networks and Transformers using Multi-Channel EEG Data","source":"crossref","abstract":"","url":"https://doi.org/10.23919/ccc63176.2024.10662685","authors":["Junyan Li","Bin Hu","Zhi-Hong Guan","Bokun Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-17T18:46:36Z","doi":"10.23919/ccc63176.2024.10662685","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.14311/nnw.2024.34.005","name":"Variations of Training Process in Vanilla Recurrent Neural Network Framework","source":"crossref","abstract":"Recurrent neural networks (RNNs) are capable of learning features and long term dependencies from sequential and time series data and show outstanding performance in sequential modeling tasks. However, training process in RNNs is troubled by issues in learning processes such as slow inference, vanishing gradients and difficulties in capturing long term dependencies. In this paper, we introduce a new learning technique to update the weight set as we change the input sequence which is shifted by certain amount of time in training process, instead of using a traditional way to calculate one set of the weights and bias in training time series with sequences shifted by certain amount of time series. We also consider an algorithm for an evaluation process. In the traditional way, the evaluation process is executed by using final weights and biases calculated in the training process. Instead, during the testing process, the weights and biases are iteratively updated in each sequence as done in the training process. Several numerical experiments demonstrate the efficiency of the proposed techniques.","url":"https://doi.org/10.14311/nnw.2024.34.005","authors":["Dokkyun Yi","Inmi Kim","Sunyoung Bu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-01T09:21:26Z","doi":"10.14311/nnw.2024.34.005","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.2139/ssrn.4842629","name":"Logisitics / Multinomial Logistics / Neural Network Probability Contributions","source":"crossref","abstract":"I develop a statistical approach to decompose the probability of logistics, multinomial logistics, and neural network models into components, called QPC(k). Where P = Σ QPC(k). This approach add another tool in analyzing and visualizing the outcome of logistics, multinomial logistics, and neural network models.","url":"https://doi.org/10.2139/ssrn.4842629","authors":["Quoc Phan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-29T13:13:38Z","doi":"10.2139/ssrn.4842629","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.1109/biocas67066.2025.00132","name":"A Spiking Convolutional Neural Network Algorithm Based on Piecewise-Linear Complementary Leaky Integrate-and-Fire (PCLIF) Neurons and Hybrid Surrogate Gradient Training","source":"crossref","abstract":"","url":"https://doi.org/10.1109/biocas67066.2025.00132","authors":["Zong-Zhe Wu","Yi-Wen Chuang","Kea-Tiong Tang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-14T20:38:47Z","doi":"10.1109/biocas67066.2025.00132","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.36227/techrxiv.173895043.31733566/v1","name":"Artificial Neural Network for Digits Classification (July 2024)","source":"crossref","abstract":"This lab report presents our work on building artificial neural networks (ANNs) from scratch and evaluating their performance on the MNIST and Kuzushiji-MNIST datasets. We experimented with different configurations to assess their impact on model accuracy, including random initialization, Kaiming/Xavier initialization, dropout regularization, and combinations of these methods. The highest accuracy of 90.611% for the MNIST dataset was achieved with a randomly initialized 5-layered network, while the Kuzushiji-MNIST dataset attained the best performance with Kaiming/Xavier initialization at 90.386%. Incorporating regularization techniques generally resulted in lower performance, underscoring the complexity of optimizing ANNs for specific datasets. These results offer valuable insights into the selection and tuning of neural network configurations for enhanced accuracy.","url":"https://doi.org/10.36227/techrxiv.173895043.31733566/v1","authors":["Girban Adhikari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-07T12:47:26Z","doi":"10.36227/techrxiv.173895043.31733566/v1","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.1504/ijcc.2025.148724","name":"BERA-CLOUD: resource allocation in cloud computing using a bald eagle optimised spiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1504/ijcc.2025.148724","authors":["Nikhil Kumar Marriwala","Sunita Panda","Priya Dasarwar","Pooja Singh","C. Gnana Kousalya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-22T11:30:14Z","doi":"10.1504/ijcc.2025.148724","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1201/9781003572886-11","name":"Neural and Neuro-Fuzzy Control Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003572886-11","authors":["Phil Picton"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-10T09:11:09Z","doi":"10.1201/9781003572886-11","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1109/lra.2024.3457371","name":"A Rapid Adapting and Continual Learning Spiking Neural Network Path Planning Algorithm for Mobile Robots","source":"crossref","abstract":"","url":"https://doi.org/10.1109/lra.2024.3457371","authors":["Harrison Espino","Robert Bain","Jeffrey L. Krichmar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-10T19:26:40Z","doi":"10.1109/lra.2024.3457371","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.1007/s11571-023-09989-1","name":"Predicting the temporal-dynamic trajectories of cortical neuronal responses in non-human primates based on deep spiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11571-023-09989-1","authors":["Jie Zhang","Liwei Huang","Zhengyu Ma","Huihui Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-05T07:01:47Z","doi":"10.1007/s11571-023-09989-1","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.1109/mapr67746.2025.11133952","name":"DSC-SNN: A Depthwise Separable Convolutional Spiking Neural Network for Efficient, Privacy-Preserving Action Recognition from Event-Based Data","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mapr67746.2025.11133952","authors":["Nguyen Tan Khang Le","Ha Dung Nguyen","Thanh Binh Nguyen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-29T17:39:20Z","doi":"10.1109/mapr67746.2025.11133952","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1109/icsidp62679.2024.10868802","name":"Real-time Image Recognition System based on Ultra-Low-Latency Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icsidp62679.2024.10868802","authors":["Bin Lan","Xi Zhang","Heng Dong","Ming Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-12T18:16:22Z","doi":"10.1109/icsidp62679.2024.10868802","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.1007/978-981-95-4378-6_42","name":"Novel Neuron-Stability Weighted Dynamic Evolving Spiking Neural Network (NSW-DeSNN) for Classification of fMRI Data","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-95-4378-6_42","authors":["Maryam Doborjeh","Zohreh Doborjeh","Nikola Kasabov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-10T15:52:47Z","doi":"10.1007/978-981-95-4378-6_42","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1038/s41598-024-77779-8","name":"Exploring spiking neural networks for deep reinforcement learning in robotic tasks","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s41598-024-77779-8","authors":["Luca Zanatta","Francesco Barchi","Simone Manoni","Silvia Tolu","Andrea Bartolini","Andrea Acquaviva"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-27T18:24:01Z","doi":"10.1038/s41598-024-77779-8","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.1109/mcsoc64144.2024.00077","name":"EnsembleSTDP: Distributed in-situ Spike Timing Dependent Plasticity Learning in Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mcsoc64144.2024.00077","authors":["Hanyu Yuga","Khanh N. Dang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-03T19:17:28Z","doi":"10.1109/mcsoc64144.2024.00077","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.53347/rid-193529","name":"Autoregressive neural network","source":"crossref","abstract":"","url":"https://doi.org/10.53347/rid-193529","authors":["Sara Rivera","Candace Moore","Joachim Feger"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-06T09:51:47Z","doi":"10.53347/rid-193529","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.2139/ssrn.4862342","name":"Plan (Pruning Learning Artificial Neural Network)","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4862342","authors":["Hasan  Can Beydili"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-12T03:59:37Z","doi":"10.2139/ssrn.4862342","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.1016/j.neunet.2024.106457","name":"Advancing neural network calibration: The role of gradient decay in large-margin Softmax optimization","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106457","authors":["Siyuan Zhang","Linbo Xie"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-12T16:57:24Z","doi":"10.1016/j.neunet.2024.106457","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.1016/j.celrep.2024.114412","name":"Emergent perceptual biases from state-space geometry in trained spiking recurrent neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.celrep.2024.114412","authors":["Luis Serrano-Fernández","Manuel Beirán","Néstor Parga"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-03T22:49:54Z","doi":"10.1016/j.celrep.2024.114412","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.1007/s00521-024-09441-3","name":"Gravitational wave isolation with autoencoder neural network cascade","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-024-09441-3","authors":["Mayank Sengupta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-15T12:02:08Z","doi":"10.1007/s00521-024-09441-3","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.1109/nice61972.2024.10549584","name":"PETNet–Coincident Particle Event Detection using Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nice61972.2024.10549584","authors":["Jan Debus","Charlotte Debus","Günther Dissertori","Markus Götz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-11T17:30:32Z","doi":"10.1109/nice61972.2024.10549584","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1109/isvlsi61997.2024.00052","name":"Compressed Latent Replays for Lightweight Continual Learning on Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isvlsi61997.2024.00052","authors":["Alberto Dequino","Alessio Carpegna","Davide Nadalini","Alessandro Savino","Luca Benini","Stefano Di Carlo","Francesco Conti"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-25T17:27:50Z","doi":"10.1109/isvlsi61997.2024.00052","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.52202/079017-0675","name":"Spatio-Temporal Interactive Learning for Efficient Image Reconstruction of Spiking Cameras","source":"crossref","abstract":"","url":"https://doi.org/10.52202/079017-0675","authors":["Bin Fan","Jiaoyang Yin","Yuchao Dai","Chao Xu","Tiejun Huang","Boxin Shi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-03T11:20:56Z","doi":"10.52202/079017-0675","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.1007/978-3-031-72341-4_11","name":"Revealing Functions of Extra-Large Excitatory Postsynaptic Potentials: Insights from Dynamical Characteristics of Reservoir Computing with Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-72341-4_11","authors":["Asato Fujimoto","Sou Nobukawa","Yusuke Sakemi","Yoshiho Ikeuchi","Kazuyuki Aihara"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-16T13:02:55Z","doi":"10.1007/978-3-031-72341-4_11","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.3389/fnins.2023.1270090","name":"SHIP: a computational framework for simulating and validating novel technologies in hardware spiking neural networks","source":"crossref","abstract":"Investigations in the field of spiking neural networks (SNNs) encompass diverse, yet overlapping, scientific disciplines. Examples range from purely neuroscientific investigations, researches on computational aspects of neuroscience, or applicative-oriented studies aiming to improve SNNs performance or to develop artificial hardware counterparts. However, the simulation of SNNs is a complex task that can not be adequately addressed with a single platform applicable to all scenarios. The optimization of a simulation environment to meet specific metrics often entails compromises in other aspects. This computational challenge has led to an apparent dichotomy of approaches, with model-driven algorithms dedicated to the detailed simulation of biological networks, and data-driven algorithms designed for efficient processing of large input datasets. Nevertheless, material scientists, device physicists, and neuromorphic engineers who develop new technologies for spiking neuromorphic hardware solutions would find benefit in a simulation environment that borrows aspects from both approaches, thus facilitating modeling, analysis, and training of prospective SNN systems. This manuscript explores the numerical challenges deriving from the simulation of spiking neural networks, and introduces SHIP, Spiking (neural network) Hardware In PyTorch, a numerical tool that supports the investigation and/or validation of materials, devices, small circuit blocks within SNN architectures. SHIP facilitates the algorithmic definition of the models for the components of a network, the monitoring of states and output of the modeled systems, and the training of the synaptic weights of the network, by way of user-defined unsupervised learning rules or supervised training techniques derived from conventional machine learning. SHIP offers a valuable tool for researchers and developers in the field of hardware-based spiking neural networks, enabling efficient simulation and validation of novel technologies.","url":"https://doi.org/10.3389/fnins.2023.1270090","authors":["Emanuele Gemo","Sabina Spiga","Stefano Brivio"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-07T23:51:25Z","doi":"10.3389/fnins.2023.1270090","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.1016/j.neucom.2024.128613","name":"K-order echo-type spiking neural P systems for time series forecasting","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2024.128613","authors":["Juan He","Hong Peng","Jun Wang","Qian Yang","Antonio Ramírez-de-Arellano"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-16T06:31:29Z","doi":"10.1016/j.neucom.2024.128613","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.62919/sdfg8911","name":"Optimizing construction cost management with BIM technology and Neural Network Models","source":"crossref","abstract":"","url":"https://doi.org/10.62919/sdfg8911","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-23T10:07:56Z","doi":"10.62919/sdfg8911","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.52202/078372-0022","name":"Investigation of Low-Energy Spiking Neural Networks Based on Temporal Coding for Scene Classification","source":"crossref","abstract":"","url":"https://doi.org/10.52202/078372-0022","authors":["Paolo Paolo_lunghi","Stefano Silvestrini","Dominik Dold","Gabriele Meoni","Alexander Hadjiivanov","Dario Izzo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-31T21:07:16Z","doi":"10.52202/078372-0022","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.1038/s41598-024-62798-2","name":"Author Correction: Enhanced read resolution in reconfigurable memristive synapses for Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s41598-024-62798-2","authors":["Hritom Das","Catherine Schuman","Nishith N. Chakraborty","Garrett S. Rose"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-23T12:01:56Z","doi":"10.1038/s41598-024-62798-2","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.24963/ijcai.2024/767","name":"Exploiting Label Skewness for Spiking Neural Networks in Federated Learning","source":"crossref","abstract":"The energy efficiency of deep spiking neural networks (SNNs) aligns with the constraints of resource-limited edge devices, positioning SNNs as a promising foundation for intelligent applications leveraging the extensive data collected by these devices. To safeguard data privacy, federated learning (FL) facilitates collaborative SNN-based model training by leveraging data distributed across edge devices without transmitting local data to a central server. However, existing FL approaches encounter challenges in handling label-skewed data across devices, inducing drift in the local SNN model and consequently impairing the performance of the global SNN model. To tackle these problems, we propose a novel framework called FedLEC, which incorporates intra-client label weight calibration to balance the learning intensity across local labels and inter-client knowledge distillation to mitigate local SNN model bias caused by label absence. Extensive experiments with three different structured SNNs across five datasets (i.e., three non-neuromorphic and two neuromorphic datasets) demonstrate the efficiency of FedLEC. Compared to seven state-of-the-art FL algorithms, FedLEC achieves an average accuracy improvement of approximately 11.59% for the global SNN model under various label skew distribution settings.","url":"https://doi.org/10.24963/ijcai.2024/767","authors":["Di Yu","Xin Du","Linshan Jiang","Huijing Zhang","Shuiguang Deng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-26T10:28:11Z","doi":"10.24963/ijcai.2024/767","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.1038/s41467-024-51110-5","name":"High-performance deep spiking neural networks with 0.3 spikes per neuron","source":"crossref","abstract":"Abstract Communication by rare, binary spikes is a key factor for the energy efficiency of biological brains. However, it is harder to train biologically-inspired spiking neural networks than artificial neural networks. This is puzzling given that theoretical results provide exact mapping algorithms from artificial to spiking neural networks with time-to-first-spike coding. In this paper we analyze in theory and simulation the learning dynamics of time-to-first-spike-networks and identify a specific instance of the vanishing-or-exploding gradient problem. While two choices of spiking neural network mappings solve this problem at initialization, only the one with a constant slope of the neuron membrane potential at threshold guarantees the equivalence of the training trajectory between spiking and artificial neural networks with rectified linear units. For specific image classification architectures comprising feed-forward dense or convolutional layers, we demonstrate that deep spiking neural network models can be effectively trained from scratch on MNIST and Fashion-MNIST datasets, or fine-tuned on large-scale datasets, such as CIFAR10, CIFAR100 and PLACES365, to achieve the exact same performance as that of artificial neural networks, surpassing previous spiking neural networks. Our approach accomplishes high-performance classification with less than 0.3 spikes per neuron, lending itself for an energy-efficient implementation. We also show that fine-tuning spiking neural networks with our robust gradient descent algorithm enables their optimization for hardware implementations with low latency and resilience to noise and quantization.","url":"https://doi.org/10.1038/s41467-024-51110-5","authors":["Ana Stanojevic","Stanisław Woźniak","Guillaume Bellec","Giovanni Cherubini","Angeliki Pantazi","Wulfram Gerstner"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-09T00:02:30Z","doi":"10.1038/s41467-024-51110-5","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.1016/b978-0-443-22299-3.00013-x","name":"Protein structure prediction with recurrent neural network and convolutional neural network: a case study","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-22299-3.00013-x","authors":["Ritu Karwasra","Kushagra Khanna","Kapil Suchal","Ajay Sharma","Surender Singh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-26T02:23:14Z","doi":"10.1016/b978-0-443-22299-3.00013-x","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.1109/icccnt61001.2024.10725825","name":"Classification of Pests in Agricultural Farms Using Convolutional Neural Network Compared to Artificial Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icccnt61001.2024.10725825","authors":["Bobbilla Ramya Sri","T. Suresh Balakrishnan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-04T23:06:46Z","doi":"10.1109/icccnt61001.2024.10725825","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.1109/percomworkshops59983.2024.10503205","name":"A Bio-inspired Low-power Hybrid Analog/Digital Spiking Neural Networks for Pervasive Smart Cameras","source":"crossref","abstract":"","url":"https://doi.org/10.1109/percomworkshops59983.2024.10503205","authors":["Yung-Ting Hsieh","Dario Pompili"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-23T18:10:48Z","doi":"10.1109/percomworkshops59983.2024.10503205","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.21203/rs.3.rs-4119202/v1","name":"NeuDen: A Framework for the Integration of Neuromorphic Evolving Spiking Neural Networks with Dynamic Evolving Neuro-Fuzzy Systems for Predictive and Explainable Modelling of Streaming Data","source":"crossref","abstract":"Abstract This paper introduces a novel framework, called here 'NeuDen' for the integration of neuromorphic evolving spiking neural networks (eSNN), that learn efficiently multiple time series in their temporal association and interaction, with dynamic evolving neuro-fuzzy systems (deNFS), that learn incrementally extracted from the eSNN feature vectors, to predict future time-series values and to produce interpretable fuzzy rules. The new framework aims to make the best out of the dominant features of the two types of models. First, spike-time-dependent plasticity (STDP) learning is used in SNN to learn temporal interaction between multiple time series, connected to a dynamic eSNN (deSNN) as a regressor/classifier. Then, feature-vectors are extracted from the trained deSNN for further learning, fuzzy inference and rule extraction in a deNFS, here exemplified by DENFIS, resulting in an accurate prediction results and explainable dynamic fuzzy rules. The NeuDen, framework and model, overcomes both the explainability problems of eSNN and the limitations of deNFS to model multiple streaming time series in their temporal interaction. NeuDen surpasses both deSNN and DENFIS by providing multiple regression models and achieving higher accuracy. NeuDen is demonstrated on bench mark data and on financial and economic time series, achieving from 3 to 100 times smaller RMSE when compared with other evolving systems. The proposed framework opens a new direction for the development of more efficient evolving systems by integrating eSNN with other methods, such as other neuro-fuzzy systems, deep neural networks and quantum classifiers for specific applications.","url":"https://doi.org/10.21203/rs.3.rs-4119202/v1","authors":["Iman AbouHassan","Nikola Kasabov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T09:56:25Z","doi":"10.21203/rs.3.rs-4119202/v1","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.21070/ups.4666","name":"Implementation Convolutional Neural Network (CNN) for Bima Script Handwriting Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.21070/ups.4666","authors":["Ahmad Angga Handoko","Mochamad Alfan Rosid"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-20T09:12:47Z","doi":"10.21070/ups.4666","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.1109/iscas58744.2024.10558381","name":"A Compact 140nW/input Winner-Take-All Circuit for Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas58744.2024.10558381","authors":["Gaurav R","Abhishek A. Kadam","Ajay K. Singh","Laxmeesha Somappa","Maryam Shojaei Baghini","Udayan Ganguly"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-02T17:22:52Z","doi":"10.1109/iscas58744.2024.10558381","addedAt":"2026-09-01T01:48:26.354Z","updatedAt":"2026-09-01T01:48:26.354Z"},{"id":"doi:10.1007/s10462-024-10790-7","name":"A new deep neural network for forecasting: Deep dendritic artificial neural network","source":"crossref","abstract":"Abstract Deep artificial neural networks have become a good alternative to classical forecasting methods in solving forecasting problems. Popular deep neural networks classically use additive aggregation functions in their cell structures. It is available in the literature that the use of multiplicative aggregation functions in shallow artificial neural networks produces successful results for the forecasting problem. A type of high-order shallow artificial neural network that uses multiplicative aggregation functions is the dendritic neuron model artificial neural network, which has successful forecasting performance. In this study, the transformation of the dendritic neuron model turned into a multi-output architecture. A new dendritic cell based on the multi-output dendritic neuron model and a new deep artificial neural network is proposed. The training of this new deep dendritic artificial neural network is carried out with the differential evolution algorithm. The forecasting performance of the deep dendritic artificial neural network is compared with basic classical forecasting methods and some recent shallow and deep artificial neural networks over stock market time series. As a result, it has been observed that deep dendritic artificial neural network produces very successful forecasting results for the forecasting problem.","url":"https://doi.org/10.1007/s10462-024-10790-7","authors":["Erol Egrioglu","Eren Bas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-11T14:02:14Z","doi":"10.1007/s10462-024-10790-7","addedAt":"2026-09-01T01:48:26.355Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.2118/222605-ms","name":"Predicting System Surface Parameters Using Artificial Neural Network","source":"crossref","abstract":"Abstract The prediction of apparent surface torque and the system standpipe pressure holds immense importance in any automated system or digital twin solution. These parameters provide crucial insights that are instrumental in determining various factors in the digitalized drilling application workspace. However, obtaining these values prior to the operation poses a challenge due to their dependence on numerous lithological and operational parameters. Due to the problem of non-linearity, a statistical tool is favored in developing a prediction system for these features. Artificial neural networks (ANN), a statistical tool in machine learning (ML), can effectively predict the system standpipe pressure and the apparent surface torque. A logical base data cleaning process is conducted to ensure consciousness cleaning of the dataset based on statistical feature exploration, feature engineering, and domain knowledge. A large dataset of 336 wells from a single operator across four concessions is used to train the ANN. This large dataset overcomes the problem of overfitting within the designed ANN, while extended training epochs avoid the underfitting problem. An extensive trial and error alternatives selection process was used to select the ANN optimum topography. The Nesterov-accelerated adaptive moment estimation algorithm is the optimization algorithm used to improve the ANN solution's training efficiency and convergence speed. The developed ANN achieved 93.09% and 92.62% accuracy for the apparent surface torque and the standpipe pressure feature, respectively, in the non-biased testing of the result. The work investigating the low-order topography for the ANN shows poor accuracy against the high and more sophisticated topography of the ANN. One of the ANN's behaviors realized is that enhancing the prediction accuracy for one feature results in a deterioration in the prediction accuracy of the other. Several attempts were made to create an automated drilling system; however, these attempts focused on the larger picture of the model and ignored the vital components that the calculated and predicted calculations are based on. System standpipe pressure and apparent surface torque prediction provide a solid foundation for an integrated system. The system's development used non-stochastic gradient decent tools to achieve the global minimum of the solution, contrary to most developed models' approaches to that topic. The high prediction accuracy of the developed ANN using the large dataset for training is a differentiator for this model.","url":"https://doi.org/10.2118/222605-ms","authors":["Mohammad Eltrissi","Omar Yousef"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-04T00:10:57Z","doi":"10.2118/222605-ms","addedAt":"2026-09-01T01:48:26.355Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1109/icons62911.2024.00017","name":"Neuro-Spark: A Submicrosecond Spiking Neural Networks Architecture for In-Sensor Filtering","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons62911.2024.00017","authors":["Narsinga Rao Miniskar","Aaron R. Young","Kazi Asifuzzaman","Shruti Kulkarni","Prasanna Date","Alice Bean","Jeffrey S. Vetter"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T18:37:03Z","doi":"10.1109/icons62911.2024.00017","addedAt":"2026-09-01T01:48:26.355Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1080/01490419.2024.2392121","name":"Utilizing Elephant Herd-Inspired Spiking Neural Networks for Enhanced Ship Detection and Classification in Marine Scene Matching","source":"crossref","abstract":"","url":"https://doi.org/10.1080/01490419.2024.2392121","authors":["Sayed Abdhahir Y.","Senthil Singh C."],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-01T17:26:01Z","doi":"10.1080/01490419.2024.2392121","addedAt":"2026-09-01T01:48:26.355Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1109/memocode63347.2024.00017","name":"Configuring Safe Spiking Neural Controllers for Cyber-Physical Systems through Formal Verification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/memocode63347.2024.00017","authors":["Arkaprava Gupta","Sumana Ghosh","Ansuman Banerjee","Swarup Kumar Mohalik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-06T18:37:48Z","doi":"10.1109/memocode63347.2024.00017","addedAt":"2026-09-01T01:48:26.355Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1016/j.neucom.2023.126984","name":"An AER-based spiking convolution neural network system for image classification with low latency and high energy efficiency","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2023.126984","authors":["Yueqi Zhang","Lichen Feng","Hongwei Shan","Liying Yang","Zhangming Zhu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-02T19:56:36Z","doi":"10.1016/j.neucom.2023.126984","addedAt":"2026-09-01T01:48:26.355Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1007/978-3-031-49407-9_12","name":"Slippage Classification in Prosthetic Hands with a Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-49407-9_12","authors":["Jone Follmann","Cosimo Gentile","Francesca Cordella","Loredana Zollo","Cesar Ramos Rodrigues"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-03T05:02:57Z","doi":"10.1007/978-3-031-49407-9_12","addedAt":"2026-09-01T01:48:26.355Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1201/9781003572886-8","name":"Efficient Training of Feed-Forward Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003572886-8","authors":["Martin Moller"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-10T09:11:09Z","doi":"10.1201/9781003572886-8","addedAt":"2026-09-01T01:48:26.355Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.3103/s1060992x24700061","name":"Analytical Calculation of Weights Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.3103/s1060992x24700061","authors":["P. Sh. Geidarov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-04T10:02:28Z","doi":"10.3103/s1060992x24700061","addedAt":"2026-09-01T01:48:26.355Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1109/icaccs60874.2024.10717307","name":"Accurate and Optimized Labelling of Fashion Products Through Attention Based Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icaccs60874.2024.10717307","authors":["N Vithyatharshana","Yedhoti Thrinayani","Yogeshwar Nitin Kulkarni","Rimjhim Padam Singh","Sneha Kanchan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-23T17:40:34Z","doi":"10.1109/icaccs60874.2024.10717307","addedAt":"2026-09-01T01:48:26.355Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1016/j.tcs.2024.114705","name":"Towards a general methodology for formal verification on spiking neural P systems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.tcs.2024.114705","authors":["Mario J. Pérez-Jiménez","Luis Valencia-Cabrera","David Orellana-Martín","Antonio Ramírez-de-Arellano"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-27T16:41:31Z","doi":"10.1016/j.tcs.2024.114705","addedAt":"2026-09-01T01:48:26.355Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1201/9781003572886-12","name":"Image Compression using Neural Networks","source":"crossref","abstract":"Data compression is increasingly becoming an important subject in all areas of computing and communications. While it is true that network speeds have significantly increased, and that the price of disk storage has decreased dramatically, new computer applications which include multimedia documents with very large data set requirements are constantly pushing the limits of these evolving boundaries. For this reason, data compression will always be important, regardless of the current state-of-the-art in network and storage technologies.","url":"https://doi.org/10.1201/9781003572886-12","authors":["Christopher Cramer","Erol Gelenbe"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-10T09:11:09Z","doi":"10.1201/9781003572886-12","addedAt":"2026-09-01T01:48:26.355Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.3390/electronics14030578","name":"Designing Spiking Neural Network-Based Reinforcement Learning for 3D Robotic Arm Applications","source":"crossref","abstract":"This study investigates a novel approach to robotic arm control through integrating spiking neural networks with the twin delayed deep deterministic policy gradient reinforcement learning algorithm. Specifically, it presents the first application of spiking neural networks-based twin delayed deep deterministic policy gradient in 3D robotic manipulation, demonstrating its extension from traditional 2D tasks to complex 3D target-reaching scenarios with improved energy efficiency and stability. Additionally, with the inertial measurement unit data the system successfully mimics human arm movements, achieving a success rate of 0.95 among 50 trials and enabling an intuitive and accurate human–robot interaction system. This pioneering attempt highlights the feasibility of combining the biologically inspired spiking neural networks with the reinforcement learning algorithm to address the real-time challenges in high-dimensional robotic environments and advance the field of human–robot interaction systems.","url":"https://doi.org/10.3390/electronics14030578","authors":["Yuntae Park","Jiwoon Lee","Donggyu Sim","Youngho Cho","Cheolsoo Park"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-03T09:35:07Z","doi":"10.3390/electronics14030578","addedAt":"2026-09-01T01:48:26.355Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.1201/9781003572886-9","name":"Exploiting Local Optima in Multiversion Neural Computing","source":"crossref","abstract":"The training of feedforward networks, such as multilayer perceptrons (MLPs) or radial basis function (RBF) nets, is well known to be highly sensitive to initial conditions. A change in the random initialization of the weights, even when all other conditions are fixed, will cause the learning process to converge on another minimum. The alternative minima on the error surface may result in drastically different generalization properties.","url":"https://doi.org/10.1201/9781003572886-9","authors":["Derek Partridge"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-10T09:11:09Z","doi":"10.1201/9781003572886-9","addedAt":"2026-09-01T01:48:26.355Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1007/s41965-024-00140-5","name":"English letter recognition based on adaptive optimization spiking neural P systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s41965-024-00140-5","authors":["Qin Deng","Zexia Huang","Xiaoliang Chen","Xianyong Li","Yajun Du"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-06T13:01:46Z","doi":"10.1007/s41965-024-00140-5","addedAt":"2026-09-01T01:48:26.355Z","updatedAt":"2026-09-01T01:48:26.355Z"},{"id":"doi:10.21203/rs.3.rs-1158026/v2","name":"Reconstructed Brain Like Neural Network R-KFDNN","source":"crossref","abstract":"Abstract Through the neural system damage and repair process of human brain, we can construct the complex deep learning and training of the repair process such as the damage of brain like high-dimensional flexible neural network system or the local loss of data, so as to prevent the dimensional disaster caused by the local loss of high-dimensional data. How to recover and extract feature information when the damaged neural system (flexible neural network) has amnesia or local loss of stored information. Information extraction generally exists in the distribution table of the generation sequence of the key group of the higher dimension or the lower dimension to find the core data stored in the brain. The generation sequence of key group exists in a hidden time tangent cluster. Brain like slice data processing runs on different levels, different dimensions, different tangent clusters and cotangent clusters. The key group in the brain can be regarded as the distribution table of memory fragments. Memory parsing has mirror reflection and is accompanied by the loss of local random data. In the compact compressed time tangent cluster, it freely switches to the high-dimensional information field, and the parsed key is buried in the information.","url":"https://doi.org/10.21203/rs.3.rs-1158026/v2","authors":["zhu rongrong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-27T16:17:00Z","doi":"10.21203/rs.3.rs-1158026/v2","addedAt":"2026-09-01T01:48:27.321Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1108/ilt-03-2020-0109/v2/review1","name":"Review for \"Assessment of artificial neural network for thermohydrodynamic lubrication analysis\"","source":"crossref","abstract":"","url":"https://doi.org/10.1108/ilt-03-2020-0109/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-05T17:04:37Z","doi":"10.1108/ilt-03-2020-0109/v2/review1","addedAt":"2026-09-01T01:48:27.321Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.21275/sr26509130439","name":"Deep Learning Models and Neural Network Optimization Strategies: A Review","source":"crossref","abstract":"","url":"https://doi.org/10.21275/sr26509130439","authors":["Akash Dattatray Raut"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-13T11:23:49Z","doi":"10.21275/sr26509130439","addedAt":"2026-09-01T01:48:27.321Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.2139/ssrn.4986549","name":"A Comprehensive Review of Neural Network Sparsification Approaches","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4986549","authors":["Zaina Lang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-04T20:11:53Z","doi":"10.2139/ssrn.4986549","addedAt":"2026-09-01T01:48:27.321Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.21203/rs.3.rs-1158026/v1","name":"Reconstructed Brain Like Neural Network R-KFDNN","source":"crossref","abstract":"Abstract Through the neural system damage and repair process of human brain, we can construct the complex deep learning and training of the repair process such as the damage of brain like high-dimensional flexible neural network system or the local loss of data, so as to prevent the dimensional disaster caused by the local loss of high-dimensional data. How to recover and extract feature information when the damaged neural system (flexible neural network) has amnesia or local loss of stored information. Information extraction generally exists in the distribution table of the generation sequence of the key group of the higher dimension or the lower dimension to find the core data stored in the brain. The generation sequence of key group exists in a hidden time tangent cluster. Brain like slice data processing runs on different levels, different dimensions, different tangent clusters and cotangent clusters. The key group in the brain can be regarded as the distribution table of memory fragments. Memory parsing has mirror reflection and is accompanied by the loss of local random data. In the compact compressed time tangent cluster, it freely switches to the high-dimensional information field, and the parsed key is buried in the information.","url":"https://doi.org/10.21203/rs.3.rs-1158026/v1","authors":["zhu rongrong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-13T16:47:14Z","doi":"10.21203/rs.3.rs-1158026/v1","addedAt":"2026-09-01T01:48:27.321Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1108/ilt-03-2020-0109/v3/review1","name":"Review for \"Assessment of artificial neural network for thermohydrodynamic lubrication analysis\"","source":"crossref","abstract":"","url":"https://doi.org/10.1108/ilt-03-2020-0109/v3/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-05T17:04:37Z","doi":"10.1108/ilt-03-2020-0109/v3/review1","addedAt":"2026-09-01T01:48:27.321Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.21203/rs.3.rs-1158026/v3","name":"Reconstructed Brain Like Neural Network R-KFDNN","source":"crossref","abstract":"Abstract Through the neural system damage and repair process of human brain, we can construct the complex deep learning and training of the repair process such as the damage of brain like high-dimensional flexible neural network system or the local loss of data, so as to prevent the dimensional disaster caused by the local loss of high-dimensional data. How to recover and extract feature information when the damaged neural system (flexible neural network) has amnesia or local loss of stored information. Information extraction generally exists in the distribution table of the generation sequence of the key group of the higher dimension or the lower dimension to find the core data stored in the brain. The generation sequence of key group exists in a hidden time tangent cluster. Brain like slice data processing runs on different levels, different dimensions, different tangent clusters and cotangent clusters. The key group in the brain can be regarded as the distribution table of memory fragments. Memory parsing has mirror reflection and is accompanied by the loss of local random data. In the compact compressed time tangent cluster, it freely switches to the high-dimensional information field, and the parsed key is buried in the information.","url":"https://doi.org/10.21203/rs.3.rs-1158026/v3","authors":["zhu rongrong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-01-11T20:13:17Z","doi":"10.21203/rs.3.rs-1158026/v3","addedAt":"2026-09-01T01:48:27.321Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.3390/jlpea11020023","name":"A Review of Algorithms and Hardware Implementations for Spiking Neural Networks","source":"crossref","abstract":"Deep Learning (DL) has contributed to the success of many applications in recent years. The applications range from simple ones such as recognizing tiny images or simple speech patterns to ones with a high level of complexity such as playing the game of Go. However, this superior performance comes at a high computational cost, which made porting DL applications to conventional hardware platforms a challenging task. Many approaches have been investigated, and Spiking Neural Network (SNN) is one of the promising candidates. SNN is the third generation of Artificial Neural Networks (ANNs), where each neuron in the network uses discrete spikes to communicate in an event-based manner. SNNs have the potential advantage of achieving better energy efficiency than their ANN counterparts. While generally there will be a loss of accuracy on SNN models, new algorithms have helped to close the accuracy gap. For hardware implementations, SNNs have attracted much attention in the neuromorphic hardware research community. In this work, we review the basic background of SNNs, the current state and challenges of the training algorithms for SNNs and the current implementations of SNNs on various hardware platforms.","url":"https://doi.org/10.3390/jlpea11020023","authors":["Duy-Anh Nguyen","Xuan-Tu Tran","Francesca Iacopi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-05-24T23:35:05Z","doi":"10.3390/jlpea11020023","addedAt":"2026-09-01T01:48:27.321Z","updatedAt":"2026-09-01T01:48:27.321Z"},{"id":"doi:10.1103/physreve.54.5585","name":"Statistical properties of stochastic nonlinear dynamical models of single spiking neurons and neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1103/physreve.54.5585","authors":["Roger Rodriguez","Henry C. Tuckwell"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-27T01:09:47Z","doi":"10.1103/physreve.54.5585","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.21203/rs.3.rs-2262084/v1","name":"Spiking Neural Networks for Predictive and Explainable Modelling of Multimodal Streaming Data with a Case Study on Financial Time-series and Online News","source":"crossref","abstract":"Abstract Human intelligence is characterized by the ability to incrementally integrate different sources of information for a better decision making. This paper argues that brain-inspired spiking neural networks (SNN) can be used for predictive and explainable modelling of multimodal streaming data. The paper proposes a new method, based on the brain-inspired SNN architecture NeuCube, where, first, all streaming data are represented as numerical times series in the same time domain. Then a NeuCube model is incrementally trained on the integrated time series and continuously interpreted. The method is illustrated on integrated modelling of financial time series and online news. In contrast to traditional machine learning techniques, the proposed method reveals the dynamic interaction between all types of temporal variables and their impact on the model accuracy. The method is applicable on a wide range of multimodal time series, such as financial, medical, environmental, supporting also the use of massively parallel and low energy neuromorphic hardware.","url":"https://doi.org/10.21203/rs.3.rs-2262084/v1","authors":["Nikola Kasabov","Iman AbouHassan","Vinayak Jagtap","Parag Kulkarni"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-05T15:53:11Z","doi":"10.21203/rs.3.rs-2262084/v1","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.21203/rs.3.rs-4909959/v1","name":"Neural Architecture Search for Adaptive Neural Network Structures: Comparative Analysis of Layer and Neuron Adjustments","source":"crossref","abstract":"Abstract The network's architecture significantly influences neural network (NN) training efficiency, which necessitates substantial computational resources and time. This paper explores the efficacy of adaptive mechanisms that dynamically modify the neural network's structure during training, focusing on both layer and neuron adjustments through Neural Architecture Search (NAS). Eight adaptive methods are investigated and compared to enhance training efficiency and performance: four for adaptive layer adjustments— Adapt Network Structure Threshold , Adapt Network Structure Moving Average , Gradual Adaptation Based on Slope of Loss Change , and Adaptive Learning Rate Adjustment ; and four for adaptive neuron adjustments— Adaptive Neuron Adjustment , Adapt Network Structure Neuron Growth , Adapt Network Structure Neuron Decay , and Adapt Network Structure Balanced . Experimental tests were conducted using a neural network with five inputs and two outputs, beginning with three inner layers, each containing ten neurons. The results demonstrate that adaptive methods significantly improve training efficiency, providing valuable insights for optimizing neural network structures. This study highlights the potential of combining adaptive strategies through NAS to achieve optimal performance, paving the way for future research and practical applications in neural network training.","url":"https://doi.org/10.21203/rs.3.rs-4909959/v1","authors":["Hamed Hosseinzadeh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-26T02:14:25Z","doi":"10.21203/rs.3.rs-4909959/v1","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.21203/rs.3.rs-4338706/v1","name":" Spectral Analysis of Cellular Neural Network: Unveiling Network Parameters and Graph Characteristics","source":"crossref","abstract":"Abstract Cellular Neural Network (CNN) finds application in a wide array of parallel processing tasks, such as image processing, non-linear operations, generating geometric maps, and high-speed computations. Functioning as an analogue paradigm, CNN comprises an array of cells interconnected at a local level. These cells can be arranged in an array of $m \\times n$ identical cells in a rectangular grid. Graphical representation is achieved by representing cells as vertices and their connections as edges, denoted as $\\Gamma_{m,n}$. This paper aims to compute spectrum based results for the CNN. To accomplish this, we determine the Laplacian and the signless Laplacian eigenvalues of $\\Gamma_{m,n}$. Utilising these results, we derive a comprehensive set of network-related parameters, including the Kirchhoff index, average path length, mean first passage time, the number of spanning trees, the Estrada index, and the resolvent Estrada index. Furthermore, we delve into graph-related parameters encompassing graph energy and spectral radius to gain deeper insights into the characteristics of $\\Gamma_{m,n}$. To streamline our analysis, we design an algorithm to calculate the network-related parameters, as mentioned earlier. Moreover, results are enhanced by the inclusion of numerical tables and vibrant 3D plots that visually depict Laplacian and signless Laplacian energies for specific configurations. Finally, we underscore the application of energy for image segmentation by selecting suitable CNN sizes based on energy, which provides precise results that reduce evaluation time and significantly enhance diagnostic accuracy in image processing. 2020 Mathematics Subject Classification. 05C50, 05C76, 05C90, 68R10, 94C15.","url":"https://doi.org/10.21203/rs.3.rs-4338706/v1","authors":["Nithya Saravanan","Manju Ganesan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-06T06:21:31Z","doi":"10.21203/rs.3.rs-4338706/v1","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.5256/f1000research.149233.r199872","name":"Peer Review Report For: Graph neural network-based anomaly detection for river network systems [version 1; peer review: 2 approved with reservations]","source":"crossref","abstract":"","url":"https://doi.org/10.5256/f1000research.149233.r199872","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-26T00:17:06Z","doi":"10.5256/f1000research.149233.r199872","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:27.322Z"},{"id":"doi:10.1111/ejn.15928/v1/review1","name":"Review for \"Dynamic attention signaling in V4: relation to fast‐spiking/non‐fast‐spiking cell class and population coupling\"","source":"crossref","abstract":"","url":"https://doi.org/10.1111/ejn.15928/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-02-06T09:03:47Z","doi":"10.1111/ejn.15928/v1/review1","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.2174/011570159x434753260323193021","name":"Role of Perineuronal Nets in Neuronal Plasticity and Repair: Molecular Perspectives on Psychiatric Disorders.","source":"europepmc","abstract":"","url":"https://doi.org/10.2174/011570159x434753260323193021","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.2174/011570159x434753260323193021","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1002/adma.73574","name":"Weaving Intelligence: Thermally Drawn Multimaterial Fibers Toward AI-Enabled Smart Textiles.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.73574","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.73574","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1126/sciadv.ady8751","name":"Incorporating brain-inspired mechanisms for multimodal learning in artificial intelligence.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.ady8751","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1126/sciadv.ady8751","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3390/biomimetics11050302","name":"Speech Recognition with an fMRISNN Constrained by Human Functional Brain Networks: A Study of Enhanced MFCC-Driven Sparse Spike Encoding.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics11050302","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/biomimetics11050302","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41467-026-73032-0","name":"Fast efficient coding and sensory adaptation in gain-adaptive recurrent networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-73032-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-73032-0","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1103/4mwt-2yb2","name":"Temporal stimulus segmentation by reinforcement learning in populations of spiking neurons.","source":"europepmc","abstract":"","url":"https://doi.org/10.1103/4mwt-2yb2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1103/4mwt-2yb2","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1016/j.pneurobio.2026.102939","name":"REM sleep as a dummy-model of the world: A theoretical framework.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.pneurobio.2026.102939","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.pneurobio.2026.102939","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41598-026-50169-y","name":"Energy efficient cyber-physical control of renewable microgrids using edge-AI enabled IoT and secure blockchain coordination.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-50169-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-50169-y","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1016/j.isci.2026.116125","name":"Post-synaptic facilitation and network dynamics underlying stimulus-specific combination sensitivity.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.isci.2026.116125","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.isci.2026.116125","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41467-026-69297-0","name":"Decoding phantom limb movements from intraneural recordings.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-69297-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-69297-0","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1371/journal.pcbi.1014177","name":"Activity-dependent neuromodulation and calcium homeostasis cooperate to produce robust and modulable neuronal function.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pcbi.1014177","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pcbi.1014177","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1371/journal.pone.0345850","name":"All-optical doubly resonant cavities for energy-efficient ReLU function in nanophotonic deep learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pone.0345850","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pone.0345850","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1016/j.neuron.2026.05.004","name":"A learning-evoked slow-oscillatory architecture paces population activity for offline reactivation across the human medial temporal lobe.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neuron.2026.05.004","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neuron.2026.05.004","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1016/j.neunet.2025.108127","name":"Spiking neural networks for EEG signal analysis: From theory to practice.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.108127","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2025.108127","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fncel.2026.1803262","name":"Stochasticity in action potential backpropagation: consequences for neuronal computation.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncel.2026.1803262","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fncel.2026.1803262","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s42003-025-09486-7","name":"Data-driven ANN-based visual decoding enables unsupervised functional alignment.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s42003-025-09486-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s42003-025-09486-7","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1103/dx7m-fpch","name":"Macroscopic dynamics of quadratic integrate-and-fire neurons subject to correlated noise.","source":"europepmc","abstract":"","url":"https://doi.org/10.1103/dx7m-fpch","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1103/dx7m-fpch","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fncom.2026.1793265","name":"A novel image-based neuronal network model framework for understanding visual multistability and neurological disorders.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2026.1793265","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fncom.2026.1793265","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41467-025-68048-x","name":"Synaptic and intrinsic membrane defects disrupt early neural network dynamics in Down syndrome.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-68048-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-025-68048-x","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3390/brainsci16020158","name":"From Spontaneous Ignitions to Sensorimotor Cell Assemblies via Dopamine: A Spiking Neurocomputational Model of Infants' Hand Action Acquisition.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/brainsci16020158","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/brainsci16020158","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fneur.2026.1779207","name":"High-frequency oscillations and sleep spindles in epilepsy: from mechanisms to modeling.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fneur.2026.1779207","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fneur.2026.1779207","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1371/journal.pcbi.1014283","name":"Spatial richness of neural magnetic fields.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pcbi.1014283","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pcbi.1014283","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1007/s11571-026-10416-4","name":"Application of neurodynamics theory in the study of neural circuits in major depressive disorder: a review on neural energy approaches.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-026-10416-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s11571-026-10416-4","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s42003-026-09918-y","name":"Reduced inhibition, bursting, and accelerated oscillations drive early hippocampal hyperactivity in Alzheimer's disease in vivo.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s42003-026-09918-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s42003-026-09918-y","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41593-026-02258-4","name":"Laminar organization of cellular microcircuits modulating human interictal epileptiform discharges.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41593-026-02258-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41593-026-02258-4","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3390/mi17050524","name":"Nanogroove-Induced Enhancement of Neural Spike Activity in Stem Cell-Derived Networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/mi17050524","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/mi17050524","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41598-026-35641-z","name":"NeoHebbian synapses to accelerate online training of neuromorphic hardware.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-35641-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-35641-z","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.3389/fncom.2026.1834521","name":"Editorial: Advancements in neural coding: sensory perception and multiplexed encoding strategies.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2026.1834521","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fncom.2026.1834521","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fncom.2026.1813959","name":"Coherent-resonant netting: disorder-enhanced selectivity from transient wave-like dynamics on biological connectomes.","source":"europepmc","abstract":"Biological agents face an energy-information bottleneck: inference requires rapid exploration of large hypothesis spaces, yet high-gain spiking is metabolically expensive. We propose Coherent-Resonant Netting (CRN) as a two-regime decision architecture in which a low-amplitude Stage-I transport process filters candidate routes on a structural graph before a higher-cost Stage-II commitment step. In this manuscript, we model Stage-I only, using a mechanistically neutral GKSL open-system proxy with dephasing rate κ and diagonal disorder ε. The model does not imply microscopic quantum coherence in neural tissue. In two biological connectome benchmarks, selectivity improves under partial coherence. In a compact Caenorhabditis elegans touch-circuit benchmark, the wave proxy yields a 1.39 × improvement in peak target absorption over a matched low-temperature classical baseline. In a Drosophila larva mushroom-body motif ( N = 243 active nodes), selectivity shows a pronounced non-monotonic disorder-enhanced selectivity peak at intermediate ε, strongest in the native topology and strongly attenuated by degree-preserving rewiring. A permutation-based reanalysis confirms the pre-specified DES contrast (ε = 3 versus ε = 0, p = 0.010), and the effect weakens progressively with increasing dephasing, becoming non-significant in the high-κ regime. We interpret these findings as evidence for a topology-sensitive, dephasing-dependent Stage-I routing effect on biological connectomes. Broader energetic and evolutionary implications remain conditional because Stage-II commitment is not explicitly modeled here.","url":"https://doi.org/10.3389/fncom.2026.1813959","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fncom.2026.1813959","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3390/biomimetics11060410","name":"A Fire Detection Method Based on a Mind-Linked Continuous-Coupled Neural Network.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics11060410","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/biomimetics11060410","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3390/jimaging12020064","name":"SIFT-SNN for Traffic-Flow Infrastructure Safety: A Real-Time Context-Aware Anomaly Detection Framework.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/jimaging12020064","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/jimaging12020064","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41598-026-45033-y","name":"A brain-inspired computational framework for image-based risk assessment.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-45033-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-45033-y","addedAt":"2026-09-01T01:48:27.322Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1371/journal.pone.0340393","name":"A biologically plausible decision-making model based on interacting neural populations.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pone.0340393","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pone.0340393","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41398-026-03991-x","name":"Role of neural oscillations in depression: highlights on gamma oscillations.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41398-026-03991-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41398-026-03991-x","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1186/s12974-026-03835-x","name":"TNF-α and IFN-γ impair neural oscillations and induce neurodegeneration by microglial nitric oxide, metabolic and oxidative stress.","source":"europepmc","abstract":"","url":"https://doi.org/10.1186/s12974-026-03835-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1186/s12974-026-03835-x","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41467-026-71034-6","name":"Light-induced giant random telegraph noise in CuScP&lt;sub&gt;2&lt;/sub&gt;S&lt;sub&gt;6&lt;/sub&gt;/MoS&lt;sub&gt;2&lt;/sub&gt; heterostructures and their use in noise resilience image inference.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-71034-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-71034-6","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41467-026-70659-x","name":"Noradrenaline causes a spread of association in the hippocampal cognitive map.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-70659-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-70659-x","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1371/journal.pcbi.1012966","name":"How the dynamic interplay of cortico-basal ganglia-thalamic pathways shapes the time course of deliberation and commitment.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pcbi.1012966","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pcbi.1012966","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1038/s41467-026-69438-5","name":"Deciphering hippocampal place codes in weak theta rhythms.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-69438-5","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-69438-5","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2023.06.20.545667","name":"Mesoscale simulations predict the role of synergistic cerebellar plasticity during classical eyeblink conditioning","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.06.20.545667","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.06.20.545667","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1101/2023.10.24.563714","name":"Offline hippocampal reactivation during dentate spikes supports flexible memory","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.10.24.563714","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.10.24.563714","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.03.24.534142","name":"A dynamical computational model of theta generation in hippocampal circuits to study theta-gamma oscillations during neurostimulation","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.03.24.534142","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.03.24.534142","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.10.17.562689","name":"Spatio-temporal organization of network activity patterns in the hippocampus","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.10.17.562689","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.10.17.562689","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.11.22.23298729","name":"Electrophysiologically-defined excitation-inhibition autism neurosubtypes","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.11.22.23298729","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.11.22.23298729","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.10.14.618224","name":"Diverse ancestral brainstem noradrenergic neuron activity across species and biological factors","source":"preprints","abstract":"The brainstem cell group, locus coeruleus (LC), is present across vertebrates and influences cardiorespiratory, metabolic, immune, and cognitive functions by activating in two putatively distinct firing patterns. Yet, the degree to which the LC firing rates and patterns are homogenous across species has never been assessed due to inherently limited sample sizes. To remedy this, we pooled cross-species data from 20 laboratories to show that firing rates differ across species and are modulated by sex, age, and type of in vitro or in vivo preparation. Contrary to the prevailing dual-mode firing pattern schema, we observed patterns spread across a low-dimensional manifold, with subregions enriched for specific biological factors and neurodegenerative disease models. Our findings show considerable diversity in an ancestral vertebrate neuromodulatory system.","url":"https://doi.org/10.1101/2024.10.14.618224","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.10.14.618224","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.05.11.540442","name":"The stabilized supralinear network accounts for the contrast dependence of visual cortical gamma oscillations","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.05.11.540442","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.05.11.540442","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.12.05.570285","name":"Beta and theta oscillations track effort and previous reward in human basal ganglia and prefrontal cortex during decision making","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.12.05.570285","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.12.05.570285","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.21203/rs.3.rs-3389804/v1","name":"Noise-Induced Hearing Loss Alters Potassium-Chloride CoTransporter KCC2 and GABA Inhibition in the auditory centers","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3389804/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-3389804/v1","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.07.19.549692","name":"The neural and computational architecture of feedback dynamics in mouse cortex during stimulus report","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.07.19.549692","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.07.19.549692","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2021.11.19.469209","name":"Neural population dynamics reveals disruption of spinal sensorimotor computations during electrical stimulation of sensory afferents","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2021.11.19.469209","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.1101/2021.11.19.469209","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.08.29.555249","name":"Interpretable modelling of input-output computations in cortex","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.08.29.555249","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.08.29.555249","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.09.26.558975","name":"Organizing the coactivity structure of the hippocampus from robust to flexible memory","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.09.26.558975","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.09.26.558975","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.31234/osf.io/cpmre","name":"Spatiotemporal Patterns in Neurobiology: An Overview for Future Artificial Intelligence","source":"preprints","abstract":"","url":"https://doi.org/10.31234/osf.io/cpmre","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.31234/osf.io/cpmre","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.11.03.565561","name":"Tonically active GABAergic neurons in the dorsal periaqueductal gray control the initiation and execution of instinctive escape","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.11.03.565561","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.11.03.565561","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.04.29.591584","name":"Modeling mTORopathy-related epilepsy in cultured murine hippocampal neurons using the multi-electrode array","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.04.29.591584","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.04.29.591584","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2021.07.14.452347","name":"Spike-based symbolic computations on bit strings and numbers","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2021.07.14.452347","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.1101/2021.07.14.452347","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2022.08.23.504923","name":"The aperiodic exponent of subthalamic field potentials reflects excitation/inhibition balance in Parkinsonism: a cross-species study  <i>in vivo</i>","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.08.23.504923","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.08.23.504923","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.05.06.592727","name":"The dorsal thalamic lateral geniculate nucleus is required for visual control of head direction cell firing direction in rats","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.05.06.592727","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.05.06.592727","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.04.25.591075","name":"Common neural mechanisms supporting time judgements in humans and monkeys","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.04.25.591075","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.04.25.591075","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.09.12.557442","name":"Hyperpolarization-Activated Currents Drive Neuronal Activation Sequences in Sleep","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.09.12.557442","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.09.12.557442","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.02.20.580978","name":"Circadian clocks in human cerebral organoids","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.02.20.580978","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.02.20.580978","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.05.08.593232","name":"A common computational and neural anomaly across mouse models of autism","source":"preprints","abstract":"Computational psychiatry has suggested that humans within the autism spectrum disorder (ASD) inflexibly update their expectations (i.e., Bayesian priors). Here, we leveraged high-yield rodent psychophysics (n = 75 mice), extensive behavioral modeling (including principled and heuristics), and (near) brain-wide single cell extracellular recordings (over 53k units in 150 brain areas) to ask (1) whether mice with different genetic perturbations associated with ASD show this same computational anomaly, and if so, (2) what neurophysiological features are shared across genotypes in subserving this deficit. We demonstrate that mice harboring mutations in Fmr1 , Cntnap2 , and Shank3B show a blunted update of priors during decision-making. Neurally, the differentiating factor between animals flexibly and inflexibly updating their priors was a shift in the weighting of prior encoding from sensory to frontal cortices. Further, in mouse models of ASD frontal areas showed a preponderance of units coding for deviations from the animals’ long-run prior, and sensory responses did not differentiate between expected and unexpected observations. These findings demonstrate that distinct genetic instantiations of ASD may yield common neurophysiological and behavioral phenotypes.","url":"https://doi.org/10.1101/2024.05.08.593232","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.05.08.593232","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2022.07.02.498537","name":"Mean-field approximations with adaptive coupling for networks with spike-timing-dependent plasticity","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.07.02.498537","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.07.02.498537","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.01.05.522833","name":"The neuron mixer and its impact on human brain dynamics","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.01.05.522833","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.01.05.522833","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.03.13.532473","name":"Pattern completion and disruption characterize contextual modulation in the visual cortex","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.03.13.532473","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.03.13.532473","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.10.03.23295921","name":"Pediatric Neural Changes to Physical and Emotional Pain After Intensive Interdisciplinary Pain Treatment: A Pilot Study","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.10.03.23295921","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.10.03.23295921","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.10.27.564330","name":"Dynamic layer-specific processing in the prefrontal cortex during working memory","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.10.27.564330","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.10.27.564330","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.12.06.627165","name":"Stimulus-repetition effects on macaque V1 and V4 microcircuits explain gamma-synchronization increase","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.12.06.627165","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.12.06.627165","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2022.09.27.509695","name":"Intrinsic neural timescales in the temporal lobe support an auditory processing hierarchy","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.09.27.509695","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.09.27.509695","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.12.06.570348","name":"Integration of rate and phase codes by hippocampal cell-assemblies supports flexible encoding of spatiotemporal context","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.12.06.570348","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.12.06.570348","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.06.26.600746","name":"Laminar CBV and BOLD response-characteristics over time and space in the human primary somatosensory cortex at 7T","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.06.26.600746","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.06.26.600746","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.07.04.547681","name":"A Brain-Wide Map of Neural Activity during Complex Behaviour","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.07.04.547681","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.07.04.547681","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2022.09.07.507054","name":"Low forces push the maturation of neural precursors into neurons","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.09.07.507054","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.09.07.507054","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.09.30.560279","name":"Default mode network shows distinct emotional and contextual responses yet common effects of retrieval demands across tasks","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.09.30.560279","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.09.30.560279","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.05.15.594341","name":"Rapid modulation of striatal cholinergic interneurons and dopamine release by satellite astrocytes","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.05.15.594341","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.05.15.594341","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2021.12.24.474090","name":"A personalizable autonomous neural mass model of epileptic seizures","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2021.12.24.474090","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.1101/2021.12.24.474090","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.03.02.530774","name":"Combined statistical-biophysical modeling links ion channel genes to physiology of cortical neuron types","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.03.02.530774","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.03.02.530774","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.04.19.536507","name":"COVID-19 and silent hypoxemia in a minimal closed-loop model of the respiratory rhythm generator","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.04.19.536507","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.04.19.536507","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2021.12.22.473863","name":"Heterogeneity of network and coding states in CA1","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2021.12.22.473863","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.1101/2021.12.22.473863","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.03.21.533548","name":"Foundation model of neural activity predicts response to new stimulus types and anatomy","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.03.21.533548","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.03.21.533548","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.04.13.536696","name":"On-chip brain slice stimulation: precise control of electric fields and tissue orientation","source":"preprints","abstract":"Non-invasive brain stimulation modalities, including transcranial direct current stimulation (tDCS), are widely used in neuroscience and clinical practice to modulate brain function and treat neuropsychiatric diseases. DC stimulation of ex vivo brain tissue slices has been a method used to understand mechanisms imparted by tDCS. However, delivering spatiotemporally uniform direct current electric fields (dcEFs) that have precisely engineered magnitudes and are also exempt from toxic electrochemical by-products are both significant limitations in conventional experimental setups. As a consequence, bioelectronic dose-response interrelations, the role of EF orientation, and the biomechanisms of prolonged or repeated stimulation over several days all remain not well understood. Here we developed a platform with fluidic, electrochemical, and magnetically-induced spatial control. Fluidically, the chamber geometrically confines precise dcEF delivery to the enclosed brain slice and allows for tissue recovery in order to monitor post-stimulation effects. Electrochemically, conducting hydrogel electrodes mitigate stimulation-induced faradaic reactions typical of commonly-used metal electrodes. Magnetically, we applied ferromagnetic substrates beneath the tissue and used an external permanent magnet to enable in situ rotational control in relation to the dcEF. By combining the microfluidic chamber with live-cell calcium imaging and electrophysiological recordings, we showcased the potential to study the acute and lasting effects of dcEFs with the potential of providing multi-session stimulation. This on-chip bioelectronic platform presents a modernized yet simple solution to electrically stimulate explanted tissue by offering more environmental control to users, which unlocks new opportunities to conduct thorough brain stimulation mechanistic investigations. Graphical abstract","url":"https://doi.org/10.1101/2023.04.13.536696","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.04.13.536696","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.21203/rs.3.rs-3388353/v1","name":"Mesoscale columnar-like organization of face and body areas","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3388353/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-3388353/v1","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.01.30.577845","name":"A deep-learning strategy to identify cell types across species from high-density extracellular recordings","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.01.30.577845","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.01.30.577845","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.07.15.603543","name":"Oxytocin facilitates social behavior of female rats via selective modulation of interneurons in the medial prefrontal cortex","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.07.15.603543","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.07.15.603543","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.11.08.566030","name":"Insights into the early-life chemical exposome of Nigerian infants and potential correlations with the developing gut microbiome","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.11.08.566030","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.11.08.566030","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.10.08.561390","name":"Increased flexibility of CA3 memory representations following environmental enrichment","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.10.08.561390","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.10.08.561390","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.04.08.588555","name":"A postnatal molecular switch drives the activity-dependent maturation of parvalbumin interneurons","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.04.08.588555","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.04.08.588555","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2021.11.16.468798","name":"Reversible inactivation of ferret auditory cortex impairs spatial and non-spatial hearing","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2021.11.16.468798","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.1101/2021.11.16.468798","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2022.11.30.518492","name":"A chromatic feature detector in the retina signals visual context changes","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.11.30.518492","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.11.30.518492","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2022.12.11.519886","name":"Sleep-like state during wakefulness induced by psychedelic 5-MeO-DMT in mice","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.12.11.519886","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.12.11.519886","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.06.21.600003","name":"Selective suppression of oligodendrocyte-derived amyloid beta rescues neuronal dysfunction in Alzheimer’s Disease","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.06.21.600003","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.06.21.600003","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.09.29.612271","name":"Heterogeneous plasticity of amygdala interneurons in associative learning and extinction","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.09.29.612271","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.09.29.612271","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.06.07.543976","name":"Transforming descending input into motor output: An analysis of the  <i>Drosophila</i>  Male Adult Nerve Cord connectome","source":"preprints","abstract":"In most animals, a relatively small number of descending neurons (DNs) connect higher brain centers in the animal’s head to circuits and motor neurons (MNs) in the nerve cord of the animal’s body that effect movement of the limbs. To understand how brain signals generate behavior, it is critical to understand how these descending pathways are organized onto the body MNs. In the fly, Drosophila melanogaster , MNs controlling muscles in the leg, wing, and other motor systems reside in a ventral nerve cord (VNC), analogous to the mammalian spinal cord. In companion papers, we introduced a densely-reconstructed connectome of the Drosophila Male Adult Nerve Cord (MANC, (Takemura et al., 2024)), including cell type and developmental lineage annotation (Marin et al., 2024), which provides complete VNC connectivity at synaptic resolution. Here, we present a first look at the organization of the VNC networks connecting DNs to MNs based on this new connectome information. We proofread and curated all DNs and MNs to ensure accuracy and reliability, then systematically matched DN axon terminals and MN dendrites with light microscopy data to link their VNC morphology with their brain inputs or muscle targets. We report both broad organizational patterns of the entire network and fine-scale analysis of selected circuits of interest. We discover that direct DN-MN connections are infrequent and identify communities of intrinsic neurons linked to control of different motor systems, including putative ventral circuits for walking, dorsal circuits for flight steering and power generation, and intermediate circuits in the lower tectulum for coordinated action of wings and legs. Our analysis generates hypotheses for future functional experiments and, together with the MANC connectome, empowers others to investigate these and other circuits of the Drosophila ventral nerve cord in richer mechanistic detail.","url":"https://doi.org/10.1101/2023.06.07.543976","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.06.07.543976","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2022.03.03.482657","name":"Beyond pulsed inhibition: Alpha oscillations modulate attenuation and amplification of neural activity in the awake resting-state","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.03.03.482657","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.03.03.482657","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2021.03.15.435518","name":"Spatial representation by ramping activity of neurons in the retrohippocampal cortex","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2021.03.15.435518","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.1101/2021.03.15.435518","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2022.03.01.482549","name":"Sub-harmonic Entrainment of Cortical Gamma Oscillations to Deep Brain Stimulation in Parkinson’s Disease: Model Based Predictions and Validation in Three Human Subjects","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.03.01.482549","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.03.01.482549","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2022.09.08.507081","name":"Successful working memory linked to theta connectivity patterns in the hippocampal-entorhinal circuit","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.09.08.507081","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.09.08.507081","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2022.06.09.495367","name":"A multi-level account of hippocampal function from behaviour to neurons","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.06.09.495367","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.06.09.495367","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2022.09.05.506618","name":"Graded optogenetic activation of the auditory pathway for hearing restoration","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.09.05.506618","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.09.05.506618","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2022.10.30.514365","name":"Whole-brain modeling of the differential influences of Amyloid-Beta and Tau in Alzheimer’s Disease","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.10.30.514365","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.10.30.514365","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.10.12.618012","name":"Region-specific spreading depolarization drives aberrant post-ictal behavior","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.10.12.618012","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.10.12.618012","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2022.12.19.520993","name":"Human mutations in  <i>SLITRK3</i>  implicated in GABAergic synapse development in mice","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.12.19.520993","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.12.19.520993","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2022.03.31.486582","name":"Downregulating α-synuclein in iPSC-derived dopaminergic neurons mimics electrophysiological phenotype of the A53T mutation","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.03.31.486582","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.03.31.486582","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2022.05.09.491042","name":"Reproducibility of  <i>in vivo</i>  electrophysiological measurements in mice","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.05.09.491042","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.05.09.491042","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2022.05.16.492186","name":"Pathogenic TDP-43 Disrupts Axon Initial Segment Structure and Neuronal Excitability in a Human iPSC Model of ALS","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.05.16.492186","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.05.16.492186","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.12.21.571679","name":"Multipair phase-modulated temporal interference electrical stimulation combined with fMRI.","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.12.21.571679","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.12.21.571679","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.05.28.542182","name":"A configural context signal simultaneously but separably drives positioning and orientation of hippocampal place fields","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.05.28.542182","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.05.28.542182","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2022.10.24.513513","name":"Reward modulates visual responses in the superficial superior colliculus of mice","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.10.24.513513","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.10.24.513513","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.2139/ssrn.3631971","name":"Diversifying Equity with Cryptocurrencies during COVID-19","source":"preprints","abstract":"","url":"https://doi.org/10.2139/ssrn.3631971","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2020","doi":"10.2139/ssrn.3631971","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.21203/rs.3.rs-1824344/v2","name":"Neuronal growth on high-aspect-ratio diamond nanopillar arrays for biosensing applications","source":"preprints","abstract":"Abstract Monitoring neuronal activity with simultaneously high spatial and temporal resolution in living cell cultures is crucial to advance understanding of the development and functioning of our brain, and to gain further insights in the origin of brain disorders. While it has been demonstrated that the quantum sensing capabilities of nitrogen-vacancy (NV) centers in diamond allow real time detection of action potentials from large neurons in marine invertebrates, quantum monitoring of mammalian neurons (presenting much smaller dimensions and thus producing much lower signal and requiring higher spatial resolution) has hitherto remained elusive. In this context, diamond nanostructuring can offer the opportunity to boost the diamond platform sensitivity to the required level. However, a comprehensive analysis of the impact of a nanostructured diamond surface on the neuronal viability and growth was lacking. Here, we pattern a single crystal diamond surface with large-scale nanopillar arrays and we successfully demonstrate growth of a network of living and functional primary mouse hippocampal neurons on it. Our study on geometrical parameters reveals preferential growth along the nanopillar grid axes with excellent physical contact between cell membrane and nanopillar apex. Our results suggest that neuron growth can be tailored on diamond nanopillars to realize a nanophotonic quantum sensing platform for wide-field and label-free neuronal activity recording with sub-cellular resolution.","url":"https://doi.org/10.21203/rs.3.rs-1824344/v2","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-1824344/v2","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2024.12.13.628340","name":"Perinatal serotonin signalling dynamically influences the development of cortical GABAergic circuits with consequences for lifelong sensory encoding","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.12.13.628340","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.12.13.628340","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2020.11.25.398081","name":"A Synergistic Workspace for Human Consciousness Revealed by Integrated Information Decomposition","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2020.11.25.398081","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2020","doi":"10.1101/2020.11.25.398081","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.22541/au.169261941.10272122/v1","name":"Rapid and timely virus detection by optical technologies: prospects for future viruses’ prevalence","source":"preprints","abstract":"","url":"https://doi.org/10.22541/au.169261941.10272122/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.22541/au.169261941.10272122/v1","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2022.03.14.484357","name":"Reciprocal feature encoding by cortical excitatory and inhibitory neurons","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.03.14.484357","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.03.14.484357","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2023.09.13.23295505","name":"Structural Variation Detection and Association Analysis of Whole-Genome-Sequence Data from 16,905 Alzheimer’s Diseases Sequencing Project Subjects","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.09.13.23295505","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.09.13.23295505","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2022.04.04.487061","name":"The theta paradox: 4-8 Hz EEG oscillations reflect both local sleep and cognitive control","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.04.04.487061","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.04.04.487061","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2020.07.08.20148999","name":"Artificial Intelligence-Assisted Loop Mediated Isothermal Amplification (ai-LAMP) for Rapid and Reliable Detection of SARS-CoV-2","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2020.07.08.20148999","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2020","doi":"10.1101/2020.07.08.20148999","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2021.07.01.450507","name":"Behaviourally modulated hippocampal theta oscillations in the ferret persist during both locomotion and immobility","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2021.07.01.450507","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.1101/2021.07.01.450507","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2021.05.23.445338","name":"Visuomotor association orthogonalizes visual cortical population codes","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2021.05.23.445338","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.1101/2021.05.23.445338","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.1101/2020.06.15.20131870","name":"A Digital Protein Microarray for COVID-19 Cytokine Storm Monitoring","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2020.06.15.20131870","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2020","doi":"10.1101/2020.06.15.20131870","addedAt":"2026-09-01T01:48:27.323Z","updatedAt":"2026-09-01T01:48:28.365Z"},{"id":"doi:10.4018/978-1-5225-2375-8","name":"Bio-Inspired Computing for Information Retrieval Applications","source":"crossref","abstract":"","url":"https://doi.org/10.4018/978-1-5225-2375-8","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-02-07T17:05:08Z","doi":"10.4018/978-1-5225-2375-8","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/978-981-15-5097-3","name":"Applications of Bat Algorithm and its Variants","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-15-5097-3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-09T10:03:15Z","doi":"10.1007/978-981-15-5097-3","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/s00521-003-0395-7","name":"An information-theoretic landscape analysis of neuro-controlled embodied organisms","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-003-0395-7","authors":["Jason Teo","Hussein A. Abbass"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2004-04-20T07:31:51Z","doi":"10.1007/s00521-003-0395-7","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/nabic.2010.5716314","name":"Perception-based approach in recognition of structured patterns","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2010.5716314","authors":["Tuan Trung Nguyen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-02-18T14:03:54Z","doi":"10.1109/nabic.2010.5716314","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1177/0036850419850394","name":"Biologically-Inspired Neuromorphic Computing","source":"crossref","abstract":"Advances in integrated circuitry from the 1950s to the present day have enabled a revolution in technology across the world. However, fundamental limits of circuitry make further improvements through historically successful methods increasingly challenging. It is becoming clear that to address new challenges and applications, new methods of computation will be required. One promising field is neuromorphic engineering, a broad field which applies biologically inspired principles to create alternative computational architectures and methods. We address why neuromorphic engineering is one of the most promising fields within emerging computational technology, elaborating on its common principles and models, and discussing its current state and future challenges.","url":"https://doi.org/10.1177/0036850419850394","authors":["Wilkie Olin-Ammentorp","Nathaniel Cady"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-15T00:54:20Z","doi":"10.1177/0036850419850394","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.67228/30715628/ijmiet-2020pii1x8q","name":"Emerging Trends in Bio-Inspired Computing Models","source":"crossref","abstract":"Bio-inspired computing models are computational approaches inspired by biological systems such as evolution, neural processing, swarm behavior, immune systems, and cellular communication. They are widely used for optimization, learning, adaptation, and control in complex environments. Recent advances in AI, edge computing, healthcare, smart cities, and autonomous systems have increased interest in these models due to their adaptability, robustness, and energy efficiency. Current research focuses on evolutionary computing, swarm intelligence, neural and spiking neural networks, immune-inspired computing, and hybrid approaches that combine multiple biological principles. Emerging technologies such as neuromorphic computing, memristive hardware, and analog in-memory computing further support low-power intelligent systems. This work presents a unified framework based on biological mechanisms, computational objectives, deployment contexts, and performance constraints, demonstrating its application in edge-IoT anomaly detection and resource management. Overall, bio-inspired computing is emerging as a practical and effective paradigm for developing adaptive, distributed, and energy-efficient intelligent systems.","url":"https://doi.org/10.67228/30715628/ijmiet-2020pii1x8q","authors":["Rajesh Kumar Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-26T06:22:26Z","doi":"10.67228/30715628/ijmiet-2020pii1x8q","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.4018/978-1-5225-0788-8.ch023","name":"Genetic Algorithms for Small Enterprises Default Prediction","source":"crossref","abstract":"Company default prediction is a widely studied topic as it has a significant impact on banks and firms. Moreover, nowadays, due to the global financial crisis, there is a need to use even more advanced methods (such as soft computing techniques) which can pick up the signs of financial distress on time to evaluate firms (especially small firms). Thus, the author proposes a Genetic Algorithms (GA) approach (a soft computing technique) and shows how GAs can contribute to small enterprise default prediction modeling. The author applied GAs to a sample of 6,200 Italian small enterprises three years and also one year prior to bankruptcy. Subsequently, a multiple discriminant analysis and a logistic regression (the two main traditional techniques in default prediction modeling) were used to benchmarking GAs. The author's results show that the best prediction results were obtained when using GAs.","url":"https://doi.org/10.4018/978-1-5225-0788-8.ch023","authors":["Niccolò Gordini"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-07-26T12:16:44Z","doi":"10.4018/978-1-5225-0788-8.ch023","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/978-0-387-09655-1_20","name":"A Model of Self-Organizing Collaboration","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-0-387-09655-1_20","authors":["Rumen Andreev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-08-19T13:40:02Z","doi":"10.1007/978-0-387-09655-1_20","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/synasc.2006.78","name":"Tuning Evolutionary Algorithm Performance Using Nature Inspired Heuristics","source":"crossref","abstract":"","url":"https://doi.org/10.1109/synasc.2006.78","authors":["Ajith Abraham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-02-28T17:23:42Z","doi":"10.1109/synasc.2006.78","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1088/1361-6463/ad7a82/v5/response1","name":"Author response for \"Brain-inspired computing with self-assembled networks of nano-objects\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1361-6463/ad7a82/v5/response1","authors":["Vahl, Alexander","Milano, Gianluca","Kuncic, Zdenka","Brown, Simon A.","Milani, Paolo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-19T17:52:56Z","doi":"10.1088/1361-6463/ad7a82/v5/response1","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/978-3-319-50862-7_8","name":"Bio-Inspired Filters for Audio Analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-50862-7_8","authors":["Nicola Strisciuglio","Mario Vento","Nicolai Petkov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-12-10T14:24:23Z","doi":"10.1007/978-3-319-50862-7_8","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1002/9781394336449.ch9","name":"Security and Privacy Aspects in Quantum‐Inspired Soft Computing for Intelligent Data Processing","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9781394336449.ch9","authors":["Kuldeep Singh Kaswan","Jagjit Singh Dhatterwal","Kiran Malik","Naresh Kumar","S. S. Sridhar","S. Babeetha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-09T21:18:51Z","doi":"10.1002/9781394336449.ch9","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1016/j.pmcj.2014.08.007","name":"Special Issue on “The Social Car: Socially-inspired Mechanisms for Future Mobility Services”","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.pmcj.2014.08.007","authors":["Andreas Riener","Myounghoon Jeon","Ignacio Alvarez","Franco Zambonelli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-09-11T06:51:56Z","doi":"10.1016/j.pmcj.2014.08.007","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1016/j.asoc.2010.05.011","name":"ARO: A new model-free optimization algorithm inspired from asexual reproduction","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2010.05.011","authors":["Alireza Farasat","Mohammad B. Menhaj","Taha Mansouri","Mohammad Reza Sadeghi Moghadam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-05-21T08:46:06Z","doi":"10.1016/j.asoc.2010.05.011","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1016/j.asoc.2017.07.007","name":"Implementation of neuro-fuzzy system with modified high performance genetic algorithm on embedded systems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2017.07.007","authors":["Ali Nasrollahzadeh","Ghader Karimian","Amir Mehrafsa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-07-14T19:31:11Z","doi":"10.1016/j.asoc.2017.07.007","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/nabic.2009.5393781","name":"Unit commitment by Genetic Evolving Ant Colony Optimization","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393781","authors":["K. Vaisakh","L.R. Srinivas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5393781","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:27.541Z"},{"id":"doi:10.1109/nabic.2009.5395597","name":"Intelligent system for Arabic character recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5395597","authors":["M. Albakoor","K. Saeed","F. Sukkar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5395597","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:27.541Z"},{"id":"doi:10.1109/nabic.2009.5393635","name":"Review on Ant Miners","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393635","authors":["V.K. Panchal","Poonam Singh","Appoorv Narula","Ashutosh Mishra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5393635","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:27.541Z"},{"id":"doi:10.1109/nabic.2010.5716341","name":"A bio-inspired computational high-precision dental milling system","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2010.5716341","authors":["V Vera","A E Garcia","M J Suarez","B Hernando","E Corchado","M A Sanchez","A Gil","Raquel Redondo","Javier Sedano"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-02-18T19:03:54Z","doi":"10.1109/nabic.2010.5716341","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/978-3-030-16681-6_44","name":"Contouring the Behavioral Patterns of the Users of Social Network(ing) Sites and the Need for Data Privacy Law in India: An Application of SEM-PLS Technique","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-16681-6_44","authors":["Sandeep Mittal","Priyanka Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-22T17:26:26Z","doi":"10.1007/978-3-030-16681-6_44","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:27.541Z"},{"id":"doi:10.1007/978-3-031-78943-4_37","name":"Technological Augmentation of Cloud Computing Depending on the Difficulties and Challenges in Service Modules and Service Providers","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78943-4_37","authors":["K. Srinu","R. Saikrishna","B. Sree Saranya","Sayyad Rasheeduddin","Maddela Parmeswar","L. Chandra Sekhar Reddy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-03T11:08:29Z","doi":"10.1007/978-3-031-78943-4_37","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:27.541Z"},{"id":"doi:10.1007/3-540-32392-9_33","name":"Nature-Inspired Algorithms for the TSP","source":"crossref","abstract":"","url":"https://doi.org/10.1007/3-540-32392-9_33","authors":["Jarosław Skaruz","Franciszek Seredyński","Michał Gamus"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-05-27T07:09:20Z","doi":"10.1007/3-540-32392-9_33","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/icmcs.2014.6911328","name":"Multi-band metamaterial-inspired half-loop antenna","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icmcs.2014.6911328","authors":["Esthelladi Ramanandraibe","Mohamed Latrach","Ala Sharaiha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-10-08T20:49:12Z","doi":"10.1109/icmcs.2014.6911328","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.4018/978-1-5225-0788-8.ch058","name":"From Optimization to Clustering","source":"crossref","abstract":"In the past two decades, Swarm Intelligence (SI)-based optimization techniques have drawn the attention of many researchers for finding an efficient solution to optimization problems. Swarm intelligence techniques are characterized by their decentralized way of working that mimics the behavior of colony of ants, swarm of bees, flock of birds, or school of fishes. Algorithmic simplicity and effectiveness of swarm intelligence techniques have made it a powerful tool for solving global optimization problems. Simulation studies of the graceful, but unpredictable, choreography of bird flocks led to the design of the particle swarm optimization algorithm. Studies of the foraging behavior of ants resulted in the development of ant colony optimization algorithm. This chapter provides insight into swarm intelligence techniques, specifically particle swarm optimization and its variants. The objective of this chapter is twofold: First, it describes how swarm intelligence techniques are employed to solve various optimization problems. Second, it describes how swarm intelligence techniques are efficiently applied for clustering, by imposing clustering as an optimization problem.","url":"https://doi.org/10.4018/978-1-5225-0788-8.ch058","authors":["Megha Vora","T. T. Mirnalinee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-07-26T12:16:44Z","doi":"10.4018/978-1-5225-0788-8.ch058","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/iadcc.2009.4809073","name":"Class-specific codebook construction for biologically inspired recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iadcc.2009.4809073","authors":["Jun Gao","Changxin Gao","Nong Sang","Qiling Tang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-03-31T14:37:00Z","doi":"10.1109/iadcc.2009.4809073","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1145/1125451.1125498","name":"Mobile blogging","source":"crossref","abstract":"","url":"https://doi.org/10.1145/1125451.1125498","authors":["Russell Beale"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-05-08T21:40:43Z","doi":"10.1145/1125451.1125498","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/nabic.2009.5393749","name":"Forecasting stock market indices using hybrid network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393749","authors":["S. Chakravarty","P. K. Dash"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393749","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1038/s41586-021-04362-w","name":"Brain-inspired computing needs a master plan","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s41586-021-04362-w","authors":["A. Mehonic","A. J. Kenyon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-13T12:06:04Z","doi":"10.1038/s41586-021-04362-w","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1007/978-3-319-26293-2_5","name":"Two-Factors High-Order Neuro-Fuzzy Forecasting Model","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-26293-2_5","authors":["Pritpal Singh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-11-21T10:03:56Z","doi":"10.1007/978-3-319-26293-2_5","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1016/j.asoc.2026.115903","name":"Synaptic style weaver: A closed-loop multi-agent neuro-symbolic system for secure and hardware-agnostic academic text humanization","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2026.115903","authors":["Rachid Djerbi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-08T16:48:19Z","doi":"10.1016/j.asoc.2026.115903","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1109/nabic.2009.5393473","name":"A novel methodology for indoor positioning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393473","authors":["Md. Ahsan Habib","Tasbirun Nahian Upal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5393473","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1109/nabic.2009.5393446","name":"Evolutionary approach to produce classifier ensemble based on weighted voting","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393446","authors":["Michal Wozniak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5393446","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1016/b978-0-08-102782-0.00009-5","name":"Vector multiplications using memristive devices and applications thereof","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-08-102782-0.00009-5","authors":["Mohammed A. Zidan","Wei D. Lu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-26T05:27:39Z","doi":"10.1016/b978-0-08-102782-0.00009-5","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1109/scm.2017.7970526","name":"Cluster analysis problems and bio-inspired clustering methods","source":"crossref","abstract":"","url":"https://doi.org/10.1109/scm.2017.7970526","authors":["E. N. Benderskaya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-07-07T18:36:11Z","doi":"10.1109/scm.2017.7970526","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1016/j.asoc.2010.04.020","name":"Machine scheduling in custom furniture industry through neuro-evolutionary hybridization","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2010.04.020","authors":["Juan C. Vidal","Manuel Mucientes","Alberto Bugarín","Manuel Lama"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-05-10T02:19:54Z","doi":"10.1016/j.asoc.2010.04.020","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1016/j.asoc.2012.03.019","name":"Estimation of heart rate signals for mental stress assessment using neuro fuzzy technique","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2012.03.019","authors":["G. Ranganathan","R. Rangarajan","V. Bindhu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-03-16T15:47:32Z","doi":"10.1016/j.asoc.2012.03.019","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1007/978-3-319-47054-2_37","name":"Neuro-Fuzzy Hybrid Model for the Diagnosis of Blood Pressure","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-47054-2_37","authors":["Juan Carlos Guzmán","Patricia Melin","German Prado-Arechiga"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-12-09T04:14:00Z","doi":"10.1007/978-3-319-47054-2_37","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1007/978-981-19-6379-7_5","name":"Potential Role of the Nature-Inspired Algorithms for Classification of High-Dimensional and Complex Gene Expression Data","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-19-6379-7_5","authors":["Sahar Qazi","Ayesha Khanam","Khalid Raza"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-31T17:04:10Z","doi":"10.1007/978-981-19-6379-7_5","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1007/978-3-030-90708-2_7","name":"A Nature-Inspired DNA Encoding Technique for Quantum Session Key Exchange Protocol","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-90708-2_7","authors":["Partha Sarathi Goswami","Tamal Chakraborty","Abir Chattopadhyay"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-26T11:04:51Z","doi":"10.1007/978-3-030-90708-2_7","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1007/978-3-7908-1902-1_81","name":"An ε-insensitive Learning in Neuro-Fuzzy Modeling","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-7908-1902-1_81","authors":["Jacek Łęski","Norbert Henzel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-03-11T00:11:40Z","doi":"10.1007/978-3-7908-1902-1_81","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1109/icet.2007.4516333","name":"Neuro-Fuzzy Hybrid Intelligent System Using Grid Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icet.2007.4516333","authors":["Laeeq Ahmed","Syed Adeel Ali Shah"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-05-15T14:52:37Z","doi":"10.1109/icet.2007.4516333","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.56536/jicet.v6i1.252","name":"K-NN based Predictive Framework Using Nature-Inspired Feature Selection","source":"crossref","abstract":"Metaheuristic algorithms have attracted considerable interest in data science because they can effectively handle high-dimensional data and optimize feature selection. In the present study, several nature-inspired metaheuristic algorithms combined with a K-Nearest Neighbors (K-NN) classifier are explored for lung cancer classification. The algorithms used for evaluation are Particle Swarm Optimization (PSO), Genetic Algorithm (GA), Firefly Algorithm (FA), Whale Optimization Algorithm (WOA), Harris Hawk Optimization (HHO), Bat Algorithm (BA), Flower Pollination Algorithm (FPA), Grey Wolf Optimizer (GWO), Salp Swarm Algorithm (SSA), Cuckoo Search Algorithm (CSA) and Differential Evolution (DE). The performance of these methods is assessed using feature subset size, accuracy, precision, recall, and F1-score. The experimental result shows that the highest accuracy of 98.19% is obtained for the classification by using 9 selected features for the method BA, while the methods PSO, GA, FA, GWO, and DE also give good accuracy of 98.18% with the same number of features 9. The other methods, such as WOA, HHO, FPA, SSA, and CSA, achieved lower accuracies of about 97.28%, respectively. Furthermore, the minimum number of features selected by both WOA and CSA was 5, indicating that they were not significantly affected by the decrease in classification performance at their selected minimum feature counts. The acquired outcomes illustrate the impact of utilizing feature selection approaches grounded in metaheuristic methods for lung cancer prediction and provide useful insights for future enhancements and hybrid optimization methods.","url":"https://doi.org/10.56536/jicet.v6i1.252","authors":["Shazia Javed"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-21T07:11:02Z","doi":"10.56536/jicet.v6i1.252","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1201/b10781-9","name":"Self-Organizing Data and Signal Cellular Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1201/b10781-9","authors":["André Stauffer","Gianluca Tempesti"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-04-13T21:41:46Z","doi":"10.1201/b10781-9","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1109/nabic.2009.5393350","name":"A simple adaptive Differential Evolution algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393350","authors":["Radha Thangaraj","Millie Pant","Ajith Abraham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393350","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch009","name":"A Dynamic Agent-Based Model of Corruption","source":"crossref","abstract":"The author builds an agent-based model wherein the societal corruption level is derived from individual corruption levels optimally chosen by heterogeneous agents with different risk aversion and human capital. The societal corruption level, in turn, affects the risk-return profile of corruption for the individual agents. Simulating a multi-generational economy with heterogeneous agents, the author shows that there are locally stable equilibrium corruption levels with certain socio-economic determinants. However, there are situations when corruption can rise until it stifles all economic activity. “You live in a society where everybody steals. Do you choose to steal? The probability that you will be caught is low ... and, even if you are caught, the chances of your being punished severely for a crime so common are low. Therefore you too steal. By contrast, if you live in a society where theft is rare, the chances of your being caught and punished are high, so you choose not to steal.” (Mauro, 1998, p. 12)","url":"https://doi.org/10.4018/978-1-59140-984-7.ch009","authors":["R. Chakrabarti"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch009","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1109/icgccee.2014.6922463","name":"A bio inspired Energy-Aware Multi objective Chiropteran Algorithm (EAMOCA) for hybrid cloud computing environment","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icgccee.2014.6922463","authors":["R Raju","J Amudhavel","Nevedha Kannan","M Monisha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-10-22T16:12:16Z","doi":"10.1109/icgccee.2014.6922463","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1007/978-3-319-28031-8_32","name":"Delay Scheduling with Reduced Workload on JobTracker in Hadoop","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-28031-8_32","authors":["Krishan Kumar Sethi","Dharavath Ramesh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-13T20:02:33Z","doi":"10.1007/978-3-319-28031-8_32","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1007/978-3-319-76354-5_32","name":"Weighted Access Control Policies Cohabitation in Distributed Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-76354-5_32","authors":["Asmaa El Kandoussi","Hanan El Bakkali"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-09T11:43:48Z","doi":"10.1007/978-3-319-76354-5_32","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1109/clustr.2005.347083","name":"A Biologically-inspired Adaptation Mechanism for Autonomic Grid Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/clustr.2005.347083","authors":["Chonho Lee","Paskorn Champrasert","Junichi Suzuki"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-04-24T20:05:29Z","doi":"10.1109/clustr.2005.347083","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1109/bicta.2007.4806420","name":"Subspace Index Method for 3D Human Motion","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2007.4806420","authors":["Jian Xiang","Hongli Zhu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-03-30T15:03:08Z","doi":"10.1109/bicta.2007.4806420","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1063/5.0209417","name":"A novel dynamic image watermarking technique with features inspired by quantum computing principles","source":"crossref","abstract":"This research proposes a novel dynamic image watermarking technique with features inspired by quantum computing principles. This method encodes binary values into qubits and embeds a watermark into an original image. The watermarking process is achieved by utilizing quantum circuits to manipulate the qubits representing the pixel values of the original and watermark images. To extract the watermark, encode each pixel value into a qubit, combine them using quantum operations, and then measure the resultant quantum state. This technique ensures the integrity and authenticity of the image by embedding a watermark that can be extracted with high fidelity. Simulation results show that our technique successfully embeds watermarks while maintaining picture quality. Moreover, this method exhibits robustness against common image processing attacks, highlighting its potential for secure image verification applications.","url":"https://doi.org/10.1063/5.0209417","authors":["Ramesh Gorle","Anitha Guttavelli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-15T11:22:14Z","doi":"10.1063/5.0209417","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1007/978-3-642-58930-0_9","name":"Intelligent Fuzzy System Modeling","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-58930-0_9","authors":["I. Burhan Türkşen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-06-15T23:06:59Z","doi":"10.1007/978-3-642-58930-0_9","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1016/j.jpdc.2019.08.009","name":"CLASSIC: A cortex-inspired hardware accelerator","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.jpdc.2019.08.009","authors":["Valentin Puente","José Ángel Gregorio"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-09-05T11:58:18Z","doi":"10.1016/j.jpdc.2019.08.009","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1007/978-981-16-9573-5_27","name":"An IoT-Based Intelligent Air Quality Monitoring System","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-16-9573-5_27","authors":["K. R. Chetan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-30T06:02:42Z","doi":"10.1007/978-981-16-9573-5_27","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1007/978-3-319-27400-3_11","name":"Modeling Insurance Fraud Detection Using Imbalanced Data Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-27400-3_11","authors":["Amira Kamil Ibrahim Hassan","Ajith Abraham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-01T17:08:38Z","doi":"10.1007/978-3-319-27400-3_11","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1109/bimnics.2007.4610129","name":"Highly adaptive cryptographic suites for autonomic WSNs","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bimnics.2007.4610129","authors":["Dennis Bliefernicht","Daniel Schreckling"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-09-08T16:06:46Z","doi":"10.1109/bimnics.2007.4610129","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1109/nabic.2009.5393603","name":"Gray-level Image Enhancement By Particle Swarm Optimization","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393603","authors":["Apurba Gorai","Ashish Ghosh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393603","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1109/bicta.2010.5645301","name":"Union-Intersection Ant System","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2010.5645301","authors":["Jinbiao Wang","Kaichi Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-12-09T10:33:18Z","doi":"10.1109/bicta.2010.5645301","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1007/978-3-319-96451-5_12","name":"A Computational Physics-Based Algorithm for Target Coverage Problems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-96451-5_12","authors":["Jordan Barry","Christopher Thron"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-08-29T22:31:42Z","doi":"10.1007/978-3-319-96451-5_12","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1007/978-3-030-37218-7_141","name":"Efficient Ranking Framework for Information Retrieval Using Similarity Measure","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_141","authors":["Shadab Irfan","Subhajit Ghosh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T15:02:40Z","doi":"10.1007/978-3-030-37218-7_141","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.5220/0013266200004646","name":"A UWB-Specific Metasurface-Inspired MIMO Antenna with Enhanced Isolation and Gain","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0013266200004646","authors":["Tejaswita Kumari","Anupama Senapati","Abu Nasar Ghazali"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-06T21:58:21Z","doi":"10.5220/0013266200004646","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1007/978-981-33-6773-9_18","name":"Optimal Allocation of Flexible Alternative Current Transmission Systems: An Application of Particle Swarm Optimization","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-33-6773-9_18","authors":["Akiko Takahashi","Hirotaka Takano","Shigeyuki Funabiki"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-31T12:03:02Z","doi":"10.1007/978-981-33-6773-9_18","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1016/j.jpdc.2009.05.004","name":"An adaptive overlay network inspired by social behaviour","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.jpdc.2009.05.004","authors":["Vincenza Carchiolo","Michele Malgeri","Giuseppe Mangioni","Vincenzo Nicosia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-06-11T05:37:03Z","doi":"10.1016/j.jpdc.2009.05.004","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1007/978-3-030-37218-7_27","name":"Association Rule Data Mining in Agriculture – A Review","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_27","authors":["N. Vignesh","D. C. Vinutha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T15:02:40Z","doi":"10.1007/978-3-030-37218-7_27","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:27.541Z"},{"id":"doi:10.1016/j.asoc.2019.105595","name":"A modified neuro-fuzzy classifier and its parallel implementation on modern GPUs for real time intrusion detection","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2019.105595","authors":["Nilam Upasani","Hari Om"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-06-26T12:12:58Z","doi":"10.1016/j.asoc.2019.105595","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1007/978-3-030-49339-4_22","name":"Design and Development of a Mobile App as a Learning Strategy in Engineering Education","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-49339-4_22","authors":["Yara C. Almanza-Arjona","Leonel A. Miranda-Camargo","Salvador E. Venegas-Andraca","Beatriz E. García-Rivera"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-05T11:05:14Z","doi":"10.1007/978-3-030-49339-4_22","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1007/978-3-030-37218-7_145","name":"Effective Spam Image Classification Using CNN and Transfer Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_145","authors":["Shrihari Rao","Radhakrishan Gopalapillai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T20:02:40Z","doi":"10.1007/978-3-030-37218-7_145","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.7567/ssdm.1990.s-b-8","name":"Devices for Optical Neuro Computing","source":"crossref","abstract":"","url":"https://doi.org/10.7567/ssdm.1990.s-b-8","authors":["Kazuo KYUMA","Jun OHTA"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-11-06T07:02:00Z","doi":"10.7567/ssdm.1990.s-b-8","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.5815/ijieeb.2026.02.07","name":"Sustainable and Fair Task Scheduling in Cloud Computing Using Hybrid Bio-Inspired Algorithms for Green Computing","source":"crossref","abstract":"Despite cloud computing's scalability and economy, energy efficiency, security, and equitable scheduling remain significant concerns. The traditional scheduling approach often fails to optimize execution time, energy consumption, and security concerns, resulting in less resource utilization and less secure systems. This paper proposes the Hybrid Bat-Genetic Algorithm (HBA-GA), which combines the Bat Algorithm for fast exploration with the Genetic Algorithm for accurate exploitation. This method reduces energy use while also reducing security risks like unauthorized access and data leaks. It uses Jain's Fairness Index (JFI) in order to ensure that workloads are evenly distributed and VM overload and conflicts are avoided. Based on simulations results, proposed HBA-GA improves energy efficiency while reducing security exposure and risk likelihood at the scheduling level by incorporating security-aware risk scoring into task–VM allocation decisions.","url":"https://doi.org/10.5815/ijieeb.2026.02.07","authors":["Garima Verma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-03T16:10:13Z","doi":"10.5815/ijieeb.2026.02.07","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1287/ijoc.2022.1253","name":"Large-Scale Inventory Optimization: A Recurrent Neural Networks–Inspired Simulation Approach","source":"crossref","abstract":"Many large-scale production networks include thousands of types of final products and tens to hundreds of thousands of types of raw materials and intermediate products. These networks face complicated inventory management decisions, which are often too complicated for inventory models and too large for simulation models. In this paper, by combining efficient computational tools of recurrent neural networks (RNNs) and the structural information of production networks, we propose an RNN-inspired simulation approach that may be thousands of times faster than the existing simulation approach and is capable of solving large-scale inventory optimization problems in a reasonable amount of time. History: Accepted by Bruno Tuffin, Area Editor for Simulation. Funding: This work was supported by the National Natural Science Foundation of China [Grant 72091211].","url":"https://doi.org/10.1287/ijoc.2022.1253","authors":["Tan Wang","L. Jeff Hong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-06T15:13:29Z","doi":"10.1287/ijoc.2022.1253","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1109/nice65350.2025.11065119","name":"Efficient Deployment of Spiking Neural Networks on SpiNNaker2 for DVS Gesture Recognition Using Neuromorphic Intermediate Representation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nice65350.2025.11065119","authors":["Sirine Arfa","Bernhard Vogginger","Chen Liu","Johannes Partzsch","Mark Schöne","Christian Mayr"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-08T13:36:20Z","doi":"10.1109/nice65350.2025.11065119","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1201/9781315153797-10","name":"Evolutionary Algorithms for the Efficient Design of Multiplier-Less Image Filter","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781315153797-10","authors":["Abhijit Chandra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-19T10:43:32Z","doi":"10.1201/9781315153797-10","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1201/9781003143499-15","name":"Introduction to neuromorphic programming","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003143499-15","authors":["Elishai Ezra Tsur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-07-19T12:30:34Z","doi":"10.1201/9781003143499-15","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1007/978-3-540-77657-4_13","name":"Bio-Inspired Networking — Self-Organizing Networked Embedded Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-540-77657-4_13","authors":["Falko Dressler"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-10-10T14:38:11Z","doi":"10.1007/978-3-540-77657-4_13","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1201/9781003248545-6","name":"Organic Computing in Cyber-Physical Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003248545-6","authors":["K Ezhilarasan","A Jeevarekha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-23T20:32:32Z","doi":"10.1201/9781003248545-6","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1201/b17333-15","name":"Nature-Inspired Intelligence: A Modern Tool for Warfare Strategic Decision Making ..................................................................................................................... LAVIKA GOEL","source":"crossref","abstract":"","url":"https://doi.org/10.1201/b17333-15","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-08-07T18:27:38Z","doi":"10.1201/b17333-15","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1109/bimnics.2006.361817","name":"Digital Ecosystems: Evolving Service-Orientated Architectures","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bimnics.2006.361817","authors":["Gerard Briscoe","Philippe de Wilde"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-06-07T19:56:37Z","doi":"10.1109/bimnics.2006.361817","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1007/s11047-009-9123-2","name":"Nature-inspired learning and adaptive systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11047-009-9123-2","authors":["Bogdan Gabrys","Davide Anguita"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-02-10T07:33:56Z","doi":"10.1007/s11047-009-9123-2","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1016/b978-0-08-102782-0.00018-6","name":"System-level integration in neuromorphic co-processors","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-08-102782-0.00018-6","authors":["Giacomo Indiveri","Bernabé Linares-Barranco","Melika Payvand"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-26T05:28:47Z","doi":"10.1016/b978-0-08-102782-0.00018-6","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.4018/978-1-5225-0788-8.ch007","name":"Artificial Neural Network and Its Application in Steel Industry","source":"crossref","abstract":"The recent developments in computational intelligence has enhances the applicability of empirical modelling in different areas particularly in the area of machine learning. These new approaches are based on analysing the data about a system, in particular finding connections between the system state variables (input, internal and output variables) without having precise knowledge about the physical behaviour of the system. These data driven methods explain advances on conventional empirical modelling and include contributions from many overlapping fields like Artificial Intelligence (AI), Computational Intelligence (CI), Soft Computing (SC), Machine Learning (ML), Intelligent Data Analysis (IDA), and Data Mining (DM). The most popular computational intelligence techniques used in process modelling of steel industry includes neural networks, fuzzy rule-based systems, genetic algorithms as well as approaches to model integration. This chapter describes mainly the application of Artificial Neural Network (ANN) in steel industry. ANN has extensively used in improving and controlling different processes of steel industry like steel making, casting and rolling which lead to indirect energy savings through reduced product rejects, improved productivity and reduced down time. The efficiency of artificial neural network tool in handling steel plant processes has been discussed in detail. ANN based models are found to be very potential to handle very complex, dynamic and non-linear problems.","url":"https://doi.org/10.4018/978-1-5225-0788-8.ch007","authors":["Itishree Mohanty","Dabashish Bhattacherjee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-07-26T12:16:44Z","doi":"10.4018/978-1-5225-0788-8.ch007","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1016/j.pmcj.2024.101999","name":"Blockchain-Inspired Trust Management in Cognitive Radio Networks with Cooperative Spectrum Sensing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.pmcj.2024.101999","authors":["Mahsa Mahvash","Neda Moghim","Mojtaba Mahdavi","Mahdieh Amiri","Sachin Shetty"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-20T08:17:11Z","doi":"10.1016/j.pmcj.2024.101999","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1007/978-3-319-26293-2_4","name":"High-Order Fuzzy-Neuro Time Series Forecasting Model","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-26293-2_4","authors":["Pritpal Singh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-11-21T10:03:56Z","doi":"10.1007/978-3-319-26293-2_4","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1007/978-3-319-27400-3_30","name":"A Generative Hyper-Heuristic for Deriving Heuristics for Classical Artificial Intelligence Problems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-27400-3_30","authors":["Nelishia Pillay"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-01T17:08:38Z","doi":"10.1007/978-3-319-27400-3_30","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1260/1478-0771.10.4.613","name":"Computational Design of a Bio Inspired Responsive Architectural Façade System","source":"crossref","abstract":"This research intends to illustrate a nonlinear relationship that could be drawn between the fundamental processes in living systems and architectural design of responsive surface. The research focuses on deriving a set of parametric relationships from the phenomenon in cell biology and generating an architectural expression of a responsive façade system. The research methods primarily investigates the cell – to – cell connection in mammary epithelial cell system and review the evident relay of communication across the entire system of cells. This thorough investigation unfolds the logical parameters of the biological system that delineates the dynamic feedback mechanism and changes in the cell surface conditions initiated from the changes in the extracellular environment (ECM). The research findings of this complex mechanism are further translated though parametric modeling tool (in this case Generative Components) to model the causalities of the changes in cell environment and surface condition changes. In the next phase of our research we have explored the architectural utility of this hybridized model operating in a user defined controlled environ, and not just a mere response to biological stimulus.","url":"https://doi.org/10.1260/1478-0771.10.4.613","authors":["Florina Dutt","Subhajit Das"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-12-24T21:06:26Z","doi":"10.1260/1478-0771.10.4.613","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1007/978-981-33-6862-0_43","name":"Low-Dose Imaging: Prediction of Projections in Sinogram Space","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-33-6862-0_43","authors":["Bhagya Sunag","Shrinivas Desai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-06-14T05:02:45Z","doi":"10.1007/978-981-33-6862-0_43","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1007/s00500-017-2800-7","name":"An interpretable neuro-fuzzy approach to stock price forecasting","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00500-017-2800-7","authors":["Sharifa Rajab","Vinod Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-09-01T05:29:05Z","doi":"10.1007/s00500-017-2800-7","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1007/978-0-387-89828-5_6","name":"Bio-inspired Cognitive Radio for Dynamic Spectrum Access","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-0-387-89828-5_6","authors":["Giacomo Oliveri","Marina Ottonello","Carlo S. Regazzoni"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-05-13T03:33:42Z","doi":"10.1007/978-0-387-89828-5_6","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1109/icma.2014.6885756","name":"Computing optical flow from bio-inspired spherical retina","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icma.2014.6885756","authors":["Shigang Li","Hanchao Jia","Isao Nakanishi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-09-03T10:13:10Z","doi":"10.1109/icma.2014.6885756","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1109/nabic.2009.5393857","name":"A three tier scheme for Devanagari hand-printed character recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393857","authors":["Satish Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393857","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1016/b978-0-08-102782-0.00015-0","name":"Memristive devices for spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-08-102782-0.00015-0","authors":["Bipin Rajendran","Damien Querlioz","Sabina Spiga","Abu Sebastian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-26T05:28:22Z","doi":"10.1016/b978-0-08-102782-0.00015-0","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.14236/ewic/isiict2009.17","name":"A Multi–Agent System for Image Segmentation A Bio-Inspired Approach","source":"crossref","abstract":"","url":"https://doi.org/10.14236/ewic/isiict2009.17","authors":["Safia Djemame","Mabrouk Nekkache","Mohammed Batouche"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-10-15T16:46:27Z","doi":"10.14236/ewic/isiict2009.17","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/s00500-013-1057-z","name":"Neuro-fuzzy system with weighted attributes","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00500-013-1057-z","authors":["Krzysztof Simiński"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-05-24T15:05:41Z","doi":"10.1007/s00500-013-1057-z","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1109/icoac.2013.6921956","name":"Adaptive neuro-fuzzy controller for vehicle suspension system","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icoac.2013.6921956","authors":["R Kalaivani","P. Lakshmi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-10-22T20:21:53Z","doi":"10.1109/icoac.2013.6921956","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1109/iwcmc.2019.8766745","name":"Real World Modeling and Design of Novel Simulator for Affective Computing Inspired Autonomous Vehicle","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iwcmc.2019.8766745","authors":["Muhammad Kabeer","Faisal Riaz","Sohail Jabbar","Moayad Aloqaily","Samia Abid"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-07-22T23:48:28Z","doi":"10.1109/iwcmc.2019.8766745","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1109/iscas.2010.5537268","name":"Live demonstration: Neuro-inspired system for realtime vision tilt correction","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas.2010.5537268","authors":["A. Jimenez-Fernandez","J. L. Fuentes-del-Bosh","R. Paz-Vicente","A. Linares-Barranco","G. Jimenez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-08-09T18:13:20Z","doi":"10.1109/iscas.2010.5537268","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-030-96993-6_47","name":"One Possibility of a Neuro-Symbolic Integration","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96993-6_47","authors":["Alexei V. Samsonovich"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-24T20:53:47Z","doi":"10.1007/978-3-030-96993-6_47","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1016/j.asoc.2020.106348","name":"A Quantum-Inspired Self-Supervised Network model for automatic segmentation of brain MR images","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2020.106348","authors":["Debanjan Konar","Siddhartha Bhattacharyya","Tapan Kr. Gandhi","Bijaya Ketan Panigrahi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-05-04T22:32:42Z","doi":"10.1016/j.asoc.2020.106348","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-030-37218-7_58","name":"Pancreatic Tumour Segmentation in Recent Medical Imaging – an Overview","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_58","authors":["A. Sindhu","V. Radha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T15:02:40Z","doi":"10.1007/978-3-030-37218-7_58","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1016/j.asoc.2014.06.023","name":"Parameter estimation for crop growth model using evolutionary and bio-inspired algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2014.06.023","authors":["Elmer César Trejo Zúñiga","Irineo Lorenzo López Cruz","Agustín Ruíz García"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-06-26T12:49:23Z","doi":"10.1016/j.asoc.2014.06.023","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1109/icmcs.2012.6320219","name":"An unsupervised fuzzy-neuro quantiser for image compression","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icmcs.2012.6320219","authors":["Mohammed Madiafi","Abdelaziz Bouroumi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-05-15T21:01:35Z","doi":"10.1109/icmcs.2012.6320219","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-78949-6_35","name":"Comprehensive Assessment on a Data Access Control Scheme, for Industrial Internet of Things (IOT) in Conjunction with Cloud Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78949-6_35","authors":["Madhavi Pingili","Bommireddy Prasanthi","K. Venkateswara Rao","Borra Sivaiah","Suraya Mubeen","K. Shilpa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T09:29:24Z","doi":"10.1007/978-3-031-78949-6_35","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1016/j.clinph.2023.03.080","name":"N°73 – Multiscale neuro-inspired models for interpretation of EEG signals in epilepsy patients","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.clinph.2023.03.080","authors":["Fabrice Wendling","Elif Köksal Ersöz","Mariam Al-Harrach","Giulio Ruffini","Fabrice Bartolomei","Pascal Benquet"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-16T01:38:47Z","doi":"10.1016/j.clinph.2023.03.080","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1145/3381755.3381781","name":"Cognitive Domain Ontologies","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3381755.3381781","authors":["Tarek M. Taha","Chris Yakopcic","Nayim Rahman","Tanvir Atahary","Scott Douglass"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-18T23:09:51Z","doi":"10.1145/3381755.3381781","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-030-37218-7_40","name":"Artificial Neural Network Hardware Implementation: Recent Trends and Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_40","authors":["Jagrati Gupta","Deepali Koppad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T20:02:40Z","doi":"10.1007/978-3-030-37218-7_40","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-78943-4_45","name":"Analysis on the Assessment of Clustering Algorithms for Mitigating Security Concerns in Cloud Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78943-4_45","authors":["Avala Raji Reddy","G. Menaka","R. Venkateswara Reddy","Maddela Parameswar","Rajesh Tiwari","Lal Bahadur Pandey"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-03T11:08:04Z","doi":"10.1007/978-3-031-78943-4_45","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-030-16681-6_28","name":"Generation of Hindi Word Embeddings and Their Utilization in Ranking Documents Using Negative Sampling Architecture, t-SNE Visualization and TF-IDF Based Weighted Average of Vectors","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-16681-6_28","authors":["Arya Prabhudesai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-22T21:26:26Z","doi":"10.1007/978-3-030-16681-6_28","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-030-37218-7_108","name":"Image Completion of Highly Noisy Images Using Deep Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_108","authors":["Piyush Agrawal","Sajal Kaushik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T15:02:40Z","doi":"10.1007/978-3-030-37218-7_108","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-322-81754-9_4","name":"Neuro-Fuzzy-Methoden in der Prüfung der Sanierungsfähigkeit","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-322-81754-9_4","authors":["Reinhard Bennert"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-12-26T11:51:45Z","doi":"10.1007/978-3-322-81754-9_4","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-030-49339-4_8","name":"Comparative Performance Exploration and Prediction of Fibrosis, Malign Lymph, Metastases, Normal Lymphogram Using Machine Learning Method","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-49339-4_8","authors":["Subrato Bharati","Md. Robiul Alam Robel","Mohammad Atikur Rahman","Prajoy Podder","Niketa Gandhi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-05T11:05:14Z","doi":"10.1007/978-3-030-49339-4_8","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-1-4613-0431-9","name":"Concurrent Learning and Information Processing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4613-0431-9","authors":["Robert J. Jannarone"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-08-25T18:43:55Z","doi":"10.1007/978-1-4613-0431-9","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-030-37218-7_74","name":"Review on Prevailing Difficulties Using IriS Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_74","authors":["C. D. Divya","A. B. Rajendra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T20:02:40Z","doi":"10.1007/978-3-030-37218-7_74","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:27.541Z"},{"id":"doi:10.1007/978-981-33-6862-0_12","name":"Transfer Learning Techniques for Skin Cancer Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-33-6862-0_12","authors":["Mirya Robin","Jisha John","Aswathy Ravikumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-06-14T05:02:45Z","doi":"10.1007/978-981-33-6862-0_12","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1016/j.asoc.2013.05.013","name":"Online bio-inspired trajectory generation of seven-link biped robot based on T–S fuzzy system","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2013.05.013","authors":["Yadollah Farzaneh","Alireza Akbarzadeh","Ali Akbar Akbari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-06-06T06:31:40Z","doi":"10.1016/j.asoc.2013.05.013","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1109/fuzzy.1997.622791","name":"Neuro-fuzzy and soft computing for speaker recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/fuzzy.1997.622791","authors":["J.-S.R. Jang","Jiuann-Jye Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-11-22T21:45:27Z","doi":"10.1109/fuzzy.1997.622791","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-319-27400-3_28","name":"Optimization of a Static VAR Compensation Parameters Using PBIL","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-27400-3_28","authors":["Dereck Dombo","Komla Agbenyo Folly"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-01T17:08:38Z","doi":"10.1007/978-3-319-27400-3_28","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-981-16-9573-5_11","name":"Solar Radio Spectrum Classification Based on ConvLSTM","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-16-9573-5_11","authors":["Ruru Cheng","Guowu Yuan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-30T06:02:42Z","doi":"10.1007/978-981-16-9573-5_11","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-981-10-6747-1_20","name":"Performance Evaluation of Neural Network Training Algorithms in Redirection Spam Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-10-6747-1_20","authors":["Kanchan Hans","Laxmi Ahuja","S. K. Muttoo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-10-04T08:25:22Z","doi":"10.1007/978-981-10-6747-1_20","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1145/1315843.1315861","name":"Organization-oriented chemical programming for the organic design of distributed computing systems","source":"crossref","abstract":"","url":"https://doi.org/10.1145/1315843.1315861","authors":["Naoki Matsumaru","Peter Dittrich"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-11-15T14:30:20Z","doi":"10.1145/1315843.1315861","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1145/3320288.3320300","name":"Low-Power Deep Learning Inference using the SpiNNaker Neuromorphic Platform","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3320288.3320300","authors":["Craig M. Vineyard","Ryan Dellana","James B. Aimone","Fredrick Rothganger","William M. Severa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-08-23T12:03:10Z","doi":"10.1145/3320288.3320300","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-642-58930-0_4","name":"Uncertainty Theories by Modal Logic","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-58930-0_4","authors":["Germano Resconi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-06-15T23:06:59Z","doi":"10.1007/978-3-642-58930-0_4","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-642-58930-0_11","name":"Fuzzy Decision Support Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-58930-0_11","authors":["H.-J. Zimmermann"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-06-15T19:06:59Z","doi":"10.1007/978-3-642-58930-0_11","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-319-28031-8_7","name":"Robust Optimized Artificial Neural Network Based PEM Fuelcell Voltage Tracking","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-28031-8_7","authors":["R. Vinu","Paul Varghese"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-14T01:02:33Z","doi":"10.1007/978-3-319-28031-8_7","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1016/j.asoc.2018.07.039","name":"A dynamic metaheuristic optimization model inspired by biological nervous systems: Neural network algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2018.07.039","authors":["Ali Sadollah","Hassan Sayyaadi","Anupam Yadav"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-07-21T11:49:24Z","doi":"10.1016/j.asoc.2018.07.039","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1299/jsmermd.2021.2p2-h08","name":"FPGA implementation of a neuro-inspired algorithm for spatio-temporal visual feature extraction","source":"crossref","abstract":"","url":"https://doi.org/10.1299/jsmermd.2021.2p2-h08","authors":["Yuuki Ymaji","Eisaku Horiguchi","Hirotsugu OKUNO"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-24T22:40:09Z","doi":"10.1299/jsmermd.2021.2p2-h08","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1299/jsmermd.2020.2p1-n19","name":"A neuro-inspired binocular stereo vision system that uses texture boundaries for corresponding point search","source":"crossref","abstract":"","url":"https://doi.org/10.1299/jsmermd.2020.2p1-n19","authors":["Shintaro Hayashi","Hirotsugu OKUNO"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-11-25T04:43:02Z","doi":"10.1299/jsmermd.2020.2p1-n19","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1109/cne.2003.1196858","name":"A neuro-controller for robotic manipulators based on biologically-inspired visuo-motor co-ordination neural models","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cne.2003.1196858","authors":["G. Asuni","F. Leoni","E. Guglielmelli","A. Starita","P. Dario"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-12-22T12:34:10Z","doi":"10.1109/cne.2003.1196858","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-981-33-6862-0_50","name":"Whale Optimization Algorithm Applied to Recognize Spammers in Facebook","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-33-6862-0_50","authors":["R. Krithiga","E. Ilavarasan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-06-14T05:02:45Z","doi":"10.1007/978-981-33-6862-0_50","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1201/9781003322931-9","name":"Virtualization Concepts and Industry Standards in Cloud Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003322931-9","authors":["Devesh Kumar Srivastava","Vijay Kumar Sharma","Akhilesh Kumar Sharma","Prakash Chandra Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-24T18:39:16Z","doi":"10.1201/9781003322931-9","addedAt":"2026-09-01T01:48:27.541Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-030-37218-7_88","name":"Smart Healthcare Data Acquisition System","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_88","authors":["Tanvi Ghole","Shruti Karande","Harshita Mondkar","Sujata Kulkarni"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T15:02:40Z","doi":"10.1007/978-3-030-37218-7_88","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.63382/jni.v1i1.5","name":"Neuromorphic Computing in Sensory Systems: A Review","source":"crossref","abstract":"Unlike traditional sensor architectures that often generate an excess of redundant data and suffer from high power consumption, neuromorphic sensors offer a streamlined approach, providing energy-efficient data processing by leveraging the mechanisms of spiking neural networks. This work reviews the latest advancements in neuromorphic visual, auditory, gustatory, olfactory, haptic and proprioceptive sensors, drawing parallels with their biological analogs and discussing their integration with neuromorphic computing frameworks. By converging neuroscience, materials science, and microelectronics, neuromorphic sensors potentially enhance human sensory capabilities, promising profound impacts on robotics and artificial intelligence.","url":"https://doi.org/10.63382/jni.v1i1.5","authors":["Weijia Yan","Jingjing Qiu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-21T18:53:28Z","doi":"10.63382/jni.v1i1.5","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:27.542Z"},{"id":"doi:10.1007/978-3-319-27400-3_18","name":"A Hyper-Heuristic Approach to Solving the Ski-Lodge Problem","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-27400-3_18","authors":["Ahmed Hassan","Nelishia Pillay"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-01T12:08:38Z","doi":"10.1007/978-3-319-27400-3_18","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-319-76354-5_17","name":"A Comprehensive Technical Review on Security Techniques and Low Power Target Architectures for Wireless Sensor Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-76354-5_17","authors":["Abdulfattah M. Obeid","Manel Elleuchi","Mohamed Wassim Jmal","Manel Boujelben","Mohamed Abid","Mohammed S. BenSaleh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-09T11:43:48Z","doi":"10.1007/978-3-319-76354-5_17","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:27.542Z"},{"id":"doi:10.1007/978-3-030-49339-4_17","name":"Short Term Load Forecasting Using Empirical Mode Decomposition (EMD), Particle Swarm Optimization (PSO) and Adaptive Network-Based Fuzzy Interference Systems (ANFIS)","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-49339-4_17","authors":["Saroj Kumar Panda","Papia Ray","Debani Prasad Mishra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-05T11:05:14Z","doi":"10.1007/978-3-030-49339-4_17","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1016/j.compositesb.2026.113685","name":"Neuro-inspired sinusoidal hybrid thin sandwich panels for high-velocity impact response","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.compositesb.2026.113685","authors":["Ahmad Ghiaskar","Farid Taheri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-06T23:16:50Z","doi":"10.1016/j.compositesb.2026.113685","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-030-96299-9_69","name":"State of the Art on Advanced Control of Electric Energy Transformation to Hydrogen","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_69","authors":["Ricardo Puga","José Boaventura","Judite Ferreira","Ana Madureira"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_69","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-78937-3_18","name":"EEG Signals Classification for Motor Imagery Task Using Different KNN Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_18","authors":["Yogendra Narayan","Riya Khera","Rajeev Ranjan","Rohit katyal","Neeshu Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:05:35Z","doi":"10.1007/978-3-031-78937-3_18","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-78937-3_33","name":"Privacy-Preserving Healthcare Data in IoMT","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_33","authors":["Karthik Kovuri","Gunipati Kanishka","Pattabhi Mary Jyosthna","A. Jyothi Babu","Nagendar Yamsani","R. Vanithamani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:07:30Z","doi":"10.1007/978-3-031-78937-3_33","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-78946-5_2","name":"Blockchain's Potential in International Criminal Justice: A Blue Ocean Analysis and Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_2","authors":["Nuno Santos","Joel Curado","Joao C. Ferreira"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:03:31Z","doi":"10.1007/978-3-031-78946-5_2","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:27.542Z"},{"id":"doi:10.1007/978-981-96-0706-8_13","name":"Tackling the 5G Cell Switch-Off as a Sparse Multi-objective Optimization Problem: A Comparison of the State-of-the-Art","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-96-0706-8_13","authors":["David Rubio-Atroche","Jesús Galeano-Brajones","Francisco Luna-Valero","Javier Carmona-Murillo","Juan F. Valenzuela-Valdés"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-19T13:37:04Z","doi":"10.1007/978-981-96-0706-8_13","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-78949-6_42","name":"Role of ICT Tools in Enhancing Teaching Pedagogy in Higher Education","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78949-6_42","authors":["B. Uma Rani","S. Kalyan","T. Roja Rani","S. Raghavendra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T09:29:22Z","doi":"10.1007/978-3-031-78949-6_42","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-78937-3_12","name":"Implementing Deep Learning Models For Identifying And Classifying Infectious Skin Disease In Humans","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_12","authors":["R. Sandhiya","K. Sruthi","S. Suruthi","S. V. Kogilavani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:06:14Z","doi":"10.1007/978-3-031-78937-3_12","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-030-96299-9_46","name":"Educational Workflow Model for Effective and Quality Management of E-Learning Systems Design and Development: A Conceptual Framework","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_46","authors":["Kingsley Okoye"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_46","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-030-96299-9_73","name":"Impact of Socio-Economic Factors on Students’ Academic Performance: A Case Study of Jawahar Navodaya Vidyalaya","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_73","authors":["Kapila Devi","Saroj Ratnoo","Anu Bajaj"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_73","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1109/bic-ta.2011.39","name":"Hyperedge Replacement Graph P System","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bic-ta.2011.39","authors":["Meena Parvathy Sankar","N.G. David","D.G. Thomas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-10-18T11:35:51Z","doi":"10.1109/bic-ta.2011.39","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1109/nabic.2009.5393713","name":"Gender identification in face images using KPCA","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393713","authors":["S Aji","T Jayanthi","M.R. Kaimal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393713","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1109/nabic.2009.5393534","name":"Software cost estimation using computational intelligence techniques","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393534","authors":["J.S. Pahariya","V. Ravi","M. Carr"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393534","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1109/nabic.2010.5716328","name":"Constraints for DNA sequences by formal language and its capacity","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2010.5716328","authors":["H Kamabe"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-02-18T19:03:54Z","doi":"10.1109/nabic.2010.5716328","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.21533/scjournal.v2i1.50","name":"Performance Evaluation of Nature-Inspired Algorithms in constrained Optimization","source":"crossref","abstract":"","url":"https://doi.org/10.21533/scjournal.v2i1.50","authors":["Ali Osman Kusakci","Mehmet Can"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-07-05T05:46:55Z","doi":"10.21533/scjournal.v2i1.50","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1109/nabic.2011.6089414","name":"Customer profile classification using transactional data","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2011.6089414","authors":["Edward T. Apeh","Bogdan Gabrys","Amanda Schierz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-12-06T16:02:25Z","doi":"10.1109/nabic.2011.6089414","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1201/9781003143499-12","name":"Communication and hybrid circuit design","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003143499-12","authors":["Elishai Ezra Tsur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-07-19T12:30:34Z","doi":"10.1201/9781003143499-12","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch011","name":"Cognitively Based Modeling of Scientific Productivity","source":"crossref","abstract":"This chapter advocates a cognitively realistic approach to social simulation. based on a model for capturing the growth of academic science. Gilbert’s (1997) model, which was equation based, is replaced in this work by an agent-based model, with the cognitive architecture CLARION providing greater cognitive realism. Using this agent model, results comparable to human data are obtained. It is found that while different cognitive settings may affect aggregate productivity of scientific articles, generally they do not lead to different distributions of productivity. It is argued that using more cognitively realistic models in social simulations may lead to novel insights.","url":"https://doi.org/10.4018/978-1-59140-984-7.ch011","authors":["I. Naveh","R. Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch011","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/s00521-003-0388-6","name":"A neuro-fuzzy approach for functional genomics data interpretation and analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-003-0388-6","authors":["Daniel Neagu","Vasile Palade"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-12-23T15:14:14Z","doi":"10.1007/s00521-003-0388-6","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1109/nabic.2010.5716376","name":"A nonparametric Bayesian approach to time series alignment","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2010.5716376","authors":["S Akimoto","N Suematsu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-02-18T19:03:54Z","doi":"10.1109/nabic.2010.5716376","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1109/bimnics.2007.4610074","name":"Digital and biological storage systems &amp;#x2014; a quantitative comparison","source":"crossref","abstract":"The paper presents a quantitative comparison of digital/electronic and biological storage systems. Two biological storage systems are included: DNA and brain memory. First we will show some examples of digital-biological systems integration. In the main part of the paper, we discuss different storage aspects, mostly quantitative, such as: organization, functionality, data density, capacity, power consumption, redundancy, integrity, access time and data transfer rate. Numerous analogies between biological and electronic storage systems are pointed out. Finally, we will try to answer the question: which digital storage systems and media are the best equivalents for brain and DNA storage? The analysis of the storage systems resemblances and differences may facilitate to carry bioinformatics research.","url":"https://doi.org/10.1109/bimnics.2007.4610074","authors":["Tomasz Bilski"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-09-08T16:06:46Z","doi":"10.1109/bimnics.2007.4610074","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1109/bicta.2008.4656698","name":"Efficient DNA sticker algorithms for DES","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2008.4656698","authors":["Zhihua Chen","Xiutang Geng","Jin Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-10-28T15:22:35Z","doi":"10.1109/bicta.2008.4656698","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-642-37502-6_37","name":"Algorithm of DNA Computing Model for Gate Assignment Problem","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-37502-6_37","authors":["Zhixiang Yin","Min Chen","Qingyan Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-05-07T08:25:55Z","doi":"10.1007/978-3-642-37502-6_37","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.3923/ijscomp.2011.75.84","name":"Applicability of Adaptive Neuro-Fuzzy Inference Systems in Daily Reservoir Inflow Forecasting","source":"crossref","abstract":"","url":"https://doi.org/10.3923/ijscomp.2011.75.84","authors":["S.H. Karimi-Goo","T.S. Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-12-10T00:33:14Z","doi":"10.3923/ijscomp.2011.75.84","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1016/j.asoc.2004.03.003","name":"Speeding-up the design of HW/SW implementations of neuro-fuzzy systems using the CodeSimulink environment","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2004.03.003","authors":["L.M. Reyneri","F. Renga"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2004-05-01T09:50:07Z","doi":"10.1016/j.asoc.2004.03.003","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-78937-3_23","name":"Real Time Face Mask Detector","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_23","authors":["Ch. Rajyalakshmi","Gampa Sri Varsha","Galipalli Vinay Teja","Dasi Bhargavi","K. Reddy Madhavi","Mohammad Gouse Galety"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:06:34Z","doi":"10.1007/978-3-031-78937-3_23","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-27499-2_55","name":"Modelling and Simulation of the Dump-Truck Problem Using MATLAB Simulink","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_55","authors":["Ibidun C. Obagbuwa","Bam Stefany","Moroka Dineo Tiffany"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_55","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-27499-2_85","name":"Thyroid Nodule Classification of Ultrasound Image by Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_85","authors":["Arunkumar Beyyala","R. Priya","Subramani Roy Choudary","R. Bhavani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_85","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-27499-2_5","name":"Transfer Learning Based Pediatric Pneumonia Diagnosis Using Residual Attention Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_5","authors":["Arun Prakash Jayakanthan","S. Shiva Rupan","V. Sowmya","Moez Krichen","Vinayakumar Ravi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_5","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-78940-3_8","name":"A Deep Dive into Southern India’s Rainfall: LSTM Perspectives","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78940-3_8","authors":["Megha Dhaka","Jeevika Rajput","Yajnaseni Dash","Ajith Abraham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-05T06:08:00Z","doi":"10.1007/978-3-031-78940-3_8","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-030-37218-7_123","name":"Design of Canny Edge Detection Hardware Accelerator Using xfOpenCV Library","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_123","authors":["Lokender Vashist","Mukesh Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T15:02:40Z","doi":"10.1007/978-3-030-37218-7_123","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/s10586-022-03740-x","name":"A quantum inspired hybrid SSA–GWO algorithm for SLA based task scheduling to improve QoS parameter in cloud computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s10586-022-03740-x","authors":["Richa Jain","Neelam Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-29T21:03:20Z","doi":"10.1007/s10586-022-03740-x","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-030-37218-7_124","name":"Application of Cloud Computing for Economic Load Dispatch and Unit Commitment Computations of the Power System Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_124","authors":["Nithiyananthan Kannan","Youssef Mobarak","Fahd Alharbi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T20:02:40Z","doi":"10.1007/978-3-030-37218-7_124","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.4203/csets.13.2","name":"Structural Design Inspired by Nature","source":"crossref","abstract":"","url":"https://doi.org/10.4203/csets.13.2","authors":["T. Arciszewski","R. Kicinger"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-05-22T15:58:56Z","doi":"10.4203/csets.13.2","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1109/icacc.2012.6","name":"COPD Prognosis under Biologically Inspired Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icacc.2012.6","authors":["Komathy Karuppanan","Abinaya Sree Vairasundaram","Manjula Sigamani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-09-30T22:42:58Z","doi":"10.1109/icacc.2012.6","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1016/b978-0-323-96104-2.00007-5","name":"Brain-inspired evolving and spiking connectionist systems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-323-96104-2.00007-5","authors":["Nikola Kirilov Kasabov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-20T10:19:45Z","doi":"10.1016/b978-0-323-96104-2.00007-5","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1201/9781003637400-10","name":"Quantum-Inspired Learning Analytics and Student Behavior Modeling","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003637400-10","authors":["Seema Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-23T20:19:51Z","doi":"10.1201/9781003637400-10","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1162/artl_a_00407","name":"Does the Field of Nature-Inspired Computing Contribute to Achieving Lifelike Features?","source":"crossref","abstract":"Abstract The main idea behind artificial intelligence was simple: what if we study living systems to develop new, practical computing systems that possess “lifelike” properties? And that’s exactly how evolutionary computing emerged. Researchers came up with ideas inspired by the principles of evolution to develop intelligent methods to tackle hard problems. The efficacy of these methods made researchers seek inspiration in living organisms and systems and extend the evolutionary concept to other nature-inspired ideas. In recent years, nature-inspired computing has exhibited an exponential increase in the number of algorithms that are presented each year. Authors claim that they are inspired by a behavior found in nature to come up with a lifelike algorithm. However, the mathematical background does not match the behavior in the majority of these cases. Thus the question is, do all nature-inspired algorithms remain lifelike? Also, are there any ideas included that contribute to computing? This study aims to (a) present some nature-inspired methods that contribute to achieving lifelike features of computing systems and (b) discuss if there is any need for new lifelike features.","url":"https://doi.org/10.1162/artl_a_00407","authors":["Alexandros Tzanetos"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-18T19:52:01Z","doi":"10.1162/artl_a_00407","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1109/mind67540.2025.11351837","name":"Deep Spiking Double Descent","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mind67540.2025.11351837","authors":["Natabara Máté Gyöngyössy","Béla János Szekeres","János Botzheim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-27T04:49:35Z","doi":"10.1109/mind67540.2025.11351837","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.22266/ijies2024.0630.16","name":"Towards Quantum Computing-Inspired Evolutionary Algorithm for Optimized Cloud Resource Management","source":"crossref","abstract":"","url":"https://doi.org/10.22266/ijies2024.0630.16","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-03T19:03:07Z","doi":"10.22266/ijies2024.0630.16","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-981-16-9573-5_42","name":"Covariance Features Improve Low-Resource Reservoir Computing Performance in Multivariate Time Series Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-16-9573-5_42","authors":["Sofía Lawrie","Rubén Moreno-Bote","Matthieu Gilson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-30T06:02:42Z","doi":"10.1007/978-981-16-9573-5_42","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-030-22868-2_87","name":"A Bug-Inspired Algorithm for Obstacle Avoidance of a Nonholonomic Wheeled Mobile Robot with Constraints","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-22868-2_87","authors":["Sing Yee Ng","Nur Syazreen Ahmad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-07-08T04:04:24Z","doi":"10.1007/978-3-030-22868-2_87","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-981-10-6747-1_14","name":"An Optimal Tree-Based Routing Protocol Using Particle Swarm Optimization","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-10-6747-1_14","authors":["Radhika Sohan","Nitin Mittal","Urvinder Singh","Balwinder Singh Sohi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-10-04T04:25:22Z","doi":"10.1007/978-981-10-6747-1_14","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-030-37218-7_103","name":"An Image Processing Based Approach for Monitoring Changes in Webpages","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_103","authors":["Raj Kothari","Gargi Vyas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T15:02:40Z","doi":"10.1007/978-3-030-37218-7_103","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-030-96299-9_54","name":"A Modified Feature Optimization Approach with Convolutional Neural Network for Apple Leaf Disease Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_54","authors":["Vagisha Sharma","Amandeep Verma","Neelam Goel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_54","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-78937-3_8","name":"HCU: A Multi-lingual Health Claim Dataset and Its NLP Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_8","authors":["Huizhi Liang","Zhiling Zhou","Zhenyu Hou","Chris Ryder","Rodney Jones"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:07:02Z","doi":"10.1007/978-3-031-78937-3_8","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-78946-5_30","name":"A Novel Signature Based Reconnaissance Attack Detection and Threat Identification System","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_30","authors":["T. Raj Kumar","M. C. Aswathy","N. V. Sobhana"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:03:44Z","doi":"10.1007/978-3-031-78946-5_30","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-7908-1866-6_9","name":"Neuro-Fuzzy Control Applications in Pressurized Water Reactors","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-7908-1866-6_9","authors":["Man Gyun Na"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-11-12T07:06:26Z","doi":"10.1007/978-3-7908-1866-6_9","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1109/edge72783.2026.00013","name":"NeSy-Edge: Neuro-Symbolic Trustworthy Self-Healing in the Computing Continuum","source":"crossref","abstract":"","url":"https://doi.org/10.1109/edge72783.2026.00013","authors":["Peihan Ye","Alfreds Lapkovskis","Alaa Saleh","Qiyang Zhang","Praveen Kumar Donta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-26T19:07:30Z","doi":"10.1109/edge72783.2026.00013","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1142/9789813143180_0004","name":"Evolutionary Algorithm for Solving Complex Multiobjective Optimization Problems","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789813143180_0004","authors":["Ye Tian","Xingyi Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-04-08T05:29:16Z","doi":"10.1142/9789813143180_0004","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.4108/icst.bionetics2007.2461","name":"Self-organizing Service Supervision","source":"crossref","abstract":"","url":"https://doi.org/10.4108/icst.bionetics2007.2461","authors":["Peter H. Deussen","Edzard Höfig"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-03-10T14:16:22Z","doi":"10.4108/icst.bionetics2007.2461","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1109/nabic.2009.5393707","name":"On-line Handwritten character Recognition using Kohonen networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393707","authors":["M. Sreeraj","Sumam Mary Idicula"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5393707","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-78943-4_11","name":"Ontology Synthesis for Transnational, Cultural and Community Studies using Hybrid Learning Paradigms","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78943-4_11","authors":["Alle Naga Rishikesh Reddy","Gerard Deepak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-03T11:08:02Z","doi":"10.1007/978-3-031-78943-4_11","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-78946-5_1","name":"OSPC: Ontology Synthesis on Peace and Conflict Studies as a Domain of Choice","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_1","authors":["S. S. Nitin Hariharan","Gerard Deepak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:03:53Z","doi":"10.1007/978-3-031-78946-5_1","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-27499-2_56","name":"Modeling and Simulation of a Robot Arm with Conveyor Belt Using Matlab Simulink Model","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_56","authors":["Ibidun Christiana Obagbuwa","Kutlo Baldwin Mogorosi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_56","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-27499-2_70","name":"Automatic Calcium Detection in Echocardiography Based on Deep Learning: A Systematic Review","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_70","authors":["Sara Gomes","Luís B. Elvas","João C. Ferreira","Tomás Brandão"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_70","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:27.542Z"},{"id":"doi:10.1007/978-3-031-78943-4_48","name":"Emergency Communication Networks – Applications and Challenges","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78943-4_48","authors":["Nagendar Yamsani","A. B. Archana","Suresh Babu Jugunta","E. Sreedevi","Naresh Tangudu","S. Ambika"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-03T11:08:20Z","doi":"10.1007/978-3-031-78943-4_48","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-78946-5_38","name":"Early Detection and Prediction of Water Quality Using Machine Learning Techniques","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_38","authors":["N. Pooja kumara","H. S. Vandana","Bobby Lukose"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:03:43Z","doi":"10.1007/978-3-031-78946-5_38","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-78943-4_29","name":"Digital Media and Talent Acquisition in the Banking, Financial Services, and Insurance Sector: A Bibliometric Analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78943-4_29","authors":["Sonika","Ashita Chadha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-03T11:07:57Z","doi":"10.1007/978-3-031-78943-4_29","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/s00500-008-0325-9","name":"Guest editorial: bio-inspired information hiding","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00500-008-0325-9","authors":["Jeng-Shyang Pan","Ajith Abraham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-05-29T13:28:16Z","doi":"10.1007/s00500-008-0325-9","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1109/nabic.2013.6617870","name":"Multi-objective optimization of building envelopes by bacterial memetic algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2013.6617870","authors":["Arpad Csik","Janos Botzheim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-10-10T23:27:30Z","doi":"10.1109/nabic.2013.6617870","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1145/3358500","name":"Proceedings of the 6th ACM SIGPLAN International Workshop on AI-Inspired and Empirical Methods for Software Engineering on Parallel Computing Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3358500","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-10-11T15:16:45Z","doi":"10.1145/3358500","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-20418-0_11","name":"A Systems Thinking Inspired Approach to Understanding Design Activity","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-20418-0_11","authors":["Gregory Litster","Ada Hurst","Carlos Cardoso"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-04T17:15:25Z","doi":"10.1007/978-3-031-20418-0_11","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1016/j.imavis.2014.04.002","name":"Covariance descriptor based on bio-inspired features for person re-identification and face verification","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.imavis.2014.04.002","authors":["Bingpeng Ma","Yu Su","Frédéric Jurie"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-04-12T22:01:04Z","doi":"10.1016/j.imavis.2014.04.002","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-27499-2_80","name":"Adding Blockchain and Smart Contracts to a Low-Code Development Platform","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_80","authors":["Ana Barbosa","Nuno Dâmaso","Diogo Pacheco","Susana Nicola","Nuno Bettencourt"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_80","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-78946-5_37","name":"Canal Water Data Monitoring System and Controlling System","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_37","authors":["Vaishali Niranjane","Shivam Patil","Trushant Dharpure","Manish Bhosle","Rutik Pawar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:04:05Z","doi":"10.1007/978-3-031-78946-5_37","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-27499-2_60","name":"Fuzzy Investment Assessment Techniques: A State-of-the-Art Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_60","authors":["Cengiz Kahraman","Basar Oztaysi","Sezi Çevik Onar","Selcuk Cebi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_60","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:27.542Z"},{"id":"doi:10.1016/j.conb.2024.102853","name":"Leveraging dendritic properties to advance machine learning and neuro-inspired computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.conb.2024.102853","authors":["Michalis Pagkalos","Roman Makarov","Panayiota Poirazi"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.conb.2024.102853","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.3389/fnins.2022.974627","name":"Editorial: Neuro-inspired computing for next-gen AI: Computing model, architectures and learning algorithms.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2022.974627","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.3389/fnins.2022.974627","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1038/s41467-022-28303-x","name":"High-precision and linear weight updates by subnanosecond pulses in ferroelectric tunnel junction for neuro-inspired computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-022-28303-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1038/s41467-022-28303-x","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.20944/preprints202109.0444.v1","name":"Bidirectional Electric-induced Conductance based on GeTe/Sb<sub>2</sub>Te<sub>3</sub> Interfacial Phase Change Memory for Neuro-inspired Computing","source":"europepmc","abstract":"","url":"https://doi.org/10.20944/preprints202109.0444.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.20944/preprints202109.0444.v1","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:28.407Z"},{"id":"doi:10.3390/biology15141148","name":"Closing the Loop on the Cocktail Party Effect: From Attention Decoding to Neuro-Steered Selective Hearing.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biology15141148","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/biology15141148","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.149Z"},{"id":"doi:10.1039/d6mh00086j","name":"Emergent neuro-mimetic oscillations in engineered granular assemblies.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d6mh00086j","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d6mh00086j","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.149Z"},{"id":"doi:10.21203/rs.3.rs-9029917/v1","name":"Neuro-Hormonal Networks: A Bio-Inspired Architecture forEnhanced Deep Learning Performance","source":"europepmc","abstract":"Abstract In this work, neuro-hormonal networks (NHNs) are presented which are a novel bioinspireddeep learning architecture that integrates dynamic neuro-modulation mechanismsto achieve superior performance in deep learning tasks. Our approach addresses fundamentallimitations in conventional neural networks and how they are enhanced by incorporatingdopamine and cortisol-like hormonal pathways that adaptively modulate synaptic weightsduring training, mirroring biological neuro-endocrine systems. The mathematical frameworkis grounded in delay differential equations, control theory, and weighted logic networks,implementing three distinct modulation types: accelerators for enhanced plasticity,suppressors for homeostatic regulation, and stabilizers for output regularization. The multihormonalmodulation component dynamically adjusts effective weights. Thus, enablingadaptive learning that responds to both current performance and historical training dynamics.Comprehensive evaluation across four benchmark datasets demonstrates consistentand statistically significant improvements: CIFAR-10 (+5.36pp), CIFAR-100 (+6.57pp),Fashion-MNIST (+0.67pp), and SVHN (+0.09pp). McNemar’s test validation confirmsstatistical significance (p ¡ 0.001) for three of four datasets, with particularly strong benefitsobserved for complex, multi-class classification tasks. Advanced performance metricsinclude ROC AUC (≥ 0.99) and PR AUC (≥ 0.95) demonstrating superior discriminationcapability and robustness across evaluation scenarios. The architecture exhibits enhancedconvergence stability, improved generalization capability, and interpretable adaptation patternsthat correlate with training dynamics. While incurring an average of 2.96× computationaloverhead per epoch, the biological plausibility and consistent performance gainsvalidate the practical effectiveness of neuro-endocrine principles in artificial intelligence.Our work establishes a rigorous mathematical foundation for hormonal computing anddemonstrates how multi-timescale biological dynamics can be successfully translated intoimproved deep learning architectures. To the best of our knowledge, the NHN is thefirst novel work to establish and implement the neuro-hormonal modulation indeep learning architectures with rigorous mathematical background, advancedimplementations and novel results.","url":"https://doi.org/10.21203/rs.3.rs-9029917/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-9029917/v1","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1038/s41598-026-50418-0","name":"A novel intelligent hybrid reinforcement learning framework for autonomous decision making in complex health cognitive systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-50418-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-50418-0","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/s11571-026-10429-z","name":"MedIntelliCare: neurodynamic-inspired AI for medical decision support by integrating retrieval-augmented generation with multimodal cognitive processing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-026-10429-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s11571-026-10429-z","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.149Z"},{"id":"doi:10.1007/s11571-025-10386-z","name":"A neuro-inspired visual SLAM approach using AKAZE feature extraction in complex and dynamic environments.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-025-10386-z","authors":["Ruibang Li","Yihong Wang","Xuying Xu","Fangfei Li","Fengzhen Tang","Xiaochuan Pan"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025-12-06T07:35:41Z","doi":"10.1007/s11571-025-10386-z","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.149Z"},{"id":"doi:10.3390/s26051518","name":"Application of AI in Cyberattack Detection: A Review.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s26051518","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/s26051518","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1098/rsif.2025.0433","name":"A bio-inspired research paradigm of collision perception neurons enabling neuro-robotic integration: the LGMD case.","source":"europepmc","abstract":"","url":"https://doi.org/10.1098/rsif.2025.0433","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1098/rsif.2025.0433","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.20944/preprints202508.1321.v1","name":"NeuroGraph-TSC: A Neuro-Inspired Graph-Based Temporal-Spatial Classifier for Cognitive State Prediction from EEG","source":"europepmc","abstract":"Accurate prediction of cognitive states such as psychological stress from electroencephalography (EEG) remains a significant challenge due to the inherently spatiotemporal and nonlinear nature of brain dynamics. To address these complexities, we propose NeuroGraph-TSC, a novel neuro-inspired, graph-based temporal-spatial classifier that incorporates domain-specific neuroscientific priors into a deep learning architecture for improved cognitive state decoding. The model constructs a spatial graph where EEG electrodes are represented as nodes, and inter-node edge weights are determined based on either scalp geometry or empirical functional connectivity, enabling physiologically meaningful spatial feature propagation. Temporal modeling is achieved through recurrent processing that captures both rapid and slow neural fluctuations. To further enhance biological plausibility, we integrate a neural mass model-based regularizer into the loss function, specifically adopting the Jansen-Rit dynamical system to constrain the model toward biophysically informed temporal dynamics.We evaluate NeuroGraph-TSC on the SAM-40 raw EEG stress dataset, achieving high classification performance across low, moderate, and high stress levels. Comprehensive ablation studies and interpretability analyses confirm the individual and collective contributions of the neuroscience-aligned components, validating both the robustness and neurophysiological relevance of the model. NeuroGraph-TSC offers a promising step toward bridging computational neuroscience and deep learning for advancing EEG-based affective computing.","url":"https://doi.org/10.20944/preprints202508.1321.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.20944/preprints202508.1321.v1","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1016/j.neunet.2025.108161","name":"A survey on neuro-mimetic deep learning via predictive coding.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.108161","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2025.108161","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1038/s41598-026-47627-y","name":"QuantumNeuroXAI: a quantum-inspired deep learning framework with explainability for brain signal analysis and neurological disorder detection.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-47627-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-47627-y","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1038/s41467-025-65387-7","name":"Exploiting neuro-inspired dynamic sparsity for energy-efficient intelligent perception.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-65387-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-65387-7","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3390/biomimetics11060392","name":"Fog Task Scheduling Using Quality-Source-Driven Multi-Anchor Synchronized Search Algorithm.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics11060392","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/biomimetics11060392","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.3389/fpls.2026.1796835","name":"Adaptive recognition network for few-shot plant diseases and pests based on homeostatic neuromodulation and meta-plasticity.","source":"europepmc","abstract":"Introduction Static networks often exhibit limited generalization on few-shot data, particularly given the scarce samples and unstructured background noise inherent to precision agriculture. To address these limitations, an adaptive recognition network for few-shot plant diseases and pests based on homeostatic neuromodulation and meta-plasticity (HNeuroNet) is proposed. Methods This framework incorporates dynamic plasticity inspired by biological systems to mitigate the data dependency paradox. First, a Neuro Modulatory Generator (NMG) is constructed utilizing a hypernetwork architecture. Simulating neurotransmitter gating mechanisms, affine transformation parameters are dynamically generated for feature channels based on support set samples. Consequently, instantaneous weight reconstruction is enabled without expensive gradient fine-tuning, thereby overcoming structural rigidity and catastrophic forgetting during rapid adaptation. Second, a Homeostatic Suppression Mechanism (HSM) integrating visual perception is introduced. Leveraging Bienenstock-Cooper-Munro (BCM) theory, an adaptive activation function is employed to regulate neuron thresholds based on historical feature map statistics. High-frequency noise from complex environments is suppressed, significantly enhancing feature extraction and target saliency in low signal-to-noise ratios. Finally, an end-to-end Dynamic Meta-Plasticity (DMP) strategy is implemented. By coupling parameter generation and threshold regulation within a bi-level optimization framework, biological homeostatic adaptation is simulated to adjust perception strategies. Context-dependent feature interaction patterns are established to secure robust discriminative boundaries under extreme few-shot conditions. Results Experimental results demonstrate that HNeuroNet significantly outperforms state-of-the-art methods on IP102, PlantDoc, and Mini-ImageNet. Notably, 5-way 1-shot accuracy on the PlantDoc dataset surpasses the second-best baseline by 4.33%. Furthermore, a 1-shot accuracy of 71.36% is achieved on the cross-domain Mini-ImageNet task. Discussion These results confirm the potential of bio-inspired computing in addressing data scarcity.","url":"https://doi.org/10.3389/fpls.2026.1796835","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fpls.2026.1796835","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s44172-026-00589-5","name":"Harnessing synthetic biology for energy-efficient bioinspired electronics: applications for logarithmic data converters.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s44172-026-00589-5","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s44172-026-00589-5","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3390/bioengineering12060628","name":"Spiking Neural Networks for Multimodal Neuroimaging: A Comprehensive Review of Current Trends and the NeuCube Brain-Inspired Architecture.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/bioengineering12060628","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/bioengineering12060628","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1021/acsnano.5c15070","name":"Retina-Inspired 2D Semiconductor NIR Sensor with PRO Architecture for Photodetection.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.5c15070","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsnano.5c15070","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fncom.2025.1657167","name":"Editorial: Interdisciplinary synergies in neuroinformatics, cognitive computing, and computational neuroscience.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2025.1657167","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fncom.2025.1657167","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fncom.2025.1495313","name":"TourismNeuro xLSTM: neuro-inspired xLSTM for rural tourism planning and innovation.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2025.1495313","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fncom.2025.1495313","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fncom.2025.1685174","name":"Editorial: Neuro-detection: advancements in pattern detection and segmentation techniques in neuroscience.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2025.1685174","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fncom.2025.1685174","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1002/adma.202511411","name":"Optically Controlled Memristor Enabling Synergistic Sensing-Memory-Computing for Neuromorphic Vision Systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202511411","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202511411","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.149Z"},{"id":"doi:10.1038/s41598-026-46823-0","name":"An explainable artificial intelligence framework for ischemic heart disease prediction using enhanced squirrel search feature selection.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-46823-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-46823-0","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fnbot.2025.1543115","name":"Editorial: Brain-inspired autonomous driving.","source":"europepmc","abstract":"Autonomous driving is one of the hallmarks of arIficial intelligence. Neuromorphic, brain-inspired compuIng architectures, are revoluIonizing vehicular autonomy through biomimeIc approaches [1].They can dramaIcally impact the mulIdimensional landscape of autonomous driving, extending across criIcal domains such as control [2], navigaIon [3], and neurophysiological assessment [4]. ParIcularly, these brain-inspired computaIonal systems leverage spiking neural networks (SNNs) and event-driven processing to enhance real-Ime percepIon [5], decision-making [6], and adapIve learning capabiliIes [7].This arIcle collecIon revolves around the state of the art of neuromorphic systems, designed to support autonomous driving across those dimensions.Neuromorphic control is posed to significantly contribute to autonomous behavior by leveraging spiking neural networks-based energy-efficient computaIonal frameworks. In this collecIon, Halaly and colleagues explored neuromorphic implementaIons of four prominent controllers for autonomous driving: pure-pursuit, Stanley, PID (ProporIonal -Integral -DerivaIve), and MPC (Model PredicIve Control), using CARLA [8], a physics-aware simulaIon framework. Their results show that those neuromorphic control models converge to their opImal performances with merely 100-1,000 neurons.They also highlight the importance of hybrid convenIonal and neuromorphic designs, as was suggested here with the MPC controller. This MPC was later extended to support adapIve behavior and to address unforeseen situaIons such as malfuncIoning and swi` steering scenarios [9]. Further in this arIcle collecIon, Lian and colleagues addressed the importance of adapIve control for changing road condiIons by proposing a neural model for deriving road adhesion coefficient (the maximum fricIon coefficient between Ire and road surface) and Ire cornering sIffness (affected by road fricIon and Ire slip angle).Those parameters can be used to improve the design of the vehicle's dynamic model and enhance the controller's robustness.Autonomous driving systems (ADSs) o`en comprise mulImodal sensing, including cameras, LiDARs, IMUs, and GPS, for real-Ime object detecIon, semanIc segmentaIon, planning, and control [10]. LiDAR-driven neural percepIon is an important stepping stone toward the design of self-navigaIng vehicles [6]. In this arIcle collecIon, Lee and colleagues propose a neural reinforcement model, they termed the \"Velocity Range-based EvaluaIon Method\" in which LiDAR data is used to provide path planning in a map-less environment.Finally, in the evoluIonary scenario of autonomous driving technologies, the transiIonal phase characterized by parIal vehicle autonomy presents criIcal challenges in human-machine interacIon [11].The emerging paradigm necessitates a sophisIcated, bidirecIonal monitoring system that transcends tradiIonal human-vehicle interfaces. In fact, the vehicle must develop robust capabiliIes for comprehensive driver state monitoring, including advanced sensor fusion techniques for enabling holisIc driver condiIon evaluaIon, to determine whether the driver is able to intervene and take control [12].Empirical research suggests that effecIve human-autonomous system collaboraIon requires not just technological sophisIcaIon, but a deep understanding of human cogniIve and physiological variability [13]. The ulImate goal is to develop a symbioIc human-machine interface where autonomous systems act as collaboraIve partners rather than mere technological subsItutes, enhancing overall transportaIon safety and efficiency. In this regard, in this arIcle collecIon, Giorgi and colleagues propose an integrated framework to assess the driver's mental faIgue in real Ime using electroencephalographic, electrooculographic, photoplethysmographic, and electrodermal acIvity. Their holisIc approach showed that the most sensiIve and Imely parameters are those related to brain acIvity. To a lesser extent, those related to ocular parameters are also sensiIve to the onset of mental faIgue but with a delayed effect.In conclusion, the confluence of neuromorphic compuIng, advanced sensing technologies, and sophisIcated human-machine interacIon represents a pivotal transformaIon in autonomous driving. This collecIon illuminates the mulIfaceted challenges and innovaIve soluIons emerging at the intersecIon of arIficial intelligence, neuroscience, and automoIve engineering. From energy-efficient neural controllers to adapIve percepIon systems and comprehensive driver state monitoring, the research demonstrates that autonomous driving is far more than a technological challenge-it is a complex socio-technical ecosystem.The future of autonomous vehicles might lie not in complete human replacement, but in creaIng intelligent, responsive systems that collaborate seamlessly with human operators. By integraIng biomimeIc computaIonal approaches, advanced sensor fusion, and a nuanced understanding of human cogniIve variability, we move closer to a transportaIon paradigm that prioriIzes safety, efficiency, and harmonious human-machine interacIon.","url":"https://doi.org/10.3389/fnbot.2025.1543115","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fnbot.2025.1543115","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fncom.2026.1851416","name":"AI-driven neuroanalytic modeling for mental health: multichannel CNN-based autism spectrum disorder detection via facial pattern analysis.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2026.1851416","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fncom.2026.1851416","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/frai.2025.1689727","name":"Self-evolving cognitive substrates through metabolic data processing and recursive self-representation with autonomous memory prioritization mechanisms.","source":"europepmc","abstract":"Introduction Conventional artificial intelligence (AI) systems are limited by static architectures that require periodic retraining and fail to adapt efficiently to continuously changing data environments. To address this limitation, this research introduces a novel biologically inspired computing paradigm that supports perpetual learning through continuous data assimilation and autonomous structural evolution. The proposed system aims to emulate biological cognition, enabling lifelong learning, self-repair, and adaptive evolution without human intervention. Methods The system is built upon dynamic cognitive substrates that continuously absorb and map real-time information streams. These substrates eliminate the traditional distinction between training and inference phases, supporting uninterrupted learning. Quantum-inspired uncertainty management ensures computational robustness, while biomimetic self-healing protocols maintain structural integrity during adaptive changes. Additionally, micro-optimization via fractal propagation enhances mathematical specialization across hierarchical computational levels. Recursive learning mechanisms allow the architecture to refine its functionality based on its own outputs. Results Experimental validation demonstrates that the proposed architecture sustains effective learning across diverse, heterogeneous data domains. The system autonomously restructures itself, maintaining stability while improving performance in dynamic environments. Specialized cognitive processing units, analogous to biological organs, perform distinct functions and collectively enhance adaptive intelligence. Notably, the system prioritizes and retains valuable information through evolution, reflecting biological memory consolidation patterns. Discussion The findings reveal that continuous, self-modifying AI architectures can outperform traditional models in non-stationary conditions. By integrating quantum uncertainty control, biomimetic repair mechanisms, and fractal-based optimization, the system achieves resilient, autonomous learning over time. This approach has far-reaching implications for developing lifelong-learning machines capable of dynamic adaptation, self-maintenance, and evolution paving the way toward fully autonomous, continuously learning artificial organisms.","url":"https://doi.org/10.3389/frai.2025.1689727","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/frai.2025.1689727","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fncom.2026.1781080","name":"NeuralVisionNet: a probabilistic neural process model for continuous visual anticipation.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2026.1781080","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fncom.2026.1781080","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1038/s41566-026-01880-9","name":"Experimental memory control in continuous-variable optical quantum reservoir computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41566-026-01880-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41566-026-01880-9","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1098/rsta.2023.0346","name":"Neural networks with quantum states of light.","source":"europepmc","abstract":"","url":"https://doi.org/10.1098/rsta.2023.0346","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1098/rsta.2023.0346","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1117/1.jbo.30.10.105004","name":"Optogenetically enhanced physical reservoir computing with &lt;i&gt;in vitro&lt;/i&gt; neural networks for obstacle avoidance.","source":"europepmc","abstract":"Significance The effects of optogenetic stimulation (OS) on in vitro neural network behavior were studied through a reservoir computing-based obstacle avoidance task, revealing its impact on the task-processing capabilities of the network. Furthermore, it is demonstrated that a minimal output of signals from 15 neurons in the network is sufficient to achieve stable task control, with a success rate exceeding 95%. The optogenetically enhanced biological reservoir computing frame could find applications in neuro-robotic control and brain-inspired intelligence. Aim We aim to utilize optogenetically controlled in vitro neural networks and the first-order reduced and controlled error (FORCE) learning algorithm to achieve obstacle avoidance in neuro-robotic systems. Approach We presented an all-optical biological reservoir computing framework that leverages optogenetics and calcium imaging to precisely regulate and record neuronal activities. A closed-loop system was developed incorporating the FORCE learning algorithm, which guided a virtual car through obstacle avoidance tasks. Results The system demonstrated high accuracy and efficiency in navigating obstacles, achieving optimal performance after ∼150 s of training. OS significantly improved the obstacle avoidance success rate, enhancing the system's adaptability and accuracy. Conclusions The results highlight the potential of optogenetically controlled biological neural networks in neuro-robotic systems, showcasing their capability to achieve accurate and efficient obstacle avoidance through physical reservoir computing.","url":"https://doi.org/10.1117/1.jbo.30.10.105004","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1117/1.jbo.30.10.105004","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fncom.2026.1810869","name":"Commentary: Editorial: The convergence of AI, LLMs, and industry 4.0: enhancing BCI, HMI, and neuroscience research.","source":"europepmc","abstract":"The ambition of Asgher's editorial is not in question. Framing the intersection of Brain-Computer Interfaces (BCI), Large Language Models (LLMs), and Industry 4.0 deployment infrastructure as a unified engineering and scientific challenge is a legitimate and timely intellectual move. The four-layer model proposed, interaction, measurement, inference, and deployment, offers a useful schematic for a community whose sub-fields often proceed in mutual ignorance.Yet an editorial that positions itself as defining a research agenda for neuroadaptive human-AI systems must be held to the standards it implicitly invokes. When a text asserts that it is grounded in a \"concrete engineering and scientific shift\" and that four articles constitute \"a credible cross-section\" of the field, it makes empirical and epistemological claims that are open to scrutiny.The present commentary argues that these claims do not withstand examination, and that the editorial's principal weaknesses are not incidental but structural.The critique proceeds in seven sections, moving from conceptual to methodological to ethical concerns, before concluding with what we consider the deepest problem: the unexamined inferential gap between the electrical signals measured by EEG and the mental states whose properties are claimed to be known.In his editorial, Asgher frames convergence through three interlocking pillars: first, AI models that infer and adapt to human cognitive and affective states via neuroadaptive control; second, LLM-centric interaction layers serving as cognitive interfaces between humans and complex systems; and third, Industry 4.0 deployment substrates integrating these capabilities into cyber-physical systems with latency, reliability, and governance constraints. He further proposes a closed-loop socio-technical control model with four layers: an interaction layer (LLM/HMI), a measurement layer (BCI/neuroergonomics), an inference and policy layer (AI/RL), and a deployment layer (Industry 4.0/CPS).The editorial opens by distinguishing its use of \"convergence\" from mere interdisciplinary work, describing it as \"a concrete engineering and scientific shift toward closed-loop human-AI systems.\" This distinction is stated but never demonstrated. For convergence to be a scientific claim rather than a programmatic aspiration, one would need to show that previously separate fields are developing shared protocols, common measurement standards, or a unified technical vocabulary. None of this is established by the four articles cited, which remain disciplinarily distinct contributions: philosophical AI alignment theory, a small-N neuroergonomics pilot, a clinical NLP classification pipeline, and a computational linguistics representational analysis.The admission in the editorial's conclusion that \"the field is still largely assembling components\" is internally inconsistent with the opening claim of ongoing convergence. If the components are not yet assembled, the convergence has not occurred, it is at best a normative goal. This conflation of descriptive and prescriptive registers is a recurring feature of what has been called \"promissory science\" (Nordmann, 2007): the practice of treating hoped-for futures as accomplished presents in order to generate research momentum and funding legitimacy.A more defensible framing would have been explicit about this prescriptive character: not \"convergence is happening\" but \"convergence is needed, here is what it would require, and here are four partial steps in that direction.\" The difference is not semantic; it determines the evidential standards to which the work can be held.3. An Empirical Base Insu@icient for Agenda-Setting analyze whether an LSTM language model develops internal representations that separate argument structure constructions, using controlled GPT-4-generated stimuli and representational analysis techniques.Asgher characterizes these four contributions as forming a \"coherent research mosaic\" that provides a \"credible cross-section\" of what convergence currently looks like in the literature.The editorial's argument rests on four articles. This is not, in itself, a disqualifying limitation, commentary pieces routinely work with small sets. The problem is that the text claims something stronger: that these four articles provide a \"credible cross-section\" of convergence as it \"currently looks in the literature.\" This is a representativeness claim that four self-selected papers cannot support.The conflict-of-interest dimension warrants explicit acknowledgment: as editor of the Research Topic, Asgher selected the articles that are subsequently used as evidence for the thesis he advances. Standard epistemological hygiene requires that this circularity be named and mitigated, for instance through explicit acknowledgment of selection criteria, reference to the broader literature, or systematic comparison with excluded submissions. None of these mitigating moves are made.The internal evidential quality is also uneven. The most prominently cited empirical study, Jiang et al.'s EEG investigation of LLM-assisted reasoning, reports results from 12 participants performing problem-solving tasks, with LLM interaction operationalized via GPT-4 in an unspecified chat-based interface. The primary datasets used (DEAP, AMIGOS, SEED, DREAMER) are affective computing benchmarks not designed to measure cognitive dynamics during LLM interaction, and their use for this purpose requires construct validity arguments that are not provided. Asgher himself notes the \"construct-validity critiques\" this invites, but then proceeds to characterize Jiang et al. as \"the clearest BCI + LLM interaction bridge in the set\", a judgment that the methodological caveats do not support.The editorial devotes particular attention to Edwards' contribution, which proposes an observercentric, functional-contextual, neuro-symbolic approach to AI alignment. Edwards targets emergent Theory of Mind (ToM) as a computational capability rather than a philosophical label, and argues that alignment cannot be reduced to surface safety prompts but requires explicit representational machinery: values specification using ACT-inspired framing, utility estimation, and perspectival reasoning to guide LLM token selection. The editorial endorses this view, stating that Edwards' most valuable contribution is the insistence that alignment must be engineered as a visible layer of the system, anchoring the ethics and safety pillar in an explicit computational vocabulary. This includes structured interpretability via hypergraph representations of ToM-relevant relations.The treatment of the Edwards contribution on AI alignment illustrates a pattern of conceptual foreclosure. Asgher endorses the view that alignment \"must be engineered as a visible layer of the system, not treated as an emergent byproduct of scale,\" and frames this as the delivery of an \"explicit computational vocabulary\" for what is called the ethics and safety pillar.The problem of AI alignment, ensuring that an increasingly capable system acts in accordance with human values and intentions, is among the most contested open problems in computer science and philosophy of mind. The computational Theory of Mind (ToM) approach advocated by Edwards is one position in a large and unresolved debate. Presenting it as a practical engineering prerequisite for robust HMI, without engaging the substantial critical literature, is misleading. Russell's (2019) argument about the difficulty of preference specification, the documented failures of RLHF-trained systems to generalize intentions rather than mimic them (Christiano et al., 2017), and the theoretical arguments about specification gaming (Krakovna et al., 2020) are directly relevant and unaddressed.More broadly, the framing of alignment as a \"designed system layer\" sidesteps the question of whose values are encoded, by whom, verified by what process, and revisable under what conditions. These are not engineering questions: they are political and institutional ones, and their absence from a text concerned with deploying neuroadaptive systems in clinical and industrial settings is a substantive gap, not a disciplinary omission.In the editorial, the deployment layer of the proposed socio-technical control loop requires integration into clinical and industrial workflows with safety monitoring, auditability, and governance.Asgher briefly lists trust calibration, cognitive offloading, overreliance, and changes in attentional allocation as new variables introduced by LLM interaction layers. He also acknowledges that the decisive next phase requires evaluation protocols that jointly assess decision quality, cognitive workload, trust, overreliance risks, robustness to drift, and governance compliance.The most consequential weakness of the editorial is the near-total absence of ethical and social analysis. The systems described, real-time measurement of workers' or patients' cognitive states, AI adaptation of behavior based on neurophysiological inference, continuous monitoring embedded in clinical and industrial cyber-physical systems, raise urgent questions of privacy, informed consent, power asymmetry, and potential coercive use. None of these are substantively addressed.\"Trust calibration,\" \"cognitive offloading,\" and \"overreliance\" are mentioned as variables introduced by LLM interaction layers, but without analysis. The identity of the subject doing the calibrating, the differential vulnerability of specific populations to overreliance, the conditions under which trust in AI systems becomes epistemically irrational, these questions are not raised.The deployment of neuroadaptive monitoring in industrial workplaces, where the power differential between employer and employee makes \"informed consent\" structurally problematic, is not mentioned. This omission is not incidental. The critical literature on technology in human contexts, from the work of Ruha Benjamin (2019) on race and technology to Kate Crawford's (2021) analysis of AI as infrastructure of power, has established that the sociotechnical consequences of deploying measurement and inference systems are not separable from their technical design. A research agenda that treats governance as a technical requirement (\"implementable, auditable, and resilient mechanisms\") without engaging the political economy of who audits, who benefits, and who bears risk, is producing incomplete science by design.The clinical context makes this especially acute. The da Vinci surgical robot system analyzed by Li et al. is a high-cost technology disproportionately deployed in high-income health systems. Presenting it as the paradigmatic example of Industry 4.0 in neuroscience implicitly frames the entire convergence agenda around a model of technological development that excludes the majority of the world's clinical contexts. Low-resource settings, community health infrastructure, and equitable access are not mentioned.The editorial concludes that the four published articles show convergence is a substantive research direction rather than a slogan. Its forward-looking call identifies the critical gap that matters most for deployment: the field is still largely assembling components, while the decisive next phase requires what Asgher terms integration science, encompassing shared benchmarks and evaluation protocols for decision quality, cognitive workload, trust, overreliance risks, robustness to drift, and governance compliance within closed-loop systems operating in realistic cyber-physical contexts.The editorial concludes by calling for \"integration science,\" \"shared benchmarks,\" and \"evaluation protocols that jointly assess decision quality, cognitive workload, trust, overreliance risks, robustness to drift, and governance compliance within closed-loop systems operating in realistic cyber-physical contexts.\" This is a reasonable list of desiderata. It is not, however, a falsifiable research agenda.No indicators of progress are specified. No criteria are provided by which a claim that the convergence is occurring, or has been achieved, could be evaluated. No benchmarks are proposed, despite the call for benchmarking. The result is what Smaldino and McElreath (2016) The editorial's measurement layer relies heavily on EEG-based neuroergonomics evidence from Jiang et al., whose pilot study with 12 participants reports three main findings: reduced frontal theta power (interpreted as lower cognitive workload), increased P300 amplitude (interpreted as enhanced attentional and decision integration), and lower NASA-TLX subjective workload ratings under LLM-assisted conditions. The editorial frames these as precisely the type of measurable neuroergonomics signals the Research Topic called for: evidence that LLMs can shift the cognitive economics of reasoning under defined interaction conditions. Moreover, the editorial suggests these quantifiable hooks (theta, P300, subjective workload) could be operationalized in future Industry 4.0 deployments as constraints or triggers for assistance adaptation, throttling, or escalation.We reserve what we consider the most fundamental concern for last, because it cuts beneath the methodological and rhetorical issues to the epistemic foundation of the convergence project itself.The entire logic of the four-layer loop, measure human cognitive state, infer, adapt, deploy, depends on the assumption that EEG and related physiological signals provide reliable access to the mental states they are claimed to index. This assumption is less secure than the editorial implies, in ways that matter for the systems being designed.EEG measures fluctuations in the electromagnetic field at the scalp surface, the aggregate electrical consequence of millions of synchronizing neurons. It does not measure attention, cognitive load, or affect as theoretical constructs. It measures a downstream physical correlate of processes occurring at multiple levels of neural organization that remain incompletely understood.When Jiang et al. report that frontal theta power decreases under LLM-assisted conditions and interpret this as evidence of \"reduced cognitive load,\" they are making an inferential move that traverses several layers of theoretical assumption: from raw signal to frequency band power, from frequency band power to cognitive construct, from cognitive construct to phenomenological state.Each transition involves acknowledged uncertainties that are rarely propagated through to the final interpretation. This is not a criticism unique to Jiang et al. , it applies broadly to applied EEG research.But the scale of the inferential leap matters when the downstream application is a neuroadaptive system that adjusts its behavior based on inferred mental states, and when the claim is that such systems can \"measure human cognitive and affective states\" in real operational environments. The gap between measuring an electromagnetic correlate and knowing a mental state is precisely the gap that the hard problem of consciousness (Chalmers, 1995) marks as unresolved: we do not know whether phenomenal experience is identical to, realized by, or emergent from physical processes, and the answer matters for what we are licensed to claim when we say a system has \"measured\" a cognitive state.Applied neuroscience routinely operates with a methodological correlationalism that brackets this question, and for many predictive purposes, this is scientifically defensible. The problem arises when the bracketing is forgotten, and correlates are described as if they were direct measurements of the states they correlate with. The editorial consistently makes this move, describing the measurement layer as providing access to \"human cognitive and affective states\" rather than to electrophysiological signals that covary with behavioral and subjective reports under specific task conditions.The consequence for the convergence agenda is significant. A closed-loop neuroadaptive system that adapts AI behavior based on inferred mental states is not adapting to what a person is experiencing: it is adapting to a model of what a person is experiencing, built on correlates whose relationship to experience is theoretically underspecified. This is not a reason to abandon the project, but it is a reason to be considerably more cautious about what such systems can and cannot do, and about the risks of deploying them in high-stakes contexts where the cost of a miscalibrated inference is borne by a patient or worker who cannot easily contest it.\"The question is not whether EEG correlates of cognitive states exist, they do, but whether those correlates are sufficient to license the inferential and operational moves that the convergence architecture requires. The editorial does not engage this question. It should.\"Intellectual honesty requires acknowledging what the editorial does well. The four-layer conceptual model, interaction, measurement, inference, deployment, is a useful heuristic that helps position contributions from disparate sub-fields within a common architecture. The insistence that LLMs be treated not only as tools but as cognitive variables that modify human reasoning, and that this modification be measured neurophysiologically, is a methodologically mature position that goes beyond most of the applied AI literature. The frank acknowledgment that the field is still assembling components, even if inconsistently framed, signals a sober realism that contrasts favorably with more triumphalist pronouncements about AI readiness.These contributions are real. The problem is that the editorial's ambitions exceed its foundations. An orientating document for a fragmented community has different standards than a foundational paper claiming to define an empirically grounded convergence. Asgher's text is closer to the former but presents itself as the latter.Asgher's editorial is a useful signal of direction. It is not, by the standards it implicitly invokes, a rigorous foundation for the agenda it proposes. Its principal weaknesses, the assertion rather than demonstration of convergence, the insufficient empirical base, the oversimplification of alignment, the near-total absence of ethical analysis, the unfalsifiable agenda, the acritical use of Industry 4.0, and most fundamentally the unexamined inferential gap between EEG signals and mental states, are structural, not peripheral.We close with a methodological proposal. A genuinely convergent research program for neuroadaptive human-AI systems should explicitly specify: (a) the inferential chain from signal to mental state, with uncertainty estimates at each step; (b) the ethical framework governing deployment, including consent, audit, and contestability mechanisms; (c) falsifiable milestones by which progress toward integration can be assessed; and (d) explicit engagement with what it would mean for the convergence thesis to be wrong. Absent these elements, the field risks mistaking a persuasive narrative for a scientific program, a substitution that is consequential precisely because the systems being designed will act on real people in real environments.","url":"https://doi.org/10.3389/fncom.2026.1810869","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fncom.2026.1810869","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fmed.2025.1755373","name":"Editorial: AI innovations in neuroimaging: transforming brain analysis.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fmed.2025.1755373","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fmed.2025.1755373","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/s40820-025-01888-w","name":"Ultrathin Gallium Nitride Quantum-Disk-in-Nanowire-Enabled Reconfigurable Bioinspired Sensor for High-Accuracy Human Action Recognition.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s40820-025-01888-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1007/s40820-025-01888-w","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1021/jacs.6c02370","name":"An Atom-Precise Approach to Damp First-Order Phase Transitions and Its Implications for Neuromorphic Signal Processing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/jacs.6c02370","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/jacs.6c02370","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.149Z"},{"id":"doi:10.3390/s25247408","name":"AI-Driven Energy-Efficient Routing in IoT-Based Wireless Sensor Networks: A Comprehensive Review.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s25247408","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/s25247408","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3390/diagnostics15162040","name":"Neuro-Bridge-X: A Neuro-Symbolic Vision Transformer with Meta-XAI for Interpretable Leukemia Diagnosis from Peripheral Blood Smears.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/diagnostics15162040","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/diagnostics15162040","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fdgth.2025.1727707","name":"Merging multimodal digital biomarkers into \"Digital Neuro Fingerprints\" for precision neurology in dementias: the promise of the right treatment for the right patient at the right time in the age of AI.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fdgth.2025.1727707","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fdgth.2025.1727707","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-026-42548-2","name":"A lightweight metaheuristic-driven adaptive PID approach for nonlinear conical tank regulation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-42548-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-42548-2","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s44325-025-00101-6","name":"Can AI help with the hardest thing: pro health behavior change.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s44325-025-00101-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s44325-025-00101-6","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fmed.2025.1686859","name":"Editorial: Artificial intelligence-assisted medical imaging solutions for integrating pathology and radiology automated systems, volume II.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fmed.2025.1686859","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fmed.2025.1686859","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/s12200-025-00151-9","name":"Temperature stabilization with Hebbian learning using an autonomous optoelectronic dendritic unit.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s12200-025-00151-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1007/s12200-025-00151-9","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.7717/peerj-cs.3042","name":"Multi-objective optimization for smart cities: a systematic review of algorithms, challenges, and future directions.","source":"europepmc","abstract":"","url":"https://doi.org/10.7717/peerj-cs.3042","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.7717/peerj-cs.3042","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3390/diagnostics15121478","name":"Edge Artificial Intelligence Device in Real-Time Endoscopy for the Classification of Colonic Neoplasms.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/diagnostics15121478","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/diagnostics15121478","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3390/mi16050517","name":"Photonic-Electronic Modulated a-IGZO Synaptic Transistor with High Linearity Conductance Modulation and Energy-Efficient Multimodal Learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/mi16050517","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/mi16050517","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/s12021-026-09792-3","name":"HESREN: A Derivative-Informed Reservoir Framework for Detecting Transient Neural Events and Windowless Estimation of Dynamic Functional Connectivity.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s12021-026-09792-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s12021-026-09792-3","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1016/j.isci.2026.115785","name":"Integrating metacognitive mechanisms optimizes EEG generative models via hierarchical regularization.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.isci.2026.115785","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.isci.2026.115785","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1073/pnas.2521560123","name":"Online supervised learning of temporal patterns in biological neural networks under feedback control.","source":"europepmc","abstract":"In vitro biological neural networks (BNNs) provide well-defined model systems for constructively investigating how living cells interact with their environments to shape high-dimensional dynamics that can be used to generate coherent temporal outputs, such as those required for motor control. Here, we develop a real-time closed-loop BNN system that is capable of generating periodic and chaotic temporal signals by integrating cultured cortical neurons with microfluidic devices and high-density microelectrode arrays. We show that training a simple linear decoder with fixed feedback weights enables the system to learn and autonomously generate diverse temporal patterns. When feedback is switched on, the irregular activity in the BNNs is transformed into low-dimensional, structured dynamics, producing coherent trajectories that are characterized by stable transitions between different neural states. BNNs trained on various target frequencies-ranging from 4 to 30 s-can be trained to sustain oscillations at distinct frequencies, demonstrating their adaptability. Importantly, top-down control of the self-organized network formation with microfluidic devices is the key to suppressing excessive synchronization and increasing dynamic complexity in BNNs, facilitating the training process and the generation of robust outputs. This work offers a biologically inspired platform for understanding the physical basis of cortical computations and for advancing energy-efficient neuromorphic computing paradigms.","url":"https://doi.org/10.1073/pnas.2521560123","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1073/pnas.2521560123","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3390/s25133995","name":"Emotion Recognition from rPPG via Physiologically Inspired Temporal Encoding and Attention-Based Curriculum Learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s25133995","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/s25133995","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fnbot.2024.1386178","name":"Editorial: Swarm neuro-robots with the bio-inspired environmental perception.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnbot.2024.1386178","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3389/fnbot.2024.1386178","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1073/pnas.2504164122","name":"Biologically grounded neocortex computational primitives implemented on neuromorphic hardware improve vision transformer performance.","source":"europepmc","abstract":"","url":"https://doi.org/10.1073/pnas.2504164122","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1073/pnas.2504164122","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fpsyt.2026.1703605","name":"AI digital-twin ecosystem translating gut-microbiome-neuroimmune signals into precision sleep-mood interventions.","source":"europepmc","abstract":"We present a novel AI-powered \"gut-brain-sleep\" digital-twin nursing ecosystem (G-B-S DT-N) that translates microbiome and neuroimmune signals into precision interventions for sleep and mood disorders. The ecosystem integrates four key layers: Microbiome Dynamics, Neuro-immune Interface, Sleep-Cognition-Emotion Circuits, and Person-Nurse-Environment Triad. These layers leverage multi-omics data, EEG sleep microstructure, real-time sensors, and EMR feeds to create a dynamic, patient-specific architecture. Uncertainty-aware explainable AI (XAI) modules ensure privacy and interpretability, enabling causal inference through advanced machine learning techniques. Adaptive care pathways, including precision pre-/post-biotic delivery and circadian light prescriptions, are optimized via nurse-in-the-loop reinforcement learning. The digital twin is operationalized through a five-step closed-loop workflow in hospital and community settings. Quantum-accelerated simulations and a proposed RCT (D-TWIN-RCT) will assess efficacy compared to standard care. Social, legal, and ethical frameworks protect data sovereignty and autonomy. This ecosystem offers a scalable solution for managing complex comorbidities, positioning nursing as a key driver of microbiome-precision medicine.","url":"https://doi.org/10.3389/fpsyt.2026.1703605","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fpsyt.2026.1703605","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-026-36121-0","name":"Hybrid quantum classical framework for electroencephalogram driven neurological processing in epileptic seizure taxonomy.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-36121-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-36121-0","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-026-50194-x","name":"An advanced hybrid deep learning framework for high-precision brain tumor detection and classification in MRI scans.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-50194-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-50194-x","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fncir.2026.1731513","name":"From small brains to smart machines: translating &lt;i&gt;Caenorhabditis elegans&lt;/i&gt; neural circuits into artificial intelligence.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncir.2026.1731513","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fncir.2026.1731513","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-025-29169-x","name":"Continuous blood glucose monitoring prediction for diabetes using evolving neural network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-29169-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-29169-x","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/frai.2025.1637105","name":"Lipschitz-based robustness estimation for hyperdimensional learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/frai.2025.1637105","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/frai.2025.1637105","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/s11517-025-03341-x","name":"Reimagining cancer tissue classification: a multi-scale framework based on multi-instance learning for whole slide image classification.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11517-025-03341-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1007/s11517-025-03341-x","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3390/brainsci16040411","name":"BrainTwin-AI: A Multimodal MRI-EEG-Based Cognitive Digital Twin for Real-Time Brain Health Intelligence.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/brainsci16040411","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/brainsci16040411","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fncom.2025.1581047","name":"Editorial: Computational intelligence for signal and image processing, volume II.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2025.1581047","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fncom.2025.1581047","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1515/nanoph-2025-0045","name":"Nonlinear inference capacity of fiber-optical extreme learning machines.","source":"europepmc","abstract":"","url":"https://doi.org/10.1515/nanoph-2025-0045","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1515/nanoph-2025-0045","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3390/brainsci16040386","name":"Quantum-Inspired and Non-Classical Approaches to Consciousness: Models, Evidence and Constraints.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/brainsci16040386","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/brainsci16040386","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fnins.2024.1386712","name":"Editorial: Emerging talents in neuromorphic engineering.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2024.1386712","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3389/fnins.2024.1386712","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.3390/s26113405","name":"Intrusion Detection in the Internet of Things: A Comprehensive Review of Techniques, Architectures, Datasets, and Emerging Trends.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s26113405","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/s26113405","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-025-31820-6","name":"Quantum-entangled neuro-symbolic swarm federation for privacy-preserving IoMT-driven multimodal healthcare.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-31820-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-31820-6","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3390/bioengineering13010057","name":"IESS-FusionNet: Physiologically Inspired EEG-EMG Fusion with Linear Recurrent Attention for Infantile Epileptic Spasms Syndrome Detection.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/bioengineering13010057","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/bioengineering13010057","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.34133/cbsystems.0367","name":"An Integrated Monolithic Synaptic Device for C-Tactile Afferent Perception and Robot Emotional Interaction.","source":"europepmc","abstract":"","url":"https://doi.org/10.34133/cbsystems.0367","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.34133/cbsystems.0367","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3390/biomimetics11060439","name":"A Systematic Taxonomy of the Sunflower Optimization Algorithm: Variants, Hybridization Strategies, Applications, and Research Directions.","source":"europepmc","abstract":"Due to the rapidly increasing number of studies conducted using SFO in recent years, a comprehensive and systematic review of the existing literature has become necessary. SFO is a bio-inspired metaheuristic optimization algorithm developed based on the sun-tracking behavior of sunflower plants. Owing to its simple mathematical structure and flexible search capability, SFO has been increasingly applied to various engineering and AI problems. This review study presents a systematic and comprehensive analysis of SFO-based studies published in the literature. The literature search was performed using the Scopus database, and a total of 192 studies were included in the final evaluation process. The reviewed studies were classified into eight major application domains, including engineering design, energy systems, machine learning, image processing, communication systems, robotics, forecasting, and multi-objective optimization. In addition, the distributions of standard, hybrid, and modified SFO approaches were comparatively analyzed. The temporal evolution of SFO studies, hybridization tendencies, application diversity, strengths, limitations, and future research directions were also systematically evaluated. The findings indicate that hybrid and modified SFO structures have become increasingly dominant in recent years, particularly in AI and data-driven optimization applications. Overall, this review provides a broad understanding of the current state and future research potential of SFO-based optimization studies.","url":"https://doi.org/10.3390/biomimetics11060439","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/biomimetics11060439","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-025-04694-x","name":"Reliability assessment of friction stir welds in AA100 aluminium alloy using ANN and ANFIS predictive models.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-04694-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-04694-x","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1186/s12891-025-09174-x","name":"Design and development of a model for tennis elbow injury prediction and prevention using Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) approaches.","source":"europepmc","abstract":"","url":"https://doi.org/10.1186/s12891-025-09174-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1186/s12891-025-09174-x","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1016/j.bbrc.2024.149725","name":"Proto-neural networks from thermal proteins.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.bbrc.2024.149725","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.bbrc.2024.149725","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1038/s41598-026-36321-8","name":"MPPT algorithms for grid-connected solar systems including deep learning approaches.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-36321-8","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-36321-8","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-025-02793-3","name":"Optimal approximate computation of Euclidean distance in spiking neural P systems framework.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-02793-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-02793-3","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1021/acsami.5c15572","name":"Controlling the Wake-Up Mechanism and Switching Kinetics of Ferroelectric Hf&lt;sub&gt;&lt;i&gt;x&lt;/i&gt;&lt;/sub&gt;Zr&lt;sub&gt;1 - &lt;i&gt;x&lt;/i&gt;&lt;/sub&gt;O&lt;sub&gt;2&lt;/sub&gt; through Hf Content Modulation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c15572","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c15572","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1016/j.patter.2024.101114","name":"Data-knowledge co-driven innovations in engineering and management.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.patter.2024.101114","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.patter.2024.101114","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1093/pnasnexus/pgae488","name":"Neuromorphic neuromodulation: Towards the next generation of closed-loop neurostimulation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1093/pnasnexus/pgae488","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1093/pnasnexus/pgae488","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.3389/fdgth.2025.1690489","name":"Cognitive frontiers: neurotechnology and global internet governance.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fdgth.2025.1690489","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fdgth.2025.1690489","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-025-29028-9","name":"Software effort estimation based on inception network optimized by enhanced banyan tree growth optimizer.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-29028-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-29028-9","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1093/sleepadvances/zpaf022","name":"Impact of spindle-inspired transcranial alternating current stimulation during a nap on sleep-dependent motor memory consolidation in healthy older adults.","source":"europepmc","abstract":"","url":"https://doi.org/10.1093/sleepadvances/zpaf022","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1093/sleepadvances/zpaf022","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3390/biomimetics10100712","name":"Semi-Automatic System for ZnO Nanoflakes Synthesis via Electrodeposition Using Bioinspired Neuro-Fuzzy Control.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics10100712","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/biomimetics10100712","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1371/journal.pone.0349451","name":"A novel hybrid framework integrating GA-driven 3D ResUNetGAN for MRI brain tumor segmentation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pone.0349451","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pone.0349451","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.34133/cbsystems.0287","name":"Opportunities and Challenges of Brain-on-a-Chip Interfaces.","source":"europepmc","abstract":"","url":"https://doi.org/10.34133/cbsystems.0287","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.34133/cbsystems.0287","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fpsyg.2026.1664747","name":"A quantum-cognitive approach to dynamic meaning construction.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fpsyg.2026.1664747","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fpsyg.2026.1664747","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-025-06719-x","name":"DDoS attack detection in intelligent transport systems using adaptive neuro-fuzzy inference system.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-06719-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-06719-x","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1186/s11671-025-04363-y","name":"Cell-to-cell communication: from physical calling to remote emotional touching.","source":"europepmc","abstract":"","url":"https://doi.org/10.1186/s11671-025-04363-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1186/s11671-025-04363-y","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1371/journal.pdig.0001442","name":"PANDIA: Personalized neuro-symbolic multimodal fusion for interpretable neonatal pain assessment.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pdig.0001442","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pdig.0001442","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1364/ol.532942","name":"Wavelength tuning of VCSELs via controlled strain.","source":"europepmc","abstract":"","url":"https://doi.org/10.1364/ol.532942","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1364/ol.532942","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1038/s41467-025-60818-x","name":"Experimental demonstration of third-order memristor-based artificial sensory nervous system for neuro-inspired robotics.","source":"europepmc","abstract":"Abstract The sensory nervous system in animals enables the perception of external stimuli. Developing an artificial sensory nervous system has been widely conducted to realize neuro-inspired robots capable of effectively responding to external stimuli. However, it remains challenging to develop artificial sensory nervous systems that possess sophisticated biological functions, such as habituation and sensitization, enabling efficient responses without bulky peripheral circuitry. Here, we introduce a memristor device with third-order switching complexity, emulating an artificial synapse that inherently possesses habituation and sensitization properties. Incorporating an additional resistive switching TiO x layer into the HfO 2 memristor exhibits third-order switching complexity and non-volatile habituation characteristics. Based on the third-order memristor, we propose a robotic system equipped with a memristor-based artificial sensory nervous system for optimizing the robot arm’s response to external stimuli without the aid of processors. It is experimentally demonstrated that the robot arm with the developed memristor-based artificial sensory nervous system ignores approximately 71% of safe and familiar stimuli while sensitively responding to threatening and significant stimuli, similar to the habituation and sensitization of biological sensory nervous systems. Our findings can be a stepping stone for energy-efficient and intelligent robotic systems with reduced hardware burden.","url":"https://doi.org/10.1038/s41467-025-60818-x","authors":["See-On Park","Hakcheon Jeong","Seokho Seo","Youna Kwon","Jongwon Lee","Shinhyun Choi"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-60818-x","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41467-023-42488-9","name":"Neuro-inspired optical sensor array for high-accuracy static image recognition and dynamic trace extraction.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-023-42488-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1038/s41467-023-42488-9","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1038/s41598-026-40982-w","name":"Fuzzy adaptive nonlinear MIMO control for rigid coupled multibody robots using reinforcement learning model.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-40982-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-40982-w","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1186/s12916-026-04903-y","name":"Structural connectome architecture and biological vulnerability shape cortical atrophy in cocaine use disorder.","source":"europepmc","abstract":"Background Cocaine use disorder (CUD) is highly prevalent and characterized by widespread gray matter atrophy across the cerebral cortex. Yet, it remains unclear whether and how connectome-based circuits and biological features shape these structural abnormalities. Methods We mapped cortical atrophy patterns in CUD (discovery cohort: N = 53; replication cohort: N = 74; controls: N = 364) onto the brain's structural connectome, functional connectivity, transcriptomic similarity and receptor similarity architecture. Using a multimodal and multiscale connectivity-based framework, we identified CUD epicenters and evaluated their spatial correspondence with therapeutic brain stimulation targets and individual variations in clinical symptoms. Results We found that CUD-related regional atrophy is constrained by the white matter (WM) structural connectome. Along these WM pathways, regions that share similar haemodynamic activity and molecular features are more likely to exhibit convergent atrophy profiles. By integrating the structural connectome with multiple connectivity blueprints, we subsequently identified CUD epicenters and revealed that the prefrontal and visual cortices serve as core systems. Furthermore, we linked these epicenters to cortical transcriptomic patterns and receptor architectures, identifying synaptic and neural homeostasis-related gene enrichment and the strongest spatial correspondence with serotonergic (5-HT 1B /5-HT 4 ) and dopaminergic (D 2 ) receptors. Finally, we demonstrated that the spatial distribution of these epicenters correlates with cocaine craving-response maps derived from repeated transcranial magnetic stimulation and can track individual variations in clinical behavioural representations, suggesting their potential as targets for therapeutic intervention. Conclusions Altogether, our findings establish a structurally constrained framework for the spread of pathology underlying cortical atrophy in CUD, where initial perturbations propagate via structural connectome pathways to vulnerable regions shaped by neural activity and molecular landscapes.","url":"https://doi.org/10.1186/s12916-026-04903-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1186/s12916-026-04903-y","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/frai.2026.1804338","name":"Dynamic nested hierarchies: self-evolving machine learning architectures for lifelong learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/frai.2026.1804338","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/frai.2026.1804338","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1186/s42492-025-00207-9","name":"Body Cosmos 2.0: embodied biofeedback interface for dancing.","source":"europepmc","abstract":"This study presents Body Cosmos 2.0, an embodied biofeedback system with an interactive interface situated at the intersection of dance, human-computer interaction, and bio-art. Building on the authors' prior work, \"Body Cosmos: An Immersive Experience Driven by Real-time Bio-data,\" the system presents the concept of a 'bio-body'-a dynamic digital embodiment of a dancer's internal state-generated in real-time through electroencephalography, heart rate sensors, motion tracking, and visualization techniques. Dancers interact with the system through three distinct experiences \"VR embodiment,\" which enables them to experience their internal states from a first-person perspective; \"dancing within your bio-body,\" which immerses them in their internal physiological and emotional states; and \"dancing with your bio-body,\" which creates a bio-digital reflection for expressive development and experiential exploration. To evaluate the system's effectiveness, a workshop was conducted with 24 experienced dancers to assess its impact on self-awareness, creativity, and dance expressions. This integration of biodata with artistic expression transcends traditional neurofeedback and delves into the realm of embodied cognition. The study explores the concept, development, and application of \"Body Cosmos 2.0,\" highlighting its potential to amplify self-awareness, augment performance, and expand the expressive and creative possibilities of dance.","url":"https://doi.org/10.1186/s42492-025-00207-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1186/s42492-025-00207-9","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1002/anie.202401477","name":"Bio-inspired Two-dimensional Nanofluidic Ionic Transistor for Neuromorphic Signal Processing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/anie.202401477","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1002/anie.202401477","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1038/s41598-026-58491-1","name":"Cross-attention guided explainable deep transformer model for multi-level classification of rare neurological disorders using MRI images.","source":"europepmc","abstract":"Neurological disorders (ND) impact a significant number of the population all over the world, affecting the brain, spinal cord, and peripheral nerves. These disorders are classified as NeuroDegenerative, NeuroBiological, and NeuroDevelopmental disorders, which vary from common to rare disorders. Traditional deep learning methods often fail to generalize efficiently in these settings and are developed for common or single-label disease classification. Also, the insufficient interpretability in these models can decrease the medical professionals' trust and utilization. Therefore, this study introduces a Cross-Attention Guided Explainable Deep Transformer Model for Multi-Level Classification of Rare Neurological Disorders (CAXDT-MLCRND) model. The proposed model involves the integration of convolutional neural network for local feature representation with transformer-based network to capture global contextual dependencies. Besides, a new cross-attention strategy is applied for enabling dynamic interaction among local and global representations, enabling the model to effectively distinguish visually similar rare disease patterns. Moreover, the derived features are fused with complementary representations from convolutional neural networks within a soft voting-based ensemble model, which integrates a Graph Neural Network (GNN), Deep Belief Network (DBN), and Stacked Autoencoder (SAE) to boost the robustness and generalization of the classification process. Additionally, Bayesian optimization (BO) is leveraged to fine-tune the hyperparameters of the DL approach for improved performance. For assuring clinical reliability, explainability is incorporated using Eigen Class Activation Mapping (EigenCAM), offering visual understanding into model prediction and improving clinical interpretability. The experimental results of the CAXDT-MLCRND system are validated utilizing open access MRI dataset, and the results report the enhanced multi-label classification performance on the simultaneous prediction of co-existing neurological conditions. Therefore, the proposed model is found to be a robust and interpretable approach to assist clinical applications for rare neurological disorder detection in resource-limited environments. Moreover, the source code used in this study is publicly available at: https://github.com/researcher010-debug/NeurologicalDisorderClassification.git .","url":"https://doi.org/10.1038/s41598-026-58491-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-58491-1","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-026-35013-7","name":"Hybrid feature selection with novel deep learning model for COVID-19 risk prediction.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-35013-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-35013-7","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1111/desc.70211","name":"Infants and Mobiles: Developing an Understanding of Cause and Effect.","source":"europepmc","abstract":"","url":"https://doi.org/10.1111/desc.70211","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1111/desc.70211","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3390/biomimetics8050436","name":"Perceiving like a Bat: Hierarchical 3D Geometric-Semantic Scene Understanding Inspired by a Biomimetic Mechanism.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics8050436","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.3390/biomimetics8050436","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.3389/frai.2025.1583079","name":"Spectral Entropic Radiomics Feature Extraction (SERFE): an adaptive approach for glioblastoma disease classification.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/frai.2025.1583079","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/frai.2025.1583079","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1117/1.jmi.12.1.017502","name":"Weakly supervised pathological differentiation of primary central nervous system lymphoma and glioblastoma on multi-site whole slide images.","source":"europepmc","abstract":"","url":"https://doi.org/10.1117/1.jmi.12.1.017502","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1117/1.jmi.12.1.017502","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fnins.2024.1383481","name":"Editorial: Brain functional analysis and brain-like intelligence.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2024.1383481","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3389/fnins.2024.1383481","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1038/s41467-024-53375-2","name":"Trainees' perspectives and recommendations for catalyzing the next generation of NeuroAI researchers.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-024-53375-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41467-024-53375-2","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1073/pnas.2426883123","name":"Primate-informed neural network for visual decision-making.","source":"europepmc","abstract":"","url":"https://doi.org/10.1073/pnas.2426883123","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1073/pnas.2426883123","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s44385-026-00086-6","name":"Symbiotic brain-machine drawing via visual brain-computer interfaces.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s44385-026-00086-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s44385-026-00086-6","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fncom.2023.1126493","name":"Editorial: Neuro-inspired sensing and computing: Novel materials, devices, and systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2023.1126493","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.3389/fncom.2023.1126493","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1021/acsami.6c02711","name":"Dopamine-Mediated Attenuation of OECT-Based Aqueous Artificial Chemical Synapses.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.6c02711","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.6c02711","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.149Z"},{"id":"doi:10.1016/j.heliyon.2024.e32609","name":"Brain-machine interactive neuromodulation research tool with edge AI computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.heliyon.2024.e32609","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.heliyon.2024.e32609","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1038/s41598-025-19265-3","name":"Optimization of scours downstream of conduit aerators.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-19265-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-025-19265-3","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3390/nano14070584","name":"Oxide Ionic Neuro-Transistors for Bio-inspired Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/nano14070584","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3390/nano14070584","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1038/s41598-025-25052-x","name":"Enhancing the precision of male fertility diagnostics through bio inspired optimization techniques.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-25052-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-25052-x","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1186/s41747-026-00741-y","name":"Whole anterior visual pathway segmentation from high-resolution MRI using artificial intelligence.","source":"europepmc","abstract":"","url":"https://doi.org/10.1186/s41747-026-00741-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1186/s41747-026-00741-y","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-025-31112-z","name":"Energy efficient transactions for blockchain networks using adaptive global best-worst particle swarm optimization.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-31112-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-025-31112-z","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1186/s40708-025-00270-1","name":"Biotuner: A python toolbox integrating music theory and signal processing for harmonic analysis of physiological and natural time series.","source":"europepmc","abstract":"","url":"https://doi.org/10.1186/s40708-025-00270-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1186/s40708-025-00270-1","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-026-44161-9","name":"Accelerating supercritical pharmaceutical formulation via interpretable data-driven prediction of drug solubility.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-44161-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-44161-9","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1093/nsr/nwae066","name":"Advancing brain-inspired computing with hybrid neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1093/nsr/nwae066","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1093/nsr/nwae066","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.3390/diagnostics16020294","name":"Hybrid ConvNeXtV2-ViT Architecture with Ontology-Driven Explainability and Out-of-Distribution Awareness for Transparent Chest X-Ray Diagnosis.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/diagnostics16020294","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/diagnostics16020294","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/frai.2025.1626804","name":"Integration of AI and ML in regenerative braking for electric vehicles: a review.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/frai.2025.1626804","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/frai.2025.1626804","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1039/d3nr06057h","name":"Organic iontronic memristors for artificial synapses and bionic neuromorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d3nr06057h","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1039/d3nr06057h","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.3390/tomography12020025","name":"Radiomics-Driven Hybrid Deep Learning for MRI-Based Prediction of Glioma Grade and 1p/19q Codeletion.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/tomography12020025","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/tomography12020025","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-026-41842-3","name":"Hybrid intelligence-powered secure clustering with trust-optimized routing for next-generation MANET communication.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-41842-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-41842-3","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1038/s41467-025-58932-x","name":"Voltage-controlled magnetoelectric devices for neuromorphic diffusion process.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-58932-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-58932-x","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1126/science.ade3483","name":"Edge learning using a fully integrated neuro-inspired memristor chip.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/science.ade3483","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1126/science.ade3483","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:28.407Z"},{"id":"doi:10.1021/acs.nanolett.5c05915","name":"Enhanced 2D MoTe&lt;sub&gt;2&lt;/sub&gt; Analogue Switching through Laser Processing and ALD-Passivation for Dual-Function Neuromorphic Devices.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.5c05915","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acs.nanolett.5c05915","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1038/s41598-025-92190-7","name":"Navigating artificial general intelligence development: societal, technological, ethical, and brain-inspired pathways.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-92190-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-92190-7","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-025-18243-z","name":"Energy-efficient clustering and routing for IoT-enabled healthcare using adaptive fuzzy logic and hybrid optimization.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-18243-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-18243-z","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-026-45657-0","name":"Enhanced Dhole Optimization Algorithm for hyperparameter tuning of a TCN-BiGRU-MHA hybrid architecture for wind power forecasting.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-45657-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-45657-0","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-025-05014-z","name":"Optimized breast cancer diagnosis using self-adaptive quantum metaheuristic feature selection.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-05014-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-05014-z","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fnhum.2026.1756589","name":"Leef: environmental neuroscience modeling for cognitive resilience.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnhum.2026.1756589","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnhum.2026.1756589","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/s40820-024-01368-7","name":"A Fully-Integrated Memristor Chip for Edge Learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s40820-024-01368-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1007/s40820-024-01368-7","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1126/sciadv.ady8518","name":"Electroluminescent perovskite QD-based neural networks for energy-efficient and accelerate multitasking learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.ady8518","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1126/sciadv.ady8518","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"epmc:MED41959946","name":"NeuroTree: Hierarchical Functional Brain Pathway Decoding for Mental Health Disorders.","source":"europepmc","abstract":"","url":"https://pubmed.ncbi.nlm.nih.gov/41959946/","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1016/j.nicl.2025.103856","name":"Quantification of brain functional connectivity deviations in individuals: A scoping review of functional MRI studies.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.nicl.2025.103856","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.nicl.2025.103856","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/frai.2026.1716108","name":"Between innovation and risk: artificial intelligence and data protection in digital Mexico.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/frai.2026.1716108","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/frai.2026.1716108","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41467-023-41046-7","name":"An all 2D bio-inspired gustatory circuit for mimicking physiology and psychology of feeding behavior.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-023-41046-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1038/s41467-023-41046-7","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1073/pnas.2411909122","name":"Emergent neuronal mechanisms mediating covert attention in convolutional neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1073/pnas.2411909122","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1073/pnas.2411909122","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41377-024-01729-2","name":"Progress on intelligent metasurfaces for signal relay, transmitter, and processor.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41377-024-01729-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41377-024-01729-2","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-024-77696-w","name":"Optimal power generation of proton exchange membrane fuel cell using ANFIS based MPPT algorithm.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-024-77696-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41598-024-77696-w","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1186/s40708-025-00281-y","name":"Brain-inspired signal processing for detecting stress during mental arithmetic tasks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1186/s40708-025-00281-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1186/s40708-025-00281-y","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41467-025-56122-3","name":"A guidance to intelligent metamaterials and metamaterials intelligence.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-56122-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-56122-3","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3390/s24154915","name":"Biomimetic Neuromorphic Sensory System via Electrolyte Gated Transistors.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s24154915","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3390/s24154915","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.3389/fncom.2024.1345644","name":"Leveraging neuro-inspired AI accelerator for high-speed computing in 6G networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2024.1345644","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3389/fncom.2024.1345644","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1016/j.xinn.2023.100455","name":"Integrating social neuroscience into human-machine mutual behavioral understanding for autonomous driving.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.xinn.2023.100455","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1016/j.xinn.2023.100455","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:28.407Z"},{"id":"doi:10.1038/s41598-026-38028-2","name":"Learning-aided Artificial Bee Colony with neural knowledge transfer for global optimization.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-38028-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-38028-2","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41593-026-02205-3","name":"Competitive interactions shape mammalian brain network dynamics and computation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41593-026-02205-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41593-026-02205-3","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1111/desc.70231","name":"Toddlers' Active Gaze Behavior Supports Self-Supervised Object Learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.1111/desc.70231","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1111/desc.70231","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.3390/brainsci15050517","name":"Co-Community Network Analysis Reveals Alterations in Brain Networks in Alzheimer's Disease.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/brainsci15050517","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/brainsci15050517","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-026-39667-1","name":"Integrating Lyapunov based backstepping and neuro fuzzy logic with sliding mode control for precise trajectory tracking of differential drive robots.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-39667-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-39667-1","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1038/s41598-025-30913-6","name":"An efficient dimensionality reduction framework using metaheuristic optimization with deep learning models for amyotrophic lateral sclerosis disease progression prediction.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-30913-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-30913-6","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-024-80894-1","name":"Enhanced operation of PVWPS based on advanced soft computing optimization techniques.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-024-80894-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41598-024-80894-1","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.3389/fchem.2023.1232949","name":"Hormonal computing: a conceptual approach.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fchem.2023.1232949","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.3389/fchem.2023.1232949","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:28.407Z"},{"id":"doi:10.1038/s41598-026-41343-3","name":"Optimized environmental prediction in smart buildings using Dynamic Greylag Goose algorithm and deep learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-41343-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-41343-3","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1002/adma.202300107","name":"Energy Efficient Neuro-Inspired Phase-Change Memory Based on Ge<sub>4</sub> Sb<sub>6</sub> Te<sub>7</sub> as a Novel Epitaxial Nanocomposite.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202300107","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1002/adma.202300107","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:28.407Z"},{"id":"doi:10.1038/s41598-026-42626-5","name":"Smart wastewater management in hydro-technical systems using digital twin technology.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-42626-5","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-42626-5","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1167/jov.26.4.4","name":"The development of object representations in children.","source":"europepmc","abstract":"","url":"https://doi.org/10.1167/jov.26.4.4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1167/jov.26.4.4","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fnbot.2023.1112839","name":"When neuro-robots go wrong: A review.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnbot.2023.1112839","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.3389/fnbot.2023.1112839","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1038/s41598-025-32880-4","name":"Multiple trajectory optimization and control of robotic agents using hybrid fuzzy embedded artificial intelligence technique for multi target problems.","source":"europepmc","abstract":"Wheeled robot is preferred for their ability to replace human efforts in performing tedious and complex tasks. To accomplish the goal of present global scenario like replacement of human effort and work on fixed automation, it is needed to target multi-objective problems in context of robotic path optimization and less time consumption. Path optimization and control over wheeled robots is very challenging and interesting part of robotic research. Here, Fuzzy logic and modified marine predator optimization algorithm are hybridized and implemented on mobile robots to fulfill real-time objectives of present scenario. In hybridization process, initially obstacle distances from robot location are fed into fuzzy-logic and interim output obtained from Fuzzy logic is again fed to marine predator optimization algorithm to obtain final output. A Petri-Net controller is added with proposed novel fuzzy- marine predator optimization algorithm that further optimizes the navigational parameters by avoiding inter-collision among robots in presence of moving obstacles. Simulation is performed through MATLAB software and the results are tested against real-time experiments under laboratory condition. Simulation and real-time experiments authenticate successful navigation of multiple robots by achieving their objectives. Furthermore, the proposed technique is tested against different AI techniques and existing paper. An average improvement of approximately 10% or more is observed in navigational parameters.","url":"https://doi.org/10.1038/s41598-025-32880-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-32880-4","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.21203/rs.3.rs-1606598/v1","name":"Improvement Learning Using a Fully Integrated Neuro-Inspired Memristor Chip","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-1606598/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.21203/rs.3.rs-1606598/v1","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:28.407Z"},{"id":"doi:10.1101/2025.06.17.659820","name":"Population-specific brain charts reveal Chinese-Western differences in neurodevelopmental trajectories","source":"preprints","abstract":"Human brain charts provide unprecedented opportunities for decoding neurodevelopmental milestones and establishing clinical benchmarks for precision brain medicine 1-7 . However, current lifespan brain charts are primarily derived from European and North American cohorts, with Asian populations severely underrepresented. Here, we present the first population-specific brain charts for China, developed through the Chinese Lifespan Brain Mapping Consortium (Phase I) using neuroimaging data from 43,037 participants (aged 0−100 years) across 384 sites nationwide. We establish the lifespan normative trajectories for 296 structural brain phenotypes, encompassing global, subcortical, and cortical measures. Cross-population comparisons with Western brain charts (based on data from 56,339 participants aged 0−100 years) reveal distinct neurodevelopmental patterns in the Chinese population, including prolonged cortical and subcortical maturation, accelerated cerebellar growth, and earlier development of sensorimotor regions relative to paralimbic regions. Crucially, these Chinese-specific charts outperform Western-derived models in predicting healthy brain phenotypes and detecting pathological deviations in Chinese clinical cohorts. These findings highlight the urgent need for diverse, population-representative brain charts to advance equitable precision neuroscience and improve clinical validity across populations.","url":"https://doi.org/10.1101/2025.06.17.659820","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.06.17.659820","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.443Z"},{"id":"doi:10.21203/rs.3.rs-1300648/v1","name":"Noise Resilient Leaky Integrate-and-fire Neuron Based on Multi-domain Spintronic Devices","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-1300648/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.21203/rs.3.rs-1300648/v1","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:28.407Z"},{"id":"doi:10.21203/rs.3.rs-7887022/v1","name":"Network-based disease fingerprinting with neuroinflammation PET imaging","source":"preprints","abstract":"Abstract Neuroinflammation is a hallmark of numerous neurodegenerative, psychiatric, and chronic pain disorders and can be assessed in vivo with 18 kDa translocator protein (TSPO) positron emission tomography (PET). However, conventional quantification methods of TSPO PET are limited and often overlook the spatial relationships between regional signals. The application of network-based approaches to TSPO PET imaging may provide a novel framework to capture disease-specific neuroinflammatory patterns. To address this question, here we developed a data-driven, network-based approach to generate individual brain-wide TSPO PET matrices, employing Euclidean distance to quantify inter-regional pharmacokinetics similarity. We applied this approach to a large multicenter dataset of 528 PET scans utilizing three different TSPO tracers ([ 11 C]-PBR28, [ 18 F]-DPA714, [ 11 C]-PK11195), including healthy controls and patients with different diseases such as multiple sclerosis, traumatic brain injury, schizophrenia, depression, and chronic low back pain. Statistical modelling and machine learning classifiers were applied to evaluate the impact of experimental and biological factors on TSPO similarity patterns and to investigate their potential for capturing disease-specific signatures. TSPO similarity patterns demonstrated high biological specificity and reproducibility, with strong test-retest correlations (mean Spearman’s ρ = 0.84). Average precision of disease classification exceeded chance performance by 23–89% across conditions and was driven by condition-specific regional hubs whose topological distributions closely mirrored disease pathophysiology. This specificity was further supported by minimal overlap in feature importance values across conditions. Altogether, our findings show that network-based analysis of human TSPO PET data can detect disease-specific neuroinflammatory signatures. Such methodologies underscore the biological significance of TSPO PET and enhance its translational value, supporting precision medicine strategies for neuroinflammatory disorders.","url":"https://doi.org/10.21203/rs.3.rs-7887022/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7887022/v1","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.22541/au.164668806.60849882/v1","name":"Artificial Multisensory Neuron with Fused  Haptic and Temperature Perception for Multimodal In-Sensor Computing             ","source":"preprints","abstract":"","url":"https://doi.org/10.22541/au.164668806.60849882/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.22541/au.164668806.60849882/v1","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:28.407Z"},{"id":"doi:10.1101/2025.04.05.647237","name":"An engine for systematic discovery of cause-effect relationships between brain structure and function","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.04.05.647237","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.04.05.647237","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.443Z"},{"id":"doi:10.21203/rs.3.rs-5661668/v1","name":"The Berlin Bimanual Test for Stroke Survivors (BeBiT-S): Evaluating exoskeleton-assisted bimanual motor function after stroke","source":"preprints","abstract":"Abstract Background. Brain/neural hand exoskeletons (B/NHEs) can restore motor function after severe stroke, enabling bimanual tasks critical for various activities of daily living (ADL). Yet, reliable clinical tests for assessing bimanual function compatible with B/NHEs are lacking. Here, we introduce the Berlin Bimanual Test for Stroke (BeBiT-S), comprising 10 relevant bimanual tasks, and evaluate its psychometric properties as well as sensitivity to change related to B/NHE application. Methods. 24 stroke survivors (mean age 56.5 years, 9 female) with upper-limb hemiparesis after stroke underwent the BeBiT-S assessment (baseline). Psychometric properties were evaluated via interrater reliability (ICC) and construct validity (as measured by the correlation with the Chedoke Arm and Hand Activity Inventory, CAHAI). Sensitivity to change related to B/NHE application (intervention) was assessed across 15 stroke survivors (mean age 50.3 years, 5 female). Order of conditions (baseline vs. intervention) was randomized across participants. Results. BeBiT-S showed excellent interrater reliability at baseline (ICC = 0.985, P Conclusions. The BeBiT-S is a reliable and valid test for evaluating bimanual task performance in stroke survivors, and sensitive to assess B/NHE-related improvements in bimanual task performance. Trial registration: NCT04440709, submitted June 18 th , 2020","url":"https://doi.org/10.21203/rs.3.rs-5661668/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-5661668/v1","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.443Z"},{"id":"doi:10.1101/2025.04.15.648746","name":"Dissociating the functional role of the para-hippocampal and the parietal cortex in human multi-step reinforcement learning","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.04.15.648746","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.04.15.648746","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.443Z"},{"id":"doi:10.1101/2025.05.30.656545","name":"Spine-Prints: Transposing Brain Fingerprints to the Spinal Cord","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.05.30.656545","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.05.30.656545","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.443Z"},{"id":"doi:10.1101/2025.07.19.665666","name":"Mapping the visual cortex with Zebra noise and wavelets","source":"preprints","abstract":"Studies of the early visual system often require characterizing the visual preferences of large populations of neurons. This task typically requires multiple stimuli such as sparse noise and drifting gratings, each of which probe only a limited set of visual features. Here we introduce a new dynamic stimulus with sharp-edged stripes called Zebra noise and a new analysis model based on wavelets, and show that in combination they are highly efficient for mapping multiple aspects of the visual preferences of thousands of neurons. We used two-photon calcium imaging to record the activity of neurons in the mouse visual cortex. Zebra noise elicited strong re-sponses that were more repeatable than those evoked by traditional stimuli. The wavelet-based model captured the repeatable aspects of the resulting responses, providing measures of neuronal tuning for multiple stimulus features: position, orientation, size, spatial frequency, drift rate, and direction. The method proved efficient, requiring only 5 minutes of stimulus (re-peated 3 times) to characterize the tuning of thousands of neurons across visual areas. In combination, the Zebra noise stimulus and the wavelet-based model provide a broadly applicable toolkit for the rapid characterization of visual representations, promising to accelerate future studies of visual function.","url":"https://doi.org/10.1101/2025.07.19.665666","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.07.19.665666","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.443Z"},{"id":"doi:10.2139/ssrn.4140095","name":"A Survey on Prediction of COVID-19 Using Machine Learning","source":"preprints","abstract":"","url":"https://doi.org/10.2139/ssrn.4140095","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.2139/ssrn.4140095","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.21203/rs.3.rs-9901682/v1","name":"An Implantable Digital Bridge Enables Arm And Hand Movements After Tetraplegia","source":"preprints","abstract":"Abstract A cervical spinal cord injury disrupts the signals between the brain and the region of the spinal cord that coordinates arm and hand movements, causing paralysis. Here, we engineered a chronically implanted and durable Digital Bridge that reestablishes communication between the brain and cervical spinal cord. This technology consists of a brain implant to record electrocorticography from the sensorimotor cortex, and a neurostimulation platform to deliver epidural electrical stimulation over the entire cervical spinal cord unilaterally. We implanted this Digital Bridge in three individuals with chronic incomplete tetraplegia. We configured a library of stimulation patterns that supported gradual control over various elementary movements of the arm and hand. A decoding pipeline incorporating a foundation model of human brain activity predicted up to 8 motor states with high accuracy. In turn, linking decoding predictions to the modulation of stimulation patterns targeting the preprogrammed elementary movements enabled the three participants to perform functional tasks with their otherwise paralyzed arm and hand. The Digital Bridge has remained stable for more than one year, and has been compatible with long-term stability and safety. While additional technological developments and clinical validations in a diverse patient population are required, these results establish essential concepts to enable arm and hand movements in humans living with chronic tetraplegia.","url":"https://doi.org/10.21203/rs.3.rs-9901682/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-9901682/v1","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1101/2025.10.23.684150","name":"Dynamic and task-dependent decoding of the human attentional spotlight from MEG","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.10.23.684150","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.10.23.684150","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.443Z"},{"id":"doi:10.1101/2023.11.02.564776","name":"Transcranial ultrasound stimulation effect in the redundant and synergistic networks consistent across macaques","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.11.02.564776","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.11.02.564776","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:28.407Z"},{"id":"doi:10.21203/rs.3.rs-5938408/v1","name":"Reevaluating the Role of Education in Cognitive Decline and Brain Aging: Insights from Large-Scale Longitudinal Cohorts across 33 Countries","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-5938408/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-5938408/v1","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.443Z"},{"id":"doi:10.21203/rs.3.rs-6117495/v1","name":"Profiling brain morphology for autism spectrum disorder with two cross-culture large-scale consortia","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-6117495/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6117495/v1","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.443Z"},{"id":"doi:10.21203/rs.3.rs-198637/v1","name":"ANFIS-Net for Automatic Detection of COVID-19","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-198637/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.21203/rs.3.rs-198637/v1","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1101/2025.05.15.654238","name":"Personalized Whole-Brain Models of Seizure Propagation","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.05.15.654238","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.05.15.654238","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.443Z"},{"id":"doi:10.1101/2024.03.07.583842","name":"Predictive learning shapes the representational geometry of the human brain","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.03.07.583842","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.03.07.583842","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1101/2024.09.20.614119","name":"A neural mechanism for compositional structure transfer in humans","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.09.20.614119","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.09.20.614119","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1101/2025.08.20.25333478","name":"Subthalamic nucleus encoding steers adaptive therapies for gait in Parkinson’s disease","source":"preprints","abstract":"ABSTRACT Parkinson’s disease leads to a spectrum of cardinal motor symptoms and locomotor deficits that vary in severity with the nature of daily activities and the fluctuating physiology of patients. Many of these deficits remain inadequately addressed by existing therapies that use continuous, activity-agnostic parameters. Instead, adaptive therapies embedding activity-specific parameters have the potential to better address the entire range of symptoms. Here, we expose physiological principles that enable real-time decoding of ongoing locomotor activities across motor fluctuations from the neural dynamics of the subthalamic nucleus. This decoding steered activity-dependent adaptations of deep brain stimulation therapies that improved both cardinal motor symptoms and locomotor deficits across activities of daily living. Our decoding framework provides a blueprint for next-generation neuromodulation therapies that continuously adapt parameters to the behavioral context and fluctuating physiology of each patient. One Sentence Summary Neural decoders that leverage the physiological principles of activity-dependent encoding in the subthalamic nucleus support the implementation of adaptive deep brain stimulation therapies that alleviate locomotor deficits in people with Parkinson’s disease.","url":"https://doi.org/10.1101/2025.08.20.25333478","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.08.20.25333478","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.443Z"},{"id":"doi:10.21203/rs.3.rs-694178/v1","name":"Fuzzy Dynamic Parameter Adaptation in the Bird Swarm Algorithm for Neural Network Optimization","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-694178/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.21203/rs.3.rs-694178/v1","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:28.407Z"},{"id":"doi:10.1101/2021.02.11.21250832","name":"Modafinil for Wakefulness in the Critical Care Units: A Literature Review and Case Series including COVID-19 Patients at a Tertiary Care Saudi Hospital","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2021.02.11.21250832","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.1101/2021.02.11.21250832","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1101/2025.07.21.665958","name":"An image-based transcriptomics atlas reveals the regional and microbiota-dependent molecular, cellular, and spatial structure of the murine gut","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2025.07.21.665958","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1101/2025.07.21.665958","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.443Z"},{"id":"doi:10.1101/2024.04.29.591421","name":"Body size interacts with the structure of the central nervous system: A multi-center in vivo neuroimaging study","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.04.29.591421","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.04.29.591421","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.21203/rs.3.rs-1081043/v1","name":"The impact of AI implementation in higher education on educational process future: A systematic review","source":"preprints","abstract":"Abstract Artificial intelligence (AI) has been playing a vital role in all life domains. A striking example is AI effective revolution in health and educational services during the COVID-19 pandemic. Therefore, this systematic literature review investigates how AI impacts higher education (HE) by focusing on its impact on education quality, the learning and teaching process, assessments, and future careers. This review uses a systematic qualitative research method. The data is collected in a systematic review of academic articles on AI impact on HE from 1900 to 2021 from the Web of Science, Scopus, and ERIC. The process went through a systematic inclusion and exclusion procedure based on date, language, reported outcomes, setting and type of publications. Articles selected were screened via Rayyan Software and coded using excel based on the following themes: education quality, learning and teaching, assessments, future careers, and ethics. The total number of articles included is 56. The results vindicate that AI plays an efficient role in providing better education quality services, practical learning/teaching, and assessments approach for a better future career. Likewise, AI impacts future employment, which entails that HE institutions should incorporate more AI to have better graduates that meet the future market requirements. However, studies on AI impact assessments, ethics and future careers are limited and require further investigation.","url":"https://doi.org/10.21203/rs.3.rs-1081043/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.21203/rs.3.rs-1081043/v1","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.2139/ssrn.3633178","name":"Cerebral Micro-Structural Changes in COVID-19 Patients: An MRI-Based Preliminary Study","source":"preprints","abstract":"","url":"https://doi.org/10.2139/ssrn.3633178","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2020","doi":"10.2139/ssrn.3633178","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:28.407Z"},{"id":"doi:10.31234/osf.io/5dyfc","name":"COVID-19 Outbreak Prediction with Machine Learning","source":"preprints","abstract":"","url":"https://doi.org/10.31234/osf.io/5dyfc","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2020","doi":"10.31234/osf.io/5dyfc","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1101/2020.04.17.20070094","name":"COVID-19 Outbreak Prediction with Machine Learning","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2020.04.17.20070094","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2020","doi":"10.1101/2020.04.17.20070094","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:28.407Z"},{"id":"doi:10.20944/preprints202004.0311.v1","name":"COVID-19 Outbreak Prediction with Machine Learning","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202004.0311.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2020","doi":"10.20944/preprints202004.0311.v1","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:28.407Z"},{"id":"doi:10.21203/rs.3.rs-27130/v1","name":"COVID-19 Outbreak Prediction with Machine Learning","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-27130/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2020","doi":"10.21203/rs.3.rs-27130/v1","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.2139/ssrn.3580188","name":"COVID-19 Outbreak Prediction with Machine Learning","source":"preprints","abstract":"","url":"https://doi.org/10.2139/ssrn.3580188","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2020","doi":"10.2139/ssrn.3580188","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1101/2023.12.07.570537","name":"The NeuroML ecosystem for standardized multi-scale modeling in neuroscience","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2023.12.07.570537","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1101/2023.12.07.570537","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:28.407Z"},{"id":"doi:10.1101/2022.08.26.505408","name":"Variability in training unlocks generalization in visual perceptual learning through invariant representations","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.08.26.505408","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.08.26.505408","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.21203/rs.3.rs-985647/v1","name":"A Review on Potentials of Artificial Intelligence Approaches to Forecasting COVID-19 Spreading","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-985647/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.21203/rs.3.rs-985647/v1","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.21203/rs.3.rs-941929/v1","name":"How to Predict the Spread of COVID-19","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-941929/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.21203/rs.3.rs-941929/v1","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1101/2021.04.19.21255763","name":"COVID-Nets: Deep CNN Architectures for Detecting COVID-19 Using Chest CT Scans","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2021.04.19.21255763","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.1101/2021.04.19.21255763","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:28.407Z"},{"id":"doi:10.1101/2022.07.12.499688","name":"Mapping Pharmacologically-induced Functional Reorganisation onto the Brain’s Neurotransmitter Landscape","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2022.07.12.499688","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1101/2022.07.12.499688","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1101/2020.07.24.20161307","name":"Employing a Systematic Approach to Biobanking and Analyzing Clinical and Genetic Data for Advancing COVID-19 Research","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2020.07.24.20161307","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2020","doi":"10.1101/2020.07.24.20161307","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.21203/rs.3.rs-30432/v1","name":"Artificial intelligence techniques for Containment COVID-19 Pandemic: A Systematic Review","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-30432/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2020","doi":"10.21203/rs.3.rs-30432/v1","addedAt":"2026-09-01T01:48:27.542Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1016/j.asoc.2022.109840","name":"A balanced-quantum inspired evolutionary algorithm for solving disassembly line balancing problem","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2022.109840","authors":["Rakshit Kumar Singh","Amit Raj Singh","Ravindra Kumar Yadav"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-29T03:05:22Z","doi":"10.1016/j.asoc.2022.109840","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-3-319-28031-8_13","name":"Ensemble of Flexible Neural Trees for Predicting Risk in Grid Computing Environment","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-28031-8_13","authors":["Sara Abdelwahab","Varun Kumar Ojha","Ajith Abraham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-14T01:02:33Z","doi":"10.1007/978-3-319-28031-8_13","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1201/9781003513889","name":"Bioinspired Materials Surfaces","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003513889","authors":["Yongmei Zheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-23T13:52:17Z","doi":"10.1201/9781003513889","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1109/nigercon62786.2024.10927379","name":"Development of a Stochastic Gradient Descent-Based Neuro Model For Identifying Fraudulent Transactions","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nigercon62786.2024.10927379","authors":["Ogunlade Michael Adegoke","Adedayo Olukayode Ojo","Babatunde Segun Adejumobi","Saheed Lekan Gbadamosi","Ibitoye Oladapo Tolulope","Ogbodo Nathaniel Imonion"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-24T17:55:09Z","doi":"10.1109/nigercon62786.2024.10927379","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1109/cosmic63293.2024.10871487","name":"Neuro-Insights: Unveiling the Power of Deep Learning for Brain Tumor Detection in Neuroimaging","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cosmic63293.2024.10871487","authors":["V. KESHAVA REDDY","Kotte Sai Dhanush Reddy","Bobbili Sai Jayanth","Guru Prasad M S","Aditi Joshi","Shradha Vatsyayan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-12T18:17:51Z","doi":"10.1109/cosmic63293.2024.10871487","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1007/978-981-33-6862-0_63","name":"A Critical Review of the Intelligent Computing Methods for the Identification of the Sleeping Disorders","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-33-6862-0_63","authors":["Anandakumar Haldorai","Arulmurugan Ramu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-06-14T05:02:45Z","doi":"10.1007/978-981-33-6862-0_63","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1016/j.imavis.2021.104214","name":"LSTM with bio inspired algorithm for action recognition in sports videos","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.imavis.2021.104214","authors":["Jun Chen","R. Dinesh Jackson Samuel","Parthasarathy Poovendran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-05-19T00:15:44Z","doi":"10.1016/j.imavis.2021.104214","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-981-97-2275-4_3","name":"A Two-Level Game-Theoretic Approach for Joint Pricing and Resource Allocation in Multi-user Mobile Edge Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-2275-4_3","authors":["Erqian Ge","Hao Tian","Wanyue Hu","Fei Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-15T19:02:10Z","doi":"10.1007/978-981-97-2275-4_3","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1007/978-3-7908-1902-1_99","name":"Formal Neuro-Immune Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-7908-1902-1_99","authors":["Alexander Tarakanov","Georgy Penev","Kurosh Madani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-03-11T00:11:40Z","doi":"10.1007/978-3-7908-1902-1_99","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-981-97-2275-4_8","name":"Sequence-Based Deep Reinforcement Learning for Task Offloading in Mobile Edge Computing: A Comparison Study","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-2275-4_8","authors":["Xiang-Jie Xiao","Yong Wang","Kezhi Wang","Pei-Qiu Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-15T19:02:10Z","doi":"10.1007/978-981-97-2275-4_8","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1016/j.suscom.2022.100806","name":"A new fuzzy-based method for energy-aware resource allocation in vehicular cloud computing using a nature-inspired algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.suscom.2022.100806","authors":["Can Li","Xiaode Zuo","Amin Salih Mohammed"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-19T16:53:21Z","doi":"10.1016/j.suscom.2022.100806","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1109/icccnt61001.2024.10725950","name":"Integration of Adaptive Neuro-Fuzzy Systems in Mobile Commerce Strategy: Enhancing Customer Relationship Management through Personalized Recommendations","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icccnt61001.2024.10725950","authors":["Ravindra Changala","Mohd Aarif","Brinda Halambi","Machhindranath M Dhane","Vuda Sreenivasa Rao","I Infant Raj"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-04T23:06:46Z","doi":"10.1109/icccnt61001.2024.10725950","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1016/b978-0-443-18508-3.09992-7","name":"About the editors","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-18508-3.09992-7","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-05T04:32:06Z","doi":"10.1016/b978-0-443-18508-3.09992-7","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1007/978-3-540-92191-2_22","name":"Biologically Inspired Approaches to Networks: The Bio-Networking Architecture and the Molecular Communication","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-540-92191-2_22","authors":["Tatsuya Suda","Tadashi Nakano","Michael Moore","Akhiro Enomoto","Keita Fujii"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-11-26T21:08:36Z","doi":"10.1007/978-3-540-92191-2_22","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/978-3-642-24553-4_29","name":"A Hybrid Quantum-Inspired Particle Swarm Evolution Algorithm and SQP Method for Large-Scale Economic Dispatch Problems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-24553-4_29","authors":["Qun Niu","Zhuo Zhou","Tingting Zeng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-01-03T09:49:00Z","doi":"10.1007/978-3-642-24553-4_29","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1016/j.asoc.2010.11.011","name":"A recurrent neuro-fuzzy system and its application in inferential sensing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2010.11.011","authors":["S. Jassar","Z. Liao","L. Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-11-25T09:48:02Z","doi":"10.1016/j.asoc.2010.11.011","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1109/nice69539.2026.11567520","name":"NEUKRAG: Neuromorphic KG-RAG with Small LLMS for Hardware-Algorithm Co-Design","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nice69539.2026.11567520","authors":["Ramakrishnan Kannan","Ashish Gautam","Robert Patton","Nicholas D Haas","Todd Thomas","James B. Aimone","Thomas Potok"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-22T19:52:43Z","doi":"10.1109/nice69539.2026.11567520","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/icccnt61001.2024.10725074","name":"A Neuro-Wave Controlled Wheelchair Combined with Gesture and Voice Control","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icccnt61001.2024.10725074","authors":["Md. Saidur Rahman","Md. Shakabul Islam Sourav","Md. Asaduzzaman Sarker","K. M. Rumman","Md Saiful Islam Sajol","Md. Shoriful Islam Shovon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-04T23:06:46Z","doi":"10.1109/icccnt61001.2024.10725074","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1016/j.asoc.2012.11.019","name":"Wavelet based Neuro-Detector for low frequencies of vibration signals in electric motors","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2012.11.019","authors":["Duygu Bayram","Serhat Şeker"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-12-11T01:33:28Z","doi":"10.1016/j.asoc.2012.11.019","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/978-3-030-16681-6_36","name":"Development of an Innovative Mobile Phone-Based Newborn Care Training Application","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-16681-6_36","authors":["Sherri Bucher","Elizabeth Meyers","Bhavani Singh Agnikula Kshatriya","Prem Chand Avanigadda","Saptarshi Purkayastha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-22T21:26:26Z","doi":"10.1007/978-3-030-16681-6_36","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/978-3-540-92191-2_19","name":"Bio-Inspired Multi-agent Collaboration for Urban Monitoring Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-540-92191-2_19","authors":["Uichin Lee","Eugenio Magistretti","Mario Gerla","Paolo Bellavista","Pietro Liò","Kang-Won Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-11-26T16:08:36Z","doi":"10.1007/978-3-540-92191-2_19","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/978-981-10-7179-9_3","name":"An Approach to the Bio-Inspired Control of Self-reconfigurable Robots","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-10-7179-9_3","authors":["Dongyang Bie","Miguel A. Gutiérrez-Naranjo","Jie Zhao","Yanhe Zhu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-11-08T04:53:32Z","doi":"10.1007/978-981-10-7179-9_3","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-030-16681-6_17","name":"A Theoretical Approach Towards Optimizing the Movement of Catom Clusters in Micro Robotics Based on the Foraging Behaviour of Honey Bees","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-16681-6_17","authors":["K. C. Jithin","Syam Sankar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-22T21:26:26Z","doi":"10.1007/978-3-030-16681-6_17","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.4018/978-1-7998-8561-0.ch003","name":"Nature-Inspired Algorithm Applied to a Renewable Energy-Integrating Hydro-Thermal Power Plant","source":"crossref","abstract":"Due to the rising requirement on energy sources and the global doubts for using fossil fuel because of its consequences on the climate changes and the global warming caused by hazardous gases, the scientific research has shifted to the renewable energy. To minimize the usage of thermal power generation plants and to meet the rising load demand, a thermal-integrated wind-hydro-system is taking an important role in renewable power systems. A proficient nature-inspired optimization is proposed for solving economic and emission dispatch for the hydro-thermal-wind (HTW) scheduling problem. Further, the opposition-based learning have been incorporated with the chemical reaction optimization for improving the performance of the algorithm. To investigate the performance of oppositional chemical reaction optimization algorithm, the algorithm is tested on two different cases. Along with this, some statistical tests have also been performed. The results obtained by the OCRO algorithm are compared with other recently proposed methods to establish its robustness.","url":"https://doi.org/10.4018/978-1-7998-8561-0.ch003","authors":["Sunanda Hazra","Provas Kumar Roy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-08T08:09:33Z","doi":"10.4018/978-1-7998-8561-0.ch003","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1109/trustcom.2012.40","name":"A Multi-agent Immunologically-inspired Model for Critical Information Infrastructure Protection -- An Immunologically-inspired Conceptual Model for Security on the Power Grid","source":"crossref","abstract":"","url":"https://doi.org/10.1109/trustcom.2012.40","authors":["S.M.A. Mavee","E.M. Ehlers"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-09-11T22:46:34Z","doi":"10.1109/trustcom.2012.40","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.4018/978-1-7998-1626-3.ch001","name":"Impact of Nature-Inspired Algorithms on Localization Algorithms in Wireless Sensor Networks","source":"crossref","abstract":"In wireless sensor networks, localization is one of the essential requirements. Most applications are of no use, if location information is not available. Based on cost, localization algorithms can be divided into two categories, namely range-based and range-free. Range-free are cost-effective, but they lack accuracy. In this chapter, the role of nature-inspired algorithms in enhancing the accuracy of range-free algorithms has been investigated. Inferences drawn from exhaustive literature survey of recent research in this area establishes the importance of these algorithms in sensor localization.","url":"https://doi.org/10.4018/978-1-7998-1626-3.ch001","authors":["Amanpreet Kaur","Govind P. Gupta","Sangeeta Mittal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-10-25T12:01:11Z","doi":"10.4018/978-1-7998-1626-3.ch001","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1063/10.0025436","name":"Lotus-inspired design to neutralize the coffee-ring effect","source":"crossref","abstract":"Microwells with gradually slopped walls enabled uniform particle deposition and distribution.","url":"https://doi.org/10.1063/10.0025436","authors":["Maura Shapiro"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T11:38:20Z","doi":"10.1063/10.0025436","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1007/978-3-642-32711-7_12","name":"A Biologically-Inspired Model for Recognition of Overlapped Patterns","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-32711-7_12","authors":["Mohammad Saifullah"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-08-10T12:17:23Z","doi":"10.1007/978-3-642-32711-7_12","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1109/icicr65456.2025.00153","name":"BioRWKV: RWKV Large Model Inspired by Biological Brain Inspired","source":"crossref","abstract":"BioRWKV aims to enhance the biological plausibility and efficiency of artificial intelligence systems by developing a novel large-scale Spiking Neural Network (SNN) architecture inspired by principles from biological neural systems. This research integrates Leaky Integrate-and-Fire (LIF) neuron activation layers, event-driven temporal encoding mechanisms, and Spike-Timing-Dependent Plasticity (STDP) learning rules into the model, effectively simulating synaptic plasticity in the brain. Additionally, the extended BioViRWKV model incorporates patch embedding and positional encoding to improve visual data processing capabilities. The results demonstrate that BioRWKV significantly enhances the processing of temporal sequence data and offers new perspectives for multimodal learning tasks. These advancements mark a significant step toward developing more efficient and biologically inspired AI systems, with potential applications in intelligent sensing, robotic vision, and biomedical signal processing.","url":"https://doi.org/10.1109/icicr65456.2025.00153","authors":["Xin Liu","Yiwen Zhang","Lei Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-29T17:50:58Z","doi":"10.1109/icicr65456.2025.00153","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.4018/978-1-7998-1626-3.ch004","name":"Nature-Inspired-Based PTS for PAPR Reduction in OFDM Systems","source":"crossref","abstract":"OFDM is widely used in high data rate applications due to its ability to mitigate frequency selectivity. However, OFDM suffers from high PAPR problem. This degrades the system performance. PTS is a promising PAPR reduction technique. However, its computational complexity is large; to reduce it, different suboptimal solution (heuristics) were presented in literature. Heuristics PTS algorithms can be categorized into descent-heuristics and metaheuristics. In this chapter, descent-heuristics-based PTS and metaheuristics-based PTS are compared. Results showed that RS-PTS is the best one among descent-heuristics algorithms. Metaheuristics algorithms can also be classified into single solution-based methods and nature-inspired methods. Among metaheuristics algorithms, two natural inspired algorithms and one single solution-based methods, namely PSO, ABC, and SA, were selected to be compared with descent-heuristics algorithms. Results showed that PTS based on nature-inspired methods is better than PTS based on descent heuristics and PTS based on single-solution metaheuristics method.","url":"https://doi.org/10.4018/978-1-7998-1626-3.ch004","authors":["Mohamed Mounir","Mohamed Bakry El Mashade","Gurjot Singh Gaba"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-10-25T12:01:11Z","doi":"10.4018/978-1-7998-1626-3.ch004","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.3390/e27080811","name":"Deep Reinforcement Learning-Based Resource Allocation for UAV-GAP Downlink Cooperative NOMA in IIoT Systems","source":"crossref","abstract":"This paper studies deep reinforcement learning (DRL)-based joint resource allocation and three-dimensional (3D) trajectory optimization for unmanned aerial vehicle (UAV)–ground access point (GAP) cooperative non-orthogonal multiple access (NOMA) communication in Industrial Internet of Things (IIoT) systems. Cooperative and non-cooperative users adopt different signal transmission strategies to meet diverse, task-oriented, quality-of-service requirements. Specifically, the DRL framework based on the Soft Actor–Critic algorithm is proposed to jointly optimize user scheduling, power allocation, and UAV trajectory in continuous action spaces. Closed-form power allocation and maximum weight bipartite matching are integrated to enable efficient user pairing and resource management. Simulation results show that the proposed scheme significantly enhances system performance in terms of throughput, spectral efficiency, and interference management, while enabling robustness against channel uncertainties in dynamic IIoT environments. The findings indicate that combining model-free reinforcement learning with conventional optimization provides a viable solution for adaptive resource management in dynamic UAV-GAP cooperative communication scenarios.","url":"https://doi.org/10.3390/e27080811","authors":["Yuanyan Huang","Jingjing Su","Xuan Lu","Shoulin Huang","Hongyan Zhu","Haiyong Zeng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-29T09:31:45Z","doi":"10.3390/e27080811","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1007/978-3-540-88079-0_14","name":"Air Quality Forecaster: Moving Window Based Neuro Models","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-540-88079-0_14","authors":["S. V. Barai","A. K. Gupta","Jayachandar Kodali"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-01-05T16:15:11Z","doi":"10.1007/978-3-540-88079-0_14","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1109/nice69539.2026.11567479","name":"Multi-Timescale Conductance Spiking Networks: A Sparse, Gradient-Trainable Framework with Rich Firing Dynamics for Enhanced Temporal Processing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nice69539.2026.11567479","authors":["Alex Fulleda-Garcia","Saray Soldado-Magraner","Josep Maria Margarit-Taulé"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-22T19:52:43Z","doi":"10.1109/nice69539.2026.11567479","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1145/1315843.1315880","name":"Biologically inspired self-governance and self-organisation for autonomic networks","source":"crossref","abstract":"","url":"https://doi.org/10.1145/1315843.1315880","authors":["Sasitharan Balasubramaniam","Dmitri Botvich","William Donnelly","Mícheál Ó Foghlú","John Strassner"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-11-15T14:30:20Z","doi":"10.1145/1315843.1315880","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1145/3584954.3584994","name":"Exploring Information-Theoretic Criteria to Accelerate the Tuning of Neuromorphic Level-Crossing ADCs","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3584954.3584994","authors":["Ali Safa","Jonah Van Assche","Charlotte Frenkel","Andre Bourdoux","Francky Catthoor","Georges Gielen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-12T13:27:54Z","doi":"10.1145/3584954.3584994","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-981-10-6747-1_3","name":"Relevance Feedback Base User Convenient Semantic Query Processing Using Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-10-6747-1_3","authors":["P. Mohan Kumar","B. Balamurugan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-10-04T04:25:22Z","doi":"10.1007/978-981-10-6747-1_3","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1016/b978-0-443-18508-3.09998-8","name":"Front Matter","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-18508-3.09998-8","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-05T04:32:23Z","doi":"10.1016/b978-0-443-18508-3.09998-8","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1016/j.asoc.2014.02.008","name":"Fault detection and diagnosis of pneumatic valve using Adaptive Neuro-Fuzzy Inference System approach","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2014.02.008","authors":["P. Subbaraj","B. Kannapiran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-02-19T20:30:42Z","doi":"10.1016/j.asoc.2014.02.008","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-030-49339-4_38","name":"A Machine Learning Prediction of Automatic Text Based Assessment for Open and Distance Learning: A Review","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-49339-4_38","authors":["Guembe Blessing","Ambrose Azeta","Sanjay Misra","Felix Chigozie","Ravin Ahuja"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-05T11:05:14Z","doi":"10.1007/978-3-030-49339-4_38","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-030-16681-6_48","name":"Diagnosing Oral Ulcers with Bayes Model","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-16681-6_48","authors":["Nureni Ayofe Azeez","Samuel O. Oyeniran","Charles Van der Vyver","Sanjay Misra","Ravin Ahuja","Robertas Damasevicius","Rytis Maskeliunas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-22T17:26:26Z","doi":"10.1007/978-3-030-16681-6_48","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-030-41862-5_141","name":"Segmentation Techniques Using Soft Computing Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-41862-5_141","authors":["Sudha Tiwari","S. M. Ghosh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-27T14:02:38Z","doi":"10.1007/978-3-030-41862-5_141","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/s00500-003-0313-z","name":"Intelligent control of a stepping motor drive using a hybrid neuro-fuzzy approach","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00500-003-0313-z","authors":["P. Melin","O. Castillo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2004-03-20T10:51:46Z","doi":"10.1007/s00500-003-0313-z","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1016/j.asoc.2014.03.001","name":"Neuro-fuzzy techniques to optimize an FPGA embedded controller for robot navigation","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2014.03.001","authors":["Iluminada Baturone","Andrés Gersnoviez","Ángel Barriga"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-03-26T14:25:43Z","doi":"10.1016/j.asoc.2014.03.001","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/s00607-025-01527-7","name":"Empowering cloud providers: optimised locust-inspired algorithm for SLA violation mitigation in green cloud computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00607-025-01527-7","authors":["Yousef A. Alsaaidah","Abdullah Muhammed","Mohammed Alaa Ala’anzy","Mohamed Othman","Azizol Abdullah"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-23T04:29:56Z","doi":"10.1007/s00607-025-01527-7","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/978-981-33-6773-9_4","name":"Modified Artificial Bee Colony Algorithm for Sizing Optimization of Truss Structures","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-33-6773-9_4","authors":["Sadik Ozgur Degertekin","Luciano Lamberti","Mehmet Sedat Hayalioglu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-31T12:03:02Z","doi":"10.1007/978-981-33-6773-9_4","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/s00500-023-09194-6","name":"Optimal design of adaptive neuro-fuzzy inference system using PSO and ant colony optimization for estimation of uncertain observed values","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00500-023-09194-6","authors":["Mahdi Danesh","Sedigheh Danesh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-15T06:01:21Z","doi":"10.1007/s00500-023-09194-6","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1007/978-3-030-49339-4_9","name":"Decision Forest Classifier with Flower Search Optimization Algorithm for Efficient Detection of BHP Flooding Attacks in Optical Burst Switching Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-49339-4_9","authors":["Mrutyunjaya Panda","Niketa Gandhi","Ajith Abraham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-05T11:05:14Z","doi":"10.1007/978-3-030-49339-4_9","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-319-01781-5_17","name":"Multi-class SVM Based Classification Approach for Tomato Ripeness","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-01781-5_17","authors":["Esraa Elhariri","Nashwa El-Bendary","Mohamed Mostafa M. Fouad","Jan Platoš","Aboul Ella Hassanien","Ahmed M. M. Hussein"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-08-01T11:21:05Z","doi":"10.1007/978-3-319-01781-5_17","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/s00422-020-00828-8","name":"EO-MTRNN: evolutionary optimization of hyperparameters for a neuro-inspired computational model of spatiotemporal learning","source":"crossref","abstract":"Abstract For spatiotemporal learning with neural networks, hyperparameters are often set manually by a human expert. This is especially the case with multiple timescale networks that require a careful setting of the values of timescales in order to learn spatiotemporal data. However, this implies a cumbersome trial-and-error process until suitable parameters are found and it reduces the long-term autonomy of artificial agents, such as robots that are controlled by multiple timescale networks. To solve the problem, we propose the evolutionary optimized multiple timescale recurrent neural network ( EO-MTRNN ) that is inspired by the neural plasticity of the human cortex. Our proposed network uses a method of evolutionary optimization to adjust its timescales and to rewire itself in terms of number of neurons and synapses. Moreover, it does not require additional neural networks for pre- and postprocessing input–output data. We validate our EO-MTRNN by applying it to a proposed benchmark training dataset with single and multiple sequence training cases, as well as by applying it to sensory-motor data from a robot. We compare different configuration modes of the network, and we compare the learning performance between a network configuration with manually set hyperparameters and a configuration with automatically estimated hyperparameters. The results show that automatically estimated hyperparameters yield approximately 43% better performance than manually estimated ones, without overfitting the given teaching data. We also validate the generalization ability by successfully learning data that were not included in the hyperparameter estimation process.","url":"https://doi.org/10.1007/s00422-020-00828-8","authors":["Erhard Wieser","Gordon Cheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-03-17T18:11:13Z","doi":"10.1007/s00422-020-00828-8","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.4018/978-1-7998-9534-3.ch006","name":"Parkinson's Disease","source":"crossref","abstract":"Parkinson's disease is a neurodegenerative disorder characterized by severe cognitive impairments. This is a condition of degeneration of substantia nigra of basal ganglia. Parkinsonism adversely influences the mental health of the person too. Parkinson's disease was first described in 1817 by James Parkinson. Parkinsonism patients may get severe complications like cognitive deficiency, which include loss of memory, attention difficulties, visual abnormalities, slow thinking, problems with word finding, and motor symptoms. Symptoms of this disease range from Parkinson's disease mild cognitive impairment (PD-MCI) to Parkinson's disease dementia (PDD). The primary motor symptoms are trembling in hands, arms, legs, jaw, and face; rigidity or stiffness of the limbs and trunk; slowness of movement; postural instability; and impaired balance and coordination. Studies on treatments of Parkinson's disease are progressing to prevent complications and sustain the normal functions of patients.","url":"https://doi.org/10.4018/978-1-7998-9534-3.ch006","authors":["Soumya Jacob P."],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-21T13:32:03Z","doi":"10.4018/978-1-7998-9534-3.ch006","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1093/neuonc/noae043","name":"Harnessing generative AI for glioma diagnosis: A step forward in neuro-oncologic imaging","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuonc/noae043","authors":["Matthew D Lee","Rajan Jain"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-01T22:52:48Z","doi":"10.1093/neuonc/noae043","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1007/978-981-15-1842-3_6","name":"Mobile Robot Path Planning Using a Flower Pollination Algorithm-Based Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-15-1842-3_6","authors":["Atul Mishra","Sankha Deb"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-02-19T10:02:35Z","doi":"10.1007/978-981-15-1842-3_6","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/3-540-45723-2_87","name":"Hybrid Framework for Neuro-Dynamic Programming Application to Water Supply Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/3-540-45723-2_87","authors":["M. Damas","M. Salmerón","J. Ortega","G. Olivares"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-02-11T14:39:51Z","doi":"10.1007/3-540-45723-2_87","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1109/cit/iucc/dasc/picom.2015.218","name":"Inspired Counter Based Broadcasting for Dynamic Source Routing in Mobile Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cit/iucc/dasc/picom.2015.218","authors":["Muneer Bani Yassein","Ahmed Y. Al-Dubai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-28T21:32:48Z","doi":"10.1109/cit/iucc/dasc/picom.2015.218","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-031-78943-4_9","name":"SportsKBGen Framework: Knowledge Base Generation for Sports as a Prospective Domain","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78943-4_9","authors":["Anamaya Vyas","Gerard Deepak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-03T11:08:11Z","doi":"10.1007/978-3-031-78943-4_9","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/978-3-031-27499-2_62","name":"Virtual Reality, Augmented Reality and Mixed Reality for Teaching and Learning in Higher Education","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_62","authors":["Anne Lin","Tendani Mawela"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_62","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-030-96299-9_45","name":"Demography of Machine Learning Education Within the K12","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_45","authors":["Kehinde Aruleba","Oluwaseun Alexander Dada","Ibomoiye Domor Mienye","George Obaido"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_45","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1016/b978-0-443-15663-2.09993-4","name":"Index","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-15663-2.09993-4","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-09T07:40:06Z","doi":"10.1016/b978-0-443-15663-2.09993-4","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1007/978-981-33-6773-9_12","name":"Metaheuristic-Based Structural Control Methods and Comparison of Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-33-6773-9_12","authors":["Serdar Ulusoy","Aylin Ece Kayabekir","Sinan Melih Nigdeli","Gebrail Bekdaş"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-31T12:03:02Z","doi":"10.1007/978-981-33-6773-9_12","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1109/icih67754.2025.11609021","name":"Evaluating Quantum-Inspired Algorithms for Data Security in Edge Computing: A Comparative Study of Traditional Cryptographic Techniques vs. Quantum-Inspired Approaches","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icih67754.2025.11609021","authors":["Loganathan S","Jayaprakash M"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-22T19:17:52Z","doi":"10.1109/icih67754.2025.11609021","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.4108/icst.bionetics2008.4728","name":"Review of Trust and Machine Ethics Research: Towards A Bio-Inspired Computational Model of Ethical Trust (CMET)","source":"crossref","abstract":"","url":"https://doi.org/10.4108/icst.bionetics2008.4728","authors":["Hock Chuan Lim","Rob Stocker","Henry Larkin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-02-19T13:40:18Z","doi":"10.4108/icst.bionetics2008.4728","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1049/pbpc053e_ch2","name":"Nature-inspired optimization algorithm: an in-depth view","source":"crossref","abstract":"","url":"https://doi.org/10.1049/pbpc053e_ch2","authors":["Ankit Gambhir","Ajit Kumar Verma","Ashish Payal","Rajeev Kumar Arya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-16T08:07:55Z","doi":"10.1049/pbpc053e_ch2","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-642-34274-5_5","name":"Biological Fluctuation “Yuragi” as the Principle of Bio-inspired Robots","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-34274-5_5","authors":["Hiroshi Ishiguro"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-09-30T13:21:47Z","doi":"10.1007/978-3-642-34274-5_5","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1109/ibica.2012.58","name":"A Bio-inspired Optimization Algorithm for Modeling the Dynamics of Biological Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ibica.2012.58","authors":["Jiann-Horng Lin","Chao-Wei Chou","Chorng-Horng Yang","Hsien-Leing Tsai","I-Ho Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-10-26T21:47:27Z","doi":"10.1109/ibica.2012.58","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1016/j.eswa.2012.01.028","name":"A novel brain-inspired neuro-fuzzy hybrid system for artificial ventilation modeling","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.eswa.2012.01.028","authors":["G.S. Ng","F. Liu","T.F. Loh","C. Quek"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-03-07T12:01:06Z","doi":"10.1016/j.eswa.2012.01.028","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-031-78937-3_5","name":"A Review of Machine Learning Techniques for Epileptic Seizure Prediction","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_5","authors":["Akshita Modi","Anu Bajaj","Vikas Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:05:58Z","doi":"10.1007/978-3-031-78937-3_5","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/978-3-031-78946-5_32","name":"Predicting Heart Diseases Using Machine Learning Algorithms: A Survey","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_32","authors":["Isha Gupta","Anu Bajaj","Vikas Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:03:59Z","doi":"10.1007/978-3-031-78946-5_32","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/978-981-96-0706-8_6","name":"Use of Neural Networks to Model an Inventory System as a Family of Industrial Belts Within the Supply Chain","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-96-0706-8_6","authors":["Heredia-Roldán Miguel Josué","Báez Sentíes Oscar","Gurruchaga-Rodríguez María Eloisa","Betanzo Torres Erick Arturo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-19T13:37:25Z","doi":"10.1007/978-981-96-0706-8_6","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/978-3-030-96299-9_77","name":"Estimation Techniques for Scrum: A Qualitative Systematic Study","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_77","authors":["Diaz Jorge-Martinez","Sanjay Misra","Shariq Aziz Butt","Foluso Ayeni"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_77","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-031-78940-3_5","name":"Pseudo-learning to Identify Prototype Networks for Interpreting Multi-layered Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78940-3_5","authors":["Ryotaro Kamimura"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-05T06:07:42Z","doi":"10.1007/978-3-031-78940-3_5","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/978-3-031-27499-2_3","name":"Cross Synergetic Mobilenet-VGG16 for UML Multiclass Diagrams Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_3","authors":["Nesrine Bnouni Rhim","Salim Cheballah","Mouna Ben Mabrouk"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_3","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1504/ijbic.2017.083127","name":"Bio-inspired parallel computing of representative geometrical objects of holes of binary 2D-images","source":"crossref","abstract":"","url":"https://doi.org/10.1504/ijbic.2017.083127","authors":["Daniel Díaz Pernil","Ainhoa Berciano","Francisco Peña Cantillana","Miguel A. Gutiérrez Naranjo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-03-22T14:11:37Z","doi":"10.1504/ijbic.2017.083127","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-981-16-3128-3_12","name":"Evolutionary Machine Learning Powered by Genetics Algorithm for IoT-Specific Health Monitoring of Agriculture Vehicles","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-16-3128-3_12","authors":["Neeraj Gupta","Saurabh Gupta","Nilesh Patel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-18T23:09:33Z","doi":"10.1007/978-981-16-3128-3_12","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-981-33-6773-9_7","name":"The Design of Trapezoidal Corrugated Web Beams Using Firefly Method","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-33-6773-9_7","authors":["Ferhat Erdal","Osman Tunca","Erkan Dogan","Ramazan Ozcelik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-31T12:03:02Z","doi":"10.1007/978-981-33-6773-9_7","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1016/b978-0-443-18508-3.00002-4","name":"Medical image analysis steps: Medical image acquisition to classification (or regression) in neuro-oncology","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-18508-3.00002-4","authors":["Suchismita Das","Meghna","Sanjay Saxena"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-05T04:30:59Z","doi":"10.1016/b978-0-443-18508-3.00002-4","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1093/neuonc/noae039","name":"Celebrating the 30th Anniversary of the European Association of Neuro-Oncology","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuonc/noae039","authors":["Matthias Preusser","Michael Platten","Susan C Short"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-02T18:44:54Z","doi":"10.1093/neuonc/noae039","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1016/j.asoc.2013.10.014","name":"Applications of neuro fuzzy systems: A brief review and future outline","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2013.10.014","authors":["Samarjit Kar","Sujit Das","Pijush Kanti Ghosh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-11-12T23:37:33Z","doi":"10.1016/j.asoc.2013.10.014","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1109/bic-ta.2011.66","name":"Apical Growth Filamentous and Branching PC Grammar Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bic-ta.2011.66","authors":["J.D. Emerald"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-10-18T15:35:51Z","doi":"10.1109/bic-ta.2011.66","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1109/bimnics.2006.361823","name":"Overlay Network Symbiosis: Evolution and Cooperation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bimnics.2006.361823","authors":["Naoki Wakamiya","Masayuki Murata"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-06-07T15:56:37Z","doi":"10.1109/bimnics.2006.361823","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1103/physrevapplied.23.030001","name":"Editorial: Introducing the Collection on Physics-Inspired Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1103/physrevapplied.23.030001","authors":["Kerem Y. Camsari","Supriyo Datta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-14T10:08:54Z","doi":"10.1103/physrevapplied.23.030001","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1049/pbpc053e_bm","name":"Back Matter","source":"crossref","abstract":"","url":"https://doi.org/10.1049/pbpc053e_bm","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-16T08:07:55Z","doi":"10.1049/pbpc053e_bm","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1201/9781003322931","name":"Bio-Inspired Optimization in Fog and Edge Computing Environments","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003322931","authors":["Punit Gupta","Dinesh Kumar Saini","Pradeep Rawat","Kashif Zia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-24T13:39:16Z","doi":"10.1201/9781003322931","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.4018/978-1-5225-0788-8.ch064","name":"Prediction of International Stock Markets Based on Hybrid Intelligent Systems","source":"crossref","abstract":"This paper compares the accuracy of three hybrid intelligent systems in forecasting ten international stock market indices; namely the CAC40, DAX, FTSE, Hang Seng, KOSPI, NASDAQ, NIKKEI, S&amp;P500, Taiwan stock market price index, and the Canadian TSE. In particular, genetic algorithms (GA) are used to optimize the topology and parameters of the adaptive time delay neural networks (ATNN) and the time delay neural networks (TDNN). The third intelligent system is the adaptive neuro-fuzzy inference system (ANFIS) that basically integrates fuzzy logic into the artificial neural network (ANN) to better model information and explain decision making process. Based on out-of-sample simulation results, it was found that contrary to the literature GA-TDNN significantly outperforms GA-ATDNN. In addition, ANFIS was found to be more effective in forecasting CAC40, FTSE, Hang Seng, NIKKEI, Taiwan, and TSE price level. In contrary, GA-TDNN and GA-ATDNN were found to be superior to ANFIS in predicting DAX, KOSPI, and NASDAQ future prices.","url":"https://doi.org/10.4018/978-1-5225-0788-8.ch064","authors":["Salim Lahmiri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-07-26T12:16:44Z","doi":"10.4018/978-1-5225-0788-8.ch064","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.4018/978-1-5225-0788-8.ch014","name":"Developmental Swarm Intelligence","source":"crossref","abstract":"In this article, the necessity of having developmental learning embedded in a swarm intelligence algorithm is confirmed by briefly considering brain evolution, brain development, brainstorming process, etc. Several swarm intelligence algorithms are looked at from developmental learning perspective. Finally, a framework of a developmental swarm intelligence algorithm is given to help understand developmental swarm intelligence algorithms, and to guide to design and/or implement any new developmental swarm intelligence algorithm and/or any developmental evolutionary algorithm.","url":"https://doi.org/10.4018/978-1-5225-0788-8.ch014","authors":["Yuhui Shi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-07-26T12:16:44Z","doi":"10.4018/978-1-5225-0788-8.ch014","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1201/9781003485803-1","name":"A Biologically Inspired Model for Perception of Flicker Wheel Illusion","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003485803-1","authors":["Keerthi S Chandran","Kuntal Ghosh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-27T21:19:39Z","doi":"10.1201/9781003485803-1","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/s11633-017-1097-4","name":"Editorial for special issue on human-inspired computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11633-017-1097-4","authors":["Hong Qiao","Hong Zhang","Florian Röhrbein"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-09-29T23:46:17Z","doi":"10.1007/s11633-017-1097-4","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-030-49339-4_29","name":"Uplink and Downlink Spectral Efficiency Estimation for Multi Antenna MIMO User","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-49339-4_29","authors":["Prajoy Podder","Subrato Bharati","Md. Robiul Alam Robel","Md. Raihan-Al-Masud","Mohammad Atikur Rahman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-05T11:05:14Z","doi":"10.1007/978-3-030-49339-4_29","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-030-16681-6_47","name":"A Fuzzy Expert System for Diagnosing and Analyzing Human Diseases","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-16681-6_47","authors":["Nureni Ayofe Azeez","Timothy Towolawi","Charles Van der Vyver","Sanjay Misra","Adewole Adewumi","Robertas Damaševičius","Ravin Ahuja"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-22T21:26:26Z","doi":"10.1007/978-3-030-16681-6_47","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.35490/ec3.2026.355","name":"A Neuro-Symbolic AI Pipeline for Generating SHACL-Based Digital Building Regulations","source":"crossref","abstract":"","url":"https://doi.org/10.35490/ec3.2026.355","authors":["Alex Donkers","Ekaterina Petrova"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-10T11:55:47Z","doi":"10.35490/ec3.2026.355","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-319-28031-8_1","name":"Multiset Genetic Algorithm Approach to Grid Resource Allocation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-28031-8_1","authors":["Absalom E. Ezugwu","Daniel I. Yakmut","Paschal A. Ochang","Seyed M. Buhari","Marc E. Frincu","Sahalu B. Junaidu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-13T20:02:33Z","doi":"10.1007/978-3-319-28031-8_1","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-030-49339-4_32","name":"2-Element Pentagon Patch Array for 25 GHz Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-49339-4_32","authors":["Ribhu Abhusan Panda","Madhusmita Kuldeep","Varanasi Swatishree","Gudla Sruthi","Udit Narayan Mohapatro","Pawan Kumar Nayak","Debasis Mishra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-05T11:05:14Z","doi":"10.1007/978-3-030-49339-4_32","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-030-16681-6_40","name":"A Comparative Study of Performance and Security Issues of Public Key Cryptography and Symmetric Key Cryptography in Reversible Data Hiding","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-16681-6_40","authors":["S. Anagha","Neenu Sebastian","K. Rosebell Paul"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-22T17:26:26Z","doi":"10.1007/978-3-030-16681-6_40","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1016/b978-0-443-16147-6.00011-6","name":"A comprehensive survey: Nature-inspired algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-16147-6.00011-6","authors":["Amir Seyyedabbasi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-31T06:19:34Z","doi":"10.1016/b978-0-443-16147-6.00011-6","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1109/drc46940.2019.9046459","name":"Phase-change memory enables energy-efficient brain-inspired computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/drc46940.2019.9046459","authors":["Manuel Le Gallo","Abu Sebastian","Evangelos Eleftheriou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-03-27T10:01:07Z","doi":"10.1109/drc46940.2019.9046459","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.4018/978-1-5225-0788-8.ch039","name":"Studies of Computational Intelligence Based on the Behaviour of Cockroaches","source":"crossref","abstract":"In this chapter, the author expands the notion of computational intelligence using the behavior of cockroaches. An introduction to cockroach as swarm intelligence emerging research area and literature review of its growing concept is explained in the beginning. The chapter also covers the ideas of hybrid cockroach optimization system. Next, the author studies the applicability of cockroach swarm optimization. Thereafter, the author presents the details of theoretical algorithm and an experimental result of integration of robot to some cockroaches to make collective decisions. Then, the author proposes his algorithm for traversing the shortest distance of city warehouses. Then, a few comparative statistical results of the progress of the present work on cockroach intelligence are shown. Finally, conclusive remarks are given. At last, the author hopes that even researchers with little experience in swarm intelligence will be enabled to apply the proposed algorithm in their own application areas.","url":"https://doi.org/10.4018/978-1-5225-0788-8.ch039","authors":["Amartya Neogi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-07-26T12:16:44Z","doi":"10.4018/978-1-5225-0788-8.ch039","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1109/bimnics.2006.361791","name":"Quantum information retrieval and gene networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bimnics.2006.361791","authors":["Dimitri Petritis","Thomas Sierocinski"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-06-07T19:56:37Z","doi":"10.1109/bimnics.2006.361791","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1109/ijcnn.2006.1716283","name":"AER Neuro-Inspired interface to Anthropomorphic Robotic Hand","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.1716283","authors":["A. Linares-Barranco","R. Paz-Vicente","G. Jimenez","J.L. Pedreno-Molina","J. Molina-Vilaplana","J. Lopez-Coronado"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-30T12:35:23Z","doi":"10.1109/ijcnn.2006.1716283","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1016/j.asoc.2014.05.004","name":"Multi-objective optimization and bio-inspired methods applied to machinability of stainless steel","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2014.05.004","authors":["F.S. Lobato","M.N. Sousa","M.A. Silva","A.R. Machado"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-06-02T12:38:00Z","doi":"10.1016/j.asoc.2014.05.004","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-030-49339-4_24","name":"Flower Shaped Patch with Circular Defective Ground Structure for 15 GHz Application","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-49339-4_24","authors":["Ribhu Abhusan Panda","Priya Kumari","Janhabi Naik","Priyanka Negi","Debasis Mishra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-05T11:05:14Z","doi":"10.1007/978-3-030-49339-4_24","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-319-01781-5_21","name":"Principal Component Analysis Neural Network Hybrid Classification Approach for Galaxies Images","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-01781-5_21","authors":["Mohamed Abd. Elfattah","Nashwa El-Bendary","Mohamed A. Abou Elsoud","Jan Platoš","Aboul Ella Hassanien"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-08-01T11:21:05Z","doi":"10.1007/978-3-319-01781-5_21","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-319-76354-5_19","name":"Straightforward MAAS to Ensure Interoperability in Heterogeneous Environment","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-76354-5_19","authors":["Majda Elhozmari","Ahmed Ettalbi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-09T11:43:48Z","doi":"10.1007/978-3-319-76354-5_19","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1109/iscas.2014.6865324","name":"Dynamic computing random access memory: A brain-inspired computing paradigm with memelements","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas.2014.6865324","authors":["Massimiliano Di Ventra","Fabio L. Traversa","Fabrizio Bonani","Yuriy V. Pershin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-30T21:16:29Z","doi":"10.1109/iscas.2014.6865324","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1002/9781394336449.ch3","name":"Integration of Quantum Computing with Soft Computing for Data Processing","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9781394336449.ch3","authors":["Vanya Arun","Kapil Deo Bodha","Ankita Awasthi","Munish Sabharwal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-09T21:18:51Z","doi":"10.1002/9781394336449.ch3","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1145/3381755.3381761","name":"Adaptive control for hindlimb locomotion in a simulated mouse through temporal cerebellar learning","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3381755.3381761","authors":["T. P. Jensen","S. Tata","A. J. Ijspeert","S. Tolu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-18T23:09:51Z","doi":"10.1145/3381755.3381761","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1016/j.asoc.2020.106339","name":"FBI inspired meta-optimization","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2020.106339","authors":["Jui-Sheng Chou","Ngoc-Mai Nguyen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-04-27T21:43:13Z","doi":"10.1016/j.asoc.2020.106339","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1016/j.asoc.2009.12.002","name":"Neuro-genetic approach to optimize parameter design of dynamic multiresponse experiments","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2009.12.002","authors":["Hsu-Hwa Chang","Yan-Kwang Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-12-17T10:11:11Z","doi":"10.1016/j.asoc.2009.12.002","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-031-59341-3_2","name":"Conventional and Advanced MRI in Neuro-Oncology","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-59341-3_2","authors":["Patrick L. Y. Tang","Esther A. H. Warnert","Marion Smits"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-01T09:25:51Z","doi":"10.1007/978-3-031-59341-3_2","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1016/b978-0-443-15663-2.00031-6","name":"Alternative and holistic approaches to neuro-oncological healthcare","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-15663-2.00031-6","authors":["Nicolette M. Gabel","Ted A. Barrios","Maaheen Ahmed","Sean Smith"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-09T08:14:39Z","doi":"10.1016/b978-0-443-15663-2.00031-6","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1007/978-3-662-49014-3_39","name":"Bio-inspired Algorithms Applied in Multi-objective Vehicle Routing Problem: Frameworks and Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-662-49014-3_39","authors":["Yuan Wang","Yongming He","Lei He","Lining Xing"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-23T14:41:36Z","doi":"10.1007/978-3-662-49014-3_39","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/s00500-025-10889-1","name":"Neuro-fuzzy control of commercial vehicles braking","source":"crossref","abstract":"Abstract Increasing dynamic performance and the general level of automation of commercial vehicles emphasize the issue of safety. Modern braking systems focus on sustaining vehicle stability, often degrading the brake performance. The major downgrades of the braking performance are nearly impossible to model using a classical mathematical approach, making them not feasible to use in real braking system controllers. In this paper, the use of combined Neural Networks and Fuzzy logic for the control of the braking system of a commercial vehicle while maximizing performance and sustaining stability is proposed. The control system comprises adhesion estimation, an inverse brake model, and a fuzzy logic controller to keep the system giving optimal control signals in various brake conditions while sustaining vehicle stability and steerability. The results based on a semi-trailer system reveal the success of the proposed AI-based braking system algorithm while braking under varying conditions. Graphical abstract","url":"https://doi.org/10.1007/s00500-025-10889-1","authors":["Veljko Vučinić","Dragan Aleksendrić"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-15T10:23:10Z","doi":"10.1007/s00500-025-10889-1","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1007/s10723-026-09831-y","name":"VRRT–DCM: Low–Latency Edge–Cloud Sensor Analytics for Real–Time Violin Performance under 6G–Inspired Architectures","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s10723-026-09831-y","authors":["Yan Han"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-29T08:58:19Z","doi":"10.1007/s10723-026-09831-y","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-319-28031-8_12","name":"Request Reply Detection Mechanism for Malicious MANETs","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-28031-8_12","authors":["S. Sreelakshmi","K. G. Preetha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-14T01:02:33Z","doi":"10.1007/978-3-319-28031-8_12","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-030-37218-7_132","name":"Image Context Based Similarity Retrieval System","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_132","authors":["Arpana D. Mahajan","Sanjay Chaudhary"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T20:02:40Z","doi":"10.1007/978-3-030-37218-7_132","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/s00500-011-0720-5","name":"Bio-inspired computing for hybrid information technology","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00500-011-0720-5","authors":["Binod Vaidya","Jong Hyuk Park","Hamid R. Arabnia","Witold Pedrycz","Sheng-Lung Peng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-06-02T23:43:34Z","doi":"10.1007/s00500-011-0720-5","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/3-540-32391-0_29","name":"A Behavior-Based Anti-Spam Technology Based on Immune-Inspired Clustering Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1007/3-540-32391-0_29","authors":["Xun Yue","Zhong-xian Chi","Zu-bo Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-12-12T23:24:22Z","doi":"10.1007/3-540-32391-0_29","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1109/nabic.2009.5393622","name":"Convergence analysis of swarm algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393622","authors":["Hongbo Liu","Ajith Abraham","Vaclav Snasel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5393622","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1016/c2022-0-02736-7","name":"Computational Intelligence and Deep Learning Methods for Neuro-rehabilitation Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1016/c2022-0-02736-7","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-25T18:01:59Z","doi":"10.1016/c2022-0-02736-7","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1007/978-3-030-16681-6_19","name":"Comparative Analysis of Chaotic Variant of Firefly Algorithm, Flower Pollination Algorithm and Dragonfly Algorithm for High Dimension Non-linear Test Functions","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-16681-6_19","authors":["Amrit Pal Singh","Arvinder Kaur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-22T17:26:26Z","doi":"10.1007/978-3-030-16681-6_19","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-319-76354-5_2","name":"Reducing Blackhole Effect in WSN","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-76354-5_2","authors":["Sana Akourmis","Youssef Fakhri","Moulay Driss Rahmani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-09T06:43:48Z","doi":"10.1007/978-3-319-76354-5_2","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1145/3529398","name":"qprof: A gprof-Inspired Quantum Profiler","source":"crossref","abstract":"We introduce qprof, a new and extensible quantum program profiler able to generate profiling reports of quantum circuits written using various quantum computing frameworks. We describe the internal structure and working of qprof and provide practical examples on quantum circuits with increasing complexity along with benchmarks of the tool execution time on large circuits. This tool will allow researchers to visualise their quantum algorithm implementation in a different and complementary way and reliably localise the bottlenecks for efficient code optimisation.","url":"https://doi.org/10.1145/3529398","authors":["Adrien Suau","Gabriel Staffelbach","Aida Todri-Sanial"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-05-24T13:20:10Z","doi":"10.1145/3529398","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-030-37218-7_2","name":"Human Pose Detection: A Machine Learning Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_2","authors":["Munindra Kakati","Parismita Sarma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T20:02:40Z","doi":"10.1007/978-3-030-37218-7_2","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-981-10-3611-8_40","name":"Decision Variable Analysis Based on Distributed Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-10-3611-8_40","authors":["Zhao Wang","Maoguo Gong","Tian Xie"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-01-06T23:29:56Z","doi":"10.1007/978-981-10-3611-8_40","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1504/ijica.2015.073007","name":"Bio-inspired algorithms for cloud computing: a review","source":"crossref","abstract":"","url":"https://doi.org/10.1504/ijica.2015.073007","authors":["Balamurugan Balusamy","Jayashree Sridhar","Divya Dhamodaran","P. Venkata Krishna"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-21T12:30:46Z","doi":"10.1504/ijica.2015.073007","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1016/b978-0-443-15663-2.00017-1","name":"In-home care resources in neuro-oncology","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-15663-2.00017-1","authors":["Emily Lambrecht-Stock","Megan Gould","Danette Birkhimer","Hamid Mohtashami","Pierre Giglio"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-09T08:11:23Z","doi":"10.1016/b978-0-443-15663-2.00017-1","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1093/neuonc/noae100","name":"Shaping the future of molecular neurosurgery: Toward epigenetic precision in surgical neuro-oncology?","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuonc/noae100","authors":["Philipp Karschnia","Joerg-Christian Tonn"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-04T23:29:11Z","doi":"10.1093/neuonc/noae100","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1093/neuonc/noae191","name":"Theranostics and molecular imaging in neuro-oncology: The beginning of a new era","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuonc/noae191","authors":["Nathalie L Albert","Matthias Preusser"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-15T11:22:43Z","doi":"10.1093/neuonc/noae191","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1007/978-3-030-49339-4_12","name":"Analytical Study of Scalability in Coastal Communication Using Hybridization of Mobile Ad-hoc Network: An Assessment to Coastal Bed of Odisha","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-49339-4_12","authors":["Sanjaya Kumar Sarangi","Mrutyunjaya Panda"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-05T11:05:14Z","doi":"10.1007/978-3-030-49339-4_12","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1109/nice69539.2026.11567452","name":"Fuzzy Encoding-Decoding to Improve Spiking Q-Learning Performance in Autonomous Driving","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nice69539.2026.11567452","authors":["Aref Ghoreishee","Abhishek Mishra","Lifeng Zhou","John Walsh","Anup Das","Nagarajan Kandasamy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-22T19:52:43Z","doi":"10.1109/nice69539.2026.11567452","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1016/j.asoc.2021.107767","name":"Time-varying Black–Litterman portfolio optimization using a bio-inspired approach and neuronets","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2021.107767","authors":["Theodore E. Simos","Spyridon D. Mourtas","Vasilios N. Katsikis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-07-30T23:54:59Z","doi":"10.1016/j.asoc.2021.107767","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-030-73603-3_50","name":"Smart Appointments Booking Systems for Social Distancing: Technologies and Solutions","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-73603-3_50","authors":["Fatimah H. Almuhsin","Naba Almadan","Atheer Almarhoon","Hawra A. Al Mohssin","Thowiba Hagali Ahmed","Dabiah Alboaneen","Enas E. El-sharawy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-04-09T06:04:19Z","doi":"10.1007/978-3-030-73603-3_50","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-030-96299-9_42","name":"A New Structured Model for ICT Competencies Assessment Through Data Warehousing Software","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_42","authors":["Vladimir Dobrynin","Michele Mastroianni","Olga Sheveleva"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_42","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-031-27499-2_9","name":"Investigating Digital Addiction in the Context of Machine Learning Based System Design","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_9","authors":["Geetika Johar","Ravindra Patel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_9","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-031-27499-2_76","name":"Hydrogen Production: Past, Present and What Will Be the Future?","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_76","authors":["Judite Ferreira","Pedro Pereira","José Boaventura"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_76","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.5040/9781839979804.ch-008","name":"Neuro Navigators in Education","source":"crossref","abstract":"","url":"https://doi.org/10.5040/9781839979804.ch-008","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-13T15:02:24Z","doi":"10.5040/9781839979804.ch-008","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1109/dtis.2010.5487553","name":"Neuro-inspired learning of low-level image processing tasks for implementation based on nano-devices","source":"crossref","abstract":"","url":"https://doi.org/10.1109/dtis.2010.5487553","authors":["Olivier Brousse","Michel Paindavoine","Christian Gamrat"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-06-24T14:37:07Z","doi":"10.1109/dtis.2010.5487553","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.35562/iris.3559","name":"Vers un neuro-imaginaire","source":"crossref","abstract":"","url":"https://doi.org/10.35562/iris.3559","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-13T03:05:21Z","doi":"10.35562/iris.3559","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1002/9781394336449.ch10","name":"Applications of Quantum‐Inspired Soft Computing for Intelligent Data Processing in Real‐Life Scenarios","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9781394336449.ch10","authors":["Priyanka Suyal","Kamal Kumar Gola","Camellia Chakraborty","Rohit Kanauzia","Mohit Suyal","Mridula"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-09T21:18:51Z","doi":"10.1002/9781394336449.ch10","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1109/bicta.2009.5338075","name":"Evolutionary optimization programming with probabilistic models","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2009.5338075","authors":["Sanghoun Oh","Sangwook Lee","Moongu Jeon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-11-24T13:50:07Z","doi":"10.1109/bicta.2009.5338075","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-319-99316-4_15","name":"Visual Priming in a Biologically Inspired Cognitive Architecture","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-99316-4_15","authors":["Pentti O. A. Haikonen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-08-23T19:34:03Z","doi":"10.1007/978-3-319-99316-4_15","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-031-78937-3_4","name":"Detecting Age Related Macular Degeneration Using Integrated Auto coder and Particle Swarm Optimization","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_4","authors":["F. Ajesh","Ajith Abraham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:06:44Z","doi":"10.1007/978-3-031-78937-3_4","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/978-3-031-78937-3_20","name":"Exploring the Performance of Brain-Computer Interfaces in Assistive Technology","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_20","authors":["Yogendra Narayan","Vishal","Rajeev Ranjan","Rohit Katyal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:07:18Z","doi":"10.1007/978-3-031-78937-3_20","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/978-3-030-96299-9_62","name":"Detecting Spinal Abnormalities Using Multilayer Perceptron Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_62","authors":["Arju Manara Begum","M. Rubaiyat Hossain Mondal","Prajoy Podder","Subrato Bharati"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_62","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-030-96299-9_26","name":"Automatic Shoe Detection Using Image Processing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_26","authors":["K. R. Prasanna Kumar","D. Pravin","N. Rokith Dhayal","S. Sathya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_26","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1016/b978-0-443-15663-2.00028-6","name":"Palliative care and hospice care in neuro-oncology","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-15663-2.00028-6","authors":["Solmaz Sahebjam","Elizabeth Pedowitz","Margaret M. Mahon","Heather E. Leeper"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-09T08:13:29Z","doi":"10.1016/b978-0-443-15663-2.00028-6","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1093/neuonc/noae064.614","name":"QOL-26. SYTHESIS OF THE LITERATURE REVIEW ON PHYSICAL ACTIVITY IN PEDIATRIC NEURO-ONCOLOGY","source":"crossref","abstract":"Abstract BACKGROUND Physical Activity plays a vital role in physical, social, phychological wellbeing of pediatric neuro-oncologic group. However, the researches investigating the effects of physical activity on this group have been sparse. The purpose of this study was to identify studies conducted about the effects of physical activity on this population. METHODS PRISMA statement conduct review was followed in electronic database of Journal of Neuro-oncology. Two authors (SY, MT) independently conducted systematic literature searches February 2024. Keywords/Mesh terms: “physical activity’’. Randomized controlled English clinical trials are included; Studies that were published as “review”, “protocol”, “books”, “news”, not reach full text and not related to physical activity excluded. After articles had been reached, used QUADAS-2 checklist for methodological quality. RESULTS 29 articles were identified from 1721 articles, and 2 of them (published 2014-2023) were about pediatric age group. One of them was assessment (50%), while the other one was interventional study (50%). Assessment study was measured by using Bruininks-Osteretsky Test of Motor Performance, Second Edition (BOT-2) and online surveys. Interventional study analyzed the effects of aerobic exercises of three 90-minute sessions per week for 12 consecutive weeks primarily on cortical thickness, white matter, hippocampal volume and secondarily reaction time, accuracy across tests of attention, processing speed, and short term memory. CONCLUSION This abstract provides an initial scoping review of physical activity in pediatric neuro-oncology group. It demonstrates limited range of assessments, and interventions which highlights the lack of clinical evidence in this specific area. The results raise the need for further research in this field to help the development of physical activity guidelines for evaluation and physical activity methods in children with ataxia, and tumours expecially posterior fossa brain tumors. Investigation of different physical activity methods in a group of neuro-oncology children in need of support is major importance.","url":"https://doi.org/10.1093/neuonc/noae064.614","authors":["Seda YILDIZ","Müberra TANRIVERDİ"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-18T06:15:34Z","doi":"10.1093/neuonc/noae064.614","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1007/978-3-030-49339-4_35","name":"The Role of ICTs in Sex Education: The Need for a SexEd App","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-49339-4_35","authors":["Victoria Adebayo","Olaperi Yeside Sowunmi","Sanjay Misra","Ravin Ahuja","Robertas Damaševičius","Jonathan Oluranti"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-05T11:05:14Z","doi":"10.1007/978-3-030-49339-4_35","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-030-96299-9_41","name":"Critical Success Factors for Information Technology and Operational Technology Convergence Within the Energy Sector","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_41","authors":["Thabani Dhlamini","Tendani Mawela"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_41","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-031-27499-2_45","name":"Ensemble Based Cyber Threat Analysis for Supply Chain Management","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_45","authors":["P. Penchalaiah","P. Harini Sri Teja","Bhasha Pydala"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_45","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1016/j.asoc.2009.09.003","name":"Nature-inspired techniques for conformance testing of object-oriented software","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2009.09.003","authors":["A. Bouchachia","R. Mittermeir","P. Sielecky","S. Stafiej","M. Zieminski"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-09-18T09:56:43Z","doi":"10.1016/j.asoc.2009.09.003","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-031-27499-2_36","name":"KIASOntoRec: A Knowledge Infused Approach for Socially Aware Ontology Recommendation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_36","authors":["Aastha Valecha","Gerard Deepak","Deep ak Surya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_36","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-030-96299-9_55","name":"Ontology Based Knowledge Visualization for Domestic Violence Cases","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_55","authors":["Tanaya Das","Abhishek Roy","Arun Kumar Majumdar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_55","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-031-27499-2_26","name":"Optimizing Pre-processing for Foetal Cardiac Ultra Sound Image Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_26","authors":["M. O. Divya","M. S. Vijaya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_26","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1080/01658107.2024.2408954","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.1080/01658107.2024.2408954","authors":["John J. Chen","Wei-Che Hung","Panitha Jindahra","Andrew C. Y. Mak","Collin McClelland","Michael S. Vaphiades","Rashmi Verma","Jim Shenchu Xie","Xiaojun Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-19T15:57:43Z","doi":"10.1080/01658107.2024.2408954","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:27.599Z"},{"id":"doi:10.1007/978-3-031-78937-3_1","name":"Communication and Rehabilitation Interface for Human Brain Disease","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_1","authors":["Aastha Sharma","Sandhya Avasthi","Kadambri Agarwal","Khushboo Jain","Ajith Abraham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:05:59Z","doi":"10.1007/978-3-031-78937-3_1","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/978-3-031-27499-2_27","name":"A Review on Dimensionality Reduction for Machine Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_27","authors":["Duarte Coelho","Ana Madureira","Ivo Pereira","Ramiro Gonçalves"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_27","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-319-26230-7","name":"Nature-Inspired Computing for Control Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-26230-7","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-16T07:35:17Z","doi":"10.1007/978-3-319-26230-7","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-0-387-09655-1_6","name":"Self-stabilizing Automata","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-0-387-09655-1_6","authors":["Torben Weis","Arno Wacker"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-08-19T09:40:02Z","doi":"10.1007/978-0-387-09655-1_6","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1109/ivcnz.2008.4762075","name":"Applications for bio-inspired visual processing algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ivcnz.2008.4762075","authors":["R.S.A. Brinkworth","D.C. O'Carroll"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-01-28T16:20:18Z","doi":"10.1109/ivcnz.2008.4762075","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-319-59156-8_14","name":"Bacterial and Viral Foraging Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-59156-8_14","authors":["Anthony Brabazon","Seán McGarraghy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-09-26T18:09:36Z","doi":"10.1007/978-3-319-59156-8_14","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1109/bimnics.2007.4610114","name":"Self-organizing mobile surveillance security networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bimnics.2007.4610114","authors":["Duco Ferro","Alfons Salden"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-09-08T20:06:46Z","doi":"10.1109/bimnics.2007.4610114","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.14236/ewic/fdia2008.10","name":"Selective Erasers: A Theoretical Framework for Representing Documents Inspired by Quantum Theory","source":"crossref","abstract":"","url":"https://doi.org/10.14236/ewic/fdia2008.10","authors":["Alvaro F. Huertas-Rosero"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-10-15T18:17:49Z","doi":"10.14236/ewic/fdia2008.10","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.4018/978-1-4666-0942-6.ch004","name":"0h!m1gas","source":"crossref","abstract":"Ants represent a natural superorganism, an autopoietic machine, much like the human society. Nevertheless, the ant society stands out due to self-organization. Ants accomplish the generation of bottom-up structures communicating mainly by pheromones, but they also produce modulatory vibrations. This phenomenon represents a fascinating subject of research that needs to be amplified in order to identify the connections between these social organisms and humans; they share the same environment with humans and participate, thus, in the construction and mutation of posthuman ecology. The human-ant relationship plays an important role in the creation of new ecosystems and the transformations of old ones. Man can approach and embrace this relationship by means of artistic experiments that explore the bioacoustics involved in the social behavior of ants supported by the combination of cybernetics, autopoiesis, self-organization, and emergence.","url":"https://doi.org/10.4018/978-1-4666-0942-6.ch004","authors":["Kuai Shen Auson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-03-22T13:17:45Z","doi":"10.4018/978-1-4666-0942-6.ch004","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1109/nabic.2010.5716270","name":"Block cipher algorithm based on programmable cellular automata","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2010.5716270","authors":["P Anghelescu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-02-18T19:03:54Z","doi":"10.1109/nabic.2010.5716270","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-031-78940-3_6","name":"Reshaping Security: Adversarial Defense in Machine Learning Application","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78940-3_6","authors":["Yajnaseni Dash","Ajith Abraham","Manish Raj"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-05T06:07:50Z","doi":"10.1007/978-3-031-78940-3_6","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/978-3-031-78937-3_16","name":"Machine Learning Based Clinical Decision Support System for the Diagnosis of Knee Injuries","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_16","authors":["Parul Chhabra","Pradeep Kumar Bhatia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:05:43Z","doi":"10.1007/978-3-031-78937-3_16","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/978-3-031-78946-5_6","name":"Hospital Remote Care Assistance AI to Reduce Workload","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_6","authors":["Luís B. Elvas","Joao C. Ferreira","Berit Irene Helgheim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:03:33Z","doi":"10.1007/978-3-031-78946-5_6","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/978-981-33-6773-9_5","name":"Electrostatic Discharge Algorithm for Optimum Design of Real-Size Truss Structures","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-33-6773-9_5","authors":["Ibrahim Aydogdu","Tevfik Oguz Ormecioglu","Serdar Carbas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-31T12:03:02Z","doi":"10.1007/978-981-33-6773-9_5","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-030-37218-7_84","name":"Instructor Performance Evaluation Through Machine Learning Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_84","authors":["J. Sowmiya","K. Kalaiselvi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T15:02:40Z","doi":"10.1007/978-3-030-37218-7_84","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1515/9783111545950-010","name":"18010 Neuromorphic computing devices: fundamental concepts of memory-based processor","source":"crossref","abstract":"","url":"https://doi.org/10.1515/9783111545950-010","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-06T19:15:47Z","doi":"10.1515/9783111545950-010","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1109/meco.2017.7977142","name":"Cognitive inspired learning based on the compressive sensing postulates","source":"crossref","abstract":"","url":"https://doi.org/10.1109/meco.2017.7977142","authors":["Srdjan Stankovic","Irena Orovic"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-07-25T15:28:31Z","doi":"10.1109/meco.2017.7977142","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/978-3-031-27499-2_53","name":"WCMIVR: A Web 3.0 Compliant Machine Intelligence Driven Scheme for Video Recommendation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_53","authors":["Beulah Divya Kannan","Gerard Deepak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_53","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/978-3-031-27499-2_35","name":"A Review on Artificial Intelligence Applications for Multiple Sclerosis Evaluation and Diagnosis","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_35","authors":["Bruno Cunha","Ana Madureira","Lucas Gonçalves"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_35","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/978-3-030-96299-9","name":"Innovations in Bio-Inspired Computing and Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/978-3-030-96299-9_28","name":"Machine Learning Model for Identification of Covid-19 Future Forecasting","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_28","authors":["N. Anitha","C. Soundarajan","V. Swathi","M. Tamilselvan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_28","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/978-3-031-78946-5_21","name":"FTISI: Folksonomy Based Automatic Tweet Tagging Integrating Community Derived Semantic Intelligence","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_21","authors":["A. Aravind Krishnan","Gerard Deepak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:03:41Z","doi":"10.1007/978-3-031-78946-5_21","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/978-3-030-96299-9_29","name":"Alzheimer’s Disease Detection Using Machine Learning and Deep Learning Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_29","authors":["K. Sentamilselvan","J. Swetha","M. Sujitha","R. Vigasini"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_29","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/978-3-030-96299-9_27","name":"Recognition of Disparaging Phrases in Social Media","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_27","authors":["K. R. Prasanna Kumar","P. Aswanth","A. Athithya","T. Gopika"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_27","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/978-3-031-27499-2_63","name":"Comparative Analysis of Filter Impact on Brain Volume Computation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_63","authors":["Prashasti Kanikar","Manoj Sankhe","Deepak Patkar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_63","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/978-3-031-78937-3_21","name":"Cybersecurity Framework for Prediction and Mitigation of Attacks in the Healthcare Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_21","authors":["C. Syamsundar Reddy","G. Anjan Babu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:06:34Z","doi":"10.1007/978-3-031-78937-3_21","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/978-3-030-96299-9_16","name":"An Analysis of Multipath TCP for Improving Network Performance","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_16","authors":["Virendra Dani","Sneha Nagar","Vishal Pawar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_16","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/978-3-031-78937-3_19","name":"Performance Analysis of DS-CDMA Using GIG Orthogonal Codes Under AWGN and Rayleigh Fading Channel","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_19","authors":["Meenakshi Munjal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:07:06Z","doi":"10.1007/978-3-031-78937-3_19","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/978-3-031-78946-5_3","name":"InCVQA: Incremental Knowledge Derivation Scheme for Visual Question Answering Using Gated Recurrent Units","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_3","authors":["Anamaya Vyas","Gerard Deepak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:03:34Z","doi":"10.1007/978-3-031-78946-5_3","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1007/978-3-031-27499-2_23","name":"Extracting and Analyzing Terms with the Component ‘Green’ in the Bulgarian Language: A Big Data Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_23","authors":["Velislava Stoykova"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_23","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/978-3-030-96299-9_13","name":"Data Prediction Model in Wireless Sensor Networks: A Machine Learning Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_13","authors":["Khushboo Jain","Manali Gupta","Ajith Abraham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_13","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/978-3-319-27400-3_23","name":"Modelling Image Processing with Discrete First-Order Swarms","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-27400-3_23","authors":["Leif Bergerhoff","Joachim Weickert"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-01T17:08:38Z","doi":"10.1007/978-3-319-27400-3_23","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1109/nabic.2009.5393568","name":"Hyper-heuristic decision tree induction","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393568","authors":["Alan Vella","David Corne","Chris Murphy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393568","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.4018/978-1-4666-1574-8.ch021","name":"Recognition of Human Silhouette Based on Global Features","source":"crossref","abstract":"The aim of this paper is people recognition based on their gait. The authors propose a computer vision approach applied to video sequences extracting global features of human motion. From the skeleton, the authors extract the information about human joints. From the silhouette and the authors get the boundary features of the human body. The binary and gray-level-images contain different aspects about the human motion. This work proposes to recover the global information of the human body based on four segmented image models and applies a fusion model to improve classification. The authors consider frames as elements of distinct classes of video sequences and the sequences themselves as classes in a database. The classification rates obtained separately from four image sequences are then merged together by a fusion technique. The results were then compared with other techniques for gait recognition.","url":"https://doi.org/10.4018/978-1-4666-1574-8.ch021","authors":["Milene Arantes","Adilson Gonzaga"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-05-10T09:54:52Z","doi":"10.4018/978-1-4666-1574-8.ch021","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1016/b978-0-44-322341-9.00003-3","name":"Copyright","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-44-322341-9.00003-3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-24T10:20:07Z","doi":"10.1016/b978-0-44-322341-9.00003-3","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1007/978-3-030-96299-9_61","name":"A Study on Sequential Transactions Using Smart Card Based Cloud Voting System","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_61","authors":["Roneeta Purkayastha","Abhishek Roy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_61","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/978-3-319-59156-8_12","name":"Spider and Antlion Foraging Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-59156-8_12","authors":["Anthony Brabazon","Seán McGarraghy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-09-26T14:09:36Z","doi":"10.1007/978-3-319-59156-8_12","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/978-1-4612-5695-3_48","name":"An Elephant Inspired by the Dutch National Flag","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4612-5695-3_48","authors":["Edsger W. Dijkstra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-07-28T23:13:33Z","doi":"10.1007/978-1-4612-5695-3_48","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch037","name":"Building Distribution Networks Using Cooperating Agents","source":"crossref","abstract":"This chapter examines the use of emergent computing to optimize solutions to logistics problems. The chapter initially explores the use of agents and evolutionary algorithms to optimise postal distribution networks. The structure of the agent community and the means of interaction between agents is based on social interactions previously used to solve these problems. The techniques developed are then adapted for use in a dynamic environment planning the despatch of goods from a supermarket. These problems are based on real-world data in terms of geography and constraints. The author hopes that this chapter will inform researchers as to the suitability of emergent computing in real-world scenarios and the abilities of agent-based systems to mimic social systems.","url":"https://doi.org/10.4018/978-1-59140-984-7.ch037","authors":["N. Urquhart"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch037","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.4018/978-1-4666-0942-6.ch010","name":"Biological Translation","source":"crossref","abstract":"This chapter explores the use of code, form, and interactivity in translating biological objects into mathematically generated digital environments. The existence of a mathematical language contained in all physical objects that is similar in function to DNA in organisms is proposed as a core component and driving force of this exploration. Relative to current education tactics, using code, form, and interactivity as a set of common lexicons creates an increasingly universal method, to explore, understand, and teach this hidden biological language by re-writing its algorithms in ways we may readily recognize and absorb. Two case studies of the designer’s own work, (a) Clouds &amp; Ichor, and (b) Stream, will be used to demonstrate and ground the concepts being discussed. In both projects, a natural learning experience is at the core of the biological process.","url":"https://doi.org/10.4018/978-1-4666-0942-6.ch010","authors":["Collin Hover"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-03-22T13:17:45Z","doi":"10.4018/978-1-4666-0942-6.ch010","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1016/j.jpdc.2026.105267","name":"Energy efficient quantum-inspired IoT-based crop recommendation framework for smart agriculture","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.jpdc.2026.105267","authors":["Amandeep Kaur","Sahil","Chenab"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-29T06:59:44Z","doi":"10.1016/j.jpdc.2026.105267","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/978-981-10-6875-1_63","name":"Bat Inspired Sentiment Analysis of Twitter Data","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-10-6875-1_63","authors":["Himja Khurana","Sanjib Kumar Sahu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-12-21T11:07:11Z","doi":"10.1007/978-981-10-6875-1_63","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/s10791-026-10234-6","name":"Domesticated animal-inspired metaheuristic algorithms for static and dynamic optimization problems","source":"crossref","abstract":"Abstract Metaheuristic optimization algorithms inspired by animal behaviors have predominantly focused on wild and predatory species, while the structured and cooperative behaviors of domesticated animals remain largely unexplored. Motivated by this gap, this paper proposes a unified family of four domesticated animal–inspired metaheuristic algorithms: Canine–Human Trust Optimization (CHTO), Feline Curiosity Optimization (FCO), Equine–Human Harmony Optimization (EHHO), and Lagomorph Bond Optimization (LBO), where lagomorph refers to rabbit-inspired bonding behavior. Each algorithm models companionship-oriented traits such as trust, curiosity, harmony, and social bonding to achieve an effective balance between exploration and exploitation. The proposed algorithms are evaluated on standard unimodal and multimodal benchmark functions and dynamic optimization problems using the Generalized Moving Peaks Benchmark (GMPB). Experimental results show that EHHO consistently outperforms classical and recent metaheuristics, including Particle Swarm Optimization (PSO), Harris Hawks Optimization (HHO), Slime Mould Algorithm (SMA), and Aquila Optimizer (AO). On highly multimodal benchmark functions such as Rastrigin (f₃), Griewank (f₄), and Levy (f₇), EHHO achieves up to 35% improvement in mean fitness values compared to Harris Hawks Optimization (HHO), which is identified as the strongest competing baseline algorithm. In dynamic optimization scenarios using the GMPB, EHHO reduces the average offline error by approximately 28% compared to Harris Hawks Optimization (HHO), while achieving a success rate of 92% across changing environments. Statistical validation using Friedman and Wilcoxon signed-rank tests confirms the robustness and statistical significance of the proposed algorithms. The findings establish domesticated animal companionship behaviors as a competitive and effective paradigm for solving both static and dynamic optimization problems.","url":"https://doi.org/10.1007/s10791-026-10234-6","authors":["Neeraj Tantubay","Surendra Solanki","Shabya Gupta","Lalit Kumar","Mahendra Kumar Jhariya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-19T12:33:48Z","doi":"10.1007/s10791-026-10234-6","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1109/bicta.2010.5645279","name":"Humoral-mediated clustering","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2010.5645279","authors":["Waseem Ahmad","Ajit Narayanan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-12-09T10:33:18Z","doi":"10.1109/bicta.2010.5645279","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1109/rivf60135.2023.10471845","name":"A Bio-Inspired Model for Audio Processing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/rivf60135.2023.10471845","authors":["Tanguy Cazalets","Joni Dambre"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-22T17:56:58Z","doi":"10.1109/rivf60135.2023.10471845","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1162/imag.a.1227","name":"Large language models reveal the neural tracking of linguistic context in attended and unattended multi-talker speech.","source":"europepmc","abstract":"","url":"https://doi.org/10.1162/imag.a.1227","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1162/imag.a.1227","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1093/bioinformatics/btag168","name":"MZSGO: multimodal zero-shot protein function annotation via evolutionary signals and textual semantics.","source":"europepmc","abstract":"Motivation Although deep learning has significantly advanced the field of protein function prediction, current approaches are limited by their reliance on a narrow set of modalities. Specifically, they primarily rely on sequence patterns and treat protein domain data and functional labels merely as categorical tags. Consequently, they fail to capitalize on the semantic richness embedded within their textual definitions. These constraints hinder their ability to generalize to novel labels. To tackle this issue, we present MZSGO, a multimodal zero-shot framework that fuses evolutionary signals from protein language models with semantic features derived from large language models (LLMs). By employing an adaptive gated fusion mechanism, MZSGO effectively aligns sequence-based and text-based modalities to enable robust predictions for unseen labels. Results By unifying protein representations and functional annotations, we bridge the semantic gap that limits current approaches. Results indicate that while our model remains competitive on supervised benchmarks, it demonstrates a marked advantage over existing methods in zero-shot tasks. It specifically excels at recognizing previously unseen long-tail and novel Gene Ontology (GO) terms. Availability and implementation The source code and datasets are available at https://github.com/toxic-byte/MZSGO.","url":"https://doi.org/10.1093/bioinformatics/btag168","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1093/bioinformatics/btag168","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1016/j.fochx.2026.103833","name":"Transformative artificial intelligence integration in aquatic supply chains: synergizing precision aquaculture with intelligent logistics and data-driven consumption.","source":"europepmc","abstract":"Aquatic supply chains currently encounter critical sustainability and efficiency challenges, ranging from resource overexploitation to inherent cold chain vulnerabilities. Although individual artificial intelligence (AI) applications are emerging, research synthesizing the entire \"Farm-to-Table\" continuum remains scarce. This review bridges this gap by evaluating AI integration-specifically machine learning and deep learning-across aquaculture, harvesting, processing, logistics, and marketing. The analysis reveals that while AI demonstrates notable efficacy in precision tasks like dynamic water quality prediction and automated catch classification, applications in pre-processing and low-altitude delivery remain nascent. Future advancements require interpretable algorithms, standardized databases, interdisciplinary collaboration, and cost-effective deployment to construct resilient, intelligent supply chains that ensure food safety and satisfy growing global market demands. Ultimately, this review provides a robust theoretical foundation for researchers and practitioners to enhance product safety and operational efficiency, fostering a sustainable, digital transformation of the aquatic industry.","url":"https://doi.org/10.1016/j.fochx.2026.103833","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.fochx.2026.103833","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/s11069-026-08078-w","name":"Hybrid methods in flood inundation modeling: a systematic review.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11069-026-08078-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s11069-026-08078-w","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1146/annurev-neuro-102124-015847","name":"Planning in the Brain: It's Not What You Think It Is.","source":"europepmc","abstract":"","url":"https://doi.org/10.1146/annurev-neuro-102124-015847","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1146/annurev-neuro-102124-015847","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-025-31219-3","name":"Quantum inspired wavelet and Fourier feature fusion for EEG based epilepsy and seizure detection.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-31219-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-025-31219-3","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1162/imag.a.36","name":"Comparing the carbon footprint of fMRI data processing and analysis approaches.","source":"europepmc","abstract":"","url":"https://doi.org/10.1162/imag.a.36","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1162/imag.a.36","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1162/imag.a.1172","name":"Neurophysiological screening of individual variability for robust decoding in c-VEP-based BCI.","source":"europepmc","abstract":"","url":"https://doi.org/10.1162/imag.a.1172","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1162/imag.a.1172","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1162/imag.a.1128","name":"Spine-prints: Transposing brain fingerprints to the spinal cord.","source":"europepmc","abstract":"","url":"https://doi.org/10.1162/imag.a.1128","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1162/imag.a.1128","addedAt":"2026-09-01T01:48:27.599Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.3390/biomimetics9120783","name":"Edge Artificial Intelligence Device in Real-Time Endoscopy for Classification of Gastric Neoplasms: Development and Validation Study.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics9120783","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3390/biomimetics9120783","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.3389/frai.2025.1731997","name":"Enhancing particle swarm optimization based on optical computing mechanism: application to dyslexia detection.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/frai.2025.1731997","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/frai.2025.1731997","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3390/healthcare14081020","name":"Bibliometric Analysis of 30 Years of Scientific Publications Related to Low-Flow Anesthesia.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/healthcare14081020","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/healthcare14081020","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1111/ejn.70542","name":"How to Foster Challenging Interdisciplinary Collaborations: Can Philosophy Support Neuroscientists?","source":"europepmc","abstract":"New conceptual and technological developments bring neuroscientists closer to other disciplines and other fields in neuroscience with different traditions. Although some neuroscientists may underrate the potential benefits of successful interdisciplinary collaborations, others may be unaware of the typical difficulties of such collaborations or are not trained in skills that render them fruitful. Here, we argue that interdisciplinary interactions have long been part of neuroscience, although they are often challenging, because neuroscientists may be confronted with concepts, assumptions, and interpretative horizons that differ from their own. This can lead to misunderstandings and little mutual appreciation. Using the historical development of brain imaging techniques, we distinguish between different types of interdisciplinary interactions and illustrate some of their benefits. In addition, we present various challenges for collaborations at the interface between traditional laboratory-type approaches and those of clinical or computational neuroscience or of ecological field approaches. To address these challenges, we invite neuroscientists to consider philosophers as collaboration partners with complementary expertise, which includes special consideration of language use, underlying assumptions and proficiency in conceptual analysis. This expertise can be used by neuroscientists to increase their understanding and address some difficulties in interdisciplinary interactions more effectively. The benefits of these interactions can be expected to outweigh challenges in the dialogue with philosophers. Importantly, neuroscientists can choose between reading philosophical literature, participating in joint events with philosophers, and integrating philosophers into neuroscience projects. This may allow neuroscientists to explore unforeseen possibilities to improve or initiate collaborations with scientists from other fields and disciplines.","url":"https://doi.org/10.1111/ejn.70542","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1111/ejn.70542","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1162/imag.a.1105","name":"Monitoring morphometric drift in lifelong learning segmentation of the spinal cord.","source":"europepmc","abstract":"","url":"https://doi.org/10.1162/imag.a.1105","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1162/imag.a.1105","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1016/j.nicl.2026.103960","name":"Altered parietal multisensory integration in chronic tinnitus during closed-loop real-time fMRI auditory downregulation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.nicl.2026.103960","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.nicl.2026.103960","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.3390/s24165130","name":"Deep Learning Technology and Image Sensing.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s24165130","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3390/s24165130","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1038/s41598-025-27191-7","name":"Optimization of automatic generation controllers in renewable multi-area power systems using the Fata Morgana algorithm.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-27191-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-27191-7","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fpsyt.2025.1648060","name":"Quantum AI for psychiatric diagnosis: enhancing dementia classification with quantum machine learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fpsyt.2025.1648060","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fpsyt.2025.1648060","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1002/advs.202409568","name":"Bio-Inspired Neuromorphic Sensory Systems from Intelligent Perception to Nervetronics.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202409568","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/advs.202409568","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1093/nop/npaf110","name":"Real-world management and long-term outcomes in adolescent, young adult, and adult medulloblastoma: Experience from a monocentric series with multimodal and targeted approaches.","source":"europepmc","abstract":"","url":"https://doi.org/10.1093/nop/npaf110","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1093/nop/npaf110","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/frai.2026.1837195","name":"Machine learning-based detection of workplace stress using wearable and multimodal data: a systematic literature review.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/frai.2026.1837195","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/frai.2026.1837195","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41467-024-47630-9","name":"Visualized in-sensor computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-024-47630-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41467-024-47630-9","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.3389/fnins.2024.1443121","name":"Neuromorphic engineering in wetware: the state of the art and its perspectives.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2024.1443121","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3389/fnins.2024.1443121","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1007/s11060-024-04757-5","name":"Artificial intelligence innovations in neurosurgical oncology: a narrative review.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11060-024-04757-5","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1007/s11060-024-04757-5","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1002/advs.202511478","name":"Artificial Nervous Systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202511478","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/advs.202511478","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1007/s13534-024-00406-y","name":"Snn and sound: a comprehensive review of spiking neural networks in sound.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s13534-024-00406-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1007/s13534-024-00406-y","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1038/s41467-024-48881-2","name":"Bio-inspired multimodal learning with organic neuromorphic electronics for behavioral conditioning in robotics.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-024-48881-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41467-024-48881-2","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.3390/pathogens13111024","name":"Method to Generate Chlorine Dioxide Gas In Situ for Sterilization of Automated Incubators.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/pathogens13111024","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3390/pathogens13111024","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.3389/frai.2026.1841639","name":"Label tree semantic losses for rich multi-class medical image segmentation.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/frai.2026.1841639","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/frai.2026.1841639","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1016/j.heliyon.2024.e37427","name":"Physiology-inspired bifocal fronto-parietal tACS for working memory enhancement.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.heliyon.2024.e37427","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.heliyon.2024.e37427","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1016/j.jare.2025.10.031","name":"Modeling homosynaptic and heterosynaptic plasticity with a single neuromemristive synapse.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.jare.2025.10.031","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.jare.2025.10.031","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.3390/s24072367","name":"Magnetic Flux Sensor Based on Spiking Neurons with Josephson Junctions.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s24072367","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3390/s24072367","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1007/s11604-024-01712-2","name":"Structured clinical reasoning prompt enhances LLM's diagnostic capabilities in diagnosis please quiz cases.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11604-024-01712-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1007/s11604-024-01712-2","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1038/s41598-024-57610-0","name":"A new intelligently optimized model reference adaptive controller using GA and WOA-based MPPT techniques for photovoltaic systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-024-57610-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41598-024-57610-0","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1371/journal.pone.0322695","name":"Improving fine-grained food classification using deep residual learning and selective state space models.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pone.0322695","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1371/journal.pone.0322695","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1126/sciadv.ads9744","name":"Subangstrom ion beam engineering of buried ultrathin oxides for scalable quantum computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.ads9744","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1126/sciadv.ads9744","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fdata.2024.1497535","name":"Advancing cybersecurity and privacy with artificial intelligence: current trends and future research directions.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fdata.2024.1497535","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3389/fdata.2024.1497535","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1111/psyp.70136","name":"Ecological Resonance Is Reflected in Human Brain Activity.","source":"europepmc","abstract":"","url":"https://doi.org/10.1111/psyp.70136","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1111/psyp.70136","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.3389/fpls.2026.1742689","name":"A review of remote sensing-based crop yield estimation: machine learning techniques and environmental, algorithmic, and hardware limitations.","source":"europepmc","abstract":"Advancements in agricultural technologies have increasingly emphasized technical innovations aimed at improving the predictability and reliability of agricultural outputs. These aspects encompass developments in agricultural machinery, automation technologies, biotechnology, and controlled environment farming systems. This article focuses on Remote Sensing (RS)-based approaches applied to agricultural yield estimation for both crops and plants. RS technologies offer enhanced precision and scalability, making them particularly effective for large-scale agricultural monitoring and analysis. A systematic classification of RS-based methodologies employed for crop yield estimation is presented in this study. These methodologies are categorized into: (i) Sensor-Based approaches, (ii) Platform-Based approaches, (iii) Analytical and Modeling-based methods, and (iv) Machine Learning (ML)-driven models. Based on findings reported across multiple studies, it is observed that Deep Learning (DL)-based architectures consistently achieve superior performance across key evaluation metrics, including accuracy, precision, recall, and F1-score. This performance advantage stems from their capacity to learn hierarchical representations, capture complex non-linear relationships, scale efficiently with large datasets, and reduce reliance on manual feature engineering. Following this classification, our article presents a comprehensive discussion of the limitations associated with these methodologies. These challenges are organized into four major categories: (i) Environmental, (ii) Algorithmic, (iii) Hardware and Operational, and (iv) Wireless Sensor Networks (WSNs) related limitations. The adopted classification framework helps readers identify and address the key challenges associated with effective yield estimation in crops and plants. Moreover, the article concludes by outlining several future research directions intended to support and guide both early-career and experienced researchers in this domain.","url":"https://doi.org/10.3389/fpls.2026.1742689","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fpls.2026.1742689","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1038/s41467-024-48399-7","name":"Firing feature-driven neural circuits with scalable memristive neurons for robotic obstacle avoidance.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-024-48399-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41467-024-48399-7","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1371/journal.pone.0327542","name":"Maximum power point tracking of photovoltaic module based on Particle Swarm Optimization enhanced with Quasi-Newton method.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pone.0327542","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1371/journal.pone.0327542","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41378-025-00882-x","name":"Brain inspired iontronic fluidic memristive and memcapacitive device for self-powered electronics.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41378-025-00882-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41378-025-00882-x","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.3390/s25082569","name":"A Variable Step-Size FxLMS Algorithm for Nonlinear Feedforward Active Noise Control.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s25082569","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/s25082569","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1186/s13568-025-01988-1","name":"Advances and challenges in the integration of artificial intelligence in microbial biosurfactant bioprocess.","source":"europepmc","abstract":"","url":"https://doi.org/10.1186/s13568-025-01988-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1186/s13568-025-01988-1","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1002/brb3.70788","name":"Inductive and Transfer Learning-Based Hybrid Model Techniques for Accurate and Automated Diagnosis of Neurological Diseases.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/brb3.70788","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/brb3.70788","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1016/j.fochx.2026.103628","name":"Artificial intelligence in functional food innovation: Bioactive enhancement and formulation optimization: A quasi-systematic review.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.fochx.2026.103628","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.fochx.2026.103628","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.3389/frai.2026.1678539","name":"The future of fundamental science led by generative closed-loop artificial intelligence.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/frai.2026.1678539","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/frai.2026.1678539","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.3389/fnbot.2024.1349498","name":"Re-framing bio-plausible collision detection: identifying shared meta-properties through strategic prototyping.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnbot.2024.1349498","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3389/fnbot.2024.1349498","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1021/acs.chemrev.4c00587","name":"Memristive Ion Dynamics to Enable Biorealistic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.chemrev.4c00587","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acs.chemrev.4c00587","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.3390/e27020138","name":"Neuro-Fuzzy Network-Based Nonlinear Hybrid Active Noise Control Systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/e27020138","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/e27020138","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"epmc:MED41306332","name":"Borrowing From the Future: Enhancing Early Risk Assessment through Contrastive Learning.","source":"europepmc","abstract":"","url":"https://pubmed.ncbi.nlm.nih.gov/41306332/","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1038/s44172-025-00511-5","name":"Toward an ion-based large-scale integrated circuit: design, simulation, and integration.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s44172-025-00511-5","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s44172-025-00511-5","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3390/nano15110863","name":"Ferroelectric-Based Optoelectronic Synapses for Visual Perception: From Materials to Systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/nano15110863","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/nano15110863","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1038/s41586-025-08742-4","name":"Synaptic and neural behaviours in a standard silicon transistor.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41586-025-08742-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41586-025-08742-4","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3390/s24103108","name":"Smart City as Cooperating Smart Areas: On the Way of Symbiotic Cyber-Physical Systems Environment.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s24103108","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3390/s24103108","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1007/s13659-025-00589-6","name":"Nature meets machine: the AI renaissance in natural product drug discovery.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s13659-025-00589-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s13659-025-00589-6","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1016/j.media.2026.104158","name":"A false discovery rate control method using a fully connected hidden Markov random field for neuroimaging data.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.media.2026.104158","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.media.2026.104158","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1007/s40820-025-02042-2","name":"Non-Invasive Brain-Computer Interfaces: Converging Frontiers in Neural Signal Decoding and Flexible Bioelectronics Integration.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s40820-025-02042-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s40820-025-02042-2","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1162/imag.a.987","name":"A self-supervised learning framework for discovering cortical folding patterns under genetic influence: Application to the Anterior Cingulate Cortex.","source":"europepmc","abstract":"","url":"https://doi.org/10.1162/imag.a.987","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1162/imag.a.987","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1038/s41598-024-79590-x","name":"Energy-efficient data routing using neuro-fuzzy based data routing mechanism for IoT-enabled WSNs.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-024-79590-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41598-024-79590-x","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1162/netn_a_00451","name":"A graph neural network approach to investigate brain critical states over neurodevelopment.","source":"europepmc","abstract":"","url":"https://doi.org/10.1162/netn_a_00451","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1162/netn_a_00451","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1038/s41467-025-55832-y","name":"Principled neuromorphic reservoir computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-55832-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-55832-y","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.7717/peerj-cs.2407","name":"A comprehensive review of sensor node deployment strategies for maximized coverage and energy efficiency in wireless sensor networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.7717/peerj-cs.2407","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.7717/peerj-cs.2407","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1073/pnas.2321032121","name":"A neural algorithm for computing bipartite matchings.","source":"europepmc","abstract":"","url":"https://doi.org/10.1073/pnas.2321032121","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1073/pnas.2321032121","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1038/s41467-024-51403-9","name":"Artificial organic afferent nerves enable closed-loop tactile feedback for intelligent robot.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-024-51403-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41467-024-51403-9","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1038/s41467-024-44723-3","name":"Neuromorphic hardware for somatosensory neuroprostheses.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-024-44723-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41467-024-44723-3","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.3389/fnins.2025.1557287","name":"AM-MTEEG: multi-task EEG classification based on impulsive associative memory.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2025.1557287","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fnins.2025.1557287","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1073/pnas.2420105122","name":"Emergence of a temporal processing gradient from naturalistic inputs and network connectivity.","source":"europepmc","abstract":"","url":"https://doi.org/10.1073/pnas.2420105122","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1073/pnas.2420105122","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1371/journal.pcbi.1012647","name":"Whole brain functional connectivity: Insights from next generation neural mass modelling incorporating electrical synapses.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pcbi.1012647","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1371/journal.pcbi.1012647","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.3390/biomimetics9060315","name":"An Improved Dyna-Q Algorithm Inspired by the Forward Prediction Mechanism in the Rat Brain for Mobile Robot Path Planning.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics9060315","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3390/biomimetics9060315","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1038/s41598-025-93113-2","name":"Towards a quantum synapse for quantum sensing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-93113-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-93113-2","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1371/journal.pcbi.1014340","name":"pyhgf: A neural network library for predictive coding.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pcbi.1014340","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pcbi.1014340","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1038/s41598-025-22956-6","name":"Rank charged system search algorithm for optimization and operations research.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-22956-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-025-22956-6","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1038/s41598-025-16354-1","name":"Optimization of SiO&lt;sub&gt;2&lt;/sub&gt; based water-diesel emulsified fuel for engine performance and emission characteristics using soft computing approaches.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-16354-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-16354-1","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1073/pnas.2412830122","name":"The functional role of oscillatory dynamics in neocortical circuits: A computational perspective.","source":"europepmc","abstract":"","url":"https://doi.org/10.1073/pnas.2412830122","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1073/pnas.2412830122","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1017/wtc.2025.3","name":"Soft back exosuit controlled by neuro-mechanical modeling provides adaptive assistance while lifting unknown loads and reduces lumbosacral compression forces.","source":"europepmc","abstract":"","url":"https://doi.org/10.1017/wtc.2025.3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1017/wtc.2025.3","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.3390/bioengineering11030269","name":"Analysis of Intracranial Aneurysm Haemodynamics Altered by Wall Movement.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/bioengineering11030269","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3390/bioengineering11030269","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1088/1741-2552/ae08ea","name":"Multitarget neurostimulation of the deep brain: clinical opportunities, challenges, and emerging technologies.","source":"europepmc","abstract":"","url":"https://doi.org/10.1088/1741-2552/ae08ea","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1088/1741-2552/ae08ea","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1016/j.heliyon.2024.e35937","name":"Dynamical behaviour and meta heuristic optimization of a hospital management software system.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.heliyon.2024.e35937","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.heliyon.2024.e35937","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1021/acsomega.4c00320","name":"Understanding the Resistive Switching Behaviors of Top Electrode (Au, Cu, and Al)-Dependent TiO<sub>2</sub>-Based Memristive Devices.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsomega.4c00320","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1021/acsomega.4c00320","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.3390/biomimetics9060329","name":"Bioinspired Control Architecture for Adaptive and Resilient Navigation of Unmanned Underwater Vehicle in Monitoring Missions of Submerged Aquatic Vegetation Meadows.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics9060329","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3390/biomimetics9060329","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.3389/fncom.2024.1349408","name":"Artificial cognition vs. artificial intelligence for next-generation autonomous robotic agents.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncom.2024.1349408","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3389/fncom.2024.1349408","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1523/jneurosci.1221-24.2024","name":"Neural Encoding of Bodies for Primate Social Perception.","source":"europepmc","abstract":"","url":"https://doi.org/10.1523/jneurosci.1221-24.2024","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1523/jneurosci.1221-24.2024","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.3390/biomimetics10090563","name":"Mobile Mental Health Screening in EmotiZen via the Novel Brain-Inspired MCoG-LDPSNet.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics10090563","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/biomimetics10090563","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1021/acs.chemmater.5c01948","name":"Solution-Phase Design of Emerging Nanomaterials.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.chemmater.5c01948","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acs.chemmater.5c01948","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.47626/1516-4446-2024-3963","name":"Emotional recognition technologies applied to health: review and challenges.","source":"europepmc","abstract":"","url":"https://doi.org/10.47626/1516-4446-2024-3963","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.47626/1516-4446-2024-3963","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1038/s41598-024-61294-x","name":"Highly reproducible and CMOS-compatible VO<sub>2</sub>-based oscillators for brain-inspired computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-024-61294-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41598-024-61294-x","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1038/s41598-025-13420-6","name":"Enhancing power efficiency in BLDC motor drives for drones using multiview learning with hybrid optimization algorithms.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-13420-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-13420-6","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-024-68359-x","name":"Hybrid CMOS-Memristor synapse circuits for implementing Ca ion-based plasticity model.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-024-68359-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41598-024-68359-x","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1002/hbm.70281","name":"Using Extreme Value Statistics to Reconceptualize Psychopathology as Extreme Deviations From a Normative Reference Model.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/hbm.70281","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/hbm.70281","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.3389/fnins.2024.1279668","name":"Neurochallenges in smart cities: state-of-the-art, perspectives, and research directions.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2024.1279668","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3389/fnins.2024.1279668","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1016/j.ynirp.2025.100283","name":"ADHD diagnostics and severity assessment using topological manifold learning of resting-state functional magnetic resonance imaging (rs-fMRI).","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.ynirp.2025.100283","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.ynirp.2025.100283","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1038/s41598-025-95288-0","name":"Efficient control of spider-like medical robots with capsule neural networks and modified spring search algorithm.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-95288-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-95288-0","addedAt":"2026-09-01T01:48:27.600Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1111/ejn.15928/v1/review2","name":"Review for \"Dynamic attention signaling in V4: relation to fast‐spiking/non‐fast‐spiking cell class and population coupling\"","source":"crossref","abstract":"","url":"https://doi.org/10.1111/ejn.15928/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-02-06T09:03:47Z","doi":"10.1111/ejn.15928/v1/review2","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1002/prot.25868/v1/review1","name":"Review for \"ProDCoNN: Protein design using a convolutional neural network\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/prot.25868/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-15T15:06:10Z","doi":"10.1002/prot.25868/v1/review1","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1088/2057-1976/ad6e87/v1/review1","name":"Review for \"RobMedNAS: searching robust neural network architectures for medical image synthesis\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2057-1976/ad6e87/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-14T17:14:57Z","doi":"10.1088/2057-1976/ad6e87/v1/review1","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.21275/v4i11.nov151124","name":"A Review on Neural Network Methodology for Diagnosis of Kidney Stone","source":"crossref","abstract":"","url":"https://doi.org/10.21275/v4i11.nov151124","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-04-28T11:43:26Z","doi":"10.21275/v4i11.nov151124","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1002/prot.25868/v2/review1","name":"Review for \"ProDCoNN: Protein design using a convolutional neural network\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/prot.25868/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-15T15:06:10Z","doi":"10.1002/prot.25868/v2/review1","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1088/0954-898x/8/2/001","name":"Plasticity in adult sensory cortex: a review","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/8/2/001","authors":["Aniruddha Das"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/8/2/001","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1039/d2dd00093h/v1/review1","name":"Review for \"Artificial neural network encoding of molecular wavefunctions for quantum computing\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d2dd00093h/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-27T00:04:51Z","doi":"10.1039/d2dd00093h/v1/review1","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.3390/app11104376","name":"A Review of Power System Fault Diagnosis with Spiking Neural P Systems","source":"crossref","abstract":"With the advancement of technologies it is becoming imperative to have a stable, secure and uninterrupted supply of power to electronic systems as well as to ensure the identification of faults occurring in these systems quickly and efficiently in case of any accident. Spiking neural P system (SNPS) is a popular parallel distributed computing model. It is inspired by the structure and functioning of spiking neurons. It belongs to the category of neural-like P systems and is well-known as a branch of the third generation neural networks. SNPS and its variants can perform the task of fault diagnosis in power systems efficiently. In this paper, we provide a comprehensive survey of these models, which can perform the task of fault diagnosis in transformers, power transmission networks, traction power supply systems, metro traction power supply systems, and electric locomotive systems. Furthermore, we discuss the use of these models in fault section estimation of power systems, fault location identification in distribution network, and fault line detection. We also discuss a software tool which can perform the task of fault diagnosis automatically. Finally, we discuss future research lines related to this topic.","url":"https://doi.org/10.3390/app11104376","authors":["Yicen Liu","Ying Chen","Prithwineel Paul","Songhai Fan","Xiaomin Ma","Gexiang Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-05-12T10:59:12Z","doi":"10.3390/app11104376","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1002/2050-7038.12506/v2/review2","name":"Review for \"An electricity price interval forecasting by using residual neural network\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/2050-7038.12506/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-16T17:05:22Z","doi":"10.1002/2050-7038.12506/v2/review2","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1002/brb3.3002/v2/review2","name":"Review for \"Recognizing schizophrenia using facial expressions based on convolutional neural network\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/brb3.3002/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-18T17:02:58Z","doi":"10.1002/brb3.3002/v2/review2","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.21203/rs.3.rs-7442318/v1","name":"Condor: A Neural Connection Network for Enhanced Attention","source":"crossref","abstract":"Abstract The attention mechanism in traditional neural networks relies on pairwise interactions between tokens, limiting its ability to capture complex, multi-token relationships. This study introduces Condor, a novel architecture that extends the attention mechanism through a neural connection network based on the KY Transform theory. Our approach replaces static attention patterns with learnable connection functions that dynamically model relationships within a local window. The Condor architecture achieves linear computational complexity of O(LWH) while maintaining the expressive power to capture sophisticated sequence patterns. Experimental results on wikitext-2 demonstrate improved perplexity and faster convergence compared to the standard Transformer, confirming that each attention head learns unique connection patterns specializing in different aspects of sequence modeling. Code is available at: https://github.com/Kim-Ai-gpu/Condor","url":"https://doi.org/10.21203/rs.3.rs-7442318/v1","authors":["Youngseong Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-27T03:48:06Z","doi":"10.21203/rs.3.rs-7442318/v1","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1017/cbp.2023.5.pr3","name":"Review: Provable Observation Noise Robustness for Neural Network Control Systems — R0/PR3","source":"crossref","abstract":"","url":"https://doi.org/10.1017/cbp.2023.5.pr3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-13T06:55:14Z","doi":"10.1017/cbp.2023.5.pr3","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.21203/rs.3.rs-5376863/v1","name":"A Subsampling Based Neural Network for Spatial Data","source":"crossref","abstract":"Abstract The application of deep neural networks in geospatial data has become a trending research problem in the present day. A significant amount of statistical research has already been introduced, such as generalized least square optimization by incorporating spatial variance-covariance matrix, considering basis functions in the input nodes of the neural networks, and so on. However, for lattice data, there is no available literature about the utilization of asymptotic analysis of neural networks in regression for spatial data. This article proposes a consistent localized two-layer deep neural network-based regression for spatial data. We have proved the consistency of this deep neural network for bounded and unbounded spatial domains under a fixed sampling design of mixed-increasing spatial regions. We have proved that its asymptotic convergence rate is faster than that of [1]'s neural network and an improved generalization of [2]'s neural network structure. We empirically observe the rate of convergence of discrepancy measures between the empirical probability distribution of observed and predicted data, which will become faster for a less smooth spatial surface. We have applied our asymptotic analysis of deep neural networks to the estimation of the monthly average temperature of major cities in the USA from its satellite image. This application is an effective showcase of non-linear spatial regression. We demonstrate our methodology with simulated lattice data in various scenarios.","url":"https://doi.org/10.21203/rs.3.rs-5376863/v1","authors":["Debjoy Thakur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-05T03:46:50Z","doi":"10.21203/rs.3.rs-5376863/v1","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1039/d2dd00093h/v1/review3","name":"Review for \"Artificial neural network encoding of molecular wavefunctions for quantum computing\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d2dd00093h/v1/review3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-27T00:04:51Z","doi":"10.1039/d2dd00093h/v1/review3","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1017/cbp.2023.5.pr2","name":"Review: Provable Observation Noise Robustness for Neural Network Control Systems — R0/PR2","source":"crossref","abstract":"","url":"https://doi.org/10.1017/cbp.2023.5.pr2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-13T06:55:14Z","doi":"10.1017/cbp.2023.5.pr2","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.21203/rs.3.rs-805003/v1","name":"House Price Prediction Model Based on Neural Network","source":"crossref","abstract":"Abstract Through an in-depth understanding of house price prediction issues, the paper aims to establish a BP neural network model for house price prediction based on ideas and methods of the BP neural network. By the BP neural network method, the paper realizes sorting, statistics, and analysis of house prices in Chongqing for 10 years as well as the main factor analysis of house prices. Then, correlative analysis is conducted with the software on house prices and their influential factors. Significant correlations are manifested. MATLAB was used to compile relevant programs and a BP neural network model was established for prediction and verification of house prices. Through the market survey, house prices are finally predicted by software.","url":"https://doi.org/10.21203/rs.3.rs-805003/v1","authors":["chusheng Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-27T14:38:24Z","doi":"10.21203/rs.3.rs-805003/v1","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1088/2057-1976/ad6e87/v2/review1","name":"Review for \"RobMedNAS: searching robust neural network architectures for medical image synthesis\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2057-1976/ad6e87/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-14T17:14:57Z","doi":"10.1088/2057-1976/ad6e87/v2/review1","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1016/j.engappai.2024.109415","name":"Spiking neural networks for autonomous driving: A review","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.engappai.2024.109415","authors":["Fernando S. Martínez","Jordi Casas-Roma","Laia Subirats","Raúl Parada"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-21T19:28:23Z","doi":"10.1016/j.engappai.2024.109415","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1039/d2dd00093h/v2/review2","name":"Review for \"Artificial neural network encoding of molecular wavefunctions for quantum computing\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d2dd00093h/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-27T00:04:51Z","doi":"10.1039/d2dd00093h/v2/review2","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.21203/rs.3.rs-2132871/v1","name":"Financial News Summarisation using Transformer Neural Network","source":"crossref","abstract":"Abstract Transformer architecture, which is based on self-attention mechanism, revolutionised the field of NLP in 2017. It overcame many of the limitations of sequential and iterative approach of the previous popular architectures like LSTM. Generative Pretrained Transformer (GPT), which is a type of transformer model, is one of the most powerful neural network architectures for the purpose of text summarisation. This paper elaborates how and why GPT-2 can be used for financial news summarisation.","url":"https://doi.org/10.21203/rs.3.rs-2132871/v1","authors":["Parth Mihir Patel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-26T02:07:37Z","doi":"10.21203/rs.3.rs-2132871/v1","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.21203/rs.3.rs-2150284/v1","name":"Organic neuromorphic spiking circuit for retina-inspired sensory coding and neurotransmitter-mediated neural pathways","source":"crossref","abstract":"Abstract The fundamental mechanisms of signal communication within the human body rely on the spiking frequency of action potentials. 1,2 Through biological receptors and afferent neuronal cells, stimuli from the external world are encoded into a spiking pattern and transmitted to the central nervous systems where they are processed via interneurons. Replicating the interdependent functions of receptors, afferent neurons and interneurons with spiking circuits 1 , sensors 3 and biohybrid synapses 4 is an essential first step towards merging neuromorphic circuits and biological systems, crucial for computing at the biological interface. We present a novel adaptive spiking circuit that replicates afferent neurons sensory coding from external physical stimuli. We emulate the neuromodulatory activity of interneurons by associating the spiking circuit with biohybrid synapses demonstrating an interdependent chemical synaptic connection. To establish a full neuronal pathway, we combine these key biological functions, showing the signal transduction from light stimulus to spiking frequency and to dopamine-mediated plasticity: a retinal pathway primitive.","url":"https://doi.org/10.21203/rs.3.rs-2150284/v1","authors":["Giovanni Maria Matrone","Eveline van Doremaele","Sophie Griggs","Gang Ye","Iain McCulloch","Francesca Santoro","Yoeri van de Burgt"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-08T16:42:35Z","doi":"10.21203/rs.3.rs-2150284/v1","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1177/15330338261426741/v1/review1","name":"Review for \"A Novel Network-Level Fused Self-Attention Deep Neural Network for Cervical Cancer Classification from Cervicography Images\"","source":"crossref","abstract":"","url":"https://doi.org/10.1177/15330338261426741/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-28T21:12:57Z","doi":"10.1177/15330338261426741/v1/review1","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1177/15330338261426741/v2/review1","name":"Review for \"A Novel Network-Level Fused Self-Attention Deep Neural Network for Cervical Cancer Classification from Cervicography Images\"","source":"crossref","abstract":"","url":"https://doi.org/10.1177/15330338261426741/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-28T21:12:57Z","doi":"10.1177/15330338261426741/v2/review1","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.5194/essd-2018-111-rc2","name":"Review: A global monthly climatology of total alkalinity: a neural network approach","source":"crossref","abstract":"","url":"https://doi.org/10.5194/essd-2018-111-rc2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-12-18T16:17:16Z","doi":"10.5194/essd-2018-111-rc2","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1039/d2dd00093h/v1/review2","name":"Review for \"Artificial neural network encoding of molecular wavefunctions for quantum computing\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d2dd00093h/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-27T00:04:51Z","doi":"10.1039/d2dd00093h/v1/review2","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1039/d2dd00093h/v2/review3","name":"Review for \"Artificial neural network encoding of molecular wavefunctions for quantum computing\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d2dd00093h/v2/review3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-27T00:04:51Z","doi":"10.1039/d2dd00093h/v2/review3","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1039/d2dd00093h/v3/review1","name":"Review for \"Artificial neural network encoding of molecular wavefunctions for quantum computing\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d2dd00093h/v3/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-27T00:04:51Z","doi":"10.1039/d2dd00093h/v3/review1","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1039/d2dd00093h/v2/review1","name":"Review for \"Artificial neural network encoding of molecular wavefunctions for quantum computing\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d2dd00093h/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-27T00:04:51Z","doi":"10.1039/d2dd00093h/v2/review1","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1016/j.sysarc.2026.103869","name":"Neuromorphic architectures for edge-oriented spiking neural networks: A review","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.sysarc.2026.103869","authors":["Kanishka Gunawardana","Sanka Peeris","Kavishka Rambukwella","Roshan Ragel","Isuru Nawinne"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-30T05:32:38Z","doi":"10.1016/j.sysarc.2026.103869","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1103/physrevb.108.184411","name":"Reconfigurable neural spiking in bias field free spin Hall nano-oscillator","source":"crossref","abstract":"","url":"https://doi.org/10.1103/physrevb.108.184411","authors":["Sourabh Manna","Rohit Medwal","Rajdeep Singh Rawat"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-14T10:08:38Z","doi":"10.1103/physrevb.108.184411","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.21203/rs.3.rs-407084/v1","name":"Prediction of Network Security Situation Awareness based on an Improved Model Combined with Neural Network","source":"crossref","abstract":"Abstract People always pay attention to the security of the network. This paper mainly analyzed the problem of network security situation prediction (NSSP). The Radial Basis Function (RBF) neural network was improved by the particle swarm optimization (PSO) algorithm, and a modified PSO (MPSO)-RBF algorithm was obtained, which was used as the prediction model. Then, the data from National Internet Emergency Center (CNCERT/CC) were used as the experimental data, and the MPSO-RBF algorithm was compared with RBF and PSO-RBF algorithms. The results showed that the MPSO-RBF algorithm could achieve convergence in about 50 times of iterations, showing a high calculation efficiency, and the mean absolute percentage error (MAPE) value, mean square error (MSE) value, and root-mean-square error (RMSE) value were small, 2.13%, 0.0005, and 0.0224, respectively, showing that the algorithm had good prediction performance. The results verify the reliability of the MPSO-RBF algorithm in NSSP, which is conducive to further improve network security.","url":"https://doi.org/10.21203/rs.3.rs-407084/v1","authors":["Li Yuan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-04-26T14:29:45Z","doi":"10.21203/rs.3.rs-407084/v1","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1002/2050-7038.12538/v2/review1","name":"Review for \"The nonlinear autoregressive network with exogenous inputs (NARX) neural network to damp power system oscillations\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/2050-7038.12538/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-07-27T17:06:47Z","doi":"10.1002/2050-7038.12538/v2/review1","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1002/2050-7038.12538/v1/review3","name":"Review for \"The nonlinear autoregressive network with exogenous inputs (NARX) neural network to damp power system oscillations\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/2050-7038.12538/v1/review3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-07-27T17:06:47Z","doi":"10.1002/2050-7038.12538/v1/review3","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1177/15330338261426741/v1/review2","name":"Review for \"A Novel Network-Level Fused Self-Attention Deep Neural Network for Cervical Cancer Classification from Cervicography Images\"","source":"crossref","abstract":"","url":"https://doi.org/10.1177/15330338261426741/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-28T21:12:57Z","doi":"10.1177/15330338261426741/v1/review2","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1002/2050-7038.12538/v2/review2","name":"Review for \"The nonlinear autoregressive network with exogenous inputs (NARX) neural network to damp power system oscillations\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/2050-7038.12538/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-07-27T17:06:47Z","doi":"10.1002/2050-7038.12538/v2/review2","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1002/2050-7038.12538/v3/review2","name":"Review for \"The nonlinear autoregressive network with exogenous inputs (NARX) neural network to damp power system oscillations\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/2050-7038.12538/v3/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-07-27T17:06:47Z","doi":"10.1002/2050-7038.12538/v3/review2","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1103/physrevlett.85.210","name":"Random Networks of Spiking Neurons: Instability in the<b><i>Xenopus</i></b>Tadpole Moto-Neural Pattern","source":"crossref","abstract":"","url":"https://doi.org/10.1103/physrevlett.85.210","authors":["Carlo Fulvi Mari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-27T02:19:41Z","doi":"10.1103/physrevlett.85.210","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.21203/rs.3.rs-2575570/v1","name":"Network learning path of university political education based on simulation data and sparse neural network","source":"crossref","abstract":"Abstract In the face of the impact of the New Coronary Pneumonia epidemic, Schools need to actively engage in online teaching in response to the Ministry of Education's call for \"uninterrupted teaching\". Ideological and political education is an important way to train socialist successors, and is the basis for establishing students' correct outlook on life, values and the world outlook. Therefore, in this paper, sparse neural network algorithm is introduced to complete the construction of ideological and political online education platform for colleges and universities. Through the design of simulation experiments, we can know that the sparse model can still maintain the stability and accuracy of the network under the condition of black box attacks, and even after a certain amount of tailoring, it can still exceed the accuracy of the original network. The experimental results show the superiority of this platform. In this paper, the platform system is roughly divided into three layers: user layer, data storage layer and functional logic layer. The evaluation is carried out from four dimensions: teaching resources, teaching activities, teacher-student interaction and teacher-student evaluation. According to the results, students have higher systematic evaluation than teachers. Among them, the recognition of teaching resources and activities is high, which proves that the platform in this paper is effective. The online teaching platform designed in this paper can make full use of the characteristics of network technology, realizes the reform and innovation development path of the ideological course in schools, and enhances the attraction of the political course and the enthusiasm of students to learn. This paper designs a kind of network education system by introducing sparse neural network into ideological online education.","url":"https://doi.org/10.21203/rs.3.rs-2575570/v1","authors":["Kaixuan Shao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-02-21T17:23:22Z","doi":"10.21203/rs.3.rs-2575570/v1","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.21203/rs.3.rs-3596530/v1","name":"Pipeline Parallelism with Reduced Network Communications for Efficient Compute-intensive Neural Network Training","source":"crossref","abstract":"Abstract Pipeline parallelism is a distributed deep neural network training method suitable for tasks that consume large amounts of memory. However, this method entails a large amount of overhead because of the dependency between devices in performing forward and backward steps through multiple devices. A method to remove forward step dependency through the all-to-all approach has been proposed for the compute-intensive models; however, this method incurs large overhead when training with a large number of devices and is inefficient in terms of weight memory consumption. Therefore, we propose a pipeline parallelism method that reduces network communication using a self-generation concept and simultaneously reduces overhead by minimizing the weight memory used for acceleration. In a Darknet53 training throughput experiment using six devices, the proposed method showed excellent performance of approximately 63.7% compared to the baseline by reduced overhead and communication costs and showed less memory consumption of approximately 17.0%.","url":"https://doi.org/10.21203/rs.3.rs-3596530/v1","authors":["Chanhee Yu","Kyongseok Park"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-20T06:40:29Z","doi":"10.21203/rs.3.rs-3596530/v1","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.21203/rs.3.rs-2791980/v1","name":"Network Traffic Prediction Based on the Multi-time Granularity GRU-BP Neural Network","source":"crossref","abstract":"Abstract A multi-time granularity GRU-BP neural network is proposed in this study for network traffic prediction. In the method, the network traffic data is fitted firstly by the cubic spline curve, and the fitted data is extracted according to different time granularities. Then, several GRU neural networks corresponding to specific time granularities are used for network traffic pre-prediction. Finally, the pre-prediction results of all the GRU neural networks are fed into the fully connected neural network. The fully connected neural network outputs the final network traffic prediction results. Comparison results show that the proposed method can improve the calculation accuracy by 9.0% and reduce the calculation time by 28.6%.","url":"https://doi.org/10.21203/rs.3.rs-2791980/v1","authors":["wang haipeng","Shuai Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-18T04:24:14Z","doi":"10.21203/rs.3.rs-2791980/v1","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.5220/0014376900004861","name":"Graph Neural Network: Review of Models, Challenges and Frontier Applications","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0014376900004861","authors":["Zirui Zhu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-31T09:12:18Z","doi":"10.5220/0014376900004861","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.3390/eng6110304","name":"A Practical Tutorial on Spiking Neural Networks: Comprehensive Review, Models, Experiments, Software Tools, and Implementation Guidelines","source":"crossref","abstract":"Spiking neural networks (SNNs) provide a biologically inspired, event-driven alternative to artificial neural networks (ANNs), potentially delivering competitive accuracy at substantially lower energy. This tutorial-study offers a unified, practice-oriented assessment that combines critical review and standardized experiments. We benchmark a shallow fully connected network (FCN) on MNIST and a deeper VGG7 architecture on CIFAR-10 across multiple neuron models (leaky integrate-and-fire (LIF), sigma–delta, etc.) and input encodings (direct, rate, temporal, etc.), using supervised surrogate-gradient training implemented in Intel Lava, SLAYER, SpikingJelly, Norse, and PyTorch. Empirically, we observe a consistent but tunable trade-off between accuracy and energy. On MNIST, sigma–delta neurons with rate or sigma–delta encodings achieve 98.1% accuracy (ANN baseline: 98.23%). On CIFAR-10, sigma–delta neurons with direct input reach 83.0% accuracy at just two time steps (ANN baseline: 83.6%). A GPU-based operation-count energy proxy indicates that many SNN configurations operate below the ANN energy baseline; some frugal codes minimize energy at the cost of accuracy, whereas accuracy-oriented settings (e.g., sigma–delta with direct or rate coding) narrow the performance gap while remaining energy-conscious—yielding up to threefold efficiency compared with matched ANNs in our setup. Thresholds and the number of time steps are decisive factors: intermediate thresholds and the minimal time window that still meets accuracy targets typically maximize efficiency per joule. We distill actionable design rules—choose the neuron–encoding pair according to the application goal (accuracy-critical vs. energy-constrained) and co-tune thresholds and time steps. Finally, we outline how event-driven neuromorphic hardware can amplify these savings through sparse, local, asynchronous computation, providing a practical playbook for embedded, real-time, and sustainable AI deployments.","url":"https://doi.org/10.3390/eng6110304","authors":["Bahgat Ayasi","Cristóbal J. Carmona","Mohammed Saleh","Angel M. García-Vico"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-03T14:00:33Z","doi":"10.3390/eng6110304","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/mnano.2021.3098219","name":"Advances in Neuromorphic Spin-Based Spiking Neural Networks: A review","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mnano.2021.3098219","authors":["Gaurav Verma","Namita Bindal","Arshid Nisar","Seema Dhull","Brajesh Kumar Kaushik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-08-13T15:54:40Z","doi":"10.1109/mnano.2021.3098219","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.5256/f1000research.149233.r208772","name":"Peer Review Report For: Graph neural network-based anomaly detection for river network systems [version 1; peer review: 2 approved with reservations]","source":"crossref","abstract":"","url":"https://doi.org/10.5256/f1000research.149233.r208772","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-25T14:52:05Z","doi":"10.5256/f1000research.149233.r208772","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.21203/rs.3.rs-9709207/v1","name":"CTP-Hybrid: From Hybrid Architecture to Native Spiking Foundation — A Two-Phase Report on Consumer-GPU Spiking LLMs","source":"crossref","abstract":"Abstract We present the complete two-phase development of CTP-Hybrid, a causal-topological pulsing architecture for large language models. Phase 1 established the first reproducible 7B-scale spiking-augmented LLM fine-tuning on an 8 GB consumer GPU (NVIDIA RTX 5060 Laptop), achieving WikiText-2 perplexity of 16.58 with fluent Chinese generation using TD-SCA microcolumns. However, full tri-module joint training (IST+TCP+DSM) failed across seven attempts due to gradient collapse from discrete pulse operations. Phase 2 resolved this fundamentally. We designed three custom autograd.Function implementations—IntervalSpikeEncoder, TemporalCausalMask, and LIFSpikeSurrogate—that provide stable surrogate gradients for previously non-differentiable pulse operations. These functions enabled: (1) the first successful tri-module joint training on a 7B hybrid model with zero NaN, and (2) a fully Transformer-free, 20M-parameter pure spiking baseline trained from scratch on WikiText-2, achieving a perplexity of 13.57. The pure spiking model contains no self-attention, no LayerNorm, and no floating-point FFN, proving that native pulse computation alone can learn natural language. All code, weights, and experiment logs are released.","url":"https://doi.org/10.21203/rs.3.rs-9709207/v1","authors":["Shutong Hou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-15T06:28:07Z","doi":"10.21203/rs.3.rs-9709207/v1","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1088/0954-898x/9/4/001","name":"A review of methods for spike sorting: the detection and classification of neural action potentials","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/9/4/001","authors":["Michael Lewicki"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-24T22:35:54Z","doi":"10.1088/0954-898x/9/4/001","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.2139/ssrn.6303961","name":"Exceptional Adversarial Robustness Through Architectural Design: A Comparative Study of Classical and Spiking Neural Networks","source":"crossref","abstract":"Adversarial attacks pose a significant threat to the deployment of deep neural networks in safetycritical applications. Achieving robustness without sacrificing clean accuracy remains a key challenge. In this work, we show that careful architectural design alone can provide substantial adversarial robustness without any adversarial training. Through systematic evaluation on MNIST under FGSM and PGD attacks, we demonstrate that a properly designed classical CNN experiences only 2.0%accuracy degradation under strong iterative PGD attacks, outperforming adversarial training methods (5-8% degradation), TRADES (4-6%), and other state-of-the-art defenses. Spiking neural networks (SNNs) achieve 4.3% degradation through their temporal dynamics. Our analysis indicates that strategic placement of dropout and pooling, combined with moderate model capacity, yields inherent robustness that rivals more complex defense mechanisms. These results suggest that architectural design should serve as a first line of defense in safety-critical neural network deployments.","url":"https://doi.org/10.2139/ssrn.6303961","authors":["Abraham Itzhak Weinberg"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-16T17:30:59Z","doi":"10.2139/ssrn.6303961","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/72.774270","name":"Solving graph algorithms with networks of spiking neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1109/72.774270","authors":["D.M. Sala","K.J. Cios"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-24T19:16:32Z","doi":"10.1109/72.774270","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1142/s021963521650028x","name":"Decision making under uncertainty in a spiking neural network model of the basal ganglia","source":"crossref","abstract":"","url":"https://doi.org/10.1142/s021963521650028x","authors":["Charlotte Héricé","Radwa Khalil","Marie Moftah","Thomas Boraud","Martin Guthrie","André Garenne"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-12-22T01:23:18Z","doi":"10.1142/s021963521650028x","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/access.2020.3041946","name":"Area- and Energy-Efficient STDP Learning Algorithm for Spiking Neural Network SoC","source":"crossref","abstract":"","url":"https://doi.org/10.1109/access.2020.3041946","authors":["Giseok Kim","Kiryong Kim","Sara Choi","Hyo Jung Jang","Seong-Ook Jung"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-02T21:17:05Z","doi":"10.1109/access.2020.3041946","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.3389/fnins.2022.909146","name":"A cerebellum inspired spiking neural network as a multi-model for pattern classification and robotic trajectory prediction","source":"crossref","abstract":"Spiking neural networks were introduced to understand spatiotemporal information processing in neurons and have found their application in pattern encoding, data discrimination, and classification. Bioinspired network architectures are considered for event-driven tasks, and scientists have looked at different theories based on the architecture and functioning. Motor tasks, for example, have networks inspired by cerebellar architecture where the granular layer recodes sparse representations of the mossy fiber (MF) inputs and has more roles in motor learning. Using abstractions from cerebellar connections and learning rules of deep learning network (DLN), patterns were discriminated within datasets, and the same algorithm was used for trajectory optimization. In the current work, a cerebellum-inspired spiking neural network with dynamics of cerebellar neurons and learning mechanisms attributed to the granular layer, Purkinje cell (PC) layer, and cerebellar nuclei interconnected by excitatory and inhibitory synapses was implemented. The model’s pattern discrimination capability was tested for two tasks on standard machine learning (ML) datasets and on following a trajectory of a low-cost sensor-free robotic articulator. Tuned for supervised learning, the pattern classification capability of the cerebellum-inspired network algorithm has produced more generalized models than data-specific precision models on smaller training datasets. The model showed an accuracy of 72%, which was comparable to standard ML algorithms, such as MLP (78%), Dl4jMlpClassifier (64%), RBFNetwork (71.4%), and libSVM-linear (85.7%). The cerebellar model increased the network’s capability and decreased storage, augmenting faster computations. Additionally, the network model could also implicitly reconstruct the trajectory of a 6-degree of freedom (DOF) robotic arm with a low error rate by reconstructing the kinematic parameters. The variability between the actual and predicted trajectory points was noted to be ± 3 cm (while moving to a position in a cuboid space of 25 × 30 × 40 cm). Although a few known learning rules were implemented among known types of plasticity in the cerebellum, the network model showed a generalized processing capability for a range of signals, modulating the data through the interconnected neural populations. In addition to potential use on sensor-free or feed-forward based controllers for robotic arms and as a generalized pattern classification algorithm, this model adds implications to motor learning theory.","url":"https://doi.org/10.3389/fnins.2022.909146","authors":["Asha Vijayan","Shyam Diwakar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-28T05:18:15Z","doi":"10.3389/fnins.2022.909146","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1007/978-3-031-43078-7_53","name":"TM-SNN: Threshold Modulated Spiking Neural Network for Multi-task Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-43078-7_53","authors":["Paolo G. Cachi","Sebastián Ventura Soto","Krzysztof J. Cios"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-30T18:02:23Z","doi":"10.1007/978-3-031-43078-7_53","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.58830/ozgur.pub1236.c5001","name":"Concepts of Machine Learning","source":"crossref","abstract":"This chapter introduces the fundamental concepts and principles of machine learning, serving as a theoretical foundation for the subsequent chapters of the book. It provides a comprehensive overview of the main learning paradigms, including supervised, unsupervised, semi-supervised, and reinforcement learning, along with essential terminology and notations commonly used in machine learning research and applications. Key topics such as data representation, preprocessing techniques, feature engineering, and the learning process are discussed to highlight how raw data is transformed into meaningful knowledge through computational models. The chapter also explains core concepts related to model training, generalization, overfitting, and the bias–variance tradeoff, which are critical for understanding model performance and reliability. In addition, fundamental ideas in optimization and model evaluation are presented, including cost functions, gradient-based learning, and standard performance metrics. Ethical and practical considerations, such as data bias, interpretability, and privacy, are briefly addressed to emphasize responsible use of machine learning technologies. Overall, this chapter establishes a conceptual framework that enables readers to better understand, design, and critically evaluate machine learning systems.","url":"https://doi.org/10.58830/ozgur.pub1236.c5001","authors":["Yousef Farhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-19T11:20:19Z","doi":"10.58830/ozgur.pub1236.c5001","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1088/2634-4386/ae8627/v1/decision1","name":"Decision letter for \"Energy-aware spike budgeting for continual learning in spiking neural networks for neuromorphic vision\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2634-4386/ae8627/v1/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-03T23:27:36Z","doi":"10.1088/2634-4386/ae8627/v1/decision1","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1016/j.parco.2022.102952","name":"Routing brain traffic through the von Neumann bottleneck: Efficient cache usage in spiking neural network simulation code on general purpose computers","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.parco.2022.102952","authors":["J. Pronold","J. Jordan","B.J.N. Wylie","I. Kitayama","M. Diesmann","S. Kunkel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-07-13T11:53:55Z","doi":"10.1016/j.parco.2022.102952","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1515/jisys-2024-0235","name":"Hyperparameters optimization of evolving spiking neural network using artificial bee colony for unsupervised anomaly detection","source":"crossref","abstract":"Abstract Nowadays, anomaly detection in streaming data has gained considerable attention due to the exponential growth in the data gathered by Internet of Things applications. Analyzing and processing vast data volumes requires a system capable of working in real-time. Moreover, obtaining labeled data for supervised learning is challenging, as it requires human involvement, is time-consuming, and costly. A promising direction is implementing evolving spiking neural networks (eSNN), which can be updated whenever new data becomes available without re-training previous samples. However, eSNN encounters significant challenges when it comes to manually tuning its hyperparameter values. As such, this work covers the current research gap by suggesting a novel method to optimize the hyperparameters of eSNN called online evolving spiking neural networks-artificial bee colony (OeSNN-ABC). Multiple scenarios have been utilized to evaluate the proposed method using two benchmark datasets: the Numenta anomaly benchmark (NAB) and the Yahoo Webscope using different criteria. Further validation was provided by comparing the proposed OeSNN-ABC against five well-known optimization algorithms: particle swarm optimization, grey wolf optimization, flower pollination algorithm, whale optimization algorithm, and grid search, alongside other classifiers such as random forest, support vector machine, and k-nearest neighbor. The findings revealed that OeSNN-ABC had the best performance among all compared optimization algorithms and classifiers, outperformed prior anomaly detection techniques for the NAB dataset, and achieved competitive results for the Yahoo Webscope dataset.","url":"https://doi.org/10.1515/jisys-2024-0235","authors":["Rabie Rehan","Shahnorbanun Sahran","Zaid Abdi Alkareem Alyasseri","Nor Samsiah Sani","Mohammed Azmi Al-Betar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-22T14:56:42Z","doi":"10.1515/jisys-2024-0235","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.15302/j-sscae-2023.06.011","name":"A Review of Recent Advances and Application for Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.15302/j-sscae-2023.06.011","authors":["Hao Liu","Hongfeng Chai","Quan Sun","Xin Yun","Xin Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-15T09:18:17Z","doi":"10.15302/j-sscae-2023.06.011","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/tcds.2024.3406168","name":"Event-Based Depth Prediction With Deep Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tcds.2024.3406168","authors":["Xiaoshan Wu","Weihua He","Man Yao","Ziyang Zhang","Yaoyuan Wang","Bo Xu","Guoqi Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-10T17:35:03Z","doi":"10.1109/tcds.2024.3406168","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1016/j.inffus.2025.103526","name":"Quantum-inspired complex spiking neural network for multi-source data joint classification","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.inffus.2025.103526","authors":["Yang Liu","Yahui Li","Haige Xu","Yinghao Lin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-22T16:05:19Z","doi":"10.1016/j.inffus.2025.103526","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1007/978-981-99-8565-4_6","name":"Finger Vein Recognition Based on Unsupervised Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-99-8565-4_6","authors":["Li Yang","Xiang Xu","Qiong Yao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-01T06:03:13Z","doi":"10.1007/978-981-99-8565-4_6","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.3389/fnins.2020.00551","name":"An On-chip Spiking Neural Network for Estimation of the Head Pose of the iCub Robot","source":"crossref","abstract":"","url":"https://doi.org/10.3389/fnins.2020.00551","authors":["Raphaela Kreiser","Alpha Renner","Vanessa R. C. Leite","Baris Serhan","Chiara Bartolozzi","Arren Glover","Yulia Sandamirskaya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-23T15:01:16Z","doi":"10.3389/fnins.2020.00551","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/aicas48895.2020.9073840","name":"Fully-Integrated Spiking Neural Network Using SiO<sub>x</sub>-Based RRAM as Synaptic Device","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aicas48895.2020.9073840","authors":["Amir REGEV","Alessandro BRICALLI","Giuseppe PICCOLBONI","Alexandre VALENTIAN","Thomas MESQUIDA","Gabriel MOLAS","Jean-Francois NODIN"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-04-24T01:16:57Z","doi":"10.1109/aicas48895.2020.9073840","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/icra57147.2024.10610553","name":"Probabilistic Spiking Neural Network for Robotic Tactile Continual Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icra57147.2024.10610553","authors":["Senlin Fang","Yiwen Liu","Chengliang Liu","Jingnan Wang","Yuanzhe Su","Yupo Zhang","Hoiio Kong","Zhengkun Yi","Xinyu Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-08T17:51:05Z","doi":"10.1109/icra57147.2024.10610553","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1109/ner49283.2021.9441462","name":"On- and Off-centre Pathways in a Retino-Geniculate Spiking Neural Network on SpiNNaker","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ner49283.2021.9441462","authors":["Basabdatta Sen Bhattacharya","Teresa Serrano-Gotarredona"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-06-03T08:16:41Z","doi":"10.1109/ner49283.2021.9441462","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.36227/techrxiv.170905886.62702188/v1","name":"Accelerating Spiking Neural Networks with Parallelizable Leaky Integrate-and-Fire Neurons","source":"crossref","abstract":"Spiking Neural Networks (SNNs) express higher biological plausibility and excel at learning spatiotemporal features while consuming less energy than conventional Artificial Neural Networks (ANNs), particularly on neuromorphic hardware. The Leaky Integrate-and-Fire (LIF) neuron stands out as one of the most widely used spiking neurons in deep learning. However, its sequential information processing leads to slow training on lengthy sequences, presenting a critical challenge for real-world applications that rely on extensive datasets. This paper introduces the Parallelizable Leaky Integrate-and-Fire (ParaLIF) neuron, which accelerates SNNs by parallelizing their simulation over time, for both feedforward and recurrent architectures. When compared to LIF in neuromorphic speech, image and gesture classification tasks, ParaLIF demonstrates speeds up to 200 times faster and, on average, achieves greater accuracy with similar sparsity. Integrated into a state-of-the-art architecture, ParaLIF's accuracy matches the highest reported performance in the literature on the Spiking Heidelberg Digits (SHD) dataset. These findings highlight ParaLIF as a promising approach for the development of rapid, accurate and energy-efficient SNNs, particularly well-suited for handling massive datasets containing long sequences.","url":"https://doi.org/10.36227/techrxiv.170905886.62702188/v1","authors":["Sidi Yaya Arnaud Yarga","Sean U N Wood"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-27T13:34:25Z","doi":"10.36227/techrxiv.170905886.62702188/v1","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1101/2020.08.10.243881","name":"A spiking neural program for sensory-motor control during foraging in flying insects","source":"crossref","abstract":"Foraging is a vital behavioral task for living organisms. Behavioral strategies and abstract mathematical models thereof have been described in detail for various species. To explore the link between underlying neural circuits and computational principles we present how a biologically detailed neural circuit model of the insect mushroom body implements sensory processing, learning and motor control. We focus on cast &amp; surge strategies employed by flying insects when foraging within turbulent odor plumes. Using a spike-based plasticity rule the model rapidly learns to associate individual olfactory sensory cues paired with food in a classical conditioning paradigm. We show that, without retraining, the system dynamically recalls memories to detect relevant cues in complex sensory scenes. Accumulation of this sensory evidence on short time scales generates cast &amp; surge motor commands. Our generic systems approach predicts that population sparseness facilitates learning, while temporal sparseness is required for dynamic memory recall and precise behavioral control. Our work successfully combines biological computational principles with spike-based machine learning. It shows how knowledge transfer from static to arbitrary complex dynamic conditions can be achieved by foraging insects and may serve as inspiration for agent-based machine learning.","url":"https://doi.org/10.1101/2020.08.10.243881","authors":["Hannes Rapp","Martin Paul Nawrot"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-10T23:15:18Z","doi":"10.1101/2020.08.10.243881","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.2139/ssrn.6741860","name":"Training Spiking Neural Networks with Real-Time Propagation Through Time","source":"crossref","abstract":"Online learning for spiking neural networks (SNNs) offers a memory-efficient alternative to Backpropagation Through Time (BPTT). However, the frequent parameter perturbations inherent in online learning may exacerbate membranepotential distribution drift previously observed in offline learning. Drift-mitigation methods developed for offline learning often assume parameters remain stable across time steps, but this assumption is violated in online algorithms with single-step parameter updates. To mitigate potential drift, we propose Real-Time Propagation Through Time (RPTT), which preserves singlestep updates while incorporating two regularizers: Spatio-Temporal Gradient Regularization (STGR) for stabilizing weight updates via moving averages, and Membrane Potential Distribution Regularization (MPDR) for constraining layerwise membrane-potential statistics. We further show that the extra gradients from STGR/MPDR are bounded and do not derail the optimization direction, ensuring RPTT converges to stationary points of the empirical risk. Experiments on CIFAR-10/100, ImageNet-1k, and DVS-CIFAR10 show that RPTT outperforms prior online methods while reducing memory by over 50% relative to BPTT. Ablations verify the roles of STGR and MPDR in drift mitigation, and streaming experiments with controlled drift demonstrate that RPTT adapts better to distribution shifts than methods using delayed parameter updates.","url":"https://doi.org/10.2139/ssrn.6741860","authors":["Yaokun Wang","Wanze Chen","Tiantian Xiao","Zhiying Long"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-29T13:28:58Z","doi":"10.2139/ssrn.6741860","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:27.725Z"},{"id":"doi:10.1007/978-3-031-68409-8_3","name":"Mean Field Limits for Discrete Time Stochastic Neural Network Models","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-68409-8_3","authors":["Antonio Galves","Eva Löcherbach","Christophe Pouzat"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-16T16:03:00Z","doi":"10.1007/978-3-031-68409-8_3","addedAt":"2026-09-01T01:48:27.725Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1007/978-3-031-78940-3_15","name":"Crime Analytics on Location Based Borough Prediction Using Deep Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78940-3_15","authors":["Jibin Joseph","P. V. Anusree","K. Asha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-05T06:07:46Z","doi":"10.1007/978-3-031-78940-3_15","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-78949-6_16","name":"Assessing the Perceived Impact of Artificial Intelligence on Education","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78949-6_16","authors":["K. M. Jemima Nilofar","N. Prakash","L. Subhitcha","L. Sasvitha","V. Priyadharshini"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T09:29:19Z","doi":"10.1007/978-3-031-78949-6_16","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-030-96299-9_7","name":"Comparison of Different Machine Learning Methods to Detect Fake News","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_7","authors":["Tanishka Badhe","Janhavi Borde","Vaishnavi Thakur","Bhagyashree Waghmare","Anagha Chaudhari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_7","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-030-96299-9_8","name":"A Tool for Air Cargo Planning and Distribution","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_8","authors":["Diana Costa","André S. Santos","João A. Bastos","Ana M. Madureira","Marlene F. Brito"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_8","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1109/nabic.2010.5716297","name":"Humoral artificial immune system (HAIS) For supervised learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2010.5716297","authors":["W Ahmad","A Narayanan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-02-18T19:03:54Z","doi":"10.1109/nabic.2010.5716297","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/nabic.2009.5393410","name":"Differential subordination associated with generalised derivative operator","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393410","authors":["Mamoun Harayzeh Al-Abbadi","Maslina Darus"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393410","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/nabic.2014.6921858","name":"Hybridizing evolutionary algorithms for creating classifier ensembles","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2014.6921858","authors":["Emmanuel Dufourq","Nelishia Pillay"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-10-22T20:05:41Z","doi":"10.1109/nabic.2014.6921858","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.54097/7cvtxe67","name":"Design of a Snake-Inspired Robot for Disaster Response","source":"crossref","abstract":"In response to the urgent need for rescue operations in complex post-disaster environments, this paper presents the design and implementation of a snake-like rescue robot characterized by high mobility, strong environmental adaptability, and intelligent capabilities. Beginning with an overview of the background, the paper highlights the critical role of rescue robots in improving operational efficiency and reducing risks to human personnel. It provides an in-depth analysis of key technologies including joint structure design, control systems, communication functions, motion control, and spatial data management. The proposed robot adopts a modular architecture, integrating multiple sensors and intelligent algorithms to enable agile navigation, real-time perception, autonomous decision-making, and remote collaboration. Capable of performing detection and rescue tasks efficiently in narrow and hazardous areas, this robot offers a viable technological solution for disaster emergency response. The research lays a solid theoretical and practical foundation for advancements in the field of intelligent search and rescue robotics.","url":"https://doi.org/10.54097/7cvtxe67","authors":["Hanfei Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-01T20:07:14Z","doi":"10.54097/7cvtxe67","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/bicta.2008.4656708","name":"An evolutionary cluster validation index","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2008.4656708","authors":["Sanghoun Oh","Chang Wook Ahn","Moongu Jeon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-10-28T15:22:35Z","doi":"10.1109/bicta.2008.4656708","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-27499-2_77","name":"Implementation of the General Regulation on Data Protection – In the Intermunicipal Community of Alto Tâmega and Barroso, Portugal","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_77","authors":["Pascoal Padrão","Isabel Lopes"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_77","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-27499-2_4","name":"Solar Irradiation and Wind Speed Forecasting Based on Regression Machine Learning Models","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_4","authors":["Yahia Amoura","Santiago Torres","José Lima","Ana I. Pereira"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_4","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-030-96299-9_25","name":"Detection of Social Distance and Intimation System for Covid-19","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_25","authors":["S. Anandamurugan","M. Saravana Kumar","K. Nithin","E. G. Prashanth"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_25","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-030-96299-9_50","name":"Immunity Passport Ledger","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_50","authors":["Marco Oliveira","Tomás Honório","Catarina I. Reis","Marisa Maximiano"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_50","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-030-96299-9_14","name":"A Study of Version Control System in Software Development Management Concerning PLC Environments","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_14","authors":["Domingos Costa","Senhorinha Teixeira","Leonilde R. Varela"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_14","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/ibica.2011.70","name":"Cloud Technology in the Security Management of Enterprise Document","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ibica.2011.70","authors":["Na Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-01-06T21:44:03Z","doi":"10.1109/ibica.2011.70","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/bic-ta.2011.25","name":"Double Hexagonal Array Splicing System","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bic-ta.2011.25","authors":["S.M. Saroja Theerdus Kalavathy","P. Helen Chandra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-10-18T11:35:51Z","doi":"10.1109/bic-ta.2011.25","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.4018/978-1-5225-0788-8.ch045","name":"Evaluation of Genetic Algorithm as Learning System in Rigid Space Interpretation","source":"crossref","abstract":"Genetic Algorithm (GA) (a structured framework of metaheauristics) has been used in various tasks such as search optimization and machine learning. Theoretically, there should be sound framework for genetic algorithms which can interpret/explain the various facts associated with it. There are various theories of the working of GA though all are subject to criticism. Hence an approach is being adopted that the legitimate theory of GA must be able to explain the learning process (a special case of the successive approximation) of GA. The analytical method of approximating some known function is expanding a complicated function an infinite series of terms containing some simpler (or otherwise useful) function. These infinite approximations facilitate the error to be made arbitrarily small by taking a progressive greater number of terms into consideration. The process of learning in an unknown environment, the form of function to be learned is known only by its form over the observation space. The problem of learning the possible form of the function is termed as experience problem. Various learning paradigms have ensured their legitimacy through the rigid space interpretation of the concentration of measure and Dvoretzky theorem. Hence it is being proposed that the same criterion should be applied to explain the learning capability of GA, various formalisms of explaining the working of GA should be evaluated by applying the criteria, and that learning capability can be used to demonstrate the probable capability of GA to perform beyond the limit cast by the No Free Lunch Theorem.","url":"https://doi.org/10.4018/978-1-5225-0788-8.ch045","authors":["Bhupesh Kumar Singh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-07-26T12:16:44Z","doi":"10.4018/978-1-5225-0788-8.ch045","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-0-85729-338-1_32","name":"Quantum-Inspired Evolution Algorithm: Experimental Analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-0-85729-338-1_32","authors":["F. Alfares","M. Alfares","I. I. Esat"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-02-24T21:18:08Z","doi":"10.1007/978-0-85729-338-1_32","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.3389/fnins.2025.1666218","name":"Editorial: Neural dynamics for brain-inspired control and computing: advances and applications","source":"crossref","abstract":"","url":"https://doi.org/10.3389/fnins.2025.1666218","authors":["Mei Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-14T05:34:58Z","doi":"10.3389/fnins.2025.1666218","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-030-96299-9_2","name":"Comparison of Ant Colony Optimization Algorithms for Small-Sized Travelling Salesman Problems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_2","authors":["Arcsuta Subaskaran","Marc Krähemann","Thomas Hanne","Rolf Dornberger"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_2","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-27499-2_24","name":"Apartments Waste Disposal Location Evaluation Using TOPSIS and Fuzzy TOPSIS Methods","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_24","authors":["S. M. Vadivel","V Sakthivel","L Praveena","V Chandana"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_24","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-030-96299-9_68","name":"State of the Art of Wind and Power Prediction for Wind Farms","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_68","authors":["Ricardo Puga","José Baptista","José Boaventura","Judite Ferreira","Ana Madureira"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_68","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/epec.2010.5697235","name":"Bio-inspired solution to Economic Dispatch problem using distributed computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/epec.2010.5697235","authors":["Arash Marzi","Hosein Marzi","Elham Marzi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-01-21T15:31:07Z","doi":"10.1109/epec.2010.5697235","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1145/1164394.1164395","name":"Toward nature-inspired computing","source":"crossref","abstract":"NIC-based systems utilize autonomous entities that self-organize to achieve the goals of systems modeling and problem solving.","url":"https://doi.org/10.1145/1164394.1164395","authors":["Jiming Liu","K.C. Tsui"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-18T18:11:32Z","doi":"10.1145/1164394.1164395","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/s42979-022-01292-w","name":"Bio-inspired Computing Techniques for Data Security Challenges and Controls","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s42979-022-01292-w","authors":["G Sripriyanka","Anand Mahendran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-08-06T16:02:45Z","doi":"10.1007/s42979-022-01292-w","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1515/9783111545950-203","name":"IXPreface","source":"crossref","abstract":"","url":"https://doi.org/10.1515/9783111545950-203","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-06T19:15:47Z","doi":"10.1515/9783111545950-203","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1515/9783111545950-fm","name":"Frontmatter","source":"crossref","abstract":"","url":"https://doi.org/10.1515/9783111545950-fm","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-06T19:15:47Z","doi":"10.1515/9783111545950-fm","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/bimnics.2007.4610135","name":"Achievable information rates for molecular communication with distinct molecules","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bimnics.2007.4610135","authors":["Andrew W. Eckford"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-09-08T16:06:46Z","doi":"10.1109/bimnics.2007.4610135","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-78937-3_6","name":"Prediction of Epileptic Seizures Based on EEG Dataset Using an Enhanced Extreme Learning Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_6","authors":["Sujata Dash","Sourav Kumar Giri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:07:37Z","doi":"10.1007/978-3-031-78937-3_6","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-78949-6_44","name":"Gesture Volume Control Using OTSU Method","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78949-6_44","authors":["Abdul Subhani Shaik","Merugu Suresh","B. Pooja","B. Premalatha","George Ghinea","K. Srujan Raju"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T09:29:29Z","doi":"10.1007/978-3-031-78949-6_44","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/iadcc.2014.6779490","name":"Greedy Politics Optimization: Metaheuristic inspired by political strategies adopted during state assembly elections","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iadcc.2014.6779490","authors":["J.S.M Lenord Melvix"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-04-08T21:56:13Z","doi":"10.1109/iadcc.2014.6779490","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1142/4632","name":"Brainware: Bio-Inspired Architecture and Its Hardware Implementation","source":"crossref","abstract":"","url":"https://doi.org/10.1142/4632","authors":["Tsutomu Miki"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-07-18T22:41:01Z","doi":"10.1142/4632","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.4018/978-1-4666-1574-8.ch022","name":"Mapping with Monocular Vision in Two Dimensions","source":"crossref","abstract":"This article presents the problem of building bi-dimensional maps of environments when the sensor available is a camera used to detect edges crossing a single line of pixels and motion is restricted to a straight line along the optical axis. The position over time must be provided or assumed. Mapping algorithms for these conditions can be built with the landmark parameters estimated from sets of matched detection from multiple images. This article shows how maps that are correctly up to scale can be built without knowledge of the camera intrinsic parameters or speed during uniform motion, and how performing an inverse parameterization of the image coordinates turns the mapping problem into the fitting of line segments to a group of points. The resulting technique is a simplified form of visual SLAM that can be better suited for applications such as obstacle detection in mobile robots.","url":"https://doi.org/10.4018/978-1-4666-1574-8.ch022","authors":["Nicolau Leal Werneck","Anna Helena Reali Costa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-05-10T09:54:52Z","doi":"10.4018/978-1-4666-1574-8.ch022","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/intech.2013.6653720","name":"Biologically inspired object tracking: A modular approach with distributed particle like sensors","source":"crossref","abstract":"","url":"https://doi.org/10.1109/intech.2013.6653720","authors":["Intekhab Alam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-11-11T19:56:53Z","doi":"10.1109/intech.2013.6653720","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/asyu.2018.8554034","name":"Performance Analysis of Relatively New Nature Inspired Computing Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1109/asyu.2018.8554034","authors":["Mustafa Oral","Sultan Sevgi Turgut"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-12-04T00:31:57Z","doi":"10.1109/asyu.2018.8554034","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/nabic.2009.5393696","name":"An evolutionary multi population approach for test data generation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393696","authors":["Anupama Deepak","Philip Samuel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5393696","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1201/9781003581215-28","name":"Power control of a DFIG based wind turbine using bio-inspired algorithm optimised fuzzy logic controller","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003581215-28","authors":["Satyabrata Sahoo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-13T12:22:19Z","doi":"10.1201/9781003581215-28","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.31838/jcvs/07.02.07","name":"AI-Optimized Design Automation and Quantum-Inspired Secure VLSI Architectures for Edge and Autonomous Computing","source":"crossref","abstract":"","url":"https://doi.org/10.31838/jcvs/07.02.07","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-27T07:50:52Z","doi":"10.31838/jcvs/07.02.07","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/nabic.2013.6617872","name":"Towards Scheduling Optimization through Artificial Bee Colony Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2013.6617872","authors":["Ana Madureira","Ivo Pereira","Ajith Abraham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-10-10T19:27:30Z","doi":"10.1109/nabic.2013.6617872","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.23919/date54114.2022.9774641","name":"PoisonHD: Poison Attack on Brain-Inspired Hyperdimensional Computing","source":"crossref","abstract":"","url":"https://doi.org/10.23919/date54114.2022.9774641","authors":["Ruixuan Wang","Xun Jiao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-05-19T20:35:05Z","doi":"10.23919/date54114.2022.9774641","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/nabic.2009.5393639","name":"Pattern extraction methods for ear biometrics - A survey","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393639","authors":["Kumar. P Ramesh","K.Nageswara Rao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393639","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/nabic.2009.5393690","name":"Cuckoo Search via L&amp;#x00E9;vy flights","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393690","authors":["Xin-She Yang","Suash Deb"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393690","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-27499-2_14","name":"Software Defect Prediction Using Cellular Automata as an Ensemble Strategy to Combine Classification Techniques","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_14","authors":["Flávio M. Tavares","Eduardo F. Franco"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_14","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-78940-3_18","name":"Privacy Preserving Advanced Persistent Threat Detection Using Fed-Adv-LSTM","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78940-3_18","authors":["Lokmane Heraguemi","Abdelaziz Amara Korba","Nacira Ghoualmi-Zine"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-05T06:07:15Z","doi":"10.1007/978-3-031-78940-3_18","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-78949-6_5","name":"Effectiveness on Implementation of Integrated Management System in Furniture Manufacturing Industry","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78949-6_5","authors":["P. Sundharesalingam","M. Mohanasundari","P. Vidhya Priya","M. Dhilip Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T09:29:37Z","doi":"10.1007/978-3-031-78949-6_5","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.23977/jnca.2025.100107","name":"A Nature-inspired Fully Enhanced Hybrid Algorithm Based on Intra-group Competition Mechanism","source":"crossref","abstract":"","url":"https://doi.org/10.23977/jnca.2025.100107","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-21T09:27:21Z","doi":"10.23977/jnca.2025.100107","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/icccnt.2015.7395240","name":"Leveraging biologically inspired models for cyber-physical systems analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icccnt.2015.7395240","authors":["Keith L. Keller"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-02-01T17:58:25Z","doi":"10.1109/icccnt.2015.7395240","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/nabic.2011.6089610","name":"Negotiation mechanism for self-organized scheduling system","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2011.6089610","authors":["Ana Madureira","Nelson Sousa","Ivo Pereira"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-12-06T16:02:25Z","doi":"10.1109/nabic.2011.6089610","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.4028/www.scientific.net/amr.655-657.1761","name":"Membrane Computing Model Design with Quantum-Inspired Evolutionary Algorithms","source":"crossref","abstract":"As a branch of natural computing, membrane computing has attracted much attention in various disciplines. But the programmability of membrane computing models is an ongoing and challenging issue in this area. This paper develops the automatic design of membrane computing models through predefining the membrane structure and initial objects and introducing a modified quantum-inspired evolutionary algorithm with a local disturbance to select an appropriate subset from a redundant evolution rule set. The main idea of the presented method is that multiple membrane computing models, instead of only one model like in the literature, can be designed by applying one redundant evolution rule set. The effectiveness of the design method is verified by the experiments.","url":"https://doi.org/10.4028/www.scientific.net/amr.655-657.1761","authors":["Hai Na Rong","Xiao Li Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-03-11T17:07:18Z","doi":"10.4028/www.scientific.net/amr.655-657.1761","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.4108/icst.bionetics2007.2414","name":"2-Layer Orchestration Mechanism for Service Composition","source":"crossref","abstract":"","url":"https://doi.org/10.4108/icst.bionetics2007.2414","authors":["lijun chu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-03-10T14:16:22Z","doi":"10.4108/icst.bionetics2007.2414","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1515/9783111545950","name":"Quantum and Brain-Inspired Device Modeling","source":"crossref","abstract":"","url":"https://doi.org/10.1515/9783111545950","authors":["Basudev Nag Chowdhury"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-06T19:15:47Z","doi":"10.1515/9783111545950","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-78946-5_36","name":"Analyzing Rainfall Patterns in North Indian States: A Long Short-Term Memory (LSTM) Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_36","authors":["Jeevika Rajput","Yajnaseni Dash","Ajith Abraham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:03:45Z","doi":"10.1007/978-3-031-78946-5_36","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-030-96299-9_40","name":"A Survey on the Quality of Service and Metaheuristic Based Resolution Methods for Multi-cloud IoT Service Selection","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_40","authors":["Ahmed Zebouchi","Youcef Aklouf"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_40","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-78946-5_19","name":"Multiparty Trust Levels in Evidence Management: Ensuring Tamper-Proof Chain of Custody in Blockchain","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_19","authors":["Nuno Santos","Joel Curado","Joao C. Ferreira"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:03:48Z","doi":"10.1007/978-3-031-78946-5_19","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-78943-4_19","name":"Frames of Understanding: Exploring Video Metadata Generation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78943-4_19","authors":["N. Sudarssan","S. Sumathi","V. Naveen","K. V. Visnupriya","K. Dhaanus","G. Hariharan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-03T11:07:58Z","doi":"10.1007/978-3-031-78943-4_19","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-78949-6_24","name":"A Questionnaire Based Survey Analysis of Cyber Crime in Rural and Urban Areas","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78949-6_24","authors":["Raj Sinha","Sannu Priya","Sandeep Gupta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T09:30:55Z","doi":"10.1007/978-3-031-78949-6_24","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/jssc.2020.3028298","name":"NeuroSLAM: A 65-nm 7.25-to-8.79-TOPS/W Mixed-Signal Oscillator-Based SLAM Accelerator for Edge Robotics","source":"crossref","abstract":"","url":"https://doi.org/10.1109/jssc.2020.3028298","authors":["Jong-Hyeok Yoon","Arijit Raychowdhury"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-10-13T19:44:37Z","doi":"10.1109/jssc.2020.3028298","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-78937-3_28","name":"Automatic Analysis and Detection of Multi-Channel ECG Signals Using Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_28","authors":["G. Naga Jyothi","R. Kiran Kumar","B. Subbarayudu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:06:27Z","doi":"10.1007/978-3-031-78937-3_28","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-27499-2_16","name":"The Impact of the Size of the Partition in the Performance of Bat Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_16","authors":["Bruno Sousa","André S. Santos","Ana M. Madureira"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_16","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-78943-4_3","name":"Hybridizing Ant-Colony Optimization with Other Optimization Algorithms for Solving Complex Problems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78943-4_3","authors":["S. Suriya","R. Sanjay Krishna"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-03T11:07:51Z","doi":"10.1007/978-3-031-78943-4_3","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-78949-6_17","name":"Revolutionizing Agriculture: Smart Farming with Autonomous Robots and AI","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78949-6_17","authors":["V. Vardhani","K. Vasunthara","V. Vaishnavi","T. P. Saravanan","V. Krishnamoorthy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T09:29:34Z","doi":"10.1007/978-3-031-78949-6_17","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-78946-5_53","name":"Quality-Aware Node-Level Routing Protocol for Energy-Efficient Cognitive Wireless Sensor Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_53","authors":["Rajashekar Reddy Eduru","Suraya Mubeen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:04:21Z","doi":"10.1007/978-3-031-78946-5_53","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-540-85954-3_3","name":"From The Wisdom of the Hive to Routing in Telecommunication Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-540-85954-3_3","authors":["Muddassar Farooq"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-11-28T15:10:40Z","doi":"10.1007/978-3-540-85954-3_3","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-319-44989-0_9","name":"Is Biologically Inspired Design Domain Independent?","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-44989-0_9","authors":["Ashok K. Goel","Christian Tuchez","William Hancock","Keith Frazer"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-01-02T01:31:03Z","doi":"10.1007/978-3-319-44989-0_9","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.4018/978-1-5225-0788-8.ch020","name":"Innovative Hierarchical Fuzzy Logic for Modelling Using Evolutionary Algorithms","source":"crossref","abstract":"This paper considers issues in the design and construction of a fuzzy logic system to model complex (nonlinear) systems. Several important applications are considered and methods for the decomposition of complex systems into hierarchical and multi-layered fuzzy logic sub-systems are proposed. The learning of fuzzy rules and internal parameters is performed using evolutionary computing. The proposed method using decomposition and conversion of systems into hierarchical and multi-layered fuzzy logic sub-systems reduces greatly the number of fuzzy rules to be defined and improves the learning speed for such systems. However such decomposition is not unique and may give rise to variables with no physical significance. This can raise then major difficulties in obtaining a complete class of rules from experts even when the number of variables is small. Application areas considered are: the prediction of interest rate, hierarchical control of the inverted pendulum, robot control, feedback boundary control for a distributed optimal control system and image processing.","url":"https://doi.org/10.4018/978-1-5225-0788-8.ch020","authors":["M. Mohammadian","R. J. Stonier"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-07-26T12:16:44Z","doi":"10.4018/978-1-5225-0788-8.ch020","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-030-37218-7_80","name":"Breast Cancer Detection Using CNN on Mammogram Images","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_80","authors":["Kushal Batra","Sachin Sekhar","R. Radha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T20:02:40Z","doi":"10.1007/978-3-030-37218-7_80","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-319-28031-8_51","name":"Optimal Reservoir Release for Hydropower Generation Maximization Using Particle Swarm Optimization","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-28031-8_51","authors":["D. Kiruthiga","T. Amudha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-13T20:02:33Z","doi":"10.1007/978-3-319-28031-8_51","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/0-387-27705-6_16","name":"Cluster Computing: High-Performance, High-Availability, and High-Throughput Processing on a Network of Computers","source":"crossref","abstract":"","url":"https://doi.org/10.1007/0-387-27705-6_16","authors":["Chee Shin Yeo","Rajkumar Buyya","Hossein Pourreza","Rasit Eskicioglu","Peter Graham","Frank Sommers"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-03-23T01:57:04Z","doi":"10.1007/0-387-27705-6_16","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1016/j.ascom.2026.101168","name":"Brain-inspired quantum machine learning architecture and its benchmarking on astronomical classification","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.ascom.2026.101168","authors":["Subhash S. Pandey","Mousam Mondal","Xing Liang","Christos Kalyvas","Dimitrios Makris","Hongwei Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-20T07:04:46Z","doi":"10.1016/j.ascom.2026.101168","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1016/j.tcs.2008.04.013","name":"A DNA computing inspired computational model","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.tcs.2008.04.013","authors":["Giuditta Franco","Maurice Margenstern"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-04-11T19:26:46Z","doi":"10.1016/j.tcs.2008.04.013","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/bimnics.2007.4610069","name":"Welcome from the bioinformatics track co-chairs","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bimnics.2007.4610069","authors":["Scott F. Smith","Alioune Ngom"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-09-08T20:06:46Z","doi":"10.1109/bimnics.2007.4610069","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-0-387-34733-2_12","name":"A Reconfigurable Ethernet Switch for Self-Optimizing Communication Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-0-387-34733-2_12","authors":["Björn Griese","Mario Porrmann"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-11-27T12:41:06Z","doi":"10.1007/978-0-387-34733-2_12","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/ibica.2011.38","name":"CTS: The New Generation Intelligent Transportation System","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ibica.2011.38","authors":["Wen-Hai Cai","Ting-Ting Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-01-06T21:44:03Z","doi":"10.1109/ibica.2011.38","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/bimnics.2007.4610083","name":"Asynchronous team algorithms for Boolean Satisfiability","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bimnics.2007.4610083","authors":["Carlos Rodriguez","Marcos Villagra","Benjamin Baran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-09-08T20:06:46Z","doi":"10.1109/bimnics.2007.4610083","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-540-92191-2_3","name":"Modelling Gene Regulatory Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-540-92191-2_3","authors":["Erol Gelenbe"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-11-26T16:08:36Z","doi":"10.1007/978-3-540-92191-2_3","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/nabic.2009.5393640","name":"Group-oriented signature schemes based on Chinese remainder theorem","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393640","authors":["C. Porkodi","R. Arumuganathan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393640","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-78949-6_18","name":"AI in Tourism: Digital Marketing and Customer Satisfaction","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78949-6_18","authors":["V. Vaishnavi","P. N. Brindha","S. Pooja","T. Visali","P. Karthikeyan","N. Prakash"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T09:29:48Z","doi":"10.1007/978-3-031-78949-6_18","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-78946-5_4","name":"StrategicVideoRec: A Strategic Approach for Scientific Video Recommendation Integrating BERT and Fact Driven Semantics","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_4","authors":["M. Prathibha","Gerard Deepak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:04:09Z","doi":"10.1007/978-3-031-78946-5_4","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-78949-6_10","name":"Digital Innovation in Tourism: Exploring the Potential of Chatbots","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78949-6_10","authors":["Isabel Lopes","Teresa Guarda","Pedro Oliveira","Paula Odete Fernandes"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T09:29:48Z","doi":"10.1007/978-3-031-78949-6_10","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-78949-6_51","name":"Smart Technologies System Implementation Using a Case Study in the South African Library Education Sector","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78949-6_51","authors":["Oluwasegun Julius Aroba","Michael Rudolph"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T09:29:58Z","doi":"10.1007/978-3-031-78949-6_51","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-27499-2_32","name":"Breast Cancer Identification Using Improved DarkNet53 Model","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_32","authors":["Noor Ul Huda Shah","Rabbia Mahum","Dur e Maknoon Nisar","Noor Ul Aman","Tabinda Azim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_32","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-662-06369-9_5","name":"Embryonics and Immunotronics: Biologically Inspired Computer Science Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-662-06369-9_5","authors":["A. Tyrrell"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-02-06T05:08:10Z","doi":"10.1007/978-3-662-06369-9_5","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1016/j.neucom.2012.05.014","name":"Bio-inspired computing and applications (LSMS-ICSEE, 2010)","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2012.05.014","authors":["Kang Li","Xia Hong","Guido Maione","Qun Niu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-06-06T02:57:58Z","doi":"10.1016/j.neucom.2012.05.014","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/nabic.2009.5393652","name":"Systems biology markup language for cancer system","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393652","authors":["Suryasarathi Barat","Avishek Das","Durjoy Majumder"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5393652","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-981-15-3836-0_5","name":"DCS Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-15-3836-0_5","authors":["Aziz Ouaarab"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-03-24T13:02:55Z","doi":"10.1007/978-981-15-3836-0_5","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-981-10-6747-1_1","name":"EasyOnto: A Collaborative Semiformal Ontology Development Platform","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-10-6747-1_1","authors":["Usha Yadav","B. K. Murthy","Gagandeep Singh Narula","Neelam Duhan","Vishal Jain"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-10-04T08:25:22Z","doi":"10.1007/978-981-10-6747-1_1","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-319-76354-5_6","name":"A Survey of Cross-Layer Design for Wireless Visual Sensor Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-76354-5_6","authors":["Afaf Mosaif","Said Rakrak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-09T11:43:48Z","doi":"10.1007/978-3-319-76354-5_6","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-981-97-7344-2","name":"Solving with Bees","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-7344-2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-01T08:28:09Z","doi":"10.1007/978-981-97-7344-2","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1201/9781003143499-16","name":"The Neural Engineering Framework (NEF)","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003143499-16","authors":["Elishai Ezra Tsur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-07-19T12:30:34Z","doi":"10.1201/9781003143499-16","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/s12559-013-9215-2","name":"Advances on Brain Inspired Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s12559-013-9215-2","authors":["Stefano Squartini","Sanqing Hu","Qingshan Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-03-21T00:12:30Z","doi":"10.1007/s12559-013-9215-2","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/camp.2005.56","name":"Bio-Inspired Computing Architectures: The Embryonics Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1109/camp.2005.56","authors":["G. Tempesti","D. Mange","A. Stauffer"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-11T16:54:11Z","doi":"10.1109/camp.2005.56","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/ibica.2011.94","name":"Smart Classroom Roll Caller System with IOT Architecture","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ibica.2011.94","authors":["Ching Hisang Chang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-01-06T16:44:03Z","doi":"10.1109/ibica.2011.94","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1002/9783527835317.ch6","name":"Neuromorphic Computing Systems with Emerging Devices","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9783527835317.ch6","authors":["Qiumeng Wei","Jianshi Tang","Bin Gao","Xinyi Li","He Qian","Huaqiang Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-17T21:34:07Z","doi":"10.1002/9783527835317.ch6","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-319-28031-8_14","name":"A Novel Approach for Malicious Node Detection in MANET","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-28031-8_14","authors":["K. P. Anjana","K. G. Preetha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-14T01:02:33Z","doi":"10.1007/978-3-319-28031-8_14","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-319-96451-5_11","name":"Enhanced Throughput and Accelerated Detection of Network Attacks Using a Membrane Computing Model Implemented on a GPU","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-96451-5_11","authors":["Rufai Kazeem Idowu","Ravie Chandren Muniyandi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-08-29T18:31:42Z","doi":"10.1007/978-3-319-96451-5_11","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.5120/ijca2017913028","name":"Nature Inspired Algorithms for Load Balancing in Cloud Computing","source":"crossref","abstract":"","url":"https://doi.org/10.5120/ijca2017913028","authors":["Sebagenzi Jason","Suchithra R."],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-02-15T12:42:06Z","doi":"10.5120/ijca2017913028","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/icpics66386.2025.11347435","name":"Bio-Inspired Visual Navigation System for Insectsized Flying Robots","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icpics66386.2025.11347435","authors":["Weixin Xiong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-28T20:54:45Z","doi":"10.1109/icpics66386.2025.11347435","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/reconfig.2008.68","name":"Fast Implementation of a Bio-inspired Model for Decentralized Gathering","source":"crossref","abstract":"","url":"https://doi.org/10.1109/reconfig.2008.68","authors":["Bernard Girau","Cesar Torres-Huitzel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-01-14T18:57:00Z","doi":"10.1109/reconfig.2008.68","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/mind67540.2025.11351613","name":"Spatiotemporal Enhanced Joint Optimization for Spike Camera Based 3D Reconstruction","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mind67540.2025.11351613","authors":["Binqiang Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-27T04:49:35Z","doi":"10.1109/mind67540.2025.11351613","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-78946-5_26","name":"Sentiment Analysis of Online Product Reviews Using CNN-LSTM Cascaded Deep Learning Architecture","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_26","authors":["Ancy Rominus","Chinju John","Jayakrushna Sahoo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:04:03Z","doi":"10.1007/978-3-031-78946-5_26","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1145/3811628.3811831","name":"Connecting Probabilistic Databases to Quantum Computing and Tensor Networks via Graphical Models","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3811628.3811831","authors":["Valter Uotila"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-04T10:29:31Z","doi":"10.1145/3811628.3811831","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-030-37218-7_117","name":"Advanced Techniques to Enhance Human Visual Ability – A Review","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_117","authors":["A. Vani","M. N. Mamatha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T15:02:40Z","doi":"10.1007/978-3-030-37218-7_117","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1002/9780470429983.ch20","name":"Concluding Remarks at the Beginning of a New Computing ERA","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9780470429983.ch20","authors":["Varun Bhojwani","Stephen Chu","Mary Mehrnoosh Eshaghian‐Wilner","Shawn Singh","Chun Wing Yip"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-11-24T16:16:40Z","doi":"10.1002/9780470429983.ch20","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1016/j.asoc.2011.08.019","name":"Prediction of scouring around an arch-shaped bed sill using Neuro-Fuzzy model","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2011.08.019","authors":["Alireza Keshavarzi","Reza Gazni","Seyed Rahman Homayoon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-08-23T00:38:17Z","doi":"10.1016/j.asoc.2011.08.019","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-78946-5_34","name":"Generalized Skin Cancer Image Classification Performance Using Xception Model","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_34","authors":["Qurban A. Memon","Ghaya Al Ameri","Namya Musthafa","Aryam AlShamsi","Aisha AlYaqoubi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:04:22Z","doi":"10.1007/978-3-031-78946-5_34","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-78940-3_24","name":"Machine Learning-Based Multimodal Depression Diagnosis for IT Personnel Using CCTV and Messaging Streams","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78940-3_24","authors":["B. Manjulatha","Suresh Pabboju"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-05T06:07:29Z","doi":"10.1007/978-3-031-78940-3_24","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-031-78949-6_12","name":"Area Efficient Lightweight Cipher System Implementation for Edge Device","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78949-6_12","authors":["Aditi Kumari","Ankita Mondal","Aditi Kumari","Tribeni Prasad Banerjee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T09:30:43Z","doi":"10.1007/978-3-031-78949-6_12","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-3-030-96299-9_47","name":"Designing Green Routing and Scheduling for Home Health Care","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_47","authors":["Hossein Shokri Garjan","Alireza Abbaszadeh Molaei","Fariba Goodarzian","Ajith Abraham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_47","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/prdc.2011.27","name":"Bio-inspired Error Detection for Complex Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/prdc.2011.27","authors":["Martin Drozda","Iain Bate","Jon Timmis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-01-30T21:48:07Z","doi":"10.1109/prdc.2011.27","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1109/bicta.2010.5645281","name":"Palindromic completion of a word","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2010.5645281","authors":["Kalpana Mahalingam","K.G. Subramanian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-12-09T10:33:18Z","doi":"10.1109/bicta.2010.5645281","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch056","name":"Multiattribute Methodologies in Financial Decision Aid","source":"crossref","abstract":"This chapter introduces the capability of the numerical multi-dimensional approach to solve complex problems in finance. It is well known how, with the growth of computational resource, scientists have developed numerical algorithms for the resolution of complex systems, in order to find the relations between the different components. One important field in this research is focused on the mimic of nature behavior to solve problems. In this chapter two technologies based on these techniques, self-organizing maps and multi-objectives genetic algorithm, have been used to solve two important fields in finance: the country risk assessment and the time series forecasting. The authors, through the examples in the chapter, would like to demonstrate how a multi-dimensional approach based on the mimic of nature could be useful to solve modern complex problems in finance.","url":"https://doi.org/10.4018/978-1-59140-984-7.ch056","authors":["M. Ciprian","M. Kaucic"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch056","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1007/978-981-33-6862-0_61","name":"Survey of Image Processing Techniques in Medical Image Assessment Methodologies","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-33-6862-0_61","authors":["Anandakumar Haldorai","Arulmurugan Ramu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-06-14T05:02:45Z","doi":"10.1007/978-981-33-6862-0_61","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.1287/ijoc.2022.0184","name":"An Interior Point–Inspired Algorithm for Linear Programs Arising in Discrete Optimal Transport","source":"crossref","abstract":"Discrete optimal transport problems give rise to very large linear programs (LPs) with a particular structure of the constraint matrix. In this paper, we present a hybrid algorithm that mixes an interior point method (IPM) and column generation, specialized for the LP originating from the Kantorovich optimal transport problem. Knowing that optimal solutions of such problems display a high degree of sparsity, we propose a column generation–like technique to force all intermediate iterates to be as sparse as possible. The algorithm is implemented nearly matrix-free. Indeed, most of the computations avoid forming the huge matrices involved and solve the Newton system using only a much smaller Schur complement of the normal equations. We prove theoretical results about the sparsity pattern of the optimal solution, exploiting the graph structure of the underlying problem. We use these results to mix iterative and direct linear solvers efficiently in a way that avoids producing preconditioners or factorizations with excessive fill-in and at the same time guaranteeing a low number of conjugate gradient iterations. We compare the proposed method with two state-of-the-art solvers and show that it can compete with the best network optimization tools in terms of computational time and memory use. We perform experiments with problems reaching more than four billion variables and demonstrate the robustness of the proposed method. History: Accepted by Antonio Frangioni, Area Editor for Design &amp; Analysis of Algorithms–Continuous. Funding: F. Zanetti received funding from the University of Edinburgh, in the form of a PhD scholarship. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2022.0184 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2022.0184 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .","url":"https://doi.org/10.1287/ijoc.2022.0184","authors":["Filippo Zanetti","Jacek Gondzio"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-12T12:50:40Z","doi":"10.1287/ijoc.2022.0184","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.964Z"},{"id":"doi:10.4018/979-8-3693-6303-4.ch009","name":"Enhancing Assistive Technologies With Neuromorphic Computing","source":"crossref","abstract":"The development of intelligent neuroprosthetics, which promise to augment human brain function is vital for augmentative assistive technologies. Neuromorphic sensors and processors are particularly adept at mimicking the brain's efficient sensory processing, offering assistive devices an advanced capability to perceive and interpret complex environmental stimuli. The application of these technologies in brain computer interfaces suggests a future where transformative advancements are not only possible but imminent, facilitating novel methods of human-computer interaction and providing insights into the intricate workings of the brain through advanced AI and machine learning techniques. This paper explores the integration of neuromorphic technologies with brain-computer interfaces (BCIs), highlighting the potential to enhance assistive devices and revolutionize communication and healthcare. However, the realization of neuromorphic computing's full potential within BCIs is contingent upon overcoming significant technological and ethical challenges.","url":"https://doi.org/10.4018/979-8-3693-6303-4.ch009","authors":["G. V. S. Anil Chandra","Bhanuprakash Ananthakumar","Ramya Raghavan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-29T15:16:27Z","doi":"10.4018/979-8-3693-6303-4.ch009","addedAt":"2026-09-01T01:48:27.964Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1109/bimnics.2007.4610077","name":"An information theoretical approach for molecular communication","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bimnics.2007.4610077","authors":["Baris Atakan","Ozgur B. Akan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-09-08T16:06:46Z","doi":"10.1109/bimnics.2007.4610077","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1109/icac3n53548.2021.9725366","name":"Nature Inspired Routing in Mobile Ad Hoc Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icac3n53548.2021.9725366","authors":["Yajnaseni Dash"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-09T15:31:58Z","doi":"10.1109/icac3n53548.2021.9725366","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1109/sis.2005.1501643","name":"Ant inspired server population management in a service based computing environment","source":"crossref","abstract":"","url":"https://doi.org/10.1109/sis.2005.1501643","authors":["M.D. Peysakhov","W.C. Regli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-08-30T10:00:41Z","doi":"10.1109/sis.2005.1501643","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1016/j.asoc.2021.107221","name":"Quantum squirrel inspired algorithm for gene selection in methylation and expression data of prostate cancer","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2021.107221","authors":["Manosij Ghosh","Sagnik Sen","Ram Sarkar","Ujjwal Maulik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-02T22:38:46Z","doi":"10.1016/j.asoc.2021.107221","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-3-319-27400-3_15","name":"Evolving Heuristic Based Game Playing Strategies for Checkers Incorporating Reinforcement Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-27400-3_15","authors":["Clive Frankland","Nelishia Pillay"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-01T12:08:38Z","doi":"10.1007/978-3-319-27400-3_15","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-3-031-78946-5_48","name":"Monitoring of Greenhouse for Improved Medicinal Plants on Pharmacological Demand via IoT","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_48","authors":["Shiva Sai","Anima Nanda","B. K. Nayak","Aakanshya Samantaray"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:04:18Z","doi":"10.1007/978-3-031-78946-5_48","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-3-031-78946-5_9","name":"Improving Evaluation Measures Using Ensemble Technique in Diabetes Dataset","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_9","authors":["Rabindra Bista","Binay Sharma","Santosh Khanal","Sanjog Sigdel","Joao C. Ferreira"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:03:36Z","doi":"10.1007/978-3-031-78946-5_9","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-3-031-78946-5_14","name":"Enhancing Education Policy Estimation: A Novel Ridge Fuzzy Regression Approach for Handling Multicollinearity with Fuzzy Input Data","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_14","authors":["Tanmoy Das","Hemlata Joshi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:03:29Z","doi":"10.1007/978-3-031-78946-5_14","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-3-031-78949-6_53","name":"The Design of ERP Systems and Tracking Systems in the Supply Chain Management Industry","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78949-6_53","authors":["Oluwasegun Julius Aroba","Michael Rudolph"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T09:29:20Z","doi":"10.1007/978-3-031-78949-6_53","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-3-030-96299-9_49","name":"Building Trust with a Contact Tracing Application: A Blockchain Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_49","authors":["Tomás Honório","Catarina I. Reis","Marco Oliveira","Marisa Maximiano"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_49","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-3-031-78946-5_44","name":"Smart Gas Leakage Detection and Temperature Alerting System Using Arduino","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_44","authors":["B. M. Mani Tripathi","K. Lohith","M. Thanmayee","M. Suraj Preetham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-25T23:04:15Z","doi":"10.1007/978-3-031-78946-5_44","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-3-031-78949-6_26","name":"Opportunities for Blockchain Technologies in Vaccine Supply Chain Management","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78949-6_26","authors":["Tendani Mawela","Hanlie Smuts","Funmi Adebesin","Marie Hattingh","George Maramba"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T09:29:29Z","doi":"10.1007/978-3-031-78949-6_26","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-981-19-6379-7_14","name":"Nature-Inspired Computing Techniques in Drug Design, Development, and Therapeutics","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-19-6379-7_14","authors":["Sarra Akermi","Abira Dey","Nicholas Franciss Lee","Ruoya Lee","Nathalie Larzat","Jean Bernard Idoipe","Ritushree Biswas","Jasbir Kaur Simak","Suparna Dey","Subrata Sinha","Surabhi Johari","Chandramohan Jana","Anshul Nigam","Sunil Jayant","Ahmet Kati","Ashwani Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-31T17:04:10Z","doi":"10.1007/978-981-19-6379-7_14","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-3-031-78940-3_23","name":"A Federated Learning Methodology for Preserving Privacy in Healthcare Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78940-3_23","authors":["S. Swetha","A. V. Sriharsha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-05T06:07:49Z","doi":"10.1007/978-3-031-78940-3_23","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.3389/fnins.2015.00222","name":"Robustness of spiking Deep Belief Networks to noise and reduced bit precision of neuro-inspired hardware platforms","source":"crossref","abstract":"","url":"https://doi.org/10.3389/fnins.2015.00222","authors":["Evangelos Stromatias","Daniel Neil","Michael Pfeiffer","Francesco Galluppi","Steve B. Furber","Shih-Chii Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-07-09T08:03:20Z","doi":"10.3389/fnins.2015.00222","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-981-16-3128-3_9","name":"Multi-objective Optimization and Decision-Making for Net-Zero Energy Smart House","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-16-3128-3_9","authors":["Ryuto Shigenobu","Masakazu Ito","Kosuke Uchida","Harun Or Rashid Howlader","Tomonobu Senjyu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-18T23:09:33Z","doi":"10.1007/978-981-16-3128-3_9","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.4018/979-8-3373-8988-2.ch008","name":"Explainable and Interpretable Decision Intelligence for Human-Centered AI Systems","source":"crossref","abstract":"As AI systems increasingly drive critical decisions across healthcare, finance, and policy domains, transparency and interpretability have become essential requirements. This chapter explores explainable AI and decision intelligence through brain-inspired cognitive mechanisms that prioritize human understanding and trust. Drawing from neuroscience and cognitive science, we examine how human-centered AI systems can mirror the brain's natural decision-making processes while maintaining interpretability. We present a comprehensive framework balancing model performance with human comprehensibility, investigating XAI techniques including attention mechanisms, feature importance, and counterfactual explanations grounded in cognitive principles. The chapter explores neuro-symbolic AI in creating hybrid systems that combine neural networks' pattern recognition with symbolic reasoning's interpretability. Through practical case studies, we demonstrate how brain-inspired explainable AI enhances human-AI collaboration and builds stakeholder trust while addressing interpretability challenges.","url":"https://doi.org/10.4018/979-8-3373-8988-2.ch008","authors":["Firdaus Alamsyah"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-07T14:49:21Z","doi":"10.4018/979-8-3373-8988-2.ch008","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1016/s1568-4946(03)00035-8","name":"Intelligent control of a stepping motor drive using a hybrid neuro-fuzzy ANFIS approach","source":"crossref","abstract":"","url":"https://doi.org/10.1016/s1568-4946(03)00035-8","authors":["Leocundo Aguilar","Patricia Melin","Oscar Castillo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-08-07T21:49:34Z","doi":"10.1016/s1568-4946(03)00035-8","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1016/j.asoc.2009.09.008","name":"Application of a new hybrid neuro-evolutionary system for day-ahead price forecasting of electricity markets","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2009.09.008","authors":["Nima Amjady","Farshid Keynia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-09-16T15:01:29Z","doi":"10.1016/j.asoc.2009.09.008","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1109/nabic.2011.6089420","name":"Penalty weight adjustment in cooperative GA for nurse scheduling","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2011.6089420","authors":["Makoto Ohki","Hideaki Kinjo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-12-06T16:02:25Z","doi":"10.1109/nabic.2011.6089420","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1109/iccmc.2018.8487983","name":"Image De-noising Based on Nature Inspired Optimization Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccmc.2018.8487983","authors":["Neha Bharti","Subhash Chandra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-10-11T18:27:43Z","doi":"10.1109/iccmc.2018.8487983","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.7567/ssdm.2023.k-5-03","name":"2D Material Based Bio-inspired Neuromorphic Edge Computing Devices","source":"crossref","abstract":"","url":"https://doi.org/10.7567/ssdm.2023.k-5-03","authors":["Saptarshi Das Das"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-11T20:18:45Z","doi":"10.7567/ssdm.2023.k-5-03","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1016/j.procs.2019.04.153","name":"Cuckoo-inspired Job Scheduling Algorithm for Cloud Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.procs.2019.04.153","authors":["Ebtesam Aloboud","Heba Kurdi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-21T16:49:57Z","doi":"10.1016/j.procs.2019.04.153","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1109/icass69550.2026.11547799","name":"Metamaterial Inspired Aperture Coupled Patch Antenna for V2X Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icass69550.2026.11547799","authors":["Chirag Arora"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-08T19:49:38Z","doi":"10.1109/icass69550.2026.11547799","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-3-031-27499-2_46","name":"Classification Model for Identification of Internet Loan Frauds Using PCA with Ensemble Method","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_46","authors":["A. Madhaveelatha","K. M. Varaprasad","Bhasha Pydala"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_46","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-3-031-27499-2_2","name":"Evolution of Configuration Data in CGP Format Using Parallel GA on Embryonic Fabric","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_2","authors":["Gayatri Malhotra","Punithavathi Duraiswamy","J. K. Kishore"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_2","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-3-031-78946-5_7","name":"The Future of News Recommendation: A Blend of User Preferences, Content Analysis, and Social Signals","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_7","authors":["Sthembiso Mkhwanazi","Absalom E. Ezugwu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:04:17Z","doi":"10.1007/978-3-031-78946-5_7","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-3-031-78949-6_9","name":"Enhancing Urban Mobility with Predictive Parking Occupancy Analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78949-6_9","authors":["S. Anitha","M. Sharmitha","P. V. Ranjith","M. P. Theeraj"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T09:29:40Z","doi":"10.1007/978-3-031-78949-6_9","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-3-031-27499-2_64","name":"The Role of AI in Combating Fake News and Misinformation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_64","authors":["Virendra Singh Nirban","Tanu Shukla","Partha Sarathi Purkayastha","Nachiket Kotalwar","Labeeb Ahsan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_64","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1109/energycon.2012.6348235","name":"A bio inspired computing paradigm for decentralized economic dispatch","source":"crossref","abstract":"","url":"https://doi.org/10.1109/energycon.2012.6348235","authors":["A. Vaccaro","D. Villacci","R. Marotta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-11-15T17:09:21Z","doi":"10.1109/energycon.2012.6348235","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1109/nabic.2009.5393624","name":"Ant colony approach to predict amino acid interaction networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393624","authors":["Omar Gaci","Stefan Balev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393624","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-3-319-71767-8","name":"Computational Vision and Bio Inspired Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-71767-8","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-02-18T23:44:47Z","doi":"10.1007/978-3-319-71767-8","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.4018/978-1-7998-8561-0","name":"Applications of Nature-Inspired Computing in Renewable Energy Systems","source":"crossref","abstract":"","url":"https://doi.org/10.4018/978-1-7998-8561-0","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-08T08:09:33Z","doi":"10.4018/978-1-7998-8561-0","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1016/j.softx.2025.102108","name":"NeoCoMM: Neocortical neuro-inspired computational model for realistic microscale simulations","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.softx.2025.102108","authors":["Mariam Al Harrach","Maxime Yochum","Fabrice Wendling"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-03T13:54:04Z","doi":"10.1016/j.softx.2025.102108","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1364/psc.2021.m2b.5","name":"Adaptive and Dynamic RF Systems Enabled by Bio-Inspired Photonics and Microwave Photonics","source":"crossref","abstract":"We introduce various bio-inspired and microwave photonic technologies for improving security, ensuring channel availability, and increase adaptability to environmental changes. Solutions from the nature are excellent candidates for tackling critical challenges in emerging RF systems.","url":"https://doi.org/10.1364/psc.2021.m2b.5","authors":["Mable Fok","Qidi Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-01-18T20:53:27Z","doi":"10.1364/psc.2021.m2b.5","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1515/9783111545950-201","name":"VDedication","source":"crossref","abstract":"","url":"https://doi.org/10.1515/9783111545950-201","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-06T19:15:47Z","doi":"10.1515/9783111545950-201","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1109/nabic.2009.5393606","name":"An analytical approach for tracking the tumor systems dynamics","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393606","authors":["Sudipta Bhattacharya","Durjoy Majumder"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5393606","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1142/9789813143180_bmatter","name":"BACK MATTER","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789813143180_bmatter","authors":["Tao Song","Pan Zheng","Mou Ling Dennis Wong","Xun Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-04-08T09:29:16Z","doi":"10.1142/9789813143180_bmatter","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1109/nabic.2009.5393670","name":"A mobile robot path planning using Genetic Artificial Immune Network algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393670","authors":["Antariksha Bhaduri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5393670","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1109/bicta.2007.4806461","name":"A Branch and Cut Algorithm for DNA Encoding","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2007.4806461","authors":["Zicheng Wang","Zehui Shao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-03-30T11:03:08Z","doi":"10.1109/bicta.2007.4806461","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1109/bic-ta.2011.48","name":"A Study on Diminishing Cells Infinite Array","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bic-ta.2011.48","authors":["N. Jansirani","V. Rajkumar Dare"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-10-18T15:35:51Z","doi":"10.1109/bic-ta.2011.48","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1142/9789813143180_0010","name":"Genetic Algorithm: From Promiscuity to Monogamy","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789813143180_0010","authors":["Ting Yee Lim","Choo Jun Tan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-04-08T05:29:16Z","doi":"10.1142/9789813143180_0010","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1109/icacci.2013.6637355","name":"Directed Artificial Bat Algorithm (DABA) - A new bio-inspired algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icacci.2013.6637355","authors":["Amr Rekaby"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-10-29T23:21:09Z","doi":"10.1109/icacci.2013.6637355","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.52783/jes.8054","name":"Optimization of Load Balancing in Cloud Computing through Nature-Inspired Metaheuristic Algorithms","source":"crossref","abstract":"Cloud computing has introduced completely new ways to administer resources and distribute services, thereby enhancing load balancing for better service provision. Based on this assumption, this paper presents an approach to optimize load balancing in cloud environments through Nature-Inspirited Metaheuristic Algorithms. These algorithms tend to imitate natural processes such as evolution, swarm behavior, and biological adaptation. Therefore, NIMA can be strong solutions in addressing the complexities of multi-criteria service selection inside dynamic cloud environments by finding workloads efficiently, enhancing system efficiency, minimizing latency, and ensuring better resource utilization. The approach presented in this paper evaluates these nature-inspired algorithms towards possible comparison of their efficiency in handling the diverse and changing demands for cloud services, considering both Particle Swarm Optimization and Genetic Algorithms. The outcome justifies the effectiveness of load balancing, offering a scalable and flexible solution to service providers of cloud services. The outcome presented in the paper further suggest to speed up the cloud computing process by optimizing the distribution of loads and improving the quality of services delivered.","url":"https://doi.org/10.52783/jes.8054","authors":["Roopali Gupta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-30T11:16:12Z","doi":"10.52783/jes.8054","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1109/nabic.2013.6617842","name":"Recentering, reanchoring &amp;amp; restarting an evolutionary algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2013.6617842","authors":["James Hughes","Sheridan Houghten","Daniel Ashlock"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-10-10T19:27:30Z","doi":"10.1109/nabic.2013.6617842","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1109/mind67540.2025.11351874","name":"Multi-Objective Genetic Algorithms in Designing Redundant Water Distribution Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mind67540.2025.11351874","authors":["Matteo Nicolini"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-27T04:49:35Z","doi":"10.1109/mind67540.2025.11351874","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1515/9783111545950-014","name":"Index","source":"crossref","abstract":"","url":"https://doi.org/10.1515/9783111545950-014","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-06T19:15:47Z","doi":"10.1515/9783111545950-014","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.3390/biomimetics11060437","name":"Empirical Logic for Bio-Inspired Soft Computing: Illustrative Applications in Control Engineering and Cluster Analysis","source":"crossref","abstract":"Empirical logic (EL) is a bio-inspired soft computing approach to rule-based decision-making that emphasizes intuitive, experience-based reasoning. While its theoretical foundations have been established in previous work, its practical applicability and accessibility have so far received less attention. This paper addresses this gap by providing two representative application examples from distinct domains: control engineering and cluster analysis. The first example demonstrates the use of EL for the speed control of a DC drive, highlighting its ability to achieve competitive dynamic performance with a small number of intuitive rules. The second example introduces a novel approach to cluster analysis, where cluster structures emerge from the collective interaction of EL rules rather than from the optimization of a predefined objective function. In addition, the paper emphasizes the availability of publicly accessible software realizations of EL, including a Maple-based prototype and a Python framework, which enable direct experimentation and practical use. By combining illustrative applications with executable tools, the paper aims to facilitate the transition from conceptual understanding to practical deployment and to support further exploration of EL in applied soft computing contexts.","url":"https://doi.org/10.3390/biomimetics11060437","authors":["Jens Grotrian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-19T13:04:04Z","doi":"10.3390/biomimetics11060437","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.4018/978-1-5225-0788-8.ch030","name":"Higher Order Neural Network for Financial Modeling and Simulation","source":"crossref","abstract":"Financial market creates a complex and ever changing environment in which population of investors are competing for profit. Predicting the future for financial gain is a difficult and challenging task, however at the same time it is a profitable activity. Hence, the ability to obtain the highly efficient financial model has become increasingly important in the competitive world. To cope with this, we consider functional link artificial neural networks (FLANNs) trained by particle swarm optimization (PSO) for stock index prediction (PSO-FLANN). Our strong experimental conviction confirms that the performance of PSO tuned FLANN model for the case of lower number of ahead prediction task is promising. In most cases LMS updated algorithm based FLANN model proved to be as good as or better than the RLS updated algorithm based FLANN but at the same time RLS updated FLANN model for the prediction of stock index system cannot be ignored.","url":"https://doi.org/10.4018/978-1-5225-0788-8.ch030","authors":["Partha Sarathi Mishra","Satchidananda Dehuri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-07-26T12:16:44Z","doi":"10.4018/978-1-5225-0788-8.ch030","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.4018/979-8-3693-1131-8.ch002","name":"Bio-Inspired Algorithms Used in Medical Image Processing","source":"crossref","abstract":"Medical image processing plays a crucial role in diagnosing diseases, guiding treatment plans, and monitoring patient progress. With the increasing complexity and volume of medical imaging data, there is a growing need for advanced techniques to extract meaningful information from these images. Traditional methods in medical image processing often face challenges related to image enhancement, segmentation, and feature extraction. These challenges stem from the inherent variability, noise, and complexity of medical images, making it difficult to obtain accurate and reliable results. In this chapter, the focus is on leveraging bio-inspired algorithms to address these challenges and improve the analysis and interpretation of medical images. Bio-inspired algorithms draw inspiration from natural processes, such as evolution, swarm behavior, neural networks, and genetic programming. It addresses the challenges and requirements specific to each modality and how bio-inspired algorithms can be adapted and tailored to meet those needs.","url":"https://doi.org/10.4018/979-8-3693-1131-8.ch002","authors":["K. Ezhilarasan","K. Somasundaram","T. Kalaiselvi","Praveenkumar Somasundaram","S. Karthigai Selvi","A. Jeevarekha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-29T10:11:06Z","doi":"10.4018/979-8-3693-1131-8.ch002","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.21467/proceedings.114.14","name":"Design of Low Power Neuro-amplifier Circuit with Miller Compensation Technique for Biomedical Neuro-implantable Devices","source":"crossref","abstract":"Neuro-amplifiers form an integral part of biomedical implantable devices. In this paper, we design a neuro-amplifier circuit with Miller compensation capacitor. The neuro-amplifier design is based on operational transconductance amplifier (OTA) with an active load. In this work, performance of the neuro-amplifier is enhanced by incorporating the Miller compensation technique. Design and simulation of the neuro-amplifier circuit is performed using SPICE simulation software. Body biasing and feedback techniques are imparted to optimize the circuit performance. Simulation results show that the neuro-amplifier circuit has a mid-frequency gain and 3-dB bandwidth of 48dB, and 16kHzrespectively.","url":"https://doi.org/10.21467/proceedings.114.14","authors":["Kriti Dwivedi","Aparna Gupta","Ritika Oberoi","Ribu Mathew"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-24T19:11:58Z","doi":"10.21467/proceedings.114.14","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-3-030-37218-7_37","name":"Optimized Machine Learning Approach for the Prediction of Diabetes-Mellitus","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_37","authors":["Manoj Challa","R. Chinnaiyan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T15:02:40Z","doi":"10.1007/978-3-030-37218-7_37","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-3-031-78940-3_7","name":"Skin-Deep AI: Convolutional Neural Networks for Predicting Dermatological Conditions","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78940-3_7","authors":["Manav Gupta","Vaibhav Pushpad","Yajnaseni Dash","Ajith Abraham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-05T06:07:32Z","doi":"10.1007/978-3-031-78940-3_7","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-3-031-78943-4_7","name":"Using Sentence Embedding Techniques for Enhancing Terms-of-Service Text Summarization","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78943-4_7","authors":["Harry Peach","Nicolay Rusnachenko","Mayank Baraskar","Huizhi Liang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-03T11:07:38Z","doi":"10.1007/978-3-031-78943-4_7","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1109/icacce.2015.131","name":"Fractal Antenna with Meta-Material Inspired DGS","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icacce.2015.131","authors":["Rajesh Kumar","Sarika","M.R. Tripathy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-10-26T22:13:53Z","doi":"10.1109/icacce.2015.131","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.4108/icst.bionetics2007.2458","name":"Access Control Mechanisms for Fraglets","source":"crossref","abstract":"","url":"https://doi.org/10.4108/icst.bionetics2007.2458","authors":["Fabio Martinelli","Marinella Petrocchi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-03-10T14:16:22Z","doi":"10.4108/icst.bionetics2007.2458","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.7494/csci.2016.17.4.483","name":"AN OCTOPUS-INSPIRED INTRUSION DETERRENCE MODEL IN DISTRIBUTED COMPUTING SYSTEM","source":"crossref","abstract":"","url":"https://doi.org/10.7494/csci.2016.17.4.483","authors":["Emmanuel Olajubu","Abiodun Akinwale","Kazeem Ogundoyin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-01-11T04:00:29Z","doi":"10.7494/csci.2016.17.4.483","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1039/d5tc01712b/v2/response1","name":"Author response for \"Reconfigurable Artificial Synapses with an Organic Antiambipolar Transistor for Brain-inspired Computing\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5tc01712b/v2/response1","authors":["Ryoma Hayakawa","Yuho Yamamoto","Kosuke Yoshikawa","Yoichi Yamada","Yutaka Wakayama"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-12T17:13:05Z","doi":"10.1039/d5tc01712b/v2/response1","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-3-031-27499-2_15","name":"A Systematic Literature Review on Home Health Care Management","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_15","authors":["Filipe Alves","Ana Maria A. C. Rocha","Ana I. Pereira","Paulo Leitão"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_15","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-3-030-96299-9_22","name":"Detection and Classification of Age-Related Macular Degeneration Using Integration of DenseNet169 and Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_22","authors":["F. Ajesh","Ajith Abraham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_22","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-3-031-78949-6_6","name":"Development of a Virtual Tutor for Remote Solar Laboratory Using Voice Synthesis","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78949-6_6","authors":["Sarah Hadjoudja","Abderrahmane Adda Benattia","Mansour Benyamina","Abdelhalim Benachenhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T09:30:39Z","doi":"10.1007/978-3-031-78949-6_6","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-3-031-78940-3_26","name":"Dance Action Recognition Using Deep Convolution Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78940-3_26","authors":["G. Divya Zion","K. Baboji","Thirumalesu Kudithi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-05T06:07:38Z","doi":"10.1007/978-3-031-78940-3_26","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/s44196-026-01491-w","name":"Quantum-Inspired Predictive Digital Twins for Self-Healing Neuro-Fusion Control in Multi-UAV Swarms for Disaster Response","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s44196-026-01491-w","authors":["Rajesh Kumar Dhanaraj","Gourav Mondal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-31T13:06:14Z","doi":"10.1007/s44196-026-01491-w","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-981-33-6862-0_36","name":"Evolutionary Computation of Facial Composites for Suspect Identification in Forensic Sciences","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-33-6862-0_36","authors":["Vijay A. Kanade"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-06-14T05:02:45Z","doi":"10.1007/978-981-33-6862-0_36","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1109/nice65350.2025.11065060","name":"Demonstrating the Advantages of Analog Wafer-Scale Neuromorphic Hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nice65350.2025.11065060","authors":["Hartmut Schmidt","Andreas Grübl","José Montes","Eric Müller","Sebastian Schmitt","Johannes Schemmel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-08T13:36:20Z","doi":"10.1109/nice65350.2025.11065060","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.52700/scir.v6i1.149","name":"Quantum-Inspired Cryptography Protocols for Enhancing Security in Cloud Computing Infrastructures","source":"crossref","abstract":"As we know, cloud computing plays a vital role in our lives. It also plays a pivotal role in modern business and information technology landscapes. But with this, there is a rise in concerns regarding the security and privacy of all data which is stored in the cloud. To tackle these concerns some effective and traditional cryptographic methods are present but they face potential vulnerabilities due to advent of quantum computing. It also threatens the basis of widely used encryption algorithms and models. This research focuses on the usage of quantum mechanics inspired cryptographic protocols, which will help to strengthen the security of cloud computing models and infrastructures. The research begins with a detailed overview of the current situation and state of security of cloud computing. There is identification of all challenges and vulnerabilities faced due to current, classical and traditional cryptographic techniques and algorithms. As we know that there is a very close arrival of quantum computing, we are surrounded by mighty and latent threats because of quantum computing algorithms that can easily overcome the widely accepted and used encryption standards and models. So, there is a dire need to develop and implement some alternative cryptographic strategies and measures. To overcome these challenges, this research proposes the creation and usage of quantum-inspired cryptographic protocols which are designed to resist attacks from both traditional and quantum vulnerabilities. These protocols are inspired from quantum mechanics, like superposition and entanglement. These protocols will help to design and create cryptographic systems and models that offer enhanced security. The research focuses on the theoretical foundations of these quantum mechanics inspired protocols and assesses their practical feasibility within cloud computing infrastructures and environment.This research contains information regarding the challenges associated with integration and deployment of quantum inspired cryptographic solutions in cloud computing. It evaluates the scalability, efficiency, performance and computational overhead of these quantum inspired protocols to ensure their practical feasibility and capability in existing cloud computing environment and infrastructures. This research also includes comparison performed with quantum cryptographic protocols and traditional cryptographic methods. The results aim to provide evidence that quantum cryptographic techniques are better, feasible and secure options to protect data over cloud. In Conclusion, the research aims to provide an insight that development and usage of advanced security measures can withstand and handle evolving threats, ensuring the continued security and protection of data in cloud computing environment by providing theoretical insights, analysis and evolution.","url":"https://doi.org/10.52700/scir.v6i1.149","authors":["Laiba Tariq","Ayesha Atta","Umer Farooq","Nida Anwar","Muhammad Asim","Nadia Tabassum"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-24T13:48:38Z","doi":"10.52700/scir.v6i1.149","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1201/9781003143499-8","name":"Models of morphologically detailed neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003143499-8","authors":["Elishai Ezra Tsur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-07-19T12:30:34Z","doi":"10.1201/9781003143499-8","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1117/12.3079776","name":"Brain-inspired complexity metrics for photonic neuromorphic computing","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3079776","authors":["Oliver Neill","Connor Kalkman","Daniele Faccio"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-05T20:51:16Z","doi":"10.1117/12.3079776","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1109/nabic.2009.5393452","name":"Swarm intelligence approach of leaker identification in secure multicast","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393452","authors":["N.K Sreelaja","G.A.Vijayalakshmi Pai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393452","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1109/bimnics.2007.4610117","name":"On the impact of network QoS on automated distributed auctions","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bimnics.2007.4610117","authors":["Ricardo Lent"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-09-08T20:06:46Z","doi":"10.1109/bimnics.2007.4610117","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1109/ibica.2011.74","name":"A Portal Architecture Based on IT Services","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ibica.2011.74","authors":["Tingting Sun","Futong Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-01-06T16:44:03Z","doi":"10.1109/ibica.2011.74","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1002/9781394296262.fmatter","name":"Front Matter","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9781394296262.fmatter","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-24T21:18:31Z","doi":"10.1002/9781394296262.fmatter","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1142/9789812790262_0002","name":"NEURONS AND SYNAPSES: THE KEY TO MEMORY AND LEARNING","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789812790262_0002","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-04-12T00:09:25Z","doi":"10.1142/9789812790262_0002","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1109/nabic.2009.5393318","name":"On the intelligent content retrieval by means of text relevance modelling","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393318","authors":["Silviu Ionita"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5393318","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1109/nabic.2009.5393605","name":"Prosima: Protein similarity algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393605","authors":["Tomas Novosad","Vaclav Snasel","Ajith Abraham","Jack Y Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5393605","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1016/b978-0-12-823749-6.00003-9","name":"Reliability redundancy allocation problems under fuzziness using genetic algorithm and dual-connection numbers","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-12-823749-6.00003-9","authors":["Laxminarayan Sahoo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-06-25T08:30:09Z","doi":"10.1016/b978-0-12-823749-6.00003-9","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1109/bicta.2010.5645266","name":"Parallel double splicing on images","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2010.5645266","authors":["V. Masilamani","D.G. Thomas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-12-09T10:33:18Z","doi":"10.1109/bicta.2010.5645266","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch055","name":"Genetic Programming for Spatiotemporal Forecasting of Housing Prices","source":"crossref","abstract":"This chapter compares forecasts of the median neighborhood prices of residential single-family homes in Cambridge, Massachusetts, using parametric and nonparametric techniques. Prices are measured over time (annually) and over space (by neighborhood). Modeling variables characterized by space and time dynamics is challenging. Multi-dimensional complexities—due to specification, aggregation, and measurement errors—thwart use of parametric modeling, and nonparametric computational techniques (specifically genetic programming and neural networks) may have the advantage. To demonstrate their efficacy, forecasts of the median prices are first obtained using a standard statistical method: weighted least squares. Genetic programming and neural networks are then used to produce two other forecasts. Variables used in modeling neighborhood median home prices include economic variables such as neighborhood median income and mortgage rate, as well as spatial variables that quantify location. Two years’ out-of-sample forecasts comparisons of median prices suggest that genetic programming may have the edge.","url":"https://doi.org/10.4018/978-1-59140-984-7.ch055","authors":["M. Kaboudan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch055","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1515/9783111545950-toc","name":"Contents","source":"crossref","abstract":"","url":"https://doi.org/10.1515/9783111545950-toc","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-06T19:15:47Z","doi":"10.1515/9783111545950-toc","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/iscas.2018.8351772","name":"Live Demonstration: Real-time neuro-inspired sound source localization and tracking architecture applied to a robotic platform","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas.2018.8351772","authors":["F. Perez-Pena","E. Cerezuela-Escudero","Angel Jimenez-Fernandez","Arturo Morgado-Estevez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-05-04T22:00:05Z","doi":"10.1109/iscas.2018.8351772","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.4018/979-8-3693-4159-9.ch006","name":"Neuro-Inspired Algorithms to Enhance Cryptography","source":"crossref","abstract":"Neurocryptology objective is to create novel and creative approaches to improve the security of cryptographic systems by incorporating knowledge from neuroscience, particularly the study of the cognitive functions of the human brain. Instead of using mathematical methods and keys to secure communication and data, neurocryptology makes use of knowledge about how the brain processes information and spots patterns. The form and operation of neural networks and biological brains serve as inspiration for neural-inspired algorithms, which have the potential to improve cryptography in several ways. Encryption keys can be created using neural networks. In order to improve encryption techniques, neural networks can be incorporated. Behavioral biometric authentication techniques can be improved by neural network-inspired algorithms. This chapter is discussing about the neuro inspired algorithms to enhance cryptographic protocols. It reviewing the different algorithms that underlie well-known cryptographic cryptosystems","url":"https://doi.org/10.4018/979-8-3693-4159-9.ch006","authors":["R. Thenmozhi","D. Vetriselvi","A. Arokiaraj Jovith"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-31T08:05:21Z","doi":"10.4018/979-8-3693-4159-9.ch006","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:27.965Z"},{"id":"doi:10.1007/978-3-030-96299-9_71","name":"A Review of Unpredictable Renewable Energy Sources Through Electric Vehicles on Islands","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_71","authors":["Juliana Chavez","João Soares","Zita Vale","Bruno Canizes","Sérgio Ramos"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_71","addedAt":"2026-09-01T01:48:27.965Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/nabic.2009.5393701","name":"Texture analysis based on Gaussian mixture modeling","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393701","authors":["T Sobha","S Remya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393701","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1103/physrevapplied.25.030001","name":"Editorial: Closing the Collection on Physics-Inspired Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1103/physrevapplied.25.030001","authors":["Kerem Y. Camsari","Supriyo Datta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-25T15:15:48Z","doi":"10.1103/physrevapplied.25.030001","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/978-3-031-27499-2_75","name":"LEEC: An Improved Linear Energy Efficient Clustering Method for Sensor Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_75","authors":["Virendra Dani","Radha Bhonde","Ayesha Mandloi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_75","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/978-3-030-16681-6_42","name":"LSTM Approach to Cancel Noise from Mouse Input for Patients with Motor Disabilities","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-16681-6_42","authors":["Soham Harnale","Ashwin Vaidya","Aditya Bhide","Aniket Sanap","Mangesh V. Bedekar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-22T17:26:26Z","doi":"10.1007/978-3-030-16681-6_42","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/978-3-030-49339-4_36","name":"Developing a Multi-modal Listing Service for Real Estate Agency Practice in Nigeria","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-49339-4_36","authors":["Adewole Adewumi","Chukwuemeka Iroham","Daniel Audu","Sanjay Misra","Ravin Ahuja"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-05T11:05:14Z","doi":"10.1007/978-3-030-49339-4_36","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/978-981-16-9573-5_17","name":"Cellular Learning Automata: Review and Future Trend","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-16-9573-5_17","authors":["Mohammad Khanjary"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-30T06:02:42Z","doi":"10.1007/978-981-16-9573-5_17","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1109/bic-ta.2011.68","name":"Comparing Membrane Computing with Ordinary Differential Equation in Modeling a Biological Process in Liver Cell","source":"crossref","abstract":"Most of the biological processes such as the processes in liver cell have been modeled by using the approach of ordinary differential equation. Such conventional model has demonstrated drawbacks and limitations primarily in preserving the stochastic and nondeterministic behaviors of biological processes by characterizing them as continuous and deterministic processes. Membrane computing has been considered as an alternative to address these limitations by providing modeling capabilities in representing the structure and processes of biological systems essential for biological applications. This study was carried out to investigate the modeling of hormone-induced calcium oscillations in liver cell with membrane computing. Simulation strategy of Gillespie algorithm and the method of model checking with Probabilistic Symbolic Model Checker were used to verify and validate the membrane computing model. The results produced by membrane computing model were compared with the results from ordinary differential equation model. The simulation and model checking of membrane computing model of the hormone-induced calcium oscillations showed that the fundamental properties of the biological process were preserved. Membrane computing model has provided a better approach in accommodating the structure and processes of hormone-induced calcium oscillations system by sustaining the basic properties of the system compared with ordinary differential equation model. However there were some other issues such as the selection of kinetic constants according to the behavior of biological processes has to be addressed to strengthen membrane computing capability in modeling biological processes.","url":"https://doi.org/10.1109/bic-ta.2011.68","authors":["Ravie Chandren Muniyandi","Abdullah Mohd. Zin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-10-18T15:35:51Z","doi":"10.1109/bic-ta.2011.68","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1016/j.asoc.2018.11.030","name":"Fuzzy signaling game of deception between ant-inspired deceptive robots with interactive learning","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2018.11.030","authors":["Maryam Kouzehgar","Mohammad Ali Badamchizadeh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-11-19T12:12:55Z","doi":"10.1016/j.asoc.2018.11.030","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1016/b978-0-443-15663-2.00002-x","name":"The experience of caregivers of patients in neuro-oncology","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-15663-2.00002-x","authors":["Allison J. Applebaum","Kelcie D. Willis","Paula R. Sherwood"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-09T08:09:30Z","doi":"10.1016/b978-0-443-15663-2.00002-x","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1093/noajnl/vdae124","name":"Fertility preserving techniques in neuro-oncology patients: A systematic review","source":"crossref","abstract":"Abstract Background Advancements in cancer treatments have enhanced survival rates and quality of life for patients with central nervous system (CNS) tumors. There is growing recognition of the significance of fertility preservation methods. Currently, techniques, including oocyte cryopreservation and sperm cryopreservation are established. Nevertheless, oncologists may exhibit reluctance when referring patients to reproductive specialists. This review aimed to assess the best evidence for fertility preservation techniques used in patients with CNS cancers and evaluate outcomes relating to their success and complications. Methods Two reviewers performed a search of Pubmed, Embase, Medline, Cochrane, and Google Scholar. Papers were included if they reported at least 1 fertility preservation technique in a neuro-oncology patient. Non-English studies, editorials, animal studies, and guidelines were excluded. Meta-analysis was performed using the random effects model. Results Sixteen studies containing data from 237 participants (78.8% female) were included in the systematic review and meta-analysis, of whom 110 (46.4%) underwent fertility preservation techniques. All patients (100%) successfully underwent fertility preservation with 1 participant (2.9%) returning to rewarm their oocytes, embryos or sperm. On average, 17.8 oocytes were retrieved with 78%, ultimately being cryopreserved. Five (6.0%) patients successfully conceived 9 healthy-term children after utilizing their cryopreserved sperm, embryos, or oocytes. Moreover, 6 patients successfully conceived naturally or using intrauterine insemination, resulting in 7 healthy-term children. Conclusions Fertility preservation techniques could offer a safe and effective way for neuro-oncology patients to deliver healthy-term babies following treatment. However, further studies concerning risks, long-term pregnancy outcomes, and cost-effectiveness are needed.","url":"https://doi.org/10.1093/noajnl/vdae124","authors":["Maia Osborne-Grinter","Jasleen Kaur Sanghera","Offorbuike Chiamaka Bianca","Chandrasekaran Kaliaperumal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-25T10:57:11Z","doi":"10.1093/noajnl/vdae124","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1007/978-3-030-96299-9_59","name":"A Detailed Review of Organizational Behavior of College Employees","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_59","authors":["V. I. Roy","K. A. Janardhanan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_59","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/978-3-031-78943-4_25","name":"Isolated Word Recognition and Feature Extraction Using Machine Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78943-4_25","authors":["Rajeev Ranjan","Yogendra Narayan","Sudhir Kumar Mishra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-03T11:07:45Z","doi":"10.1007/978-3-031-78943-4_25","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1007/978-1-4471-0427-8_3","name":"Triune-Brain Inspired Unifying View of Intelligent Computation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4471-0427-8_3","authors":["Raju Surampudi Bapi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-09-24T01:34:23Z","doi":"10.1007/978-1-4471-0427-8_3","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/978-3-642-40179-4","name":"Advances in Bio-inspired Computing for Combinatorial Optimization Problems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-40179-4","authors":["Camelia-Mihaela Pintea"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-08-07T08:27:53Z","doi":"10.1007/978-3-642-40179-4","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1016/b978-0-08-102782-0.00016-2","name":"Neuronal realizations based on memristive devices","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-08-102782-0.00016-2","authors":["Zhongrui Wang","Rivu Midya","J. Joshua Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-26T05:28:39Z","doi":"10.1016/b978-0-08-102782-0.00016-2","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1515/9783111545950-202","name":"VIIAcknowledgements","source":"crossref","abstract":"","url":"https://doi.org/10.1515/9783111545950-202","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-06T19:15:47Z","doi":"10.1515/9783111545950-202","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.36227/techrxiv.21837027.v1","name":"Brain Inspired Computing: A Systematic Survey and Future Trends","source":"crossref","abstract":"Brain Inspired Computing (BIC) is an emerging research field that aims to build fundamental theories, models, hardware architectures, and application systems toward more general Artificial Intelligence (AI) by learning from the information processing mechanisms or structures/functions of biological nervous systems. It is regarded as one of the most promising research directions for future intelligent computing in the post-Moore era. In the past few years, various new schemes in this field have sprung up to explore more general AI. These works are quite divergent in the aspects of modeling/algorithm, software tool, hardware platform, and benchmark data, since BIC is an interdisciplinary field that consists of many different domains, including computational neuroscience, artificial intelligence, computer science, statistical physics, material science, microelectronics and so forth. This situation greatly impedes researchers from obtaining a clear picture and getting started in the right way. Hence, there is an urgent requirement to do a comprehensive survey in this field to help correctly recognize and analyze such bewildering methodologies. What are the key issues to enhance the development of BIC? What roles do the current mainstream technologies play in the general framework of BIC? Which techniques are truly useful in real-world applications? These questions largely remain open. To address the above issues, in this survey we first clarify the biggest challenge of BIC: how can AI models benefit from the recent advancements in computational neuroscience? With this challenge in mind, we will focus on discussing the concept of BIC and summarize four components of BIC infrastructure development: 1) modeling/algorithm; 2) hardware platform; 3) software tool; and 4) benchmark data. For each component, we will summarize its recent progress, main challenges to resolve, and future trends. On the basis of these studies, we present a general framework for the real-world applications of BIC systems, which is promising to benefit both AI and brain science. Finally, we claim that it is extremely important to build a research ecology to promote prosperity continuously in this field.","url":"https://doi.org/10.36227/techrxiv.21837027.v1","authors":["Guoqi Li","Lei Deng","Huajing Tang","Gang Pan","Yonghong Tian","Kaushik Roy","Wolfgang Maass"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-18T22:30:06Z","doi":"10.36227/techrxiv.21837027.v1","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/978-3-211-78775-5_17","name":"Visual Control of a Roving Robot based on Turing Patterns","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-211-78775-5_17","authors":["Paola Brunetto","Arturo Buscarino","Alberta Latteri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-11-29T07:44:42Z","doi":"10.1007/978-3-211-78775-5_17","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1093/nop/npae061","name":"European Association of Neuro-Oncology’s 30th anniversary: A successful and growing relationship with <i>Neuro-Oncology Practice</i>","source":"crossref","abstract":"","url":"https://doi.org/10.1093/nop/npae061","authors":["Martin J B Taphoorn","Norbert Galldiks","Matthias Preusser","Michael Platten","Susan C Short"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-10T20:19:05Z","doi":"10.1093/nop/npae061","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1109/nabic.2011.6089416","name":"Artificial metamorphosis for self-growing adaptable interface","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2011.6089416","authors":["Ohbyung Kwon","Namyeon Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-12-06T16:02:25Z","doi":"10.1109/nabic.2011.6089416","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1109/bimnics.2007.4610068","name":"Welcome from the workshop co-chairs","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bimnics.2007.4610068","authors":["Jun Suzuki","Stephan Steglich"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-09-08T20:06:46Z","doi":"10.1109/bimnics.2007.4610068","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/978-3-030-37218-7","name":"Computational Vision and Bio-Inspired Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T20:02:40Z","doi":"10.1007/978-3-030-37218-7","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.4018/978-1-7998-8561-0.ch007","name":"DNA Computing","source":"crossref","abstract":"The modern era of classical silicon-based computing is at the edge of a number of technological challenges which include huge energy consumption, requirement of massive memory space, and generation of e-waste. The proposed alternative to this pitfall is nanocomputing, which was first exemplified in the form of DNA computing. Recently, DNA computing is gaining acceptance in the field of eco-friendly, unconventional, nature-inspired computation. The future of computing depends on making it renewable, as this can cause a drastic improvement in energy consumption. Thus, to save the natural resources and to stop the growing toxicity of the planet, reversibility is being imposed on DNA computing so that it can replace the traditional form of computation. This chapter reflects the foundation of DNA computing and renewability of this multidisciplinary domain that can be produced optimally and run from available natural resources.","url":"https://doi.org/10.4018/978-1-7998-8561-0.ch007","authors":["Mandrita Mondal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-08T08:09:33Z","doi":"10.4018/978-1-7998-8561-0.ch007","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1002/9781394214211.fmatter","name":"Front Matter","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9781394214211.fmatter","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-08T07:08:27Z","doi":"10.1002/9781394214211.fmatter","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1007/978-3-030-16681-6_46","name":"A Fuzzy Based Hybrid Firefly Optimization Technique for Load Balancing in Cloud Datacenters","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-16681-6_46","authors":["M. Lawanya Shri","E. Ganga Devi","Balamurugan Balusamy","Seifedine Kadry","Sanjay Misra","Modupe Odusami"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-22T17:26:26Z","doi":"10.1007/978-3-030-16681-6_46","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/978-3-031-27499-2_61","name":"A Comparative Analysis of Classification Algorithms for Dementia Prediction","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_61","authors":["Prashasti Kanikar","Manoj Sankhe","Deepak Patkar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_61","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/978-3-031-78943-4_16","name":"Disparity in the Adoption of XBRL Taxonomies – A Cross-Industry Analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78943-4_16","authors":["Dapeng Liu","Meijun Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-03T11:07:54Z","doi":"10.1007/978-3-031-78943-4_16","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-031-78949-6_14","name":"Vehicle-BD: A Benchmark Dataset of Bangladeshi Local Vehicles","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78949-6_14","authors":["Md Sazedur Rahman","Md Zahim Hassan","Sifat Ibtisum"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T09:29:50Z","doi":"10.1007/978-3-031-78949-6_14","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-031-78937-3_24","name":"Cardio Inspect Using ECG Images","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_24","authors":["Thoutireddy Shilpa","Nagendar Yamsani","Ranjith Kumar Marrikukkala","P. Kumaraswamy","A. Harshavardhan","B. Sachuthananthan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:06:50Z","doi":"10.1007/978-3-031-78937-3_24","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-031-78946-5_13","name":"Optimizing Healthcare Analytics: A Zero-Inflated Poisson Approach to Pediatric Emergency Room Visits","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_13","authors":["Nadashree Bose","Hemlata Joshi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-27T08:44:52Z","doi":"10.1007/978-3-031-78946-5_13","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.5194/egusphere-egu26-9219","name":"Quantum Computing and Bayesian Optimization-Inspired Multilayer Perceptron Approach for Suspended Sediment Concentration Estimates at Rivers","source":"crossref","abstract":"Suspended Sediment Concentration (SSC) is an indicator of a river system's quality and has several ecological impacts on aquatic life. Increased levels of SSC typically reduce the transparency of the water, thereby reducing photosynthetic activity. Moreover, it has an adverse effect on aquatic organisms due to impediments to respiration and altered habitat conditions. Additionally, contaminants, including heavy metals and organic pollutants, can be carried by suspended sediments as they attach to them. Thus, understanding and prediction of SSC became an active research topic in hydrologic science for better analyzing the sources and variations of SSC . The current research aims to estimate and predict SSC levels using measured data from the flow station 07373420 located on the Mississippi River in West Feliciana Parish in the Gulf of Mexico operated by the US Geological Survey. Over 29 years (1992 to 2021) of monthly flow and SSC data were obtained and used in this research. The SSC values were estimated using three machine learning-based modeling frameworks: Multilayer Perceptron (MLP), hybrid Quantum-Inspired Algorithms - Multilayer Perceptron (QIS-MLP), and Bayesian Optimization-Multilayer Perceptron (BO-MLP). The MLP models the complex, nonlinear relationship between independent and dependent variables using an artificial neural network. Each neuron receives the weighted inputs from the previous layer and processes them through the activation function, allowing the MLP to detect nonlinear relationships among the various input variables. With BO, the optimal hyperparameters of the MLP model (number of hidden layers, number of neurons, and learning rate) were tuned automatically. BO-MLP selects promising configurations through iterative evaluations of the acquisition function, optimally exploring the hyperparameter search space for the MLP model. The QIS-MLP utilizes an improved global search strategy combined with enhanced ability to conduct local searches by virtue of its advanced quantum optimization algorithm. To evaluate the performance of each model, the standard statistical measures of model performance were utilized, including Root Mean Squared Error (RMSE), Nash-Sutcliffe Efficiency (NSE), Kling-Gupta Efficiency (KGE), and Correlation Coefficient (CC). Among all tested input combinations, the QIS-MLP with three lagged SSC values and three lagged discharge values represents the best performance with the highest degree of accuracy and greatest potential for generalization of SSC values (RMSE = 37.34, NSE = 0.418, KGE = 0.537, and CC = 0.7). As a result, the QIS-MLP achieved superior output through optimization of functions and reduction in error rates. Based on the results, QIS-MLP were found to demonstrate superior accuracy and reliability of monthly SSC estimates and, therefore, considered an excellent candidate for intelligent modeling of complex hydrological systems.Keywords: Hydrological Modeling, Quantum-Inspired Algorithms, Suspended Sediment Concentration","url":"https://doi.org/10.5194/egusphere-egu26-9219","authors":["Neda Beirami","Saeed Samadianfard","Orhan Gündüz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-13T23:35:41Z","doi":"10.5194/egusphere-egu26-9219","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1016/j.asoc.2011.07.017","name":"A Quantum-inspired Evolutionary Algorithm with a competitive variation operator for Multiple-Fault Diagnosis","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2011.07.017","authors":["P. Arpaia","D. Maisto","C. Manna"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-08-14T16:03:39Z","doi":"10.1016/j.asoc.2011.07.017","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1201/9781003322931-11","name":"Resource Management in Fog Computing Environment Using Optimal Fog Network Topology","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003322931-11","authors":["Pradeep Singh Rawat","Srabanti Maji","Devendra Prasad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-24T18:39:16Z","doi":"10.1201/9781003322931-11","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/s10723-026-09845-6","name":"Event-Driven Neuromorphic-Inspired Task Offloading for Energy-Efficient Edge-IoT Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s10723-026-09845-6","authors":["Pedro Henrique Sachete Garcia","Fábio Diniz Rossi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-24T10:18:18Z","doi":"10.1007/s10723-026-09845-6","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1109/ietc47856.2020.9249149","name":"Tweet-Inspired Intelligent Subselection of Semantically-Related Lyrical Training Data","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ietc47856.2020.9249149","authors":["Dylan Lasher","Paul Bodily"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-11-11T17:13:28Z","doi":"10.1109/ietc47856.2020.9249149","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1109/ipdpsw.2010.5470693","name":"Workshop on nature inspired distributed computing - NIDISC","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ipdpsw.2010.5470693","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-05-28T14:25:42Z","doi":"10.1109/ipdpsw.2010.5470693","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1109/tdc.2010.5484284","name":"Unit commitment with nature and biologically inspired computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tdc.2010.5484284","authors":["Lingamurthy Belede","Amit Jain","Ravikanth Reddy. Gaddam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-06-23T15:18:59Z","doi":"10.1109/tdc.2010.5484284","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1109/nabic.2011.6089426","name":"Selectional forces in ontogenetic with application to the TSP","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2011.6089426","authors":["Daniel Surgent"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-12-06T21:02:25Z","doi":"10.1109/nabic.2011.6089426","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1016/b978-0-44-322341-9.00004-5","name":"Dedication","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-44-322341-9.00004-5","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-24T10:20:11Z","doi":"10.1016/b978-0-44-322341-9.00004-5","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1007/978-3-031-27499-2_40","name":"Bi-CSem: A Semantically Inclined Bi-Classification Framework for Web Service Recommendation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_40","authors":["Deepak Surya","S. Palvannan","Gerard Deepak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_40","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.5860/choice.42-4067","name":"Recent developments in biologically inspired computing","source":"crossref","abstract":"","url":"https://doi.org/10.5860/choice.42-4067","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-01-24T02:24:37Z","doi":"10.5860/choice.42-4067","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.5040/9781839979804.ch-007","name":"Neuro Navigators in Families","source":"crossref","abstract":"","url":"https://doi.org/10.5040/9781839979804.ch-007","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-13T15:02:24Z","doi":"10.5040/9781839979804.ch-007","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1007/978-3-031-78949-6_11","name":"IOT Based MQTT Protocol in Wi-Fi Module ESP8266","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78949-6_11","authors":["Pallavi S. Bangare","Kishor P. Patil"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T09:29:24Z","doi":"10.1007/978-3-031-78949-6_11","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-031-27499-2_10","name":"Multiobjective Optimization of Airline Crew Management with a Genetic Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_10","authors":["Alfredo Crego","Thomas Hanne","Rolf Dornberger"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_10","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-030-96299-9_51","name":"Computer Graphics Rendering Survey: From Rasterization and Ray Tracing to Deep Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_51","authors":["Houssam Halmaoui","Abdelkrim Haqiq"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_51","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-030-37218-7_122","name":"FSO: Issues, Challenges and Heuristic Solutions","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_122","authors":["Saloni Rai","Amit Kumar Garg"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T20:02:40Z","doi":"10.1007/978-3-030-37218-7_122","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-030-49339-4_33","name":"Design of Two Slot Multiple Input Multiple Output UWB Antenna for WiMAX and WLAN Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-49339-4_33","authors":["S. Malathi","S. Aruna","K. Srinivasa Naik","B. Bharani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-05T11:05:14Z","doi":"10.1007/978-3-030-49339-4_33","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-031-78943-4_21","name":"N-Queen Problem Solution Using Modified Genetic Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78943-4_21","authors":["Raj Sinha","Navpreet Kaur","Sandeep Gupta","Padmanabh Thakur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-03T11:07:40Z","doi":"10.1007/978-3-031-78943-4_21","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-031-78949-6_15","name":"Cybercrime Legislation in India: Bridging the Gaps for Effective Cybersecurity","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78949-6_15","authors":["Manish Kumar","Pradeep Kumar Kulshrestha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T09:29:57Z","doi":"10.1007/978-3-031-78949-6_15","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/s41066-018-0122-5","name":"Nature-inspired framework of ensemble learning for collaborative classification in granular computing context","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s41066-018-0122-5","authors":["Han Liu","Mihaela Cocea"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-07-30T06:29:20Z","doi":"10.1007/s41066-018-0122-5","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-981-15-5163-5","name":"Applications of Cuckoo Search Algorithm and its Variants","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-15-5163-5","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-23T14:03:06Z","doi":"10.1007/978-981-15-5163-5","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-981-16-0662-5","name":"Applied Optimization and Swarm Intelligence","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-16-0662-5","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-05-17T20:04:51Z","doi":"10.1007/978-981-16-0662-5","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1109/nabic.2009.5393482","name":"Change detection in dynamic fitness landscapes: An immunological approach","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393482","authors":["Hendrik Richter"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5393482","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1109/hpcs.2010.5547088","name":"Towards a bio-inspired architecture for autonomic network-on-chip","source":"crossref","abstract":"","url":"https://doi.org/10.1109/hpcs.2010.5547088","authors":["Mohamed Bakhouya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-08-18T14:21:20Z","doi":"10.1109/hpcs.2010.5547088","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-031-27499-2_33","name":"Comprehensive and Systematic Review of Various Feature Extraction Techniques for Vernacular Languages","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_33","authors":["Payal Goel","Shweta Bansal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_33","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1007/978-3-031-78937-3_9","name":"HealthTech Horizons: Promoting Sustainable Healthcare in Developing Nations","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_9","authors":["Vijay Bhargav Bhamidi","Yash Kanani","Yajnaseni Dash","Ajith Abraham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:05:55Z","doi":"10.1007/978-3-031-78937-3_9","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1016/b978-0-08-102782-0.00006-x","name":"Memristive devices as computational memory","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-08-102782-0.00006-x","authors":["Abu Sebastian","Damien Querlioz","Bipin Rajendran","Sabina Spiga"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-26T05:26:39Z","doi":"10.1016/b978-0-08-102782-0.00006-x","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1049/pbpc053e_fm","name":"Front Matter","source":"crossref","abstract":"","url":"https://doi.org/10.1049/pbpc053e_fm","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-16T08:07:55Z","doi":"10.1049/pbpc053e_fm","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1109/nabic.2009.5393684","name":"Cellular automata for image noise filtering","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393684","authors":["P. Jebaraj Selvapeter","Wim Hordijk"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393684","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.31219/osf.io/mwh2b","name":"Pan-neuro: interactive computing at scale with BRAIN datasets","source":"crossref","abstract":"New technical and scientific breakthroughs are enabling neuroscientific measurements that are both wider in scope and denser in their sampling, providing views of the brain that have not been possible before. At the same time, funding initiatives, as well as scientific institutions and communities are promoting sharing of neuroscientific data. These factors are creating a deluge of neuroscience data that promises to provide new and meaningful insights into brain function. However, the size, complexity, and identifiability of the data also present challenges that arise from the difficulties in storing, accessing, processing, analyzing, visualizing and understanding data at large scale. Based on their successful adoption in the earth sciences, we have started adopting and adapting a set of tools for interactive scalable computing in neuroscience. We are building an approach that is based on a combination of a vibrant ecosystem of open-source software libraries and standards, coupled with the massive computational power of the public cloud, and served through interactive browser-based Jupyter interfaces. Together, these could provide uniform universal access to datasets for flexible and scalable exploration and analysis. We present a few prototype use-cases of this approach. We identify barriers and technical challenges that still need to be addressed to facilitate wider deployment of this approach and full exploitation of its advantages.","url":"https://doi.org/10.31219/osf.io/mwh2b","authors":["Ariel Rokem","Ben Dichter","Christopher Holdgraf","Satrajit S Ghosh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-13T12:43:36Z","doi":"10.31219/osf.io/mwh2b","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1109/bicta.2007.4806426","name":"Typhoon Image Denoising in Curvelet Domain","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2007.4806426","authors":["Changjiang Zhang","Lu Xiaoqin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-03-30T11:03:08Z","doi":"10.1109/bicta.2007.4806426","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1109/synasc.2015.12","name":"Building a Nature-Inspired Computer","source":"crossref","abstract":"","url":"https://doi.org/10.1109/synasc.2015.12","authors":["Peter J. Bentley"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-03-07T16:21:15Z","doi":"10.1109/synasc.2015.12","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1109/date.2011.5763006","name":"Biologically-inspired massively-parallel architectures &amp;#x2014; Computing beyond a million processors","source":"crossref","abstract":"","url":"https://doi.org/10.1109/date.2011.5763006","authors":["S Furber"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-02-19T17:45:16Z","doi":"10.1109/date.2011.5763006","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch029","name":"Autonomous Systems with Emergent Behavior","source":"crossref","abstract":"This chapter presents the notion of autonomous engineered systems working without central control through self-organization and emergent behavior. It argues that future large-scale applications from domains as diverse as networking systems, manufacturing control, or e-government services will benefit from being based on such systems. The goal of this chapter is to highlight engineering issues related to such systems, and to discuss some potential applications.","url":"https://doi.org/10.4018/978-1-59140-984-7.ch029","authors":["G. D.M. Serugendo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch029","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1002/9780470429983.ch19","name":"Nanoscale Image Processing","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9780470429983.ch19","authors":["Mary Mehrnoosh Eshaghian‐Wilner","Shiva Navab"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-11-24T16:16:40Z","doi":"10.1002/9780470429983.ch19","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1109/bimnics.2006.361794","name":"Modeling of Vocal Tract","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bimnics.2006.361794","authors":["Zygmunt Ciota","Malgorzata Napieralska","Andrzej Napieralski"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-06-07T15:56:37Z","doi":"10.1109/bimnics.2006.361794","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1145/3604550","name":"A Survey of Quantum-cognitively Inspired Sentiment Analysis Models","source":"crossref","abstract":"Quantum theory, originally proposed as a physical theory to describe the motions of microscopic particles, has been applied to various non-physics domains involving human cognition and decision-making that are inherently uncertain and exhibit certain non-classical, quantum-like characteristics. Sentiment analysis is a typical example of such domains. In the last few years, by leveraging the modeling power of quantum probability (a non-classical probability stemming from quantum mechanics methodology) and deep neural networks, a range of novel quantum-cognitively inspired models for sentiment analysis have emerged and performed well. This survey presents a timely overview of the latest developments in this fascinating cross-disciplinary area. We first provide a background of quantum probability and quantum cognition at a theoretical level, analyzing their advantages over classical theories in modeling the cognitive aspects of sentiment analysis. Then, recent quantum-cognitively inspired models are introduced and discussed in detail, focusing on how they approach the key challenges of the sentiment analysis task. Finally, we discuss the limitations of the current research and highlight future research directions.","url":"https://doi.org/10.1145/3604550","authors":["Yaochen Liu","Qiuchi Li","Benyou Wang","Yazhou Zhang","Dawei Song"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-14T02:41:07Z","doi":"10.1145/3604550","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.4018/979-8-3693-4001-1.ch020","name":"Quantum-Inspired Machine Learning for Chemical Reaction Path Prediction","source":"crossref","abstract":"The purpose of this study is to provide a novel method for predicting chemical response routes that is designed to exercise machine literacy techniques inspired by the concept of amount. When it comes to addressing the large number of mechanical interactions that are needed in chemical reactions, traditional types of response path vaticination frequently face obstacles. Within the scope of this investigation, the authors apply the ideas of amount computing in order to create a machine literacy framework that is inspired by amount computing and is developed for the purpose of providing accurate and efficient vaticination of response paths. The solution that has been proposed combines the suggestive power of algorithms that are inspired by amounts with the scalability and versatility of machine literacy models. This framework has been shown to have greater performance in predicting reaction courses when compared to conventional methods. This was demonstrated through extensive testing and confirmation on a variety of chemical systems.","url":"https://doi.org/10.4018/979-8-3693-4001-1.ch020","authors":["P. Neelima","V. Satyanarayana","K. B. Sravanthi","K. Sherin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-05T12:23:41Z","doi":"10.4018/979-8-3693-4001-1.ch020","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1007/978-3-031-78946-5_15","name":"A Comprehensive Review on Integration of Blockchain and IoT","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_15","authors":["P. L. Divya","B. Soniya","J. S. Jayasudha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:04:15Z","doi":"10.1007/978-3-031-78946-5_15","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1007/978-3-031-78946-5_5","name":"OSMA: Ontology Generation and Synthesis for Sports Medicine and Athletics","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_5","authors":["Harshada Anavkar","Gerard Deepak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:03:35Z","doi":"10.1007/978-3-031-78946-5_5","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-030-96299-9_6","name":"A Survey on Arrhythmia Disease Detection Using Deep Learning Methods","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_6","authors":["George C. Lufiya","Jyothi Thomas","S. U. Aswathy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_6","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-030-96299-9_1","name":"BIC Algorithm for Heineken Brand Awareness in Vietnam Market","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_1","authors":["Nguyen Thi Ngan","Bui Huy Khoi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_1","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-031-27499-2_74","name":"A Recommender System to Close Skill Gaps and Drive Organisations’ Success","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_74","authors":["E. Luciano Zickler","Susana Nicola","Nuno Bettencourt"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T15:03:17Z","doi":"10.1007/978-3-031-27499-2_74","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-319-01781-5_24","name":"Rough Power Set Tree for Feature Selection and Classification: Case Study on MRI Brain Tumor","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-01781-5_24","authors":["Waleed Yamany","Nashwa El-Bendary","Hossam M. Zawbaa","Aboul Ella Hassanien","Václav Snášel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-08-01T11:21:05Z","doi":"10.1007/978-3-319-01781-5_24","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-031-27499-2_44","name":"An Efficient Machine Learning Model for Bitcoin Price Prediction","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_44","authors":["Habeeba Tabassum Shaik","B. Sunil Kumar","Bhasha Pydala"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_44","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-031-27499-2_78","name":"Implementing ML Techniques to Predict Mental Wellness Amongst Adolescents Considering EI Levels","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_78","authors":["Pooja Manghirmalani Mishra","Rabiya Saboowala"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_78","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1109/aicare66005.2025.11402700","name":"Explanation in Bio-inspired Computing: Towards Understanding of AI Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aicare66005.2025.11402700","authors":["Rolf Drechsler","Christina Plump","Bernhard J. Berger"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-25T20:54:54Z","doi":"10.1109/aicare66005.2025.11402700","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-94-017-9112-0_1","name":"Analogical Problem Evolution in Biologically Inspired Design","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-94-017-9112-0_1","authors":["Michael E. Helms","Ashok K. Goel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-09-03T13:40:11Z","doi":"10.1007/978-94-017-9112-0_1","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-540-85954-3_6","name":"A Formal Framework for Analyzing the Behavior of BeeHive","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-540-85954-3_6","authors":["Muddassar Farooq"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-11-28T15:10:40Z","doi":"10.1007/978-3-540-85954-3_6","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.36227/techrxiv.21837027","name":"Brain Inspired Computing: A Systematic Survey and Future Trends","source":"crossref","abstract":"&lt;p&gt;Brain Inspired Computing (BIC) is an emerging research field that aims to build fundamental theories, models, hardware architectures, and application systems toward more general Artificial Intelligence (AI) by learning from the information processing mechanisms or structures/functions of biological nervous systems. It is regarded as one of the most promising research directions for future intelligent computing in the post-Moore era. In the past few years, various new schemes in this field have sprung up to explore more general AI. These works are quite divergent in the aspects of modeling/algorithm, software tool, hardware platform, and benchmark data, since BIC is an interdisciplinary field that consists of many different domains, including computational neuroscience, artificial intelligence, computer science, statistical physics, material science, microelectronics and so forth. This situation greatly impedes researchers from obtaining a clear picture and getting started in the right way. Hence, there is an urgent requirement to do a comprehensive survey in this field to help correctly recognize and analyze such bewildering methodologies. What are the key issues to enhance the development of BIC? What roles do the current mainstream technologies play in the general framework of BIC? Which techniques are truly useful in real-world applications? These questions largely remain open. To address the above issues, in this survey we first clarify the biggest challenge of BIC: how can AI models benefit from the recent advancements in computational neuroscience? With this challenge in mind, we will focus on discussing the concept of BIC and summarize four components of BIC infrastructure development: 1) modeling/algorithm; 2) hardware platform; 3) software tool; and 4) benchmark data. For each component, we will summarize its recent progress, main challenges to resolve, and future trends. On the basis of these studies, we present a general framework for the real-world applications of BIC systems, which is promising to benefit both AI and brain science. Finally, we claim that it is extremely important to build a research ecology to promote prosperity continuously in this field.&lt;/p&gt;","url":"https://doi.org/10.36227/techrxiv.21837027","authors":["Guoqi Li","Lei Deng","Huajing Tang","Gang Pan","Yonghong Tian","Kaushik Roy","Wolfgang Maass"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-19T03:30:04Z","doi":"10.36227/techrxiv.21837027","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.4018/978-1-5225-0788-8.ch053","name":"Customer Profiling in Complex Analytical Environments Using Swarm Intelligence Algorithms","source":"crossref","abstract":"Customer profiling is always an interesting task from perspective of business. It became even bigger challenge in situation of complex analytical environment. Complex analytical environment can be caused by multiple modality of output variable as well as from big data environment, which cause data complexity in way of data quantity. As an illustration of presented concept particle swarm optimization algorithm will be used as a tool, which will find profiles from developed predictive model of neural network. Presented methodology has practical value for decision support in business, where information about customer profiles which prefers to buy some product or group products are valuable information for campaign planning and customer portfolio management.","url":"https://doi.org/10.4018/978-1-5225-0788-8.ch053","authors":["Goran Klepac"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-07-26T12:16:44Z","doi":"10.4018/978-1-5225-0788-8.ch053","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-642-58930-0_6","name":"Measures of Specificity","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-58930-0_6","authors":["Ronald R. Yager"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-06-15T19:06:59Z","doi":"10.1007/978-3-642-58930-0_6","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1109/bimnics.2007.4610073","name":"Rule-based Genetic Programming","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bimnics.2007.4610073","authors":["Thomas Weise","Michael Zapf","Kurt Geihs"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-09-08T20:06:46Z","doi":"10.1109/bimnics.2007.4610073","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1145/3075564.3075597","name":"Brain-Inspired Memory Architecture for Sparse Nonlocal and Unstructured Workloads","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3075564.3075597","authors":["Yasunao Katayama"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-06-07T12:47:29Z","doi":"10.1145/3075564.3075597","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch025","name":"On Technological Specialization in Industrial Clusters","source":"crossref","abstract":"In this chapter an agent-based industry simulation model is employed to analyze the relationship between technological specialization, cluster formation, and profitability in an industry where demand is characterized by love-for-variety preferences. The main focus is on the firms’ decisions concerning the position of their products in the technology landscape. Different types of strategies are compared with respect to induced technological specialization of the industry and average industry profits. Furthermore, the role of technological spillovers in a cluster as a technological coordination device is highlighted, and it is shown that due to competition effects, such technological coordination negatively affects the profits of cluster firms.","url":"https://doi.org/10.4018/978-1-59140-984-7.ch025","authors":["H. Dawid"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch025","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-319-08156-4_27","name":"A Framework of Secured and Bio-Inspired Image Steganography Using Chaotic Encryption with Genetic Algorithm Optimization (CEGAO)","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-08156-4_27","authors":["Debiprasad Bandyopadhyay","Kousik Dasgupta","J. K. Mandal","Paramartha Dutta","Varun Kumar Ojha","Václav Snášel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-06-13T15:07:31Z","doi":"10.1007/978-3-319-08156-4_27","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1109/nabic.2009.5393698","name":"Fractal signatures for the characterization of mammograms","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393698","authors":["Deepa Sankar","Tessamma Thomas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393698","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1109/nabic.2011.6089423","name":"Explicit class structure with closeness and similarity between neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2011.6089423","authors":["Ryotaro Kamimura"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-12-06T21:02:25Z","doi":"10.1109/nabic.2011.6089423","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-7908-1902-1_70","name":"A Systolic Realisation of the Neuro-Tomograph","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-7908-1902-1_70","authors":["Robert Cierniak","Jacek Smoląg"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-03-11T00:11:40Z","doi":"10.1007/978-3-7908-1902-1_70","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-031-78946-5_17","name":"Enhancing Fault Tolerance Level in E-Health Monitoring System Using Proactive Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_17","authors":["Praynita Karki"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:04:14Z","doi":"10.1007/978-3-031-78946-5_17","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-031-78937-3_11","name":"Deep Learning Methods for Biomedical Named Entity Recognition: A Comprehensive Review","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_11","authors":["S. Sabitha","Anitha S. Pillai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:06:31Z","doi":"10.1007/978-3-031-78937-3_11","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1007/978-3-031-78937-3_3","name":"Simulation on Home Healthcare Problem: A Systematic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_3","authors":["Emerson José de Paiva","Ana Maria A. C. Rocha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:06:57Z","doi":"10.1007/978-3-031-78937-3_3","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1007/978-3-031-27499-2_30","name":"The Future in Fishfarms: An Ocean of Technologies to Explore","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_30","authors":["Ana Rita Pires","Joao C. Ferreira","Øystein Klakegg"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_30","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-981-15-6695-0_2","name":"Parameter Tuning onto Recurrent Neural Network and Long Short-Term Memory (RNN-LSTM) Network for Feature Selection in Classification of High-Dimensional Bioinformatics Datasets","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-15-6695-0_2","authors":["Richard Millham","Israel Edem Agbehadji","Hongji Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-25T10:03:38Z","doi":"10.1007/978-981-15-6695-0_2","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-031-78937-3_7","name":"Self-supervised Learning for Pathological Speech Analysis of Parkinson’s Disease","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_7","authors":["Ashwin Kumar Uniyal","Huizhi Liang","Varun Ojha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:06:43Z","doi":"10.1007/978-3-031-78937-3_7","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-031-27499-2_21","name":"Automated Depression Diagnosis in MDD (Major Depressive Disorder) Patients Using EEG Signal","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_21","authors":["Sweety Singh","Poonam Sheoran","Manoj Duhan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_21","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-030-96299-9_64","name":"Trust Management Model in IoT: A Comprehensive Survey","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_64","authors":["Muhammad Saeed","Muhammad Aftab","Rashid Amin","Deepika Koundal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_64","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.4018/979-8-3693-6834-3.ch002","name":"Task Scheduling Strategy Using Chaotic Whale Optimization Algorithm in Cloud Computing","source":"crossref","abstract":"Cloud computing is becoming popular because it can provide cloud consumers with IT services scaled up globally over the internet. These services include platforms, applications, and infrastructure. Moreover, cloud computing can be provided on demand and offered in different pricing packages. To schedule the task optimally in a cloud environment is considered an NP-hard problem, which has become complex with the introduction of variables such as resource dynamicity and on-demand consumer applications. The proposed research introduces a Whale Optimization Algorithm (WOA) incorporating a transfer function (TF) and a tent chaotic map to tackle scheduling challenges in cloud computing. The performance of the proposed chaotic-based whale optimization algorithm (CWOA) is compared to that of well-known metaheuristics methods. The results show that CWOA may significantly reduce the makespan of the task scheduling problem compared to standard Grey Wolf Optimizer (GWO) and BAT algorithms. Furthermore, it converges quickly as the search space grows more prominent, making it suitable for large-scale scheduling issues.","url":"https://doi.org/10.4018/979-8-3693-6834-3.ch002","authors":["Mohammad Qasim","Mohammad Sajid","Ranjit Rajak","Mohammad Shahid"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-06T15:02:17Z","doi":"10.4018/979-8-3693-6834-3.ch002","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.3390/materproc2025020004","name":"Performance of Fish Scale-Inspired Armour Subjected to Impact Loading by Different Impactor Shapes: A Numerical Investigation","source":"crossref","abstract":"","url":"https://doi.org/10.3390/materproc2025020004","authors":["Hari Bahadur Dura","Paul J. Hazell","Hongxu Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-07T04:28:26Z","doi":"10.3390/materproc2025020004","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1201/9781003581215-9","name":"Nature-Inspired Meta-Heuristic Algorithms for Optimizing Neural Network Training A Focus on Particle Swarm Optimization and Firefly Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003581215-9","authors":["K. P. Swains","A. S. Das","S. K. Nayak","S. K. Mohapatra","Parsuram Behera","Basudev Das"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-13T12:22:19Z","doi":"10.1201/9781003581215-9","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1109/qcnc64685.2025.00079","name":"Spider Web-Inspired Quantum Circuit for Autoencoder","source":"crossref","abstract":"","url":"https://doi.org/10.1109/qcnc64685.2025.00079","authors":["Agi Prasetiadi","Masahiro Mambo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-15T17:30:38Z","doi":"10.1109/qcnc64685.2025.00079","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1109/nabic.2009.5393858","name":"A new signature similarity measure","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393858","authors":["Piotr Porwik","Rafal Doroz","Krzysztof Wrobel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393858","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1109/bic-ta.2011.73","name":"Properties of Binding-Blocking Automata: A Study","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bic-ta.2011.73","authors":["M. Sakthi Balan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-10-18T15:35:51Z","doi":"10.1109/bic-ta.2011.73","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1109/ncis.2011.124","name":"Ant Algorithm Inspired Immune Intrusion Detector Generation Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ncis.2011.124","authors":["Xiaowei Wang","Lina Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-07-13T15:57:57Z","doi":"10.1109/ncis.2011.124","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.4018/978-1-5225-0788-8.ch029","name":"Cosine and Sigmoid Higher Order Neural Networks for Data Simulations","source":"crossref","abstract":"New open box and nonlinear model of Cosine and Sigmoid Higher Order Neural Network (CS-HONN) is presented in this paper. A new learning algorithm for CS-HONN is also developed from this study. A time series data simulation and analysis system, CS-HONN Simulator, is built based on the CS-HONN models too. Test results show that average error of CS-HONN models are from 2.3436% to 4.6857%, and the average error of Polynomial Higher Order Neural Network (PHONN), Trigonometric Higher Order Neural Network (THONN), and Sigmoid polynomial Higher Order Neural Network (SPHONN) models are from 2.8128% to 4.9077%. It means that CS-HONN models are 0.1174% to 0.4917% better than PHONN, THONN, and SPHONN models.","url":"https://doi.org/10.4018/978-1-5225-0788-8.ch029","authors":["Ming Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-07-26T12:16:44Z","doi":"10.4018/978-1-5225-0788-8.ch029","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-031-78937-3_10","name":"Unbalanced Dataset Preprocessing Using Hybrid Combination Algorithm for Arrhythmia Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_10","authors":["Lufiya George Cheruvathoor","Jyothi Thomas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:07:16Z","doi":"10.1007/978-3-031-78937-3_10","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-030-96299-9_30","name":"Crime Factor Anaysis and Prediction Using Machine Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_30","authors":["N. Anitha","S. Gowtham","M. Kaarniha Shri","T. Kalaiyarasi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_30","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-031-78937-3_2","name":"Home Healthcare Optimization: A Systematic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_2","authors":["Emerson José de Paiva","Ana Maria A. C. Rocha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:06:11Z","doi":"10.1007/978-3-031-78937-3_2","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1007/978-3-031-78949-6_13","name":"Revolutionizing Recruitment and Selection: Exploring Artificial Intelligence Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78949-6_13","authors":["R. Somasundaram","K. Nandhini","P. Dhivya","S. Jagatheesh Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T09:30:10Z","doi":"10.1007/978-3-031-78949-6_13","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-3-030-96299-9_24","name":"Remote Monitor System for Alzheimer Disease","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_24","authors":["Luis B. Elvas","Daniel Cale","Joao C. Ferreira","Ana Madureira"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_24","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-981-33-6104-1","name":"Applications of Flower Pollination Algorithm and its Variants","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-33-6104-1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-17T12:03:08Z","doi":"10.1007/978-981-33-6104-1","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1109/ibica.2011.68","name":"HAZARDS and Prevention of BLEVE","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ibica.2011.68","authors":["Tan Xian","Li Fang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-01-06T21:44:03Z","doi":"10.1109/ibica.2011.68","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1109/ictcs.2017.49","name":"Arabic LFG-inspired Dependency Treebank","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ictcs.2017.49","authors":["Dana Halabi","Arafat Awajan","Ebaa Fayyoumi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-01-11T18:57:16Z","doi":"10.1109/ictcs.2017.49","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.4018/978-1-7998-1626-3","name":"Nature-Inspired Computing Applications in Advanced Communication Networks","source":"crossref","abstract":"","url":"https://doi.org/10.4018/978-1-7998-1626-3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-10-25T12:01:11Z","doi":"10.4018/978-1-7998-1626-3","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1109/nabic.2009.5393667","name":"Evolving solutions to the school timetabling problem","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393667","authors":["Rushil Raghavjee","Nelishia Pillay"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5393667","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.2514/6.2012-1297513","name":"Planning as a Service: A Plan Repository Model Inspired by Cloud Computing","source":"crossref","abstract":"","url":"https://doi.org/10.2514/6.2012-1297513","authors":["Khawaja Shams"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-05-15T19:56:14Z","doi":"10.2514/6.2012-1297513","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-981-97-5979-8","name":"Engineering Applications of AI and Swarm Intelligence","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-5979-8","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-25T20:59:46Z","doi":"10.1007/978-981-97-5979-8","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1145/1102256.1102259","name":"Challenges for biologically-inspired computing","source":"crossref","abstract":"","url":"https://doi.org/10.1145/1102256.1102259","authors":["Russ Abbott"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-02-06T15:52:40Z","doi":"10.1145/1102256.1102259","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.4018/979-8-3693-1131-8.ch007","name":"Endometrial Cancer Detection Using Pipeline Biopsies Through Machine Learning Techniques","source":"crossref","abstract":"Endometrial carcinoma (EC) is a common uterine cancer that leads to morbidity and death linked to cancer. Advanced EC diagnosis exhibits a subpar treatment response and requires a lot of time and money. Data scientists and oncologists focused on computational biology due to its explosive expansion and computer-aided cancer surveillance systems. Machine learning offers prospects for drug discovery, early cancer diagnosis, and efficient treatment. It may be pertinent to use ML techniques in EC diagnosis, treatments, and prognosis. Analysis of ML utility in EC may spur research in EC and help oncologists, molecular biologists, biomedical engineers, and bioinformaticians advance collaborative research in EC. It also leads to customised treatment and the growing trend of using ML approaches in cancer prediction and monitoring. An overview of EC, its risk factors, and diagnostic techniques are covered in this study. It concludes a thorough investigation of the prospective ML modalities for patient screening, diagnosis, prognosis, and the deep learning models, which gave the good accuracy.","url":"https://doi.org/10.4018/979-8-3693-1131-8.ch007","authors":["Vemasani Varshini","Maheswari Raja","Sharath Kumar Jagannathan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-29T10:11:06Z","doi":"10.4018/979-8-3693-1131-8.ch007","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1007/978-3-540-45240-9_27","name":"A Multi-layered Immune Inspired Machine Learning Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-540-45240-9_27","authors":["Thomas Knight","Jon Timmis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-12-29T16:46:55Z","doi":"10.1007/978-3-540-45240-9_27","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.4018/978-1-5225-0788-8.ch010","name":"Diagnosis of Breast Cancer Using Intelligent Information Systems Techniques","source":"crossref","abstract":"Breast cancer is the second leading cause of cancer deaths in women worldwide. Early diagnosis of this illness can increase the chances of long-term survival of cancerous patients. To help in this aid, computerized breast cancer diagnosis systems are being developed. Machine learning algorithms and data mining techniques play a central role in the diagnosis. This paper describes neural network based approaches to breast cancer diagnosis. The aim of this research is to investigate and compare the performance of supervised and unsupervised neural networks in diagnosing breast cancer. A multilayer perceptron has been implemented as a supervised neural network and a self-organizing map as an unsupervised one. Both models were simulated using a variety of parameters and tested using several combinations of those parameters in independent experiments. It was concluded that the multilayer perceptron neural network outperforms Kohonen's self-organizing maps in diagnosing breast cancer even with small data sets.","url":"https://doi.org/10.4018/978-1-5225-0788-8.ch010","authors":["Ahmad Al-Khasawneh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-07-26T12:16:44Z","doi":"10.4018/978-1-5225-0788-8.ch010","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1201/9781315217826-13","name":"HAMSoC: A Monitoring-Centric Design Approach for Adaptive Parallel Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781315217826-13","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-05T22:36:37Z","doi":"10.1201/9781315217826-13","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.4018/979-8-3693-7076-6.ch004","name":"Quantum-Inspired Algorithms for AI and Machine Learning","source":"crossref","abstract":"Quantum-inspired algorithms help handle complex optimization and inference challenges in AI and ML. Quantum-like algorithms based on quantum mechanics address challenges classical computer paradigms can't. These algorithms innovate data handling, solution finding, and pattern recognition. Quantum effects like superposition, entanglement, and tunneling influenced them. In particular, they work in parallel to explore large solution spaces and speed up processing for large datasets. Next, quantum-inspired algorithms including quantum annealing, optimization, and neural networks are discussed. Simulated annealing and the quantum approximate optimization algorithm (QAOA) make combinatorial optimization tasks in AI and ML easier. Quantum-inspired evolutionary and swarm intelligence algorithms tackle multi-modal optimization issues quickly. Furthermore, quantum-inspired neural networks (QNNs) have revolutionized deep learning. QNNs use quantum gates and quantum circuits to improve classification, regression, and generative modeling.","url":"https://doi.org/10.4018/979-8-3693-7076-6.ch004","authors":["Kamaleswari Pandurangan","A. Priyadharshini","Rakheeba Taseen","B. Galebathullah","Haseeba Yaseen","P. Ravichandran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-29T12:37:09Z","doi":"10.4018/979-8-3693-7076-6.ch004","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1007/978-3-031-27499-2_28","name":"Detecting Depression on Social Platforms Using Machine Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_28","authors":["Muhammad Ishtiaq","Kainat Bibi","Mehmoon Anwar","Rashid Amin","Rahul Nijhawan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_28","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-031-78940-3_22","name":"On Hyperspectral Image Classification and Deep Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78940-3_22","authors":["K. Prema","A. V. Sriharsha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-05T06:07:09Z","doi":"10.1007/978-3-031-78940-3_22","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-030-96299-9_44","name":"My Buddy: A 3D Game for Children Based on Voice Commands","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_44","authors":["Diana Carvalho","Tânia Rocha","João Barroso"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_44","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-031-27499-2_54","name":"RMSLRS: Real-Time Multi-terminal Sign Language Recognition System","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_54","authors":["Yilin Zhao","Biao Zhang","Kun Ma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_54","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-3-031-27499-2_37","name":"Policy-Based Code Slicing of Database Application Using Semantic Rule-Based Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_37","authors":["Anwesha Kashyap","Angshuman Jana"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_37","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1109/nabic.2009.5393874","name":"Hybrid multispectral image fusion method","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393874","authors":["Tanish Zaveri","Ishit Makwana","Mukesh Zaveri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5393874","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1109/icgec.2011.70","name":"Immunity-Inspired Host-Based Intrusion Detection Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icgec.2011.70","authors":["Chung-Ming Ou","C.R. Ou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-10-13T16:56:10Z","doi":"10.1109/icgec.2011.70","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1038/d41586-020-02829-w","name":"Brain-inspired computing boosted by new concept of completeness","source":"crossref","abstract":"","url":"https://doi.org/10.1038/d41586-020-02829-w","authors":["Oliver Rhodes"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-10-14T14:03:15Z","doi":"10.1038/d41586-020-02829-w","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.4018/979-8-3693-6303-4.ch016","name":"Neuromorphic Software Tools and Development Environments","source":"crossref","abstract":"We are seeing a technological transformation now that was unthinkable ten years ago. Although introducing artificial intelligence (AI) in contemporary business theoretically permits unrestricted expansion, the dreaded power-wall issue in the parallel computing paradigm prevents us from fully using AI's potential. Because they are expected to operate at extremely low power, modern Neuromorphic accelerators provide a profitable substitute for conventional artificial neural network (ANN) accelerators for deep learning (DL). Neuromorphic accelerators are centred on Spiking Neural Networks (SNN), which seek to mimic the extremely energy-efficient mechanism operating in our brains. This chapter covers the general overview of Neuromorphic software tools and development environments, including platforms, frameworks, and best practices.","url":"https://doi.org/10.4018/979-8-3693-6303-4.ch016","authors":["D. Sailaja","Yogesh Kumar Sharma","V. L. Manaswini Nune"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-29T15:16:27Z","doi":"10.4018/979-8-3693-6303-4.ch016","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1093/neuonc/noae165.0577","name":"DISP-03. HEALTH DISPARITIES IN NEURO-ONCOLOGY","source":"crossref","abstract":"Abstract Significant disparities in diagnosis, research, and treatment exist in neuro-oncology. Patients who identify as racial or ethnic minorities, sexual or gender minorities, elderly, rural, or have low socioeconomic status are more likely to have adverse outcomes. Using PubMed and expert opinion, we summarized the existing literature on health disparities in neuro-oncology. We categorized disparities based on primary central nervous system tumors (CNS), secondary CNS tumors, pediatric neuro-oncology, clinical trial enrollment and diversity, and financial toxicity. For patients with primary CNS tumors, we found that marginalized groups faced delays in diagnosis, lower rates of resection, and lower rates of postoperative radiation. For secondary CNS tumors, marginalized groups had lower rates of indicated cancer screening, less access to genetic testing, less access to advanced imaging, and lower rates of stereotactic radiosurgery and targeted therapies. Pediatric neuro-oncology patients had differences in morbidity and mortality based on socioeconomic status and race and faced substantial delays in diagnosis. Financial toxicity, the side effects of the high financial cost of a cancer diagnosis, disproportionately affects marginalized populations. This may be further exacerbated by the use of long-term medications such as IDH inhibitors. There is also unequal representation of diverse populations in neuro-oncology clinical trials. Compared to other cancer subspecialties, there is less available data on disparities, however, the types of disparities such as delays in diagnosis and outcomes are similar. Notably, there are not many interventions focused on mitigating these disparities. There needs to be additional research on health disparities in neuro-oncology, including both descriptions of existing disparities, but also on methods and interventions to address these disparities.","url":"https://doi.org/10.1093/neuonc/noae165.0577","authors":["Joshua Budhu","Nara Michaelson","Amanda Watsula","Anu Bakare","Mali Mohamadpour","Ugonma Chukwueke"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-11T19:44:39Z","doi":"10.1093/neuonc/noae165.0577","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1109/ijcnn.1989.118391","name":"Neuro-algorithms for data compression with new generation computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.1989.118391","authors":["Y. Matsuyama"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-01-13T18:46:33Z","doi":"10.1109/ijcnn.1989.118391","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-981-96-9585-0_2","name":"On Tricyclic Graphs with Maximal Graovac-Ghorbani Index","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-96-9585-0_2","authors":["Mengya Cui","Xianya Geng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-22T09:23:20Z","doi":"10.1007/978-981-96-9585-0_2","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1016/j.eswa.2007.08.108","name":"GenSoFNN-Yager: A novel brain-inspired generic self-organizing neuro-fuzzy system realizing Yager inference","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.eswa.2007.08.108","authors":["R.J. Oentaryo","M. Pasquier","C. Quek"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-10-01T14:00:10Z","doi":"10.1016/j.eswa.2007.08.108","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1016/b978-0-443-15663-2.00040-7","name":"Quality of life and patient-reported outcomes in neuro-oncology clinical care and research","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-15663-2.00040-7","authors":["Amanda L. King","Jennifer Cahill"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-09T08:16:09Z","doi":"10.1016/b978-0-443-15663-2.00040-7","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.5220/0013924000004919","name":"Neuro Genetic Disorder’s: Epilepsy and Huntington’s Disease","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0013924000004919","authors":["R. Yamini","Zahid Wani","Arham Chowdary"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-01T04:02:08Z","doi":"10.5220/0013924000004919","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1016/j.asoc.2005.06.007","name":"Improving the COCOMO model using a neuro-fuzzy approach","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2005.06.007","authors":["Xishi Huang","Danny Ho","Jing Ren","Luiz F. Capretz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-10-13T09:45:49Z","doi":"10.1016/j.asoc.2005.06.007","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1016/j.asoc.2011.06.012","name":"An adaptive neuro-fuzzy approach to risk factor analysis of Salmonella Typhimurium infection","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2011.06.012","authors":["Lixu Qin","Simon X. Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-07-10T17:45:34Z","doi":"10.1016/j.asoc.2011.06.012","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1201/9781032644752-21","name":"Review on multi-robot path planning in complex industrial dynamic environment using improved nature inspired techniques","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781032644752-21","authors":["Subhash Yadav","Shubham Shukla","Ritu Tiwari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-21T11:06:31Z","doi":"10.1201/9781032644752-21","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1007/s00500-014-1414-6","name":"Biologically inspired deoxyribonucleic acid soft computing for inverse kinematics solver of five-DOF robotic manipulators","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00500-014-1414-6","authors":["Hsu-Chih Huang","Huan-Shiuan Hsu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-08-09T05:50:58Z","doi":"10.1007/s00500-014-1414-6","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-3-319-28031-8_35","name":"A Hybrid Dimension Reduction Technique for Document Clustering","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-28031-8_35","authors":["Cynthia Marea Nebu","Sumy Joseph"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-13T20:02:33Z","doi":"10.1007/978-3-319-28031-8_35","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1016/j.suscom.2025.101082","name":"Bio-inspired optimizer with deep learning model for energy management system in electric vehicles","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.suscom.2025.101082","authors":["C. Srinivasan","C. Sheeba Joice"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-11T11:40:15Z","doi":"10.1016/j.suscom.2025.101082","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.21203/rs.3.rs-1121838/v1","name":"Application of Nature Inspired Soft Computing Techniques for Gene Selection: A Novel Frame Work for Classification of Cancer.","source":"crossref","abstract":"Abstract A modified Artificial Bee Colony (ABC) metaheuristics optimization technique is applied for cancer classification, that reduces the classifier's prediction errors and allows for faster convergence by selecting informative genes. Cuckoo search (CS) algorithm was used in the onlooker bee phase (exploitation phase)of ABC to boost performance by maintaining the balance between exploration and exploitation of ABC. Tuned the modified ABC algorithm by using Naïve Bayes (NB) classifiers to improve the further accuracy of the model. Independent Component Analysis (ICA) is used for dimensionality reduction. In the first step, the reduced dataset is optimized by using Modified ABC and after that, in the second step, the optimized dataset is used to train the NB classifier. Extensive experiments were performed for comprehensive comparative analysis of the proposed algorithm with well-known metaheuristic algorithms, namely Genetic Algorithm (GA) when used with the same framework for the classification of six high-dimensional cancer datasets. The comparison results showed that the proposed model with the CS algorithm achieves the highest performance as maximum classification accuracy with less count of selected genes. This shows the effectiveness of the proposed algorithm which is validated using ANOVA for cancer classification.","url":"https://doi.org/10.21203/rs.3.rs-1121838/v1","authors":["Rabia Musheer Aziz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-01-04T23:37:59Z","doi":"10.21203/rs.3.rs-1121838/v1","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1007/978-3-031-78940-3_10","name":"A Comparison of Machine Learning Algorithms on Handwritten Digit Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78940-3_10","authors":["Neha","Meenakshi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-05T06:07:39Z","doi":"10.1007/978-3-031-78940-3_10","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-3-030-96299-9_21","name":"A Review on MOEA and Metaheuristics for Feature-Selection","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_21","authors":["Duarte Coelho","Ana Madureira","Ivo Pereira","Ramiro Gonçalves"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_21","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1007/978-3-030-96299-9_60","name":"Non-invasive Flexible Electromagnetic Sensor for Potassium Level Monitoring in Sweat","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_60","authors":["Gianvito Mevoli","Claudio Maria Lamacchia","Luciano Mescia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_60","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-3-031-78943-4_1","name":"Ant Collective Behavior Inspires Robotics for Finding Proper Size of Swarm Involving Functional Heterogeneity","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78943-4_1","authors":["Hideyasu Sasaki"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-03T07:07:40Z","doi":"10.1007/978-3-031-78943-4_1","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-3-7908-1814-7_9","name":"Neuro-Fuzzy Modelling of Time Series","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-7908-1814-7_9","authors":["Jianwei Zhang","Alois Knoll"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-08-10T02:19:45Z","doi":"10.1007/978-3-7908-1814-7_9","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-981-97-2275-4_16","name":"Controllability of Windmill Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-2275-4_16","authors":["Pengcheng Guo","Pengchao Lv","Junjie Huang","Bo Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-15T19:02:10Z","doi":"10.1007/978-981-97-2275-4_16","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1109/tcad.2022.3164330","name":"Neuro-Ising: Accelerating Large-Scale Traveling Salesman Problems via Graph Neural Network Guided Localized Ising Solvers","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tcad.2022.3164330","authors":["Sourav Sanyal","Kaushik Roy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-01T19:59:05Z","doi":"10.1109/tcad.2022.3164330","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1016/j.asoc.2019.02.008","name":"A fuzzy-filtered neuro-fuzzy framework for software fault prediction for inter-version and inter-project evaluation","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2019.02.008","authors":["Kapil Juneja"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-02-11T12:01:13Z","doi":"10.1016/j.asoc.2019.02.008","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1002/aisy.202500526","name":"Speech Recognition with Cochlea‐Inspired In‐Sensor Computing","source":"crossref","abstract":"Traditional speech recognition methods rely on software‐based feature extraction that introduces latency and high energy costs, making them unsuitable for low‐power devices. A proof‐of‐concept demonstration is provided of a bioinspired tonotopic sensor for speech recognition that mimics the human cochlea, using a spiral‐shaped elastic metamaterial. The measured modal response of the structure at different frequencies generates a spatially distributed signal, providing a spatiotemporal map of the input named “tonogram”. The device acts as an in‐sensor physical reservoir computing system, working simultaneously as a sensor and as a computing unit, capable of extracting features of spoken words relevant to speech recognition. Results indicate that this can serve as a valid alternative to traditional software‐based digital preprocessing, ensuring high accuracy in terms of classification, while reducing computational requirements. This work demonstrates the potential of bioinspired metamaterials for energy‐efficient auditory sensing and, beyond speech recognition, for applications such as IoT devices and edge computing artificial intelligence systems.","url":"https://doi.org/10.1002/aisy.202500526","authors":["Paolo H. Beoletto","Gianluca Milano","Carlo Ricciardi","Federico Bosia","Antonio S. Gliozzi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-18T19:13:57Z","doi":"10.1002/aisy.202500526","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.4018/ijcac.297104","name":"Efficient Resource Management Using Improved Bio-Inspired Algorithms for the Fog Computing Environment","source":"crossref","abstract":"The resource monitoring and management services together play a vital role in improving the overall performance of fog computing services. The monitoring system continuously keeps track of all resources by collecting and analyzing the status information and alert the user when the performance decreases. Resource management involves load balancing, resource scheduling and allocation and it requires accurate resource status which is provided by resource monitoring system to take scheduling and allocation decisions. The resource management activities are NP-hard problems and require optimal techniques to improve resource utilization and reduce energy consumption and latency. This paper proposes resource management model using improved bio-inspired algorithms and fog monitoring model to improve resource utilization and reduce energy consumption. The simulation results show that the proposed model is effective in terms of execution time, response time and energy consumption compared to the state of art techniques.","url":"https://doi.org/10.4018/ijcac.297104","authors":["Chetan M. Bulla","Mahantesh N. Birje"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-04T15:50:03Z","doi":"10.4018/ijcac.297104","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/s00779-023-01778-1","name":"Retraction Note: An improved nature inspired meta-heuristic algorithm for 1-D bin packing problems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00779-023-01778-1","authors":["Mohamed Abdel-Basset","Gunasekaran Manogaran","Laila Abdel-Fatah","Seyedali Mirjalili"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-07T04:02:36Z","doi":"10.1007/s00779-023-01778-1","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1007/978-3-211-78775-5_21","name":"Cooperative behavior of robots controlled by CNN autowaves","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-211-78775-5_21","authors":["Paolo Crucitti","Giuseppe Dimartino","Marco Pavone","Calogero D. Presti"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-11-29T12:44:42Z","doi":"10.1007/978-3-211-78775-5_21","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1145/3381755.3381764","name":"Caspian","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3381755.3381764","authors":["J. Parker Mitchell","Catherine D. Schuman","Robert M. Patton","Thomas E. Potok"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-18T23:09:51Z","doi":"10.1145/3381755.3381764","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1016/j.eswa.2020.114133","name":"Quantum-inspired neuro coevolution model applied to coordination problems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.eswa.2020.114133","authors":["Eduardo Dessupoio Moreira Dias","Marley Maria Bernardes Rebuzzi Vellasco","André Vargas Abs da Cruz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-10-20T22:38:17Z","doi":"10.1016/j.eswa.2020.114133","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1145/3253209","name":"Session details: Neuro-fuzzy applications","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3253209","authors":["Ernesto Damiani","Athanasios Vasilakos"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-10T16:58:21Z","doi":"10.1145/3253209","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-981-99-7227-2_2","name":"Advancements in Rank-Based Ant System: Enhancements for Improved Solution Quality in Combinatorial Optimization","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-99-7227-2_2","authors":["Sara Pérez-Carabaza","Akemi Gálvez","Andrés Iglesias"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-15T13:02:31Z","doi":"10.1007/978-981-99-7227-2_2","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1007/978-3-642-02490-0_93","name":"Brain-Inspired Emergence of Behaviors Based on the Desire for Existence by Reinforcement Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-02490-0_93","authors":["Mikio Morita","Masumi Ishikawa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-07-30T06:08:21Z","doi":"10.1007/978-3-642-02490-0_93","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-3-7908-1802-4","name":"Neuro-Fuzzy Architectures and Hybrid Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-7908-1802-4","authors":["Danuta Rutkowska"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-11-11T19:21:46Z","doi":"10.1007/978-3-7908-1802-4","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1145/3613904.3642346","name":"DoodleTunes: Interactive Visual Analysis of Music-Inspired Children Doodles with Automated Feature Annotation","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3613904.3642346","authors":["Shuqi Liu","Jia Bu","Huayuan Ye","Juntong Chen","Shiqi Jiang","Mingtian Tao","Liping Guo","Changbo Wang","Chenhui Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-11T08:37:41Z","doi":"10.1145/3613904.3642346","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1007/978-3-031-69257-4_11","name":"Success Rate Based Scaling Factor Adaptation in Dual-Population Differential Evolution","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-69257-4_11","authors":["Vladimir Stanovov","Eugene Semenkin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-14T08:03:00Z","doi":"10.1007/978-3-031-69257-4_11","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1007/978-981-97-5979-8_9","name":"Depth Perspective-Aware Multiple Object Tracking","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-5979-8_9","authors":["Kha Gia Quach","Pha Nguyen","Chi Nhan Duong","Tien Dai Bui","Khoa Luu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-25T20:59:46Z","doi":"10.1007/978-981-97-5979-8_9","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1016/j.asoc.2015.04.014","name":"Speed control of Brushless DC motor using bat algorithm optimized Adaptive Neuro-Fuzzy Inference System","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2015.04.014","authors":["K. Premkumar","B.V. Manikandan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-04-15T18:18:39Z","doi":"10.1016/j.asoc.2015.04.014","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-1-4471-3740-5_5","name":"Evolving Neuro-Fuzzy Inference Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4471-3740-5_5","authors":["Nikola Kasabov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-01-04T12:06:39Z","doi":"10.1007/978-1-4471-3740-5_5","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-981-99-7227-2_6","name":"Utilizing Ant Colony Optimization to Construct an S-Box Based on the 2D Logistic-Sine Coupled Map","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-99-7227-2_6","authors":["Serap Şahinkaya","Deniz Ustun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-15T13:02:31Z","doi":"10.1007/978-981-99-7227-2_6","addedAt":"2026-09-01T01:48:28.162Z","updatedAt":"2026-09-01T01:48:28.162Z"},{"id":"doi:10.1007/978-981-96-9582-9_3","name":"Segmentation of Hepatic Vessels with Deep Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-96-9582-9_3","authors":["Wei Jiang","Xueshuang Deng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-23T05:52:53Z","doi":"10.1007/978-981-96-9582-9_3","addedAt":"2026-09-01T01:48:28.163Z","updatedAt":"2026-09-01T01:48:28.163Z"},{"id":"doi:10.1109/ssci.2017.8285226","name":"Evolving neuro-fuzzy system based online identification of a bio-inspired flapping wing micro aerial vehicle","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ssci.2017.8285226","authors":["Md Meftahul Ferdaus","Mahardhika Pratama","Sreenatha G. Anavatti","Matthew A. Garratt"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-02-12T22:52:06Z","doi":"10.1109/ssci.2017.8285226","addedAt":"2026-09-01T01:48:28.163Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-981-97-7344-2_3","name":"Swarm Intelligence for Optimization: A Bee’s-Eye View on Multi-objective and Dynamic Challenges","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-7344-2_3","authors":["R. S. M. Lakshmi Patibandla","D. Madhusudhana Rao","Y. Gokul"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-01T08:28:15Z","doi":"10.1007/978-981-97-7344-2_3","addedAt":"2026-09-01T01:48:28.163Z","updatedAt":"2026-09-01T01:48:28.163Z"},{"id":"doi:10.1109/mcom.022.2300099","name":"An Evaluation of Bio-Inspired Resource Allocation Methods for Vehicular Edge Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mcom.022.2300099","authors":["Douglas D. Lieira","Matheus S. Quessada","Sandra Sampaio","Antonio A. F. Loureiro","Rodolfo I. Meneguette"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-28T17:55:08Z","doi":"10.1109/mcom.022.2300099","addedAt":"2026-09-01T01:48:28.163Z","updatedAt":"2026-09-01T01:48:28.163Z"},{"id":"doi:10.1007/978-981-97-2272-3_25","name":"Numerical P Systems with Thresholds and Petri Nets","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-2272-3_25","authors":["Luping Zhang","Zhimeng Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-15T19:02:10Z","doi":"10.1007/978-981-97-2272-3_25","addedAt":"2026-09-01T01:48:28.163Z","updatedAt":"2026-09-01T01:48:28.163Z"},{"id":"doi:10.1016/j.aci.2017.05.005","name":"Genetic-neuro-fuzzy system for grading depression","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.aci.2017.05.005","authors":["Kumar Ashish","Anish Dasari","Subhagata Chattopadhyay","Nirmal Baran Hui"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-05-25T04:30:53Z","doi":"10.1016/j.aci.2017.05.005","addedAt":"2026-09-01T01:48:28.163Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1093/neuonc/noae110","name":"Forthcoming Meetings","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuonc/noae110","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-05T19:44:51Z","doi":"10.1093/neuonc/noae110","addedAt":"2026-09-01T01:48:28.163Z","updatedAt":"2026-09-01T01:48:28.163Z"},{"id":"doi:10.1038/s41467-023-39070-8","name":"Eye accommodation-inspired neuro-metasurface focusing","source":"crossref","abstract":"Abstract The human eye, which relies on a flexible and controllable lens to focus light onto the retina, has inspired many scientific researchers to understand better and imitate the biological vision system. However, real-time environmental adaptability presents an enormous challenge for artificial eye-like focusing systems. Inspired by the mechanism of eye accommodation, we propose a supervised-evolving learning algorithm and design a neuro-metasurface focusing system. Driven by on-site learning, the system exhibits a rapid response to ever-changing incident waves and surrounding environments without any human intervention. Adaptive focusing is achieved in several scenarios with multiple incident wave sources and scattering obstacles. Our work demonstrates the unprecedented potential for real-time, fast, and complex electromagnetic (EM) wave manipulation for various purposes, such as achromatic, beam shaping, 6 G communication, and intelligent imaging.","url":"https://doi.org/10.1038/s41467-023-39070-8","authors":["Huan Lu","Jiwei Zhao","Bin Zheng","Chao Qian","Tong Cai","Erping Li","Hongsheng Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-06T14:41:45Z","doi":"10.1038/s41467-023-39070-8","addedAt":"2026-09-01T01:48:28.163Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/s00607-012-0190-3","name":"A trust-based bio-inspired approach for credit lending decisions","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00607-012-0190-3","authors":["Monireh Sadat Mirtalaei","Morteza Saberi","Omar Khadeer Hussain","Behzad Ashjari","Farookh Khadeer Hussain"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-03-01T08:54:36Z","doi":"10.1007/s00607-012-0190-3","addedAt":"2026-09-01T01:48:28.163Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-3-319-27400-3_13","name":"Sinuosity Coefficients for Leaf Shape Characterisation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-27400-3_13","authors":["Jules R. Kala","Serestina Viriri","Deshendran Moodley"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-01T17:08:38Z","doi":"10.1007/978-3-319-27400-3_13","addedAt":"2026-09-01T01:48:28.163Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1039/d4ra02843k/v2/review1","name":"Review for \"Lotus leaf-inspired thermal insulation and anti-icing topography\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d4ra02843k/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-12T17:03:14Z","doi":"10.1039/d4ra02843k/v2/review1","addedAt":"2026-09-01T01:48:28.163Z","updatedAt":"2026-09-01T01:48:28.163Z"},{"id":"doi:10.33034/paideia.2024.1.103","name":"Creation Inspired by Music","source":"crossref","abstract":"This study reveals the preliminary results of a project involving pre-service preschool teachers (N=32). This investigation is relevant since it is crucial that students must benefit from tasks aimed at developing productive imagination during their preschool teacher training, as their future job is one of the professions that requires the most creativity within pedagogy. Accordingly, in the framework of the “Play in the Arts” course, the participants could experience the manifestation of their own creative imagination through a multi-step project. As a result, various unique products (drawings or paintings; stories; scenes of the stories visualised in plasticine; photos of scenes; photo slides etc.) were created. The results are related to the first phase of the project: creating associations inspired by music, then representing the created internal images and verbal associations as external images.","url":"https://doi.org/10.33034/paideia.2024.1.103","authors":["Ágnes Magyar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-06T13:40:56Z","doi":"10.33034/paideia.2024.1.103","addedAt":"2026-09-01T01:48:28.163Z","updatedAt":"2026-09-01T01:48:28.163Z"},{"id":"doi:10.1007/978-3-031-64067-4_18","name":"A New Type of Classification Algorithm Inspired by the Chromatographic Separation Mechanism","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-64067-4_18","authors":["Mariusz Święcicki"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-07T23:03:35Z","doi":"10.1007/978-3-031-64067-4_18","addedAt":"2026-09-01T01:48:28.163Z","updatedAt":"2026-09-01T01:48:28.163Z"},{"id":"doi:10.1093/neuonc/noae075","name":"Forthcoming Meetings","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuonc/noae075","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-03T14:27:13Z","doi":"10.1093/neuonc/noae075","addedAt":"2026-09-01T01:48:28.163Z","updatedAt":"2026-09-01T01:48:28.163Z"},{"id":"doi:10.1016/b978-0-443-15663-2.09991-0","name":"Front Matter","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-15663-2.09991-0","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-09T07:39:50Z","doi":"10.1016/b978-0-443-15663-2.09991-0","addedAt":"2026-09-01T01:48:28.163Z","updatedAt":"2026-09-01T01:48:28.163Z"},{"id":"doi:10.1109/roman.2016.7745090","name":"Using natural language feedback in a neuro-inspired integrated multimodal robotic architecture","source":"crossref","abstract":"","url":"https://doi.org/10.1109/roman.2016.7745090","authors":["Johannes Twiefel","Xavier Hinaut","Marcelo Borghetti","Erik Strahl","Stefan Wermter"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-11-17T16:34:23Z","doi":"10.1109/roman.2016.7745090","addedAt":"2026-09-01T01:48:28.163Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-981-33-6862-0_13","name":"Particle Swarm Optimization Based on Random Walk","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-33-6862-0_13","authors":["Rajesh Misra","Kumar Sankar Ray"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-06-14T05:02:45Z","doi":"10.1007/978-981-33-6862-0_13","addedAt":"2026-09-01T01:48:28.163Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1201/9781003455233-3","name":"Amazing Technologies Inspired by Insects and Beetles","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003455233-3","authors":["R. Ramakrishna Reddy","T. Pullaiah"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-03T10:36:24Z","doi":"10.1201/9781003455233-3","addedAt":"2026-09-01T01:48:28.163Z","updatedAt":"2026-09-01T01:48:28.163Z"},{"id":"doi:10.1142/9789811235740_0008","name":"Organic Memristive Devices for Bio-inspired Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789811235740_0008","authors":["Victor Erokhin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-08-23T06:59:55Z","doi":"10.1142/9789811235740_0008","addedAt":"2026-09-01T01:48:28.163Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1201/9781003248545-9","name":"Bio-Inspired Algorithm for Communication Network System Architecture and Protocols","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003248545-9","authors":["P Chitra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-23T20:32:32Z","doi":"10.1201/9781003248545-9","addedAt":"2026-09-01T01:48:28.163Z","updatedAt":"2026-09-01T01:48:28.163Z"},{"id":"doi:10.1109/ijcnn.2006.246872","name":"AER Neuro-Inspired interface to Anthropomorphic Robotic Hand","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.246872","authors":["A. Linares-Barranco","R. Paz-Vicente","G. Jimenez","J.L. Pedreno-Molina","J. Molina-Vilaplana","J. Lopez-Coronado"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T11:34:22Z","doi":"10.1109/ijcnn.2006.246872","addedAt":"2026-09-01T01:48:28.163Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.4018/ijcac.314209","name":"Improving Virtual Machine Migration Effects in Cloud Computing Environments Using Depth First Inspired Opportunity Exploration","source":"crossref","abstract":"The cloud platform has established itself as the de-facto standard in IT outsourcing. This is resulting in large-scale migration of infrastructure and development platforms from in-house to cloud service providers. Many recent proposals on cloud platforms have addressed several issues that appeared on the cloud horizon. VM placement (VMP) has been a serious concern when it comes to placement of VMs after migration or VM reallocation. Most of the recent works have lacked multiple VM placement (MVMP) problem instances. A recently researched idea of MVMP through depth first opportunistic exploration (DFOE) is proposed in this paper. The performance of MVMP is compared with existing single VM placement benchmark algorithm. Improvement in terms of number of VM migrations, energy consumption, and VM reallocation is reported through simulation of real-time load scenario. Cloud environments can benefit from MVMP and improve operating margins in terms of power saving and load balancing.","url":"https://doi.org/10.4018/ijcac.314209","authors":["Kamal Kumar","Jyoti Thaman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-17T10:03:59Z","doi":"10.4018/ijcac.314209","addedAt":"2026-09-01T01:48:28.163Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1134/s263516762560052x","name":"Modeling of Hardware Dopamine-Like Learning in a Spiking Neural Network with Memristive Synaptic Weights","source":"crossref","abstract":"","url":"https://doi.org/10.1134/s263516762560052x","authors":["I. V. Alyaev","I. A. Surazhevsky","A. I. Iliasov","V. V. Rylkov","V. A. Demin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-25T14:54:13Z","doi":"10.1134/s263516762560052x","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/iscas45731.2020.9180629","name":"Scalable Block-Based Spiking Neural Network Hardware with a Multiplierless Neuron Model","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas45731.2020.9180629","authors":["Vishnu P. Nambiar","Eng Kiat Koh","Junran Pu","Aarthy Mani","Wong Ming Ming","Li Fei","Wang Ling Goh","Anh Tuan Do"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-29T13:22:27Z","doi":"10.1109/iscas45731.2020.9180629","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1007/978-1-4471-2063-6_265","name":"Pattern Segmentation and Feature Linking as Simultaneous Processes in an Associative Network of Spiking Neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4471-2063-6_265","authors":["Raphael Ritz","J. Leo van Hemmen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-04-10T03:08:22Z","doi":"10.1007/978-1-4471-2063-6_265","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1016/j.aeue.2025.156004","name":"Spiking neural network circuit with op-amp based LIF neuron and RRAM synaptic array","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.aeue.2025.156004","authors":["Eashwar M.V.","Nivetha T.","Bindu B.","Noor Ain Kamsani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-20T13:13:37Z","doi":"10.1016/j.aeue.2025.156004","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1145/3444950.3444951","name":"Gyro: A Digital Spiking Neural Network Architecture for Multi-Sensory Data Analytics","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3444950.3444951","authors":["Federico Corradi","Guido Adriaans","Sander Stuijk"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-02-25T01:33:15Z","doi":"10.1145/3444950.3444951","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1016/j.asoc.2023.111218","name":"Binarized Spiking Neural Network with blockchain based intrusion detection framework for enhancing privacy and security in cloud computing environment","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2023.111218","authors":["Velliangiri Sarveshwaran","Shanthini Pandiaraj","Garikapati Bindu","Vithya Ganesan","Iwin Thanakumar Joseph Swamidason"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-27T02:47:21Z","doi":"10.1016/j.asoc.2023.111218","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1007/978-3-319-44778-0_6","name":"Multilayer Spiking Neural Network for Audio Samples Classification Using SpiNNaker","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-44778-0_6","authors":["Juan Pedro Dominguez-Morales","Angel Jimenez-Fernandez","Antonio Rios-Navarro","Elena Cerezuela-Escudero","Daniel Gutierrez-Galan","Manuel J. Dominguez-Morales","Gabriel Jimenez-Moreno"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-08-12T11:20:33Z","doi":"10.1007/978-3-319-44778-0_6","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/72.977304","name":"NeuroPipe-Chip: A digital neuro-processor for spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/72.977304","authors":["T. Schoenauer","S. Atasoy","N. Mehrtash","H. Klar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-24T20:14:45Z","doi":"10.1109/72.977304","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/ijcnn.2015.7280816","name":"Composer classification based on temporal coding in adaptive spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2015.7280816","authors":["Chaitanya Prasad N","Krishnakant Saboo","Bipin Rajendran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-10-01T17:48:02Z","doi":"10.1109/ijcnn.2015.7280816","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1162/08997660252741167","name":"Temporal Correlations in Stochastic Networks of Spiking Neurons","source":"crossref","abstract":"The determination of temporal and spatial correlations in neuronal activity is one of the most important neurophysiological tools to gain insight into the mechanisms of information processing in the brain. Its interpretation is complicated by the difficulty of disambiguating the effects of architecture, single-neuron properties, and network dynamics. We present a theory that describes the contribution of the network dynamics in a network of “spiking” neurons. For a simple neuron model including refractory properties, we calculate the temporal cross-correlations in a completely homogeneous, excitatory, fully connected network in a stable, stationary state, for stochastic dynamics in both discrete and continuous time. We show that even for this simple network architecture, the cross-correlations exhibit a large variety of qualitatively different properties, strongly dependent on the level of noise, the decay constant of the refractory function, and the network activity. At the critical point, the cross-correlations oscillate with a frequency that depends on the refractory properties or decay exponentially with a diverging damping constant (for “weak” refractory properties). We also investigate the effect of the synaptic time constants. It is shown that these time constants may, apart from their influence on the asymmetric peak arising from the direct synaptic connection, also affect the long-term properties of the cross-correlations.","url":"https://doi.org/10.1162/08997660252741167","authors":["Carsten Meyer","Carl van Vreeswijk"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-27T07:56:30Z","doi":"10.1162/08997660252741167","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1140/epjqt/s40507-025-00443-1","name":"A hybrid spiking neural network - quantum framework for spatio-temporal data classification: a case study on EEG data","source":"crossref","abstract":"Abstract The study introduces a hybrid computational framework that combines neuro-inspired information processing using spiking neural networks (SNNs) and quantum information processing using quantum kernels to develop quantum-enhanced machine learning models for spatio-temporal data, demonstrated through the classification of EEG data as a case study. In the proposed SNN-quantum computation (SNN-QC) framework, SNN with spike time information representation is employed to learn spatio-temporal interactions (EEG recorded from multiple channels over time). Frequency-based (rate-based) information as spike frequency state vectors are extracted from the SNN and classified using a quantum classifier. In the latter part, we use the quantum kernel approach utilising feature maps for classification tasks. The proposed SNN-QC is demonstrated on a benchmark EEG dataset to classify three distinct wrist movement tasks in six binary classification setups as a proof of concept. We introduce a novel high-order nonlinear feature map that demonstrates improved performance over state-of-the-art feature maps and several machine learning methods across most of the tasks studied. Furthermore, the role of hyperparameters for enhanced feature maps is also highlighted. The performance of SNN-QC is evaluated using statistical metrics and cross-validation techniques, demonstrating its efficacy across multiple binary classifiers. Quantum hardware validation is conducted using both a superconducting IBM-QPU and a high-fidelity noisy simulation that replicates a real QPU. Furthermore, the results demonstrate that the SNN-QC outperforms models that use statistical features rather than features extracted from the SNN, as the SNN accounts for the temporal interaction between the spatio-temporal input variables. Finally, we conclude that the SNN-QC offers a potential pathway for developing more accurate neuromorphic-quantum enhanced systems that are both energy-efficient and biologically-inspired, well-suited for dealing with spatio-temporal data.","url":"https://doi.org/10.1140/epjqt/s40507-025-00443-1","authors":["Ravi Kumar Jha","Nikola Kasabov","Saugat Bhattacharyya","Damien Coyle","Girijesh Prasad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-11T12:54:48Z","doi":"10.1140/epjqt/s40507-025-00443-1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1002/htj.23294","name":"Sheaf Attention–Based Osprey Spiking Neural Network for Effective Thermal Management and Self‐Heating Mitigation in GaAs and GaN HEMTs","source":"crossref","abstract":"ABSTRACT This research introduces the sheaf attention–based osprey spiking neural network (SA‐OSNN) to optimize the thermal performance of GaAs and GaN high electron mobility transistors (HEMTs), which are critical for radio frequency and microwave circuits due to their excellent electron characteristics. By integrating modified osprey optimization, the SA‐OSNN approach enhances thermal management by dynamically adjusting model parameters in response to changing environmental conditions, ensuring efficient and effective thermal control. This method is used as an optimization tool that works in conjunction with established thermal management solutions, such as GaN, SiC, and AlN materials, which provide the physical properties necessary for effective heat dissipation. This analysis covers a temperature between −100°C and 200°C, examining frequencies up to 50 GHz validating the accuracy and reliability for GaAs and GaN HEMT thermal optimization. Overall, this research achieves a minimum error of 5.97834e−01 and 6.01251e−05. Also, SA‐OSNN achieves an accuracy of 97% with better performances than existing methods.","url":"https://doi.org/10.1002/htj.23294","authors":["Preethi Elizabeth Iype","V. Suresh Babu","Geenu Paul"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-31T06:11:11Z","doi":"10.1002/htj.23294","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1002/oca.70023","name":"An Optimized Spiking Neural Network With Weighted Feature Integration for Epilepsy Seizure Detection Using\n                    <scp>EEG</scp>\n                    Signal","source":"crossref","abstract":"ABSTRACT Epilepsy becomes the most hazardous neurological disorder affecting humans, and it leads to death if it is not treated on time. When designing the diagnostic model of seizure disease, the input source is requisite. Rather than imaging, the signal recordings are helpful in identifying the disorder. Among these, an EEG signal is accounted for as input and taken in the form of raw data used in the detection process. This EEG is a tool that assists in retrieving the data of neural activities of the brain. Prompted to design an automated model with an intelligent approach, resolving the existing issues or challenges facilitates better treatment for such affected patients. Earlier implemented methods involve classifying the disorder; still, it is burdened with manually crafted features that easily trap it into less performance. Moreover, the lack of generalization and categorization tends to mislead the identification process. Comparatively, deep learning is emerging with beneficial points in the medical industry to forecast human disorders. In today's context, the SNN acts as a pivotal role in seizure classification with spiking units. So, to tackle these issues, an automated SNN‐based epilepsy seizure detection model is implemented in this proposal. The goal of this research is to develop an efficient SNN model for epileptic seizure detection using EEGs, a complicated pattern recognition problem. At first, from the benchmark data sources, the EEG signals are garnered for subsequent processes and given to the feature extraction stage. In this stage, the temporal features are extracted from the RNN and the spatial features are extracted from the CNN. Moreover, the Path Signature features and the wave features are also extracted from the given EEG signals. Further, these features are fused with the support of optimal weights. Here, the IBBROA is utilized for optimizing the weights. Due to the functional similarity of biological activity, the Spike Network or STDP is considered during training of the network. So, the weighted fused features are subjected to ASNN‐LIF for detecting the seizure disorder. Here also, the same IBBROA algorithm is supported for optimizing the parameters in ASNN‐LIF. At last, a detailed research study is conducted to verify the effectiveness of the implemented epilepsy seizure detection model by contrasting numerous conventional detection techniques and optimization algorithms.","url":"https://doi.org/10.1002/oca.70023","authors":["Kunduru Venkateswara Reddy","Narayanam Balaji"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-26T03:14:34Z","doi":"10.1002/oca.70023","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/ijcnn60899.2024.10651135","name":"Can Timing-Based Backpropagation Overcome Single-Spike Restrictions in Spiking Neural Networks?","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn60899.2024.10651135","authors":["Kakei Yamamoto","Yusuke Sakemi","Kazuyuki Aihara"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T17:35:05Z","doi":"10.1109/ijcnn60899.2024.10651135","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/biocas67066.2025.00145","name":"An Efficient Fixed-Point Spiking Neural Network Training Architecture with Reconfigurable Processing Elements and Dynamic Clocks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/biocas67066.2025.00145","authors":["Zhenhui Dai","Li Lun","Cheng Zhao","Tingting Zhong","Yi Zhong","Yingying Cui","Yuan Wang","Dunshan Yu","Xiaoxin Cui"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-14T20:38:47Z","doi":"10.1109/biocas67066.2025.00145","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/access.2025.3541408","name":"Multi-Task Spiking Neural Network for Simultaneous Vapor Recognition and Concentration Estimation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/access.2025.3541408","authors":["Pedro Sartori Locatelli","Salma Ait Fares","Dalton Martini Colombo","Kamal El-Sankary","Michael S. Freund"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-13T18:43:51Z","doi":"10.1109/access.2025.3541408","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1561/978-1-68083-653-020251005","name":"Stacks of Software Stacks","source":"crossref","abstract":"","url":"https://doi.org/10.1561/978-1-68083-653-020251005","authors":["Andrew Rowley","Oliver Rhodes","Petrut Bogdan","Christian Brenninkmeijer","Simon Davidson","Donal Fellows","Steve Furber","Andrew Gait","Michael Hopkins","David Lester","Mantas Mikaitis","Luis Plana","Alan Stokes"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-04T15:37:20Z","doi":"10.1561/978-1-68083-653-020251005","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1088/0954-898x_9_4_001","name":"A review of methods for spike sorting: the detection and classification of neural action potentials","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_9_4_001","authors":["Michael S Lewicki"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T16:04:59Z","doi":"10.1088/0954-898x_9_4_001","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1007/s11141-021-10054-2","name":"Synchronization in a Network of Spiking Neural Oscillators with Plastic Connectivity","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11141-021-10054-2","authors":["M. V. Bazhanova","N. P. Krylova","V. B. Kazantsev","A. E. Khramov","S. A. Lobov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-02-18T18:47:00Z","doi":"10.1007/s11141-021-10054-2","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/cict67193.2025.11398975","name":"Eco - SNNRFD: Energy-Conscious Spiking Neural Network with River Formation Dynamics Framework for Flying Ad Hoc Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cict67193.2025.11398975","authors":["B. Narasimhan","D. Hari Prasad","S. Thavamani","B. Ramesh Kumar","S. Sudha","A. Praveena"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-24T20:55:40Z","doi":"10.1109/cict67193.2025.11398975","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/ijcnn52387.2021.9534087","name":"Q-SpiNN: A Framework for Quantizing Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn52387.2021.9534087","authors":["Rachmad Vidya Wicaksana Putra","Muhammad Shafique"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-20T21:27:41Z","doi":"10.1109/ijcnn52387.2021.9534087","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.5573/jsts.2025.25.2.123","name":"Hardware Implementation of Integration-and-Fire Neuron Circuit on FPGA and Performance Evaluation for Applications in Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.5573/jsts.2025.25.2.123","authors":["Yeji Lee","Arati Kumari Shah","Myounggon Kang","Seongjae Cho"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-07T04:24:59Z","doi":"10.5573/jsts.2025.25.2.123","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/iceic51217.2021.9369724","name":"Training and Inference using Approximate Floating-Point Arithmetic for Energy Efficient Spiking Neural Network Processors","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iceic51217.2021.9369724","authors":["Myeongjin Kwak","Jungwon Lee","Hyoju Seo","Mingyu Sung","Yongtae Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-10T22:01:44Z","doi":"10.1109/iceic51217.2021.9369724","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.26855/acc.2025.12.009","name":"A Spiking Neural Network for Visual Causal Inference with the Hidden Markov Model","source":"crossref","abstract":"","url":"https://doi.org/10.26855/acc.2025.12.009","authors":["Ruihuan Ren","Pengcheng Cui","Jinping Yuan","Jiaheng Song","Yiran Li","Yutong Lu","Zixuan Huang","Jianyu Wang","Weisi Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-31T09:45:02Z","doi":"10.26855/acc.2025.12.009","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/miel66332.2025.11261196","name":"Statistical Analysis of Synaptic Weights in Spiking Neural Network Trained on the DVS128 Gesture Dataset","source":"crossref","abstract":"","url":"https://doi.org/10.1109/miel66332.2025.11261196","authors":["Jelena Nikolić","Stefan Tomić","Aleksandra Jovanović","Zoran Perić","Milan Dinčić","Edward Jones","Davide Bertozzi","Riccardo Zese","Marko Andjelković"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-02T18:45:59Z","doi":"10.1109/miel66332.2025.11261196","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/computingcon64838.2025.11377285","name":"Neuromorphic Spiking Neural Network-Based Explainable AI for Energy-Efficient, Quantum-Resistant Dynamic Access Control Systems with Temporal Causal Traceability","source":"crossref","abstract":"","url":"https://doi.org/10.1109/computingcon64838.2025.11377285","authors":["Vishnukumar A","Dinesh B","Harini Pachaiyappan","Govarthan V","Lakshmi Priya V","Suvathika K"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-20T21:13:05Z","doi":"10.1109/computingcon64838.2025.11377285","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1007/978-3-030-58607-2_23","name":"Deep Spiking Neural Network: Energy Efficiency Through Time Based Coding","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-58607-2_23","authors":["Bing Han","Kaushik Roy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-11-06T03:04:11Z","doi":"10.1007/978-3-030-58607-2_23","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/ijcnn.2016.7727313","name":"Simulation of bayesian learning and inference on distributed stochastic spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2016.7727313","authors":["Khadeer Ahmed","Amar Shrestha","Qinru Qiu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-11-08T16:15:56Z","doi":"10.1109/ijcnn.2016.7727313","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/ijcnn60899.2024.10650857","name":"Topological Representations of Heterogeneous Learning Dynamics of Recurrent Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn60899.2024.10650857","authors":["Biswadeep Chakraborty","Saibal Mukhopadhyay"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T17:35:05Z","doi":"10.1109/ijcnn60899.2024.10650857","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1162/089976600300015899","name":"Population Dynamics of Spiking Neurons: Fast Transients, Asynchronous States, and Locking","source":"crossref","abstract":"An integral equation describing the time evolution of the population activity in a homogeneous pool of spiking neurons of the integrate-and-fire type is discussed. It is analytically shown that transients from a state of incoherent firing can be immediate. The stability of incoherent firing is analyzed in terms of the noise level and transmission delay, and a bifurcation diagram is derived. The response of a population of noisy integrate-and-fire neurons to an input current of small amplitude is calculated and characterized by a linear filter L. The stability of perfectly synchronized “locked” solutions is analyzed.","url":"https://doi.org/10.1162/089976600300015899","authors":["Wulfram Gerstner"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-27T11:57:56Z","doi":"10.1162/089976600300015899","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.3390/electronics12020310","name":"Spiking Neural-Networks-Based Data-Driven Control","source":"crossref","abstract":"Machine learning can be effectively applied in control loops to make optimal control decisions robustly. There is increasing interest in using spiking neural networks (SNNs) as the apparatus for machine learning in control engineering because SNNs can potentially offer high energy efficiency, and new SNN-enabling neuromorphic hardware is being rapidly developed. A defining characteristic of control problems is that environmental reactions and delayed rewards must be considered. Although reinforcement learning (RL) provides the fundamental mechanisms to address such problems, implementing these mechanisms in SNN learning has been underexplored. Previously, spike-timing-dependent plasticity learning schemes (STDP) modulated by factors of temporal difference (TD-STDP) or reward (R-STDP) have been proposed for RL with SNN. Here, we designed and implemented an SNN controller to explore and compare these two schemes by considering cart-pole balancing as a representative example. Although the TD-based learning rules are very general, the resulting model exhibits rather slow convergence, producing noisy and imperfect results even after prolonged training. We show that by integrating the understanding of the dynamics of the environment into the reward function of R-STDP, a robust SNN-based controller can be learned much more efficiently than TD-STDP.","url":"https://doi.org/10.3390/electronics12020310","authors":["Yuxiang Liu","Wei Pan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-09T04:42:17Z","doi":"10.3390/electronics12020310","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1101/2020.03.17.995563","name":"Unsupervised learning and clustered connectivity enhance reinforcement learning in spiking neural networks","source":"crossref","abstract":"ABSTRACT Reinforcement learning is a learning paradigm that can account for how organisms learn to adapt their behavior in complex environments with sparse rewards. However, implementations in spiking neuronal networks typically rely on input architectures involving place cells or receptive fields. This is problematic, as such approaches either scale badly as the environment grows in size or complexity, or presuppose knowledge on how the environment should be partitioned. Here, we propose a learning architecture that combines unsupervised learning on the input projections with clustered connectivity within the representation layer. This combination allows input features to be mapped to clusters; thus the network self-organizes to produce task-relevant activity patterns that can serve as the basis for reinforcement learning on the output projections. On the basis of the MNIST and Mountain Car tasks, we show that our proposed model performs better than either a comparable unclustered network or a clustered network with static input projections. We conclude that the combination of unsupervised learning and clustered connectivity provides a generic representational substrate suitable for further computation.","url":"https://doi.org/10.1101/2020.03.17.995563","authors":["Philipp Weidel","Renato Duarte","Abigail Morrison"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-03-19T03:05:16Z","doi":"10.1101/2020.03.17.995563","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1299/jsmermd.2019.1a1-m08","name":"A study on self organization of spiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1299/jsmermd.2019.1a1-m08","authors":["Kenji IWADATE","Ikuo SUZUKI","Michiko WATANABE","Masashi FURUKAWA"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-12-24T22:22:07Z","doi":"10.1299/jsmermd.2019.1a1-m08","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.4015/s1016237225500012","name":"HYBRID DEEP SPIKING NEURAL PRINCIPAL COMPONENT ANALYSIS NETWORK FOR DIABETIC RETINOPATHY DETECTION USING RETINAL FUNDUS IMAGE","source":"crossref","abstract":"Diabetic Retinopathy (DR) is a common retinal vascular disease to injure the retinal blood vessels. DR causes the vision-related disorder without showing any symptoms. As the condition becomes more severe, it can result the partial or complete vision loss. Numerous clinical approaches were developed for treating DR; still, the processing cost and processing period are high. For solving such difficulties, the Deep Spiking Neural Principle Component Analysis Network (DSNPCANet) is proposed for DR detection. The input retinal fundus images are employed for detecting the DR. Pre-processing is the initial process, where the Wiener filter is utilized for eliminating the noise. The optic disc segmentation is used to segment the optic disc, where the active contour model is employed, moreover, the Artery/Vein Classification Network (AVNet) is employed for segmenting the blood vessel using the preprocessed images. Furthermore, the significant features are extracted from the preprocessed, optic disc-segmented, and blood vessel-segmented images. At last, the DSNPCANet is employed for DR detection. Moreover, the accuracy, sensitivity, specificity, precision, and [Formula: see text] 1-score are utilized to validate the DSNPCANet, which yields the finest values of 90.67%, 91.26%, 89.86%, 90.19%, and 90.14%.","url":"https://doi.org/10.4015/s1016237225500012","authors":["Kavita Tallusing Rathod-Jadhav","Aparna Sachin Pande"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-23T23:14:21Z","doi":"10.4015/s1016237225500012","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1049/cim2.70004","name":"Spiking neural network tactile classification method with faster and more accurate membrane potential representation","source":"crossref","abstract":"Abstract Robot perception is an important topic in artificial intelligence field, and tactile recognition in particular is indispensable for human–computer interaction. Efficiently classifying data obtained by touch sensors has long been an issue. In recent years, spiking neural networks (SNNs) have been widely used in tactile data categorisation due to their temporal information processing benefits, low power consumption, and high biological dependability. However, traditional SNN classification methods often encounter under‐convergence when using membrane potential representation, decreasing their classification accuracy. Meanwhile, due to the time‐discrete nature of SNN models, classification requires a significant time overhead, which restricts their real‐time tactile sensing application potential. Considering these concerns, the authors propose a faster and more accurate SNN tactile classification approach using improved membrane potential representation. This method effectively overcomes model convergence problems by optimising the membrane potential expression and the relationship between the loss function and network parameters while significantly reducing the time overhead and enhancing the classification accuracy and robustness of the model. The experimental results show that the propose approach improves the classification accuracy by 4.16% and 2.71% and reduces the overall time by 8.00% and 8.14% on the EvTouch‐Containers dataset and EvTouch‐Objects dataset, respectively, when compared with existing models.","url":"https://doi.org/10.1049/cim2.70004","authors":["Jing Yang","Zukun Yu","Xiaoyang Ji","Zhidong Su","Shaobo Li","Yang Cao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-22T06:07:36Z","doi":"10.1049/cim2.70004","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1016/j.neunet.2025.107962","name":"A spiking network model of the cerebellum for predicting movements with diverse complex spikes","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107962","authors":["Tomohiro Mitsuhashi","Yusuke Kuniyoshi","Koji Ikezoe","Kazuo Kitamura","Tadashi Yamazaki"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-13T06:45:30Z","doi":"10.1016/j.neunet.2025.107962","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.3390/a17040156","name":"Spike-Weighted Spiking Neural Network with Spiking Long Short-Term Memory: A Biomimetic Approach to Decoding Brain Signals","source":"crossref","abstract":"Background. Brain–machine interfaces (BMIs) offer users the ability to directly communicate with digital devices through neural signals decoded with machine learning (ML)-based algorithms. Spiking Neural Networks (SNNs) are a type of Artificial Neural Network (ANN) that operate on neural spikes instead of continuous scalar outputs. Compared to traditional ANNs, SNNs perform fewer computations, use less memory, and mimic biological neurons better. However, SNNs only retain information for short durations, limiting their ability to capture long-term dependencies in time-variant data. Here, we propose a novel spike-weighted SNN with spiking long short-term memory (swSNN-SLSTM) for a regression problem. Spike-weighting captures neuronal firing rate instead of membrane potential, and the SLSTM layer captures long-term dependencies. Methods. We compared the performance of various ML algorithms during decoding directional movements, using a dataset of microelectrode recordings from a macaque during a directional joystick task, and also an open-source dataset. We thus quantified how swSNN-SLSTM performed compared to existing ML models: an unscented Kalman filter, LSTM-based ANN, and membrane-based SNN techniques. Result. The proposed swSNN-SLSTM outperforms both the unscented Kalman filter, the LSTM-based ANN, and the membrane based SNN technique. This shows that incorporating SLSTM can better capture long-term dependencies within neural data. Also, our proposed swSNN-SLSTM algorithm shows promise in reducing power consumption and lowering heat dissipation in implanted BMIs.","url":"https://doi.org/10.3390/a17040156","authors":["Kyle McMillan","Rosa Qiyue So","Camilo Libedinsky","Kai Keng Ang","Brian Premchand"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-12T09:28:06Z","doi":"10.3390/a17040156","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1049/icp.2026.0572","name":"A fully pipelined FPGA-based accelerator of spiking neural network for SAR image recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1049/icp.2026.0572","authors":["Bin Lan","Ming Xu","Xi Zhang","Hao Shi","Jiahao Li","Heng Dong","Yuxin Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-09T13:42:16Z","doi":"10.1049/icp.2026.0572","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1016/j.neucom.2020.07.111","name":"Encoding specificity of scale-free spiking neural network under different external stimulations","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2020.07.111","authors":["Lei Guo","LiTing Hou","YouXi Wu","Huan Lv","HongLi Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-31T11:26:33Z","doi":"10.1016/j.neucom.2020.07.111","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.2528/pierl11050605","name":"EVOLVING SPIKING NEURAL NETWORK TOPOLOGIES FOR BREAST CANCER CLASSIFICATION IN A DIELECTRICALLY HETEROGENEOUS BREAST","source":"crossref","abstract":"","url":"https://doi.org/10.2528/pierl11050605","authors":["Martin O'Halloran","Seamus Cawley","Brian McGinley","Raquel Cruz Conceicao","Fearghal Morgan","Edward Jones","Martin Glavin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-01-13T00:02:39Z","doi":"10.2528/pierl11050605","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.7498/aps.63.080503","name":"Application of memristor-based spiking neural network in image edge extraction","source":"crossref","abstract":"By simulating biological synapses with memristors according to the function and principle of biological visual system and by combining the memory characteristic of memristor with high-efficient processing ability in spiking neural network, a three-layer spiking neural network model for image edge extraction is constructed, in which the image edge information is represented by the variation of the memristor conductance. The edge extraction result obtained with this approach has the characteristics of continuity, smoothness, low false leak detection and edge positioning accuracy. Since the processing mechanism of this neural network conforms to the biological counterpart, it offers a new idea for the bionic implementation of biological visual system.","url":"https://doi.org/10.7498/aps.63.080503","authors":["Liu Yu-Dong","Wang Lian-Ming"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-13T00:42:30Z","doi":"10.7498/aps.63.080503","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1007/978-1-4615-3254-5_20","name":"Designing Networks of Spiking Silicon Neurons and Synapses","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4615-3254-5_20","authors":["Lloyd Watts"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-11-19T14:48:16Z","doi":"10.1007/978-1-4615-3254-5_20","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1101/2025.06.30.662308","name":"LatenZy, non-parametric, binning-free estimation of latencies from neural spiking data","source":"crossref","abstract":"Precisely estimating the onset of neural spiking responses and the timing at which activity begins to diverge between conditions is crucial for understanding temporal dynamics in brain information processing. Conventional methods require arbitrary parameter choices such as bin widths and response thresholds, limiting reproducibility and comparability. Here, we present latenZy and latenZy2, two non-parametric, binning-free methods that directly analyze spike times using cumulative statistics and iterative refinement, without assumptions about response shape. LatenZy estimates neuronal response onset latency, while latenZy2 detects when spiking activity diverges between conditions. We validate these methods on electrophysiological datasets from mouse and macaque visual cortex, and show that they outperform standard approaches in precision, robustness, sensitivity, and statistical power. LatenZy captures contrast-dependent latency shifts and hierarchical timing across visual areas, and latenZy2 reveals earlier attentional modulation in higher visual cortex consistent with top-down feedback. Together, they offer scalable, parameter-free tools for reliable latency estimation in large-scale neural recordings. Open-source implementations are available in Python and MATLAB.","url":"https://doi.org/10.1101/2025.06.30.662308","authors":["Robin Haak","J. Alexander Heimel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-04T17:41:00Z","doi":"10.1101/2025.06.30.662308","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1016/j.infrared.2024.105251","name":"Hyper-S3NN: Spatial–spectral spiking neural network for hyperspectral image classification","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.infrared.2024.105251","authors":["Jiangyun Li","Haoran Shen","Wenxuan Wang","Peixian Zhuang","Xi Liu","Tianxiang Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-28T11:13:37Z","doi":"10.1016/j.infrared.2024.105251","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/cleo/europe-eqec65582.2025.11111622","name":"Achieving More with Less: Training a Spiking Neural Network of 40.000 Neurons with Rank Order Coding, Leveraging Sparsity","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cleo/europe-eqec65582.2025.11111622","authors":["Ria Talukder","Anas Skalli","Daniel Brunner"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-15T18:11:27Z","doi":"10.1109/cleo/europe-eqec65582.2025.11111622","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1007/978-981-10-7566-7_16","name":"Applications of Spiking Neural Network to Predict Software Reliability","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-10-7566-7_16","authors":["Ramakanta Mohanty","Aishwarya Priyadarshini","Vishnu Sai Desai","G. Sirisha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-04-09T23:47:23Z","doi":"10.1007/978-981-10-7566-7_16","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/icsict55466.2022.9963415","name":"Residual Spiking Neural Network on a Programmable Neuromorphic Hardware for Speech Keyword Spotting","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icsict55466.2022.9963415","authors":["Chenglong Zou","Xiaoxin Cui","Shuo Feng","Guang Chen","Xinan Wang","Yuan Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T20:52:39Z","doi":"10.1109/icsict55466.2022.9963415","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1088/2634-4386/ac889b","name":"General spiking neural network framework for the learning trajectory from a noisy mmWave radar","source":"crossref","abstract":"Abstract Emerging usages for millimeter wave (mmWave) radar have drawn extensive attention and inspired the exploration of learning mmWave radar data. To be effective, instead of using conventional approaches, recent works have employed modern neural network models to process mmWave radar data. However, due to some inevitable obstacles, e.g., noise and sparsity issues in data, the existing approaches are generally customized for specific scenarios. In this paper, we propose a general neuromorphic framework, termed mm-SNN, to process mmWave radar data with spiking neural networks (SNNs), leveraging the intrinsic advantages of SNNs in processing noisy and sparse data. Specifically, we first present the overall design of mm-SNN, which is adaptive and easily expanded for multi-sensor systems. Second, we introduce general and straightforward attention-based improvements into the mm-SNN to enhance the data representation, helping promote performance. Moreover, we conduct explorative experiments to certify the robustness and effectiveness of the mm-SNN. To the best of our knowledge, mm-SNN is the first SNN-based framework that processes mmWave radar data without using extra modules to alleviate the noise and sparsity issues, and at the same time, achieve considerable performance in the task of trajectory estimation.","url":"https://doi.org/10.1088/2634-4386/ac889b","authors":["Xin Liu","Mingyu Yan","Lei Deng","Yujie Wu","De Han","Guoqi Li","Xiaochun Ye","Dongrui Fan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-08-10T22:17:35Z","doi":"10.1088/2634-4386/ac889b","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/vlsic.2018.8502423","name":"A 4096-Neuron 1M-Synapse 3.8PJ/SOP Spiking Neural Network with On-Chip STDP Learning and Sparse Weights in 10NM FinFET CMOS","source":"crossref","abstract":"","url":"https://doi.org/10.1109/vlsic.2018.8502423","authors":["Gregory K. Chen","Raghavan Kumar","H. Ekin Sumbul","Phil C. Knag","Ram K. Krishnamurthy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-11-16T03:04:38Z","doi":"10.1109/vlsic.2018.8502423","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1007/s00500-024-10103-8","name":"Retraction Note: A novel multi-layer multi-spiking neural network for EEG signal classification using Mini Batch SGD","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00500-024-10103-8","authors":["M. Ramesh","Swetha Revoori","Damodar Reddy Edla","K. V. D. Kiran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-22T12:45:45Z","doi":"10.1007/s00500-024-10103-8","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/tasc.2024.3367618","name":"Unsupervised SFQ-Based Spiking Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tasc.2024.3367618","authors":["Mustafa Altay Karamuftuoglu","Beyza Zeynep Ucpinar","Sasan Razmkhah","Mehdi Kamal","Massoud Pedram"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-20T19:03:35Z","doi":"10.1109/tasc.2024.3367618","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.5573/jsts.2022.22.2.115","name":"Review of Analog Neuron Devices for Hardware-based Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.5573/jsts.2022.22.2.115","authors":["Dongseok Kwon","Sung-Yun Woo","Jong-Ho Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-05-01T20:38:58Z","doi":"10.5573/jsts.2022.22.2.115","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.21203/rs.3.rs-3402926/v1","name":"Classified Vpn Network Traffic Flow Using Time Related to Artificial Neural Network","source":"crossref","abstract":"Abstract In the rapidly evolving landscape of cybersecurity threats, Virtual Private Networks (VPNs) have become an essential tool for securing communication channels. However, the rising complexity and diversity of network attacks call for more sophisticated methods to identify and classify different types of VPN network traffic effectively. In this study, we propose a novel approach using Artificial Neural Networks (ANN) to classify VPN network traffic flows. The primary goal of this research is to develop a robust and efficient system capable of distinguishing between legitimate VPN traffic and potential malicious activities, such as intrusion attempts, data exfiltration, and denial-of-service attacks. We begin by collecting a diverse dataset of labeled VPN traffic flows encompassing various applications and usage patterns. Next, we design an ANN architecture tailored to handle the intricacies of encrypted traffic and effectively capture the subtle differences between benign and malicious activities. The neural network model incorporates several layers, including input, hidden, and output layers, to process and classify the encrypted packets accurately. To enhance the ANN's classification accuracy, we apply advanced feature extraction techniques, enabling the model to leverage both statistical and behavioral characteristics of the network traffic. Moreover, we implement state-of-the-art optimization algorithms to fine-tune the network parameters and improve its performance. We evaluate the proposed ANN-based classification system through extensive experimentation and performance analysis. The results demonstrate the model's effectiveness in accurately identifying and categorizing different VPN traffic types. Furthermore, we compare our ANN-based approach with existing methods, showcasing its superiority in terms of precision, recall, and F1-score with an accuracy of 98.79%. The contributions of this research are significant for enhancing the security of VPN networks and protecting against emerging cyber threats. By efficiently classifying VPN traffic flows, organizations can better safeguard their sensitive data, preserve network integrity, and respond promptly to potential security incidents. The findings of this study provide a valuable step forward in the realm of network security and lay the foundation for future advancements in ANN-based cybersecurity solutions.","url":"https://doi.org/10.21203/rs.3.rs-3402926/v1","authors":["Saad Abdalla Agaili MOHAMED","Sefer KURNAZ"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-24T15:43:58Z","doi":"10.21203/rs.3.rs-3402926/v1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1016/j.neunet.2013.02.005","name":"Event management for large scale event-driven digital hardware spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2013.02.005","authors":["Louis-Charles Caron","Michiel D’Haene","Frédéric Mailhot","Benjamin Schrauwen","Jean Rouat"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-03-06T17:16:16Z","doi":"10.1016/j.neunet.2013.02.005","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/ijcnn.2004.1379957","name":"Dual threshold based neural modeling to study systems of spiking neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2004.1379957","authors":["J.J. Lovelace","K.J. Cios"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-02-28T16:14:54Z","doi":"10.1109/ijcnn.2004.1379957","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1162/089976601750264974","name":"Stationary Bumps in Networks of Spiking Neurons","source":"crossref","abstract":"We examine the existence and stability of spatially localized “bumps” of neuronal activity in a network of spiking neurons. Bumps have been proposed in mechanisms of visual orientation tuning, the rat head direction system, and working memory. We show that a bump solution can exist in a spiking network provided the neurons fire asynchronously within the bump. We consider a parameter regime where the bump solution is bistable with an all-off state and can be initiated with a transient excitatory stimulus. We show that the activity profile matches that of a corresponding population rate model. The bump in a spiking network can lose stability through partial synchronization to either a traveling wave or the all-off state. This can occur if the synaptic timescale is too fast through a dynamical effect or if a transient excitatory pulse is applied to the network. A bump can thus be activated and deactivated with excitatory inputs that may have physiological relevance.","url":"https://doi.org/10.1162/089976601750264974","authors":["Carlo R. Laing","Carson C. Chow"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-27T11:55:01Z","doi":"10.1162/089976601750264974","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1016/j.eswa.2024.123606","name":"Energy-efficient craters detection based on spiking neural network using digital elevation models","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.eswa.2024.123606","authors":["Keke Zha","Jiabin Yuan","Lili Fan","Xu Liu","Xuewei Niu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-11T04:58:18Z","doi":"10.1016/j.eswa.2024.123606","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1016/j.neucom.2024.128707","name":"A novel label-aware global graph construction method and spiking-coded graph neural network for intelligent process fault diagnosis","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2024.128707","authors":["Dazi Li","Yurui Zhu","Zhihuan Song","Hamid Reza Karimi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-04T22:48:10Z","doi":"10.1016/j.neucom.2024.128707","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/ijcnn.2013.6706952","name":"Neural spiking dynamics in asynchronous digital circuits","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2013.6706952","authors":["Nabil Imam","Kyle Wecker","Jonathan Tse","Robert Karmazin","Rajit Manohar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-01-10T15:08:44Z","doi":"10.1109/ijcnn.2013.6706952","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.52202/085713-0382","name":"Spike-RetinexFormer: Rethinking Low-light Image Enhancement with Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.52202/085713-0382","authors":["Hongzhi Wang","Xiubo Liang","Jinxing Han","Weidong Geng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-06T14:44:29Z","doi":"10.52202/085713-0382","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.3389/fnins.2017.00454","name":"A Spiking Neural Network Model of the Lateral Geniculate Nucleus on the SpiNNaker Machine","source":"crossref","abstract":"","url":"https://doi.org/10.3389/fnins.2017.00454","authors":["Basabdatta Sen-Bhattacharya","Teresa Serrano-Gotarredona","Lorinc Balassa","Akash Bhattacharya","Alan B. Stokes","Andrew Rowley","Indar Sugiarto","Steve Furber"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-08-09T04:03:43Z","doi":"10.3389/fnins.2017.00454","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/lo.2018.8435458","name":"Quantum-Dot Laser Assisted Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/lo.2018.8435458","authors":["Dimitris Syvridis","Charis Mesaritakis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-08-17T20:17:05Z","doi":"10.1109/lo.2018.8435458","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/nmdc50713.2021.9677533","name":"A Proposal of Energy Efficient Ferroelectric PDSOI LIF Neuron for Spiking Neural Network Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nmdc50713.2021.9677533","authors":["P Sowparna","V Rajakumari","K P Pradhan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-01-21T21:59:05Z","doi":"10.1109/nmdc50713.2021.9677533","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1186/s40708-023-00192-w","name":"Prediction and detection of virtual reality induced cybersickness: a spiking neural network approach using spatiotemporal EEG brain data and heart rate variability","source":"crossref","abstract":"Abstract Virtual Reality (VR) allows users to interact with 3D immersive environments and has the potential to be a key technology across many domain applications, including access to a future metaverse. Yet, consumer adoption of VR technology is limited by cybersickness (CS)—a debilitating sensation accompanied by a cluster of symptoms, including nausea, oculomotor issues and dizziness. A leading problem is the lack of automated objective tools to predict or detect CS in individuals, which can then be used for resistance training, timely warning systems or clinical intervention. This paper explores the spatiotemporal brain dynamics and heart rate variability involved in cybersickness and uses this information to both predict and detect CS episodes. The present study applies deep learning of EEG in a spiking neural network (SNN) architecture to predict CS prior to using VR (85.9%, F7) and detect it (76.6%, FP1, Cz). ECG-derived sympathetic heart rate variability (HRV) parameters can be used for both prediction (74.2%) and detection (72.6%) but at a lower accuracy than EEG. Multimodal data fusion of EEG and sympathetic HRV does not change this accuracy compared to ECG alone. The study found that Cz (premotor and supplementary motor cortex) and O2 (primary visual cortex) are key hubs in functionally connected networks associated with both CS events and susceptibility to CS. F7 is also suggested as a key area involved in integrating information and implementing responses to incongruent environments that induce cybersickness. Consequently, Cz, O2 and F7 are presented here as promising targets for intervention.","url":"https://doi.org/10.1186/s40708-023-00192-w","authors":["Alexander Hui Xiang Yang","Nikola Kirilov Kasabov","Yusuf Ozgur Cakmak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-12T13:02:04Z","doi":"10.1186/s40708-023-00192-w","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1007/978-981-96-9946-9_43","name":"Frontiers of Spiking Neural Network Encoding Techniques: A Comprehensive Review","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-96-9946-9_43","authors":["Yuze Li","Xingyue Zhang","Hao Cheng","Shaoting Guo","Lei Li","Yongbin Yu","Nyima Tashi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-14T13:55:42Z","doi":"10.1007/978-981-96-9946-9_43","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1101/2023.05.27.542589","name":"Slow ramping emerges from spontaneous fluctuations in spiking neural networks","source":"crossref","abstract":"Abstract Highlights 1. We reveal a mechanism for slow-ramping signals before spontaneous voluntary movements. 2. Slow synapses stabilize spontaneous fluctuations in spiking neural network. 3. We validate model predictions in human frontal cortical single-neuron recordings. 4. The model recreates the readiness potential in an EEG proxy signal. 5. Neurons that ramp together had correlated activity before ramping onset. The capacity to initiate actions endogenously is critical for goal-directed behavior. Spontaneous voluntary actions are typically preceded by slow-ramping activity in medial frontal cortex that begins around two seconds before movement, which may reflect spontaneous fluctuations that influence action timing. However, the mechanisms by which these slow ramping signals emerge from single-neuron and network dynamics remain poorly understood. Here, we developed a spiking neural-network model that produces spontaneous slow ramping activity in single neurons and population activity with onsets ∼2 seconds before threshold crossings. A key prediction of our model is that neurons that ramp together have correlated firing patterns before ramping onset. We confirmed this model-derived hypothesis in a dataset of human single neuron recordings from medial frontal cortex. Our results suggest that slow ramping signals reflect bounded spontaneous fluctuations that emerge from quasi-winner-take-all dynamics in clustered networks that are temporally stabilized by slow-acting synapses.","url":"https://doi.org/10.1101/2023.05.27.542589","authors":["Jake Gavenas","Ueli Rutishauser","Aaron Schurger","Uri Maoz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-30T13:00:21Z","doi":"10.1101/2023.05.27.542589","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1002/9781394381609.ch08","name":"Medical Signal Processing","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9781394381609.ch08","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-28T07:11:02Z","doi":"10.1002/9781394381609.ch08","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.21203/rs.3.rs-3263186/v2","name":"Uncertainty-Aware Graph Neural Network for Semi-Supervised Diversified Recommendation","source":"crossref","abstract":"Abstract Graphs are a powerful tool for representing structured and relational data in various domains, including social networks, knowledge graphs, and molecular structures. Semi-supervised learning on graphs has emerged as a promising approach to address real-world challenges and applications. In this paper, we propose an uncertainty-aware pseudo-label selection framework for promoting diversity learning in recommendation systems. Our approach harnesses the power of semi-supervised Graph Neural Networks (GNNs), utilizing both labeled and unlabeled data, to address data sparsity issues often encountered in real-world recommendation scenarios. Pseudo-labeling, a prevalent semi-supervised method, combats label scarcity by enhancing the training set with high-confidence pseudolabels for unlabeled nodes, enabling self-training cycles for supervised models. By incorporating pseudo-labels selected based on the model’s uncertainty, our framework is designed to improve the model’s generalization and foster diverse recommendations. The main contributions of this paper include introducing the uncertainty-aware pseudo-label selection framework, providing a comprehensive description of the framework, and presenting an experimental evaluation comparing its performance against baseline methods in terms of recommendation quality and diversity. Our proposed method demonstrates the effectiveness of uncertainty-aware pseudo-label selection in enhancing the diversity of recommendation systems and delivering a more engaging, personalized, and diverse set of suggestions for users.","url":"https://doi.org/10.21203/rs.3.rs-3263186/v2","authors":["Minjie"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-09T12:29:39Z","doi":"10.21203/rs.3.rs-3263186/v2","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1007/978-1-4614-7320-6_792-2","name":"Spiking Network Models and Theory: Overview","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4614-7320-6_792-2","authors":["Marc-Oliver Gewaltig"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-08-23T11:20:22Z","doi":"10.1007/978-1-4614-7320-6_792-2","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1007/978-981-16-7088-6_72","name":"VLSI Implementation of the Low Power Neuromorphic Spiking Neural Network with Machine Learning Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-16-7088-6_72","authors":["K. Venkateswara Reddy","N. Balaji"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-15T09:04:45Z","doi":"10.1007/978-981-16-7088-6_72","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.18517/ijaseit.8.6.5011","name":"Classification of Spatio-Temporal fMRI Data in the Spiking Neural Network","source":"crossref","abstract":"Deep learning machine that employs Spiking Neural Network (SNN) is currently one of the main techniques in computational intelligence to discover knowledge from various fields. It has been applied in many application areas include health, engineering, finances, environment, and others. This paper addresses a classification problem based on a functional Magnetic Resonance Image (fMRI) brain data experiment involving a subject who reads a sentence or looks at a picture. In the experiment, Signal to Noise Ratio (SNR) is used to select the most relevant features (voxels) before they were propagated in an SNN-based learning architecture. The spatiotemporal relationships between Spatio Temporal Brain Data (STBD) are learned and classified accordingly. All the brain regions are taken from data with label star plus-04847-v7.mat. The overall results of this experiment show that the SNR method helps to get the most relevant features from the data to produced higher accuracy for Reading a Sentence instead of Looking a Picture.","url":"https://doi.org/10.18517/ijaseit.8.6.5011","authors":["Shaznoor Shakira Saharuddin","Norhanifah Murli","Muhammad Azani Hasibuan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-03-03T04:56:41Z","doi":"10.18517/ijaseit.8.6.5011","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1007/s12530-017-9178-8","name":"Evolving, dynamic clustering of spatio/spectro-temporal data in 3D spiking neural network models and a case study on EEG data","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s12530-017-9178-8","authors":["Maryam Gholami Doborjeh","Nikola Kasabov","Zohreh Gholami Doborjeh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-04-17T04:00:40Z","doi":"10.1007/s12530-017-9178-8","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1162/neco_a_00387","name":"A Spiking Neural Model for Stable Reinforcement of Synapses Based on Multiple Distal Rewards","source":"crossref","abstract":"In this letter, a novel critic-like algorithm was developed to extend the synaptic plasticity rule described in Florian ( 2007 ) and Izhikevich ( 2007 ) in order to solve the problem of learning multiple distal rewards simultaneously. The system is augmented with short-term plasticity (STP) to stabilize the learning dynamics, thereby increasing the system's learning capacity. A theoretical threshold is estimated for the number of distal rewards that this system can learn. The validity of the novel algorithm was verified by computer simulations.","url":"https://doi.org/10.1162/neco_a_00387","authors":["Michael J. O'Brien","Narayan Srinivasa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-09-28T18:37:36Z","doi":"10.1162/neco_a_00387","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1162/neco.2010.08-09-1084","name":"A Spiking Neuron as Information Bottleneck","source":"crossref","abstract":"Neurons receive thousands of presynaptic input spike trains while emitting a single output spike train. This drastic dimensionality reduction suggests considering a neuron as a bottleneck for information transmission. Extending recent results, we propose a simple learning rule for the weights of spiking neurons derived from the information bottleneck (IB) framework that minimizes the loss of relevant information transmitted in the output spike train. In the IB framework, relevance of information is defined with respect to contextual information, the latter entering the proposed learning rule as a “third” factor besides pre- and postsynaptic activities. This renders the theoretically motivated learning rule a plausible model for experimentally observed synaptic plasticity phenomena involving three factors. Furthermore, we show that the proposed IB learning rule allows spiking neurons to learn a predictive code, that is, to extract those parts of their input that are predictive for future input.","url":"https://doi.org/10.1162/neco.2010.08-09-1084","authors":["Lars Buesing","Wolfgang Maass"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-03-25T22:19:36Z","doi":"10.1162/neco.2010.08-09-1084","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/ijcnn.2010.5596822","name":"Neural behaviors and nonlinear dynamics of a rotate-and-fire digital spiking neuron","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2010.5596822","authors":["Tetsuya Hishiki","Hiroyuki Torikai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-10-19T18:58:15Z","doi":"10.1109/ijcnn.2010.5596822","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1007/978-1-4471-0877-1_33","name":"From Spiking Neurons to Dynamic Perceptrons","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4471-0877-1_33","authors":["Francesco Palmieri","Antonella Luongo","Andrew Moiseff"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-08-24T10:09:05Z","doi":"10.1007/978-1-4471-0877-1_33","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.5256/f1000research.162799.r282583","name":"Peer Review Report For: Graph neural network-based anomaly detection for river network systems [version 2; peer review: 1 approved, 2 approved with reservations]","source":"crossref","abstract":"","url":"https://doi.org/10.5256/f1000research.162799.r282583","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-25T17:07:07Z","doi":"10.5256/f1000research.162799.r282583","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1162/neco_a_01238","name":"Reinforcement Learning in Spiking Neural Networks with Stochastic and Deterministic Synapses","source":"crossref","abstract":"Though succeeding in solving various learning tasks, most existing reinforcement learning (RL) models have failed to take into account the complexity of synaptic plasticity in the neural system. Models implementing reinforcement learning with spiking neurons involve only a single plasticity mechanism. Here, we propose a neural realistic reinforcement learning model that coordinates the plasticities of two types of synapses: stochastic and deterministic. The plasticity of the stochastic synapse is achieved by the hedonistic rule through modulating the release probability of synaptic neurotransmitter, while the plasticity of the deterministic synapse is achieved by a variant of a reward-modulated spike-timing-dependent plasticity rule through modulating the synaptic strengths. We evaluate the proposed learning model on two benchmark tasks: learning a logic gate function and the 19-state random walk problem. Experimental results show that the coordination of diverse synaptic plasticities can make the RL model learn in a rapid and stable form.","url":"https://doi.org/10.1162/neco_a_01238","authors":["Mengwen Yuan","Xi Wu","Rui Yan","Huajin Tang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-10-15T21:52:21Z","doi":"10.1162/neco_a_01238","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1103/physrevapplied.6.064003","name":"Hybrid Spintronic-CMOS Spiking Neural Network with On-Chip Learning: Devices, Circuits, and Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1103/physrevapplied.6.064003","authors":["Abhronil Sengupta","Aparajita Banerjee","Kaushik Roy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-12-08T17:08:29Z","doi":"10.1103/physrevapplied.6.064003","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1007/s41870-025-02579-w","name":"Automated cervical cancer classification using stacked BI-LSTM and optimized spiking neural network with deer hunting optimization algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s41870-025-02579-w","authors":["Harika Vanam","G. Vijaylaxmi","Vanam Sravan Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-24T06:14:43Z","doi":"10.1007/s41870-025-02579-w","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1016/j.bspc.2022.103749","name":"Building and training a deep spiking neural network for ECG classification","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.bspc.2022.103749","authors":["Yifei Feng","Shijia Geng","Jianjun Chu","Zhaoji Fu","Shenda Hong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-05-02T17:20:31Z","doi":"10.1016/j.bspc.2022.103749","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/access.2021.3126311","name":"Spiking Neural Network Discovers Energy-Efficient Hexapod Motion in Deep Reinforcement Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/access.2021.3126311","authors":["Katsumi Naya","Kyo Kutsuzawa","Dai Owaki","Mitsuhiro Hayashibe"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-08T22:35:42Z","doi":"10.1109/access.2021.3126311","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1016/s0893-6080(00)00101-5","name":"Temporal clustering with spiking neurons and dynamic synapses: towards technological applications","source":"crossref","abstract":"","url":"https://doi.org/10.1016/s0893-6080(00)00101-5","authors":["Jan Storck","Frank Jäkel","Gustavo Deco"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-10-14T18:58:33Z","doi":"10.1016/s0893-6080(00)00101-5","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1162/neco.2006.18.10.2359","name":"Estimating Spiking Irregularities Under Changing Environments","source":"crossref","abstract":"We considered a gammadistribution of interspike intervals as a statistical model for neuronal spike generation. A gamma distribution is a natural extension of the Poisson process taking the effect of a refractory period into account. The model is specified by two parameters: a time-dependent firing rate and a shape parameter that characterizes spiking irregularities of individual neurons. Because the environment changes over time, observed data are generated from a model with a time-dependent firing rate, which is an unknown function. A statistical model with an unknown function is called a semiparametric model and is generally very difficult to solve. We used a novel method of estimating functions in information geometry to estimate the shape parameter without estimating the unknown function. We obtained an optimal estimating function analytically for the shape parameter independent of the functional form of the firing rate. This estimation is efficient without Fisher information loss and better than maximum likelihood estimation. We suggest a measure of spiking irregularity based on the estimating function, which may be useful for characterizing individual neurons in changing environments.","url":"https://doi.org/10.1162/neco.2006.18.10.2359","authors":["Keiji Miura","Masato Okada","Shun-ichi Amari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-08-14T16:06:19Z","doi":"10.1162/neco.2006.18.10.2359","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1007/978-3-319-57081-5_5","name":"A New Approach to the Identification of Sensory Processing Circuits Based on Spiking Neuron Data","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-57081-5_5","authors":["Dorian Florescu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-04-21T13:35:41Z","doi":"10.1007/978-3-319-57081-5_5","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1016/j.rcim.2022.102383","name":"A fusion-based spiking neural network approach for predicting collaboration request in human-robot collaboration","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.rcim.2022.102383","authors":["Rong Zhang","Jie Li","Pai Zheng","Yuqian Lu","Jinsong Bao","Xuemin Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-05-27T18:58:17Z","doi":"10.1016/j.rcim.2022.102383","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.3390/s21082678","name":"Spatial Memory in a Spiking Neural Network with Robot Embodiment","source":"crossref","abstract":"Cognitive maps and spatial memory are fundamental paradigms of brain functioning. Here, we present a spiking neural network (SNN) capable of generating an internal representation of the external environment and implementing spatial memory. The SNN initially has a non-specific architecture, which is then shaped by Hebbian-type synaptic plasticity. The network receives stimuli at specific loci, while the memory retrieval operates as a functional SNN response in the form of population bursts. The SNN function is explored through its embodiment in a robot moving in an arena with safe and dangerous zones. We propose a measure of the global network memory using the synaptic vector field approach to validate results and calculate information characteristics, including learning curves. We show that after training, the SNN can effectively control the robot’s cognitive behavior, allowing it to avoid dangerous regions in the arena. However, the learning is not perfect. The robot eventually visits dangerous areas. Such behavior, also observed in animals, enables relearning in time-evolving environments. If a dangerous zone moves into another place, the SNN remaps positive and negative areas, allowing escaping the catastrophic interference phenomenon known for some AI architectures. Thus, the robot adapts to changing world.","url":"https://doi.org/10.3390/s21082678","authors":["Sergey A. Lobov","Alexey I. Zharinov","Valeri A. Makarov","Victor B. Kazantsev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-04-12T05:52:00Z","doi":"10.3390/s21082678","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1002/aisy.202500806","name":"Review of Memristors for In‐Memory Computing and Spiking Neural Networks","source":"crossref","abstract":"The convergence of in‐memory computing (IMC) and neuromorphic architectures offers a promising path toward energy‐efficient, scalable artificial intelligence, particularly for edge and real‐time applications. Memristors, resistive devices with nonvolatile, analog switching, uniquely enable this convergence by serving both as computational memory units for matrix‐vector multiplication and as synaptic elements for spike‐based learning. This review comprehensively explores the physical mechanisms, material classes, and integration strategies of memristors tailored for IMC and spiking neural networks, with emphasis on their implementation in crossbar arrays, synapse‐neuron emulation, and hybrid CMOS circuits. It discusses how memristors facilitate key biological learning rules like STDP and LTP/LTD and examine their deployment in edge artificial intelligence, adaptive robotics, and neuromorphic sensors. Despite their potential, device variability, noise, relaxation, scalability limits, and standardization remain pressing challenges. By synthesizing device‐level insights with architectural innovation and emerging applications, this work outlines a roadmap toward fully integrated, low‐power, and brain‐inspired computing systems.","url":"https://doi.org/10.1002/aisy.202500806","authors":["Mostafa Shooshtari","Teresa Serrano‐Gotarredona","Bernabé Linares‐Barranco"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-03T06:50:12Z","doi":"10.1002/aisy.202500806","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1002/gj.70260/v1/review1","name":"Review for \"Mapping China’s Environmental Sustainability Drivers with Wavelet-Based Artificial Neural Network\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/gj.70260/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-13T21:09:03Z","doi":"10.1002/gj.70260/v1/review1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.21203/rs.3.rs-2648993/v1","name":"Intrusion Detection for IoT Network Security with Deep Neural Network","source":"crossref","abstract":"Abstract one of the most important challenges of the Internet of Things is security. Today, the Internet of Things has found an important place in information technology and human daily life. One of the main challenges of the Internet of Things is security. One of the common methods to intervene in Internet of Things services is Denial of Service (DoS) attacks and Distributed Denial of Service (DDoS) attacks. Therefore, intrusion detection systems or IDSs are currently the main and most complete parts of a network monitoring system. This paper uses the CICIDS 2017 data set to present an intrusion detection model in software-driven Internet of Things networks based on deep neural networks to detect distributed denial of service attacks and several other cyber attacks. In addition, we explored effective deep learning models to represent cyber security knowledge in Internet of Things networks, including CNN, DenseNet, CNN and LSTM hybrid models, and our proposed model.","url":"https://doi.org/10.21203/rs.3.rs-2648993/v1","authors":["Roya Morshedi","S Mojtaba Matinkhah","Mohammad Taghi Sadeghi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-08T23:59:44Z","doi":"10.21203/rs.3.rs-2648993/v1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1039/d5dd00012b/v1/review1","name":"Review for \"ACES-GNN: Can Graph Neural Network Learn to Explain Activity Cliffs?\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5dd00012b/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-01T17:08:16Z","doi":"10.1039/d5dd00012b/v1/review1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1039/d5dd00012b/v1/review3","name":"Review for \"ACES-GNN: Can Graph Neural Network Learn to Explain Activity Cliffs?\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5dd00012b/v1/review3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-01T17:08:16Z","doi":"10.1039/d5dd00012b/v1/review3","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1002/cjce.24281/v1/review3","name":"Review for \"Improved bilayer convolution transfer learning neural network for industrial fault detection\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/cjce.24281/v1/review3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-10T07:19:00Z","doi":"10.1002/cjce.24281/v1/review3","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1111/jph.70032/v1/review2","name":"Review for \"Identification of Plant Species Using Convolutional Neural Network with Transfer Learning\"","source":"crossref","abstract":"","url":"https://doi.org/10.1111/jph.70032/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-05T16:15:21Z","doi":"10.1111/jph.70032/v1/review2","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.5194/gi-2018-53-ec1","name":"Review comment by handling associate editor","source":"crossref","abstract":"","url":"https://doi.org/10.5194/gi-2018-53-ec1","authors":["Walter Schmidt"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-08-09T12:29:28Z","doi":"10.5194/gi-2018-53-ec1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.2139/ssrn.4545036","name":"Spiking Neural Networks with Consistent Mapping Relations Allow High-Accuracy Inference","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4545036","authors":["Yang Li","Xiang He","Qingqun Kong","Yi Zeng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-18T15:18:43Z","doi":"10.2139/ssrn.4545036","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/sai.2017.8252173","name":"Solving the linearly inseparable XOR problem with spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/sai.2017.8252173","authors":["Mirela Reljan-Delaney","Julie Wall"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-01-11T18:49:34Z","doi":"10.1109/sai.2017.8252173","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.21203/rs.3.rs-7019575/v1","name":"Cell Attention Networks Integrated with Spiking Neural Networks and Binary Light Spectrum Optimization for Efficient Task Scheduling in Cloud Computing: Blockchain-Enhanced","source":"crossref","abstract":"Abstract Task scheduling in cloud computing remains a persistent and complex challenge due to inherently dynamic resource requirements and fluctuating workload patterns. Traditional methodologies—whether heuristic or AI-driven—often fall short in delivering real-time adaptability, robust scalability, and verifiable security. To address these limitations, this study introduces a composite framework integrating Cell Attention Networks (CANs), Spiking Neural Networks (SNNs), and Binary Light Spectrum Optimization (BLSO), underpinned by a Blockchain infrastructure for secure and trustworthy task management. CANs facilitate dynamic task prioritization by attending in real-time to resource-sensitive attributes. SNNs, inspired by the spike-based signaling of biological neurons, enable efficient temporal encoding and representation of task data. BLSO, as a discrete binary metaheuristics technique, ensures lightweight yet effective optimization in the task-to-resource allocation process. Security and trust are reinforced through blockchain deployment, guaranteeing immutability, auditability, and decentralized validation via smart contracts. The proposed architecture was empirically validated using simulated cloud workload environments and standard benchmark datasets within a Python–TensorFlow–BindsNET framework, integrated with Ethereum Testnet for decentralized verification. Experimental outcomes demonstrated significant enhancements in execution latency, energy efficiency, SLA compliance, and trustworthiness when compared to conventional scheduling algorithms.","url":"https://doi.org/10.21203/rs.3.rs-7019575/v1","authors":["Babasaheb Annasaheb Abhale","Nitin Laxman Shelake","Prakash Pandharinath Rokade","Somnath Gade"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-01T16:11:06Z","doi":"10.21203/rs.3.rs-7019575/v1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1039/d5dd00012b/v1/review2","name":"Review for \"ACES-GNN: Can Graph Neural Network Learn to Explain Activity Cliffs?\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5dd00012b/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-01T17:08:16Z","doi":"10.1039/d5dd00012b/v1/review2","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1002/eng2.12854/v2/review1","name":"Review for \"Preserving node similarity adversarial learning graph representation with graph neural network\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/eng2.12854/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-29T16:15:16Z","doi":"10.1002/eng2.12854/v2/review1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1186/1471-2202-13-s1-p156","name":"Determinants of associative memory performance in spiking and non-spiking neural networks with different synaptic plasticity regimes","source":"crossref","abstract":"","url":"https://doi.org/10.1186/1471-2202-13-s1-p156","authors":["Alex Metaxas","Reinoud Maex","Rod Adams","Volker Steuber","Neil Davey"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-07-22T09:20:22Z","doi":"10.1186/1471-2202-13-s1-p156","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.21203/rs.3.rs-7117847/v1","name":"Artificial Neural Network for Stability-Constrained Optimal Power Flow","source":"crossref","abstract":"Abstract The usage of the development of machine learning is extremely important these days, especially in power systems. Artificial neural networks (ANN) have been developed and implemented successfully to improve power system performance and solve complex problems. This paper introduces a new machine learning-based approach to the power flow operation using different types of ANNs, including simple feedforward neural networks (SFNN), learning neural networks (TLNN), simple deep neural networks (SDNN), deep feedforward neural networks (DFFNN) and long short long memory neural network (LSTM). The modeling aims to predict the optimal power flow parameters to ensure efficient and economical power system operation considering the power system stability constraints such as voltage control limits and power angle limits. ANN performance is evaluated using each parameter's mean square error (MSE). The study results show high system stability prediction data accuracy, essential for power system operation. The results also confirm that the proposed approach can offer a significant advancement in utilizing machine learning to improve the monitoring of optimal power flow in real-time operation, considering stability constraints.","url":"https://doi.org/10.21203/rs.3.rs-7117847/v1","authors":["Hassan Alsobaie"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-15T03:55:33Z","doi":"10.21203/rs.3.rs-7117847/v1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1017/eds.2024.49.pr3","name":"Review: The challenge of land in a neural network ocean model — R0/PR3","source":"crossref","abstract":"","url":"https://doi.org/10.1017/eds.2024.49.pr3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-22T04:57:34Z","doi":"10.1017/eds.2024.49.pr3","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.21203/rs.3.rs-6736952/v1","name":"Parallelizing Convolution Neural Network for Image Classification","source":"crossref","abstract":"Abstract The problem in classifying images using CNN is that it is a time consuming process. Actually it takes minutes to identify one image in average cases. This case has been studied regarding its uses, types, and importance. Due to its several practices, it was very crucial to find some ways that decrease its needed time and maintaining the quality and efficiency of the program. CNN, in all its types used matrix calculations a lot to classify images which was one of the main reasons for the high needed time. Solving the problem begins by modifying these calculations and make them faster. Using several parallelism techniques such as MPI, OpenMP, Cuda C can be of great assistance in this case. Although those methods are different in terms of applications, all of them will be used to increase the speed of the CNN while maintaining its accuracy. Experimental results show that these techniques were different in terms of needed time but similar in being very less than the sequential version of the CNN. It is recommended that future studies should research other types of image classification and parallel techniques.","url":"https://doi.org/10.21203/rs.3.rs-6736952/v1","authors":["Ali Al Hajj Ali"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-29T09:13:54Z","doi":"10.21203/rs.3.rs-6736952/v1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.5194/essd-2018-111-rc3","name":"Review of 'A global monthly climatology of total alkalinity: a neural network approach'","source":"crossref","abstract":"","url":"https://doi.org/10.5194/essd-2018-111-rc3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-12-19T09:03:59Z","doi":"10.5194/essd-2018-111-rc3","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.21203/rs.2.21664/v3","name":"WITHDRAWN: Exploring the Effectiveness of Convolutional Neural Network with Ensemble Technique","source":"crossref","abstract":"Abstract The full text of this preprint has been withdrawn by the authors due to author disagreement with the posting of the preprint. Therefore, the authors do not wish this work to be cited as a reference. Questions should be directed to the corresponding author.","url":"https://doi.org/10.21203/rs.2.21664/v3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-08-31T10:40:42Z","doi":"10.21203/rs.2.21664/v3","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1002/cjce.24281/v2/review1","name":"Review for \"Improved bilayer convolution transfer learning neural network for industrial fault detection\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/cjce.24281/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-10T07:19:00Z","doi":"10.1002/cjce.24281/v2/review1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1002/cem.3529/v1/review1","name":"Review for \"Adaptive deep fusion neural network based soft sensor for industrial process\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/cem.3529/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-21T16:11:21Z","doi":"10.1002/cem.3529/v1/review1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1002/prot.26079/v1/review1","name":"Review for \"Protein secondary structure assignment using pc ‐polyline and convolutional neural network\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/prot.26079/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-29T17:02:26Z","doi":"10.1002/prot.26079/v1/review1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1007/978-1-4757-5858-0_7","name":"Nonspiking and Spiking Local Interneurons in the Locust","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4757-5858-0_7","authors":["Malcolm Burrows"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-06-01T13:13:58Z","doi":"10.1007/978-1-4757-5858-0_7","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/cec.2011.5949684","name":"Training spiking neural models using cuckoo search algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cec.2011.5949684","authors":["Roberto A. Vazquez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-07-20T20:51:24Z","doi":"10.1109/cec.2011.5949684","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1002/cjce.24281/v1/review2","name":"Review for \"Improved bilayer convolution transfer learning neural network for industrial fault detection\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/cjce.24281/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-10T07:19:00Z","doi":"10.1002/cjce.24281/v1/review2","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/jcice66205.2025.11182074","name":"Spiking-STGCN: A Lightweight Spiking Spatio-Temporal Graph Convolutional Network Model for Urban Traffic Flow Prediction","source":"crossref","abstract":"","url":"https://doi.org/10.1109/jcice66205.2025.11182074","authors":["Zhiqiang Cao","Hui Xu","HaoMeng Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-09T17:50:38Z","doi":"10.1109/jcice66205.2025.11182074","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/ijcnn.2018.8489410","name":"Mastering the Output Frequency in Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2018.8489410","authors":["Pierre Falez","Pierre Tirilly","Ioan Marius Bilasco","Philippe Devienne","Pierre Boulet"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-10-19T22:25:09Z","doi":"10.1109/ijcnn.2018.8489410","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1162/neco_a_00450","name":"A New Supervised Learning Algorithm for Spiking Neurons","source":"crossref","abstract":"The purpose of supervised learning with temporal encoding for spiking neurons is to make the neurons emit a specific spike train encoded by the precise firing times of spikes. If only running time is considered, the supervised learning for a spiking neuron is equivalent to distinguishing the times of desired output spikes and the other time during the running process of the neuron through adjusting synaptic weights, which can be regarded as a classification problem. Based on this idea, this letter proposes a new supervised learning method for spiking neurons with temporal encoding; it first transforms the supervised learning into a classification problem and then solves the problem by using the perceptron learning rule. The experiment results show that the proposed method has higher learning accuracy and efficiency over the existing learning methods, so it is more powerful for solving complex and real-time problems.","url":"https://doi.org/10.1162/neco_a_00450","authors":["Yan Xu","Xiaoqin Zeng","Shuiming Zhong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-03-21T15:56:17Z","doi":"10.1162/neco_a_00450","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1007/s00521-013-1397-8","name":"Homogenous spiking neural P systems with anti-spikes","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-013-1397-8","authors":["Tao Song","Xun Wang","Zhujin Zhang","Zhihua Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-05-31T05:49:21Z","doi":"10.1007/s00521-013-1397-8","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1002/gj.70260/v1/review2","name":"Review for \"Mapping China’s Environmental Sustainability Drivers with Wavelet-Based Artificial Neural Network\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/gj.70260/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-13T21:09:03Z","doi":"10.1002/gj.70260/v1/review2","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1039/d5dd00012b/v2/review1","name":"Review for \"ACES-GNN: Can Graph Neural Network Learn to Explain Activity Cliffs?\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5dd00012b/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-01T17:08:16Z","doi":"10.1039/d5dd00012b/v2/review1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.21203/rs.3.rs-863687/v1","name":"Explainable Neural Network Ensembles","source":"crossref","abstract":"Abstract Neural networks are known for providing impressive classification performance, and the ensemble learning technique is further acting as a catalyst to enhance this performance by integrating multiple networks. But like neural networks, neural network ensembles are also considered as a black-box because they cannot explain their decision making process. So, despite having high classification performance, neural networks and their ensembles are not suited for some applications which require explainable decisions. However, the rule extraction technique can overcome this drawback by representing the knowledge learned by a neural network in the guise of interpretable decision rules. A rule extraction algorithm provides neural networks with the power to justify their classification responses through explainable classification rules. Several rule extraction algorithms exist to extract classification rules from neural networks, but only a few of them generates rules using neural network ensembles. So this paper proposes an algorithm named Rule Extraction using Ensemble of Neural Network Ensembles (RE-E-NNES) to demonstrate the high performance of neural network ensembles through rule extraction. RE-E-NNES extracts classification rules by ensembling several neural network ensembles. Results show the efficacy of the proposed RE-E-NNES algorithm compared to different existing rule extraction algorithms.","url":"https://doi.org/10.21203/rs.3.rs-863687/v1","authors":["Manomita Chakraborty","Saroj Kumar Biswas","Biswajit Purkayastha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-15T19:25:48Z","doi":"10.21203/rs.3.rs-863687/v1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1017/eds.2024.49.pr2","name":"Review: The challenge of land in a neural network ocean model — R0/PR2","source":"crossref","abstract":"","url":"https://doi.org/10.1017/eds.2024.49.pr2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-22T04:57:34Z","doi":"10.1017/eds.2024.49.pr2","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/tevc.2024.3507812/mm1","name":"Brain-Inspired Multi-Scale Evolutionary Neural Architecture Search for Deep Spiking Neural Networks_supp1-3507812.pdf","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tevc.2024.3507812/mm1","authors":["Wenxuan Pan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-10T20:25:15Z","doi":"10.1109/tevc.2024.3507812/mm1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/pdp2018.2018.00110","name":"Gaussian and Exponential Lateral Connectivity on Distributed Spiking Neural Network Simulation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/pdp2018.2018.00110","authors":["Elena Pastorelli","Pier Stanislao Paolucci","Francesco Simula","Andrea Biagioni","Fabrizio Capuani","Paolo Cretaro","Giulia De Bonis","Francesca Lo Cicero","Alessandro Lonardo","Michele Martinelli","Luca Pontisso","Piero Vicini","Roberto Ammendola"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-06-07T23:44:22Z","doi":"10.1109/pdp2018.2018.00110","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1088/0954-898x_8_2_001","name":"Plasticity in adult sensory cortex: a review","source":"crossref","abstract":"There is growing evidence of significant plasticity in neuronal receptive fields and functional architecture in adult primary sensory cortex. Surgical lesions or rewiring of nerves in the periphery lead to large-scale changes in the corresponding cortical maps. Such changes are also seen after protracted training on sensory discrimination tasks, in a manner that reflects the subjects' improved discriminative abilities after training and is governed by their attentional state during training. More rapid and dynamic changes in cortical receptive field properties are seen with selective visual stimulation and during conditioning experiments. In the visual system, adult plasticity is clearly attributable to changes in cortex and not subcortical changes; moreover, the evidence suggests that the network of horizontal collaterals in primary visual cortex (V1) may play a significant role in V1 plasticity, both long-term and rapid. The same network is also likely to underlie some aspects of routine visual integration in V1. This leads to the speculation that plastic processes could form a part of routine cortical processing. At a cellular level, neurons in adult cortex possess the synaptic machinery that could underlie much of the observed adult plasticity. This includes short- as well as long-term activity-dependent processes for synaptic modification, as well as the modulation of such effects by the context of a task.","url":"https://doi.org/10.1088/0954-898x_8_2_001","authors":["Aniruddha Das"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:05:00Z","doi":"10.1088/0954-898x_8_2_001","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.7287/peerj.preprints.2595v1","name":"Somatic inhibition controls dendritic selectivity in a sparse coding network of spiking neurons","source":"crossref","abstract":"Sparse coding is an effective operating principle for the brain, one that can guide the discovery of features and support the learning of assocations. Here we show how spiking neurons with discrete dendrites can learn sparse codes via an online, nonlinear Hebbian rule based on the concept of somato-dendritic mismatch. The rule gives lateral inhibition direct control over the selectivity of dendritic receptive fields, without the need for a sliding threshold. The network discovers independent components that are similar to the features learned by a sparse autoencoder. This improves the linear decodability of the input: combined with a linear readout, our single-layer network performs as well as a deeper multi-layer Perceptron on the MNIST dataset. It can also produce topographic feature maps when the lateral connections are organised in a center-surround pattern, although this does not improve the quality of the encoding.","url":"https://doi.org/10.7287/peerj.preprints.2595v1","authors":["Damien Drix"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-01-13T05:54:38Z","doi":"10.7287/peerj.preprints.2595v1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1017/eds.2024.49.pr7","name":"Review: The challenge of land in a neural network ocean model — R1/PR7","source":"crossref","abstract":"","url":"https://doi.org/10.1017/eds.2024.49.pr7","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-22T04:57:34Z","doi":"10.1017/eds.2024.49.pr7","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1101/766758","name":"Learning long temporal sequences in spiking networks by multiplexing neural oscillations","source":"crossref","abstract":"Many cognitive and behavioral tasks – such as interval timing, spatial navigation, motor control and speech – require the execution of precisely-timed sequences of neural activation that cannot be fully explained by a succession of external stimuli. We show how repeatable and reliable patterns of spatiotemporal activity can be generated in chaotic and noisy spiking recurrent neural networks. We propose a general solution for networks to autonomously produce rich patterns of activity by providing a multi-periodic oscillatory signal as input. We show that the model accurately learns a variety of tasks, including speech generation, motor control and spatial navigation. Further, the model performs temporal rescaling of natural spoken words and exhibits sequential neural activity commonly found in experimental data involving temporal processing. In the context of spatial navigation, the model learns and replays compressed sequences of place cells and captures features of neural activity such as the emergence of ripples and theta phase precession. Together, our findings suggest that combining oscillatory neuronal inputs with different frequencies provides a key mechanism to generate precisely timed sequences of activity in recurrent circuits of the brain.","url":"https://doi.org/10.1101/766758","authors":["Philippe Vincent-Lamarre","Matias Calderini","Jean-Philippe Thivierge"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-09-12T20:07:24Z","doi":"10.1101/766758","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1017/eds.2024.49.pr8","name":"Review: The challenge of land in a neural network ocean model — R1/PR8","source":"crossref","abstract":"","url":"https://doi.org/10.1017/eds.2024.49.pr8","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-22T04:57:34Z","doi":"10.1017/eds.2024.49.pr8","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.21203/rs.3.rs-1689613/v1","name":"Research on Rose Classification Based on Neural Network Model","source":"crossref","abstract":"Abstract As an important industry in China, rose has extremely important economic value and ornamental value. However, affected by human factors and planting environment, even roses of the same variety will have different levels of classification. In order to solve the low efficiency of wrong classification and missing classification caused by manual visual classification and realize the transformation of rose classification from manual judgment to machine independent recognition, this paper first performs data enhancement, image naming and other operations on 200 manually photographed yellow rose images of 5 levels of the same variety, and constructs an image database. Then, in Python language and tensorflow2.0 deep learning tool, design rose classification algorithm based on artificial neural network(ANN), rose classification algorithm based on convolution neural network(CNN) and rose classification algorithm based on feature extraction(FE) and artificial neural network(ANN). Finally, the experimental results show that the third algorithm significantly speeds up the running speed and significantly improves the average recognition rate compared with the first two algorithms, which effectively solves the problems of wrong or missing classification and low classification efficiency in manual intuitive classification, and realizes the transformation from manual classification to machine independent classification.","url":"https://doi.org/10.21203/rs.3.rs-1689613/v1","authors":["Jiaojiao Hui"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-27T17:26:59Z","doi":"10.21203/rs.3.rs-1689613/v1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.21203/rs.3.rs-849560/v1","name":"Analysis of Industry Convergence Based on Improved Neural Network","source":"crossref","abstract":"Abstract Economic growth in the information age is no longer a stage driven by unipolarity. It has entered a multi-polar driving stage characterized by integration, fusion, and integrated development on a larger scale between regions, and the trend of group competition with urban agglomerations as carriers has become increasingly obvious. This paper improves the neural network algorithm based on the needs of industrial economic integration in the digital age, and proposes an industry convergence analysis model based on the improved neural network algorithm. Moreover, this article combines industry models to analyze actual needs and constructs an industry convergence analysis model based on improved neural networks, and analyzes the integration of different industries. In addition, this article conducts experiments through multiple sets of data, and combines the neural network model of this article to conduct research. Through experimental research, we know that the model constructed in this paper can play an important role in the analysis of industry convergence.","url":"https://doi.org/10.21203/rs.3.rs-849560/v1","authors":["Nan Ma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-08T21:41:06Z","doi":"10.21203/rs.3.rs-849560/v1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1101/2021.03.22.436372","name":"Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks","source":"crossref","abstract":"ABSTRACT Inspired by more detailed modeling of biological neurons, Spiking neural networks (SNNs) have been investigated both as more biologically plausible and potentially more powerful models of neural computation, and also with the aim of extracting biological neurons’ energy efficiency; the performance of such networks however has remained lacking compared to classical artificial neural networks (ANNs). Here, we demonstrate how a novel surrogate gradient combined with recurrent networks of tunable and adaptive spiking neurons yields state-of-the-art for SNNs on challenging benchmarks in the time-domain, like speech and gesture recognition. This also exceeds the performance of standard classical recurrent neural networks (RNNs) and approaches that of the best modern ANNs. As these SNNs exhibit sparse spiking, we show that they theoretically are one to three orders of magnitude more computationally efficient compared to RNNs with comparable performance. Together, this positions SNNs as an attractive solution for AI hardware implementations.","url":"https://doi.org/10.1101/2021.03.22.436372","authors":["Bojian Yin","Federico Corradi","Sander M. Bohté"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-22T13:50:19Z","doi":"10.1101/2021.03.22.436372","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1101/2020.12.15.422863","name":"Leveraging spiking deep neural networks to understand the neural mechanisms underlying selective attention","source":"crossref","abstract":"Abstract Spatial attention enhances sensory processing of goal-relevant information and improves perceptual sensitivity. Yet, the specific neural mechanisms underlying the effects of spatial attention on performance are still contested. Here, we examine different attention mechanisms in spiking deep convolutional neural networks. We directly contrast effects of precision (internal noise suppression) and two different gain modulation mechanisms on performance on a visual search task with complex real-world images. Unlike standard artificial neurons, biological neurons have saturating activation functions, permitting implementation of attentional gain as gain on a neuron’s input or on its outgoing connection. We show that modulating the connection is most effective in selectively enhancing information processing by redistributing spiking activity, and by introducing additional task-relevant information, as shown by representational similarity analyses. Precision only produced minor attentional effects in performance. Our results, which mirror empirical findings, show that it is possible to adjudicate between attention mechanisms using more biologically realistic models and natural stimuli.","url":"https://doi.org/10.1101/2020.12.15.422863","authors":["Lynn K. A. Sörensen","Davide Zambrano","Heleen A. Slagter","Sander M. Bohté","H. Steven Scholte"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-16T21:49:50Z","doi":"10.1101/2020.12.15.422863","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1111/jph.70032/v2/review1","name":"Review for \"Identification of Plant Species Using Convolutional Neural Network with Transfer Learning\"","source":"crossref","abstract":"","url":"https://doi.org/10.1111/jph.70032/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-05T16:15:21Z","doi":"10.1111/jph.70032/v2/review1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.21203/rs.3.rs-75530/v1","name":"Domain Randomization for Neural Network Classification","source":"crossref","abstract":"Abstract Large data requirements are often the main hurdle in training neural networks. Synthetic data is a cheap and efficient solution to assemble such large datasets. Using domain randomization, we show that a sufficiently well generated synthetic image dataset can be used to train a neural network classifier, achieving accuracy levels as high as 88% on 2 category classification. We show that the most important domain randomization parameter is a large variety of subjects, while secondary parameters such as lighting and textures are not. Based on our results, there is reason to believe that models trained on domain randomized images transfer to new domains better than those trained on real photos. Model performance seems to diminish slightly as the number of categories increases.","url":"https://doi.org/10.21203/rs.3.rs-75530/v1","authors":["Svetozar Zarko Valtchev","Jianhong Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-23T00:09:43Z","doi":"10.21203/rs.3.rs-75530/v1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/iscas45731.2020.9181005/video","name":"Video for Algorithmic Enablers for Compact Neural Network Topology Hardware Design: Review and Trends","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas45731.2020.9181005/video","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-29T09:22:27Z","doi":"10.1109/iscas45731.2020.9181005/video","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1162/neco.1996.8.1.1","name":"Lower Bounds for the Computational Power of Networks of Spiking Neurons","source":"crossref","abstract":"We investigate the computational power of a formal model for networks of spiking neurons. It is shown that simple operations on phase differences between spike-trains provide a very powerful computational tool that can in principle be used to carry out highly complex computations on a small network of spiking neurons. We construct networks of spiking neurons that simulate arbitrary threshold circuits, Turing machines, and a certain type of random access machines with real valued inputs. We also show that relatively weak basic assumptions about the response and threshold functions of the spiking neurons are sufficient to employ them for such computations.","url":"https://doi.org/10.1162/neco.1996.8.1.1","authors":["Wolfgang Maass"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-04-04T15:24:53Z","doi":"10.1162/neco.1996.8.1.1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1007/978-1-4614-7320-6_792-3","name":"Spiking Network Models and Theory: Overview","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4614-7320-6_792-3","authors":["Marc-Oliver Gewaltig"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-09-29T17:23:06Z","doi":"10.1007/978-1-4614-7320-6_792-3","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1103/6958-v2np","name":"Artificial neural network (ANN) - oscillatory neural network (ONN) hybrid system using domain-wall synapse devices and nano-constriction spin hall nano oscillators","source":"crossref","abstract":"","url":"https://doi.org/10.1103/6958-v2np","authors":["Anonymous"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-19T17:56:37Z","doi":"10.1103/6958-v2np","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1007/978-1-4614-7320-6_792-1","name":"Spiking Network Models and Theory: Overview","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4614-7320-6_792-1","authors":["Marc-Oliver Gewaltig"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-10-02T02:13:53Z","doi":"10.1007/978-1-4614-7320-6_792-1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/icc.2018.8422760","name":"A Cognitive Network Controller Based on Spiking Neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icc.2018.8422760","authors":["Ricardo Lent"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-08-20T22:51:41Z","doi":"10.1109/icc.2018.8422760","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/72.668899","name":"Self-organization of spiking neurons using action potential timing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/72.668899","authors":["B. Ruf","M. Schmitt"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-24T19:16:32Z","doi":"10.1109/72.668899","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/ijcnn48605.2020.9207620","name":"Self-regulated Learning Algorithm for Distributed Coding Based Spiking Neural Classifier","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn48605.2020.9207620","authors":["Pranav Machingal","Mohammed Thousif","Shirin Dora","Suresh Sundaram"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-29T20:40:33Z","doi":"10.1109/ijcnn48605.2020.9207620","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1007/3-540-44989-2_115","name":"A Complex-Valued Spiking Machine","source":"crossref","abstract":"","url":"https://doi.org/10.1007/3-540-44989-2_115","authors":["Gilles Vaucher"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-11-19T22:10:02Z","doi":"10.1007/3-540-44989-2_115","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.52202/068431-2213","name":"Training Spiking Neural Networks with Event-Driven Backpropagation","source":"crossref","abstract":"","url":"https://doi.org/10.52202/068431-2213","authors":["Yaoyu Zhu","Zhaofei Yu","Wei Fang","Xiaodong Xie","Tiejun Huang","Timothée Masquelier"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-02T13:17:52Z","doi":"10.52202/068431-2213","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1016/j.neunet.2024.106630","name":"SNN-BERT: Training-efficient Spiking Neural Networks for energy-efficient BERT","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106630","authors":["Qiaoyi Su","Shijie Mei","Xingrun Xing","Man Yao","Jiajun Zhang","Bo Xu","Guoqi Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-22T21:44:20Z","doi":"10.1016/j.neunet.2024.106630","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1037/e538112010-001","name":"A Simple Two-Dimensional Map for Modeling of Spiking-Bursting Neural Activity","source":"crossref","abstract":"","url":"https://doi.org/10.1037/e538112010-001","authors":["N. Rulkov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-02-23T16:51:52Z","doi":"10.1037/e538112010-001","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1016/b978-0-12-820125-1.00022-1","name":"Spiking neural networks and dendrite morphological neural networks: an introduction","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-12-820125-1.00022-1","authors":["Humberto Sossa","Carlos D. Virgilio-G."],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-01-14T16:50:48Z","doi":"10.1016/b978-0-12-820125-1.00022-1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/ijcnn.2016.7727211","name":"BPSpike: A backpropagation learning for all parameters in spiking neural networks with multiple layers and multiple spikes","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2016.7727211","authors":["Satoshi Matsuda"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-11-08T16:15:56Z","doi":"10.1109/ijcnn.2016.7727211","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/ijcnn.2016.7727759","name":"Probabilistic inference using stochastic spiking neural networks on a neurosynaptic processor","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2016.7727759","authors":["Khadeer Ahmed","Amar Shrestha","Qinru Qiu","Qing Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-11-08T21:15:56Z","doi":"10.1109/ijcnn.2016.7727759","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.20944/preprints202411.2358.v1","name":"Studying the Reduction of Entropy in the Brain During Sleep Through Spiking Neural Networks","source":"crossref","abstract":"Sleep remains one of the most confusing biological functions, yet its role in maintaining physiological and cognitive well-being in is undeniable. This paper investigates the hypothesis that of sleep’s primary functions is to reduce neural entropy, drawing parallels between biological processes and artificial Spiking Neural Networks (SNNs). This study is an initial prototype of the final model which will incorporate mechanisms like Spike-Timing-Dependent Plasticity (STDP) and synaptic homeostasis, to simulate the entropic reduction and memory consolidation functions of sleep. The initial prototype shows how neural entropy will be quantified using statistical mechanics principles, and the architecture and training protocols of SNNs are designed to mirror biological neural activity during sleep.","url":"https://doi.org/10.20944/preprints202411.2358.v1","authors":["Joshua Gupta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T02:00:11Z","doi":"10.20944/preprints202411.2358.v1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1088/2634-4386/ae7ab5/data1","name":"Additional results and theory","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2634-4386/ae7ab5/data1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-23T06:26:26Z","doi":"10.1088/2634-4386/ae7ab5/data1","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.2139/ssrn.6343052","name":"LogSNN: Spiking Neural Networks for System Log Anomaly Detection","source":"crossref","abstract":"Log anomaly detection is the most important method for identifying potential system failure. However, current Artificial Neural Networks (ANNs) based methods significantly increase the energy consumption of the system while improving the accuracy of log classification. In this paper, we present a novel SNN framework specifically designed for system log anomaly detection, offering distinct advantages in energy efficiency and temporal information processing. First, we introduce a new LLMs-based Spike Feature Encoding (LSFE) method, which encodes word embeddings from a pre-trained T5-base model into spatiotemporal spike sequences. This approach bridge the gap between high accuracy and low energy consumption in SNNs. Second, we propose an SNN Fine-Tuning (SFT) method that integrates SNN with the T5-base model, allowing supervised fine-tuning to enhance the learning capabilities of the network. This fine-tuning process addresses the accuracy limitations typically encountered in traditional SNNs. Experimental results demonstrate that 1) LogSNN consumes only 23\\% of the energy required by UniLog and LogBERT; and 2) LogSNN achieves the highest performance with an F1-score of 0.9951 on the HDFS dataset and 0.9948 on the BGL dataset. This work presents a breakthrough in the application of SNNs to log anomaly detection, positioning SNNs as a competitive solution in resource-constrained environments.","url":"https://doi.org/10.2139/ssrn.6343052","authors":["Song Chen","Hai Liao","Yan Liang","Hang Zhou","Fan Min"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-04T14:39:38Z","doi":"10.2139/ssrn.6343052","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.2139/ssrn.4121104","name":"Saliency Map Using Features Derived from Spiking Neural Networks of Primate Visual Cortex","source":"crossref","abstract":"We propose a framework inspired by biological vision systems to produce saliency maps of digital images. Well-known computational models for receptive fields of areas in the visual cortex that are specialized for color and orientation perception are used. To model the connectivity between these areas we use the CARLsim library which is a spiking neural network(SNN) simulator. The spikes generated by CARLsim, then serve as extracted features and input to our saliency detection algorithm. This new method of saliency detection is described and applied to benchmark images.","url":"https://doi.org/10.2139/ssrn.4121104","authors":["Reza Hojjaty Saeedy","Richard  A. Messner"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-05-28T08:35:39Z","doi":"10.2139/ssrn.4121104","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/ijcnn.2017.7966177","name":"EnsembleSNN: Distributed assistive STDP learning for energy-efficient recognition in spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2017.7966177","authors":["Priyadarshini Panda","Gopalakrishnan Srinivasan","Kaushik Roy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-07-10T17:41:30Z","doi":"10.1109/ijcnn.2017.7966177","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.52202/068431-0920","name":"Training Spiking Neural Networks with Local Tandem Learning","source":"crossref","abstract":"","url":"https://doi.org/10.52202/068431-0920","authors":["Qu Yang","Jibin Wu","Malu Zhang","Yansong Chua","Xinchao Wang","Haizhou Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-02T13:17:52Z","doi":"10.52202/068431-0920","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1007/978-1-4419-1428-6_1714","name":"Supervised Learning in Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4419-1428-6_1714","authors":["Răzvan V. Florian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-01-06T12:19:05Z","doi":"10.1007/978-1-4419-1428-6_1714","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1101/2021.06.24.449760","name":"Reproducing Human Motor Adaptation in Spiking Neural Simulation and known Synaptic Learning Rules","source":"crossref","abstract":"Abstract Sensorimotor adaptation enables us to adjust our goal-oriented movements in response to external perturbations. These phenomena have been studied experimentally and computationally at the level of human and animals reaching movements, and have clear links to the cerebellum as evidenced by cerebellar lesions and neurodegeneration. Yet, despite our macroscopic understanding of the high-level computational mechanisms it is unclear how these are mapped and are implemented in the neural substrates of the cerebellum at a cellular-computational level. We present here a novel spiking neural circuit model of the sensorimotor system including a cerebellum which control physiological muscle models to reproduce behaviour experiments. Our cerebellar model is composed of spiking neuron populations reflecting cells in the cerebellar cortex and deep cerebellar nuclei, which generate motor correction to change behaviour in response to perturbations. The model proposes two learning mechanisms for adaptation: predictive learning and memory formation, which are implemented with synaptic updating rules. Our model is tested in a force-field sensorimotor adaptation task and successfully reproduce several phenomena arising from human adaptation, including well-known learning curves, aftereffects, savings and other multi-rate learning effects. This reveals the capability of our model to learn from perturbations and generate motor corrections while providing a bottom-up view for the neural basis of adaptation. Thus, it also shows the potential to predict how patients with specific types of cerebellar damage will perform in behavioural experiments. We explore this by in silico experiments where we selectively incapacitate selected cerebellar circuits of the model which generate and reproduce defined motor learning deficits. Author summary A rich body of work in human motor neuroscience developed high-level computational theories of sensorimotor control, learning and adaptation. But there is a gap in understanding how this may be implemented and learn on the level of neurons, synapses and spikes. Conversely, studies of patients with cerebellar lesions or neurological disease highlight the essential role the cerebellum plays in our ability to perform motor learning. Yet, how these anatomical and molecular defects play out in terms of human movement have to date not been linked to a model that spans multiple level of biological organisation from neural circuits to reproducing human motor experiments. To address this gap, we present a spiking neuron of the sensorimotor system focused on the cerebellum, with which we can on the one side reproduce the high-level behaviour learning phenomena observed in healthy subjects, as well as quantitatively predicting the putative effects on human movement trajectories of cerebellar lesions implemented at the cellular level.","url":"https://doi.org/10.1101/2021.06.24.449760","authors":["Yufei Wu","Shlomi Haar","Aldo Faisal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-06-25T14:50:24Z","doi":"10.1101/2021.06.24.449760","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1007/s00521-022-08162-9","name":"Spiking Neural P System with weight model of majority voting technique for reliable interactive image segmentation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-022-08162-9","authors":["Mehran Dalvand","Abdolhossein Fathi","Arezoo Kamran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-25T04:15:06Z","doi":"10.1007/s00521-022-08162-9","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1016/j.neunet.2025.107256","name":"Spiking neural networks on FPGA: A survey of methodologies and recent advancements","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107256","authors":["Mehrzad Karamimanesh","Ebrahim Abiri","Mahyar Shahsavari","Kourosh Hassanli","André van Schaik","Jason Eshraghian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-14T17:53:32Z","doi":"10.1016/j.neunet.2025.107256","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1007/978-1-4419-1428-6_1713","name":"Reinforcement Learning in Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4419-1428-6_1713","authors":["Răzvan V. Florian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-01-06T12:11:29Z","doi":"10.1007/978-1-4419-1428-6_1713","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1109/icons69015.2025.00037","name":"Uncertainty-Aware Spiking Neural Networks for Regression","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icons69015.2025.00037","authors":["Tao Sun","Sander Bohté"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-21T21:07:17Z","doi":"10.1109/icons69015.2025.00037","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.5772/intechopen.89781","name":"Integration of Spiking Neural Networks for Understanding Interval Timing","source":"crossref","abstract":"","url":"https://doi.org/10.5772/intechopen.89781","authors":["Nicholas A. Lusk"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-11-05T13:00:48Z","doi":"10.5772/intechopen.89781","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.2139/ssrn.4685965","name":"Secure Inference on Layered Spiking Neural P Systems Using Homomorphic Encryption","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4685965","authors":["Mihail-Iulian Plesa","Prof. Marian Gheorghe","Florentin Ipate"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-06T07:22:42Z","doi":"10.2139/ssrn.4685965","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1016/j.biosystems.2006.06.006","name":"Small universal spiking neural P systems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.biosystems.2006.06.006","authors":["Andrei Păun","Gheorghe Păun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-07-01T09:40:19Z","doi":"10.1016/j.biosystems.2006.06.006","addedAt":"2026-09-01T01:48:28.363Z","updatedAt":"2026-09-01T01:48:28.363Z"},{"id":"doi:10.1162/neco.2007.19.9.2433","name":"Computational Properties of Networks of Synchronous Groups of Spiking Neurons","source":"crossref","abstract":"We demonstrate a model in which synchronously firing ensembles of neurons are networked to produce computational results. Each ensemble is a group of biological integrate-and-fire spiking neurons, with probabilistic interconnections between groups. An analogy is drawn in which each individual processing unit of an artificial neural network corresponds to a neuronal group in a biological model. The activation value of a unit in the artificial neural network corresponds to the fraction of active neurons, synchronously firing, in a biological neuronal group. Weights of the artificial neural network correspond to the product of the interconnection density between groups, the group size of the presynaptic group, and the postsynaptic potential heights in the synchronous group model. All three of these parameters can modulate connection strengths between neuronal groups in the synchronous group models. We give an example of nonlinear classification (XOR) and a function approximation example in which the capability of the artificial neural network can be captured by a neural network model with biological integrate-and-fire neurons configured as a network of synchronously firing ensembles of such neurons. We point out that the general function approximation capability proven for feedforward artificial neural networks appears to be approximated by networks of neuronal groups that fire in synchrony, where the groups comprise integrate-and-fire neurons. We discuss the advantages of this type of model for biological systems, its possible learning mechanisms, and the associated timing relationships.","url":"https://doi.org/10.1162/neco.2007.19.9.2433","authors":["Judith E. Dayhoff"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-07-24T17:08:08Z","doi":"10.1162/neco.2007.19.9.2433","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1023/a:1009697008681","name":"Learning Temporally Encoded Patterns in Networks of Spiking Neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1023/a:1009697008681","authors":["Berthold Ruf","Michael Schmitt"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-12-22T22:47:08Z","doi":"10.1023/a:1009697008681","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1162/0899766053491913","name":"Image Segmentation by Networks of Spiking Neurons","source":"crossref","abstract":"A network of leaky integrate-and-fire (IAF) neurons is proposed to segment gray-scale images. The network architecture with local competition between neurons that encode segment assignments of image blocks is motivated by a histogram clustering approach to image segmentation. Lateral excitatory connections between neighboring image sites yield a local smoothing of segments. The mean firing rate of class membership neurons encodes the image segmentation. A weight modification scheme is proposed that estimates segment-specific prototypical histograms. The robustness properties of the network implementation make it amenable to an analog VLSI realization. Results on synthetic and real-world images demonstrate the effectiveness of the architecture.","url":"https://doi.org/10.1162/0899766053491913","authors":["Joachim M. Buhmann","Tilman Lange","Ulrich Ramacher"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-03-25T00:09:56Z","doi":"10.1162/0899766053491913","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1109/ijcnn60899.2024.10650023","name":"Atrial Fibrillation Detector from ECG on Wearable Edge Devices using Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn60899.2024.10650023","authors":["Dighanchal Banerjee","Sounak Dey","Arpan Pal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T17:35:05Z","doi":"10.1109/ijcnn60899.2024.10650023","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1109/ijcnn52387.2021.9533874","name":"Minimizing Inference Time: Optimization Methods for Converted Deep Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn52387.2021.9533874","authors":["Etienne Mueller","Julius Hansjakob","Daniel Auge","Alois Knoll"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-20T17:27:41Z","doi":"10.1109/ijcnn52387.2021.9533874","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.22541/au.169564699.96503493/v1","name":"On training spiking neural networks by means of a novel quantum inspired machine learning method","source":"crossref","abstract":"In spite of the high potential shown by spiking neural networks (e.g., temporal patterns), training them remains an open and complex problem [1]. In practice, while in theory these networks are computationally as powerful as mainstream artificial neural networks [2], they have not reached the same accuracy levels yet. The major reason for such situation seems to be represented by the lack of adequate training algorithms for deep spiking neural networks, since spike signals are not differentiable, i.e. no direct way to compute a gradient is provided. Recently a novel training method, based on the (digital) simulation of certain quantum systems, has been suggested. It has already shown interesting advantages, among which the fact that no gradient is required to be computed. In this work, we apply this approach to the problem of training spiking neural networks and we show that this recent training method is capable of training deep and complex spiking neural networks on the MNIST data set.","url":"https://doi.org/10.22541/au.169564699.96503493/v1","authors":["Jean Michel Sellier","Alexandre Martini"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-25T09:03:28Z","doi":"10.22541/au.169564699.96503493/v1","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1088/2634-4386/accd90/v2/response1","name":"Author response for \"Spiking neural networks compensate weight drift in organic neuromorphic device networks\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2634-4386/accd90/v2/response1","authors":["Daniel Felder","John Linkhorst","Matthias Wessling"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-18T17:03:24Z","doi":"10.1088/2634-4386/accd90/v2/response1","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/neuro.11.005.2008","name":"Brian: a simulator for spiking neural networks in Python","source":"crossref","abstract":"","url":"https://doi.org/10.3389/neuro.11.005.2008","authors":["Dan Goodman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-11-18T15:14:41Z","doi":"10.3389/neuro.11.005.2008","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.5256/f1000research.196566.r475917","name":"Peer Review Report For: Measuring Neural Network Similarity [version 1; peer review: 1 approved with reservations]","source":"crossref","abstract":"","url":"https://doi.org/10.5256/f1000research.196566.r475917","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-20T10:36:06Z","doi":"10.5256/f1000research.196566.r475917","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1109/apemc53576.2022.9888650","name":"Temporal Neural Encoding Methods for Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/apemc53576.2022.9888650","authors":["Quankun Chen","Da Li","Tuomin Tao","Hanzhi Ma","Erping Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-20T15:33:28Z","doi":"10.1109/apemc53576.2022.9888650","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1109/asp-dac66049.2026.11420478","name":"Spiking-NeRF: Neural Graphics Acceleration With Spiking Feature Encoding for Edge 3D Rendering","source":"crossref","abstract":"","url":"https://doi.org/10.1109/asp-dac66049.2026.11420478","authors":["Jianzhen Gao","Wei Liu","Yue Liu","Hengyi Zhou","Zhiyi Yu","Shanlin Xiao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-10T19:51:15Z","doi":"10.1109/asp-dac66049.2026.11420478","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1142/s0129065727500213","name":"Compensation-Balanced Recurrent Neural Architecture Based on Nonlinear Spiking Neural Membrane Systems","source":"crossref","abstract":"Nonlinear spiking neural P (NSNP) systems offer a biologically inspired framework for modeling nonlinear temporal dynamics via spike consumption and generation. Existing NSNP-based recurrent architectures, such as the long short-term memory model inspired from spiking neural P systems (LSTM-SNP), primarily rely on implicit gating mechanisms and lack explicit state correction during recurrent propagation, which can lead to unstable state evolution and excessive information decay in long-term temporal modeling. To address this limitation, a compensation-balanced LSTM-SNP (CBLSTM-SNP) architecture is proposed. The model introduces a compensation-driven regulation mechanism, comprising a regulation branch and an adaptive compensation branch, to dynamically adjust hidden state evolution. From a nonlinear dynamical systems perspective, CBLSTM-SNP establishes a balanced recurrent state transition integrating memory preservation, nonlinear spike processing, and adaptive state restoration. Theoretical analysis confirms the boundedness and Lipschitz continuity of the proposed recurrent dynamics. Empirical evaluations on five benchmark time series datasets demonstrate that CBLSTM-SNP produces smoother hidden state trajectories and achieves comparable forecasting performance compared with several representative recurrent and hybrid models.","url":"https://doi.org/10.1142/s0129065727500213","authors":["Jun Fu","Hong Peng","Bing Li","Ziyin Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-14T07:47:49Z","doi":"10.1142/s0129065727500213","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/fnsys.2016.00065","name":"The Second Spiking Threshold: Dynamics of Laminar Network Spiking in the Visual Cortex","source":"crossref","abstract":"","url":"https://doi.org/10.3389/fnsys.2016.00065","authors":["Lars E. Forsberg","Lars H. Bonde","Michael A. Harvey","Per E. Roland"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-08-17T03:30:53Z","doi":"10.3389/fnsys.2016.00065","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1037/rev0000396.supp","name":"Supplemental Material for Free Association in a Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1037/rev0000396.supp","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-29T13:16:59Z","doi":"10.1037/rev0000396.supp","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.7554/elife.44324.012","name":"Author response: Fast and flexible sequence induction in spiking neural networks via rapid excitability changes","source":"crossref","abstract":"","url":"https://doi.org/10.7554/elife.44324.012","authors":["Rich Pang","Adrienne L Fairhall"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-28T10:00:32Z","doi":"10.7554/elife.44324.012","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.3389/conf.fncom.2012.55.00154","name":"A Robotic Platform for Spiking Neural Control Architectures","source":"crossref","abstract":"","url":"https://doi.org/10.3389/conf.fncom.2012.55.00154","authors":["Nawrot Martin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-10-25T08:14:18Z","doi":"10.3389/conf.fncom.2012.55.00154","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.2139/ssrn.4596284","name":"Differentiable Architecture Search with Multi-Dimensional Attention for Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4596284","authors":["YiLei Man YiLei Man","Delong Shang","Linhai Xie"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-09T11:05:53Z","doi":"10.2139/ssrn.4596284","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1101/2020.02.11.944751","name":"Strong inhibitory signaling underlies stable temporal dynamics and working memory in spiking neural networks","source":"crossref","abstract":"Abstract Cortical neurons process information on multiple timescales, and areas important for working memory (WM) contain neurons capable of integrating information over a long timescale. However, the underlying mechanisms for the emergence of neuronal timescales stable enough to support WM are unclear. By analyzing a spiking recurrent neural network (RNN) model trained on a WM task and activity of single neurons in the primate prefrontal cortex, we show that the temporal properties of our model and the neural data are remarkably similar. Dissecting our RNN model revealed strong inhibitory-to-inhibitory connections underlying a disinhibitory microcircuit as a critical component for long neuronal timescales and WM maintenance. We also found that enhancing inhibitory-to-inhibitory connections led to more stable temporal dynamics and improved task performance. Finally, we show that a network with such microcircuitry can perform other tasks without disrupting its pre-existing timescale architecture, suggesting that strong inhibitory signaling underlies a flexible WM network.","url":"https://doi.org/10.1101/2020.02.11.944751","authors":["Robert Kim","Terrence J. Sejnowski"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-02-13T02:05:12Z","doi":"10.1101/2020.02.11.944751","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.32470/ccn.2022.1220-0","name":"Exploring the Plasticity-Stability Trade-Off in Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.32470/ccn.2022.1220-0","authors":["Nicholas Soures","Dhireesha Kudithipudi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-08-15T15:19:59Z","doi":"10.32470/ccn.2022.1220-0","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1109/cec.2010.5586035","name":"A spiking neural representation for XCSF","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cec.2010.5586035","authors":["Gerard Howard","Larry Bull","Pier-Luca Lanzi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-09-29T19:54:29Z","doi":"10.1109/cec.2010.5586035","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1109/iscas58744.2024.10558057","name":"Investigation of Influence of APCMA-based Wireless Communication on Neural Computation in Wireless Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas58744.2024.10558057","authors":["Naoki Wakamiya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-02T17:22:52Z","doi":"10.1109/iscas58744.2024.10558057","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.5256/f1000research.196566.r474649","name":"Peer Review Report For: Measuring Neural Network Similarity [version 1; peer review: 2 approved with reservations]","source":"crossref","abstract":"","url":"https://doi.org/10.5256/f1000research.196566.r474649","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-12T04:01:08Z","doi":"10.5256/f1000research.196566.r474649","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.52202/085713-1661","name":"A Scalable, Causal, and Energy Efficient Framework for Neural Decoding with Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.52202/085713-1661","authors":["Georgios Mentzelopoulos","Ioannis Asmanis","Konrad Kording","Eva L Dyer","Kostas Daniilidis","Flavia Vitale"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-06T14:44:29Z","doi":"10.52202/085713-1661","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1016/s0893-6080(01)00046-6","name":"Regularization mechanisms of spiking–bursting neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1016/s0893-6080(01)00046-6","authors":["P Varona","J.J Torres","R Huerta","H.D.I Abarbanel","M.I Rabinovich"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-10-14T18:58:33Z","doi":"10.1016/s0893-6080(01)00046-6","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1109/wacv48630.2021.00400","name":"Spike-Thrift: Towards Energy-Efficient Deep Spiking Neural Networks by Limiting Spiking Activity via Attention-Guided Compression","source":"crossref","abstract":"","url":"https://doi.org/10.1109/wacv48630.2021.00400","authors":["Souvik Kundu","Gourav Datta","Massoud Pedram","Peter A. Beerel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-06-14T16:34:13Z","doi":"10.1109/wacv48630.2021.00400","addedAt":"2026-09-01T01:48:28.364Z","updatedAt":"2026-09-01T01:48:28.364Z"},{"id":"doi:10.1007/978-981-96-0706-8_9","name":"Multivariate Inverse Artificial Neural Network as an Optimization Tool to Improve the Performance of Energy Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-96-0706-8_9","authors":["O. May Tzuc","M. Jiménez Torres","Román A. Canul-Turriza","Karla M. Aguilar-Castro","E. V. Macias-Melo","Rasikh Tariq"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-19T13:37:03Z","doi":"10.1007/978-981-96-0706-8_9","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-031-27499-2_11","name":"A Novel Approach to the Two-Dimensional Cargo Load Problem","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_11","authors":["Francisco Mateus","André S. Santos","Marlene F. Brito","Ana M. Madureira"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_11","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-031-78946-5_24","name":"Subjective Question Bank Generation Using Large Language Models with Custom Knowledge Base","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_24","authors":["Amaan Sayed","Mahendra Kanojia","Subhashish Nabajja"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:03:45Z","doi":"10.1007/978-3-031-78946-5_24","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-030-96299-9_76","name":"Automated Fingerprint Biometric System for Crime Record Management","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_76","authors":["Muyideen AbdulRaheem","Sanjay Misra","Joseph Bamidele Awotunde","Idowu Dauda Oladipo","Jonathan Oluranti"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_76","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-030-96299-9_15","name":"REGION: Relevant Entropy Graph spatIO-temporal convolutional Network for Pedestrian Trajectory Prediction","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_15","authors":["Naiyao Wang","Yukun Wang","Changdong Zhou","Ajith Abraham","Hongbo Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_15","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-030-96299-9_3","name":"Tamilnadu Omnibus Travels Evaluation Using TOPSIS and Fuzzy TOPSIS Methods","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_3","authors":["S. M. Vadivel","A. H. Sequeira","Sunil Kumar Jauhar","V. Chandana"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_3","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1142/9789813143180_fmatter","name":"FRONT MATTER","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789813143180_fmatter","authors":["Tao Song","Pan Zheng","Mou Ling Dennis Wong","Xun Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-04-08T09:29:16Z","doi":"10.1142/9789813143180_fmatter","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.15412/j.jbtw.01070104","name":"A Review of Bio Inspired Computing and its Applications","source":"crossref","abstract":"","url":"https://doi.org/10.15412/j.jbtw.01070104","authors":["B Suresh kumar","Deepshikha Bhargava"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-08-06T04:13:56Z","doi":"10.15412/j.jbtw.01070104","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/aiid51893.2021.9456483","name":"Neuromorphic Brain-Inspired Computing with Hybrid Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aiid51893.2021.9456483","authors":["Zongyuan Cai","Xinze Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-06-23T19:56:26Z","doi":"10.1109/aiid51893.2021.9456483","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.4108/icst.collaboratecom.2012.250508","name":"Biologically-inspired Network “Memory” for Smarter Networking","source":"crossref","abstract":"","url":"https://doi.org/10.4108/icst.collaboratecom.2012.250508","authors":["Bassem Mokhtar","Mohamed Eltoweissy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-02-14T10:59:46Z","doi":"10.4108/icst.collaboratecom.2012.250508","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch020","name":"Evolutionary Modeling and Industrial Structure Emergence","source":"crossref","abstract":"In the first part of the chapter, an outline of the evolutionary model of industrial dynamics is presented. The second part deals with a simulation study of the model focused on identification of necessary conditions for emergence of different industrial strictures. Textbooks of traditional economics distinguish four typical industry structures and study them under the names of pure competition, pure monopoly, oligopoly, and monopolistic competition. Variations in behavior modes of differently concentrated industries ought to be an outcome of the cooperation of well-understood evolutionary mechanisms, and not the result of juggling differently placed curves representing supply, demand, marginal revenue, marginal cost, average costs, and so forth. Textbook analysis of industrial structures usually omits influence of innovation on market behavior. Evolutionary approach and simulation allow for such analysis and through that allow enriching the industrial development study. One of the important conclusions from this chapter is that evolutionary analysis may be considered as a very useful and complementary tool to teach economics.","url":"https://doi.org/10.4018/978-1-59140-984-7.ch020","authors":["H. Kwasnicka","W. Kwasnicki"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch020","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/ngct.2015.7375264","name":"Multi-criteria website optimization using multi-objective quantum inspired genetic algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ngct.2015.7375264","authors":["Kumar Dilip"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-01-11T21:45:13Z","doi":"10.1109/ngct.2015.7375264","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.4018/978-1-60566-054-7.ch236","name":"A Bio-Inspired Approach for the Next Generation of Cellular Systems","source":"crossref","abstract":"In the current 3G systems and the upcoming 4G wireless systems, missing neighbor pilot refers to the condition of receiving a high-level pilot signal from a Base Station (BS) that is not listed in the mobile receiver’s neighbor list (LCC International, 2004; Agilent Technologies, 2005). This pilot signal interferes with the existing ongoing call, causing the call to be possibly dropped and increasing the handoff call dropping probability. Figure 1 describes the missing pilot scenario where BS1 provides the highest pilot signal compared to BS1 and BS2’s signals. Unfortunately, this pilot is not listed in the mobile user’s active list. The horizontal and vertical handoff algorithms are based on continuous measurements made by the user equipment (UE) on the Primary Scrambling Code of the Common Pilot Channel (CPICH). In 3G systems, UE attempts to measure the quality of all received CPICH pilots using the Ec/Io and picks a dominant one from a cellular system (Chiung &amp; Wu, 2001; El-Said, Kumar, &amp; Elmaghraby, 2003). The UE interacts with any of the available radio access networks based on its memorization to the neighboring BSs. As the UE moves throughout the network, the serving BS must constantly update it with neighbor lists, which tell the UE which CPICH pilots it should be measuring for handoff purposes. In 4G systems, CPICH pilots would be generated from any wireless system including the 3G systems (Bhashyam, Sayeed, &amp; Aazhang, 2000). Due to the complex heterogeneity of the 4G radio access network environment, the UE is expected to suffer from various carrier interoperability problems. Among these problems, the missing neighbor pilot is considered to be the most dangerous one that faces the 4G industry. The wireless industry responded to this problem by using an inefficient traditional solution relying on using antenna downtilt such as given in Figure 2. This solution requires shifting the antenna’s radiation pattern using a mechanical adjustment, which is very expensive for the cellular carrier. In addition, this solution is permanent and is not adaptive to the cellular network status (Agilent Technologies, 2005; Metawave, 2005).","url":"https://doi.org/10.4018/978-1-60566-054-7.ch236","authors":["Mostafa El-Said"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:44:10Z","doi":"10.4018/978-1-60566-054-7.ch236","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-031-78946-5_11","name":"Wearable Devices for Long-Term Care – Survey and Opportunities","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_11","authors":["Sudip Phuyal","Luís B. Elvas","João C. Ferreira","Rabindra Bista"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:03:28Z","doi":"10.1007/978-3-031-78946-5_11","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-031-27499-2_17","name":"Automatic Diagnosis Framework for Catheters and Tubes Semantic Segmentation and Placement Errors Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_17","authors":["Abdelfettah Elaanba","Mohammed Ridouani","Larbi Hassouni"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_17","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-031-78946-5_33","name":"Impact of Contextual Factors on Adaptive Performance: A Study on Indian PSBs Using ANN Analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_33","authors":["Deeksha Sanjay Shetty","K. R. Suprabha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:03:59Z","doi":"10.1007/978-3-031-78946-5_33","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-030-96299-9_72","name":"Fish Control Process and Traceability for Value Creation Using Blockchain Technology","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_72","authors":["Joao C. Ferreira","Ana Lucia Martins","Ulpan Tokkozhina","Berit Irene Helgheim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_72","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-031-78946-5_12","name":"Gamification System for Eco-Driving: Enhancing Driver Motivation and Fuel Savings Through Game Mechanics","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_12","authors":["Adriana Franco","Daniel Cale","Joao C. Ferreira"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:03:54Z","doi":"10.1007/978-3-031-78946-5_12","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/aici.2009.199","name":"Neuro-computing Method for Data Mining","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aici.2009.199","authors":["Jui-Yu Wu","Chi-Jie Lu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-20T20:12:00Z","doi":"10.1109/aici.2009.199","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-540-92191-2","name":"Bio-Inspired Computing and Communication","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-540-92191-2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-11-26T16:08:36Z","doi":"10.1007/978-3-540-92191-2","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1016/j.pmcj.2021.101481","name":"Secure D2D caching framework inspired on trust management and blockchain for Mobile Edge Caching","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.pmcj.2021.101481","authors":["Acquila Santos Rocha","Billy Anderson Pinheiro","Vinicius C.M. Borges"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-10-19T05:28:27Z","doi":"10.1016/j.pmcj.2021.101481","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1016/j.asoc.2019.04.006","name":"Bio-inspired voice evaluation mechanism","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2019.04.006","authors":["Dawid Połap","Marcin Woźniak","Robertas Damaševičius","Rytis Maskeliūnas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-04-12T11:46:17Z","doi":"10.1016/j.asoc.2019.04.006","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-030-37218-7_19","name":"Cross Modal Retrieval for Different Modalities in Multimedia","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_19","authors":["T. J. Osheen","Linda Sara Mathew"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T15:02:40Z","doi":"10.1007/978-3-030-37218-7_19","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-031-27499-2_72","name":"Mapping the Research in Orange Economy: A Bibliometric Analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_72","authors":["Homero Rodriguez-Insuasti","Marcelo Leon","Néstor Montalván-Burbano","Katherine Parrales-Guerrero"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_72","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-031-27499-2_50","name":"Hostel Out-Pass Implementation Using Multi Factor Authentication","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_50","authors":["Naresh Tangudu","Nagaraju Rayapati","Y. Ramesh","Panduranga Vital","K. Kavitha","G. V. L. Narayana"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_50","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-031-27499-2_59","name":"Blockchain Enabled Internet of Things: Current Scenario and Open Challenges for Future","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_59","authors":["Sanskar Srivastava","Anshu","Rohit Bansal","Gulshan Soni","Amit Kumar Tyagi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_59","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-031-78937-3_27","name":"Analysis and Detection of Breast Cancer Using Recursive Feature Elimination","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_27","authors":["G. Reddy Hemantha","V. Sai Anusha","G. Charan Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:06:38Z","doi":"10.1007/978-3-031-78937-3_27","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-030-96299-9_36","name":"A New Cascade-Hybrid Recommender System Approach for the Retail Market","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_36","authors":["Miguel Ângelo Rebelo","Duarte Coelho","Ivo Pereira","Fábio Fernandes"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_36","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/nabic.2012.6402234","name":"A system for building immunity in social networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2012.6402234","authors":["Heena Rathore","Abhay Samant"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-01-10T00:26:08Z","doi":"10.1109/nabic.2012.6402234","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/nabic.2009.5393479","name":"ACO approaches for large scale information retrieval","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393479","authors":["Habiba Drias","Moufida Rahmani","Manel Khodja"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5393479","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-030-96299-9_75","name":"Information Technology Roles and Their Most-Used Programming Languages","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_75","authors":["Oluwaseun Alexander Dada","Kehinde Aruleba","Abdullahi Abubakar Yunusa","Ismaila Temitayo Sanusi","George Obaido"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_75","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-031-78949-6_27","name":"Implementing Technology in Student-Centric Learning Environments: Prospects and Challenges","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78949-6_27","authors":["Manoj Kumar Pandey","Ashish Kumar Gupta","Rabindra Kumar Verma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T09:30:47Z","doi":"10.1007/978-3-031-78949-6_27","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-031-78940-3_3","name":"Doctors’ Handwriting Recognition Using CNN and BLSTM Models","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78940-3_3","authors":["Santosh Khanal","Rabindra Bista","Joao C. Ferreira"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-05T06:06:55Z","doi":"10.1007/978-3-031-78940-3_3","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-031-78946-5_46","name":"Analysis on 5G Wireless Technology &amp; Challenges: Massive MIMO","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_46","authors":["Pradeep Kondapalli","A. Kamala Kumari","P. Rajesh Kumar","T. Vishnu Murty"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:03:28Z","doi":"10.1007/978-3-031-78946-5_46","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-031-78949-6_2","name":"AI-Enabled Drone Technology for Disaster Management: A Review","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78949-6_2","authors":["Yogendra Narayan","S. Tarun","Tushar","Arshad Ali","Neeshu Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T09:30:31Z","doi":"10.1007/978-3-031-78949-6_2","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/nabic.2009.5393687","name":"An associative classifier using weighted association rule","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393687","authors":["Sunita Soni","Jyothi Pillai","O.P. Vyas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393687","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/nabic.2014.6921879","name":"Genetic algorithm versus memetic algorithm for association rules mining","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2014.6921879","authors":["Habiba Drias"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-10-22T16:05:41Z","doi":"10.1109/nabic.2014.6921879","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/chicc.2008.4605541","name":"A distributed approach inspired by membrane computing for optimizing bijective S-boxes","source":"crossref","abstract":"","url":"https://doi.org/10.1109/chicc.2008.4605541","authors":["Yin Xinchun","Qiu Liang","Zhang Hailing"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-08-28T15:32:51Z","doi":"10.1109/chicc.2008.4605541","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/bimnics.2007.4610086","name":"A conventional strands evaluator for DNA computations","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bimnics.2007.4610086","authors":["Filomena de Santis","Gennaro Iaccarino"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-09-08T20:06:46Z","doi":"10.1109/bimnics.2007.4610086","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/ibica.2011.49","name":"Access Control of Cloud Computing Using Rapid Face and Fingerprint Identification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ibica.2011.49","authors":["Bao Rong Chang","Hsiu-Fen Tsai","Chi-Ming Chen","Chien-Feng Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-01-06T16:44:03Z","doi":"10.1109/ibica.2011.49","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-031-78946-5_28","name":"Enhancing Epilepsy Care in Resource-Constrained Settings Through Streamlined EEG Data Analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_28","authors":["Romel Thommeykutty","Anwesh Roy","K. Asha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:03:52Z","doi":"10.1007/978-3-031-78946-5_28","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/bicta.2009.5338148","name":"0&amp;#x2013;1 Programming problem based on sticker model","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2009.5338148","authors":["Lingying Zhi","Zhi-xia Yin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-11-24T18:50:07Z","doi":"10.1109/bicta.2009.5338148","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-0-387-09655-1","name":"Biologically-Inspired Collaborative Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-0-387-09655-1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-08-19T13:40:02Z","doi":"10.1007/978-0-387-09655-1","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/s12293-015-0156-z","name":"Thematic issue on hybrid nature-inspired algorithms: concepts, analysis and applications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s12293-015-0156-z","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-02-11T08:01:23Z","doi":"10.1007/s12293-015-0156-z","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/nabic.2009.5393736","name":"General framework of Artificial Physics Optimization Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393736","authors":["Liping Xie","Jianchao Zeng","Zhihua Cui"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393736","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch044","name":"Toward an Agent-Oriented Paradigm of Information Systems","source":"crossref","abstract":"This chapter presents a meta-model of information systems as a foundation for the methodology of caste-centric agent-oriented software development, which is suitable for applications on the Internet/Web platform and the utilization of mobile computing devices. In the model, the basic elements are agents classified into a number of castes. Agents are defined as active computational entities that encapsulate: (a) a set of state variables, (b) a set of actions that the agents are capable of performing, (c) a set of behaviour rules that determine when the agents will change their states and when to take actions, and (d) a definition of their environments in which they operate. Caste is the classifier of agents and the modular unit of the systems. It serves as the template that defines the structure and behaviour properties of agents, as class does for objects. Agents can be declared statically or created dynamically at runtime as instances of castes. This chapter also illustrates the advantages of agent-oriented information systems by an example.","url":"https://doi.org/10.4018/978-1-59140-984-7.ch044","authors":["H. Zhu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch044","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1145/3320288.3320292","name":"Synaptic plasticity in an artificial Hebbian network exhibiting continuous, unsupervised, rapid learning","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3320288.3320292","authors":["J. Campbell Scott","Thomas F. Hayes","Ahmet S. Ozcan","Winfried W. Wilcke"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-08-23T12:03:10Z","doi":"10.1145/3320288.3320292","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/bfb0100528","name":"Parametric characterization of hardness profiles of steels with neuro-wavelet networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/bfb0100528","authors":["V. Colla","L. M. Reyneri","M. Sgarbi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-12-07T13:00:25Z","doi":"10.1007/bfb0100528","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-642-32615-8_61","name":"Bio-inspired Visual Information Processing – The Neuromorphic Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-32615-8_61","authors":["Woo Joon Han","Il Song Han"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-07-24T04:50:30Z","doi":"10.1007/978-3-642-32615-8_61","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-319-73347-0_1","name":"Biological Investigation of Neural Circuits in the Insect Brain","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-73347-0_1","authors":["Luca Patanè","Roland Strauss","Paolo Arena"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-20T08:24:29Z","doi":"10.1007/978-3-319-73347-0_1","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/iconstem65670.2025.11374760","name":"Bio-Inspired Neuro-Swarm Communication Protocol with Dynamic Spectrum Intelligence for IoT and UAV Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iconstem65670.2025.11374760","authors":["Thillaiyarasi S","Lincy Golda Careline S","S L Priyenga","Nansy K"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-18T21:13:43Z","doi":"10.1109/iconstem65670.2025.11374760","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-981-33-6862-0_60","name":"Artificial Intelligence and Medical Decision Support in Advanced Healthcare System","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-33-6862-0_60","authors":["Anandakumar Haldorai","Arulmurugan Ramu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-06-14T05:02:45Z","doi":"10.1007/978-981-33-6862-0_60","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-030-37218-7_62","name":"An Approach for Sentiment Analysis Using Gini Index with Random Forest Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_62","authors":["Manpreet Kaur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T20:02:40Z","doi":"10.1007/978-3-030-37218-7_62","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1016/j.procs.2015.12.194","name":"Respective Advantages and Disadvantages of Model-based and Model-free Reinforcement Learning in a Robotics Neuro-inspired Cognitive Architecture","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.procs.2015.12.194","authors":["Erwan Renaudo","Benoît Girard","Raja Chatila","Mehdi Khamassi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-23T09:49:26Z","doi":"10.1016/j.procs.2015.12.194","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/bicta.2009.5338159","name":"Solving satisfiability problems with membrane algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2009.5338159","authors":["Gexiang Zhang","Chunxiu Liu","Marian Gheorghe","Florentin Ipate"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-11-24T18:50:07Z","doi":"10.1109/bicta.2009.5338159","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1201/9781003143499-7","name":"Models of point neuronal dynamic","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003143499-7","authors":["Elishai Ezra Tsur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-07-19T12:30:34Z","doi":"10.1201/9781003143499-7","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/nabic.2009.5393655","name":"Transaction mapping based approach for mining software specifications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393655","authors":["R. Jeevarathinam","Antony Selvadoss Thanamani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393655","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.15224/978-1-63248-131-3-26","name":"Associative Memory Inspired by Antibody Dynamics","source":"crossref","abstract":"","url":"https://doi.org/10.15224/978-1-63248-131-3-26","authors":["CHUNG MING OU"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-21T08:40:06Z","doi":"10.15224/978-1-63248-131-3-26","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1201/9781003612858-8","name":"Quantum computing-based metaheuristics for medical image segmentation","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003612858-8","authors":["Ahmad Sajad Rather","Sujit Das"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-06T23:59:32Z","doi":"10.1201/9781003612858-8","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/nabic.2009.5393617","name":"An extensive review of research in swarm robotics","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393617","authors":["Yogeswaran Mohan","S. G. Ponnambalam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393617","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-642-24553-4_37","name":"Reliability of Standby Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-24553-4_37","authors":["Salvatore Distefano"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-01-03T04:49:00Z","doi":"10.1007/978-3-642-24553-4_37","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/nabic.2009.5393854","name":"Towards modeling stored-value electronic money systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393854","authors":["Shunsuke Inenaga","Kenichirou Oyama","Hiroto Yasuura"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5393854","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.3389/frobt.2015.00005","name":"Bits from Brains for Biologically Inspired Computing","source":"crossref","abstract":"","url":"https://doi.org/10.3389/frobt.2015.00005","authors":["Michael Wibral","Joseph T. Lizier","Viola Priesemann"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-03-24T17:08:25Z","doi":"10.3389/frobt.2015.00005","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/bicta.2010.5645085","name":"Analysis of protein sequence similarity","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2010.5645085","authors":["Yusen Zhang","Xiangtian Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-12-09T10:33:18Z","doi":"10.1109/bicta.2010.5645085","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.3390/electronics13234659","name":"TS-GRU: A Stock Gated Recurrent Unit Model Driven via Neuro-Inspired Computation","source":"crossref","abstract":"Existing risk measurement methods often fail to fully consider the impact of climatic conditions on stock market risk, making it difficult to capture dynamic patterns and long-term dependencies. To address these issues, we propose the TS-GRU method: this approach utilizes a temporal convolutional network (TCN) to extract underlying features from historical data, capturing key characteristics of time series data. Subsequently, a gated recurrent unit (GRU) model is employed to capture dynamic patterns and long-term dependencies within the stock market. Finally, the TS-GRU model is optimized using the Sparrow algorithm based on collective behavior, iteratively evaluating and refining model parameters to obtain improved solutions. Experimental results demonstrate the effectiveness of the TS-GRU method in providing accurate risk assessment and forecasting. This comprehensive approach takes into account carbon finance, climate change, and environmental factors, offering valuable insights to investors to help them to understand and manage investment risks in the ever-changing stock market.","url":"https://doi.org/10.3390/electronics13234659","authors":["Yuanfang Zhang","Heinz D. Fill"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-26T04:02:18Z","doi":"10.3390/electronics13234659","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-981-19-9819-5_17","name":"Comparison of Classification Method for Alzheimer’s Disease Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-19-9819-5_17","authors":["Tamchi Yani","Utpal Bhattacharjee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-07T14:02:42Z","doi":"10.1007/978-981-19-9819-5_17","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/ccgridw63211.2024.00024","name":"Design and Development of a Novel Bio-Inspired VM Placement in Green Cloud Computing Environment","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ccgridw63211.2024.00024","authors":["Nirmal Kr Biswas","Sourav Banerjee","Uttam Ghosh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-11T17:19:53Z","doi":"10.1109/ccgridw63211.2024.00024","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.4018/979-8-3693-6303-4.ch017","name":"Neuromorphic Computing","source":"crossref","abstract":"The exponential growth of data and information has stimulated technological progress in computing systems that utilize them to effectively discover patterns and produce important insights. Neural network algorithms have been applied to conventional silicon transistor-based hardware to do highly parallel computations, drawing inspiration from the structure and functions of biological synapses and neurons in the brain. Nevertheless, synapses composed of many transistors are limited to storing binary data, and the utilization of intricate silicon neuron circuits to handle these digital states poses challenges in achieving low-power and low-latency computing. This study examines the significance of developing memories and switches for synaptic and neural components in building Neuromorphic systems that can efficiently conduct cognitive tasks and recognition. This chapter closely examines and rates the latest progress in Neuromorphic computing, focusing on how these changes impact edge and Internet of Things technologies. It is also being thought about how to use tiny switches and short-term memory to copy the action of neurons. Once this is done, more Studies in many areas should be able to focus on the design, circuitry, and devices of Neuromorphic systems.","url":"https://doi.org/10.4018/979-8-3693-6303-4.ch017","authors":["Devendra G. Pandey","Yogesh Kumar Sharma","Nimish Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-29T15:16:27Z","doi":"10.4018/979-8-3693-6303-4.ch017","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/sofa.2007.4318314","name":"Real Case Study of a Neuro-Fuzzy Intelligent Car","source":"crossref","abstract":"","url":"https://doi.org/10.1109/sofa.2007.4318314","authors":["V. Lupu","C. Lupu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-09-24T14:55:02Z","doi":"10.1109/sofa.2007.4318314","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/iciict.2015.7396064","name":"A Honey Bee behaviour inspired novel Attribute-based access control using enhanced Bell-Lapadula model in cloud computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iciict.2015.7396064","authors":["B Balamurugan","N Gnana Shivitha","V Monisha","V Saranya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-02-04T16:53:47Z","doi":"10.1109/iciict.2015.7396064","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1016/j.asoc.2010.07.001","name":"Prostate boundary detection in ultrasound images using biologically-inspired spiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2010.07.001","authors":["Aboul Ella Hassanien","Hameed Al-Qaheri","El-Sayed A. El-Dahshan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-07-22T08:51:18Z","doi":"10.1016/j.asoc.2010.07.001","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-981-10-6747-1_9","name":"Segmentation of Mammograms Using a Novel Intuitionistic Possibilistic Fuzzy C-Mean Clustering Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-10-6747-1_9","authors":["Chiranji Lal Chowdhary","D. P. Acharjya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-10-04T08:25:22Z","doi":"10.1007/978-981-10-6747-1_9","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-030-37218-7_33","name":"Optimized Machine Learning Models for Diagnosis and Prediction of Hypothyroidism and Hyperthyroidism","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_33","authors":["Manoj Challa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T20:02:40Z","doi":"10.1007/978-3-030-37218-7_33","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/roman.2017.8172289","name":"NICO — Neuro-inspired companion: A developmental humanoid robot platform for multimodal interaction","source":"crossref","abstract":"","url":"https://doi.org/10.1109/roman.2017.8172289","authors":["Matthias Kerzel","Erik Strahl","Sven Magg","Nicolas Navarro-Guerrero","Stefan Heinrich","Stefan Wermter"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-12-14T17:13:46Z","doi":"10.1109/roman.2017.8172289","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-030-90708-2_6","name":"A Review of Nature-Inspired Artificial Intelligence and Machine Learning Methods for Cybersecurity Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-90708-2_6","authors":["Mais Nijim","Ayush Goyal","Avdesh Mishra","David Hicks"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-26T11:04:51Z","doi":"10.1007/978-3-030-90708-2_6","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-981-15-2133-1_16","name":"Design and Comparison of Two Evolutionary and Hybrid Neural Network Algorithms in Obtaining Dynamic Balance for Two-Legged Robots","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-15-2133-1_16","authors":["Ravi Kumar Mandava","Pandu R. Vundavilli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-03-11T18:03:41Z","doi":"10.1007/978-981-15-2133-1_16","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.5220/0001056701620169","name":"BIOSIGNAL-BASED COMPUTING BY AHL INDUCED SYNTHETIC GENE REGULATORY NETWORKS - From an in vivo Flip-Flop Implementation to Programmable Computing Agents","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0001056701620169","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-02-22T01:45:53Z","doi":"10.5220/0001056701620169","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.5220/0005913701060117","name":"A Wavelet-inspired Anomaly Detection Framework for Cloud Platforms","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0005913701060117","authors":["David O'Shea","Vincent C. Emeakaroha","John Pendlebury","Neil Cafferkey","John P. Morrison","Theo Lynn"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-05-11T11:49:05Z","doi":"10.5220/0005913701060117","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-030-33820-6_1","name":"An Efficient Classification of Tuberous Sclerosis Disease Using Nature Inspired PSO and ACO Based Optimized Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-33820-6_1","authors":["Shamim Ripon","Md. Golam Sarowar","Fahima Qasim","Shamse Tasnim Cynthia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-11-26T05:02:34Z","doi":"10.1007/978-3-030-33820-6_1","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-031-78946-5_29","name":"ASDS: Ontology Synthesis for Space Science as a Strategic Domain Using Semantics Oriented AI","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_29","authors":["Haiya Shah","Gerard Deepak","A. Santhanavijayan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:03:53Z","doi":"10.1007/978-3-031-78946-5_29","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-031-78943-4_12","name":"A Comparative Study of Optimizers on Non-pretrained CNN Models for Stray Animal Surveillance System","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78943-4_12","authors":["Sonali Chakraborty"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-03T11:08:06Z","doi":"10.1007/978-3-031-78943-4_12","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-031-78937-3_30","name":"Smart Healthcare on 5G Platform","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_30","authors":["Bura Vijay Kumar","Pothreddypally Jhansi Devi","V. Lavanya","K. Bhuvaneswari","S. Malarvizhi","Siva Durga Rao Parasa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:06:32Z","doi":"10.1007/978-3-031-78937-3_30","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1145/3517343.3517350","name":"Evaluating parameter tuning and real-time closed-loop simulation of large scale spiking networks before mapping to neuromorphic hardware: Comparing GeNN and NEST","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3517343.3517350","authors":["Felix Johannes Schmitt","Martin Paul Nawrot"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-05-04T07:28:08Z","doi":"10.1145/3517343.3517350","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/tfuzz.2020.2984201","name":"Optimizing a Neuro-Fuzzy System Based on Nature-Inspired Emperor Penguins Colony Optimization Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tfuzz.2020.2984201","authors":["Sasan Harifi","Madjid Khalilian","Javad Mohammadzadeh","Sadoullah Ebrahimnejad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-04-02T21:43:22Z","doi":"10.1109/tfuzz.2020.2984201","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-642-58930-0","name":"Computational Intelligence: Soft Computing and Fuzzy-Neuro Integration with Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-58930-0","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-06-15T19:06:59Z","doi":"10.1007/978-3-642-58930-0","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-642-58930-0_7","name":"What’s in a Fuzzy Membership Value?","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-58930-0_7","authors":["Sukhamay Kundu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-06-15T19:06:59Z","doi":"10.1007/978-3-642-58930-0_7","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-981-10-7179-9_48","name":"Hand Target Extraction of Thermal Trace Image Using Feature and Manifold Inspired by Coordination of Immune","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-10-7179-9_48","authors":["Tao Yang","Dongmei Fu","Xiaogang Li","Jintao Meng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-11-07T23:53:32Z","doi":"10.1007/978-981-10-7179-9_48","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-981-33-6773-9_8","name":"Designing Fuzzy Controllers for Frame Structures Based on Ground Motion Prediction Using Grasshopper Optimization Algorithm: A Case Study of Tabriz, Iran","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-33-6773-9_8","authors":["Mahdi Azizi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-31T12:03:02Z","doi":"10.1007/978-981-33-6773-9_8","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.47839/ijc.13.3.630","name":"THE INSTANCE SELECTION METHOD FOR NEURO-FUZZY MODEL SYNTHESIS","source":"crossref","abstract":"The problem of automation of neuro-fuzzy model synthesis on instance set is addressed. The method of instance selection for neuro-fuzzy model synthesis is proposed. It allows reducing the sample size, and decreasing the requirements to computer resources. The method also performs transformation of the original multi-dimensional coordinate set to the one-dimensional axis, which is also discretized to improve the data generalization properties. The software implementing proposed method is developed. The experiments were conducted to study the proposed method at the real problem solution. The results of experiments allow recommending proposed method for usage at practice.","url":"https://doi.org/10.47839/ijc.13.3.630","authors":["Sergey A. Subbotin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-02-28T20:10:12Z","doi":"10.47839/ijc.13.3.630","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1201/9781003143499-6","name":"Biological description of neuronal dynamics","source":"crossref","abstract":"Neuronal models are the backbone of neuromorphic engineering. They span a wide range of complexities, trying to maintain the delicate balance between bio-plausibility and model tractability. This chapter will discuss the fundamentals of the scientist s perspective on neuromorphic engineering emphasizing the biological description of neuronal dynamics. The main aim of this chapter is to provide the necessary background to comprehensively understand the followed electrical and mathematical descriptions. The chapter will present a useful way to coarsely grasp some biological details which can later be utilized to design large-scale neuronal simulations and electrical implementations.","url":"https://doi.org/10.1201/9781003143499-6","authors":["Elishai Ezra Tsur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-07-19T12:30:34Z","doi":"10.1201/9781003143499-6","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1149/ma2024-01573021mtgabs","name":"(Invited) Bio-Inspired Time Varying Networks for Novel Computing Primitives","source":"crossref","abstract":"As a result of a hundred million years of evolution, living animals have adapted extremely well to their ecological niche. Such adaptation implies species-specific interactions with their immediate environment by processing sensory cues and responding with appropriate behavior. Understanding how living creatures perform pattern recognition and cognitive tasks is of particular importance for computing architectures: by studying these information pathways refined over eons of evolution, researchers may be able to streamline the process of developing more highly advanced, energy efficient autonomous systems. With the advent of novel electronic and ionic components along with a deeper understanding of information pathways in living species, a plethora of opportunities to develop completely novel information processing avenues are within reach. Basal biological principles are highlighted, including phylogenies, ontogenesis, and homeostasis, with particular emphasis on network topology and dynamics. While in machine learning, system training is performed on virgin networks without any a priori knowledge, the approach proposed here distinguishes itself unambiguously by employing growth mechanisms as a guideline to design novel computing architectures. Within this framework, experiments on low-frequency relaxation type oscillators coupled via complex time-varying networks will be presents. The spatio-temporal development of the network results from a mutual interaction between the oscillator ensemble and the network structure. The blooming and pruning of suddenly appearing conductive bridges and their relation to the synchrony state of the oscillator ensemble will be discussed.","url":"https://doi.org/10.1149/ma2024-01573021mtgabs","authors":["Hermann Kohlstedt"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-19T15:54:01Z","doi":"10.1149/ma2024-01573021mtgabs","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1145/1774088.1774514","name":"Chemical-inspired self-composition of competing services","source":"crossref","abstract":"","url":"https://doi.org/10.1145/1774088.1774514","authors":["Mirko Viroli","Matteo Casadei"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-04-27T12:45:48Z","doi":"10.1145/1774088.1774514","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/nabic.2011.6089655","name":"Lip print recognition based on DTW algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2011.6089655","authors":["Lukasz Smacki","Krzysztof Wrobel","Piotr Porwik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-12-06T21:02:25Z","doi":"10.1109/nabic.2011.6089655","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1201/9781315153797-2","name":"Multilevel Thresholding for Image Segmentation Using Cricket Chirping Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781315153797-2","authors":["S. Siva Sathya","Jonti Deuri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-19T10:43:32Z","doi":"10.1201/9781315153797-2","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.3844/jcssp.2013.264.270","name":"MEMBRANE COMPUTING INSPIRED GENETIC ALGORITHM ON MULTI-CORE PROCESSORS","source":"crossref","abstract":"","url":"https://doi.org/10.3844/jcssp.2013.264.270","authors":["Maroosi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-10-10T15:39:40Z","doi":"10.3844/jcssp.2013.264.270","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch039","name":"Applications of Neural Networks in Supply Chain Management","source":"crossref","abstract":"This chapter focuses on significant applications of self-organizing maps (SOMs), that is, unsupervised learning neural networks in two supply chain applications: cellular manufacturing and real-time management of a delayed delivery vehicle. Both problems require drastic complexity reduction, which is addressed effectively by clustering using SOMs. In the first problem, we cluster machines into cells and we use Latent Semantic Indexing for effective training of the network. In the second problem, we group the distribution sites into clusters based on their geographical location. The available vehicle time is distributed to each cluster by solving an appropriate non-linear optimization problem. Within each cluster an established orienteering heuristic is used to determine the clients to be served and the vehicle route. Extensive experimental results indicate that in terms of solution quality, our approach in general outperforms previously proposed methods. Furthermore, the proposed techniques are more efficient, especially in cases involving large numbers of data points. Neural networks have and will continue to play a significant role in solving effectively complex problems in supply chain applications, some of which are also highlighted in this chapter.","url":"https://doi.org/10.4018/978-1-59140-984-7.ch039","authors":["I. Minis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch039","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-319-76354-5_29","name":"Scalable and Dynamic Network Intrusion Detection and Prevention System","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-76354-5_29","authors":["Safaa Mahrach","Oussama Mjihil","Abdelkrim Haqiq"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-09T06:43:48Z","doi":"10.1007/978-3-319-76354-5_29","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-981-10-6875-1_21","name":"A Study on Some Aspects of Biologically Inspired Multi-agent Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-10-6875-1_21","authors":["Gautam Mitra","Susmita Bandyopadhyay"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-12-21T16:07:11Z","doi":"10.1007/978-981-10-6875-1_21","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-540-89619-7_15","name":"GA Inspired Heuristic for Uncapacitated Single Allocation Hub Location Problem","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-540-89619-7_15","authors":["Vladimir Filipović","Jozef Kratica","Dušan Tošić","Djordje Dugošija"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-09-28T22:53:53Z","doi":"10.1007/978-3-540-89619-7_15","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-981-10-6747-1_23","name":"A Comparative Study on Decision-Making Capability Between Human and Artificial Intelligence","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-10-6747-1_23","authors":["Soham Banerjee","Pradeep Kumar Singh","Jaya Bajpai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-10-04T04:25:22Z","doi":"10.1007/978-981-10-6747-1_23","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/bic-ta.2011.2","name":"Parallel Communicating Graph Grammar","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bic-ta.2011.2","authors":["S. Jeya Bharathi","M. Saravana Vadivu","K. Thiagarajan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-10-18T11:35:51Z","doi":"10.1109/bic-ta.2011.2","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.37965/jait.2024.0543","name":"Cognitive-Inspired Computational Computing for Intelligent Health Informatics","source":"crossref","abstract":"","url":"https://doi.org/10.37965/jait.2024.0543","authors":["Chinmay Chakraborty","Gabriella Casalino","Guangjie Han"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-22T13:30:05Z","doi":"10.37965/jait.2024.0543","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-7908-1775-1","name":"Biologically Inspired Robot Behavior Engineering","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-7908-1775-1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-05-02T10:32:50Z","doi":"10.1007/978-3-7908-1775-1","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/isorc65339.2025.00048","name":"Bio-Inspired Coordination for Measurement Timing in Sensor Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isorc65339.2025.00048","authors":["Takashi Ikegami","Ichiro Satoh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-29T17:50:47Z","doi":"10.1109/isorc65339.2025.00048","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/nabic.2009.5393870","name":"A novel clustering based niching EDA for protein folding","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393870","authors":["Benhui Chen","Jinglu Hu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393870","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-642-34274-5_38","name":"Insertion Cognitive Architecture","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-34274-5_38","authors":["Alexander Letichevsky"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-09-30T13:21:47Z","doi":"10.1007/978-3-642-34274-5_38","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.4018/978-1-4666-0942-6.ch018","name":"Getting Closer to Nature","source":"crossref","abstract":"The term bio art has emerged in the past few years to cover the kind of art that seems to come from the biology lab, with simulations of life forms through generative processes, with data taken from organisms, or even through organisms themselves. This is often at the micro level, invisible to the naked eye, where seeing requires some degree of computer modeling. This could be a hybrid form, serving the interests of both art and science, but recent exhibitions have prompted some debate about the divergent roles of art and science. Rob Kesseler and Andrew Carnie are artists who have worked alongside biologists to produce visual works of extraordinary quality, in both their decorative and intellectual aspects. They follow in a long tradition of artists who have been fascinated by the close-up detail. Drawing manuals of a hundred years ago advocated the study of plant forms, sometimes as the basis for pattern design. The author describes his own use of scientific sources, arguing that there is also a place for art that evokes the wonders of nature without being tied to the visible facts.","url":"https://doi.org/10.4018/978-1-4666-0942-6.ch018","authors":["James Faure Walker"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-03-22T13:17:45Z","doi":"10.4018/978-1-4666-0942-6.ch018","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-031-27499-2_47","name":"Comparative Analysis of Learning Models in Depression Detection Using MRI Image Data","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_47","authors":["S. Mano Venkat","C. Rajendra","K. Venu Madhav"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_47","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-031-78937-3_13","name":"Skin Cancer Detection and Classification Using Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_13","authors":["Davinder Paul Singh","Asheesh Pandey","Ajay Prakash Pasupulla","Mandeep Kaur Ghumman","Sandeep Gupta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:07:14Z","doi":"10.1007/978-3-031-78937-3_13","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-031-78949-6_4","name":"Comprehensive Blockchain-Based Cross-Platform Application For Roadside Assistance","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78949-6_4","authors":["Vinayak Somvanshi","Gandharvi Walavekar","Kevin Thakkar","Yogesh Kumbhar","Neha Deshmukh","Kiran Deshpande"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T09:29:50Z","doi":"10.1007/978-3-031-78949-6_4","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-031-78943-4_31","name":"Representation of Water Quality Through Geospatial Technique in and Around Pulivendula Area","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78943-4_31","authors":["Manisha Pendlimarri","A. Kalpana","K. Sesha Maheswaramma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-03T11:07:49Z","doi":"10.1007/978-3-031-78943-4_31","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-031-27499-2_39","name":"DRHTG: A Knowledge-Centric Approach for Document Retrieval Based on Heterogeneous Entity Tree Generation and RDF Mapping","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_39","authors":["M. Arulmozhi Varman","Gerard Deepak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_39","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-030-96299-9_31","name":"Detection of Fake Reviews on Online Products Using Machine Learning Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_31","authors":["H. Muthu Krishnan","J. Preetha","S. P. Shona","A. Sivakami"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_31","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-031-78937-3_22","name":"Early Detection and Prediction of Pneumonia Disease Using VGG16 Deep Learning Technique","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78937-3_22","authors":["N. Arfa Taj","Jessin George","Jissy Thomas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T10:05:35Z","doi":"10.1007/978-3-031-78937-3_22","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-030-96299-9_12","name":"Production Scheduling Using Multi-objective Optimization and Cluster Approaches","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_12","authors":["Beatriz Flamia Azevedo","Maria Leonilde R. Varela","Ana I. Pereira"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_12","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.47839/ijc.16.1.869","name":"FAST MEDICAL DIAGNOSTICS USING AUTOASSOCIATIVE NEURO-FUZZY MEMORY","source":"crossref","abstract":"This paper proposes an architecture of fast medical diagnostics system based on autoassociative neuro-fuzzy memory. The architecture of proposed system is close to traditional Takagi-Sugeno-Kang neuro-fuzzy system, but it is based on other principles. This system contains of recording subsystem and pattern retrieval subsystem, where diagnostics of patients with unknown diagnoses is realized. Level of memberships for all other possible diagnoses from recording subsystem is determined too. System tuning is based on lazy learning procedure and “neurons in data points” principle and uses bell-shaped fuzzy basis functions. Number of these functions changes during training process using principles of evolving connectionist systems. Bell-shaped membership functions centers can be tuned using proposed algorithm, processes of accumulation patients in fundamental memory and patients retrieval are described. This hybrid neuro-fuzzy associative memory combines advantages of fuzzy inference systems, artificial neural networks and evolving systems and its using provides the increasing of autoassociative memories capacity without essential complication of its architecture for medical diagnostics tasks.","url":"https://doi.org/10.47839/ijc.16.1.869","authors":["Iryna Perova","Yevgeniy Bodyanskiy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-02-28T19:51:57Z","doi":"10.47839/ijc.16.1.869","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.4018/978-1-5225-5020-4.ch001","name":"Application of Natural-Inspired Paradigms on System Identification","source":"crossref","abstract":"In this chapter, the application of nature-inspired paradigms on system identification is discussed. A review of the recent applications of techniques such as genetic algorithms, genetic programming, immuno-inspired algorithms, and particle swarm optimization to the system identification is presented, discussing the application to linear, nonlinear, time invariant, time variant, monovariable, and multivariable cases. Then the application of an immuno-inspired algorithm to solve the linear time variant multivariable system identification problem is detailed with examples and comparisons to other methods. Finally, the future directions of the application of nature-inspired paradigms to the system identification problem are discussed, followed by the chapter conclusions.","url":"https://doi.org/10.4018/978-1-5225-5020-4.ch001","authors":["Mateus Giesbrecht","Celso Pascoli Bottura"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-07T10:20:59Z","doi":"10.4018/978-1-5225-5020-4.ch001","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-1-4471-3744-3_6","name":"TACDSS: Adaptation Using a Hybrid Neuro-Fuzzy System","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4471-3744-3_6","authors":["Cong Tran","Ajith Abraham","Lakhmi Jain"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-02-20T20:24:19Z","doi":"10.1007/978-1-4471-3744-3_6","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1038/nature.2016.19672","name":"Flagship brain project releases neuro-computing tools","source":"crossref","abstract":"","url":"https://doi.org/10.1038/nature.2016.19672","authors":["Quirin Schiermeier","Alison Abbott"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-03-31T13:22:03Z","doi":"10.1038/nature.2016.19672","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-7908-1902-1_84","name":"A Neural Network Equivalent to a Neuro-Fuzzy System for Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-7908-1902-1_84","authors":["Danuta Rutkowska"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-03-10T20:11:40Z","doi":"10.1007/978-3-7908-1902-1_84","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-319-50920-4_8","name":"Nature-inspired Algorithm-based Optimization for Beamforming of Linear Antenna Array System","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-50920-4_8","authors":["Gopi Ram","Durbadal Mandal","S. P. Ghoshal","Rajib Kar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-03-08T06:42:10Z","doi":"10.1007/978-3-319-50920-4_8","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-642-58930-0_10","name":"Fuzzy Inference Systems: A Critical Review","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-58930-0_10","authors":["Vladimir Cherkassky"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-06-15T23:06:59Z","doi":"10.1007/978-3-642-58930-0_10","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.2172/1856292","name":"Platform-Agnostic Neural Algorithm Composition using Fugu.","source":"crossref","abstract":"","url":"https://doi.org/10.2172/1856292","authors":["William Severa","James Aimone","Craig Vineyard","Srideep Musuvathy","Yang Ho","Zubin Kane","Leah Reeder"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-26T02:18:47Z","doi":"10.2172/1856292","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-981-16-3128-3_7","name":"Reconfiguration of Electric Power Distribution Networks: A Typical Application of Metaheuristics in Electrical Power Field","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-16-3128-3_7","authors":["H. Takano","J. Murata","H. Asano","N. D. Tuyen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-18T23:09:33Z","doi":"10.1007/978-981-16-3128-3_7","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1080/23746149.2021.1894234","name":"Neuromorphic nanowire networks: principles, progress and future prospects for neuro-inspired information processing","source":"crossref","abstract":"","url":"https://doi.org/10.1080/23746149.2021.1894234","authors":["Zdenka Kuncic","Tomonobu Nakayama"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-18T09:21:08Z","doi":"10.1080/23746149.2021.1894234","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-7908-1853-6","name":"Fuzzy and Neuro-Fuzzy Intelligent Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-7908-1853-6","authors":["Ernest Czogała","Jacek Łęski"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-08-09T22:07:04Z","doi":"10.1007/978-3-7908-1853-6","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1016/j.aci.2015.06.001","name":"A Genetic-Neuro-Fuzzy inferential model for diagnosis of tuberculosis","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.aci.2015.06.001","authors":["Mumini Olatunji Omisore","Oluwarotimi Williams Samuel","Edafe John Atajeromavwo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-06-24T21:37:41Z","doi":"10.1016/j.aci.2015.06.001","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.4018/978-1-61520-753-4.ch012","name":"Neuro Linguistic Programming","source":"crossref","abstract":"The power of computers is now beginning to be exploited in subjective areas of human study like those related to human psychology in order to make the interaction between humans and computers more natural. An effective interaction must involve automatic analysis of human behavior by the computer, and responding to it. Neuro-Linguistic Programming was developed, drawing its inspiration from the computer programs, so as to change the perception of the human brain to a more successful behavior. In addition to that, Neuro Linguistic Programming gave an algorithmic approach to ‘observe’ and analyze human behavior, both verbal and non-verbal, and serve to effectively perceive the human behavior and interaction. The interaction is a more deep rooted cognitive interaction. With the use of Neuro Linguistic Programming and the fundamentals of cybernetics, the humans and computer can be brought closer, with automatic transfer of valuable information between the two. This chapter describes the fundamentals of Neuro Linguistic Programming and aims at developing a hypothetical model on how Neuro Linguistic Programming can be used to better understand the interaction between the humans and the computers.","url":"https://doi.org/10.4018/978-1-61520-753-4.ch012","authors":["Ankur Choubey","Ramesh Singh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:21:41Z","doi":"10.4018/978-1-61520-753-4.ch012","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.5121/ijccsa.2016.6102","name":"Neuro-Fuzzy System Based Dynamic Resource Allocation in Collaborative Cloud Computing Using Multi Attribute QOS","source":"crossref","abstract":"","url":"https://doi.org/10.5121/ijccsa.2016.6102","authors":["Anirban Basu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-03-10T01:20:10Z","doi":"10.5121/ijccsa.2016.6102","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.35490/ec3.2026.427","name":"Neuro-Symbolic Reinforcement Learning for Multi-Category Construction Relationship with Reasoning and Sequence Planning","source":"crossref","abstract":"","url":"https://doi.org/10.35490/ec3.2026.427","authors":["Akarsth Kumar Singh","Shang-Hsien Hsieh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-10T11:55:47Z","doi":"10.35490/ec3.2026.427","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-642-58930-0_2","name":"Computational Intelligence Defined - By Everyone !","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-58930-0_2","authors":["James C. Bezdek"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-06-15T19:06:59Z","doi":"10.1007/978-3-642-58930-0_2","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/s00500-005-0486-8","name":"Descriptor vector redesign by neuro-fuzzy analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00500-005-0486-8","authors":["J. Paetz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-04-28T08:01:44Z","doi":"10.1007/s00500-005-0486-8","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-981-15-0306-1_9","name":"Plant Biology-Inspired Genetic Algorithm: Superior Efficiency to Firefly Optimizer","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-15-0306-1_9","authors":["Neeraj Gupta","Mahdi Khosravy","Om Prakash Mahela","Nilesh Patel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-11-09T12:03:08Z","doi":"10.1007/978-981-15-0306-1_9","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.4018/978-1-5225-2128-0.ch015","name":"Quantum-Inspired Computational Intelligence for Economic Emission Dispatch Problem","source":"crossref","abstract":"Economic emission dispatch (EED) problems are one of the most crucial problems in power systems. Growing energy demand, limited reserves of fossil fuel and global warming make this topic into the center of discussion and research. In this chapter, we will discuss the use and scope of different quantum inspired computational intelligence (QCI) methods for solving EED problems. We will evaluate each previously used QCI methods for EED problem and discuss their superiority and credibility against other methods. We will also discuss the potentiality of using other quantum inspired CI methods like quantum bat algorithm (QBA), quantum cuckoo search (QCS), and quantum teaching and learning based optimization (QTLBO) technique for further development in this area.","url":"https://doi.org/10.4018/978-1-5225-2128-0.ch015","authors":["Fahad Parvez Mahdi","Pandian Vasant","Vish Kallimani","M. Abdullah-Al-Wadud","Junzo Watada"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-03-10T08:19:51Z","doi":"10.4018/978-1-5225-2128-0.ch015","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-642-00563-3_27","name":"Simplification of Neuro-Fuzzy Models","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-00563-3_27","authors":["Krzysztof Simiński"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-12-30T18:11:20Z","doi":"10.1007/978-3-642-00563-3_27","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-540-38233-1_8","name":"Application of Neuro-Fuzzy Methods for Noise Filtering, Noise Detection and Edge Extraction in Digital Images Corrupted by Impulse Noise","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-540-38233-1_8","authors":["Emin Yüksel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-06-23T07:59:08Z","doi":"10.1007/978-3-540-38233-1_8","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1016/j.asoc.2006.10.001","name":"Neuro fuzzy schemes for fault detection in power transformer","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2006.10.001","authors":["V. Duraisamy","N. Devarajan","D. Somasundareswari","A. Antony Maria Vasanth","S.N. Sivanandam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-11-22T15:10:04Z","doi":"10.1016/j.asoc.2006.10.001","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1016/j.asoc.2020.106400","name":"Neuro-fuzzy system dynamics technique for modeling construction systems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2020.106400","authors":["Nima Gerami Seresht","Aminah Robinson Fayek"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-05-17T10:01:57Z","doi":"10.1016/j.asoc.2020.106400","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-7908-1768-3_13","name":"Neuro-fuzzy Filtering Techniques for the Analysis of Complex Acoustic Scenarios","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-7908-1768-3_13","authors":["Rinaldo Poluzzzi","Alberto Savi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-03-10T20:11:43Z","doi":"10.1007/978-3-7908-1768-3_13","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/nafips.1996.534755","name":"A neuro-fuzzy computing model of human pattern generation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nafips.1996.534755","authors":["Y. Hata","M.A. Lee","K. Yamato"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-12-23T23:52:33Z","doi":"10.1109/nafips.1996.534755","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/icicic.2008.384","name":"New Basic Theory on Quantum Neuro-Computation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icicic.2008.384","authors":["Hiroyuki Matsuura","Masahiro Nakano"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-03-08T09:44:47Z","doi":"10.1109/icicic.2008.384","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/iadcc.2014.6779505","name":"Neuro-fuzzy ensembler for cognitive states classification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iadcc.2014.6779505","authors":["Shantipriya Parida","Satchidananda Dehuri","Sung-Bae Cho"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-04-08T21:56:13Z","doi":"10.1109/iadcc.2014.6779505","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1142/9789814619998_0016","name":"USING DUAL-ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM IN PILOT'S RISK ASSESSMENT","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789814619998_0016","authors":["KAIJUN XU"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-21T10:11:35Z","doi":"10.1142/9789814619998_0016","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/tcsi.2020.3037028","name":"A Hardware-Friendly Approach Towards Sparse Neural Networks Based on LFSR-Generated Pseudo-Random Sequences","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tcsi.2020.3037028","authors":["Foroozan Karimzadeh","Ningyuan Cao","Brian Crafton","Justin Romberg","Arijit Raychowdhury"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-11-20T04:40:25Z","doi":"10.1109/tcsi.2020.3037028","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-030-37218-7_142","name":"Detection and Removal of RainDrop from Images Using DeepLearning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_142","authors":["Y. Himabindu","R. Manjusha","Latha Parameswaran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T20:02:40Z","doi":"10.1007/978-3-030-37218-7_142","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/smartworld-uic-atc-scalcom-iop-sci.2019.00187","name":"A New Image Classification Architecture Inspired by Working Memory","source":"crossref","abstract":"","url":"https://doi.org/10.1109/smartworld-uic-atc-scalcom-iop-sci.2019.00187","authors":["Jiahui Shen","Ji Xiang","Nan Mu","Lei Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-04-09T23:03:00Z","doi":"10.1109/smartworld-uic-atc-scalcom-iop-sci.2019.00187","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.4018/979-8-3373-8988-2.ch010","name":"Bridging Human Thought and Machine Intelligence","source":"crossref","abstract":"Artificial intelligence has achieved significant progress in perception and prediction, yet many contemporary systems remain limited in interpretability, contextual reasoning, and alignment with human cognition. This chapter advances the concept of cognitive aligned neuro symbolic AI systems as a framework for bridging human thought and machine intelligence in dynamic environments. By integrating neural learning mechanisms with structured symbolic reasoning, these systems combine adaptive perception with transparent inference and explicit knowledge representation. Drawing from cognitive science and systems theory, the chapter proposes that meaningful AI advancement requires architectural alignment with core human cognitive processes, including contextual judgment, memory integration, and reflective reasoning. The discussion conceptualizes how such systems operate under uncertainty, support human centered collaboration, and contribute to trustworthy and responsible AI development.","url":"https://doi.org/10.4018/979-8-3373-8988-2.ch010","authors":["Rubee Singh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-07T14:49:21Z","doi":"10.4018/979-8-3373-8988-2.ch010","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/sofa.2007.4318312","name":"Neuro-Fuzzy System for Intelligent Course Control of Underactuated Conventional Ships","source":"crossref","abstract":"","url":"https://doi.org/10.1109/sofa.2007.4318312","authors":["Viorel Nicolau"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-09-24T18:55:02Z","doi":"10.1109/sofa.2007.4318312","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-981-13-0761-4_96","name":"Fibonacci Series-Inspired Local Search in Artificial Bee Colony Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-13-0761-4_96","authors":["Nirmala Sharma","Harish Sharma","Ajay Sharma","Jagdish Chand Bansal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-08-23T06:28:55Z","doi":"10.1007/978-981-13-0761-4_96","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/biocas58349.2023.10388601","name":"A Standard-Cell-Based Neuro-Inspired Integrate-and-Fire ATC for Biological and Low-Frequency Signals","source":"crossref","abstract":"","url":"https://doi.org/10.1109/biocas58349.2023.10388601","authors":["Miguel Lima Teixeira","João P. Oliveira","José C. Príncipe","João Goes"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-18T18:27:59Z","doi":"10.1109/biocas58349.2023.10388601","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1016/j.asoc.2009.08.027","name":"A new methodology to improve interpretability in neuro-fuzzy TSK models","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2009.08.027","authors":["Miguel Ángel Vélez","Omar Sánchez","Sixto Romero","José Manuel Andújar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-08-29T06:01:29Z","doi":"10.1016/j.asoc.2009.08.027","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1016/j.asoc.2017.09.001","name":"Prediction of landslide displacement with controlling factors using extreme learning adaptive neuro-fuzzy inference system (ELANFIS)","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2017.09.001","authors":["Shihabudheen KV","G.N. Pillai","Bipin Peethambaran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-09-11T12:46:47Z","doi":"10.1016/j.asoc.2017.09.001","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-642-58930-0_1","name":"Roles of Soft Computing and Fuzzy Logic in the Conception, Design and Deployment of Information/Intelligent Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-58930-0_1","authors":["Lotfi A. Zadeh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-06-15T23:06:59Z","doi":"10.1007/978-3-642-58930-0_1","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-981-13-1592-3_68","name":"Neuro-Fuzzy Analysis of Demonetization on NSE","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-13-1592-3_68","authors":["Rashmi Bhardwaj","Aashima Bangia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-12-13T17:26:17Z","doi":"10.1007/978-981-13-1592-3_68","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-540-89619-7_10","name":"A Neuro-Fuzzy Control for TCP Network Congestion","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-540-89619-7_10","authors":["S. Hadi Hosseini","Mahdieh Shabanian","Babak N. Araabi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-09-29T02:53:53Z","doi":"10.1007/978-3-540-89619-7_10","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1016/j.asoc.2014.03.038","name":"A two level real-time path planning method inspired by cognitive map and predictive optimization in human brain","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2014.03.038","authors":["Yeganeh M. Marghi","Farzad Towhidkhah","Shahriar Gharibzadeh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-04-03T12:34:38Z","doi":"10.1016/j.asoc.2014.03.038","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1016/j.asoc.2012.06.012","name":"A meta-cognitive sequential learning algorithm for neuro-fuzzy inference system","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2012.06.012","authors":["K. Subramanian","S. Suresh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-07-06T04:21:44Z","doi":"10.1016/j.asoc.2012.06.012","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1016/j.asoc.2016.03.023","name":"Optimal design of adaptive type-2 neuro-fuzzy systems: A review","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2016.03.023","authors":["Saima Hassan","Mojtaba Ahmadieh Khanesar","Erdal Kayacan","Jafreezal Jaafar","Abbas Khosravi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-04-11T17:52:53Z","doi":"10.1016/j.asoc.2016.03.023","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/sai.2016.7556146","name":"Science or non-science? The challenge for medical research — To explain neuro-regulation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/sai.2016.7556146","authors":["G W Ewing"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-09-01T22:39:56Z","doi":"10.1109/sai.2016.7556146","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1016/j.asoc.2018.01.009","name":"Neuro-heuristics for nonlinear singular Thomas-Fermi systems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2018.01.009","authors":["Zulqurnain Sabir","Muhammad Anwaar Manzar","Muhammad Asif Zahoor Raja","Muhammad Sheraz","Abdul Majid Wazwaz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-01-30T23:35:56Z","doi":"10.1016/j.asoc.2018.01.009","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/s00521-003-0389-5","name":"Neuro-fuzzy clustering techniques for complex acoustic scenarios","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-003-0389-5","authors":["Rinaldo Poluzzi","Alberto Savi","Davide Vago","Giuseppe Martina"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-12-23T20:14:14Z","doi":"10.1007/s00521-003-0389-5","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/ted.2020.3008887","name":"Neuro-Inspired-in-Memory Computing Using Charge-Trapping MemTransistor on Germanium as Synaptic Device","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ted.2020.3008887","authors":["Yu-Che Chou","Chien-Wei Tsai","Chin-Ya Yi","Wan-Hsuan Chung","Shin-Yuan Wang","Chao-Hsin Chien"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-07-31T16:17:01Z","doi":"10.1109/ted.2020.3008887","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-981-99-3970-1_4","name":"QOPTLib: A Quantum Computing Oriented Benchmark for Combinatorial Optimization Problems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-99-3970-1_4","authors":["Eneko Osaba","Esther Villar-Rodriguez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-21T15:04:55Z","doi":"10.1007/978-981-99-3970-1_4","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1016/j.asoc.2015.04.048","name":"The runner-root algorithm: A metaheuristic for solving unimodal and multimodal optimization problems inspired by runners and roots of plants in nature","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2015.04.048","authors":["F. Merrikh-Bayat"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-05-05T00:50:10Z","doi":"10.1016/j.asoc.2015.04.048","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/s005210170009","name":"Neuro-Flight Controllers for Aircraft Using Minimal Resource Allocating Networks (MRAN)","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s005210170009","authors":["Yan Li","N. Sundararajan","P. Saratchandran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-10-06T16:59:17Z","doi":"10.1007/s005210170009","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1006/jpdc.1997.1343","name":"A Reconfigurable Bit-Serial VLSI Systolic Array Neuro-Chip","source":"crossref","abstract":"","url":"https://doi.org/10.1006/jpdc.1997.1343","authors":["Paul J. Murtagh","Ah Chung Tsoi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-10-07T11:41:49Z","doi":"10.1006/jpdc.1997.1343","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.4018/978-1-6684-6596-7.ch011","name":"Biologically Inspired SNN for Robot Control","source":"crossref","abstract":"In recent years, there has been a trend towards more sophisticated robot control. This has been driven by advances in artificial intelligence (AI) and machine learning, which have enabled robots to become more autonomous and effective in completing tasks. One trend is towards using AI for robot control. This involves teaching robots how to carry out tasks by providing them with data and letting them learn from it. This approach can be used for tasks such as object recognition and navigation. Another trend is towards using machine learning for robot control. This involves using algorithms to learn from data and improve the performance of the robot. This approach can be used for tasks such as object recognition and navigation. A third trend is towards using more sophisticated sensors for robot control. This includes using sensors that can detect things such as temperature, humidity, and pressure.","url":"https://doi.org/10.4018/978-1-6684-6596-7.ch011","authors":["S. Ganeshkumar","J. Maniraj","S. Gokul","Krishnaraj Ramaswamy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-19T08:20:15Z","doi":"10.4018/978-1-6684-6596-7.ch011","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/nabic.2010.5716325","name":"Explicit class structure produced by information-theoretic competitive and cooperative learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2010.5716325","authors":["R Kamimura"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-02-18T19:03:54Z","doi":"10.1109/nabic.2010.5716325","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/s42979-023-01717-0","name":"Correction: Bio-inspired Computing Techniques for Data Security Challenges and Controls","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s42979-023-01717-0","authors":["G. Sripriyanka","Anand Mahendran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-02-15T09:54:50Z","doi":"10.1007/s42979-023-01717-0","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/iitcee57236.2023.10090893","name":"Cerebellum-Inspired Artificial Neural Networks Architecture","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iitcee57236.2023.10090893","authors":["A.R. Nurutdinov","R.Kh. Latypov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-10T14:59:54Z","doi":"10.1109/iitcee57236.2023.10090893","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-981-99-8107-6","name":"Frontiers in Genetics Algorithm Theory and Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-99-8107-6","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-20T10:03:42Z","doi":"10.1007/978-981-99-8107-6","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.3233/ida-170875","name":"Membrane computing inspired feature selection model for microarray cancer data","source":"crossref","abstract":"","url":"https://doi.org/10.3233/ida-170875","authors":["Naeimeh Elkhani","Ravie Chandren Muniyandi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-04-07T11:42:32Z","doi":"10.3233/ida-170875","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/bicta.2008.4656699","name":"One-Time-Pads encryption in the tile assembly model","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2008.4656699","authors":["Zhihua Chen","Jin Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-10-28T15:22:35Z","doi":"10.1109/bicta.2008.4656699","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1016/j.asoc.2025.112703","name":"Neuro-fuzzy based Indian Topographic map understanding system","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2025.112703","authors":["Gitanjali Ganpatrao Nikam","Jayanta Kumar Ghosh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-05T06:03:00Z","doi":"10.1016/j.asoc.2025.112703","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-319-27400-3_19","name":"Real-Time Vehicle Emission Monitoring and Location Tracking Framework","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-27400-3_19","authors":["Eyob Shiferaw Abera","Ayalew Belay","Ajith Abraham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-01T17:08:38Z","doi":"10.1007/978-3-319-27400-3_19","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/wisp.2007.4447532","name":"Biology Inspired Approximate Data Representation for Signal Processing, Soft Computing and Control Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/wisp.2007.4447532","authors":["Emil M. Petriu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-02-15T12:33:14Z","doi":"10.1109/wisp.2007.4447532","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/nabic.2014.6921881","name":"Optimization of structures modeled with a meshfree approach","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2014.6921881","authors":["G.M.S. Bernardo","M.A.R. Loja"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-10-22T16:05:41Z","doi":"10.1109/nabic.2014.6921881","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/bimnics.2006.361811","name":"Stepwise Probabilistic Buffering for Epidemic Information Dissemination","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bimnics.2006.361811","authors":["Emrah Ahi","Mine Cavlar","Oznur Ozkasap"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-06-07T15:56:37Z","doi":"10.1109/bimnics.2006.361811","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1016/j.asoc.2025.112963","name":"Saccade inspired Attentive Visual Patch Transformer for image sentiment analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2025.112963","authors":["Jing Zhang","Jixiang Zhu","Han Sun","Xinzhou Zhang","Jiangpei Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-12T16:51:12Z","doi":"10.1016/j.asoc.2025.112963","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-981-16-9573-5_16","name":"Corona Warrior Smart Band","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-16-9573-5_16","authors":["Soham S. Methul","Shubhangee K. Varma","Ashok S. Chandak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-30T06:02:42Z","doi":"10.1007/978-981-16-9573-5_16","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-319-27400-3_27","name":"A Neural Network Model for Road Traffic Flow Estimation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-27400-3_27","authors":["Ayalew Belay Habtie","Ajith Abraham","Dida Midekso"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-01T17:08:38Z","doi":"10.1007/978-3-319-27400-3_27","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.5860/choice.40-3448","name":"Machine nature: the coming age of bio-inspired computing","source":"crossref","abstract":"","url":"https://doi.org/10.5860/choice.40-3448","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-01-24T01:32:24Z","doi":"10.5860/choice.40-3448","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1186/2190-8532-1-17","name":"Biologically-inspired analysis in the real world: computing, informatics, and ecologies of use","source":"crossref","abstract":"","url":"https://doi.org/10.1186/2190-8532-1-17","authors":["Laura A McNamara"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-11-06T21:14:16Z","doi":"10.1186/2190-8532-1-17","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-981-15-3836-0_2","name":"Combinatorial Optimization Space","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-15-3836-0_2","authors":["Aziz Ouaarab"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-03-24T13:02:55Z","doi":"10.1007/978-981-15-3836-0_2","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/esic64052.2025.10962683","name":"Chernobyl-Inspired Optimization for Efficient Wireless Sensor Network Routing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/esic64052.2025.10962683","authors":["Garima","Amita Rani","Sanjay Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-16T17:46:32Z","doi":"10.1109/esic64052.2025.10962683","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/ibica.2011.39","name":"Data Maintenance and Control Strategy of Group Management","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ibica.2011.39","authors":["Yuchun Zhang","Zhiqiang Ye"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-01-06T21:44:03Z","doi":"10.1109/ibica.2011.39","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/s005000000069","name":"A new method for adaptive model-based control of non-linear dynamic plants using a neuro-fuzzy-fractal approach","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s005000000069","authors":["P. Melin","O. Castillo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-02-11T13:20:45Z","doi":"10.1007/s005000000069","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-981-33-6862-0_2","name":"Object-Based Neural Model in Multicore Environments with Improved Biological Plausibility","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-33-6862-0_2","authors":["R. Krishnan","A. Murugan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-06-14T05:02:45Z","doi":"10.1007/978-981-33-6862-0_2","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-030-32530-5_8","name":"Role of AI and Bio-Inspired Computing in Decision Making","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-32530-5_8","authors":["Surekha Paneerselvam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-12-28T06:02:28Z","doi":"10.1007/978-3-030-32530-5_8","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-030-37218-7_41","name":"A Computer Vision Based Fall Detection Technique for Home Surveillance","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_41","authors":["Katamneni Vinaya Sree","G. Jeyakumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T20:02:40Z","doi":"10.1007/978-3-030-37218-7_41","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-030-37218-7_111","name":"Global Normalization for Fingerprint Image Enhancement","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_111","authors":["Meghna B. Patel","Satyen M. Parikh","Ashok R. Patel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T15:02:40Z","doi":"10.1007/978-3-030-37218-7_111","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.64823/ijter.2621029","name":"Neuromorphic Computing: Current Progress and the Future of Brain-Inspired Computing","source":"openalex","abstract":"Neuromorphic computing borrows its design logic from the nervous system rather than from the von Neumann architecture that has dominated computing for seventy years. Instead of shuttling data back and forth between separate memory and processing units, it favors event-driven communication, computation that happens close to (or inside) memory, and massive parallelism across simple processing elements. This paper takes stock of where the field currently stands: spiking neural networks, digital and analog processors, memristive and other emerging devices, the software ecosystems that support them, and application areas ranging from robotics and edge intelligence to biomedical monitoring and event-based vision. What emerges from the recent literature is a field that has largely moved past small proof-of-concept chips and is now building larger, more programmable platforms with tighter hardware-algorithm integration. Even so, real obstacles remain around training methods, benchmarking practices, programmability, device variability, and fabrication, and it is still unclear how much of the field's energy advantage survives contact with general-purpose workloads. The view taken here is that brain-inspired computing is heading toward a hybrid future: conventional digital processors will keep doing what they do best, while event-driven and in-memory accelerators take over the workloads where they have a genuine edge. Neuromorphic computing is therefore unlikely to displace mainstream AI hardware outright, but it looks well positioned to become a key ingredient in low-power, adaptive, real-time intelligence at the edge. Keywords: edge AI; neuromorphic computing; brain-inspired computing; spiking neural networks; memristors; in-memory computing","url":"https://doi.org/10.64823/ijter.2621029","authors":["Jisna C Jeejo","Habeeba M A"],"tags":["Neuromorphic engineering","Computer science","Von Neumann architecture","Computer architecture","Unconventional computing"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2026-08-23","doi":"10.64823/ijter.2621029","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"doi:10.1016/j.aci.2014.04.002","name":"An adaptive neuro fuzzy model for estimating the reliability of component-based software systems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.aci.2014.04.002","authors":["Kirti Tyagi","Arun Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-05-06T19:45:44Z","doi":"10.1016/j.aci.2014.04.002","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1109/icsccw.2009.5379422","name":"New neuro-fuzzy approach to recession prediction","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icsccw.2009.5379422","authors":["Nijat Sh. Mehdiyev","Babek.G. Guirimov","Rafig R. Aliyev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-20T20:57:36Z","doi":"10.1109/icsccw.2009.5379422","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-319-03110-1_9","name":"Synchronous Finite State Machines Design with Quantum-Inspired Evolutionary Computation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-03110-1_9","authors":["Nadia Nedjah","Luiza de Macedo Mourelle"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-11-18T02:36:09Z","doi":"10.1007/978-3-319-03110-1_9","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-030-37218-7_28","name":"Human Face Recognition Using Local Binary Pattern Algorithm - Real Time Validation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_28","authors":["P. Shubha","M. Meenakshi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T15:02:40Z","doi":"10.1007/978-3-030-37218-7_28","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1007/978-3-030-37218-7_56","name":"Autism Spectrum Disorder Prediction Using Machine Learning Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_56","authors":["Shanthi Selvaraj","Poonkodi Palanisamy","Summia Parveen","Monisha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T20:02:40Z","doi":"10.1007/978-3-030-37218-7_56","addedAt":"2026-09-01T01:48:28.406Z","updatedAt":"2026-09-01T01:48:28.406Z"},{"id":"doi:10.1038/s42256-023-00747-w","name":"Incorporating neuro-inspired adaptability for continual learning in artificial intelligence","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s42256-023-00747-w","authors":["Liyuan Wang","Xingxing Zhang","Qian Li","Mingtian Zhang","Hang Su","Jun Zhu","Yi Zhong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-16T17:01:58Z","doi":"10.1038/s42256-023-00747-w","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/s12652-024-04917-5","name":"Retraction Note: Brain epilepsy seizure detection using bio-inspired krill herd and artificial alga optimized neural network approaches","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s12652-024-04917-5","authors":["Ahed Abugabah","Ahmad Ali AlZubi","Mohammed Al-Maitah","Abdulaziz Alarifi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-02T02:11:17Z","doi":"10.1007/s12652-024-04917-5","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.2139/ssrn.4999124","name":"Nature-Inspired Business Defense Tactics","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4999124","authors":["Tojin Eapen","Daniel  J. Finkenstadt"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-25T08:38:02Z","doi":"10.2139/ssrn.4999124","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1007/978-3-319-27400-3_1","name":"A Diverse Meta Learning Ensemble Technique to Handle Imbalanced Microarray Dataset","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-27400-3_1","authors":["Sujata Dash"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-01T17:08:38Z","doi":"10.1007/978-3-319-27400-3_1","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/s10791-025-09632-z","name":"A multi-level intrusion detection system for industrial IoT using bowerbird courtship-inspired feature selection and hybrid data balancing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s10791-025-09632-z","authors":["S Kumar Reddy Mallidi","Rajeswara Rao Ramisetty"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-07T05:33:55Z","doi":"10.1007/s10791-025-09632-z","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1016/b978-0-08-102782-0.00008-3","name":"Hyperdimensional computing nanosystem: in-memory computing using monolithic 3D integration of RRAM and CNFET","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-08-102782-0.00008-3","authors":["Abbas Rahimi","Tony F. Wu","Haitong Li","Jan M. Rabaey","H.-S. Philip Wong","Max M. Shulaker","Subhasish Mitra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-26T05:27:00Z","doi":"10.1016/b978-0-08-102782-0.00008-3","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-981-10-7179-9_43","name":"Computing Stability of Products of Grassmannians with Fixed Total Dimension Using MAXIMA","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-10-7179-9_43","authors":["Dun Liang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-11-07T23:53:32Z","doi":"10.1007/978-981-10-7179-9_43","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-981-10-6747-1_19","name":"Distributed Denial of Service Attack Detection Using Ant Bee Colony and Artificial Neural Network in Cloud Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-10-6747-1_19","authors":["Uzma Ali","Kranti K. Dewangan","Deepak K. Dewangan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-10-04T08:25:22Z","doi":"10.1007/978-981-10-6747-1_19","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-981-97-2275-4_30","name":"Distributed Intelligence Analysis Architecture for 6G Core Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-2275-4_30","authors":["Wen Sun","QiBo Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-15T19:02:10Z","doi":"10.1007/978-981-97-2275-4_30","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1093/neuonc/noae196","name":"Society News","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuonc/noae196","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-04T22:18:12Z","doi":"10.1093/neuonc/noae196","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1007/978-3-031-62017-1_12","name":"Medulloblastoma","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-62017-1_12","authors":["Sara Khan","Vijay Ramaswamy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-22T06:01:48Z","doi":"10.1007/978-3-031-62017-1_12","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1007/s11082-024-07914-2","name":"Retraction Note: Neuro quantum computing based optoelectronic artificial intelligence in electroencephalogram signal analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11082-024-07914-2","authors":["M. Sangeetha","P. Senthil","Adel H. Alshehri","Shamimul Qamar","Hashim Elshafie","V. P. Kavitha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-18T23:51:53Z","doi":"10.1007/s11082-024-07914-2","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1093/neuonc/noae144.497","name":"Disclosure Information","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuonc/noae144.497","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-17T18:20:55Z","doi":"10.1093/neuonc/noae144.497","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1093/neuonc/noae144.495","name":"Author Index","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuonc/noae144.495","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-17T18:21:24Z","doi":"10.1093/neuonc/noae144.495","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1093/neuonc/noae023","name":"Forthcoming Meetings","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuonc/noae023","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-05T06:02:25Z","doi":"10.1093/neuonc/noae023","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1007/978-3-642-58930-0_18","name":"Fuzzy Data Analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-58930-0_18","authors":["H.-J. Zimmermann"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-06-15T19:06:59Z","doi":"10.1007/978-3-642-58930-0_18","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1097/wno.0000000000002283","name":"How Advancements in AI Can Help Improve Neuro-Ophthalmologic Diagnostic Clarity","source":"crossref","abstract":"","url":"https://doi.org/10.1097/wno.0000000000002283","authors":["Rachel C. Kenney","Kimberly A. O'Neill"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-19T22:00:19Z","doi":"10.1097/wno.0000000000002283","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1109/sensorcomm.2010.24","name":"Advanced Bio-inspired Plausibility Checking in a Wireless Sensor Network Using Neuro-immune Systems: Autonomous Fault Diagnosis in an Intelligent Transportation System","source":"crossref","abstract":"","url":"https://doi.org/10.1109/sensorcomm.2010.24","authors":["Amir Jabbari","Walter Lang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-08-27T10:38:49Z","doi":"10.1109/sensorcomm.2010.24","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1093/neuonc/noae159","name":"Society News","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuonc/noae159","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-03T17:47:51Z","doi":"10.1093/neuonc/noae159","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1007/978-981-97-8171-3_13","name":"Graph Neural Networks in Neural-Symbolic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-8171-3_13","authors":["Bikram Pratim Bhuyan","Amar Ramdane-Cherif","Thipendra P. Singh","Ravi Tomar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-22T11:43:42Z","doi":"10.1007/978-981-97-8171-3_13","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1093/neuonc/noae144.496","name":"Keyword Index","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuonc/noae144.496","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-17T18:21:16Z","doi":"10.1093/neuonc/noae144.496","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1093/neuonc/noae010","name":"Forthcoming Meetings","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuonc/noae010","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-05T03:14:53Z","doi":"10.1093/neuonc/noae010","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1007/978-3-540-73554-0_21","name":"Bond Computing Systems: A Biologically Inspired and High-Level Dynamics Model for Pervasive Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-540-73554-0_21","authors":["Linmin Yang","Zhe Dang","Oscar H. Ibarra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-08-22T09:27:13Z","doi":"10.1007/978-3-540-73554-0_21","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1109/iscas.2010.5537271","name":"Neuro-inspired system for real-time vision sensor tilt correction","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas.2010.5537271","authors":["A. Jimenez-Fernandez","J.L. Fuentes-del-Bosh","R. Paz-Vicente","A. Linares-Barranco","G. Jimenez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-08-09T18:13:20Z","doi":"10.1109/iscas.2010.5537271","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.3233/apc210256","name":"Brain Inspired Visual Effects and Animation Psychological Computing Impact in Indian Television Advertisement Pre and Post 2000s","source":"crossref","abstract":"Technology in its immense boom in the last decade has made us aware of a lot of ways to increase consumer potential and engagement with different products in various spheres and aspects of production. Taking this idea forward, the main idea of this study is to identify the major visual effects facets being used and how they contributed towards consumer engagement. In this regard, a pilot study was done and then questionnaire has been prepared which was completed by 369 participants between the age group 18–60 years. Hence the main aim of this work is to use statistical data to understand how the last decade has proved beneficial for the Advertising industry through the use of visual effects Statistical analysis is used to interpret the data.","url":"https://doi.org/10.3233/apc210256","authors":["Gondi Surender Dhanunjay","Pranjal Singh","Sayyad Samee","K. Vengatesan","Abhishek Kumar","Achintya Singhal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-03T07:52:50Z","doi":"10.3233/apc210256","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1145/3381755.3381762","name":"Neuromorphic Graph Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3381755.3381762","authors":["Bill Kay","Prasanna Date","Catherine Schuman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-18T23:09:51Z","doi":"10.1145/3381755.3381762","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.2172/2002131","name":"Localization through Grid-based Encodings on Digital Elevation Models.","source":"crossref","abstract":"","url":"https://doi.org/10.2172/2002131","authors":["Felix Wang","Corinne Teeter","Sarah Luca","Srideep Musuvathy","James Aimone"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-03T03:10:09Z","doi":"10.2172/2002131","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1002/9781394355600.ch3","name":"Brain‐Inspired Artificial Neural Network for Energy‐Efficient and Adaptive Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9781394355600.ch3","authors":["R. Dhanalakshmi","Sahaya Beni Prathiba","L. Kavisankar","S. Balasubramani","M. Pandiyanathan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-31T21:30:31Z","doi":"10.1002/9781394355600.ch3","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1093/neuonc/noae003","name":"Forthcoming Meetings","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuonc/noae003","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-02T18:25:46Z","doi":"10.1093/neuonc/noae003","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1016/j.mlwa.2026.100869","name":"Quantum-inspired bi-level neuro-swarm optimization for UAV-based disaster recognition and response","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.mlwa.2026.100869","authors":["Gourav Mondal","Rajesh Kumar Dhanaraj","Dragan Pamucar","Balamurugan Balusamy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-18T17:04:22Z","doi":"10.1016/j.mlwa.2026.100869","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1093/neuonc/noae084","name":"Forthcoming Meetings","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuonc/noae084","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-06T07:57:21Z","doi":"10.1093/neuonc/noae084","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1016/b978-0-443-15663-2.09986-7","name":"About the editors","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-15663-2.09986-7","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-09T07:38:35Z","doi":"10.1016/b978-0-443-15663-2.09986-7","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1093/neuonc/noae064.780","name":"Author Index","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuonc/noae064.780","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-19T08:41:03Z","doi":"10.1093/neuonc/noae064.780","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.5573/ieiespc.2015.4.6.379","name":"Distance Measurement Using the Kinect Sensor with Neuro-image Processing","source":"crossref","abstract":"","url":"https://doi.org/10.5573/ieiespc.2015.4.6.379","authors":["Kajal Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-02-16T01:34:50Z","doi":"10.5573/ieiespc.2015.4.6.379","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1093/neuonc/noad254","name":"Forthcoming Meetings","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuonc/noad254","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-05T17:58:51Z","doi":"10.1093/neuonc/noad254","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1007/978-3-031-62017-1_1","name":"Introduction","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-62017-1_1","authors":["Eric Bouffet","Katrin Scheinemann"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-22T06:02:21Z","doi":"10.1007/978-3-031-62017-1_1","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1016/j.asoc.2021.107963","name":"Novel hybrid ANN and clustering inspired load balancing algorithm in cloud environment","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2021.107963","authors":["Sarita Negi","Neelam Panwar","Man Mohan Singh Rauthan","Kunwar Singh Vaisla"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-10-07T23:41:38Z","doi":"10.1016/j.asoc.2021.107963","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-981-10-6747-1_21","name":"Novel Method for Predicting Academic Performance of Students by Using Modified Particle Swarm Optimization (PSO)","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-10-6747-1_21","authors":["Satyajee Srivastava"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-10-04T08:25:22Z","doi":"10.1007/978-981-10-6747-1_21","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1080/10798587.2009.10643020","name":"Guest Editorial","source":"crossref","abstract":"","url":"https://doi.org/10.1080/10798587.2009.10643020","authors":["Xiaobu Yuan","Simon X. Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-03-02T07:56:34Z","doi":"10.1080/10798587.2009.10643020","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-3-319-76354-5_31","name":"A Statistical Analysis for High-Speed Stream Ciphers","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-76354-5_31","authors":["Youssef Harmouch","Rachid El Kouch"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-09T11:43:48Z","doi":"10.1007/978-3-319-76354-5_31","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-3-030-37218-7_98","name":"Eye Movement Event Detection with Deep Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_98","authors":["K. Anusree","J. Amudha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T15:02:40Z","doi":"10.1007/978-3-030-37218-7_98","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.59461/ijdiic.v5i2.281","name":"Hybrid Quantum-Inspired Intelligent Computing Model for Real-Time Optimization of Massive Heterogeneous Climate Datasets","source":"crossref","abstract":"The volume of climate observations is now growing faster than classical optimizers can process it. With petabyte-scale reanalysis archives and multi-source satellite streams in routine operation, the training budget of large climate models has become a genuine bottleneck for real-time forecasting. In this paper, we propose a hybrid quantum-inspired intelligent computing model (HQI-Opt) for fast and energy-efficient optimization of deep forecasting networks trained on heterogeneous climate tensors. The method combines a classical gradient branch, driven by a parameter-shift-style analytic estimator over a latitude-weighted loss, with a quantum-inspired branch that encodes the parameter state into an Ising/QUBO representation and applies a quantum rotation-gate mixing step modulated by an adiabatic schedule. A training loop with three concurrent branches is developed and evaluated on an ERA5 subset following the WeatherBench 2 protocol. The method is compared against six widely used optimizers: SGD with momentum, Adam, AdamW, LAMB, Lion, and Sophia. Across 69 variables and four lead times, HQI-Opt reaches the target latitude-weighted loss in approximately 43% fewer epochs; the training energy per run falls from 29.8 to 17.6 kWh, the associated carbon footprint is reduced by 41%, and the RMSE at the 3-day lead on geopotential height at 500 hPa improves from 140.8 to 137.3 m²/s². A convergence analysis is provided showing that the iterates approach a stationary point of the latitude-weighted loss as the annealing schedule decays. The results indicate that a classically simulated quantum-inspired update step, with no quantum hardware in the loop, is already a viable building block for real-time climate informatics pipelines.","url":"https://doi.org/10.59461/ijdiic.v5i2.281","authors":["Anirudha Gaikwad","Atit Gaikwad","Shardul Singh Chauhan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-08T17:51:21Z","doi":"10.59461/ijdiic.v5i2.281","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1007/s11060-024-04773-5","name":"The Journal of Neuro-Oncology: the last and next 40 years","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11060-024-04773-5","authors":["Jason P. Sheehan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-29T09:02:57Z","doi":"10.1007/s11060-024-04773-5","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1007/978-981-15-2133-1_8","name":"Tracing the Points in Search Space in Plant Biology Genetics Algorithm Optimization","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-15-2133-1_8","authors":["Mahdi Khosravy","Neeraj Gupta","Nilesh Patel","Om Prakash Mahela","Gazal Varshney"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-03-11T18:03:41Z","doi":"10.1007/978-981-15-2133-1_8","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1007/978-981-15-2133-1_14","name":"Evolutionary Artificial Neural Networks: Comparative Study on State-of-the-Art Optimizers","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-15-2133-1_14","authors":["Neeraj Gupta","Mahdi Khosravy","Nilesh Patel","Saurabh Gupta","Gazal Varshney"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-03-11T18:03:41Z","doi":"10.1007/978-981-15-2133-1_14","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1007/978-981-97-7344-2_9","name":"Smart Diagnostics for Diabetic Retinopathy: Integrating Artificial Bee Colony Algorithms into Medical Image Analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-7344-2_9","authors":["R. S. M. Lakshmi Patibandla","B. Tarakeswara Rao","M. Ramakrishna Murthy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-01T08:28:13Z","doi":"10.1007/978-981-97-7344-2_9","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1007/978-981-97-7344-2_5","name":"Integrating Artificial Bee Colony Algorithms for Deep Learning Model Optimization: A Comprehensive Review","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-7344-2_5","authors":["Faiz Akram","Shafaque Aziz","Nayyar Ahmed Khan","Syed Akramah Faizi","Khalid Raza"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-01T03:28:09Z","doi":"10.1007/978-981-97-7344-2_5","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1093/neuonc/noae057","name":"Forthcoming Meetings","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuonc/noae057","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-03T10:20:11Z","doi":"10.1093/neuonc/noae057","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1016/j.softx.2025.102505","name":"Version [2.0]-[NeoCoMM: Neocortical neuro-inspired computational model for realistic microscale simulations]","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.softx.2025.102505","authors":["M. Yochum","F. Karimi","F. Wendling","M. Al Harrach"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-07T12:57:41Z","doi":"10.1016/j.softx.2025.102505","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.4018/978-1-7998-2460-2.ch004","name":"Cognitive Computing","source":"crossref","abstract":"Cognitive Computing (CC) is a contemporary field of studies on intelligent computing methodologies and brain-inspired mechanisms of cognitive systems, cognitive machine learning and cognitive robotics. The IEEE conference ICCI*CC'17 on Cognitive Informatics and Cognitive Computing was focused on the theme of neurocomputation, cognitive machine learning and brain-inspired systems. This article reports the plenary panel (Part II) in IEEE ICCI*CC'17 at Oxford University. The summary is contributed by distinguished panelists who are part of the world's renowned scholars in the transdisciplinary field of cognitive computing.","url":"https://doi.org/10.4018/978-1-7998-2460-2.ch004","authors":["Yingxu Wang","Victor Raskin","Julia M. Rayz","George Baciu","Aladdin Ayesh","Fumio Mizoguchi","Shusaku Tsumoto","Dilip Patel","Newton Howard"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-03-27T08:13:45Z","doi":"10.4018/978-1-7998-2460-2.ch004","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1097/wno.0000000000002220","name":"Literature Commentary","source":"crossref","abstract":"In this issue of JNO, Drs. Mark L. Moster, Marc Dinkin, and Deborah I. Friedman discuss the following 3 articles.","url":"https://doi.org/10.1097/wno.0000000000002220","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-20T04:02:08Z","doi":"10.1097/wno.0000000000002220","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.31234/osf.io/bg2d7","name":"Magnetism-Inspired Quantum-Mechanical Model of Gender Fluidity","source":"crossref","abstract":"Quantum-mechanical models of human cognition, opinion formation and decision-making have changed the way we understand and predict human behaviour in many practical situations, including political elections, financial decisions and international affairs. Yet, at present, such models overlook certain essential social aspects of human behaviour and self-identification. In this paper, we introduce a magnetism-inspired quantum-mechanical model of gender fluidity, a concept that challenges social norms across the globe. Addressing a number of independent suggestions made by members of the general public concerning a potential analogy between quantum superposition and non-binary self-identification, we explore new territories, demonstrating that physic of magnetism can help explain gender fluidity and similar social phenomena better than the traditional quantum-mechanical models of human cognition and perception. We anticipate that the proposed model can be used to analyse experimental datasets aimed to develop sexual orientation and gender identity legal definitions as well as to create artificial intelligence systems that can sensibly identify both binary and non-binary genders.","url":"https://doi.org/10.31234/osf.io/bg2d7","authors":["Ivan Maksymov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-27T00:00:23Z","doi":"10.31234/osf.io/bg2d7","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1016/b978-0-12-813788-8.00005-6","name":"Soft Computing Applications in Mobile Robotics","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-12-813788-8.00005-6","authors":["Alma Y. Alanis","Nancy Arana-Daniel","Carlos López-Franco"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-07T19:48:18Z","doi":"10.1016/b978-0-12-813788-8.00005-6","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1109/bicta.2009.5338082","name":"A weakly universal spiking neural P system","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2009.5338082","authors":["Xiangxiang Zeng","Chun Lu","Linqiang Pan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-11-24T18:50:07Z","doi":"10.1109/bicta.2009.5338082","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1023/a:1026746406754","name":"Nature-Inspired Computing Technology and Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1023/a:1026746406754","authors":["P Marrow"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-11-06T18:09:07Z","doi":"10.1023/a:1026746406754","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1093/neuonc/noae212","name":"Forthcoming Meetings","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuonc/noae212","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-10T21:38:20Z","doi":"10.1093/neuonc/noae212","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1007/978-981-10-3611-8_17","name":"A General Object-Oriented Description for Membrane Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-10-3611-8_17","authors":["Xiyu Liu","Yuzhen Zhao","Wenping Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-01-07T04:29:56Z","doi":"10.1007/978-981-10-3611-8_17","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1016/j.asoc.2010.05.032","name":"Quantum-inspired design of resilient substitution boxes: From coding to hardware implementation","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2010.05.032","authors":["Nadia Nedjah","Luiza M. Mourelle","Marcos Paulo M. Araujo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-07-01T08:54:07Z","doi":"10.1016/j.asoc.2010.05.032","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1007/s00607-012-0205-0","name":"An optimization algorithm inspired by social creativity systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00607-012-0205-0","authors":["Roman Anselmo Mora-Gutiérrez","Javier Ramírez-Rodríguez","Eric Alfredo Rincón-García","Antonin Ponsich","Oscar Herrera"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-08-14T05:12:59Z","doi":"10.1007/s00607-012-0205-0","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1007/978-3-319-14370-5_4","name":"Membrane Computing Inspired Approach for Executing Scientific Workflow in the Cloud","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-14370-5_4","authors":["Tanveer Ahmed","Rohit Verma","Miroojin Bakshi","Abhishek Srivastava"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-12-16T11:07:01Z","doi":"10.1007/978-3-319-14370-5_4","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1007/s00521-024-09697-9","name":"Training neuro-fuzzy using flower pollination algorithm to predict number of COVID-19 cases: situation analysis for twenty countries","source":"crossref","abstract":"Abstract Predicting the number of COVID-19 cases offers a reflection of the future, and it is important for the implementation of preventive measures. The numbers of COVID-19 cases are constantly changing on a daily. Adaptive methods are needed for an effective estimation instead of traditional methods. In this study, a novel method based on neuro-fuzzy and FPA is proposed to estimate the number of COVID-19 cases. The antecedent and conclusion parameters of the neuro-fuzzy model are determined by using FPA. In other words, neuro-fuzzy training is carried out with FPA. The number of COVID-19 cases belonging to twenty countries including USA, India, Brazil, Russian, France, UK, Italy, Spain, Argentina, Germany, Colombia, Mexico, Poland, Turkey, Iran, Peru, Ukraine, South Africa, the Netherlands and Indonesia is estimated. Time series is created using the number of COVID-19 cases. Daily, weekly and monthly estimates are realized by utilizing these time series. MSE is used as the error metric. Although it varies according to the example and problem type, the best training error values between 0.000398027 and 0.0286562 are obtained. These best test error values are between 0.0005607 and 0.409867. The best training and test error values are 0.000398027 and 0.0005607, respectively. In addition to FPA, the number of cases is also predicted with the algorithms such as particle swarm optimization, harmony search, bee algorithm, differential evolution and their performances are compared. Success score and ranking are created for all algorithms. The scores of FPA for the daily, weekly and monthly forecast are 71, 77 and 62, respectively. These scores have shown that neuro-fuzzy training based on FPA is successful than other meta-heuristic algorithms for all three prediction types in the short- and medium-term estimation of COVID-19 case numbers.","url":"https://doi.org/10.1007/s00521-024-09697-9","authors":["Ceren Baştemur Kaya","Ebubekir Kaya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-27T18:02:23Z","doi":"10.1007/s00521-024-09697-9","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1007/978-981-33-6773-9_15","name":"Artificial Bee Colony Algorithm and Its Application to Content Filtering in Digital Communication","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-33-6773-9_15","authors":["Bilge Kagan Dedeturk","Bahriye Akay","Dervis Karaboga"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-31T12:03:02Z","doi":"10.1007/978-981-33-6773-9_15","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1007/978-3-642-13467-8_4","name":"Human Inspired Self-developmental Model of Neural Network (HIM): Introducing Content/Form Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-13467-8_4","authors":["Jiří Krajíček"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-09-10T11:33:37Z","doi":"10.1007/978-3-642-13467-8_4","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1007/978-3-030-37218-7_36","name":"Deep Learning Model for Image Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_36","authors":["Sudarshana Tamuly","C. Jyotsna","J. Amudha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T20:02:40Z","doi":"10.1007/978-3-030-37218-7_36","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1016/j.suscom.2026.101351","name":"Bio-inspired superb fairy-wren optimization framework for post-islanding energy management in hybrid microgrids","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.suscom.2026.101351","authors":["Madamaneri Ramya","T. Devaraju"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-02T03:24:03Z","doi":"10.1016/j.suscom.2026.101351","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1016/b978-0-44-322341-9.00008-2","name":"Biographies","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-44-322341-9.00008-2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-24T10:20:16Z","doi":"10.1016/b978-0-44-322341-9.00008-2","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1201/9781003143499-17","name":"Learning spiking neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003143499-17","authors":["Elishai Ezra Tsur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-07-19T12:30:34Z","doi":"10.1201/9781003143499-17","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1109/nabic.2009.5393716","name":"Face recognition using probabilistic neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393716","authors":["K V Vinitha","G Santhosh Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5393716","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1109/ccaa.2015.7148397","name":"A novel chemo-inspired GA for solving constrained optimization problem","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ccaa.2015.7148397","authors":["Rajashree Mishra","Kedar Nath Das"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-07-07T21:44:01Z","doi":"10.1109/ccaa.2015.7148397","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1109/nabic.2009.5393882","name":"A randomized iterative improvement algorithm for photomosaic generation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393882","authors":["Harikrishna Narasimhan","Sanjeev Satheesh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5393882","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1142/9789812790262_0003","name":"THE CORTEX ARCHITECTURE: THE BUILDING BLOCK OF INTELLIGENCE","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789812790262_0003","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-04-12T00:09:25Z","doi":"10.1142/9789812790262_0003","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1007/978-3-030-37218-7_25","name":"Dynamic Link Prediction in Biomedical Domain","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_25","authors":["M. V. Anitha","Linda Sara Mathew"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T20:02:40Z","doi":"10.1007/978-3-030-37218-7_25","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1007/978-3-319-08156-4","name":"Proceedings of the Fifth International Conference on Innovations in Bio-Inspired Computing and Applications IBICA 2014","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-08156-4","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-06-13T15:07:31Z","doi":"10.1007/978-3-319-08156-4","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1007/978-3-319-76354-5_30","name":"A Hybrid Feature Selection for MRI Brain Tumor Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-76354-5_30","authors":["Ahmed Kharrat","Mahmoud Neji"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-09T11:43:48Z","doi":"10.1007/978-3-319-76354-5_30","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1007/s00500-022-07032-9","name":"Application of nature inspired soft computing techniques for gene selection: a novel frame work for classification of cancer","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00500-022-07032-9","authors":["Rabia Musheer Aziz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-07T02:03:03Z","doi":"10.1007/s00500-022-07032-9","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1260/1478-0771.11.4.437","name":"Designing Biologically-Inspired Smart Building Systems: Processes and Guidelines","source":"crossref","abstract":"This paper investigates design processes of and guidelines for biologically-inspired smart building systems (BISBS). Within the functional and performance requirements of building systems, biologically-inspired design is explored as the key approach and smart technology as the enabling technology. The Soft Modular Pneumatic System (SMoPS) is developed as a design experiment in order to verify the effectiveness of the BISBS design process. Similarly to how independent cells coordinate with each other to undergo certain tasks in multicellular systems, the SMoPS consists of autonomous modules that collectively achieve assigned functions. Within the soft body of each SMoPS module, sensor, actuation, and control components are integrated which enables the module to kinetically respond to and interact with its environment. The modular design and hierarchical assembly logic contribute to creating a flexible as well as robust building system. Throughout the design process, prototyping, simulation, and animation are utilized as an iterative and diversified development method.","url":"https://doi.org/10.1260/1478-0771.11.4.437","authors":["Daekwon Park","Martin Bechthold"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-01-21T21:49:48Z","doi":"10.1260/1478-0771.11.4.437","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1016/j.asoc.2023.110699","name":"Solving non-linear fixed-charge transportation problems using nature inspired non-linear particle swarm optimization algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2023.110699","authors":["Shivani","Deepika Rani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-02T12:13:10Z","doi":"10.1016/j.asoc.2023.110699","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1109/icscai61790.2024.10866055","name":"A Study of Delay Differential Models and Prediction Models of Neuro - Fuzzy Techniques in Diabetes Management","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icscai61790.2024.10866055","authors":["Akriti Srivastava","Vijay K. Yadav","Nilam","Manoj Kumar","Arun Pratap Srivastava"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-13T18:29:13Z","doi":"10.1109/icscai61790.2024.10866055","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1097/wno.0000000000002104","name":"Literature Commentary","source":"crossref","abstract":"In this issue of JNO Drs. Mark L. Moster, Marc Dinkin, and Deborah I. Friedman discuss the following six articles.","url":"https://doi.org/10.1097/wno.0000000000002104","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-13T18:00:10Z","doi":"10.1097/wno.0000000000002104","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1145/3736393.3736692","name":"Leveraging Quantum Computing for Optimal Data Allocation in Distributed Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3736393.3736692","authors":["Immanuel Trummer"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-23T12:39:22Z","doi":"10.1145/3736393.3736692","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.5040/9781839979804.ch-009","name":"Neuro Navigators in the Workplace","source":"crossref","abstract":"","url":"https://doi.org/10.5040/9781839979804.ch-009","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-13T15:02:24Z","doi":"10.5040/9781839979804.ch-009","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1097/wno.0000000000002154","name":"Literature Commentary","source":"crossref","abstract":"In this issue of JNO Drs. Mark L. Moster, Marc Dinkin, and Deborah I. Friedman discuss the following six articles.","url":"https://doi.org/10.1097/wno.0000000000002154","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-25T18:06:27Z","doi":"10.1097/wno.0000000000002154","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1145/1315843.1315884","name":"A new bio-inspired location search algorithm for peer to peer network based internet telephony","source":"crossref","abstract":"","url":"https://doi.org/10.1145/1315843.1315884","authors":["Sachin Kulkarni","Niloy Ganguly","Geoffrey Canright","Andreas Deutsch"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-11-15T14:30:20Z","doi":"10.1145/1315843.1315884","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/isac.2010.5670477","name":"A human behavior inspired awareness system for document analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isac.2010.5670477","authors":["Jie Ji","Daichi Kunita","Qiangfu Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-12-22T01:35:11Z","doi":"10.1109/isac.2010.5670477","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch054","name":"Complexity-Based Modelling Approaches for Commercial Applications","source":"crossref","abstract":"Understanding complex socio-economic systems is a key problem for commercial organizations. In this chapter we discuss the use of agent-based modelling to produce decision support tools to enhance this understanding. We consider the important aspects of the model creation process which include the facilitation of dialogue necessary to extract knowledge, the building of understanding, and the identification of model limitations. It is these aspects that are crucial in the establishment of trust in a model. We use the example of modelling opinion diffusion within a customer population and its effect on product adoption to illustrate how the agent-based modelling technique can be an ideal tool to create models of complex socioeconomic systems. We consider the advantages compared to alternative, more conventional approaches available to analysts and management decision makers.","url":"https://doi.org/10.4018/978-1-59140-984-7.ch054","authors":["D. Collings"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch054","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.4018/978-1-4666-0942-6.ch001","name":"Bio-Interfaces","source":"crossref","abstract":"The bio-interfaces are widening the notions of complexity, affectiveness, and naturalness to an organic scale, in which the physiological information of the users acts as data to configure an interaction that responds to their emotional state in order to match the state of their body at that particular moment. In this context, the chapter discusses the role of the bio-interfaces in building a differentiated condition of interaction governed by the biology of the users. For this, the chapter presents applications of bio-interfaces in the areas of design, art, and games, considering their use as wearable devices that provide an organic interaction between man and machine, which could, in turn, lead these systems to a co-evolutionary relationship.","url":"https://doi.org/10.4018/978-1-4666-0942-6.ch001","authors":["Rachel Zuanon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-03-22T13:17:45Z","doi":"10.4018/978-1-4666-0942-6.ch001","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/978-3-030-25719-4_29","name":"Biologically Inspired Algorithm for Increasing the Number of Artificial Neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-25719-4_29","authors":["Lyubov V. Kolobashkina"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-07-16T15:02:34Z","doi":"10.1007/978-3-030-25719-4_29","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1142/9789812810250_0005","name":"Motion Detection with Bio-Inspired Analog MOS Circuits","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789812810250_0005","authors":["Hiroo Yonezu","Tetsuya Asai","Masahiro Ohtani","Naoki Ohshima"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-11-12T07:21:45Z","doi":"10.1142/9789812810250_0005","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/978-3-319-12084-3_7","name":"COSFIRE: A Brain-Inspired Approach to Visual Pattern Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-12084-3_7","authors":["George Azzopardi","Nicolai Petkov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-10-16T04:25:57Z","doi":"10.1007/978-3-319-12084-3_7","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/978-3-642-32615-8_66","name":"Bio-inspired Robotics Hands: A Work in Progress","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-32615-8_66","authors":["Ebrahim Mattar","Khaled Al Mutib"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-07-24T08:50:30Z","doi":"10.1007/978-3-642-32615-8_66","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/978-981-33-6773-9_2","name":"Harmony Search Algorithm for Structural Engineering Problems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-33-6773-9_2","authors":["Aylin Ece Kayabekir","Gebrail Bekdaş","Melda Yücel","Sinan Melih Nigdeli","Zong Woo Geem"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-31T12:03:02Z","doi":"10.1007/978-981-33-6773-9_2","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/978-981-33-6773-9_9","name":"Optimization and Artificial Neural Network Models for Reinforced Concrete Members","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-33-6773-9_9","authors":["Melda Yücel","Sinan Melih Nigdeli","Aylin Ece Kayabekir","Gebrail Bekdaş"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-31T12:03:02Z","doi":"10.1007/978-981-33-6773-9_9","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1039/d4ra02843k/v1/review1","name":"Review for \"Lotus leaf-inspired thermal insulation and anti-icing topography\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d4ra02843k/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-12T17:03:14Z","doi":"10.1039/d4ra02843k/v1/review1","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1587/transele.2024lhp0003","name":"An Embedded Intelligent System for Real-Time Image Classification with a Neuro-Inspired Color Constancy Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1587/transele.2024lhp0003","authors":["Akito MORITA","Hirotsugu OKUNO"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-26T22:34:25Z","doi":"10.1587/transele.2024lhp0003","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/nice69539.2026.11567466","name":"Memory Trade-Offs in Neuromorphic Communication Strategies of the Flywire Connectome on Loihi 2","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nice69539.2026.11567466","authors":["Felix Wang","Bradley H. Theilman","Fred Rothganger","Craig M. Vineyard","James B. Aimone","William Severa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-22T19:52:43Z","doi":"10.1109/nice69539.2026.11567466","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/978-3-642-34274-5_51","name":"How to Engineer Biologically Inspired Cognitive Architectures","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-34274-5_51","authors":["Valeria Seidita","Massimo Cossentino","Antonio Chella"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-09-30T13:21:47Z","doi":"10.1007/978-3-642-34274-5_51","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/978-3-642-37502-6","name":"Proceedings of The Eighth International Conference on Bio-Inspired Computing: Theories and Applications (BIC-TA), 2013","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-37502-6","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-05-07T08:25:55Z","doi":"10.1007/978-3-642-37502-6","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1080/01658107.2024.2311131","name":"Predictive Factors for Biopsy-Negative Giant Cell Arteritis and Alternative Diagnoses in a Neuro-Ophthalmology Context","source":"crossref","abstract":"","url":"https://doi.org/10.1080/01658107.2024.2311131","authors":["Lawrence Kwok","Emma Wu","Shivanand J. Sheth","Thomas G. Campbell","Rahul Chakrabarti"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-07T20:07:40Z","doi":"10.1080/01658107.2024.2311131","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1093/neuonc/noae165.1304","name":"Author Index","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuonc/noae165.1304","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-11T20:03:00Z","doi":"10.1093/neuonc/noae165.1304","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1021/acsaelm.4c00023.s001","name":"Aloe Vera-Inspired Cognitive Computing: Unveiling the Power of Pavlovian Conditioning and Pattern Recognition with a Synaptic RRAM Device","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acsaelm.4c00023.s001","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-20T13:10:20Z","doi":"10.1021/acsaelm.4c00023.s001","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1039/d4ra02843k/v1/review2","name":"Review for \"Lotus leaf-inspired thermal insulation and anti-icing topography\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d4ra02843k/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-12T17:03:14Z","doi":"10.1039/d4ra02843k/v1/review2","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.4018/978-1-5225-0788-8.ch002","name":"An Exploration of Backpropagation Numerical Algorithms in Modeling US Exchange Rates","source":"crossref","abstract":"This chapter applies the Backpropagation Neural Network (BPNN) trained with different numerical algorithms and technical analysis indicators as inputs to forecast daily US/Canada, US/Euro, US/Japan, US/Korea, US/Swiss, and US/UK exchange rate future price. The training algorithms are the Fletcher-Reeves, Polak-Ribiére, Powell-Beale, quasi-Newton (Broyden-Fletcher-Goldfarb-Shanno, BFGS), and the Levenberg-Marquardt (LM). The standard Auto Regressive Moving Average (ARMA) process is adopted as a reference model for comparison. The performance of each BPNN and ARMA process is measured by computing the Mean Absolute Error (MAE), Mean Absolute Deviation (MAD), and Mean of Squared Errors (MSE). The simulation results reveal that the LM algorithm is the best performer and show strong evidence of the superiority of the BPNN over ARMA process. In sum, because of the simplicity and effectiveness of the approach, it could be implemented for real business application problems to predict US currency exchange rate future price.","url":"https://doi.org/10.4018/978-1-5225-0788-8.ch002","authors":["Salim Lahmiri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-07-26T12:16:44Z","doi":"10.4018/978-1-5225-0788-8.ch002","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1201/9781315207353-14","name":"Chapter 13: Bio‒Inspired Computing Paradigms","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781315207353-14","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-09-08T08:20:48Z","doi":"10.1201/9781315207353-14","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.3390/s17061186","name":"Natural Inspired Intelligent Visual Computing and Its Application to Viticulture","source":"crossref","abstract":"This paper presents an investigation of natural inspired intelligent computing and its corresponding application towards visual information processing systems for viticulture. The paper has three contributions: (1) a review of visual information processing applications for viticulture; (2) the development of natural inspired computing algorithms based on artificial immune system (AIS) techniques for grape berry detection; and (3) the application of the developed algorithms towards real-world grape berry images captured in natural conditions from vineyards in Australia. The AIS algorithms in (2) were developed based on a nature-inspired clonal selection algorithm (CSA) which is able to detect the arcs in the berry images with precision, based on a fitness model. The arcs detected are then extended to perform the multiple arcs and ring detectors information processing for the berry detection application. The performance of the developed algorithms were compared with traditional image processing algorithms like the circular Hough transform (CHT) and other well-known circle detection methods. The proposed AIS approach gave a Fscore of 0.71 compared with Fscores of 0.28 and 0.30 for the CHT and a parameter-free circle detection technique (RPCD) respectively.","url":"https://doi.org/10.3390/s17061186","authors":["Li Ang","Kah Seng","Feng Ge"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-05-23T11:14:33Z","doi":"10.3390/s17061186","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/978-3-030-90582-8_12","name":"Organic Memristive Devices and Organic Electrochemical Transistors as Promising Elements for Bio-inspired Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-90582-8_12","authors":["Silvia Battistoni"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-23T13:07:05Z","doi":"10.1007/978-3-030-90582-8_12","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1016/j.pnpbp.2024.111075","name":"Editorial: Metabolomic aspects in neuropsychiatric disorders","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.pnpbp.2024.111075","authors":["Nela Pivac","Gordana Nedic Erjavec"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-21T00:58:19Z","doi":"10.1016/j.pnpbp.2024.111075","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1109/smartworld-uic-atc-scalcom-iop-sci.2019.00268","name":"Review of Innovative Cyberspace Security Research Inspired by Bionics Computing Methods","source":"crossref","abstract":"","url":"https://doi.org/10.1109/smartworld-uic-atc-scalcom-iop-sci.2019.00268","authors":["Jianfeng Chen","Chunlin Li","Zhihong Rao","Rui Xu","Chunhui Hu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-04-09T23:03:00Z","doi":"10.1109/smartworld-uic-atc-scalcom-iop-sci.2019.00268","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1007/978-981-99-0597-3_19","name":"Optimization Methods Using Music-Inspired Algorithm and Its Comparison with Nature-Inspired Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-99-0597-3_19","authors":["Debabrata Datta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-10T20:25:17Z","doi":"10.1007/978-981-99-0597-3_19","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1039/d4sm01340a/v1/review1","name":"Review for \"Training Allostery-Inspired Mechanical Response in Disordered Elastic Networks\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d4sm01340a/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-05T17:03:50Z","doi":"10.1039/d4sm01340a/v1/review1","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1007/978-3-642-32711-7_15","name":"Gossip Inspired Sensor Activation Protocol for a Correlated Chemical Environment","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-32711-7_15","authors":["Champake Mendis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-08-10T12:17:23Z","doi":"10.1007/978-3-642-32711-7_15","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.2174/9789815136357123010009","name":"Conclusion and Future Scope","source":"crossref","abstract":"The conclusion drawn from the research work presented in the book, with some recommendations for future work, is presented in this chapter.&amp;nbsp;","url":"https://doi.org/10.2174/9789815136357123010009","authors":["Balwinder S. Dhaliwal","Suman Pattnaik","Shyam Sundar Pattnaik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-26T11:51:56Z","doi":"10.2174/9789815136357123010009","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1201/9781003598404-10","name":"Comparison of Conventional, Bio-Inspired, and Hybrid Algorithms: A Review","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003598404-10","authors":["Ankita","Sudip Kumar Sahana"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-18T11:07:19Z","doi":"10.1201/9781003598404-10","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.3390/su142316322","name":"Nature-Inspired Cloud–Crowd Computing for Intelligent Transportation System","source":"crossref","abstract":"Nowadays, it is crucial to have effective road traffic signal timing, especially in an ideal traffic light cycle. This problem can be resolved with modern technologies such as artificial intelligence, cloud and crowd computing. We hereby present a functional model named Cloud–Crowd Computing-based Intelligent Transportation System (CCCITS). This model aims to organize traffic by changing the phase of traffic lights in real-time based on road conditions and incidental crowdsourcing sentiment. Crowd computing is responsible for fine-tuning the system with feedback. In contrast, the cloud is responsible for the computation, which can use AI to secure efficient and effective paths for users. As a result of its installation, traffic management becomes more efficient, and traffic lights change dynamically depending on the traffic volume at the junction. The cloud medium collects updates about mishaps through the crowd computing system and incorporates updates to refine the model. It is observed that nature-inspired algorithms are very useful in solving complex transportation problems and can deal with NP-hard situations efficiently. To establish the feasibility of CCCITS, the SUMO simulation environment was used with nature-inspired algorithms (NIA), namely, Particle Swarm Optimization (PSO), Ant Colony Optimization and Genetic Algorithm (GA), and found satisfactory results.","url":"https://doi.org/10.3390/su142316322","authors":["Vandana Singh","Sudip Kumar Sahana","Vandana Bhattacharjee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-07T02:18:48Z","doi":"10.3390/su142316322","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/978-0-387-34733-2","name":"Biologically Inspired Cooperative Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-0-387-34733-2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-11-27T12:41:06Z","doi":"10.1007/978-0-387-34733-2","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/978-4-431-88981-6_14","name":"Toward Biologically Inspired Constructive Computation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-4-431-88981-6_14","authors":["Hideyuki Nakashima"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-12-17T02:29:54Z","doi":"10.1007/978-4-431-88981-6_14","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch058","name":"Modeling an Artificial Stock Market","source":"crossref","abstract":"This chapter presents an artificial stock market created to analyze market dynamics from the behavior of investors. It argues that information—delivered by financial intermediaries as rating agencies and considered as cognitive institution—directs the decisions of investors who are heterogeneous agents endowed with capabilities of learning in a changing environment. The objective is to demonstrate that information influences market dynamics as it allows the coordination of the decisions of investment in the same direction: information is a focal point for investors and contributes to generate a speculative dynamic on the market.","url":"https://doi.org/10.4018/978-1-59140-984-7.ch058","authors":["S. Lavigne","S. Sanchez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch058","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch006","name":"Evolutionary Multi-Objective Optimization in Finance","source":"crossref","abstract":"This chapter provides a brief introduction of the use of evolutionary algorithms in the solution of multi-objective optimization problems (an area now called “evolutionary multi-objective optimization”). Besides providing some basic concepts and a brief description of the approaches that are more commonly used nowadays, the chapter also provides some of the current and future research trends in the area. In the final part of the chapter, we provide a short description of the sort of applications that multi-objective evolutionary algorithms have found in finance, identifying some possible paths for future research.","url":"https://doi.org/10.4018/978-1-59140-984-7.ch006","authors":["C. A.C. Coello"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch006","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/nabic.2010.5716369","name":"Predictive internal neural dynamics for delay compensation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2010.5716369","authors":["Jaerock Kwon","Yoonsuck Choe"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-02-18T14:03:54Z","doi":"10.1109/nabic.2010.5716369","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/nabic.2009.5393522","name":"Searching co-integrated portfolios by a genetic algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393522","authors":["Pravesh Kriplani","Luigi Troiano"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393522","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.4018/978-1-5225-0788-8.ch032","name":"Swarm Intelligence for Biometric Feature Optimization","source":"crossref","abstract":"Swarm Intelligence (SI) and bio-inspired computation has gathered great attention in research in the last few years. Numerous SI-based optimization algorithms have gained huge popularity to solve the complex combinatorial optimization problems, non-linear design system optimization, and biometric features selection and optimization. These algorithms are inspired by nature. In biometrics, face recognition is a non-intrusive method, and facial characteristics are probably the most common biometric features to identify individuals and provide a competent level of security. This chapter presents a novel biometric feature selection algorithm based on swarm intelligence (i.e. Particle Swarm Optimization [PSO] and Bacterial Foraging Optimization Algorithm [BFOA] metaheuristics approaches). This chapter provides the stepping stone for future researchers to unveil how swarm intelligence algorithms can solve the complex optimization problems to improve the biometric identification accuracy. In addition, it can be utilized for many different areas of application.","url":"https://doi.org/10.4018/978-1-5225-0788-8.ch032","authors":["Santosh Kumar","Deepanwita Datta","Sanjay Kumar Singh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-07-26T12:16:44Z","doi":"10.4018/978-1-5225-0788-8.ch032","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1093/nop/npad079","name":"Towards gender equity in neuro-oncology","source":"crossref","abstract":"","url":"https://doi.org/10.1093/nop/npad079","authors":["Solmaz Sahebjam","Heather Leeper"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-28T08:32:03Z","doi":"10.1093/nop/npad079","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:28.622Z"},{"id":"doi:10.1109/reconfig.2009.10","name":"Bio-inspired Self-Testing and Self-Organizing Bit Slice Processors","source":"crossref","abstract":"","url":"https://doi.org/10.1109/reconfig.2009.10","authors":["André Stauffer","Joël Rossier"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-20T21:06:20Z","doi":"10.1109/reconfig.2009.10","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/978-3-540-71805-5_53","name":"Self-organizing Bio-inspired Sound Transformation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-540-71805-5_53","authors":["Marcelo Caetano","Jônatas Manzolli","Fernando Zuben"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-06-20T13:01:18Z","doi":"10.1007/978-3-540-71805-5_53","addedAt":"2026-09-01T01:48:28.622Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.2174/266625581503220121141409","name":"Neural Computing and Bio-Inspired Algorithms for Engineering Problems","source":"crossref","abstract":"","url":"https://doi.org/10.2174/266625581503220121141409","authors":["Gaurav Dhiman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-01-23T12:50:26Z","doi":"10.2174/266625581503220121141409","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/nabic.2010.5716345","name":"Fractional order PI","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2010.5716345","authors":["P N Narayanaswamy","P Kanthabhabha","S E Hamamci"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-02-18T14:03:54Z","doi":"10.1109/nabic.2010.5716345","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/nabic.2009.5393653","name":"Biogeography based land cover feature extraction","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393653","authors":["VK Panchal","Samiksha Goel","Mitul Bhatnagar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393653","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.54254/2755-2721/20/20231098","name":"Spiking neural network research based on brain-inspired computing","source":"crossref","abstract":"With the shortcomings of deep learning in training cost, generalization ability, interpretability, and reliability, increasing attention was concentrated on the novel neuromorphic devices. A spiking neural network can better simulate the information transmission mode of biological neurons, and has the characteristics of strong computing power and low power consumption. Therefore, this study provides an overview of the pulse neural network from the perspective of its fundamental structure and operating principle. In terms of structure optimization, there is a summary of the aspects of the encoding mode of a spiking neural network and topology structure. In addition, the deficiency and development of the spiking neural network are analyzed. Pulsed neurons work by integrating the mechanism of firing, exchanging information with the time of the signal, and transmitting signals to adjacent neurons only when the membrane potential reaches a threshold. Spiking neural network (SNN) still lags behind traditional Artificial neural network (ANN) in accuracy, has large computational capacity and is inefficiently trained due to the complexity of pulsed neuron models. Future developments lie in bionics, deeper studies of the complex dynamics of the human brain, and synaptic connections in the human brain.","url":"https://doi.org/10.54254/2755-2721/20/20231098","authors":["Yichen Geng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-23T23:58:20Z","doi":"10.54254/2755-2721/20/20231098","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch010","name":"Human Nature in the Adaptation of Trust","source":"crossref","abstract":"This chapter pleads for more inspiration from human nature in agent-based modeling. As an illustration of an effort in that direction, it summarizes and discusses an agent-based model of the build-up and adaptation of trust between multiple producers and suppliers. The central question is whether, and under what conditions, trust and loyalty are viable in markets. While the model incorporates some well-known behavioral phenomena from the trust literature, more extended modeling of human nature is called for. The chapter explores a line of further research on the basis of notions of mental framing and frame switching on the basis of relational signaling, derived from social psychology.","url":"https://doi.org/10.4018/978-1-59140-984-7.ch010","authors":["B. Nooteboom"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch010","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/nigercon62786.2024.10927000","name":"Development and Performance Evaluation of a Neuro-Based Software for Modelling of Orbital Properties of Satellites","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nigercon62786.2024.10927000","authors":["Ogunlade Michael Adegoke","Adedayo Olukayode Ojo","Babatunde Segun Adejumobi","Saheed Lekan Gbadamosi","Ibitoye Oladapo Tolulope","Akeem Aderibigbe Adebomehin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-24T17:55:09Z","doi":"10.1109/nigercon62786.2024.10927000","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1016/j.comcom.2006.08.013","name":"Nature-inspired distributed computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.comcom.2006.08.013","authors":["Enrique Alba","El-ghazali Talbi","Albert Y. Zomaya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-09-13T07:16:35Z","doi":"10.1016/j.comcom.2006.08.013","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch017","name":"Agent-Based Modelnig with Boundedly Rational Agents","source":"crossref","abstract":"This chapter introduces an agent-based modeling framework for reproducing micro behavior in economic experiments. It gives an overview of the theoretical concept which forms the foundation of the framework as well as short descriptions of two exemplary models based on experimental data. The heterogeneous agents are endowed with a number of attributes like cooperativeness and employ more or less complex heuristics during their decision-making processes. The attributes help to distinguish between agents, and the heuristics distinguish between behavioral classes. Through this design, agents can be modeled to behave like real humans and their decision making is observable and traceable, features that are important when agent-based models are to be used in collaborative planning or participatory model-building processes.","url":"https://doi.org/10.4018/978-1-59140-984-7.ch017","authors":["E. Ebenhoh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch017","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/3-540-36080-8_11","name":"Biologically Inspired Fault-Tolerant Computer Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/3-540-36080-8_11","authors":["Andy Tyrrell"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-03-29T21:55:19Z","doi":"10.1007/3-540-36080-8_11","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/nabic.2009.5393654","name":"Localization using Average Landmark Vector in the presence of clutter","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393654","authors":["Pratik Chaudhari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5393654","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1016/b978-0-12-813788-8.00004-4","name":"Soft Computing Applications in Robot Vision","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-12-813788-8.00004-4","authors":["Alma Y. Alanis","Nancy Arana-Daniel","Carlos López-Franco"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-08T00:48:20Z","doi":"10.1016/b978-0-12-813788-8.00004-4","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/nabic.2011.6089424","name":"Dynamic learning of pairwise and three-way entanglement","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2011.6089424","authors":["E.C. Behrman","J.E. Steck"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-12-06T21:02:25Z","doi":"10.1109/nabic.2011.6089424","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/cccs.2015.7374201","name":"A quantum-inspired cuckoo search algorithm for the travelling salesman problem","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cccs.2015.7374201","authors":["Sumit Laha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-01-07T17:16:16Z","doi":"10.1109/cccs.2015.7374201","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/nabic.2010.5716298","name":"Outlier detection using humoral-mediated clustering (HAIS)","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2010.5716298","authors":["Waseem Ahmad","Ajit Narayanan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-02-18T14:03:54Z","doi":"10.1109/nabic.2010.5716298","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.4018/ijamc.2021010105","name":"A New Bio-Inspired Social Spider Algorithm","source":"crossref","abstract":"The concept of bio-inspired algorithms is used in real-world problems to search the efficient problem-solving methods. Evolutionary computation and swarm intelligence are outstanding examples of nature-inspired solution techniques of metahuristics. In this paper, an effort has been made to propose a modified social spider algorithm to solve global optimization problems in the real world. Social spiders used the foraging strategy, vibrations on the spider web to determine the positions of prey. The selection of vibration, estimated new position and calculation of the fitness function, has been furnished in details way as compared to different previously proposed swarm intelligence algorithms. Moreover, experimental result has been carried out by modified social spider on series of widely-used benchmark problem with four benchmark algorithms. Furthermore, a modified form of the proposed algorithm has superior performance as compared to other state-of-the-art metaheuristics algorithms.","url":"https://doi.org/10.4018/ijamc.2021010105","authors":["Dharmpal Singh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-07T12:02:52Z","doi":"10.4018/ijamc.2021010105","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/bimnics.2007.4610132","name":"U-Hopper: User-centric heteogeneous opportunistic middleware","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bimnics.2007.4610132","authors":["Iacopo Carreras","David Tacconi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-09-08T16:06:46Z","doi":"10.1109/bimnics.2007.4610132","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/bicta.2008.4656695","name":"Social interaction is a powerful optimiser: The particle swarm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2008.4656695","authors":["James Kennedy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-10-28T15:22:35Z","doi":"10.1109/bicta.2008.4656695","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/icmcs.2014.6911330","name":"Metamaterial-inspired high directive half-loop antenna","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icmcs.2014.6911330","authors":["Esthelladi Ramanandraibe","Mohamed Latrach","Ala Sharaiha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-10-08T16:49:12Z","doi":"10.1109/icmcs.2014.6911330","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/nabic.2009.5393389","name":"Image processing algorithms for improved character recognition and components inspection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393389","authors":["Anima Majumder"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393389","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/978-3-030-82427-3_8","name":"Brain-Inspired Algorithms for Processing of Visual Data","source":"crossref","abstract":"Abstract The study of the visual system of the brain has attracted the attention and interest of many neuro-scientists, that derived computational models of some types of neuron that compose it. These findings inspired researchers in image processing and computer vision to deploy such models to solve problems of visual data processing. In this paper, we review approaches for image processing and computer vision, the design of which is based on neuro-scientific findings about the functions of some neurons in the visual cortex. Furthermore, we analyze the connection between the hierarchical organization of the visual system of the brain and the structure of Convolutional Networks (ConvNets). We pay particular attention to the mechanisms of inhibition of the responses of some neurons, which provide the visual system with improved stability to changing input stimuli, and discuss their implementation in image processing operators and in ConvNets.","url":"https://doi.org/10.1007/978-3-030-82427-3_8","authors":["Nicola Strisciuglio","Nicolai Petkov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-07-20T07:03:33Z","doi":"10.1007/978-3-030-82427-3_8","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/ucc.2011.49","name":"An Extensible Cloud Platform Inspired by Operating Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ucc.2011.49","authors":["A. Sugiki","K. Kato"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-01-27T23:07:14Z","doi":"10.1109/ucc.2011.49","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1088/978-0-7503-6169-9ch3","name":"Memristive devices in brain-inspired computing","source":"crossref","abstract":"","url":"https://doi.org/10.1088/978-0-7503-6169-9ch3","authors":["Shaibal Mukherjee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-06T11:25:25Z","doi":"10.1088/978-0-7503-6169-9ch3","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1016/b978-0-08-102782-0.00012-5","name":"Memristive devices for deep learning applications","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-08-102782-0.00012-5","authors":["Damien Querlioz","Sabina Spiga","Abu Sebastian","Bipin Rajendran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-26T05:28:08Z","doi":"10.1016/b978-0-08-102782-0.00012-5","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch043","name":"Worker Performance Modeling in Manufacturing Systems Simulation","source":"crossref","abstract":"Discrete event simulation is generally recognized as a valuable aid to the strategic and tactical decision making that is required in the evaluation stage of the manufacturing systems design and redesign processes. It is common practice to represent workers within these simulation models as simple resources, often using deterministic performance values derived from time studies. This form of representing the factory worker ignores the potentially large effect that human performance variation can have on system performance, and it particularly affects the predictive capability of simulation models with a high proportion of manual tasks. The intentions of the chapter are twofold: firstly, to raise awareness of the importance of considering human performance variation in such simulation models; and secondly, to present some conceptual ideas for developing a worker agent for representing worker performance in manufacturing systems simulation models.","url":"https://doi.org/10.4018/978-1-59140-984-7.ch043","authors":["P. Siebers"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch043","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/nabic.2011.6089658","name":"Artificial immune system in risk of falling classification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2011.6089658","authors":["Dragan Simic","Svetlana Simic"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-12-06T16:02:25Z","doi":"10.1109/nabic.2011.6089658","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1201/9781003313649-11","name":"Application of Genetic Algorithms and Partial Swarm Optimization in Cloud Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003313649-11","authors":["Krishn Kumar Mishra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-06T18:34:26Z","doi":"10.1201/9781003313649-11","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/bicta.2009.5338123","name":"Partitioning the state space by critical states","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2009.5338123","authors":["Zhao Jin","WeiYi Liu","Jian Jin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-11-24T13:50:07Z","doi":"10.1109/bicta.2009.5338123","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1016/b978-0-08-102782-0.00017-4","name":"Synaptic realizations based on memristive devices","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-08-102782-0.00017-4","authors":["Valerio Milo","Thomas Dalgaty","Daniele Ielmini","Elisa Vianello"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-26T05:28:46Z","doi":"10.1016/b978-0-08-102782-0.00017-4","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.17303/jaist.2025.2.105","name":"Optimizing Bat-Inspired Navigation Systems with Automata-Based Theory","source":"crossref","abstract":"","url":"https://doi.org/10.17303/jaist.2025.2.105","authors":["Syed Asif Ali"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-16T11:53:35Z","doi":"10.17303/jaist.2025.2.105","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/icsc.2010.51","name":"Web-Inspired Sentence Complexity-Index","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icsc.2010.51","authors":["Juan-Pablo Ramirez","Alexander Raake","Ashkan Sharifi","Hamed Ketabdar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-11-19T16:30:33Z","doi":"10.1109/icsc.2010.51","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/978-3-540-44999-7_49","name":"Biology-Inspired Approaches to Peer-to-Peer Computing in BISON","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-540-44999-7_49","authors":["Alberto Montresor","Ozalp Babaoglu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-12-29T16:56:32Z","doi":"10.1007/978-3-540-44999-7_49","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/icci-cc.2017.8109761","name":"Brain-inspired systems and predicative competence","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icci-cc.2017.8109761","authors":["Rodolfo A. Fiorini"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-11-16T16:49:41Z","doi":"10.1109/icci-cc.2017.8109761","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/978-981-15-3836-0_1","name":"Introduction","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-15-3836-0_1","authors":["Aziz Ouaarab"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-03-24T13:02:55Z","doi":"10.1007/978-981-15-3836-0_1","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/978-3-319-59156-8_15","name":"Slime Mould and Fungal Foraging Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-59156-8_15","authors":["Anthony Brabazon","Seán McGarraghy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-09-26T18:09:36Z","doi":"10.1007/978-3-319-59156-8_15","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/nabic.2009.5393661","name":"An overview of neural networks in simulation soccer","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393661","authors":["William Plant","Gerald Schaefer"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393661","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/bicta.2009.5338129","name":"Spectral clustering for detecting protein complexes in PPI networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2009.5338129","authors":["Guimin Qin","Lin Gao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-11-24T18:50:07Z","doi":"10.1109/bicta.2009.5338129","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/nabic.2011.6089604","name":"The effect of redundancy and neutrality in genetic search","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2011.6089604","authors":["Marisol B. Correia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-12-06T21:02:25Z","doi":"10.1109/nabic.2011.6089604","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/nabic.2009.5393461","name":"Distributed area coverage using robot flocks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393461","authors":["Ke Cheng","Yi Wang","Prithviraj Dasgupta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393461","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/bimnics.2007.4610125","name":"Mapping external functionalities into autonomic services","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bimnics.2007.4610125","authors":["Borbala Katalin Benko","Robert Schulcz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-09-08T16:06:46Z","doi":"10.1109/bimnics.2007.4610125","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/ibica.2011.98","name":"Genetic and Ant Algorithms Based Focused Crawler Design","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ibica.2011.98","authors":["Song Zheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-01-06T16:44:03Z","doi":"10.1109/ibica.2011.98","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/978-3-030-33820-6","name":"Nature Inspired Computing for Data Science","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-33820-6","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-11-26T05:02:34Z","doi":"10.1007/978-3-030-33820-6","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1093/neuonc/noae056","name":"Editorial Scholars Program (2023–2024)","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuonc/noae056","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-03T10:20:12Z","doi":"10.1093/neuonc/noae056","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1016/b978-0-44-322341-9.00005-7","name":"Contents","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-44-322341-9.00005-7","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-24T10:20:12Z","doi":"10.1016/b978-0-44-322341-9.00005-7","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1093/neuonc/noae162","name":"Design and conduct of theranostic trials in neuro-oncology: Challenges and opportunities","source":"crossref","abstract":"Abstract Theranostics is a new treatment modality integrating molecular imaging with targeted radionuclide therapy. Theranostic agents have received regulatory approval for some systemic cancers and have therapeutic potential in neuro-oncology. As clinical trials are developed to evaluate the efficacy of theranostic agents in brain tumors, specific considerations will have to be considered, taking into account lessons learned from previous studies examining other treatment modalities in neuro-oncology. These include the need for molecular imaging or surgical window-of-opportunity studies to confirm adequate passage across the blood-brain barrier, optimize eligibility criteria, and selection of the most appropriate response criteria and endpoints to address issues such as pseudoprogression. This review will discuss some of the issues that should be considered when designing clinical trials for theranostic agents.","url":"https://doi.org/10.1093/neuonc/noae162","authors":["Patrick Y Wen","Matthias Preusser","Nathalie L Albert"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-05T17:17:43Z","doi":"10.1093/neuonc/noae162","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1007/0-387-27705-6_18","name":"Predicting Grid Resource Performance Online","source":"crossref","abstract":"","url":"https://doi.org/10.1007/0-387-27705-6_18","authors":["Rich Wolski","Graziano Obertelli","Matthew Allen","Daniel Nurmi","John Brevik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-03-23T06:57:04Z","doi":"10.1007/0-387-27705-6_18","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/nabic.2009.5393671","name":"Credit scoring using Artificial Immune System algorithms: A comparative study","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393671","authors":["Antariksha Bhaduri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5393671","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/nabic.2010.5716351","name":"Evolution of a yoga performing humanoid","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2010.5716351","authors":["Dhammika Suresh Hettiarachchi","Hitoshi Iba"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-02-18T14:03:54Z","doi":"10.1109/nabic.2010.5716351","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/978-981-99-3970-1","name":"Benchmarks and Hybrid Algorithms in Optimization and Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-99-3970-1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-21T15:04:55Z","doi":"10.1007/978-981-99-3970-1","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/bimnics.2007.4610090","name":"Detecting DoS attacks using packet size distribution","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bimnics.2007.4610090","authors":["Ping Du","Shunji Abe"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-09-08T16:06:46Z","doi":"10.1109/bimnics.2007.4610090","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/nabic.2009.5393754","name":"Particle swarm optimization based regularization for image restoration","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393754","authors":["Ratnakar Dash","Banshidhar Majhi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393754","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/bimnics.2007.4610097","name":"Evaluating activator-inhibitor mechanisms for sensors coordination","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bimnics.2007.4610097","authors":["Giovanni Neglia","Giuseppe Reina"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-09-08T16:06:46Z","doi":"10.1109/bimnics.2007.4610097","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/s00500-004-0414-3","name":"Neuro-computing based short range prediction of some meteorological parameters during the pre-monsoon season","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00500-004-0414-3","authors":["Sutapa Chaudhuri","Surajit Chattopadhyay"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-01-28T08:45:39Z","doi":"10.1007/s00500-004-0414-3","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1155/acis/8864479","name":"Software Defect Prediction With Quantum‐Inspired Feature Selection","source":"crossref","abstract":"Accurate software defect prediction is crucial for reducing maintenance costs and improving system reliability. Effective feature selection ensures that models focus on the most informative metrics while avoiding overfitting and excessive complexity. We introduce a quantum‐inspired evolutionary algorithm (QIEA) that encodes candidate feature subsets using probability amplitudes and then iteratively refines them through adaptive rotation operations inspired by quantum mechanics. Our approach simultaneously optimizes prediction quality and model simplicity by balancing F1‐score maximization with subset size reduction. We evaluate QIEA on four public benchmarks—NASA PC1, CM1, and PROMISE KC1, JM1—using both within‐project cross‐validation and leave‐one‐project‐out protocols. Across all scenarios, QIEA delivers a consistent absolute improvement of six percentage points in F1‐score over classical genetic algorithms, while reducing the number of selected features by 30–40 percent. Hypervolume analysis confirms that our method achieves superior tradeoffs between accuracy and compactness. The experimental setup and parameter settings are described in detail throughout this paper.","url":"https://doi.org/10.1155/acis/8864479","authors":["Mohammad Salah Uddin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-06T05:15:12Z","doi":"10.1155/acis/8864479","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/978-3-031-71464-1_32","name":"Enhancing Adversarial Robustness in Automatic Modulation Recognition with Dynamical Systems-Inspired Deep Learning Frameworks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-71464-1_32","authors":["Xiaohu Li","Yajian Zhou","Hongchao Yan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-12T17:49:38Z","doi":"10.1007/978-3-031-71464-1_32","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1080/17590914.2024.2394352","name":"Implications of Iron in Ferroptosis, Necroptosis, and Pyroptosis as Potential Players in TBI Morbidity and Mortality","source":"crossref","abstract":"","url":"https://doi.org/10.1080/17590914.2024.2394352","authors":["Makenzie Nolt","James Connor"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T15:04:05Z","doi":"10.1080/17590914.2024.2394352","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1093/neuonc/noae064.721","name":"LMIC-04. BUILDING PEDIATRIC NEURO-ONCOLOGY CAPACITY IN LMICS THROUGH MULTIDISCIPLINARY EDUCATION AND COLLABORATION","source":"crossref","abstract":"Abstract BACKGROUND The St. Jude Global Academy Neuro-Oncology Training Seminar (NOTS) is a course in pediatric neuro-oncology (PNO) designed for physicians from low-income and middle-income countries. The curriculum was systematically designed and includes 9 weeks of online learning and a 5-day in-person workshop. The NOTS has been run 3 times: 2019, 2022, and 2023. We sought to evaluate the outcomes of these courses. METHODS After the initial course where institutions were invited, applying institutions were selected based on the size of the neuro-oncology program, multidisciplinary representation, and perceived impact of the course. Data on course participants have been prospectively collected. A survey evaluating course impact was completed by graduates. RESULTS For 2022, 51 institutions from 29 countries applied and 15 were selected. In 2023, 60 institutions from 31 countries applied and 18 were selected. Overall, 41 institutions from 29 countries have participated in NOTS. Furthermore, 191 individuals, including 68 pediatric oncologists, 37 neurosurgeons, 22 radiation oncologists, 19 radiologists, 18 pathologists, and 27 other specialists have participated. Survey responses (n=39) describe that 47% did not have multidisciplinary tumor boards (MDTB) before NOTS. 55% of those institutions now have MDTB, all claiming to be influenced by their participation in NOTS. 89% of participants claim that multidisciplinary communication improved after the course. The participants of NOTS have continued to be engaged beyond the course through the creation of the Global Alliance in Pediatric Neuro-Oncology (GAPNO). GAPNO workstreams have included monthly cases discussions, a multisite retrospective review of medulloblastoma outcomes collecting &amp;gt;300 patients in 8 countries, and the design of a comprehensive tool to evaluate PNO services. CONCLUSIONS A multidisciplinary course focused on pediatric CNS tumors care for resource-limited settings can help expand international engagement in PNO. Furthermore, through multidisciplinary collaboration, the PNO community can be galvanized to expand activities in capacity building.","url":"https://doi.org/10.1093/neuonc/noae064.721","authors":["Daniel Moreira","Allyson Andujar","Ibrahim Qaddoumi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-18T06:54:29Z","doi":"10.1093/neuonc/noae064.721","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1109/mcse.2008.53","name":"Computer Vision, Inspired by the Human Brain","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mcse.2008.53","authors":["Pam Frost Gorder"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-02-21T20:22:55Z","doi":"10.1109/mcse.2008.53","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1016/j.micpro.2020.103227","name":"Fog Computing-inspired Smart Home Framework for Predictive Veterinary Healthcare","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.micpro.2020.103227","authors":["Munish Bhatia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-14T21:11:23Z","doi":"10.1016/j.micpro.2020.103227","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1097/wno.0000000000002166","name":"The 50th Annual Meeting of the North American Neuro-Ophthalmology Society in Honolulu, Hawaii","source":"crossref","abstract":"","url":"https://doi.org/10.1097/wno.0000000000002166","authors":["Meagan D. Seay","Kathleen B. Digre"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-06T04:02:08Z","doi":"10.1097/wno.0000000000002166","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1093/neuonc/noae144.431","name":"P22.17.B THE NEURO-ONCOLOGICAL CAREGIVER ROLES AND RESPONSIBILITIES - A QUANTITATIVE SURVEY","source":"crossref","abstract":"Abstract BACKGROUND In Denmark, cancer treatment is increasingly offered on an outpatient basis. This adds a responsibility on the caregivers, who often handle treatment agreements, provide 24/7 care, and offer practical support within the home environment. Especially, caregivers of individuals with brain cancer due to the disease’s unique characteristics, including cognitive and physical alterations. Qualitative exploration of the caregiver role has been undertaken, but there remains a notable absence of quantitative measurements regarding the burden faced by neuro-oncological caregivers. Therefore, this study aimed to quantitatively investigate the impact of caregiving on individuals caring for brain cancer patients. MATERIAL AND METHODS A cross-sectional study was conducted. The questionnaire used was the validated and standardized questionnaire “Caregiver roles and responsibilities scale” (CRRS). It consists of 51 questions grouped into 6 core areas: Support and Impact, Lifestyle, Emotional Health and Well-being, Self-care, Financial situation, and Work and Career. Responses are scored on a 5-point Likert scale ranging from 0 (“not at all”) to 4 (“very much”). The CRRS questionnaire has an official scoring guideline that calculates a score ranging from 0-152, in which 0 accounts for the most burdened, and 152 the least burdened. However, there isn’t a specific cut-off score to indicate when the CRRS score should raise concern. The questionnaire was distributed for two weeks to all caregivers attending the neuro-oncology outpatient clinic at Rigshospitalet. RESULTS Included were 27 primary caregivers (out of 30 eligible). 64% were female, and age was categorized in under 65 (younger) and over 65 (older); with a range from 39 to 80 years old. Data indicated that the younger caregivers (CRRS score = 87), those being in the initial 6 months of the disease (CRRS score = 85), and those receiving minimal to no practical assistance from family and friends (CRRS score = 90) were at a higher risk of burden, compared to those being older (CRRS score = 103), in the stage of 12-24 month post-diagnose (CRRS score = 106) and who received moderate to substantial support (CRRS score = 101). 18% of women rated their physical health as impaired to a large degree due to the patient’s disease, and none of the men noted this. CONCLUSION The CRRS questionnaire could serve as a valuable screening tool to identify the specific support required by individual caregivers. The study indicates that female caregivers under the age of 65, particularly within the initial 6 months of the disease onset, and those lacking practical support from friends and family, tend to experience elevated levels of burden. The study’s findings do not specify the frequency or timing for administering the CRRS questionnaire as a screening tool, initial steps could involve integrating the screening process within the first six months of caregiving.","url":"https://doi.org/10.1093/neuonc/noae144.431","authors":["V R Smith","S S Kjærgård","K Piil"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-17T18:20:46Z","doi":"10.1093/neuonc/noae144.431","addedAt":"2026-09-01T01:48:28.623Z","updatedAt":"2026-09-01T01:48:28.623Z"},{"id":"doi:10.1109/ic3.2015.7346689","name":"Firefly inspired feature selection for face recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ic3.2015.7346689","authors":["Vandana Agarwal","Surekha Bhanot"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-08T17:17:05Z","doi":"10.1109/ic3.2015.7346689","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.32604/cmes.2025.060973","name":"Quantum Inspired Adaptive Resource Management Algorithm for Scalable and Energy Efficient Fog Computing in Internet of Things (IoT)","source":"crossref","abstract":"","url":"https://doi.org/10.32604/cmes.2025.060973","authors":["Sonia Khan","Naqash Younas","Wahib Jamal Khan","Musaed Alhussein","Khursheed Aurangzeb","Muhammad Shahid Anwar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-02T22:34:11Z","doi":"10.32604/cmes.2025.060973","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1049/pbpc053e_ch3","name":"Application aspects of nature-inspired optimization algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1049/pbpc053e_ch3","authors":["Abhinav Kumar","Subodh Srivastava","Vinay Kumar","Niharika Kulshrestha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-16T08:07:55Z","doi":"10.1049/pbpc053e_ch3","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1007/978-3-030-96299-9_10","name":"NLP and Logic Reasoning for Fully Automating Test","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_10","authors":["Nesrine Bnouni Rhim","Mouna Ben Mabrouk"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_10","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1016/b978-0-08-102782-0.00004-6","name":"Magnetic and ferroelectric memories","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-08-102782-0.00004-6","authors":["Nicolas Locatelli","Liza Herrera Diez","Thomas Mikolajick"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-26T05:26:20Z","doi":"10.1016/b978-0-08-102782-0.00004-6","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1145/3714394.3756152","name":"MS-PDPM: A Bio-Inspired Framework for Underwater Wearable Acoustic Communication","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3714394.3756152","authors":["Zhiwen Qiao","Jie Zhang","Jiaming Zhang","Songzuo Liu","Mengran Zhao","Simon L. Cotton"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-29T21:13:49Z","doi":"10.1145/3714394.3756152","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1007/978-3-031-27499-2_29","name":"Impact of Green Hydrogen Production on Energy Pricing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_29","authors":["Judite Ferreira","José Boaventura"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_29","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1145/3411763.3450370","name":"Perfectly Imperfect: A Speculation about Wabi-Sabi Inspired User Experience Design","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3411763.3450370","authors":["Aparna Kongot","Alexandra Matz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-05-08T00:36:14Z","doi":"10.1145/3411763.3450370","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1109/bicta.2008.4656703","name":"Input data analysis by neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2008.4656703","authors":["Tim Hendtlass"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-10-28T15:22:35Z","doi":"10.1109/bicta.2008.4656703","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1109/ibica.2011.90","name":"Analyzing Thermodynamics of DNA Spaces","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ibica.2011.90","authors":["Maryam Nuser"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-01-06T16:44:03Z","doi":"10.1109/ibica.2011.90","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1088/1361-6463/ad7a82/v4/decision1","name":"Decision letter for \"Brain-inspired computing with self-assembled networks of nano-objects\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1361-6463/ad7a82/v4/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-19T17:52:56Z","doi":"10.1088/1361-6463/ad7a82/v4/decision1","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch001","name":"Artificially in Social Sciences","source":"crossref","abstract":"This chapter provides an introduction to the modern approach of artificiality and simulation in social sciences. It presents the relationship between complexity and artificiality, before introducing the field of artificial societies which greatly benefited from the fast increase of computer power, gifting social sciences with formalization and experimentation tools previously owned by the “hard” sciences alone. It shows that as “a new way of doing social sciences,” artificial societies should undoubtedly contribute to a renewed approach in the study of sociality and should play a significant part in the elaboration of original theories of social phenomena.","url":"https://doi.org/10.4018/978-1-59140-984-7.ch001","authors":["J. Rennard"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch001","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1007/978-3-319-59156-8_9","name":"Ant Foraging Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-59156-8_9","authors":["Anthony Brabazon","Seán McGarraghy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-09-26T14:09:36Z","doi":"10.1007/978-3-319-59156-8_9","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1109/wac.2002.1049513","name":"Psychologically-inspired integrated circuits for human-like soft computing systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/wac.2002.1049513","authors":["T. Shibata"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-06-26T00:51:07Z","doi":"10.1109/wac.2002.1049513","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1109/sofa.2007.4318320","name":"Semantics of Dempster-Shafer Inspired Si-Logic","source":"crossref","abstract":"","url":"https://doi.org/10.1109/sofa.2007.4318320","authors":["Dmitri Iourinski","Roman Belavkin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-09-24T18:55:02Z","doi":"10.1109/sofa.2007.4318320","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1109/bimnics.2007.4610115","name":"Panelists from industry and academia - Moderator: Mihaela Ulieru","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bimnics.2007.4610115","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-06-07T13:33:41Z","doi":"10.1109/bimnics.2007.4610115","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1007/978-981-15-3836-0","name":"Discrete Cuckoo Search for Combinatorial Optimization","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-15-3836-0","authors":["Aziz Ouaarab"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-03-24T09:02:55Z","doi":"10.1007/978-981-15-3836-0","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1007/978-981-33-6195-9_2","name":"Automatic Generation Control Scheme for Power Quality Improvement of Multi-source Power Generating System with Secondary Controller Optimization Using Parameter-Setting-Free Harmony Search","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-33-6195-9_2","authors":["K. Jagatheesan","B. Anand","Soumadip Sen","Swarnavo Mondal","Sourav Samanta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-17T09:08:02Z","doi":"10.1007/978-981-33-6195-9_2","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1007/978-3-030-96299-9_33","name":"Reducing Time Complexity of Fuzzy C Means Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_33","authors":["Amrita Bhattacherjee","Sugata Sanyal","Ajith Abraham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_33","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1007/978-3-319-59156-8_16","name":"Plant Foraging Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-59156-8_16","authors":["Anthony Brabazon","Seán McGarraghy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-09-26T18:09:36Z","doi":"10.1007/978-3-319-59156-8_16","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1145/3247393","name":"Session details: Grid computing","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3247393","authors":["Carlo Mastroianni"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-06T22:32:33Z","doi":"10.1145/3247393","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1142/9789812790262_0014","name":"CONCLUSIONS — THE MIND THAT MATTERS","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789812790262_0014","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-04-12T00:09:25Z","doi":"10.1142/9789812790262_0014","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1109/bicta.2009.5338157","name":"A novel cooperative bacterial foraging algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2009.5338157","authors":["Yichuan Shao","Hanning Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-11-24T13:50:07Z","doi":"10.1109/bicta.2009.5338157","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1016/j.asoc.2016.10.010","name":"Evolutionary neuro-fuzzy system for surface roughness evaluation","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2016.10.010","authors":["Ilija Svalina","Goran Šimunović","Tomislav Šarić","Roberto Lujić"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-10-21T14:20:13Z","doi":"10.1016/j.asoc.2016.10.010","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1093/noajnl/vdaf213.119","name":"SVSC-07 The Impact of Technological Advances in Nursing Care of Neuro-oncological Pathologies; Kenya","source":"crossref","abstract":"Abstract Technology provides tools that oncology nurses today use to transform cancer care for their patients as well as the practice. This review explores the impact of recent digital technologies on nursing practice highlighting its benefits and limitations. It examines the use of electronic health records (EHRs), telehealth devices, mobile devices, wearable technology, simulation technology and artificial intelligence in nursing care of patients. Additionally, it discusses the impact of digitization on patient outcomes, ethics and nursing education. This review aims at providing information on the evolving technologies currently used and the importance of embracing their integration in the nursing practice to deliver high quality and patient-centered care. This is an explorative study carried out in oncology units at various hospitals in Kenya. The study population includes cancer patients and oncology nurses. The data collected by reviewing existing records, interviews and empirical evidence shows that technological innovations improve the management of neurological pathologies in various ways. Nurses have access to a vast amount of information and resources at their fingertips. Technology has streamlined processes such as patient documentation, medication management and data analysis leading to improved accuracy and efficiency. Communication between healthcare professions is more efficient enabling better coordination and collaboration in enhanced patient care. However, concerns were raised on data privacy, job displacement, potential for replacement of human touch and the generational gap in integration of the tools in the 21st century. In conclusion, it is recommended to embrace these innovations in the clinical practice. Nursing practice now demands critical thinking and technological adaptability.","url":"https://doi.org/10.1093/noajnl/vdaf213.119","authors":["Joy Yaya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-09T08:40:54Z","doi":"10.1093/noajnl/vdaf213.119","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.23919/indiacom66777.2025.11115611","name":"Biologically-Inspired Artificial Lymphocyte Networks for Adaptive and Scalable Malware Detection Against Zero-Day and Persistent Threats","source":"crossref","abstract":"","url":"https://doi.org/10.23919/indiacom66777.2025.11115611","authors":["G. Bala Krishna","Gidigam Udayasri","Rupa Devi T","K. Gnaneshwar","D. Sandhya Rani","Rajitha Ala"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-21T18:17:57Z","doi":"10.23919/indiacom66777.2025.11115611","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1109/icc.2018.8422666","name":"Computing-Inspired Detection of Multiple Cancers","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icc.2018.8422666","authors":["Shaolong Shi","Yifan Chen","Xin Yao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-08-20T22:51:41Z","doi":"10.1109/icc.2018.8422666","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1109/hpcsim.2011.5999905","name":"Bacteria inspired patterns grown with hyperbolic cellular automata","source":"crossref","abstract":"","url":"https://doi.org/10.1109/hpcsim.2011.5999905","authors":["Maurice Margenstern"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-08-31T15:18:55Z","doi":"10.1109/hpcsim.2011.5999905","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1007/978-3-211-78775-5_5","name":"Locomotion as a Spatial-temporal Phenomenon: Models of the Central Pattern Generator","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-211-78775-5_5","authors":["Paolo Arena"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-11-29T07:44:42Z","doi":"10.1007/978-3-211-78775-5_5","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1088/1361-6463/ad7a82/v5/decision1","name":"Decision letter for \"Brain-inspired computing with self-assembled networks of nano-objects\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1361-6463/ad7a82/v5/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-19T17:52:56Z","doi":"10.1088/1361-6463/ad7a82/v5/decision1","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1007/978-3-319-59156-8_8","name":"Aquatic Foraging Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-59156-8_8","authors":["Anthony Brabazon","Seán McGarraghy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-09-26T14:09:36Z","doi":"10.1007/978-3-319-59156-8_8","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1109/nabic.2011.6089605","name":"Parallel swarm optimization for web information retrieval","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2011.6089605","authors":["Habiba Drias"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-12-06T21:02:25Z","doi":"10.1109/nabic.2011.6089605","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1109/rcar65431.2025.11139433","name":"VRT*: Optimal Sampling-Based Multi-Robot Path Planning via Voronoi-Inspired Filtering Framework","source":"crossref","abstract":"","url":"https://doi.org/10.1109/rcar65431.2025.11139433","authors":["Feng Han","Yanjie Chen","Zhennan Lai","Jingkai Wang","Liping Zhang","Zhiqiang Miao","Yaonan Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-04T18:16:38Z","doi":"10.1109/rcar65431.2025.11139433","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1109/mind67540.2025.11351881","name":"SEEND: A Spike-Based End-to-End Framework for Energy-Efficient Speaker Diarization","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mind67540.2025.11351881","authors":["Kexin Shi","Hanwen Liu","Jibin Wu","Wenyu Chen","Malu Zhang","Yang Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-27T04:49:35Z","doi":"10.1109/mind67540.2025.11351881","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.14257/ijhit.2015.8.9.17","name":"Neuro Inspired Genetic Hybrid Algorithm for Active Power Dispatch Planning Problem in Small Scale System","source":"crossref","abstract":"","url":"https://doi.org/10.14257/ijhit.2015.8.9.17","authors":["Navpreet Singh Tung","Sandeep Chakravorty"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-11-13T00:17:20Z","doi":"10.14257/ijhit.2015.8.9.17","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1145/3517343.3517345","name":"Stable Lifelong Learning: Spiking neurons as a solution to instability in plastic neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3517343.3517345","authors":["Samuel Schmidgall","Joe Hays"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-05-04T07:28:08Z","doi":"10.1145/3517343.3517345","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1109/iccpct65132.2025.11176648","name":"Advanced Speed Control of Induction Motors with Addax-Inspired Optimization Strategy for Robust Performance in Varying Load Conditions","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccpct65132.2025.11176648","authors":["S Manikandan","M Priyadharshini","N. Shanthi","G.W. Martin","P. Karputha Pandi","S. Sivarajan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-09T17:50:30Z","doi":"10.1109/iccpct65132.2025.11176648","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1007/978-3-030-73603-3_21","name":"Analysis of Socio-cognitive Skills Among 90’s and 2k’s Generations Using Machine Learning Techniques","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-73603-3_21","authors":["Natarajan Anitha","Rangasamy Devi Priya","Chelladurai Baskar","V. Devi Surya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-04-09T06:04:19Z","doi":"10.1007/978-3-030-73603-3_21","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1007/978-3-030-16681-6_25","name":"A Modified IEEE 802.11 Protocol for Increasing Confidentiality in WLANs","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-16681-6_25","authors":["Abhijath Ande","Nakul Singh","B. K. S. P. Kumar Raju"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-22T21:26:26Z","doi":"10.1007/978-3-030-16681-6_25","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1109/icoiics67115.2025.11390653","name":"Threat Vision: A Next-Generation SOC-Inspired Platform Leveraging Hybrid Malware Analysis and Real-Time Social Media Threat Intelligence for Enhanced Cybersecurity","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icoiics67115.2025.11390653","authors":["Harshith C M","Nihal Manohar","Shreya Venugopal","Amaan Kudroli","Neeraj Jha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-24T20:54:18Z","doi":"10.1109/icoiics67115.2025.11390653","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1080/01658107.2025.2507771","name":"Directors of Accredited Neuro-Ophthalmology Fellowship Programs: A Descriptive Analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1080/01658107.2025.2507771","authors":["Nuha Arefin","Carolyn Huynh","Jared Moon","Eileen Bowden","Moe H. Aung","Jane Edmond"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-21T12:08:34Z","doi":"10.1080/01658107.2025.2507771","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1007/978-3-319-28031-8_25","name":"Understanding the Consequences of Social Isolation Using Fireworks Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-28031-8_25","authors":["Lourdes Margain","Alberto Ochoa","Teresa Padilla","Saúl González","Jorge Rodas","Odalid Tokudded","Julio Arreola"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-13T20:02:33Z","doi":"10.1007/978-3-319-28031-8_25","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1007/978-3-319-28031-8_8","name":"Gravitational Search Algorithm to Solve Open Vehicle Routing Problem","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-28031-8_8","authors":["Ali Asghar Rahmani Hosseinabadi","Maryam Kardgar","Mohammad Shojafar","Shahab Shamshirband","Ajith Abraham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-14T01:02:33Z","doi":"10.1007/978-3-319-28031-8_8","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1007/978-3-030-73603-3_3","name":"A Novel Clustering Based Undersampling Algorithm for Imbalanced Data Sets Using Artificial Bee Colony Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-73603-3_3","authors":["O. A. Ajilisa","V. P. Jagathyraj","M. K. Sabu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-04-09T06:04:19Z","doi":"10.1007/978-3-030-73603-3_3","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1109/mind67540.2025.11351711","name":"JQA: Joint Design of Hardware-Friendly Quantization and Efficient Accelerator for Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mind67540.2025.11351711","authors":["Hanwen Liu","Kexin Shi","Wenyu Chen","Malu Zhang","Yang Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-27T04:49:35Z","doi":"10.1109/mind67540.2025.11351711","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1145/3517343.3517348","name":"Oscillatory Neural Network as Hetero-Associative Memory for Image Edge Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3517343.3517348","authors":["Madeleine Abernot","Thierry Gil","Aida Todri-Sanial"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-05-04T07:28:08Z","doi":"10.1145/3517343.3517348","addedAt":"2026-09-01T01:48:29.740Z","updatedAt":"2026-09-01T01:48:29.740Z"},{"id":"doi:10.1109/vlsid60093.2024.00024","name":"A Neuro Inspired Pulse Density Modulator Sensing Unipolar and Bipolar Current Signals","source":"crossref","abstract":"","url":"https://doi.org/10.1109/vlsid60093.2024.00024","authors":["Tamal Chowdhury","Pradip Mandal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-02T18:38:37Z","doi":"10.1109/vlsid60093.2024.00024","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/icmlc63072.2024.10935140","name":"Neuro-Cognitive Inspired Deep Learning for Enhanced Navigation in No-Till Agriculture Using Multisensory Data","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icmlc63072.2024.10935140","authors":["Anhar Risnumawan","Fernando Ardilla","Yoshimasa Nakamura","Naoyuki Kubota"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-28T02:39:19Z","doi":"10.1109/icmlc63072.2024.10935140","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.21917/ijsc.2025.0540","name":"AN ADAPTIVE PATTERN-DRIVEN OPTIMIZATION - TAILOR-INSPIRED METAHEURISTIC FOR SOLVING CONSTRAINED REAL-WORLD OPTIMIZATION PROBLEMS","source":"crossref","abstract":"Real-world optimization problems in engineering, logistics, and resource allocation are often constrained and multi-modal, posing a challenge for traditional optimization algorithms. Metaheuristic algorithms inspired by natural and artificial phenomena have shown promise, but many fail to balance exploration and exploitation effectively, especially under stringent constraints. Existing algorithms such as Genetic Algorithms (GA), Particle Swarm Optimization (PSO), and Differential Evolution (DE) face issues in convergence speed and constraint handling, particularly in high-dimensional spaces or when constraints are dynamic or complex. We propose an Adaptive Pattern-Driven Optimization (APDO) algorithm, a novel tailor-inspired metaheuristic that mimics the adaptive decision-making process of a tailor designing garments. APDO integrates three primary operators—Pattern Selection, Fabric Adjustment, and Stitch Reinforcement—to handle constraints adaptively. The algorithm combines pattern memory (historical bests), probabilistic pattern mutation, and a constraint-domination principle to ensure feasibility and diversity. The core idea is to iteratively “cut and stitch” solutions to adapt the search process, enabling dynamic constraint satisfaction and global optimization. We benchmarked APDO against five popular methods (GA, PSO, DE, Firefly Algorithm, and Whale Optimization Algorithm) on a suite of 10 real-world constrained problems, including mechanical component design and energy scheduling tasks. APDO outperformed all baselines in terms of convergence speed, constraint satisfaction rate, and solution quality. In particular, APDO achieved an average feasibility rate of 97.6% and an improvement of 4.2–11.8% in best fitness across problems.","url":"https://doi.org/10.21917/ijsc.2025.0540","authors":["Karthik Chandran","Vishal Sharad Hingmire"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-31T09:53:19Z","doi":"10.21917/ijsc.2025.0540","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/sisimpact67725.2025.11439692","name":"Nature-Inspired Feature Selection for Single-Lead Cognitive Load Detection Using CiSSA","source":"crossref","abstract":"","url":"https://doi.org/10.1109/sisimpact67725.2025.11439692","authors":["Satender Singh","Amita Pareek","Vishwa Nath Sharma","Mayank Vishwakarma","K.Shiva Krishna","Suman Punia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-26T19:47:30Z","doi":"10.1109/sisimpact67725.2025.11439692","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/mind67540.2025.11351593","name":"Black-Box Watermark Removal Using Diffusion Models and Self-Attention Mechanisms","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mind67540.2025.11351593","authors":["Qingyuan Zeng","Yunpeng Gong","Chuangliang Zhang","Shu Jiang","Zhenzhong Wang","Min Jiang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-27T04:49:35Z","doi":"10.1109/mind67540.2025.11351593","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/ccmcc67628.2025.11380809","name":"Energy-convergence trade off for the training of neural networks on bio-inspired hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ccmcc67628.2025.11380809","authors":["Nikhil Garg","Paul Uriarte Vicandi","Yanming Zhang","Alexandre Baigol","Donato Francesco Falcone","Saketh Ram Mamidala","Bert Jan Offrein","Laura Bégon-Lours"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-16T21:03:11Z","doi":"10.1109/ccmcc67628.2025.11380809","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-030-16681-6_24","name":"GABoost: A Clustering Based Undersampling Algorithm for Highly Imbalanced Datasets Using Genetic Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-16681-6_24","authors":["O. A. Ajilisa","V. P. Jagathyraj","M. K. Sabu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-22T17:26:26Z","doi":"10.1007/978-3-030-16681-6_24","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-030-16681-6_20","name":"Analysis of Optimised LQR Controller Using Genetic Algorithm for Isolated Power System","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-16681-6_20","authors":["Anju G. Pillai","Elizabeth Rita Samuel","A. Unnikrishnan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-22T17:26:26Z","doi":"10.1007/978-3-030-16681-6_20","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-642-34274-5_44","name":"A Biologically-Inspired Perspective on Commonsense Knowledge","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-34274-5_44","authors":["Pietro Perconti"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-09-30T13:21:47Z","doi":"10.1007/978-3-642-34274-5_44","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-0-387-34733-2_10","name":"A Biologically Motivated Computational Architecture Inspired in the Human Immunological System to Quantify Abnormal Behaviors to Detect Presence of Intruders","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-0-387-34733-2_10","authors":["Omar U. Flórez-Choque","Ernesto Cuadros-Vargas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-11-27T12:41:06Z","doi":"10.1007/978-0-387-34733-2_10","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-030-73603-3_19","name":"Machine Learning for Intrusion Detection: Design and Implementation of an IDS Based on Artificial Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-73603-3_19","authors":["Younes Wadiai","Yousef El Mourabit","Mohammed Baslam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-04-09T06:04:19Z","doi":"10.1007/978-3-030-73603-3_19","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-319-28031-8_37","name":"Solution to Constrained Test Problems Using Cohort Intelligence Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-28031-8_37","authors":["Apoorva S. Shastri","Priya S. Jadhav","Anand J. Kulkarni","Ajith Abraham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-14T01:02:33Z","doi":"10.1007/978-3-319-28031-8_37","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/iedm.2015.7409718","name":"Scaling-up resistive synaptic arrays for neuro-inspired architecture: Challenges and prospect","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iedm.2015.7409718","authors":["Shimeng Yu","Pai-Yu Chen","Yu Cao","Lixue Xia","Yu Wang","Huaqiang Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-03-28T15:11:21Z","doi":"10.1109/iedm.2015.7409718","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-030-49339-4_19","name":"A Progressive Method Based Approach to Understand Sleep Disorders in the Adult Healthy Population","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-49339-4_19","authors":["Vanita Ramrakhiyani","Niketa Gandhi","Sanjay Deshmukh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-05T11:05:14Z","doi":"10.1007/978-3-030-49339-4_19","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.2174/9789815136357123010003","name":"Acknowledgement","source":"crossref","abstract":"","url":"https://doi.org/10.2174/9789815136357123010003","authors":["Balwinder S. Dhaliwal","Suman Pattnaik","Shyam Sundar Pattnaik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-26T11:51:56Z","doi":"10.2174/9789815136357123010003","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1016/j.neucom.2025.132027","name":"Neuro-inspired dynamic dual-processing framework for object detection","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2025.132027","authors":["Tianpeng Bu","Minying Zhang","Lulu Hu","Hua Qian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-15T05:54:41Z","doi":"10.1016/j.neucom.2025.132027","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-981-97-5979-8_3","name":"Swarm Intelligence Algorithms and Their Engineering Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-5979-8_3","authors":["Adam Slowik","Krzysztof Cpalka","Absalom Ezugwu","Ali Wagdy Mohamed"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-25T20:57:33Z","doi":"10.1007/978-981-97-5979-8_3","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-030-96299-9_20","name":"Deep Learning for Big Data","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_20","authors":["Filipe Correia","Ana Madureira","Jorge Bernardino"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_20","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-319-76354-5_4","name":"Differential Evolution Assisted MUD for MC-CDMA Systems Using Non-orthogonal Spreading Codes","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-76354-5_4","authors":["Atta-ur-Rahman","Kiran Sultan","Nahier Aldhafferi","Abdullah Alqahtani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-09T11:43:48Z","doi":"10.1007/978-3-319-76354-5_4","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.3390/en14020433","name":"Energy Efficiency of a Quadruped Robot with Neuro-Inspired Control in Complex Environments","source":"crossref","abstract":"This paper proposes an analysis of the energy efficiency of a small quadruped robotic structure, designed based on the MIT Mini Cheetah, controlled using a central pattern generator based on the FitzHugh–Nagumo neuron. The robot’s performance evaluated on structurally complex terrain in a dynamic simulation environment is compared with other robotic structures on wheels and with hybrid architectures. The energy cost involved in carrying out an assigned task involving the need to traverse uneven terrain is calculated as a relevant index to be taken into account. In particular, simple control strategies impacting the leg trajectories are taken into account as the main factors affecting the energy efficiency in different terrain configurations. The adaptation of the leg trajectories is evaluated depending on the terrain characteristics, improving the locomotion performance.","url":"https://doi.org/10.3390/en14020433","authors":["Paolo Arena","Luca Patanè","Salvatore Taffara"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-01-14T11:39:14Z","doi":"10.3390/en14020433","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/bic-ta.2011.10","name":"Machine Loading Optimization in Flexible Manufacturing System Using a Hybrid of Bio-inspired and Musical-Composition Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bic-ta.2011.10","authors":["Umi Kalsom Yusof","Rahmat Budiarto","Ibrahim Venkat","Safaai Deris"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-10-18T11:35:51Z","doi":"10.1109/bic-ta.2011.10","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-030-49339-4_34","name":"Information Technology in Learning Institutions: An Advantage or A Disadvantage?","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-49339-4_34","authors":["Jonathan A. Odukoya","O. Omonijo","Sanjay Misra","Ravin Ahuja"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-05T11:05:14Z","doi":"10.1007/978-3-030-49339-4_34","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1145/3259205","name":"Session details: Brain-inspired autonomous computing and modeling","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3259205","authors":["Yiran Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-11T03:08:01Z","doi":"10.1145/3259205","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.4018/978-1-4666-0942-6.ch011","name":"Looking at Science through Water","source":"crossref","abstract":"This chapter is focused on creating the visual approach to natural processes, concepts, and events, rather than their description for learning. It has been designed as an active, involving, action-based exercise in visual communication. Interactive reading is a visual tool aimed at communication, activation, and expansion of one’s visual literacy. It addresses the interests of professionals who would like to further their developments in their domains. The reader is encouraged to read this chapter interactively by developing visual responses to the inspiring issues. This experience will be thus generated cooperatively with the readers who will construct interactively many different, meaningful pictorial interpretations. “How to produce texts by reading them,” asks a philosopher, semiotician, and writer Umberto Eco, (1984, 2). The chapter comprises two projects about water-related themes; each project invites the reader to create visual presentation of this theme. Selected themes involve: (1) States of matter exemplified by ice, water, and steam, and (2) Water habitats: lake, river, and swamp.","url":"https://doi.org/10.4018/978-1-4666-0942-6.ch011","authors":["Anna Ursyn"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-03-22T13:17:45Z","doi":"10.4018/978-1-4666-0942-6.ch011","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/parelec.2006.70","name":"Reconfigurable Parallel Hardware for Computing Local Linear Neuro-Fuzzy Model","source":"crossref","abstract":"","url":"https://doi.org/10.1109/parelec.2006.70","authors":["A. Pedram","M.R. Jamali","S.M. Fakhraie","C. Lucas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-24T09:07:05Z","doi":"10.1109/parelec.2006.70","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1016/j.asoc.2020.106488","name":"Neuro-genetic programming for multigenre classification of music content","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2020.106488","authors":["G. Campobello","D. Dell’Aquila","M. Russo","A. Segreto"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-20T09:29:51Z","doi":"10.1016/j.asoc.2020.106488","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/mind67540.2025.11351696","name":"Federated Learning with Robust Local Training for Noisy MRI-Based Mental Disorder Diagnosis","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mind67540.2025.11351696","authors":["Yao Hu","Rui Liu","Jibin Wu","Zhi-An Huang","Kay Chen Tan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-27T04:49:35Z","doi":"10.1109/mind67540.2025.11351696","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch014","name":"Agent-Based Computational Economics","source":"crossref","abstract":"This chapter argues that the economic system is best perceived as a complex adaptive system, and as such, the traditional analytical methods of economics are not optimal for its study. Agent-based computational economics (ACE) studies the economic system from the bottom up and recognizes interaction between autonomous agents as the central mechanism in generating the self-organizing features of economic systems. Besides a discussion of this new economic methodology, a short how-to introduction is given, and the problem of constraining economics as a science within the ACE approach is raised. It is argued that ACE should be perceived as a new methodological approach to the study of economic systems rather than a new approach to economics, and that the use of ACE should be anchored in existing economic theory.","url":"https://doi.org/10.4018/978-1-59140-984-7.ch014","authors":["C. Bruun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch014","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-1-4615-3062-6_25","name":"Neuro-computing and concurrent engineering","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4615-3062-6_25","authors":["Cihan H. Dagli","Pipatpong Poshyanonda","Ali Bahrami"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-09-16T23:41:45Z","doi":"10.1007/978-1-4615-3062-6_25","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1016/j.asoc.2007.03.005","name":"A real-time neuro-adaptive controller with guaranteed stability","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2007.03.005","authors":["Ali Reza Mehrabian","Mohammad B. Menhaj"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-04-05T07:11:57Z","doi":"10.1016/j.asoc.2007.03.005","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch007","name":"Simulation in Social Sciences","source":"crossref","abstract":"Advancing the state of the art of simulation in the social sciences requires appreciating the unique value of simulation as a third way of doing science, in contrast to both induction and deduction. Simulation can be an effective tool for discovering surprising consequences of simple assumptions. This chapter offers advice for doing simulation research, focusing on the programming of a simulation model, analyzing the results, sharing the results, and replicating other people’s simulations. Finally, suggestions are offered for building a community of social scientists who do simulation.","url":"https://doi.org/10.4018/978-1-59140-984-7.ch007","authors":["R. Axelrod"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch007","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.3233/atde260221","name":"Quantum-Behaved Pigeon-Inspired Optimization Algorithm for Multi-UAV Mission Assignment","source":"crossref","abstract":"In order to address the challenge of large-scale reconnaissance mission assignment, the K-means cluster algorithm is applied to divide the numerous targets into several clusters. Every cluster of targets is reconnoitred by a single unmanned aerial vehicle (UAV). The quantum-behaved pigeon-inspired optimization (QPIO) algorithm with a discretization algorithm is developed to determine the reconnaissance sequence of every cluster of targets. The discretization algorithm consists of three steps: rounding the elements of the position vector, eliminating the repeated elements, and supplementing the missing elements. Two simulation experiments are conducted for multi-UAV mission assignment. The QPIO algorithm with the discretization algorithm is applied to the first experiment. The conventional PIO algorithm with the discretization algorithm is applied to the second one. The comparison of experimental results demonstrates that the QPIO algorithm with the discretization algorithm has superior performance and effectiveness.","url":"https://doi.org/10.3233/atde260221","authors":["Hongchao Zhao","Jianzhong Zhao","Tingting Ge"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-18T19:42:28Z","doi":"10.3233/atde260221","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/compas67506.2025.11381874","name":"A Nature-Inspired Electric Eel Optimization Strategy for PID Tuning in DC Motor Speed Stabilization","source":"crossref","abstract":"","url":"https://doi.org/10.1109/compas67506.2025.11381874","authors":["Krishnapada Mondal","Md. Abu Salman","Md Moklesur Rahman Bhuiyan","Md. Ferdous Mahmud Fahim","Joyonta Sana","Md. Sohel Rana"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-12T20:57:13Z","doi":"10.1109/compas67506.2025.11381874","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-030-96299-9_70","name":"Dynamic Modelling of a Thermal Solar Heating System","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_70","authors":["José Boaventura-Cunha","Judite Ferreira"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_70","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-030-73603-3_39","name":"Assessment of Plant Health in the Green Belt Around Coal Handling Area for Sustained and Effective Control of Fugitive Emissions","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-73603-3_39","authors":["Prashant Kokil","Niketa Gandhi","Sanjay Deshmukh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-04-09T06:04:19Z","doi":"10.1007/978-3-030-73603-3_39","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-030-73603-3_40","name":"ICT in Indian Agriculture: An Overview of the Major Services, Their Penetration and Infrastructural Development","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-73603-3_40","authors":["Nikhil Kumar Rajput","Niketa Gandhi","Bhavya Ahuja Grover"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-04-09T06:04:19Z","doi":"10.1007/978-3-030-73603-3_40","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-030-16681-6_34","name":"Reducing the Negative Effect of Malicious Nodes in Opportunistic Networks Using Reputation Based Trust Management","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-16681-6_34","authors":["Smritikona Barai","Nupur Boral","Parama Bhaumik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-22T21:26:26Z","doi":"10.1007/978-3-030-16681-6_34","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-030-96299-9_52","name":"A Sentiment-Based Approach to Predict Learners’ Perceptions Towards YouTube Educational Videos","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-96299-9_52","authors":["Rdouan Faizi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-21T17:09:04Z","doi":"10.1007/978-3-030-96299-9_52","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1016/b978-0-443-18509-0.09992-8","name":"Preface","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-18509-0.09992-8","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-25T05:34:22Z","doi":"10.1016/b978-0-443-18509-0.09992-8","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1145/3584954.3584962","name":"Neuromorphic Downsampling of Event-Based Camera Output","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3584954.3584962","authors":["Charles P. Rizzo","Catherine D. Schuman","James S. Plank"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-12T13:27:54Z","doi":"10.1145/3584954.3584962","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/jproc.2014.2310713","name":"Stochastic Electronics: A Neuro-Inspired Design Paradigm for Integrated Circuits","source":"crossref","abstract":"","url":"https://doi.org/10.1109/jproc.2014.2310713","authors":["Tara Julia Hamilton","Saeed Afshar","Andre van Schaik","Jonathan Tapson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-04-09T18:02:06Z","doi":"10.1109/jproc.2014.2310713","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/nabic.2011.6089638","name":"A Multi-Layered Perceptron fingerprint idenfication system","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2011.6089638","authors":["Terje Kristensen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-12-06T16:02:25Z","doi":"10.1109/nabic.2011.6089638","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1145/3320288.3320291","name":"Acquisition and Representation of Spatio-Temporal Signals in Polychronizing Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3320288.3320291","authors":["Felix Wang","William M. Severa","Fred Rothganger"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-08-23T12:03:10Z","doi":"10.1145/3320288.3320291","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/icar.2005.1507471","name":"A bio-inspired sensory-motor neural model for a neuro-robotic manipulation platform","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icar.2005.1507471","authors":["G. Asuni","G. Teti","C. Laschi","E. Guglielmelli","P. Dario"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-11T16:54:11Z","doi":"10.1109/icar.2005.1507471","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/otcon65728.2025.11070818","name":"Stability Improvement in Microgrid Systems using Bio-Inspired Optimization Methods: An Investigative Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1109/otcon65728.2025.11070818","authors":["Murugeswari S","Vijay Dhote","Anubhav Rai","Karthik M","A. Srinivasula Reddy","Arulananth T S"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-14T17:40:30Z","doi":"10.1109/otcon65728.2025.11070818","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/nice61972.2024.10548776","name":"GPU-RANC: A CUDA Accelerated Simulation Framework for Neuromorphic Architectures","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nice61972.2024.10548776","authors":["Sahil Hassan","Michael Inouye","Miguel C. Gonzalez","Ilkin Aliyev","Joshua Mack","Maisha Hafiz","Ali Akoglu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-11T17:30:32Z","doi":"10.1109/nice61972.2024.10548776","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1145/3584954.3584969","name":"Impact of Noisy Input on Evolved Spiking Neural Networks for Neuromorphic Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3584954.3584969","authors":["Karan P. Patel","Catherine D. Schuman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-12T13:27:54Z","doi":"10.1145/3584954.3584969","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-319-59156-8_13","name":"Worm Foraging Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-59156-8_13","authors":["Anthony Brabazon","Seán McGarraghy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-09-26T14:09:36Z","doi":"10.1007/978-3-319-59156-8_13","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/bimnics.2006.361800","name":"Crypto-fraglets: Networking, Biology and Security","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bimnics.2006.361800","authors":["Marinella Petrocchi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-06-07T15:56:37Z","doi":"10.1109/bimnics.2006.361800","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.4018/978-1-4666-0942-6.ch002","name":"Flow Simulation with Vortex Elements","source":"crossref","abstract":"While fluid flow is a ubiquitous phenomenon on both Earth’s surface and elsewhere in the cosmos, its existence, as a mathematical field quantity without discrete form, color, or shape, defies representation in the visual arts. Both physical biology and computational physics are, at their roots, very large systems of interacting agents. The field of computational fluid dynamics deals with solving the essential formulas of fluid dynamics over large numbers of interacting elements. This chapter presents a novel method for creating fluid-like forms and patterns via interacting elements. Realistic fluid-like motions are presented on a computer using a particle representation of the rotating portions of the flow. The straightforward method works in two or three dimensions and is amenable to instruction and easy application to a variety of visual media. Examples from digital flatwork and video art illustrate the method’s potential to bring space, shape, and form to an otherwise ephemeral medium. Though the rules are simple, the resulting behavior frequently exhibits emergent properties not anticipated by the original formulae. This makes both fluid simulations and related biological computations deep, interesting, and ready for exploration.","url":"https://doi.org/10.4018/978-1-4666-0942-6.ch002","authors":["Mark Stock"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-03-22T13:17:45Z","doi":"10.4018/978-1-4666-0942-6.ch002","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-030-16681-6_9","name":"A Novel Meta-heuristic Differential Evolution Algorithm for Optimal Target Coverage in Wireless Sensor Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-16681-6_9","authors":["Chandra Naik","D. Pushparaj Shetty"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-22T21:26:26Z","doi":"10.1007/978-3-030-16681-6_9","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.47363/jaicc/2025(4)502","name":"Advancing Moving Target Strategy with Bio-Inspired Reinforcement Learning to Secure Misconfigured Software Applications","source":"crossref","abstract":"Misconfigurations in software systems are a persistent source of security vulnerabilities, particularly within static architectures that fail to adapt over time. Moving Target Defense (MTD) offers a proactive approach by dynamically altering the system’s attack surface, thereby reducing exposure. This paper builds upon an MTD model, RL-MTD, which leverages Reinforcement Learning (RL) to generate adaptive secure configurations. Although effective, RL-MTD faces limitations due to an unoptimized and sparse search space. To address this, two hybrid models—GA-RL and PSO-RL—are proposed, integrating Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) into the RL-MTD framework. Experiments on four misconfigured SUTs show both models outperform the baseline. Notably, PSO-RL yields the most secure configurations in most scenarios. The authors present a prototype demonstrating how PSO-RL could be applied on a constrained Windows 10 system to defend against an attack. These findings enhance MTDbased adaptive cybersecurity via optimized search.","url":"https://doi.org/10.47363/jaicc/2025(4)502","authors":["Shuvalaxmi Dass","Niloofar Heidarikohol"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-29T09:28:13Z","doi":"10.47363/jaicc/2025(4)502","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-030-73603-3_31","name":"IoT Based Time Triggered SPE Smart Switch for AC Appliances Control","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-73603-3_31","authors":["Omar Bin Samin","Maryam Omar","Musadaq Mansoor","Noman Naseeb","Samad Ali Shah","Aqil Amjad Khan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-04-09T06:04:19Z","doi":"10.1007/978-3-030-73603-3_31","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-319-01781-5_26","name":"SVM-Based Classification for Identification of Ice Types in SAR Images Using Color Perception Phenomena","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-01781-5_26","authors":["Parthasarty Subashini","Marimuthu Krishnaveni","Bernadetta Kwintiana Ane","Dieter Roller"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-08-01T11:21:05Z","doi":"10.1007/978-3-319-01781-5_26","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-030-73603-3_43","name":"A Hybrid Machine Learning Model for Predicting Customer Churn in the Telecommunication Industry","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-73603-3_43","authors":["Modupe Odusami","Olusola Abayomi-Alli","Sanjay Misra","Adebayo Abayomi-Alli","Mayank Mohan Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-04-09T06:04:19Z","doi":"10.1007/978-3-030-73603-3_43","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.2174/9789815136357123010002","name":"Preface","source":"crossref","abstract":"","url":"https://doi.org/10.2174/9789815136357123010002","authors":["Balwinder S. Dhaliwal","Suman Pattnaik","Shyam Sundar Pattnaik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-26T11:51:56Z","doi":"10.2174/9789815136357123010002","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-319-59156-8_6","name":"Mammal Foraging Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-59156-8_6","authors":["Anthony Brabazon","Seán McGarraghy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-09-26T14:09:36Z","doi":"10.1007/978-3-319-59156-8_6","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/1-4020-4995-1_3","name":"Bio-Inspired Data Management","source":"crossref","abstract":"","url":"https://doi.org/10.1007/1-4020-4995-1_3","authors":["Martin L. Kersten","Arno P. J. M. Siebes"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-09-08T17:20:45Z","doi":"10.1007/1-4020-4995-1_3","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.29007/xc5q","name":"Society 5.0-Inspired Digitalization Framework for Resilient and Sustainable Agriculture","source":"crossref","abstract":"This research paper proposes a digitalization framework based on Society 5.0 principles for promoting resilient and sustainable agricultural value chains in the context of climate change. Climate change is affecting the productivity and sustainability of agricultural systems and threatening food security in many parts of the world. Digitalization has the potential to enhance the resilience of agricultural value chains to climate change by improving efficiency, promoting sustainability, and reducing vulnerability to climate risks. This study reviews the literature to investigate the potential benefits and challenges of Society 5.0-inspired digitalization for agricultural value chains in the context of resilience and sustainability. Further, this study establishes critical design requirements for digitalization, which inform the development of a theoretical framework for Society 5.0-inspired digitalization framework in realizing resilient and sustainable agricultural value chains.","url":"https://doi.org/10.29007/xc5q","authors":["Ronald Tombe","Hanlie Smuts"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-26T22:10:13Z","doi":"10.29007/xc5q","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1515/9783110676112-205","name":"List of contributors","source":"crossref","abstract":"","url":"https://doi.org/10.1515/9783110676112-205","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-02-10T12:01:39Z","doi":"10.1515/9783110676112-205","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-031-27499-2_68","name":"A Deep Learning Approach to Monitoring Workers’ Stress at Office","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_68","authors":["Fátima Rodrigues","Jacqueline Marchetti"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_68","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-030-90708-2_4","name":"Malicious Activity Detection in IoT Networks: A Nature-Inspired Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-90708-2_4","authors":["Andria Procopiou","Thomas M. Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-26T11:04:51Z","doi":"10.1007/978-3-030-90708-2_4","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/cniot65435.2025.11070537","name":"A Keyword-Spotting(KWS) Chip Featuring a Bio-Inspired Neuron Model in 65-nm CMOS","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cniot65435.2025.11070537","authors":["Yantong Liu","Fei Tan","Ka-Fai Un","Wei-Han Yu","Rui P. Martins","Pui-In Mak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-14T17:41:09Z","doi":"10.1109/cniot65435.2025.11070537","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/icccnp63914.2025.11233757","name":"Adaptive Neuro-Federated Distributed Computing Framework for Intelligent Edge-Cloud Collaboration in Real-Time Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icccnp63914.2025.11233757","authors":["K. Kalai Kumar","S. Nanthini","S. Jothi Shri","L. Jimson","V. Lavanya","Vinothini S"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T18:47:01Z","doi":"10.1109/icccnp63914.2025.11233757","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.4324/9781003642336-10","name":"Other Neuro-Inclusive Communities","source":"crossref","abstract":"","url":"https://doi.org/10.4324/9781003642336-10","authors":["Charles Durrett"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-20T15:12:46Z","doi":"10.4324/9781003642336-10","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1016/j.asoc.2005.02.001","name":"A neuro-fuzzy approach for prediction of human work efficiency in noisy environment","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2005.02.001","authors":["Zaheeruddin","Garima"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-04-04T14:28:53Z","doi":"10.1016/j.asoc.2005.02.001","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/3-211-27389-1_94","name":"Intelligent Agent-Inspired Genetic Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1007/3-211-27389-1_94","authors":["C. G. Wu","Y.C. Liang","H.P. Lee","C. Lu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-12-08T01:34:44Z","doi":"10.1007/3-211-27389-1_94","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1145/1536274.1536312","name":"eScience inspired CS education","source":"crossref","abstract":"","url":"https://doi.org/10.1145/1536274.1536312","authors":["Yan Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-05-05T14:40:53Z","doi":"10.1145/1536274.1536312","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/iscas45731.2020.9181172/video","name":"Video for Binarized Weight Neural-Network Inspired Ultra-Low Power Speech Recognition Processor with Time-Domain Based Digital-Analog Mixed Approximate Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas45731.2020.9181172/video","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-29T09:22:27Z","doi":"10.1109/iscas45731.2020.9181172/video","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.14236/ewic/eva2022.27","name":"Neuro Art: liminal reflection, introspection, and participatory art","source":"crossref","abstract":"","url":"https://doi.org/10.14236/ewic/eva2022.27","authors":["Oliver Gingrich","Shama Rahman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-16T23:17:54Z","doi":"10.14236/ewic/eva2022.27","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-981-16-9573-5_57","name":"A Survey on Brain Computer Interface: A Computing Intelligence","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-16-9573-5_57","authors":["A. Shanmugapriya","A. Grace Selvarani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-30T06:02:42Z","doi":"10.1007/978-981-16-9573-5_57","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/nabic.2009.5393646","name":"Modified Differential Evolution algorithms for Global Optimization","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393646","authors":["Musrrat Ali"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5393646","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.21203/rs.3.rs-8893792/v1","name":"Medical Image Encryption Using DNA Computing and a Bio-Inspired PRNG for Healthcare Data Privacy","source":"crossref","abstract":"Abstract As digital healthcare systems increasingly rely on electronic medical records, secure and high-quality encryption mechanisms are essential to prevent unauthorized access and cyber threats. This study proposes a novel Hardy–Weinberg equilibrium-inspired pseudorandom number generator (PRNG) integrated with a medical image encryption framework using nonlinear quadratic functions, DNA encoding, and substitution-box-based permutation. The proposed PRNG passed 100\\% of the NIST statistical test suite for 30 and 100 generated sequences, with an average entropy of 7.9 and no detectable periodicity. Key sensitivity analysis demonstrated near-zero correlation between sequences generated from minimally different inputs, indicating strong diffusion properties. Encryption experiments conducted on the MedPix and USC-SIPI datasets achieved an average information entropy of 7.999, near-zero correlation coefficients between adjacent pixels in all directions, and NPCR and UACI values within theoretical ranges. Comparative analysis shows that the proposed scheme provides superior randomness and resistance to statistical and differential attacks compared with state-of-the-art methods.","url":"https://doi.org/10.21203/rs.3.rs-8893792/v1","authors":["Faiza Waheed","Takreem Haider"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-03T17:02:46Z","doi":"10.21203/rs.3.rs-8893792/v1","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-981-16-3128-3_6","name":"Particle Swarm Optimization Advances in Internet of Things Industry","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-16-3128-3_6","authors":["Ahmed M. Helmi","Mohammed Elsayed Lotfy","Amr A. Zamel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-18T23:09:33Z","doi":"10.1007/978-981-16-3128-3_6","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-642-34274-5_49","name":"Biologically Inspired Methods for Automatic Speech Understanding","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-34274-5_49","authors":["Giampiero Salvi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-09-30T13:21:47Z","doi":"10.1007/978-3-642-34274-5_49","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1002/9781394336449.ch7","name":"Quantum‐Inspired Soft Computing for Intelligent Data Processing in Real‐Life Scenarios","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9781394336449.ch7","authors":["Kuldeep Singh Kaswan","Jagjit Singh Dhatterwal","Kiran Malik","Santar Pal Singh","S. Viveka"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-09T21:18:51Z","doi":"10.1002/9781394336449.ch7","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-031-27499-2_34","name":"Parallel Ant Colony Optimization for Scheduling Independent Tasks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_34","authors":["Robert Dietze","Maximilian Kränert"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_34","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-031-27499-2_25","name":"Detection of Cracks in Building Facades Using Infrared Thermography","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_25","authors":["Tiago Fonseca","Joao C. Ferreira"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_25","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-7908-1902-1_85","name":"Compromise Weighted Neuro — Fuzzy Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-7908-1902-1_85","authors":["Leszek Rutkowski","Krzysztof Cpałka"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-03-10T20:11:40Z","doi":"10.1007/978-3-7908-1902-1_85","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/etcm67548.2025.11304418","name":"Quantum-Inspired Strategies: Bridging Classical and Quantum Computing for Enhanced Optimization in Structural Engineering and Feature Selection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/etcm67548.2025.11304418","authors":["Alejandra Ospina","Daniel Riofrío","Felipe Grijalva","José Vega-Sánchez","Pablo Torres","Diego Benítez","Noel Pérez-Pérez","Maria Baldeon-Calisto"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-25T18:25:04Z","doi":"10.1109/etcm67548.2025.11304418","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/s00521-025-11059-y","name":"MCI-GAN: a novel GAN with identity blocks inspired by menstrual cycle behavior for missing pixel imputation","source":"crossref","abstract":"Abstract This paper presents MCI-GAN, a novel menstrual cycle imputation (MCI) and generative adversarial network (GAN) framework designed to address the challenge of missing pixel imputation in medical images. Inspired by the intelligent behavior of the endometrial lining during the menstrual cycle, our method introduces four key innovations. First, we propose a novel metaheuristic algorithm that assigns weights to surround pixels based on menstrual cycle behavior, ensuring that the imputed pixels maintain structural integrity and coherence with their neighbors, thus preserving overall image quality. Second, to enhance the learning capability of the GAN, identity blocks are integrated into the network architecture, improving the network’s ability to capture complex spatial relationships and leading to more accurate and consistent imputation of missing pixels. Third, we introduce an adaptive loss function that dynamically adjusts the penalty for pixel discrepancies based on local image context, allowing the model to focus on areas where accurate imputation is most critical and thereby enhancing overall image fidelity. Fourth, the framework incorporates a multi-scale feature extraction mechanism, enabling the GAN to process and combine information at various levels of detail, ensuring that both fine-grained textures and larger structural patterns are accurately captured during the imputation process. The efficacy of MCI-GAN is demonstrated across three diverse medical imaging datasets: mammograms, magnetic resonance imaging (MRI) scans, and skin lesion images. Our results show that the proposed method significantly outperforms existing approaches in terms of accuracy and structural coherence, offering a robust solution for missing pixel imputation in medical imaging.","url":"https://doi.org/10.1007/s00521-025-11059-y","authors":["Hanaa Salem Marie","Mostafa Elbaz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-06T13:49:33Z","doi":"10.1007/s00521-025-11059-y","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/bicta.2010.5645341","name":"Plasmid DNA computing model of 0&amp;#x2013;1 programming problem","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2010.5645341","authors":["zhixiang Yin","Hua chen","Song Bosheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-12-09T15:33:18Z","doi":"10.1109/bicta.2010.5645341","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-981-99-3970-1_3","name":"Review of Parameter Tuning Methods for Nature-Inspired Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-99-3970-1_3","authors":["Geethu Joy","Christian Huyck","Xin-She Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-21T15:04:55Z","doi":"10.1007/978-981-99-3970-1_3","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/nabic.2011.6089656","name":"A bio-inspired knowledge system for control tuning (BIO-KSY)","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2011.6089656","authors":["Jose Luis Calvo-Rolle","Ramon Ferreiro Garcia","Emilio Corchado","Pedro Antonio Hernandez","Maria Luisa Perez","Maria Araceli Sanchez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-12-06T21:02:25Z","doi":"10.1109/nabic.2011.6089656","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1201/9781003322931-7","name":"Fog Computing for Agriculture Applications and its Issues","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003322931-7","authors":["Akruti Sinha","Gaurav Srivastava","Devika Sapra","Chhavi Deshlahra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-24T18:39:16Z","doi":"10.1201/9781003322931-7","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-319-76354-5_21","name":"System Multi Agents for Automatic Negotiation of SLA in Cloud Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-76354-5_21","authors":["Zineb Bakraouy","Amine Baina","Mostafa Bellafkih"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-09T11:43:48Z","doi":"10.1007/978-3-319-76354-5_21","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/aectsd65988.2025.11411524","name":"Deep Neuro-Fuzzy Systems for Self-Learning Robotic Manipulation in Dynamic Environments","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aectsd65988.2025.11411524","authors":["Neelamegam G","B Leena","S Sathya Priya","Reeba Rose L","M Sundarrajan","Mani Deepak Choudhry"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-03T20:50:27Z","doi":"10.1109/aectsd65988.2025.11411524","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/nabic.2009.5393692","name":"Speech recognition of Malayalam numbers","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393692","authors":["Cini Kurian","Kannan Balakrishnan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5393692","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-319-28031-8_22","name":"Generating Picture Arrays Based on Grammar Systems with Flat Splicing Operation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-28031-8_22","authors":["K. G. Subramanian","G. Samdanielthompson","N. Gnanamalar David","Atulya K. Nagar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-13T20:02:33Z","doi":"10.1007/978-3-319-28031-8_22","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-030-49339-4_18","name":"Energy Conservation Perspective for Recharging Cell Phone Battery Utilizing Speech Through Piezoelectric System","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-49339-4_18","authors":["Ashish Tiwary","Yashraj","Amar Kumar","Mandeep Biruly"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-05T11:05:14Z","doi":"10.1007/978-3-030-49339-4_18","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-030-73603-3_49","name":"Cyber Security Management Model for Critical Infrastructure and Improving the Security Level on Transferring Digital Data","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-73603-3_49","authors":["Pradeep Bedi","S. B. Goyal","Jugnesh Kumar","Ritika"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-04-09T06:04:19Z","doi":"10.1007/978-3-030-73603-3_49","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-030-73603-3_25","name":"Effectiveness of Ensemble Machine Learning Algorithms in Weather Forecasting of Bangladesh","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-73603-3_25","authors":["Atik Mahabub","Al-Zadid Sultan Bin Habib","M. Rubaiyat Hossain Mondal","Subrato Bharati","Prajoy Podder"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-04-09T06:04:19Z","doi":"10.1007/978-3-030-73603-3_25","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/mind67540.2025.11351754","name":"Constrained Human Preference Alignment for Natural Language Planning with LLMs","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mind67540.2025.11351754","authors":["Yu Zhou","Haokai Hong","Ran Cheng","Kay Chen Tan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-27T04:49:35Z","doi":"10.1109/mind67540.2025.11351754","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-319-01781-5_4","name":"Fuzzy Rules and SVM Approach to the Estimation of Use Case Parameters","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-01781-5_4","authors":["Svatopluk Štolfa","Jakub Štolfa","Pavel Krömer","Ondřej Koběrský","Martin Kopka","Václav Snášel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-08-01T11:21:05Z","doi":"10.1007/978-3-319-01781-5_4","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-030-73603-3_27","name":"Relationship Between the Monopoly of Tobacco Law and Lung Cancer Using the Theory of Dynamic Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-73603-3_27","authors":["Nazanin Fozooni","Hamed Daneshvari","Sohaib Dastgoshade","Ajith Abraham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-04-09T06:04:19Z","doi":"10.1007/978-3-030-73603-3_27","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.2174/2665997201666210329104604","name":"Hierarchical and Multi-resolution Neuron Network Computing for Complex Inverse Problems-An Approach Based on Brain-inspired Computing and Learning Method","source":"crossref","abstract":"Background: Complex inverse problems such as Radar Imaging and CT/EIT imaging are well investigated in mathematical algorithms with various regularization methods. However it is difficult to obtain stable inverse solutions with fast convergence and high accuracy at the same time due to the ill-posed property and non-linear property. Objective: In this paper, we propose a hierarchical and multi-resolution scalable method from both algorithm perspective and hardware perspective to achieve fast and accurate solu-tions for inverse problems by taking radar and EIT imaging as examples. Method: We present an extension of discussion on neuromorphic computing as brain-inspired computing method and the learning/training algorithm to design a series of problem specific AI “brains” (with different memristive values) to solve a general complex ill-posed inverse problems that are traditionally solved by mathematical regular operators. We design a hierarchical and multi-resolution scalable method and an algorithm framework to train AI deep learning neuron network and map into the memristive circuit so that the memristive val-ues are optimally obtained. We propose FPGA as an emulation implementation for neuro-morphic circuit as well. Result: We compared the methodology between our approach and traditional regulariza-tion method. In particular we use Electrical Impedance Tomography (EIT) and Radar imaging as typical examples to compare how to design an AI deep learning neuron network architec-tures to solve inverse problems. Conclusion: With EIT imaging as a typical example, we show that any moderate complex inverse problem, as long as it can be described as combinational problem, AI deep learning neuron network is a practical alternative approach to try to solve the inverse problems with any given expected resolution accuracy, as long as the neuron network width is large enough and computational power is strong enough for all combination samples training purpose.","url":"https://doi.org/10.2174/2665997201666210329104604","authors":["Mingyong Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-30T05:19:33Z","doi":"10.2174/2665997201666210329104604","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-981-10-6747-1_12","name":"An Approach for Iris Segmentation in Constrained Environments","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-10-6747-1_12","authors":["Ritesh Vyas","Tirupathiraju Kanumuri","Gyanendra Sheoran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-10-04T04:25:22Z","doi":"10.1007/978-981-10-6747-1_12","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-981-19-9819-5","name":"Computational Vision and Bio-Inspired Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-19-9819-5","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-07T14:02:42Z","doi":"10.1007/978-981-19-9819-5","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1088/1361-6463/ad7a82/v3/decision1","name":"Decision letter for \"Brain-inspired computing with self-assembled networks of nano-objects\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1361-6463/ad7a82/v3/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-19T17:52:56Z","doi":"10.1088/1361-6463/ad7a82/v3/decision1","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-030-16681-6_49","name":"Design and Implementation of a Fault Management System","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-16681-6_49","authors":["Abiola Salau","Chika Yinka-Banjo","Sanjay Misra","Adewole Adewumi","Ravin Ahuja","Rytis Maskeliunas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-22T17:26:26Z","doi":"10.1007/978-3-030-16681-6_49","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-030-49339-4_13","name":"Effect of Environmental and Occupational Exposures on Human Telomere Length and Aging: A Review","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-49339-4_13","authors":["Jasbir Kaur Chandani","Niketa Gandhi","Sanjay Deshmukh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-05T11:05:14Z","doi":"10.1007/978-3-030-49339-4_13","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.12928/telkomnika.v24i1.27594","name":"Anchovy-inspired filter algorithm: A bio-inspired optimization approach for high-dimensional benchmark functions","source":"crossref","abstract":"","url":"https://doi.org/10.12928/telkomnika.v24i1.27594","authors":["Azrul Mahfurdz","Muhammad Muizz Mohd Nawawi","Sunardi Sunardi","Mohd Azriq Abd Aziz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-30T04:53:57Z","doi":"10.12928/telkomnika.v24i1.27594","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1016/j.asoc.2020.106967","name":"A comparative analysis of bio-inspired optimization algorithms for automated test pattern generation in sequential circuits","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2020.106967","authors":["Majed Alateeq","Witold Pedrycz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-24T17:21:37Z","doi":"10.1016/j.asoc.2020.106967","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-981-97-5979-8_1","name":"Transmit Beamforming Designs in Wireless Communications Using the Firefly Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-5979-8_1","authors":["Tuan Anh Le","Xin-She Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-25T16:57:33Z","doi":"10.1007/978-981-97-5979-8_1","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/bicta.2010.5645198","name":"Membrane computing based particle swarm optimization algorithm and its application","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2010.5645198","authors":["Yang Sun","Lingbo Zhang","Xingsheng Gu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-12-09T15:33:18Z","doi":"10.1109/bicta.2010.5645198","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-319-59156-8_7","name":"Bird Foraging Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-59156-8_7","authors":["Anthony Brabazon","Seán McGarraghy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-09-26T18:09:36Z","doi":"10.1007/978-3-319-59156-8_7","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/nabic.2011.6089652","name":"Evolving alphabet using genetic algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2011.6089652","authors":["Jan Platos","Pavel Kromer"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-12-06T21:02:25Z","doi":"10.1109/nabic.2011.6089652","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.18260/1-2--41998","name":"Research Experiences for Teachers Summer Program in Biologically-inspired Computing Systems","source":"crossref","abstract":"","url":"https://doi.org/10.18260/1-2--41998","authors":["Na Gong","Shenghua Zha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-06T17:48:32Z","doi":"10.18260/1-2--41998","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/bicta.2009.5338092","name":"Government control, diversification and corporate performance","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2009.5338092","authors":["Tao Wang","Xuefeng Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-11-24T18:50:07Z","doi":"10.1109/bicta.2009.5338092","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/nabic.2009.5393650","name":"Design of decoder in quantum computing based on spin field effect","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393650","authors":["Saeid Rafiei","Amir Abolfazl Suratgar","Avat Taherpour","Abolghasem Babaei"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393650","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1016/j.asoc.2021.107892","name":"Elephant clan optimization: A nature-inspired metaheuristic algorithm for the optimal design of structures","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2021.107892","authors":["Malihe Jafari","Eysa Salajegheh","Javad Salajegheh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-13T11:37:58Z","doi":"10.1016/j.asoc.2021.107892","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-030-73603-3_29","name":"A Comprehensive Review on Cyber Physical System and Its Applications in Robotic Process Automation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-73603-3_29","authors":["Durgesh M. Sharma","Shishir Kumar Shandilya","Ashish K. Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-04-09T06:04:19Z","doi":"10.1007/978-3-030-73603-3_29","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-1-4613-0431-9_3","name":"The Rapid Learning Neuro-Computing System","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4613-0431-9_3","authors":["Robert J. Jannarone"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-08-25T18:43:55Z","doi":"10.1007/978-1-4613-0431-9_3","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1016/j.imavis.2014.04.006","name":"Improving texture categorization with biologically-inspired filtering","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.imavis.2014.04.006","authors":["Ngoc-Son Vu","Thanh Phuong Nguyen","Christophe Garcia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-04-13T01:16:17Z","doi":"10.1016/j.imavis.2014.04.006","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1142/s1793351x07000056","name":"BIO-INSPIRED PROCESSING AND PROPAGATION OF SEMANTICS IN LOOSELY COUPLED COMPUTING ENVIRONMENTS","source":"crossref","abstract":"Human-centric computing has grown to be the major influence in today's computing research. Due to demand from industry and even lawmakers for easy-to-use computer systems, the user is now regarded as being the center of a ubiquitously available environment that supports the execution of task and anticipates user actions. This environment allows for the establishment of completely new ways for the delivery of legacy services and represents an opportunity for the introduction of a new type of services, addressing the user-focused service consumption. As a cause of this shift, the increasing saturation of everyday environments with computing devices can be identified. This saturation implies a numerical growth of computing systems and entails an increasing complexity, which negatively influences maintainability and manageability. Moreover, the shortcomings caused by the mobility of system elements, a common trait of human-centric environments, require consideration about the reliability of cooperative actions. In this paper, we present an approach that copes with complexity and dynamic while making service-oriented systems autonomous by the use of bio-inspired concepts. In particular, the aim is to make service architectures environment-aware. Thus, service architectures are supposed to adapt autonomously to their current environment like biological species do to survive. This approach requires services to obtain knowledge about characteristics and state of the environment through gathering semantically enhanced information about the context of the computing environment, which is intended to help in forming a virtual counterpart of the real world as reference for service adaptation. For this purpose, we illustrate the architecture for context provisioning in highly dynamic computing environments. As base for this architecture a middleware is introduced utilizing a loosely coupled interaction model. Moreover, a pheromone-based concept is outlined to optimize the dissemination of context data in the absence of adequate context sources.","url":"https://doi.org/10.1142/s1793351x07000056","authors":["CARSTEN JACOB","DAVID LINNER","HEIKO PFEFFER","ILJA RADUSCH"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-05-07T02:17:59Z","doi":"10.1142/s1793351x07000056","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/s00521-021-05884-0","name":"S. I: hybridization of neural computing with nature-inspired algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-021-05884-0","authors":["Hari Mohan Pandey","Nik Bessis","Neeraj Kumar","Ankit Chaudhary"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-26T08:03:04Z","doi":"10.1007/s00521-021-05884-0","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-319-28031-8_46","name":"An Extended Study on the Association Between Elicitation Issues and Software Project Performance: A Theoretical Model","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-28031-8_46","authors":["S. Neetu Kumari","S. Pillai Anitha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-13T20:02:33Z","doi":"10.1007/978-3-319-28031-8_46","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/iccmc65190.2025.11140663","name":"Neuro-Signal-Informed AI Models for Comprehensive Diagnosis of Dermatological Disorders","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccmc65190.2025.11140663","authors":["Ramesh M","G. Hari Siva Prasad Reddy","Gandhimathi Alias Usha S","M. Charan Kumar Reddy","Y. J. Lakshmi Murty","A. Giriprasad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-04T18:17:01Z","doi":"10.1109/iccmc65190.2025.11140663","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/icmctc62214.2025.11196455","name":"Neuro-Symbolic AI-Driven Data Warehouses: Self-Learning Architectures for Dynamic Schema Evolution and Adaptive Query Optimization","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icmctc62214.2025.11196455","authors":["D T V Dharmajee Rao","Ch. Vidyadhari","R. Barathy","Md Afzal","Shilpa Sargari","A.S.Anakath"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-17T17:38:30Z","doi":"10.1109/icmctc62214.2025.11196455","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/access.2024.3368748","name":"Improving Measurement Accuracy With a Neuro-Inspired Multi-Sensor Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1109/access.2024.3368748","authors":["Yun Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-21T18:56:30Z","doi":"10.1109/access.2024.3368748","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/iscmi67495.2025.11358596","name":"Experimental Real-Time EMPC for PV-Battery Systems using Neuro-Fuzzy Forecasting","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscmi67495.2025.11358596","authors":["William D. Chicaiza","Pablo G. Camacho","Javier Gómez","Danilo Herrera","Sergio Vázquez","Juan M. Escaño","Carlos Bordons"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-30T21:00:10Z","doi":"10.1109/iscmi67495.2025.11358596","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/drc61706.2024.10605469","name":"CMOS+X Technologies for Neuro-Vector-Symbolic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/drc61706.2024.10605469","authors":["Luqi Zheng","Haitong Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-29T19:15:01Z","doi":"10.1109/drc61706.2024.10605469","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1016/j.suscom.2026.101367","name":"Fog-Quant: A quantum computing inspired framework for fog computing deployment over 6G radio access networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.suscom.2026.101367","authors":["Shabir Ali","Dhirendra Kumar Shukla","Arvind Dagur","Akhilesh Kumar","Nitin Shukla","Sambit Satpathy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-27T23:52:45Z","doi":"10.1016/j.suscom.2026.101367","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-981-97-5979-8_12","name":"A Multiobjective Metaheuristic Algorithm Perspective to Design Riesz Digital Differentiator Exhibiting Zero-Phase Response","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-5979-8_12","authors":["Chandan Nayak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-25T20:59:46Z","doi":"10.1007/978-981-97-5979-8_12","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-032-05103-5_19","name":"Intelligent Mobile Robot Using Hybrid Neuro-Fuzzy Controller","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-05103-5_19","authors":["Ayman AbuBaker","Aiman Turani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-17T18:22:27Z","doi":"10.1007/978-3-032-05103-5_19","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.5772/35701","name":"Neuro-Fuzzy Digital Filter","source":"crossref","abstract":"","url":"https://doi.org/10.5772/35701","authors":["Jos de Jess Medel","Juan Carlos","Juan Carlos"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-05-18T08:01:43Z","doi":"10.5772/35701","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1287/ijoc.2024.0996","name":"A New Crossover Algorithm for LP Inspired by the Spiral Dynamic of PDHG","source":"crossref","abstract":"Motivated by large-scale applications, there is a recent trend of research on using first-order methods for solving LP. Among them, PDLP, which is based on a primal-dual hybrid gradient (PDHG) algorithm, may be the most promising one. In this paper, we present a geometric viewpoint on the behavior of PDHG for LP. We demonstrate that PDHG iterates exhibit a spiral pattern with a closed-form solution when the variable basis remains unchanged. This spiral pattern consists of two orthogonal components: rotation and forward movement, where rotation improves primal and dual feasibility, while forward movement advances the duality gap. We also characterize the different situations in which basis change events occur. Inspired by the spiral behavior of PDHG, we design a new crossover algorithm to obtain a vertex solution from any optimal LP solution. This approach differs from traditional simplex-based crossover methods. Our numerical experiments demonstrate the effectiveness of the proposed algorithm, showcasing its potential as an alternative option for crossover. History: Accepted by Antonio Frangioni, Area Editor for Design &amp; Analysis of Algorithms–Continuous. Funding: T. Liu is partially supported by National Natural Science Foundation of China [Grants NSFC-72225009, 72394360, 72394365]. H. Lu is partially supported by Air Force Office of Scientific Research [Grant FA9550-24-1-0051] and Office of Naval Research [Grant N000142412735]. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc . 2024.0996 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2024.0996 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .","url":"https://doi.org/10.1287/ijoc.2024.0996","authors":["Tianhao Liu","Haihao Lu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-06T17:16:30Z","doi":"10.1287/ijoc.2024.0996","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1016/j.asoc.2017.02.028","name":"Swarm robotics search &amp; rescue: A novel artificial intelligence-inspired optimization approach","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2017.02.028","authors":["M. Bakhshipour","M. Jabbari Ghadi","F. Namdari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-03-02T14:36:41Z","doi":"10.1016/j.asoc.2017.02.028","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1038/s41467-025-64470-3","name":"Modeling macroscopic brain dynamics with brain-inspired computing architecture","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s41467-025-64470-3","authors":["Zhong Zheng","Jing Wei","Yaru Xu","Chenhua Li","Tianying Lu","Qili Guo","Xueyao Ji","Hao Guo","Gang Wang","Lei Deng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-24T15:24:17Z","doi":"10.1038/s41467-025-64470-3","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-981-33-6773-9_14","name":"An Extensive Review of Charged System Search Algorithm for Engineering Optimization Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-33-6773-9_14","authors":["Siamak Talatahari","Mahdi Azizi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-31T12:03:02Z","doi":"10.1007/978-981-33-6773-9_14","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-642-34274-5_63","name":"Bio-inspired Sensory Data Aggregation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-34274-5_63","authors":["Alessandra De Paola","Marco Morana"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-09-30T13:21:47Z","doi":"10.1007/978-3-642-34274-5_63","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-981-16-3128-3_3","name":"Memetic Strategies for Network Design Problems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-16-3128-3_3","authors":["Mehrdad Amirghasemi","Thach-Thao Duong","Nathanael Hutchison","Johan Barthelemy","Yan Li","Pascal Perez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-18T23:09:33Z","doi":"10.1007/978-981-16-3128-3_3","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1016/b978-0-443-18634-9.09994-3","name":"Preface","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-18634-9.09994-3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-18T21:41:41Z","doi":"10.1016/b978-0-443-18634-9.09994-3","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1016/b978-012059781-9/50014-6","name":"Neuro Slicer","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-012059781-9/50014-6","authors":["Bijan Timsari","Richard M. Leahy","Jean-Marie Bouteiller","Michel Baudry"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-05-16T13:33:28Z","doi":"10.1016/b978-012059781-9/50014-6","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-031-84617-5_5","name":"A Bio-inspired Leader-Based Energy Management System for Drone Fleets","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-84617-5_5","authors":["Rosario Napoli","Antonio Celesti","Massimo Villari","Maria Fazio"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-20T06:59:30Z","doi":"10.1007/978-3-031-84617-5_5","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1016/b978-0-443-18509-0.09998-9","name":"Copyright","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-18509-0.09998-9","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-25T05:34:26Z","doi":"10.1016/b978-0-443-18509-0.09998-9","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1016/b978-0-443-15684-7.00012-9","name":"Waterproofing function","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-15684-7.00012-9","authors":["Songtao Hu","Xijia Ding"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-01T11:42:26Z","doi":"10.1016/b978-0-443-15684-7.00012-9","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1142/s1793292024500462","name":"Design of Nonlinear Autoregressive Neuro-Computing Structure for Bioconvective Micropolar Nanofluidic Model","source":"crossref","abstract":"In the present arena, the tools of artificial intelligence (AI) play a significant role in research across various fields by enabling advanced data analysis, pattern recognition and decision-making. This research work presents the numerical investigation of bioconvective micropolar nanofluidic model (BCMNFM) by employing the knacks of AI-based nonlinear autoregressive (NAR) approach with a combination of backpropagated Levenberg–Marquardt neural networks (BLMNNs) represented as NAR-BLMNNs. This research work investigates the flow design to highlight the attributes of mass and heat exchange. A dataset for BCMNFM is created by applying the Adam numerical procedure by variation of unsteadiness parameter ([Formula: see text], magnetic field parameter ([Formula: see text] thermophoresis parameter (Nt), Brownian motion parameter (Nb), bioconvection Peclet number (Pe) and spin gradient viscosity parameter ([Formula: see text] The skills of AI-based NAR-BLMNNs technique is then utilized on the dataset created for BCMNFM to investigate the approximate solutions. The achieved and impactful values of performance consistently range between [Formula: see text] and [Formula: see text] across all scenarios of BCMNFM. The precision and the validation of predicted approach NAR-BLMNNs is exceptionally established by the graphical demonstration for all scenarios of MSE, regression metrics, error histograms and time series graphs. The numerical calculations attained through AI-based NAR-BLMNNs technique further rationalize the precision of the proposed methodology for solving the BCMNFM effectively and efficiently.","url":"https://doi.org/10.1142/s1793292024500462","authors":["Zahoor Shah","Attika Jamil","Muhammad Asif Zahoor Raja","Muhammad Shoaib","Adiqa Kausar Kiani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-25T08:01:44Z","doi":"10.1142/s1793292024500462","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/ccis.2018.8691350","name":"Towards WARSHIP: Combining Components of Brain-Inspired Computing of RSH for Image Super Resolution","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ccis.2018.8691350","authors":["Wendi Xu","Ming Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-04-15T18:51:49Z","doi":"10.1109/ccis.2018.8691350","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1063/10.0039453","name":"Quantum Network Mapping Method Inspired by Nature","source":"crossref","abstract":"Non-invasive probe proves promising for navigating quantum world.","url":"https://doi.org/10.1063/10.0039453","authors":["Ben Ikenson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-17T15:44:51Z","doi":"10.1063/10.0039453","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1016/b978-0-443-15684-7.00007-5","name":"Hierarchical structures","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-15684-7.00007-5","authors":["Rui Xiong","Helmut Cölfen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-01T11:42:00Z","doi":"10.1016/b978-0-443-15684-7.00007-5","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-030-37218-7_61","name":"Comprehensive Review of Various Speech Enhancement Techniques","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_61","authors":["Savy Gulati"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T15:02:40Z","doi":"10.1007/978-3-030-37218-7_61","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.3997/2214-4609.2022615018","name":"Accelerating and Optimizing Oil and Gas Exploration Planning Using Quantum Inspired Classical Computing or Vector Annealing","source":"crossref","abstract":"","url":"https://doi.org/10.3997/2214-4609.2022615018","authors":["D. Pathania","S. Momose","T. Nishimura","M. Ikuta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-28T02:02:10Z","doi":"10.3997/2214-4609.2022615018","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-981-33-6862-0","name":"Computational Vision and Bio-Inspired Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-33-6862-0","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-06-14T01:02:45Z","doi":"10.1007/978-981-33-6862-0","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1007/978-3-319-50920-4_15","name":"Brain Action Inspired Morphological Image Enhancement","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-50920-4_15","authors":["Mahdi Khosravy","Neeraj Gupta","Ninoslav Marina","Ishwar K. Sethi","Mohammad Reza Asharif"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-03-08T06:42:10Z","doi":"10.1007/978-3-319-50920-4_15","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/bicta.2009.5338094","name":"A molecular computing model for 3-coloring graph problem based on circular DNA branch migration","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2009.5338094","authors":["Zhang Cheng","Yang Jing","Xu Jin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-11-24T13:50:07Z","doi":"10.1109/bicta.2009.5338094","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1109/hpcsim.2015.7237070","name":"Market-inspired dynamic resource allocation in many-core high performance computing systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/hpcsim.2015.7237070","authors":["Amit Kumar Singh","Piotr Dziurzanski","Leandro Soares Indrusiak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-09-03T21:45:56Z","doi":"10.1109/hpcsim.2015.7237070","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1016/j.asoc.2012.10.012","name":"Bacterially inspired evolving system with an application to time series prediction","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2012.10.012","authors":["D. Barrios Rolanía","J.M. Font","D. Manrique"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-11-13T00:35:51Z","doi":"10.1016/j.asoc.2012.10.012","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.1016/s1568-4946(03)00037-1","name":"Nonlinear dynamic system identification and control via constructivism inspired neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/s1568-4946(03)00037-1","authors":["Loo Chu Kiong","Mandava Rajeswari","M.V.C. Rao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-07-31T22:43:15Z","doi":"10.1016/s1568-4946(03)00037-1","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:29.741Z"},{"id":"doi:10.29121/ijrsmp.v12.i3.2025.01","name":"Method of Sustainable Product Development through Nature-Inspired Form.","source":"crossref","abstract":"","url":"https://doi.org/10.29121/ijrsmp.v12.i3.2025.01","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-12T11:22:13Z","doi":"10.29121/ijrsmp.v12.i3.2025.01","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1016/b978-0-443-18634-9.09996-7","name":"Index","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-18634-9.09996-7","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-18T21:41:43Z","doi":"10.1016/b978-0-443-18634-9.09996-7","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1038/s41598-025-91911-2","name":"Legendre based neural networks integrated with heuristic algorithms for the analysis of Lorenz chaotic model: an intelligent and comparative study.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-91911-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-91911-2","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-025-32695-3","name":"Adaptive virtual impedance control strategy based on IWOA-fuzzy PID and its application to reactive power sharing in islanded microgrids.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-32695-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-32695-3","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3390/diagnostics16091361","name":"A Verifiable Framework for Brain Tumor Classification: Combining Vision Transformers, Class-Weighted Learning, and SMT-Based Formal Decision Traces.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/diagnostics16091361","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/diagnostics16091361","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3390/s25237188","name":"Smart Irrigation with Fuzzy Decision Support Systems in Trentino Vineyards.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s25237188","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/s25237188","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-025-31037-7","name":"Reforming disease prognosis and treatment prediction for palliative care with hybrid metaheuristic deep neural architectures in IoT healthcare ecosystems.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-31037-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-31037-7","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1088/1741-2552/ade189","name":"Failure modes and mitigations for Bayesian optimization of neuromodulation parameters.","source":"europepmc","abstract":"","url":"https://doi.org/10.1088/1741-2552/ade189","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1088/1741-2552/ade189","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-025-32394-z","name":"Integration of fast charging EV infrastructure with high gain Z-source converters and hybrid optimized MPPT algorithm.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-32394-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-32394-z","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3390/brainsci15111165","name":"MFA-CNN: An Emotion Recognition Network Integrating 1D-2D Convolutional Neural Network and Cross-Modal Causal Features.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/brainsci15111165","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/brainsci15111165","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3390/biomimetics11010017","name":"Bio-Inspired Reactive Approaches for Automated Guided Vehicle Path Planning: A Review.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics11010017","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/biomimetics11010017","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3390/biomimetics10110723","name":"Vocabulary at the Living-Machine Interface: A Narrative Review of Shared Lexicon for Hybrid AI.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics10110723","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/biomimetics10110723","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-025-29908-0","name":"Software cost estimation using TabNet and Harris Hawks Optimization.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-29908-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-29908-0","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-025-03185-3","name":"Developing a novel hybrid model based on GRU deep neural network and Whale optimization algorithm for precise forecasting of river's streamflow.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-03185-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-03185-3","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41698-025-01183-2","name":"Enhancing decision-making in glioblastoma surgery through an explainable human-AI collaboration: an international multicenter model development and external validation study.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41698-025-01183-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41698-025-01183-2","addedAt":"2026-09-01T01:48:29.741Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-025-13991-4","name":"A fused weighted federated learning-based adaptive approach for early-stage drug prediction.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-13991-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-13991-4","addedAt":"2026-09-01T01:48:29.742Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1093/bib/bbaf682","name":"MetImputBERT: a pretrained BERT framework for missing value imputation in NMR metabolomics data.","source":"europepmc","abstract":"","url":"https://doi.org/10.1093/bib/bbaf682","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1093/bib/bbaf682","addedAt":"2026-09-01T01:48:29.742Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-025-26009-w","name":"Improving efficiency in smart grid monitoring using hybrid classification and dimensionality reduction.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-26009-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-26009-w","addedAt":"2026-09-01T01:48:29.742Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-025-17736-1","name":"Assessment of off-road agricultural traction in situ using large scale machine learning and neurocomputing models.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-17736-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-17736-1","addedAt":"2026-09-01T01:48:29.742Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-025-05146-2","name":"Prediction of compressive strength of fiber-reinforced concrete containing silica (SiO&lt;sub&gt;2&lt;/sub&gt;) based on metaheuristic optimization algorithms and machine learning techniques.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-05146-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-05146-2","addedAt":"2026-09-01T01:48:29.742Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41467-025-57995-0","name":"Computational memory capacity predicts aging and cognitive decline.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-57995-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-57995-0","addedAt":"2026-09-01T01:48:29.742Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1371/journal.pone.0323098","name":"Neuro-symbolic procedural semantics for explainable visual dialogue.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pone.0323098","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1371/journal.pone.0323098","addedAt":"2026-09-01T01:48:29.742Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1073/pnas.2502193122","name":"Novelty as a drive of human exploration in complex stochastic environments.","source":"europepmc","abstract":"","url":"https://doi.org/10.1073/pnas.2502193122","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1073/pnas.2502193122","addedAt":"2026-09-01T01:48:29.742Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-025-99957-y","name":"A lightweight deep evidence fusion framework for smart home appliance detection and classification via internet of things devices.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-99957-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-99957-y","addedAt":"2026-09-01T01:48:29.742Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41398-025-03662-3","name":"Distinct neuroimaging subtypes of ADHD among adolescents based on semi-supervised learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41398-025-03662-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41398-025-03662-3","addedAt":"2026-09-01T01:48:29.742Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1038/s41598-025-85206-9","name":"Enhancing feature selection for multi-pose facial expression recognition using a hybrid of quantum inspired firefly algorithm and artificial bee colony algorithm.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-85206-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-85206-9","addedAt":"2026-09-01T01:48:29.742Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1016/j.heliyon.2025.e42393","name":"GA-Attention-Fuzzy-Stock-Net: An optimized neuro-fuzzy system for stock market price prediction with genetic algorithm and attention mechanism.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.heliyon.2025.e42393","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.heliyon.2025.e42393","addedAt":"2026-09-01T01:48:29.742Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.3389/fncir.2025.1584322","name":"Deviance detection and regularity sensitivity in dissociated neuronal cultures.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fncir.2025.1584322","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fncir.2025.1584322","addedAt":"2026-09-01T01:48:29.742Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1186/s12874-025-02686-z","name":"HILAMA: High-dimensional multi-omics mediation analysis with latent confounding.","source":"europepmc","abstract":"","url":"https://doi.org/10.1186/s12874-025-02686-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1186/s12874-025-02686-z","addedAt":"2026-09-01T01:48:29.742Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.52305/zgqm5576","name":"Psychobiotics and the Neuro-Gastro Frontier","source":"crossref","abstract":"Psychobiotics and the Neuro-Gastro Frontier includes fourteen Chapters, intending to take readers from basic ideas to new clinical and translational applications. The first sections describe the structure and function of the gut–brain axis, developmental origins of microbiome–brain interactions, and lifestyle and environmental factors that shape microbial ecosystems. The following chapters discuss psychobiotic classifications, mechanistic pathways, neuroimmune interactions, clinical trials, safety issues, and regulatory frameworks. The purpose of this work is to synthesize up-to-date research with practical and mechanistic insights, bringing together basic neurogastroenterological science and therapeutic potential in the real world.","url":"https://doi.org/10.52305/zgqm5576","authors":["Mahdi Asghari Ozma","Niloofar Fallahi Alileh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-28T20:32:21Z","doi":"10.52305/zgqm5576","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.55277/researchhub.5vpc8em3","name":"~^@+The Neuro Wave ReviEws (2026): We Tried It—My Honest Review!!&amp;","source":"crossref","abstract":"","url":"https://doi.org/10.55277/researchhub.5vpc8em3","authors":["Jahid Hossain"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-07T09:51:33Z","doi":"10.55277/researchhub.5vpc8em3","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1007/978-981-15-2133-1_13","name":"Continuous Optimizers for Automatic Design and Evaluation of Classification Pipelines","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-15-2133-1_13","authors":["Iztok Fister","Milan Zorman","Dušan Fister"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-03-11T18:03:41Z","doi":"10.1007/978-981-15-2133-1_13","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1007/978-3-319-27400-3_2","name":"A Self-configuring Multi-strategy Multimodal Genetic Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-27400-3_2","authors":["Evgenii Sopov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-01T12:08:38Z","doi":"10.1007/978-3-319-27400-3_2","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1109/jiot.2024.3358900","name":"Quantum-Computing-Inspired Optimal Power Allocation Mechanism in Edge Computing Environment","source":"crossref","abstract":"","url":"https://doi.org/10.1109/jiot.2024.3358900","authors":["Munish Bhatia","Sandeep Sood"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-26T18:58:08Z","doi":"10.1109/jiot.2024.3358900","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.64751/ajaccm.2026.v6.n2(2).691","name":"Neuro Fusion-CART: A Hybrid Intelligence Framework for Anomaly Detection in VANETs","source":"crossref","abstract":"Vehicular Ad Hoc Network (VANET) generate large volumes of real-time data such as packet size, latency, vehicle speed, and signal strength, which can be vulnerable to malicious attacks. Ensuring secure and reliable communication is therefore a critical challenge. Traditionally, anomaly detection in such networks relied on rule-based systems and statistical threshold techniques. These methods depended heavily on predefined rules and manual monitoring, making them less effective in handling complex, dynamic traffic patterns. They often failed to detect unknown or evolving attack behaviors and lacked adaptability to real-time scenarios. In the proposed system, a Machine Learning (ML) and Deep Learning (DL) – Classification and Regression Trees (CART) based hybrid approach is implemented to improve detection accuracy and adaptability. The system utilizes multiple algorithms including Linear Regression (LR), Decision Tree (DT), Passive Aggressive (PA) algorithms, and a novel proposed model called KNeuroFusion CART. This hybrid model integrates Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) for feature extraction, combined with K-Nearest Neighbors (KNN) for final classification and regression. The models are trained on VANET dataset features such as packet rate, vehicle speed, and anomaly score, achieving high accuracy in detecting normal and attack patterns. The research is developed using Flask for web deployment, SQLite for database management, and libraries like Scikit-learn, TensorFlow, Pandas, and Matplotlib. The system provides both single and batch prediction capabilities, along with visualization and analysis tools","url":"https://doi.org/10.64751/ajaccm.2026.v6.n2(2).691","authors":["S. Sundeep Kumar","Penti Bhavani","Mohammed Mudassir","Goshika Navya","Kurmeti Prem Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-23T06:05:57Z","doi":"10.64751/ajaccm.2026.v6.n2(2).691","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1109/nice65350.2025.11065250","name":"A LIF-based Legendre Memory Unit as neuromorphic State Space Model benchmarked on a second-long spatio-temporal task","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nice65350.2025.11065250","authors":["Benedetto Leto","Gianvito Urgese","Enrico Macii","Vittorio Fra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-08T13:36:20Z","doi":"10.1109/nice65350.2025.11065250","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1016/j.engappai.2025.111889","name":"A neuro-inspired approach for Continual Multi-Label Learning with evolving spiking networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.engappai.2025.111889","authors":["Sourav Mishra","Suresh Sundaram","P.Md. Thousif"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-13T16:21:05Z","doi":"10.1016/j.engappai.2025.111889","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1504/ijbic.2014.062633","name":"A catalytic neuro-fuzzy approach to model agent-based simulation for ombudsman (Lokpal)","source":"crossref","abstract":"","url":"https://doi.org/10.1504/ijbic.2014.062633","authors":["Praveen Ranjan Srivastava","Saurabh Verma","Shivam Upadhyay"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-06-12T07:45:52Z","doi":"10.1504/ijbic.2014.062633","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1016/b978-0-443-33490-0.00013-2","name":"Introduction","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-33490-0.00013-2","authors":["R. Silva-Néto","Kathleen B. Digre"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-01T00:48:11Z","doi":"10.1016/b978-0-443-33490-0.00013-2","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1016/b978-0-443-49243-3.20001-3","name":"Index","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-49243-3.20001-3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-26T13:49:33Z","doi":"10.1016/b978-0-443-49243-3.20001-3","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1007/978-3-032-23604-3_33","name":"Self-organized Criticality for Green Distributed Computing: A Sandpile-Inspired Model of Energy-Efficient Load Balancing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-23604-3_33","authors":["Juan Luis Jiménez Laredo","Juan Julián Merelo Guervós","Paulin Héleine","Damien Olivier"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-08T03:17:05Z","doi":"10.1007/978-3-032-23604-3_33","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1002/aelm.202500794","name":"Millisecond‐Scale Relaxation in Metastable HZO Ferroelectric Capacitors for Bio‐Inspired Temporal Computing","source":"crossref","abstract":"ABSTRACT Depolarization effects in ‐based ferroelectric devices have gained significant interest for research on non‐volatile memory applications. Understanding retention mechanisms enables device optimization for temporal and brain‐inspired computing in hardware. This work presents a ferroelectric capacitor stack that shows a metastable state that relaxes on a millisecond scale through a unique interface configuration. Electrical characterization demonstrates the device's capability for implementing tunable time constants in hardware, followed by investigation of the electronic mechanisms underlying observed retention times to facilitate modeling of retention processes in ‐based ferroelectric capacitors. Internal electric fields stabilize one polarization state, enabling unipolar operation with millisecond retention for the unstable polarization. The observed retention loss depends on both polarization state and programming conditions, allowing exploitation of multiple memory time‐scales in a single device. The defective interface in the material stack provides insight into retention loss mechanisms and internal bias field origins in ‐based ferroelectric devices. These internal bias fields are related to interface composition, with oxygen vacancies identified as a possible source. The results demonstrate that ‐based ferroelectric devices offer an elegant solution for realizing tunable time constants in scaled memory devices, providing memory elements for brain‐inspired temporal computing hardware.","url":"https://doi.org/10.1002/aelm.202500794","authors":["Luca Fehlings","Thomas Mikolajick","Beatriz Noheda","Erika Covi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-17T11:41:45Z","doi":"10.1002/aelm.202500794","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1016/j.asoc.2007.10.020","name":"Artificial wavelet neural network and its application in neuro-fuzzy models","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2007.10.020","authors":["Ahmad Banakar","Mohammad Fazle Azeem"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-11-20T12:21:08Z","doi":"10.1016/j.asoc.2007.10.020","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-3-540-87536-9_53","name":"Neuro-inspired Speech Recognition with Recurrent Spiking Neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-540-87536-9_53","authors":["Arfan Ghani","T. Martin McGinnity","Liam P. Maguire","Jim Harkin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-09-05T15:23:30Z","doi":"10.1007/978-3-540-87536-9_53","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1007/978-3-211-78775-5_1","name":"Overview of Motor Systems. Types of Movements: Reflexes, Rhythmical and Voluntary Movements","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-211-78775-5_1","authors":["Tatiana G. Deliagina"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-11-29T07:44:42Z","doi":"10.1007/978-3-211-78775-5_1","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1093/nop/npag040","name":"Society News","source":"crossref","abstract":"","url":"https://doi.org/10.1093/nop/npag040","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-14T06:01:28Z","doi":"10.1093/nop/npag040","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1109/dicta.2009.75","name":"Biologically Inspired Contrast Enhancement Using Asymmetric Gain Control","source":"crossref","abstract":"","url":"https://doi.org/10.1109/dicta.2009.75","authors":["Asim A. Khwaja","Roland Goecke"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-22T16:14:42Z","doi":"10.1109/dicta.2009.75","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1109/nabic.2009.5393688","name":"File format identification and information extraction","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393688","authors":["R. Dhanalakshmi","C. Chellappan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393688","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1007/s40012-016-0133-9","name":"Computing inspired by daily life","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s40012-016-0133-9","authors":["Tanay Chattopadhyay"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-12-28T04:48:40Z","doi":"10.1007/s40012-016-0133-9","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1016/j.asoc.2007.07.011","name":"Using adaptive neuro-fuzzy inference system for hydrological time series prediction","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2007.07.011","authors":["Mohammad Zounemat-Kermani","Mohammad Teshnehlab"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-08-20T12:45:21Z","doi":"10.1016/j.asoc.2007.07.011","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1177/15330338251391080/v3/response1","name":"Author response for \"NeuroMorphFusion: A Neuro-Inspired Hybrid Learning Framework for Interpretable Deep Lesion Detection in IoT-Enabled Healthcare Systems\"","source":"crossref","abstract":"","url":"https://doi.org/10.1177/15330338251391080/v3/response1","authors":["Roseline Oluwaseun Ogundokun","Rotimi-Williams Bello","Pius Adewale Owolawi","Etienne A. van Wyk","Chunling Tu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-12T21:04:38Z","doi":"10.1177/15330338251391080/v3/response1","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1504/ijbic.2012.047174","name":"Neuro-fuzzy-based torque ripple reduction and performance improvement of VSI fed induction motor drive","source":"crossref","abstract":"","url":"https://doi.org/10.1504/ijbic.2012.047174","authors":["G. Durgasukumar","Mukesh Kumar Pathak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-06-05T16:42:56Z","doi":"10.1504/ijbic.2012.047174","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1007/3-211-27389-1_87","name":"Comparison of nature inspired and deterministic scheduling heuristics considering optimal schedules","source":"crossref","abstract":"","url":"https://doi.org/10.1007/3-211-27389-1_87","authors":["Udo Hönig","Wolfram Schiffmann"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-12-08T01:34:44Z","doi":"10.1007/3-211-27389-1_87","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1109/dest.2011.5936568","name":"Track A — Ecosystems inspired computing and theoretical foundations","source":"crossref","abstract":"","url":"https://doi.org/10.1109/dest.2011.5936568","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-07-07T14:59:45Z","doi":"10.1109/dest.2011.5936568","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1364/cosi.2018.cw3b.1","name":"A Neuro-Inspired Model for Image Motion Processing","source":"crossref","abstract":"","url":"https://doi.org/10.1364/cosi.2018.cw3b.1","authors":["Kaiser Niknam","Amir Akbarian","Behrad Noudoost","Neda Nategh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-06-18T13:45:21Z","doi":"10.1364/cosi.2018.cw3b.1","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1109/iscas56072.2025.11043612","name":"Live Demonstration: Improving efficiency of speech recognition with neuro-inspired units on AIU Spyre","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas56072.2025.11043612","authors":["Yannick Schnider","Thomas Ortner","Stanisław Woźniak","Alberto Mannari","Angeliki Pantazi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-27T17:42:19Z","doi":"10.1109/iscas56072.2025.11043612","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1109/cicc.2019.8780116","name":"A 2048-Neuron Spiking Neural Network Accelerator With Neuro-Inspired Pruning And Asynchronous Network On Chip In 40nm CMOS","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cicc.2019.8780116","authors":["Sung-Gun Cho","Edith Beigne","Zhengya Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-08-01T20:03:04Z","doi":"10.1109/cicc.2019.8780116","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1007/978-3-319-59156-8_4","name":"Individual and Social Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-59156-8_4","authors":["Anthony Brabazon","Seán McGarraghy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-09-26T14:09:36Z","doi":"10.1007/978-3-319-59156-8_4","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1109/nabic.2009.5393359","name":"Paired comparison-based Interactive Differential Evolution","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393359","authors":["Hideyuki Takagi","Denis Pallez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393359","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/nice61972.2024.10548609","name":"Spiking Neural Network-based Flight Controller","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nice61972.2024.10548609","authors":["Diego Chavez Arana","Omar A. García A.","Luis Rodolfo Garcia Carrillo","Ignacio Rubio Scola","Eduardo S. Espinoza","Andrew T. Sornborger"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-11T17:30:32Z","doi":"10.1109/nice61972.2024.10548609","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1117/12.3091280","name":"Decentralized fabrication of functional oxide films through bio-inspired microreactor platforms","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3091280","authors":["Chih-Hung Chang","Alvin Chang","Venkata Vinay Doddapaneni"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-17T17:05:47Z","doi":"10.1117/12.3091280","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1080/01658107.2026.2677630","name":"Sight Impairment Registration in the Neuro-Ophthalmology Clinic","source":"crossref","abstract":"","url":"https://doi.org/10.1080/01658107.2026.2677630","authors":["Sana Khan","Lina Sorour","Irene M. Pepper","Joanna M. Jefferis","Simon J. Hickman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-29T19:47:46Z","doi":"10.1080/01658107.2026.2677630","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1007/978-3-319-59156-8_19","name":"Looking to the Future","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-59156-8_19","authors":["Anthony Brabazon","Seán McGarraghy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-09-26T18:09:36Z","doi":"10.1007/978-3-319-59156-8_19","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1145/3736393","name":"Proceedings of the 2nd Workshop on Quantum Computing and Quantum-Inspired Technology for Data-Intensive Systems and Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3736393","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-23T12:39:22Z","doi":"10.1145/3736393","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1007/978-3-540-72432-2_33","name":"Nonlinear Neuro-fuzzy Network for Channel Equalization","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-540-72432-2_33","authors":["Rahib Abiyev","Fakhreddin Mamedov","Tayseer Al-shanableh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-09-19T04:32:12Z","doi":"10.1007/978-3-540-72432-2_33","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/icicic.2007.406","name":"Neuro-Fuzzy, Chaos Applications A Study of Neuro-fuzzy Learning Algorithm for Hardware Implementation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icicic.2007.406","authors":["Kuniaki Fujimoto","Hirofumi Sasaki","Ren-Qi Yang","Yan Shi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-01-16T09:20:19Z","doi":"10.1109/icicic.2007.406","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1145/3320288.3320303","name":"Analysis of Wide and Deep Echo State Networks for Multiscale Spatiotemporal Time Series Forecasting","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3320288.3320303","authors":["Zachariah Carmichael","Humza Syed","Dhireesha Kudithipudi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-08-23T12:03:10Z","doi":"10.1145/3320288.3320303","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1145/3381755.3381776","name":"Closed-loop experiments on the BrainScaleS-2 architecture","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3381755.3381776","authors":["K. Schreiber","T. C. Wunderlich","C. Pehle","M. A. Petrovici","J. Schemmel","K. Meier"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-18T23:09:51Z","doi":"10.1145/3381755.3381776","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.62762/tmi.2025.403059","name":"Neuro-Inspired Alert System for Air Quality Prediction Using Ensemble Preprocessing and SNN Classification","source":"crossref","abstract":"Air pollution has emerged as a critical challenge, directly affecting human health, urban sustainability, and climate systems. Traditional air-quality index (AQI) prediction models often struggle to provide timely alerts because they are not very sensitive to changes over time and are hard to understand. This paper proposes a Neuro-Inspired Alert System for Air Quality Prediction (NAS--AQP) that incorporates an ensemble learning approach using voting regression to enhance input quality, followed by classification through a Spiking Neural Network (SNN). The system is designed such that it captures the temporal and nonlinear relationships between air pollutants such as Nitrogen Dioxide ($NO_2$), Sulphur Dioxide ($SO_2$), Respirable Suspended Particulate Matter (RSPM) and Suspended Particulate Matter (SPM). The proposed method starts with preprocessing of the data and normalizing the features. After that, models like Linear Regression (LR), Random Forest (RF), and Decision Tree (DT) are trained and evaluated using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination ($R^2$) metrics. After the training of above models, a voting based ensemble approach is used to improve AQI regression accuracy. A threshold based rule is then used to convert received, AQI predictions into binary alerts. Finally, SNN is trained to classify these alerts to achieve energy, efficient, real time, alerting by using its temporal coding and sparse activation. The ensemble voting regression model achieved an RMSE of 8.43 and MAE of 6.21, while the SNN classifier attained a classification accuracy of 92.4%.","url":"https://doi.org/10.62762/tmi.2025.403059","authors":["Sneh Sharma","Kashish Devgan","Devanshi Jangra","Aanshi Bhardwaj","Shubhani Aggarwal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-06T22:52:09Z","doi":"10.62762/tmi.2025.403059","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.3390/pr9030511","name":"An In Vivo Proposal of Cell Computing Inspired by Membrane Computing","source":"crossref","abstract":"Intractable problems are challenging and not uncommon in Computer Science. The computing generation we are living in forces us to look for an alternative way of computing, as current computers are facing limitations when dealing with complex problems and bigger input data. Physics and Biology offer great alternatives to solve these problems that traditional computers cannot. Models like Quantum Computing and cell computing are emerging as possible solutions to the current problems the conventional computers are facing. This proposal describes an in vivo framework inspired by membrane computing and based on alternative computational frameworks that have been proven to be theoretically correct such as chemical reaction series. The abilities of a cell as a computational unit make this proposal a starting point in the creation of feasible potential frameworks to enhance the performance of applications in different disciplines such as Biology, BioMedicine, Computer networks, and Social Sciences, by accelerating drastically the way information is processed by conventional architectures and possibly achieving results that presently are not possible due to the limitations of the current computing paradigm. This paper introduces an in vivo solution that uses the principles of membrane computing and it can produce non-deterministic outputs.","url":"https://doi.org/10.3390/pr9030511","authors":["Alberto Arteta Albert","Ernesto Díaz-Flores","Luis Fernando de Mingo López","Nuria Gómez Blas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-14T23:52:06Z","doi":"10.3390/pr9030511","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1080/10798587.1999.10750764","name":"A VLSI Neuro-Fuzzy Controller","source":"crossref","abstract":"","url":"https://doi.org/10.1080/10798587.1999.10750764","authors":["Nasser Sadati","Hoorman Mohseni"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-10-24T14:49:41Z","doi":"10.1080/10798587.1999.10750764","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1016/j.asoc.2016.03.009","name":"Suspended sediment concentration estimation by stacking the genetic programming and neuro-fuzzy predictions","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2016.03.009","authors":["Ehsan Shamaei","Marjan Kaedi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-04-14T19:43:08Z","doi":"10.1016/j.asoc.2016.03.009","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1145/2954679.2872417","name":"Brain Inspired Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1145/2954679.2872417","authors":["R. Stanley Williams"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-06-10T13:54:00Z","doi":"10.1145/2954679.2872417","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.4018/978-1-5225-0235-7.les1","name":"Prediction of Iron Adsorption Capacity of Calcareous Soil from Aqueous Solution","source":"crossref","abstract":"","url":"https://doi.org/10.4018/978-1-5225-0235-7.les1","authors":["Siddhartha Bhattacharyya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-09-07T14:02:34Z","doi":"10.4018/978-1-5225-0235-7.les1","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-3-319-73347-0_4","name":"Controlling and Learning Motor Functions","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-73347-0_4","authors":["Luca Patanè","Roland Strauss","Paolo Arena"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-20T08:24:29Z","doi":"10.1007/978-3-319-73347-0_4","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/nice65350.2025.11065806","name":"Threshold Adaptation in Spiking Networks Enables Shortest Path Finding and Place Disambiguation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nice65350.2025.11065806","authors":["Robin Dietrich","Tobias Fischer","Nicolai Waniek","Nico Reeb","Michael Milford","Alois Knoll","Adam D. Hines"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-08T13:36:20Z","doi":"10.1109/nice65350.2025.11065806","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1093/neuonc/nox168.245","name":"DDIS-09. IDH1 MUTATION-INSPIRED Α-KETOGLUTARIC ACID MIMICS FOR EPIGENETIC THERAPY OF HIGHER GRADE GLIOMAS","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuonc/nox168.245","authors":["Hanumantha Rao Madala","Surendra Reddy Punganuru","Kalkunte Srivenugopal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-11-06T11:14:03Z","doi":"10.1093/neuonc/nox168.245","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1145/2954680.2872417","name":"Brain Inspired Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1145/2954680.2872417","authors":["R. Stanley Williams"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-06-10T13:54:00Z","doi":"10.1145/2954680.2872417","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-3-319-59156-8_17","name":"Foraging Models and Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-59156-8_17","authors":["Anthony Brabazon","Seán McGarraghy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-09-26T14:09:36Z","doi":"10.1007/978-3-319-59156-8_17","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.2139/ssrn.4316071","name":"A New Algorithm for Computing Path Integrals and Weak Approximation of SDEs Inspired by Large Deviations and Malliavin Calculus","source":"crossref","abstract":"The paper gives a novel path integral formula inspired by large deviation theory and Malliavin calculus. The proposed finite-dimensional approximation of integrals on path space will be a new higher-order weak approximation of multidimensional stochastic differential equations where the dominant part of the local expansion is governed by Varadhan's geodesic distance and the correction terms are given as Malliavin weights. An optimal truncation of asymptotic expansion is used to reduce computational effort. Kusuoka's estimate is applied to justify the finite-dimensional approximation of path integrals. An efficient simulation method is provided with the algorithm. Numerical results are shown to verify the effectiveness.","url":"https://doi.org/10.2139/ssrn.4316071","authors":["Toshihiro Yamada"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-03T15:27:19Z","doi":"10.2139/ssrn.4316071","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1016/j.asoc.2014.06.009","name":"An adaptive neuro-fuzzy identification model for the detection of meat spoilage","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2014.06.009","authors":["Vassilis S. Kodogiannis","Abeer Alshejari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-06-13T16:52:53Z","doi":"10.1016/j.asoc.2014.06.009","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1201/9781315153797-7","name":"Digital Image Segmentation Using Computational Intelligence Approaches","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781315153797-7","authors":["S. Vijayakumar","V. Santhi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-19T05:43:32Z","doi":"10.1201/9781315153797-7","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/s11227-025-07644-6","name":"Quantum computing-inspired resource distribution in healthcare","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11227-025-07644-6","authors":["Abdullah Alqahtani","Munish Bhatia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-25T10:40:24Z","doi":"10.1007/s11227-025-07644-6","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1109/bicta.2009.5338132","name":"Orthogonal locality discriminant embedding for document classification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2009.5338132","authors":["Ziqiang Wang","Xia Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-11-24T13:50:07Z","doi":"10.1109/bicta.2009.5338132","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-0-387-73394-4_6","name":"Statistically inspired preconditioners","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-0-387-73394-4_6","authors":["Daniela Calvetti","Erkki Somersalo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-11-19T11:30:32Z","doi":"10.1007/978-0-387-73394-4_6","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/nabic.2010.5716356","name":"An evolutionary design for software systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2010.5716356","authors":["Thuy-Linh Nguyen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-02-18T19:03:54Z","doi":"10.1109/nabic.2010.5716356","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1021/acsaelm.4c00584.s001","name":"Multifunctional Resistive Switching in a Magnetization-Graded Ni/NiMnIn/V2O5 Flexible Heterostructure toward Brain-Inspired Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acsaelm.4c00584.s001","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-06T12:10:13Z","doi":"10.1021/acsaelm.4c00584.s001","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1117/12.2277955","name":"Nanodevices for bio-inspired computing (Conference Presentation)","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.2277955","authors":["Julie Grollier"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-09-19T18:38:14Z","doi":"10.1117/12.2277955","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/nabic.2011.6089650","name":"Meta-heuristic optimization reloaded","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2011.6089650","authors":["Mario Koppen","Kaori Yoshida","Kei Ohnishi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-12-06T21:02:25Z","doi":"10.1109/nabic.2011.6089650","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1016/j.asoc.2018.06.012","name":"Adaptive critic-based quaternion neuro-fuzzy controller design with application to chaos control","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2018.06.012","authors":["Pouria Tooranjipour","Ramin Vatankhah"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-06-15T03:50:00Z","doi":"10.1016/j.asoc.2018.06.012","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1016/j.asoc.2017.10.021","name":"A dual fast and slow feature interaction in biologically inspired visual recognition of human action","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2017.10.021","authors":["Bardia Yousefi","Chu Kiong Loo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-10-23T11:53:59Z","doi":"10.1016/j.asoc.2017.10.021","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-0-387-09655-1_11","name":"Distributed Fault-Tolerant Robot Control Architecture Based on Organic Computing Principles","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-0-387-09655-1_11","authors":["Adam Auf","Marek Litza","Erik Maehle"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-08-19T13:40:02Z","doi":"10.1007/978-0-387-09655-1_11","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.18494/sam.2020.2708","name":"Development of an Automated Assistive Trainer Inspired by Neuro-developmental Treatment","source":"crossref","abstract":"","url":"https://doi.org/10.18494/sam.2020.2708","authors":["Fu-Cheng Wang","Yu-You Lin","You-Chi Li","Po-Yin Chen","Chung-Huang Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-29T22:06:27Z","doi":"10.18494/sam.2020.2708","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-3-642-58930-0_22","name":"Intelligent Robotic Systems Based on Soft Computing—Adaptation, Learning and Evolution","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-58930-0_22","authors":["Toshio Fukuda","Koji Shimojima"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-06-15T23:06:59Z","doi":"10.1007/978-3-642-58930-0_22","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/bimnics.2007.4610092","name":"Access control mechanisms for fraglets","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bimnics.2007.4610092","authors":["Fabio Martinelli","Marinella Petrocchi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-09-08T20:06:46Z","doi":"10.1109/bimnics.2007.4610092","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1002/9780470429983.ch18","name":"Biomedical and Biomedicine Applications of CNTs","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9780470429983.ch18","authors":["Tulin Mangir"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-11-24T16:16:40Z","doi":"10.1002/9780470429983.ch18","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.4018/978-1-4666-1574-8.ch020","name":"Microscope Volume Segmentation Improved through Non-Linear Restoration","source":"crossref","abstract":"An efficient segmentation technique based on the use of a modified k-Means algorithm and the Otsu’s thresholding method is improved through a non-linear restoration of microscope volumes. An algorithm is proposed to automatically compute the k value for the clustering k-Means method. The unsupervised algorithm is used in the context of segmentation by considering regions as clusters. A comparison between the segmentation results before and after restoration is presented. The evaluation of the region segmentation included the root mean squared error and a normalized uniformity measure. Results showed significant improvement of segmentation when using the non-linear restoration method based on prior known information, such as the imaging system and the noise statistics.","url":"https://doi.org/10.4018/978-1-4666-1574-8.ch020","authors":["Moacir P. Ponti"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-05-10T09:54:52Z","doi":"10.4018/978-1-4666-1574-8.ch020","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1201/9781003186885-8","name":"Virtual Machine Selection Optimization Using Nature-Inspired Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003186885-8","authors":["R. B. Madhumala","Harshvardhan Tiwari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-06T17:48:56Z","doi":"10.1201/9781003186885-8","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/hpec.2016.7761643","name":"An approach to big data inspired by statistical mechanics","source":"crossref","abstract":"","url":"https://doi.org/10.1109/hpec.2016.7761643","authors":["John A. Cortese"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-12-01T21:44:07Z","doi":"10.1109/hpec.2016.7761643","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/sai.2017.8252094","name":"Cognitive artificial intelligence: Brain-inspired intelligent computation in artificial intelligence","source":"crossref","abstract":"","url":"https://doi.org/10.1109/sai.2017.8252094","authors":["Adang Suwandi Ahmad","Arwin Datumaya Wahyudi Sumari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-01-11T23:49:34Z","doi":"10.1109/sai.2017.8252094","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1038/ncomms11059","name":"Semiconductor-inspired design principles for superconducting quantum computing","source":"crossref","abstract":"Abstract Superconducting circuits offer tremendous design flexibility in the quantum regime culminating most recently in the demonstration of few qubit systems supposedly approaching the threshold for fault-tolerant quantum information processing. Competition in the solid-state comes from semiconductor qubits, where nature has bestowed some very useful properties which can be utilized for spin qubit-based quantum computing. Here we begin to explore how selective design principles deduced from spin-based systems could be used to advance superconducting qubit science. We take an initial step along this path proposing an encoded qubit approach realizable with state-of-the-art tunable Josephson junction qubits. Our results show that this design philosophy holds promise, enables microwave-free control, and offers a pathway to future qubit designs with new capabilities such as with higher fidelity or, perhaps, operation at higher temperature. The approach is also especially suited to qubits on the basis of variable super-semi junctions.","url":"https://doi.org/10.1038/ncomms11059","authors":["Yun-Pil Shim","Charles Tahan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-03-17T06:10:08Z","doi":"10.1038/ncomms11059","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/nabic.2010.5716339","name":"Communication via quantum neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2010.5716339","authors":["A Sagheer","N Metwally"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-02-18T19:03:54Z","doi":"10.1109/nabic.2010.5716339","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/apscc.2008.28","name":"On Novel Economic-Inspired Centrality Measures in Weighted Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/apscc.2008.28","authors":["Yufeng Wang","Akihiro Nakao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-02-13T19:46:34Z","doi":"10.1109/apscc.2008.28","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1002/9780470429983.ch15","name":"Computational Tasks in Medical Nanorobotics","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9780470429983.ch15","authors":["Robert A. Freitas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-11-24T16:16:40Z","doi":"10.1002/9780470429983.ch15","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.12783/dtcse/ammso2019/30111","name":"Bio-inspired Computing Practice on Traveling Salesman Problem","source":"crossref","abstract":"","url":"https://doi.org/10.12783/dtcse/ammso2019/30111","authors":["Wei-jun SU"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-06-24T22:31:43Z","doi":"10.12783/dtcse/ammso2019/30111","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/nabic.2011.6089618","name":"Optimizers derived from human opinion formation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2011.6089618","authors":["Martin Macas","Lenka Lhotska"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-12-06T16:02:25Z","doi":"10.1109/nabic.2011.6089618","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1145/3517343.3517370","name":"A Framework to Enable Top-Down Co-Design of Neuromorphic Systems for Real-World Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3517343.3517370","authors":["Catherine Schuman","James Plank","Robert Patton","Thomas Potok","Garrett Rose"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-05-04T07:28:08Z","doi":"10.1145/3517343.3517370","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1145/3517343.3517372","name":"Encoding Event-Based Data With a Hybrid SNN Guided Variational Auto-encoder in Neuromorphic Hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3517343.3517372","authors":["Kenneth Stewart","Andreea Danielescu","Timothy Shea","Emre Neftci"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-05-04T07:28:08Z","doi":"10.1145/3517343.3517372","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-3-319-59156-8_2","name":"Formal Models of Foraging","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-59156-8_2","authors":["Anthony Brabazon","Seán McGarraghy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-09-26T18:09:36Z","doi":"10.1007/978-3-319-59156-8_2","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.4018/978-1-5225-0788-8.ch018","name":"Hookes-Jeeves-Based Variant of Memetic Algorithm","source":"crossref","abstract":"Due to their wide applicability and easy implementation, Genetic algorithms (GAs) are preferred to solve many optimization problems over other techniques. When a local search (LS) has been included in Genetic algorithms, it is known as Memetic algorithms. In this chapter, a new variant of single-meme Memetic Algorithm is proposed to improve the efficiency of GA. Though GAs are efficient at finding the global optimum solution of nonlinear optimization problems but usually converge slow and sometimes arrive at premature convergence. On the other hand, LS algorithms are fast but are poor global searchers. To exploit the good qualities of both techniques, they are combined in a way that maximum benefits of both the approaches are reaped. It lets the population of individuals evolve using GA and then applies LS to get the optimal solution. To validate our claims, it is tested on five benchmark problems of dimension 10, 30 and 50 and a comparison between GA and MA has been made.","url":"https://doi.org/10.4018/978-1-5225-0788-8.ch018","authors":["Dipti Singh","Kusum Deep"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-07-26T12:16:44Z","doi":"10.4018/978-1-5225-0788-8.ch018","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.4018/979-8-3693-6303-4.ch012","name":"Neuromorphic Advancements","source":"crossref","abstract":"The healthcare industry has recently experienced an increasing need for miniaturization, low power consumption, rapid treatments, and non-invasive clinical approaches. To fulfil these requirements, healthcare professionals actively search for innovative technological frameworks to enhance diagnostic precision while guaranteeing patient adherence. Neuromorphic computing, which employs hardware and software neural models to imitate brain-like behaviors, can facilitate a new era in medicine by providing energy-efficient solutions, having minimal delay, occupying less space, and offering high data transfer rates. Neuromorphic plays a vital role in healthcare, i.e., image processing, drug discovery, and disease prediction. This chapter provides a comprehensive overview of Neuromorphic advancements and their application in healthcare using intelligent computing.","url":"https://doi.org/10.4018/979-8-3693-6303-4.ch012","authors":["Krishan Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-29T15:16:27Z","doi":"10.4018/979-8-3693-6303-4.ch012","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.2139/ssrn.5136545","name":"Optimizing Load Balancing and Task Scheduling in Cloud Computing Based on Nature-Inspired Optimization Algorithms","source":"crossref","abstract":"A paradigm for high-performance computing services, cloud computing integrates the latest developments in distributed computing, virtualization, load balancing, parallel processing, network storage, and hot backup redundancy. In light of the fact that there is currently no reliable method for DAG task scheduling that guarantees a balanced distribution of resources across nodes, this study suggests an approach for LB algorithms in cloud computing. This research presents a new paradigm for resource selection and job scheduling, which is abstracted from swarm intelligence such as PSO, SA, Cuckoo search, etc. The LBA tackles critical issues with the system under investigation, such as system overhead or resource limits, with the goal of achieving lowest makespan and execution time while concurrently improving resource usage. This component is incorporated in the CloudSim simulation environment where the framework measures performance under different cloud models, task intensity and resource provisioning. Experimental outcomes prove that an LBA is better than an existing algorithm, where it gives an average makespan of 894.85ms, execution time of 614.88ms, and resource utilization was 69%. Comparative analysis with PSO and CSSA confirms the superior efficiency of LBA in maximizing resource allocation. These results highlight the possibility of optimization methods derived from nature to improve cloud performance by means of efficient scheduling and load balancing.","url":"https://doi.org/10.2139/ssrn.5136545","authors":["Srinivas Chippagiri","Preethi Ravula","Divya Gangwani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-13T11:12:11Z","doi":"10.2139/ssrn.5136545","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1007/978-3-319-73347-0_5","name":"Learning Spatio-Temporal Behavioural Sequences","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-73347-0_5","authors":["Luca Patanè","Roland Strauss","Paolo Arena"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-20T08:24:29Z","doi":"10.1007/978-3-319-73347-0_5","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1177/15330338251391080/v2/response1","name":"Author response for \"NeuroMorphFusion: A Neuro-Inspired Hybrid Learning Framework for Interpretable Deep Lesion Detection in IoT-Enabled Healthcare Systems\"","source":"crossref","abstract":"","url":"https://doi.org/10.1177/15330338251391080/v2/response1","authors":["Roseline Oluwaseun Ogundokun","Rotimi-Williams Bello","Pius Adewale Owolawi","Etienne A. van Wyk","Chunling Tu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-12T21:04:38Z","doi":"10.1177/15330338251391080/v2/response1","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.29363/nanoge.matsus.2024.434","name":"Synaptic Plasticity on Demand for Neuromorphic Computing and Bio-Inspired Artificial Nerve","source":"crossref","abstract":"","url":"https://doi.org/10.29363/nanoge.matsus.2024.434","authors":["Tae-Woo Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-12T12:24:58Z","doi":"10.29363/nanoge.matsus.2024.434","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-3-030-98108-2","name":"Nature Inspired Optimisation for Delivery Problems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-98108-2","authors":["Neil Urquhart"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-05-14T12:10:26Z","doi":"10.1007/978-3-030-98108-2","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch022","name":"Competitive Advantage of Geographical Clusters","source":"crossref","abstract":"This chapter deals with complexity science issues from two sides: from one side, it uses complexity science concepts to give new contributions to the theoretical understanding of geographical clusters (GCs); from the other side, it presents an application of complexity science tools such as emergent (bottom-up) simulation, using agent-based modeling to study the sources of GC competitive advantage. Referring to the first direction, complexity science is used as a conceptual framework to identify the key structural conditions of GCs that give them the adaptive capacity, so assuring their competitive advantage. Regarding the methodological approach, the agent-based simulation is used to analyze the dynamics of GCs. To this aim, we model the main characteristics of GCs and carry out a simulation analysis to observe that the behaviors of GCs are coherent with the propositions built up on the basis of complexity science literature.","url":"https://doi.org/10.4018/978-1-59140-984-7.ch022","authors":["V. Albino"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch022","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.4018/978-1-59140-312-8.ch014","name":"Once More Unto the Breach","source":"crossref","abstract":"The field of biologically inspired computing has generated many novel, interesting and useful computational systems. None of these systems alone is capable of approaching the level of behaviour for which the artificial intelligence and robotics communities strive. We suggest that it is now time to move on to integrating a number of these approaches in a biologically justifiable way. To this end we present a conceptual framework that integrates artificial neural networks, artificial immune systems and a novel artificial endocrine system. The natural counterparts of these three components are usually assumed to be the principal actors in maintaining homeostasis within biological systems. This chapter proposes a system that promises to capitalise on the self-organising properties of these artificial systems to yield artificially homeostatic systems. The components develop in a common environment and interact in ways that draw heavily on their biological counterparts for inspiration. A case study is presented, in which aspects of the nervous and endocrine systems are exploited to create a simple robot controller. Mechanisms for the moderation of system growth using an artificial immune system are also presented.","url":"https://doi.org/10.4018/978-1-59140-312-8.ch014","authors":["Mark Neal","Jon Timmis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T12:54:50Z","doi":"10.4018/978-1-59140-312-8.ch014","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/s11761-025-00469-4","name":"IoT-inspired scalability assessment for interoperable applications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11761-025-00469-4","authors":["Renu Sharma","Anil Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-04T17:49:04Z","doi":"10.1007/s11761-025-00469-4","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch018","name":"Heterogeneous Learning Using Genetic Algorithms","source":"crossref","abstract":"The goal of this chapter is twofold. First, assuming that all agents belong to a genetic population, the evolution of inflation learning will be studied using a heterogeneous genetic learning process. Second, by using real-floating-point coding and different genetic operators, the quality of the learning tools and their possible impact on the learning process will be examined.","url":"https://doi.org/10.4018/978-1-59140-984-7.ch018","authors":["T. Vallee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch018","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1016/j.asoc.2023.110152","name":"An online learning algorithm for a neuro-fuzzy classifier with mixed-attribute data","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2023.110152","authors":["Thanh Tung Khuat","Bogdan Gabrys"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-01T17:53:47Z","doi":"10.1016/j.asoc.2023.110152","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-3-662-72069-1_1","name":"Pocket Guide Neuro-/Psychopharmaka im Kindes- und Jugendalter","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-662-72069-1_1","authors":["Manfred Gerlach","Andreas Warnke"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-31T09:12:58Z","doi":"10.1007/978-3-662-72069-1_1","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1007/978-3-032-04558-4_52","name":"Complexity and Criticality in Neuro-Inspired Reservoirs","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-04558-4_52","authors":["Michiel van der Vlag","Alper Yegenoglu","Cristian Jimenez-Romero","Abigail Morrison","Sandra Diaz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-11T11:16:45Z","doi":"10.1007/978-3-032-04558-4_52","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.22489/cinc.2022.065","name":"Classification of Murmurs in PCG Using Combined Frequency Domain and Physician Inspired Features","source":"crossref","abstract":"","url":"https://doi.org/10.22489/cinc.2022.065","authors":["\"Julia Ding","Jing-Jing Li","Max Xu\""],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-02T16:34:11Z","doi":"10.22489/cinc.2022.065","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1515/9783110676112-004","name":"4 Role of intelligent IoT applications in fog computing","source":"crossref","abstract":"","url":"https://doi.org/10.1515/9783110676112-004","authors":["Gunturu Harika","Arun Malik","Isha Batra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-02-10T12:03:55Z","doi":"10.1515/9783110676112-004","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1016/j.asoc.2011.10.006","name":"Hybrid bio-inspired techniques for land cover feature extraction: A remote sensing perspective","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2011.10.006","authors":["Lavika Goel","Daya Gupta","V.K. Panchal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-11-02T00:38:44Z","doi":"10.1016/j.asoc.2011.10.006","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1016/j.asoc.2019.106030","name":"A nonlinear method of learning neuro-fuzzy models for dynamic control systems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2019.106030","authors":["Maxim V. Bobyr","Sergey G. Emelyanov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-12-18T22:39:09Z","doi":"10.1016/j.asoc.2019.106030","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1201/9781003648123-6","name":"Nanotechnology in Bio-Inspired Materials","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003648123-6","authors":["Waseem Ahmed Khattak","Afshan Farid","Muhammad Anas","Adnan Khattak","Aina Nawaz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-23T10:35:25Z","doi":"10.1201/9781003648123-6","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1007/978-0-387-34733-2_13","name":"Learning Useful Communication Structures for Groups of Agents","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-0-387-34733-2_13","authors":["Andreas Goebels"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-11-27T07:41:06Z","doi":"10.1007/978-0-387-34733-2_13","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch032","name":"Evolutionary Optimization in Production Research","source":"crossref","abstract":"This chapter provides a short guide on the use of evolutionary computation methods in the field of production research. The application of evolutionary computation methods is explained using a number of typical examples taken from the areas of production scheduling, assembly lines, and cellular manufacturing. A detailed case study on the solution of the cell-formation problem illustrates the benefits of the proposed approach. The chapter also provides a critical review on the up-to-date use of evolutionary computation methods in the field of production research and indicates potential enhancements as well as promising application areas. The aim of the chapter is to present researchers, practitioners, and managers with a basic understanding of the current use of evolutionary computation techniques and allow them to either initiate further research or employ the existing algorithms in order to optimize their production lines.","url":"https://doi.org/10.4018/978-1-59140-984-7.ch032","authors":["C. Dimopoulos"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch032","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.2174/9789815136357123010011","name":"Subject Index","source":"crossref","abstract":"","url":"https://doi.org/10.2174/9789815136357123010011","authors":["Balwinder S. Dhaliwal","Suman Pattnaik","Shyam Sundar Pattnaik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-26T11:51:56Z","doi":"10.2174/9789815136357123010011","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch049","name":"Agents for Multi-Issue Negotiation","source":"crossref","abstract":"This chapter describes a generic multi-issue negotiating agent that is designed for a dynamic information-rich environment. The agent strives to make informed decisions by observing signals in the marketplace and by observing general information sources including news feeds. The agent assumes that the integrity of some of its information decays with time, and that a negotiation may break down under certain conditions. The agent makes no assumptions about the internals of its opponent—it focuses only on the signals that it receives. Two agents are described. The first agent conducts multi-issue bilateral bargaining. It constructs two probability distributions over the set of all deals: the probability that its opponent will accept a deal, and the probability that a deal should be accepted by the agent. The second agent bids in multi-issue auctions—as for the bargaining agent, this agent constructs probability distributions using entropy-based inference.","url":"https://doi.org/10.4018/978-1-59140-984-7.ch049","authors":["J. Debenham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch049","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/nabic.2009.5393628","name":"Query translation from SQL to XPath","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393628","authors":["P.M Vidhya","Philip Samuel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393628","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1201/9781003143499-11","name":"Neuromorphic hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003143499-11","authors":["Elishai Ezra Tsur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-07-19T12:30:34Z","doi":"10.1201/9781003143499-11","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.20944/preprints202605.1577.v1","name":"Holographic-Inspired Dynamical Dark Energy with Running Dimension","source":"crossref","abstract":"Based on what we have achieved previously in [1] we present a dynamical dark energy model motivated by holographic principles and an anomalous running of the effective spacetime dimension. The model features a redshift-dependent infrared cutoff parameter α(z) derived from a scalar-tensor action with a conformal anomaly term originating from a TeV-scale sector. After fixing the ultraviolet scale to LHC energies and the anomaly coefficient to unity, the model contains only two free parameters: a transition redshift zc and a sharpness parameter β. The effective dark energy equation of state weff(z) is derived from first principles, yielding a closed-form expression that generalizes standard holographic dark energy. The model naturally suppresses matter growth at low redshifts, reducing σ8 from 0.811 to 0.769 when the late-time Hubble constant H0 = 73 km/s/Mpc is used, thereby resolving the S8 tension while simultaneously easing the H0 tension. We present numerical solutions, convergence checks, and a comparison with ΛCDM and constant-α models. Therefore, we will explain how the model is theoretically consistent, phenomenologically viable, and falsifiable with upcoming Stage-IV dark energy surveys.","url":"https://doi.org/10.20944/preprints202605.1577.v1","authors":["Ahmed Ali"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-27T02:26:36Z","doi":"10.20944/preprints202605.1577.v1","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1007/s00607-011-0156-x","name":"Survival of the flexible: explaining the recent popularity of nature-inspired optimization within a rapidly evolving world","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00607-011-0156-x","authors":["James M. Whitacre"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-10-11T05:27:24Z","doi":"10.1007/s00607-011-0156-x","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.31224/6232","name":"Drone-Based Search Algorithms Inspired by Ant Colonies","source":"crossref","abstract":"Efficient search, mapping, and coverage of large or uncertain environments remain fundamental challenges in unmanned aerial vehicle (UAV) operations, particularly in disaster response, surveillance, and environmental monitoring. Centralized planning and single-drone strategies suffer from scalability limits, communication bottlenecks, and vulnerability to individual agent failure. This paper presents a drone-based search and mapping framework inspired by ant colony intelligence, translating biological principles such as pheromone-based exploration, stigmergy, decentralized decision-making, and adaptive path reinforcement into deployable UAV swarm algorithms. Without relying on heavy mathematical formulations, the study develops a practical, engineering-oriented algorithmic architecture in which UAVs coordinate indirectly through virtual pheromones embedded in shared or local maps. The proposed approach demonstrates inherent robustness, scalability, and adaptability to dynamic environments, obstacles, and drone failures. The paper’s primary contribution lies in presenting a realistic, implementable ant-inspired swarm search system suitable for real-world UAV missions, bridging the gap between bio-inspired theory and operational aerospace robotics.","url":"https://doi.org/10.31224/6232","authors":["Mokshith Sharma T. P."],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-09T20:46:29Z","doi":"10.31224/6232","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1088/1402-4896/ae7ac7/v2/review1","name":"Review for \"Novel circular fractal-inspired compact EBG for wireless capsule endoscopy\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1402-4896/ae7ac7/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-10T21:06:51Z","doi":"10.1088/1402-4896/ae7ac7/v2/review1","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.2139/ssrn.4415871","name":"Novel Harmony-Based Bio-Inspired Resource Allocation Algorithm Hcat for Qos Improvement in the Fog Computing Environment","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4415871","authors":["Gaurav Goel","Rajeev Tiwari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-11T12:09:57Z","doi":"10.2139/ssrn.4415871","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.21203/rs.3.rs-1521871/v1","name":"Research on the Cross-modal Cognitive Neural Computing Framework of the Brain and Mind Inspired Intelligence","source":"crossref","abstract":"Abstract To address the problems of scientific theory of brain and mind, common technology and engineering application of nature-inspired intelligence, this paper is focused on research in the semantic-oriented computing framework design for multimedia and multimodal information. The multimedia neural cognitive computing model of brain-inspired computing was designed based on the brain mechanism of nervous system and mind architecture of cognitive system. Furthermore, the semantic-oriented hierarchical cross-modal cognitive neural computing framework of brain-like computing was proposed based on multimedia neural cognitive computing model. Furthermore, the formal description and analysis of cross-modal cognitive neural computing framework was given. It would effectively improve the performance of semantic processing of multimedia and cross-modal information such as target detection, classification and recognition in high-resolution remote sensing image, and has far-reaching significance for exploration and realization brain and mind inspired computing.","url":"https://doi.org/10.21203/rs.3.rs-1521871/v1","authors":["Yang Liu","Jianshe Wei"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-10T21:04:20Z","doi":"10.21203/rs.3.rs-1521871/v1","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-3-319-50862-7_7","name":"Visual Processing in Cortical Architecture from Neuroscience to Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-50862-7_7","authors":["Tobias Brosch","Stephan Tschechne","Heiko Neumann"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-12-10T09:24:23Z","doi":"10.1007/978-3-319-50862-7_7","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.19139/soic-2310-5070-2305","name":"Enhancing IoT Systems with Bio-Inspired Intelligence in fog computing environments","source":"crossref","abstract":"In the context of deploying delay-sensitive Internet of Things (IoT) applications, the fog computing paradigm faces critical challenges in optimal node placement to ensure both connectivity and coverage. Traditional optimization approaches often fail to effectively balance these competing objectives in dynamic IoT environments. This paper presents a novel bio-inspired approach using the Pufferfish Optimization Algorithm (POA) to solve this multi-objective optimization problem. Our solution uniquely leverages a two-stage optimization process, inspired by pufferfish predator response mechanisms, to dynamically balance global exploration and local exploitation. Experimental evaluation across varied network configurations demonstrates that POA significantly outperforms existing state-of-the-art algorithms in both network connectivity and coverage metrics (p &lt; 0.001). The proposed algorithm exhibited robust performance across different communication ranges, while maintaining optimal network connectivity and comprehensive coverage of edge devices. These results demonstrate POA's effectiveness of the POA in optimizing fog node placement for real-world IoT applications.","url":"https://doi.org/10.19139/soic-2310-5070-2305","authors":["Islam S. Fathi","Mohammed Tawfik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-03T14:54:38Z","doi":"10.19139/soic-2310-5070-2305","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.5737/23688076263221227","name":"Délais dans l’octroi des congés en neuro-oncologie : utilisation d’une approche inspirée des méthodes Lean Six Sigma pour en déterminer les causes internes","source":"crossref","abstract":"","url":"https://doi.org/10.5737/23688076263221227","authors":["Karen Rezk","Catherine-Anne Miller"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-07-20T15:55:46Z","doi":"10.5737/23688076263221227","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/s10791-025-09634-x","name":"Design and implementation of quantum hippo inspired convolutional neural networks using parametric quantum circuits for an efficient lung cancer classification","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s10791-025-09634-x","authors":["S. Radhika","G. Sharada"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-16T09:10:43Z","doi":"10.1007/s10791-025-09634-x","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.4018/978-1-5225-0788-8.ch006","name":"Evolutionary Algorithms","source":"crossref","abstract":"Inspired from nature, evolutionary algorithms have been proven effective and unique in different real world applications. Comparing to traditional algorithms, its parallel search capability and stochastic nature enable it to excel in search performance in a unique way. In this chapter, evolutionary algorithms are reviewed and discussed from concepts and designs to applications in bioinformatics. The history of evolutionary algorithms is first discussed at the beginning. An overview on the state-of-the-art evolutionary algorithm concepts is then provided. Following that, the related design and implementation details are discussed on different aspects: representation, parent selection, reproductive operators, survival selection, and fitness function. At the end of this chapter, real world evolutionary algorithm applications in bioinformatics are reviewed and discussed.","url":"https://doi.org/10.4018/978-1-5225-0788-8.ch006","authors":["Ka-Chun Wong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-07-26T12:16:44Z","doi":"10.4018/978-1-5225-0788-8.ch006","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.2174/9789815136357123010006","name":"Fractal Antennas","source":"crossref","abstract":"This chapter discusses fractal geometry concepts and fractal antennas. Selected fractal antennas and their features are described, and all the designed fractal antennas are introduced in this chapter. The important features like miniaturization &amp;amp; multiband operation of the designed fractal antennas are highlighted, and their applications are also discussed.&amp;nbsp;","url":"https://doi.org/10.2174/9789815136357123010006","authors":["Balwinder S. Dhaliwal","Suman Pattnaik","Shyam Sundar Pattnaik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-26T11:51:56Z","doi":"10.2174/9789815136357123010006","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/bimnics.2007.4610120","name":"Self-organizing service supervision","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bimnics.2007.4610120","authors":["Peter H. Deussen","Edzard Hofig"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-09-08T20:06:46Z","doi":"10.1109/bimnics.2007.4610120","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1142/9789812790262_0001","name":"THE BRAIN: THE CENTER OF ATTRACTION","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789812790262_0001","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-04-12T00:09:25Z","doi":"10.1142/9789812790262_0001","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1142/9789812810250","name":"Brainware: Bio-Inspired Architecture And Its Hardware Implementation","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789812810250","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-11-12T07:21:45Z","doi":"10.1142/9789812810250","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.66588/ncmr.v3i1.4","name":"The Pathway from Skin to Liver: Psoriasis","source":"crossref","abstract":"Psoriasis is a chronic, recurrent, autoimmune, inflammatory skin disease. While psoriasis was considered limited to the skin in the past, it is now recognized as a chronic systemic inflammatory disease accompanied by many comorbidities. The main comorbidities of the disease are non-alcoholic fatty liver disease (NAFLD), mood disorders including depression, cardiometabolic diseases including myocardial infarction, hypertension, type 2 diabetes mellitus, hyperuricemia, dyslipidemia, obesity, metabolic syndrome, and psoriatic arthritis. NAFLD is estimated to have a prevalence of 25% in the general population and is a leading cause of cirrhosis and liver transplantation. Currently, NAFLD has become an escalating epidemic, driven by the rising incidence of obesity, metabolic syndrome, and insulin resistance, as well as the systemic effects of psoriasis itself. This review aims to highlight the adverse effects of psoriasis, a skin disease requiring long-term medication, on the liver, and to emphasize these effects when planning treatment regimens.","url":"https://doi.org/10.66588/ncmr.v3i1.4","authors":["Neşe Çölçimen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-29T17:30:30Z","doi":"10.66588/ncmr.v3i1.4","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1007/978-3-030-37218-7_14","name":"Personality Trait with E-Graphologist","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-37218-7_14","authors":["Pranoti S. Shete","Anita Thengade"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-06T15:02:40Z","doi":"10.1007/978-3-030-37218-7_14","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-981-10-6747-1_6","name":"Alternate Procedure for the Diagnosis of Malaria via Intuitionistic Fuzzy Sets","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-10-6747-1_6","authors":["Vijay Kumar","Sarika Jain"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-10-04T08:25:22Z","doi":"10.1007/978-981-10-6747-1_6","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-3-642-58930-0_16","name":"Boolean Soft Computing by Non-linear Neural Networks With Hyperincursive Stack Memory","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-58930-0_16","authors":["Daniel M. Dubois"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-06-15T19:06:59Z","doi":"10.1007/978-3-642-58930-0_16","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/s11047-010-9245-6","name":"Graph multiset transformation: a new framework for massively parallel computation inspired by DNA computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11047-010-9245-6","authors":["Hans-Jörg Kreowski","Sabine Kuske"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-01-10T06:06:26Z","doi":"10.1007/s11047-010-9245-6","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-981-16-9573-5","name":"Computational Vision and Bio-Inspired Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-16-9573-5","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-30T06:02:42Z","doi":"10.1007/978-981-16-9573-5","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1016/j.asoc.2020.106876","name":"Resource provisioning in scalable cloud using bio-inspired artificial neural network model","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2020.106876","authors":["Pradeep Singh Rawat","Priti Dimri","Punit Gupta","G.P. Saroha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-11-05T12:31:59Z","doi":"10.1016/j.asoc.2020.106876","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/bicta.2008.4656694","name":"On the power of endocytosis and exocytosis","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2008.4656694","authors":["Gabriel Ciobanu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-10-28T11:22:35Z","doi":"10.1109/bicta.2008.4656694","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1039/d5nh00562k/v2/response1","name":"Author response for \"Interface Engineered V2O5-based Flexible Memristors towards High-Performance Brain-Inspired Neuromorphic Computing\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5nh00562k/v2/response1","authors":["Kumar Kaushlendra","Bhanu Ranjan","Davinder Kaur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-12T21:07:03Z","doi":"10.1039/d5nh00562k/v2/response1","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1109/nabic.2009.5393682","name":"What is there in a training sample?","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393682","authors":["Ninan Sajeeth Philip"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393682","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1039/d5tc01712b/v1/decision1","name":"Decision letter for \"Reconfigurable Artificial Synapses with an Organic Antiambipolar Transistor for Brain-inspired Computing\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5tc01712b/v1/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-12T17:13:05Z","doi":"10.1039/d5tc01712b/v1/decision1","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1080/01658107.2026.2660194","name":"<i>DNAJC19</i>\n                    Associated Optic Neuropathy","source":"crossref","abstract":"","url":"https://doi.org/10.1080/01658107.2026.2660194","authors":["Raed S. Behbehani","Hamad Ali"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-23T14:36:21Z","doi":"10.1080/01658107.2026.2660194","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.23919/snw57900.2023.10183958","name":"Single-Electron Information-Processing Circuit Inspired by Principles of Molecular Computing","source":"crossref","abstract":"","url":"https://doi.org/10.23919/snw57900.2023.10183958","authors":["Kairi Yokoyama","Takahide Oya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-21T13:21:52Z","doi":"10.23919/snw57900.2023.10183958","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1016/b978-0-12-821343-8.00019-8","name":"Human-inspired models for tactile computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-12-821343-8.00019-8","authors":["Christel Baier","Darío Cuevas Rivera","Clemens Dubslaff","Stefan J. Kiebel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-20T10:31:55Z","doi":"10.1016/b978-0-12-821343-8.00019-8","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/nabic.2009.5393651","name":"Modeling amino acid strings using electrical ladder circuits","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393651","authors":["R. Marshall"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T17:36:43Z","doi":"10.1109/nabic.2009.5393651","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1039/d5tc01712b/v2/decision1","name":"Decision letter for \"Reconfigurable Artificial Synapses with an Organic Antiambipolar Transistor for Brain-inspired Computing\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5tc01712b/v2/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-12T17:13:05Z","doi":"10.1039/d5tc01712b/v2/decision1","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1007/978-981-10-6747-1_5","name":"Analysing the Genetic Diversity of Commonly Occurring Diseases","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-10-6747-1_5","authors":["Shamita Malik","Sunil Kumar Khatri","Dolly Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-10-04T08:25:22Z","doi":"10.1007/978-981-10-6747-1_5","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1145/1993069.1993071","name":"INSPIRED High School Computing Academies","source":"crossref","abstract":"If we are to attract more women and minorities to computing we must engage students at an early age. As part of its mission to increase participation of women and underrepresented minorities in computing, the Increasing Student Participation in Research Development Program (INSPIRED) conducts computing academies for high school students. The academies are designed to increase students’ knowledge of and interest in computing and to encourage females and minorities to participate in computing. INSPIRED academies differ from others in several ways. They are relatively easy to organize and require relatively few resources; they focus on computing concepts and object-oriented programming; they expose students to successful female and minority computer scientists; and they actively engage university students from underrepresented groups to organize, coordinate, teach, and help assess the academies. This not only provides role models for the high school students but also helps engage the university students and promote their professional development. Our assessment results show that high school student participants have gained significant knowledge and interest in computing through participation in the academies. This article describes the organization, coordination, content, and assessment of the academies, along with suggestions for those who would like to design academies like these. It also discusses how to prepare university students for their roles in the academies and how their participation has helped in their professional development. It includes pointers to sites from which the instructional and assessment materials can be downloaded for those who wish to replicate or adapt these materials.","url":"https://doi.org/10.1145/1993069.1993071","authors":["Peggy Doerschuk","Jiangjiang Liu","Judith Mann"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-08-10T16:16:22Z","doi":"10.1145/1993069.1993071","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-981-10-6747-1_15","name":"Sybil Attack Prevention Algorithm for Body Area Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-10-6747-1_15","authors":["Rohit Kumar Ahlawat","Amita Malik","Archana Sadhu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-10-04T08:25:22Z","doi":"10.1007/978-981-10-6747-1_15","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1016/j.imavis.2024.105308","name":"Attention enhanced machine instinctive vision with human-inspired saliency detection","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.imavis.2024.105308","authors":["Habib Khan","Muhammad Talha Usman","Imad Rida","JaKeoung Koo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-04T22:07:27Z","doi":"10.1016/j.imavis.2024.105308","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-3-642-28765-7_26","name":"Bio-inspired Self-adaptive Agents in Distributed Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-28765-7_26","authors":["Ichiro Satoh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-03-23T09:50:43Z","doi":"10.1007/978-3-642-28765-7_26","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/nabic.2010.5716321","name":"Embryonic stream processing using morphogens","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2010.5716321","authors":["K Sabir","D Lowe"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-02-18T14:03:54Z","doi":"10.1109/nabic.2010.5716321","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1201/9781003598404-4","name":"Work Done Using Conventional and Bio-Inspired Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003598404-4","authors":["Ankita","Sudip Kumar Sahana"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-18T11:07:19Z","doi":"10.1201/9781003598404-4","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1109/icoct64433.2025.11118699","name":"Quantum Inspired Search Algorithm for Bias Mitigation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icoct64433.2025.11118699","authors":["Harsha Bhute","Ashish Bhosale","Abhinandan Ashtekar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-15T18:12:04Z","doi":"10.1109/icoct64433.2025.11118699","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1016/j.asoc.2026.114575","name":"Bio-YOLO: A bio-inspired lightweight small object detection network for aerial images","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2026.114575","authors":["Jiansheng Peng","Sihan Huang","Chuan Lin","Xintao Pang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-06T07:55:05Z","doi":"10.1016/j.asoc.2026.114575","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1109/smartworld.2018.00329","name":"Socially-Inspired Peer Discovery for D2D Communications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/smartworld.2018.00329","authors":["Hui Wu","Yufeng Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-12-07T00:38:21Z","doi":"10.1109/smartworld.2018.00329","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-981-99-3428-7_8","name":"Comparison of Biologically Inspired Algorithm with Socio-inspired Technique on Load Frequency Control of Multi-source Single-Area Power System","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-99-3428-7_8","authors":["D. Murugesan","K. Jagatheesan","Anand J. Kulkarni","Pritesh Shah","Ravi Sekhar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-01T05:02:42Z","doi":"10.1007/978-981-99-3428-7_8","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/bicta.2010.5645071","name":"Enzymatic numerical P systems - a new class of membrane computing systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bicta.2010.5645071","authors":["Ana Pavel","Octavian Arsene","Catalin Buiu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-12-09T15:33:18Z","doi":"10.1109/bicta.2010.5645071","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1088/1402-4896/ae7ac7/v2/review2","name":"Review for \"Novel circular fractal-inspired compact EBG for wireless capsule endoscopy\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1402-4896/ae7ac7/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-10T21:06:51Z","doi":"10.1088/1402-4896/ae7ac7/v2/review2","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1039/d6mh00718j/v1/review2","name":"Review for \"Neutron-Star-Inspired Metamaterials: Mitigating Friction–Strength–Conductivity Trade-offs\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d6mh00718j/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-13T21:08:35Z","doi":"10.1039/d6mh00718j/v1/review2","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.2139/ssrn.4917843","name":"Intrusion detection in In-vehicle Networks using neuro computing","source":"crossref","abstract":"A good way to detect illegitimate use is through motoring unusual activity in the In-vehicle Network (IVN). This paper proposes a detailed review&lt;br&gt;of the approaches used to detect intrusions in IVNs by applying methods inclusive of neuromorphic computing (NC). It explores Security threats to IVNs&lt;br&gt;and briefs security solutions using machine learning algorithms. NC offers effective intrusion detection systems to interpret intrusion attempts in the&lt;br&gt;incoming network traffic efficiently with minimal energy consumption. The review elaborates on IVN security solutions using NC. A multiscale histogram&lt;br&gt;method using a dataset based on a dictionary of Controller Area Network Identification (CANID) sequences subsequently applied with Deep Learning for&lt;br&gt;feature generation is explored. The results using Deep Convolutional Neural Network (DCNN) are proven to report very low error rates and false negatives.&lt;br&gt;The spiking neural network (SNN) based method incorporates presynaptic neuron modulation, which generates a spike in postsynaptic neurons when&lt;br&gt;membrane potential crosses the threshold. Another SNN-based method uses AWID and NSL-KDD intrusion detection datasets to demonstrate that nonleaky&lt;br&gt;neurons can be easily trained and show better performance. Supervised learning with indirect training is used to convert Deep Neural Networks (DNNs) to&lt;br&gt;SNNs with single-spike temporal coding, providing high-performance accuracy. A DNN is used to fetch statistical data from high-dimensional CAN packets&lt;br&gt;to extract corresponding features and provide an instant response to the intrusion. The Electronic Control Unit (ECU) embedded monitoring module identifies&lt;br&gt;the known attacks based on trained features. It uses a profiling module that records the attack and updates the system for upcoming data packets. Another&lt;br&gt;method uses KDD cup 99, which incorporates a mixture of symbolic and numeric values to detect intrusion. Intrusion Detection System (IDS) using the&lt;br&gt;Deep Learning (DL) method incorporates the Discrete vector factorization (DVF) method to generate synaptic weights, crossbar weight, and thresholds for&lt;br&gt;neurons and shows 90.12 % accuracy in network intrusion detection and shows 81.13 % recognition accuracy in detection of malicious and correct packets&lt;br&gt;with minimal power. From the various summarised experimental outcomes, it has been justified that NC delivers excellent classification and accuracy in&lt;br&gt;detection for IDS, and also consumes minimal power.","url":"https://doi.org/10.2139/ssrn.4917843","authors":["Parag Parandkar","Suresh D","Prashant V. Joshi","Sudharshan K. M."],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-06T15:34:08Z","doi":"10.2139/ssrn.4917843","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-981-33-6862-0_17","name":"Fuzzy C-means for Diabetic Retinopathy Lesion Segmentation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-33-6862-0_17","authors":["Shalini","Sasikala"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-06-14T05:02:45Z","doi":"10.1007/978-981-33-6862-0_17","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1201/9781003430421-35","name":"Computer vision-inspired smart attendance system (SAS)","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003430421-35","authors":["Ajay Kumar Bansal","Georgina Asuah"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-23T10:48:38Z","doi":"10.1201/9781003430421-35","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1201/9781003648123-18","name":"Bio-Inspired Water Purification","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003648123-18","authors":["Aashna Sinha","Aman Kumar","Rajesh Singh","Vineet Singh Sikarwar","Amit Kumar Thakur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-23T10:35:25Z","doi":"10.1201/9781003648123-18","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1109/iwcmc69287.2026.11580073","name":"Optimizing Wireless Multimedia Task Offloading in UAV-LEO Networks: A Bio-inspired Hybrid Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iwcmc69287.2026.11580073","authors":["Die Yang","Cheng Zhan","Tingting Li","Jiayi Chen","Hu Lu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-03T19:49:45Z","doi":"10.1109/iwcmc69287.2026.11580073","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.20944/preprints202607.2211.v1","name":"An Erdős-Inspired Perspective on Abiogenesis","source":"crossref","abstract":"Whether life is an inevitable consequence of the laws of nature or an exceptional outcome of prebiotic evolution is unresolved. Origin-of-life hypotheses primarily seek to reconstruct molecular pathways linking prebiotic chemistry to the first evolving systems. Here, we introduce a theoretical framework inspired by the probabilistic reasoning of Paul Erdős, reformulating abiogenesis as a mathematical existence problem rather than a historical reconstruction problem. We define an abstract chemical configuration space comprising all chemically accessible prebiotic organizations and identify life as the subset of configurations simultaneously exhibiting compartmentalization, energy transduction, information persistence and heritable variation. Using probability theory and set theory, we aim to investigate whether this subset necessarily occupies a nonzero region of chemical configuration space. We establish the general conditions under which life-capable organizations have positive measure and derive an abiogenetic threshold beyond which the probability of life's emergence approaches unity. Our framework predicts threshold behavior, functional convergence and scaling relationships that are independent of any particular molecular substrate. In our setting, origin-of-life hypotheses like RNA-first, metabolism-first, compartment-based and autocatalytic models are interpreted as complementary mechanisms that either enlarge the life-capable subset or increase the exploration of chemical configuration space. Potential applications include quantitative analyses of prebiotic experimental systems, comparative assessment of planetary habitability and computational studies of chemical organization.","url":"https://doi.org/10.20944/preprints202607.2211.v1","authors":["Arturo Tozzi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-05T08:51:16Z","doi":"10.20944/preprints202607.2211.v1","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1109/synasc.2016.060","name":"Continuation Semantics of a Language Inspired by Membrane Computing with Symport/Antiport Interactions","source":"crossref","abstract":"","url":"https://doi.org/10.1109/synasc.2016.060","authors":["Gabriel Ciobanu","Eneia Nicolae Todoran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-01-26T18:07:19Z","doi":"10.1109/synasc.2016.060","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.55277/researchhub.aybs2u6r","name":"~NEuRO Energizer ReviEw (Honest Review 2026) We Tried It My Honest Customer Review","source":"crossref","abstract":"","url":"https://doi.org/10.55277/researchhub.aybs2u6r","authors":["Aksea Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-26T16:44:22Z","doi":"10.55277/researchhub.aybs2u6r","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1109/nabic.2009.5393875","name":"Analysis of mammograms using fractal features","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393875","authors":["Deepa Sankar","Tessammma Thomas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393875","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/itc50571.2021.00020","name":"Brain-Inspired Computing for Wafer Map Defect Pattern Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/itc50571.2021.00020","authors":["Paul R. Genssler","Hussam Amrouch"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-24T20:39:59Z","doi":"10.1109/itc50571.2021.00020","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-3-7908-1767-6_10","name":"A Bio-Inspired Robotic Mechanism for Autonomous Locomotion in Unconventional Environments","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-7908-1767-6_10","authors":["Darío Maravall","Javier de Lope"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-03-09T12:18:16Z","doi":"10.1007/978-3-7908-1767-6_10","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/otcon69332.2026.11629763","name":"Quantum-Inspired NLP Framework for Context-Aware Multilingual and Multimodal Emotion Understanding with Personalized Recommendations","source":"crossref","abstract":"","url":"https://doi.org/10.1109/otcon69332.2026.11629763","authors":["D. N. V. S. L. S. Indira","E. Vidya Rani","A.Hema Sri Chandu","D. Sravya","G. Ganapathi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-11T19:12:11Z","doi":"10.1109/otcon69332.2026.11629763","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch003","name":"Stochastic Optimization Algorithms","source":"crossref","abstract":"When looking for a solution, deterministic methods have the enormous advantage that they do find global optima. Unfortunately, they are very CPU intensive, and are useless on untractable NP-hard problems that would require thousands of years for cutting-edge computers to explore. In order to get a result, one needs to revert to stochastic algorithms that sample the search space without exploring it thoroughly. Such algorithms can find very good results, without any guarantee that the global optimum has been reached; but there is often no other choice than using them. This chapter is a short introduction to the main methods used in stochastic optimization.","url":"https://doi.org/10.4018/978-1-59140-984-7.ch003","authors":["P. Collet","J. Rennard"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch003","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1097/wno.0000000000002436","name":"Literature Commentary","source":"crossref","abstract":"In this issue, Drs. Mark L. Moster and Deborah I. Friedman review the following 5 articles, 3 of which were co-authored by our NANOS colleagues. Lee L, Vemuri JP, Belilos A, Sismanis A, Haines S, Felton W, Gharavi M, Tang Y, Coelho DH. Number of radiologic abnormalities associated with idiopathic intracranial hypertension as a predictor of the presence of pulsatile tinnitus. Otol Neurotol Open . 2025;5:e072. doi: 10.1097/ONO.0000000000000072. Snowden A, Van Stavern GP, Leanne Stunkel L Persistence of pulsatile tinnitus in patients with idiopathic intracranial hypertension following resolution of papilledema. J Neurol Sci . 2025:476:123608. doi: 10.1016/j.jns.2025.123608. Nachira D, Congedo MT, Kuzmych K, Evoli A, Iorio R, Vita ML, Petracca-Ciavarella L, Nocera A, Sassorossi C, Evangelista J, Lyberis P, Comacchio GM, Brandolini J, Aprile V, Zifara CC, Mastromarino MG, Patirelis A, Asteggiano E, Anile M, Venuta F, Imperatori A, Ambrogi V, Solli P, Dell'Amore A, Lucchi M, Melfi F, Ibrahim M, Ruffini E, Rea F, Margaritora S, Meacci E. Thymectomy in ocular myasthenia gravis: results before and after generalization and prognostic predictors of outcomes. J Clin Med . 2025;14:7840. doi: 10.3390/jcm14217840. Clément G, Puisieux S, Pellerin D, Brais B, Bonnet C, Renaud M. Spinocerebellar ataxia 27B (SCA27B), a frequent late-onset cerebellar ataxia. Rev Neurol (Paris) . 2024;80:410–416. doi: 10.1016/j.neurol.2024.03.007. Thakolwiboon S, Redenbaugh V, Chen B, Hewitt S, Shah S, Lotan I, Levy M, Forcadela M, Huda S, Pique J, Marignier R, Boutiere C, Audoin B, Poullin P, Champsas D, Choi D, Danesh-Meyer HV, Vasileiou E, Sotirchos ES, Davis JB, Henderson AD, Wilf-Yarkoni A, Stiebel-Kalish H, Maillart E, Bonelli L, Arnold AC, Boudot De La Motte M, Deschamps R, Jitprapaikulsan J, Moss HE, Villarreal Navarro SE, Mao-Draayer Y, Mishra M, Vorasoot N, Cacciaguerra L, Tisavipat N, Tajfirouz DA, Tillema JM, Lopez-Chiriboga SA, Palace J, Hacohen Y, Pittock SJ, Flanagan EP, Chen JJ. Outcomes after acute plasma exchange for myelin oligodendrocyte glycoprotein antibody-associated disease. Neurology . 2025;105:e213903. doi: 10.1212/WNL.0000000000213903.","url":"https://doi.org/10.1097/wno.0000000000002436","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-17T15:00:20Z","doi":"10.1097/wno.0000000000002436","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1016/b978-0-443-40441-2.00021-4","name":"Title page","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-40441-2.00021-4","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-27T14:16:56Z","doi":"10.1016/b978-0-443-40441-2.00021-4","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1007/978-3-319-12084-3_13","name":"Towards Brain-Inspired System Architectures","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-12084-3_13","authors":["Thomas Sterling","Maciej Brodowicz","Timur Gilmanov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-10-16T04:25:57Z","doi":"10.1007/978-3-319-12084-3_13","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/iscas.1990.112638","name":"Active analog memories for neuro-computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas.1990.112638","authors":["Y. Horio","M. Ymamamoto","S. Nakamura"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-12-04T14:27:50Z","doi":"10.1109/iscas.1990.112638","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-3-642-58930-0_15","name":"The Morphogenetic Neuron","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-58930-0_15","authors":["Germano Resconi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-06-15T23:06:59Z","doi":"10.1007/978-3-642-58930-0_15","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.2139/ssrn.6122000","name":"Survey on Bio-Inspired Optimization Algorithms: Applications and Uses","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.6122000","authors":["Ashwini C"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-23T15:43:43Z","doi":"10.2139/ssrn.6122000","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1002/9781394355600.ch4","name":"Neuro‐Symbolic AI with a CNN‐Based Framework for Detecting Tomato Leaf Diseases","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9781394355600.ch4","authors":["Khaleelullah Shaik","Mohammed Ali Shaik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-31T21:30:31Z","doi":"10.1002/9781394355600.ch4","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.55277/researchhub.kldh7kor","name":"Neuro Surge Reviews – Is It Legit, a Scam or Worth Buying? (2026 Update)","source":"crossref","abstract":"","url":"https://doi.org/10.55277/researchhub.kldh7kor","authors":["juleebina accote"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-09T09:30:22Z","doi":"10.55277/researchhub.kldh7kor","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1109/2575-8411.2026.00109","name":"Physics-Inspired Decomposition for Weak Low-Rank Spatiotemporal Completion in Sparse Crowdsensing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/2575-8411.2026.00109","authors":["Mijia Zhang","En Wang","Wenbin Liu","Junwei Zhao","Yang Xu","Bo Yang","Jie Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-04T19:12:45Z","doi":"10.1109/2575-8411.2026.00109","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1007/978-981-15-1842-3_9","name":"Natural Heuristic Methods for Underwater Vehicle Path Planning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-15-1842-3_9","authors":["Yu-Xin Zhao","De-Quan Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-02-19T05:02:35Z","doi":"10.1007/978-981-15-1842-3_9","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.2139/ssrn.6734481","name":"MIRF: Mahjong-inspired Reasoning Framework for Large Language Models","source":"crossref","abstract":"&lt;div&gt; &amp;nbsp; &amp;nbsp; &amp;nbsp; Large Language Models (LLMs) fundamentally operate in a binary manner, either generating an output or not. Due to this limitation, hallucinations often occur where the model outputs incorrect information with high confidence. In this paper, we discovered that the gameplay of Mahjong and the reasoning methods of LLM are very similar, and we propose MIRF (Mahjong-Inspired Reasoning Framework for Large Language Models), a reasoning framework for large language models inspired by the game of Mahjong.&amp;nbsp; &lt;/div&gt; &lt;div&gt; &amp;nbsp; &amp;nbsp; &amp;nbsp;MIRF consists of four core pipelines. First, we formally define Tenpai in LLM reasoning. Tenpai represents an intermediate state where a solution can be reached structurally, but one cannot be perfectly certain. Second, we introduce a new reasoning state called Yakunashi. Yakunashi represents a situation where the model is in a Tenpai state but cannot determine an output because certain preconditions are not met. This is similar to a situation where one possesses a structurally perfect Mahjong set but lacks valid tile combinations, making it impossible to declare victory. Third, we define Beta-Ori as the primary defensive output strategy and distinguish between a principle-based safety-first fold and a final state where all tiles are drawn. Fourth, we propose a MIRF-weighted RLHF reward function that imposes a multiplicatively higher penalty than the standard error on confident hallucinations (Noten's Riichi).&amp;nbsp; &lt;/div&gt; &lt;div&gt; &amp;nbsp; &amp;nbsp; &amp;nbsp; We empirically evaluate MIRF on local LLM (qwen3.5:0.6b and gemma4:e4b) for 21 pairs of QAs across 5 question categories. The experimental results show that the Deal-in rate was 0% in all experimental runs, and the Yakunashi state emerged naturally through the interaction of Tenpai and Noten. This is a state discovered through experimentation, not an intentionally designed state. In this study, we propose new evaluation indicators including the Deal-in ratio, Tenpai declaration rate, Betaori precision, and Yakunashi ratio, which better represent the reliability of LLM that cannot be captured by accuracy alone. &lt;/div&gt;","url":"https://doi.org/10.2139/ssrn.6734481","authors":["Jaehwan Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-21T15:06:10Z","doi":"10.2139/ssrn.6734481","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.2478/jaiscr-2026-0001","name":"A Hybridizing-Enhanced Quantum-Inspired Differential Evolution Algorithm with Multi-Strategy for Complicated Optimization","source":"crossref","abstract":"Abstract Differential Evolution (DE) has been found to be inefficient and inaccurate for high-dimensional complex problems. Quantum-inspired Differential Evolution (QDE) possesses quantum computational properties, enabling effective handling of high-dimensional problems. However, QDE is plagued by issues of excessive mutation and poor convergence. Therefore, a hybrid enhanced Quantum-inspired Differential Evolution algorithm, termed QAHQDE, is proposed. Within QAHQDE, an improved chaotic strategy is designed. Non-repeating distributed quantum positions are generated, enhancing the diversity of initialized individuals. A quantum-adaptive mutation strategy is adopted to address the over-mutation problem inherent in QDE. The mutation degree is adaptively reduced, and convergence performance is thereby improved. A novel hybrid mutation strategy is constructed. Weighted mutation operators are combined with standard differential evolution. Local and global search capabilities are balanced, and convergence accuracy is enhanced. The performance of QAHQDE was evaluated against 38 algorithms using 48 benchmark functions from CEC2005, CEC2010, and CEC2013, across dimensions D=100, 500, 1000, and 3000. Experimental results demonstrate that QAHQDE outperforms QDE by at least three orders of magnitude. Superior convergence performance, higher convergence accuracy, and excellent stability are exhibited by QAHQDE on most functions.","url":"https://doi.org/10.2478/jaiscr-2026-0001","authors":["Yu Chen","Haotian Xu","Jie Liu","Ming Hou","Yang Li","Shaopeng Qiu","Maohua Sun","Huimin Zhao","Wu Deng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-26T18:00:34Z","doi":"10.2478/jaiscr-2026-0001","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1007/978-3-032-22830-7_11","name":"Enhancing Text-Based Sentiment and Emotion Classification with Quantum-Inspired Deep Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-22830-7_11","authors":["Santosh Kumar","Ravi Sharma","Abhilesh Kumar Rai","Abhishek Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-05T22:17:49Z","doi":"10.1007/978-3-032-22830-7_11","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1002/9781394474325.ch9","name":"Adaptive Cyber Resilience via Bio‐Inspired Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9781394474325.ch9","authors":["Disha ARSUDE","Mritunjay Kr. RANJAN","Ramdas GORE","Kalyani PURKAR","Ankita PATIL","Rajashri RIKAME"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-31T21:30:47Z","doi":"10.1002/9781394474325.ch9","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1039/d6mh00718j/v2/review1","name":"Review for \"Neutron-Star-Inspired Metamaterials: Mitigating Friction–Strength–Conductivity Trade-offs\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d6mh00718j/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-13T21:08:35Z","doi":"10.1039/d6mh00718j/v2/review1","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.55277/researchhub.ux6ixwa6","name":"Pink Themed Treats Inspired by Barbie You Must Try Today","source":"crossref","abstract":"","url":"https://doi.org/10.55277/researchhub.ux6ixwa6","authors":["Manish Rangi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-06T08:21:56Z","doi":"10.55277/researchhub.ux6ixwa6","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1088/2634-4386/ae9006","name":"A neuromorphic digital Ising solver with Tabu-inspired inhibitory dynamics for scalable graph optimization","source":"crossref","abstract":"Abstract We present a fully digital Ising solver for maximum-cut implemented on a low-cost Artix-7 field-programmable gate array (FPGA), where tabu-inspired inhibitory dynamics are realized as a compact, Block RAM-resident short-term memory. The solver operates in deterministic fixed-point arithmetic and scales up to the on-chip limit of N = 850 spins across multiple graph sizes and sparsity regimes. We benchmark the proposed Tabu-based dynamics against (i) a parallel Hopfield-network update rule implemented on the same FPGA, and (ii) a CPU-based quantum approximate optimization algorithm (QAOA) reference used as a fixed variational baseline for solution quality under a prescribed budget. Across the tested graph families, the Tabu-enhanced solver reaches higher cut values with reduced run-to-run dispersion than purely deterministic descent. Quantitatively, field-aligned warm start improves the median normalized cut of TS by 0.014 and reduces solve time by 0.18 ms at N = 100 , ρ = 20 % . At the largest tested size ( N = 850 ), TS improves the median normalized cut over the fixed-budget CPU-QAOA reference by 0.014–0.016, with median CPU–FPGA solve-time differences of 640–720 ms under the reported protocol. The N = 850 FPGA implementation closes timing at 100 MHz, demonstrating that short-term inhibitory memory can be embedded in a fully digital Ising network without relying on stochasticity, analog variability, or annealing schedules.","url":"https://doi.org/10.1088/2634-4386/ae9006","authors":["Juan Núñez","Rafaella Fiorelli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-24T22:51:22Z","doi":"10.1088/2634-4386/ae9006","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1088/1402-4896/ae7ac7/v1/review2","name":"Review for \"Novel circular fractal-inspired compact EBG for wireless capsule endoscopy\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1402-4896/ae7ac7/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-10T21:06:51Z","doi":"10.1088/1402-4896/ae7ac7/v1/review2","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.55277/researchhub.yi5rtz8i","name":"Neuro Energizer Reviews 2026 | Does It Really Boost Brain Power, Focus &amp; Energy?#","source":"crossref","abstract":"","url":"https://doi.org/10.55277/researchhub.yi5rtz8i","authors":["Al Hossain"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-26T18:31:16Z","doi":"10.55277/researchhub.yi5rtz8i","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.55277/researchhub.ao19uipb","name":"Neuro Surge Reviews – Is It Legit, a Scam or Worth Buying? (2026 Update)","source":"crossref","abstract":"","url":"https://doi.org/10.55277/researchhub.ao19uipb","authors":["Jahid Hossain"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-07T13:52:22Z","doi":"10.55277/researchhub.ao19uipb","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.55277/researchhub.08l3hxhy","name":"Neuro Serge Review 2026 | Does It Really Boost Brain Power, Focus &amp; Memory?","source":"crossref","abstract":"","url":"https://doi.org/10.55277/researchhub.08l3hxhy","authors":["jovan ahmed"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-26T19:57:15Z","doi":"10.55277/researchhub.08l3hxhy","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.21203/rs.3.rs-9596914/v1","name":"Carbon Nanotubes inspired Resistance Temperature Detector","source":"crossref","abstract":"Abstract Resistance Temperature Detectors (RTDs) are currently the most reliable and robust temperature sensors used in industry and academia to measure temperature variations. RTDs are temperature sensors based on the change in electrical resistance of materials to measure temperature variations with high accuracy. This paper describes the design, simulation, creation, and temperature characterization validation of a Resistance Temperature Detector (RTD) based on the high surface area geometry found in Carbon Nanotubes (CNTs). The purpose of this paper is to develop a new, simple, and robust RTD geometry for use in applications where stress levels are high, such as jet engine or plasma reactor thermal management applications. The high electrical conductivity and large surface area of CNTs served as key factors in designing this geometry. The steps included performing simulations with the help of COMSOL Multiphysics to simulate heat dissipation and electrical potential within this element. These simulations demonstrated a linear relationship between resistance and temperature. This element has been created through multiple steps, involving wire-electric discharge machining and manual punching of a meshed structure onto it. The element was then tested using a heating apparatus and an electrical setup. The element’s performance at varying temperature values revealed a linear behaviour with a constant slope measurement of 0.1057 ± 0.0032 in its resistance values (R²=0.9944). This paper comprehensively demonstrates that new and simple robust CNT-based geometry structures can also be used to create efficient RTDs.","url":"https://doi.org/10.21203/rs.3.rs-9596914/v1","authors":["Kuneh Shah","Mayank Goswami"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-05T06:33:23Z","doi":"10.21203/rs.3.rs-9596914/v1","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1088/1402-4896/ae7ac7/v1/review1","name":"Review for \"Novel circular fractal-inspired compact EBG for wireless capsule endoscopy\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1402-4896/ae7ac7/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-10T21:06:51Z","doi":"10.1088/1402-4896/ae7ac7/v1/review1","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1115/dmd2026-1053","name":"Bio-Inspired 3D-Printed Exoskeleton for Accelerating Knee Injury Rehabilitation","source":"crossref","abstract":"Abstract Knee injuries affect millions of individuals each year and often lead to long-term mobility limitations, muscle weakness, and extended rehabilitation timelines. During recovery, patients frequently struggle to fully load the joint, resulting in muscle atrophy, reduced bone-loading activity, delayed healing, and a greater risk of reinjury. These challenges contribute to persistent joint instability and prolonged rehabilitation. In this paper, we present a novel bioinspired knee exoskeleton designed to enhance rehabilitation and reduce reinjury risk. Mimicking the behavior of biological tissue, the exoskeleton stores and releases strain energy during knee flexion and extension. Fully customizable through additive manufacturing, the exoskeleton can be designed to fit patient-specific anatomical and rehabilitation needs. In this paper, experimental testing is conducted to test the functionality of the exoskeleton. Results show that the device provides controlled and tunable resistance under knee flexion. This resistance is essential for effective rehabilitation, validating the exoskeleton’s functionality. This novel exoskeleton has the potential to shorten rehabilitation timelines, restore joint stability, and reduce the likelihood of future injury.","url":"https://doi.org/10.1115/dmd2026-1053","authors":["Ashley Criger","Ankit Saxena"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-04T05:33:21Z","doi":"10.1115/dmd2026-1053","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1063/10.0043468","name":"Follow the Vikings: A student exercise in optics and navigation inspired by history","source":"crossref","abstract":"Vikings may have used the sky’s polarization as a navigation tool. Making similar measurements helps students connect science with real life.","url":"https://doi.org/10.1063/10.0043468","authors":["Anashe Bandari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-21T12:09:20Z","doi":"10.1063/10.0043468","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1016/j.suscom.2026.101318","name":"Performance evaluation of economic viability of a virtual power plant employing multiple nature inspired meta-heuristic techniques","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.suscom.2026.101318","authors":["Anubhav Kumar Pandey","Vinay Kumar Jadoun","Jayalakshmi N.S.","Nandini K.K."],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-13T08:14:50Z","doi":"10.1016/j.suscom.2026.101318","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1097/wno.0000000000002504","name":"Literature Commentary","source":"crossref","abstract":"In this issue, we are very glad to welcome Kimberly Gokoffski, MD, PhD from UC Irvine as a commentator. Doctors Moster and Gokoffski review the following 4 articles. Boudot de la Motte M, Gavoille A, Papeix C, et al. Treatment discontinuation in patients with myelin oligodendrocyte glycoprotein antibody-associated disease. JAMA Neurol . 2026. Ayupov, T, Moreno-Juan, V, Curtoni, S. et al. Cell-type–targeted mitochondrial transplantation rescues cell degeneration. Nature . 2026;653:221–231. Yang DL, Cao Q, Liu F, et al. Quantification of vascular burden on cranial vessel wall MRI and ophthalmic complications in giant cell arteritis. ACR Open Rheumatol . 2026;8:e90066. Fogg, LG, Tom, E, Policarpo, M, et al . The visual system of the longest-living vertebrate, the Greenland shark. Nat Commun . 2026;17:39.","url":"https://doi.org/10.1097/wno.0000000000002504","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-29T15:00:11Z","doi":"10.1097/wno.0000000000002504","addedAt":"2026-09-01T01:48:30.039Z","updatedAt":"2026-09-01T01:48:30.039Z"},{"id":"doi:10.1038/s41598-026-50758-x","name":"Telecommunication-inspired network models of healthy and diseased brains.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-50758-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-50758-x","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1371/journal.pone.0347838","name":"Design of a dynamics-based hydraulic controller for lifting manipulator wrist and its stability analysis.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pone.0347838","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pone.0347838","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1038/s41540-026-00732-0","name":"A rule-based simulation model illuminates the role of asymmetric mitochondrial fission on beta-cell health.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41540-026-00732-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41540-026-00732-0","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1038/s41598-026-45357-9","name":"AI enhanced optimization of college physical education programs using hybrid genetic algorithms and learning based fitness evaluation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-45357-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-45357-9","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.3389/fmed.2026.1780240","name":"Data-driven prediction of lipophilic drug solubility in supercritical CO&lt;sub&gt;2&lt;/sub&gt; using an adaptive ensemble learning architecture.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fmed.2026.1780240","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fmed.2026.1780240","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1038/s42003-026-09917-z","name":"Dynamic spatiotemporal features in action recognition: a multimodal study.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s42003-026-09917-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s42003-026-09917-z","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1186/s41747-026-00686-2","name":"Acute deep neck infection MRI: deep learning segmentation and clinical relevance of retropharyngeal edema volume.","source":"europepmc","abstract":"","url":"https://doi.org/10.1186/s41747-026-00686-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1186/s41747-026-00686-2","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1038/s42003-026-10444-0","name":"The electrofluidic brain as a basement layer for neural computation.","source":"europepmc","abstract":"This article reappraises brain function by reconsidering the role of cerebral fluid dynamics in cognition. Tracing a lineage from early modern thinkers like Descartes-who invoked hydraulic metaphors and 'animal spirits'-to J.C. Bose's pioneering studies on electro-mechanical plant physiology, and culminating in contemporary findings on cerebrospinal fluid (CSF), extracellular space (ECS), and neurovascular coupling, we reveal a forgotten yet vital computational substrate. We argue that alongside the well-studied digital operations of neural circuits exists a slower, analog, evolutionarily older layer of electrofluidic computation. This system-comprised of ionic diffusion, convective CSF flow, and vascular modulation-not only supports but dynamically shapes neural activity. The brain emerges as an electromechanical ecology of electric pulses and fluid flows, where the mind is both a pattern of neural activity and a choreography of fluid flows.","url":"https://doi.org/10.1038/s42003-026-10444-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s42003-026-10444-0","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1038/s41598-026-41534-y","name":"Groundwater quality index prediction and aquifer failure risk analysis using metaheuristic-tuned artificial neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-41534-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-41534-y","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1073/pnas.2533498123","name":"A hemispheric decoding principle for vestibular heading perception in the posterior sylvian area.","source":"europepmc","abstract":"","url":"https://doi.org/10.1073/pnas.2533498123","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1073/pnas.2533498123","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1038/s41598-026-41039-8","name":"Multiple antenna performance parameters estimation of folded dipole antenna using Adaptive Neuro-Fuzzy Inference System trained with Particle Swarm Optimization.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-41039-8","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-41039-8","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1038/s41598-026-42297-2","name":"AI driven dual constraint cooptimization of affective semantics and engineering parameters for biomimetic product design.","source":"europepmc","abstract":"In response to the limitation of the separation between emotion and rationality in traditional bionic design of product forms, an artificial intelligence-based dual-constraint generative design framework (AI-DCF) is proposed, which deeply integrates computer vision and visual dynamics modeling technology to achieve systematic coupling of biological semantics and engineering parameters. Firstly, an emotional semantic graph is constructed through the TextRank algorithm in natural language processing (NLP), combined with OpenCV contour detection to generate biological form tensor representations, forming a cross-modal semantic-morphological knowledge graph, breaking through the barrier of traditional design’s reliance on subjective experience. Secondly, a dual-channel optimization engine based on deep reinforcement learning (DRL) is developed, where the Alpha channel fusion technology realizes shape matching based on visual attention, and the visual dynamics model completes the inference of structural parameters guided by mechanics, and a real-time gradient feedback mechanism is embedded to form a data-algorithm-decision closed loop. Finally, taking Mingyu forklift as the experimental carrier, a comparative experiment is conducted to verify the significant advantages of the dual-constraint model over traditional methods in terms of biological feature recognizability (+ 37.5%), comprehensive performance score (+ 25%), and design iteration efficiency (+ 31.25%). These findings demonstrate case-level feasibility of aligning emotional semantics with engineering parameterization within the study’s constraints; it provides a preliminary feasibility verification for the mapping relationship between the emotional semantic descriptors based on artificial intelligence and engineering parameterization.","url":"https://doi.org/10.1038/s41598-026-42297-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-42297-2","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1007/978-3-032-05141-7_34","name":"Learning Explainable Imaging-Genetics Associations Related to a Neurological Disorder.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/978-3-032-05141-7_34","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/978-3-032-05141-7_34","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1038/s41598-026-49980-4","name":"Uncertainty-resilient control of large-scale industrial IoT networks via learning-guided fuzzy intelligence.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-49980-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-49980-4","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1073/pnas.2516572123","name":"A data-driven framework linking the connectome to spatial gene expression gradients inspired by chemoaffinity theory.","source":"europepmc","abstract":"","url":"https://doi.org/10.1073/pnas.2516572123","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1073/pnas.2516572123","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1038/s41467-026-70334-1","name":"Biomimetic hairy affective-touch sensory AI interface.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-70334-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-70334-1","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1038/s41598-026-42248-x","name":"Integrated ore classification using stand-alone and hybridised machine learning algorithms.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-42248-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-42248-x","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.3390/biomimetics11060413","name":"A Modified Complex-Valued Encoding Greater Cane Rat Algorithm for Global Optimization and Constrained Engineering Applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics11060413","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/biomimetics11060413","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.3390/jimaging12060254","name":"Segmentation-Free Preoperative 3D MRI Classification of Low-Grade Versus High-Grade Glioma Using Task-Oriented Neural Architecture Search.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/jimaging12060254","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/jimaging12060254","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1038/s41598-025-33874-y","name":"A hybrid AI-genetic algorithm framework for the optimization of polymer flooding strategies: a numerical simulation-based approach.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-33874-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-025-33874-y","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1038/s41598-026-47208-z","name":"Predicting unconfined compressive strength of geopolymer-stabilized clays using a sector fruit fly-based extreme learning machine.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-47208-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-47208-z","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1016/j.acra.2025.11.018","name":"From Artificial Intelligence to Robotics: How to Navigate Technological Innovation in Radiology With the Gartner Hype Cycle.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.acra.2025.11.018","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.acra.2025.11.018","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1038/s41467-026-73289-5","name":"SuperARC: a test for artificial superintelligence based on compressed modelling, recursive prediction and problem complexity.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-73289-5","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-73289-5","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1002/adma.202521689","name":"Photo-Patternable PEDOT:PSS for High Performance Organic Electrochemical Transistors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202521689","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202521689","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.3390/s26082416","name":"KA-IHO: A Kinematic-Aware Improved Hippo Optimization Algorithm for Collision-Free Mobile Robot Path Planning in Complex Grid Environments.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s26082416","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/s26082416","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1093/pnasnexus/pgag009","name":"Efficient planning and implementation of optimal foraging strategies under energetic constraints.","source":"europepmc","abstract":"","url":"https://doi.org/10.1093/pnasnexus/pgag009","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1093/pnasnexus/pgag009","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1038/s41467-026-72146-9","name":"Modeling attention and binding in the brain through bidirectional recurrent gating.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-72146-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-72146-9","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1038/s41598-026-49976-0","name":"Predictive control of earth pressure balance in shield tunneling using a hybrid learning approach.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-49976-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-49976-0","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1177/13524585261427333","name":"Generalizable spinal cord multiple sclerosis lesion segmentation across MRI contrasts, protocols, and centers.","source":"europepmc","abstract":"","url":"https://doi.org/10.1177/13524585261427333","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1177/13524585261427333","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1177/20552076261431902","name":"Integrating deep learning and thermal estimation for enhanced MRI-based brain tumor diagnosis.","source":"europepmc","abstract":"","url":"https://doi.org/10.1177/20552076261431902","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1177/20552076261431902","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.3390/jcm15103606","name":"Trigemino-Vagal Recalibration in Pediatric Anesthesia: A Prospective Cohort Study on the \"60-Minute Autonomic Cliff,\" \"Trigger Mass,\" and Recovery Dynamics in 1115 Dental Procedures.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/jcm15103606","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/jcm15103606","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1186/s12929-025-01213-y","name":"Mod-SE(2): a geometric deep learning framework for brain tumor classification and segmentation in MRI images.","source":"europepmc","abstract":"","url":"https://doi.org/10.1186/s12929-025-01213-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1186/s12929-025-01213-y","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1038/s41598-026-35669-1","name":"Hybrid fuzzy machine learning models optimized with meta-heuristics for accurate EEG-based neurological assessment.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-35669-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-35669-1","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1371/journal.pone.0346576","name":"CDR-Net: A computerized framework to detect Alzheimer's diseases and mild cognitive impairment.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pone.0346576","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pone.0346576","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1186/s12974-026-03788-1","name":"Network-based disease fingerprinting with neuroinflammation PET imaging.","source":"europepmc","abstract":"","url":"https://doi.org/10.1186/s12974-026-03788-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1186/s12974-026-03788-1","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.3390/biomimetics11040240","name":"Aquila Optimization-Assisted Artificial Neural Network for Classification Problems.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics11040240","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/biomimetics11040240","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1038/s41598-026-37700-x","name":"Neural tracking at theta predicts drumming-induced altered states of consciousness.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-37700-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-37700-x","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1038/s41598-026-50158-1","name":"NeXtSwin-X: dual-branch cross-attention fusion of ConvNeXt and swin transformer for accurate brain tumor classification from MRI and CT.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-50158-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-50158-1","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.3390/biomimetics11060368","name":"Seamless Human-Computer Interaction Enabled by Wearable Biointerfaces and Intelligent Systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics11060368","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/biomimetics11060368","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1038/s42003-026-09852-z","name":"EEG hyperscanning reveals dynamic interbrain network patterns during interactive social decision-making.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s42003-026-09852-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s42003-026-09852-z","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1038/s41598-026-48314-8","name":"Automatic generation of labanotation based on a hybrid transformer-LSTM network with multi-scale spatio-temporal features.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-48314-8","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-48314-8","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1038/s41598-026-41127-9","name":"Experimental validation of MRAS sensorless direct torque control using ANN for induction motors in a pumping system.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-41127-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-41127-9","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1016/j.media.2025.103893","name":"AtlasMorph: Learning conditional deformable templates for brain MRI.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.media.2025.103893","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.media.2025.103893","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1007/s10548-025-01170-7","name":"Exploring Dynamic Alpha Band Connectivity in Parkinson's Disease: A Novel Approach to Postural Control Assessment Using the BioVRSea Paradigm.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s10548-025-01170-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s10548-025-01170-7","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.3390/e28020173","name":"An Information-Theoretic Model of Abduction for Detecting Hallucinations in Explanations.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/e28020173","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/e28020173","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1038/s44182-025-00056-x","name":"Biohybrid living robotics: A comprehensive review of recent advances, technological innovation, and future prospects.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s44182-025-00056-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s44182-025-00056-x","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.303Z"},{"id":"doi:10.1107/s160057752500997x","name":"FaXToR: the hard X-ray micro-tomography beamline at the Spanish synchrotron ALBA.","source":"europepmc","abstract":"","url":"https://doi.org/10.1107/s160057752500997x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1107/s160057752500997x","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1007/s10548-026-01205-7","name":"Dictionary Learning Methods for Brain Activity Mapping with MEG Data.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s10548-026-01205-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s10548-026-01205-7","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1038/s41598-026-59656-8","name":"Intelligent adaptive frequency regulation of interconnected power networks under renewable uncertainty and time delays.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-59656-8","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-59656-8","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.3390/ma19071301","name":"Artificial Intelligence in Metal Additive Manufacturing: Applications in Design, Process Modeling, Monitoring, and Quality Optimization.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/ma19071301","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/ma19071301","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1002/advs.202510658","name":"A Mussel-Inspired Bioadhesive Patch to Selectively Kill Glioblastoma Cells.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202510658","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.202510658","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1038/s41598-025-34578-z","name":"A data analytics-driven approach to backorder prediction using federated machine learning in industrial supply chains.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-34578-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-025-34578-z","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.3390/s26123726","name":"Rethinking Brain-Computer Interfaces for Soft Robotic Systems: A Unified Framework and Perspective.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s26123726","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/s26123726","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.3758/s13421-025-01734-9","name":"Understanding lightbulb moments: Meaning-making in visual morphology from comics and emoji.","source":"europepmc","abstract":"","url":"https://doi.org/10.3758/s13421-025-01734-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3758/s13421-025-01734-9","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1038/s41598-026-41102-4","name":"Intelligent techniques for predictive analytics in Agile software development.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-41102-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-41102-4","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1093/bib/bbag059","name":"A de novo assembly based fusion gene detection concept based on DNA-seq data of 100 Ewing sarcoma cases.","source":"europepmc","abstract":"","url":"https://doi.org/10.1093/bib/bbag059","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1093/bib/bbag059","addedAt":"2026-09-01T01:48:30.040Z","updatedAt":"2026-09-01T01:48:31.150Z"},{"id":"doi:10.1080/01658107.2019.1698254","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.1080/01658107.2019.1698254","authors":["David Bellows","John Chen","Hui-Chen Cheng","Peter MacIntosh","Jenny Nij Bijvank","Michael Vaphiades","Konrad Weber"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-12-12T15:05:35Z","doi":"10.1080/01658107.2019.1698254","addedAt":"2026-09-01T01:48:30.046Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1080/01658107.2016.1191247","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.1080/01658107.2016.1191247","authors":["Carmen Chan","Peter MacIntosh","Evan Price","John H. Pula","Michael Vaphiades","An-Guor Wang","Sui Wong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-06-08T14:24:21Z","doi":"10.1080/01658107.2016.1191247","addedAt":"2026-09-01T01:48:30.046Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.3109/01658107.2012.687556","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.3109/01658107.2012.687556","authors":["Carmen K. M. Chan","Panitha Jindahra","Silvia Muñoz","John H. Pula","Matthieu P. Robert","Michael Vaphiades"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-05-25T18:01:00Z","doi":"10.3109/01658107.2012.687556","addedAt":"2026-09-01T01:48:30.046Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.3109/01658107.2015.1019760","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.3109/01658107.2015.1019760","authors":["Carmen Chan","Panitha Jindahra","Axel Petzold","Evan Price","John H. Pula","Michael Vaphiades","An-Guor Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-05-04T20:05:07Z","doi":"10.3109/01658107.2015.1019760","addedAt":"2026-09-01T01:48:30.046Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1002/btm2.10217/v1/review1","name":"Review for \"Mesenchymal Stem Cell‐Inspired Microgel Scaffolds to Control Macrophage Polarization\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/btm2.10217/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-08T05:34:02Z","doi":"10.1002/btm2.10217/v1/review1","addedAt":"2026-09-01T01:48:30.046Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1002/btm2.10217/v2/review1","name":"Review for \"Mesenchymal Stem Cell‐Inspired Microgel Scaffolds to Control Macrophage Polarization\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/btm2.10217/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-08T05:34:02Z","doi":"10.1002/btm2.10217/v2/review1","addedAt":"2026-09-01T01:48:30.046Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1039/d6mh00718j/v1/review1","name":"Review for \"Neutron-Star-Inspired Metamaterials: Mitigating Friction–Strength–Conductivity Trade-offs\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d6mh00718j/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-13T21:08:35Z","doi":"10.1039/d6mh00718j/v1/review1","addedAt":"2026-09-01T01:48:30.046Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1088/2631-8695/ae1bfd/v2/review1","name":"Review for \"AxelSMOTE: An Interaction-Based Oversampling Algorithm Inspired by Cultural Dissemination\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2631-8695/ae1bfd/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-06T21:07:57Z","doi":"10.1088/2631-8695/ae1bfd/v2/review1","addedAt":"2026-09-01T01:48:30.046Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1088/2631-8695/ae3880/v1/review2","name":"Review for \"Enhancing Underwater Scene Visualization through a Biological Vision-Inspired Approach\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2631-8695/ae3880/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-15T21:11:51Z","doi":"10.1088/2631-8695/ae3880/v1/review2","addedAt":"2026-09-01T01:48:30.046Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.3109/01658107.2013.809957","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.3109/01658107.2013.809957","authors":["Carmen K. M. Chan","Panitha Jindahra","Silvia Muñoz","Matthieu P. Robert","John H. Pula","Michael Vaphiades"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-07-25T19:19:06Z","doi":"10.3109/01658107.2013.809957","addedAt":"2026-09-01T01:48:30.046Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.3109/01658107.2012.755057","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.3109/01658107.2012.755057","authors":["Carmen K. M. Chan","Panitha Jindahra","Silvia Muñoz","Matthieu P. Robert","John H. Pula","Michael Vaphiades"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-01-29T12:53:31Z","doi":"10.3109/01658107.2012.755057","addedAt":"2026-09-01T01:48:30.046Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1017/cbo9781139775380.042","name":"Neuro","source":"crossref","abstract":"","url":"https://doi.org/10.1017/cbo9781139775380.042","authors":["Ruchir Gupta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-06-09T03:22:39Z","doi":"10.1017/cbo9781139775380.042","addedAt":"2026-09-01T01:48:30.046Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.55277/researchhub.8b7135fs","name":"Is Neuro Surge Worth Trying? A 2026 Review","source":"crossref","abstract":"","url":"https://doi.org/10.55277/researchhub.8b7135fs","authors":["Jahid Hossain"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-07T13:51:34Z","doi":"10.55277/researchhub.8b7135fs","addedAt":"2026-09-01T01:48:30.046Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.3109/01658107.2014.930601","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.3109/01658107.2014.930601","authors":["Carmen K. M. Chan","Evan Price","John H. Pula","Michael Vaphiades","An-Guor Wang","Sui Wong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-22T15:02:13Z","doi":"10.3109/01658107.2014.930601","addedAt":"2026-09-01T01:48:30.046Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1109/ietc61393.2024.10564486","name":"Development of a Bio-Inspired Microfluidic Valve","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ietc61393.2024.10564486","authors":["Todd Flake","Reece Villella","Matthew S. Ballard"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-28T17:53:36Z","doi":"10.1109/ietc61393.2024.10564486","addedAt":"2026-09-01T01:48:30.046Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1002/brb3.1665/v1/review1","name":"Review for \"Neuro‐Sjögren: Uncommon or underestimated problem?\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/brb3.1665/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-25T17:02:34Z","doi":"10.1002/brb3.1665/v1/review1","addedAt":"2026-09-01T01:48:30.046Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.3109/01658107.2013.773245","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.3109/01658107.2013.773245","authors":["Carmen K. M. Chan","Panitha Jindahra","Silvia Muñoz","Matthieu P. Robert","John H. Pula","Michael Vaphiades"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-03-22T10:05:41Z","doi":"10.3109/01658107.2013.773245","addedAt":"2026-09-01T01:48:30.046Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1007/978-981-15-7907-3_3","name":"Literature Review of Various Nature-Inspired Optimization Algorithms Used for Digital Watermarking","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-15-7907-3_3","authors":["Preeti Garg","R. Rama Kishore"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-11-04T11:03:07Z","doi":"10.1007/978-981-15-7907-3_3","addedAt":"2026-09-01T01:48:30.046Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.54480/slrm.v3i1.29","name":"Symbiotic Organisms Search Optimization Algorithm in Cloud Computing: A Nature-inspired Meta-heuristic","source":"crossref","abstract":"In the past few years nature-inspired algorithms are experiencing rapid growth where most optimisation problems in different domains are addressed using it. As a result of this development come the issue of handling a complex optimisation problem within a short period remains very difficult. Symbiotic organisms search (SOS) algorithm is one of the nature-inspired metaheuristics that mimics the symbiotic association of organisms in an ecosystem. This paper proposes to investigate symbiotic organisms search algorithms used in handling various optimisation problems in different fields to bring out strengths and weaknesses of the existing algorithms as well as to point out future directions for the upcoming studies in the domain. To achieve that, studies done in optimisation problems using symbiotic organisms search from 2014 – 2020 that are obtained from some databases (Scopus, ScienceDirect, IEEE Xplore, ACM) were surveyed; where the review of various issues related to SOS such as diversity of solution search space, variants, scalability, and applications of the SOS. Finally, future research directions in the area were recommended.","url":"https://doi.org/10.54480/slrm.v3i1.29","authors":["Suleiman Sa'ad","Muhammed Abdullah","Azizol Abdullah","Fahrul Hakim Ayob"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-29T09:18:04Z","doi":"10.54480/slrm.v3i1.29","addedAt":"2026-09-01T01:48:30.046Z","updatedAt":"2026-09-01T01:48:30.046Z"},{"id":"doi:10.1016/j.asoc.2023.111210","name":"Neuro-evolution-based generic missile guidance law for many-scenarios","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2023.111210","authors":["Adham Salih","Amiram Moshaiov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-27T17:09:13Z","doi":"10.1016/j.asoc.2023.111210","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.55277/researchhub.6nnh1zhy","name":"Neuro Energizer Review 2026: Real Benefits and Results#","source":"crossref","abstract":"","url":"https://doi.org/10.55277/researchhub.6nnh1zhy","authors":["jovan ahmed"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-26T18:28:47Z","doi":"10.55277/researchhub.6nnh1zhy","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.3109/01658107.2013.792195","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.3109/01658107.2013.792195","authors":["Carmen K. M. Chan","Panitha Jindahra","Silvia Muñoz","Matthieu P. Robert","John H Pula","Michael Vaphiades"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-05-31T15:27:41Z","doi":"10.3109/01658107.2013.792195","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-3-030-41862-5_92","name":"A Review on Object Tracking Wireless Sensor Network an Approach for Smart Surveillance","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-41862-5_92","authors":["Nilima D. Zade","Shubhada Deshpande","R. Kamatchi Iyer"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-27T14:02:38Z","doi":"10.1007/978-3-030-41862-5_92","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1097/00041327-200303000-00040","name":"New evidence for stroke prevention: scientific review.","source":"crossref","abstract":"","url":"https://doi.org/10.1097/00041327-200303000-00040","authors":["Thomas R. Mizen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-11-18T17:37:55Z","doi":"10.1097/00041327-200303000-00040","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1097/00041327-199412000-00046","name":"Annual Review","source":"crossref","abstract":"","url":"https://doi.org/10.1097/00041327-199412000-00046","authors":["Barry Skarf"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-30T11:48:50Z","doi":"10.1097/00041327-199412000-00046","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1016/j.asoc.2024.111458","name":"A data-driven implicit deep adaptive neuro-fuzzy inference system capable of manifold learning for function approximation","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2024.111458","authors":["Armin Salimi-Badr"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-04T11:45:02Z","doi":"10.1016/j.asoc.2024.111458","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-3-319-69096-4_104","name":"Mutual Fund Performance Analysis Using Nature Inspired Optimization Techniques: A Critical Review","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-69096-4_104","authors":["Zeenat Afroz","Smruti Rekha Das","Debahuti Mishra","Srikanta Patnaik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-10-31T02:48:31Z","doi":"10.1007/978-3-319-69096-4_104","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-981-13-0761-4_75","name":"Toward Human-Powered Lower Limb Exoskeletons: A Review","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-13-0761-4_75","authors":["Ashish Singla","Saurav Dhand","Ashwin Dhawad","Gurvinder S. Virk"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-08-23T02:28:55Z","doi":"10.1007/978-981-13-0761-4_75","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-981-13-0761-4_1","name":"Privacy Preserving Data Mining: A Review of the State of the Art","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-13-0761-4_1","authors":["Shivani Sharma","Sachin Ahuja"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-08-23T06:28:55Z","doi":"10.1007/978-981-13-0761-4_1","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.3109/01658107.2015.1044398","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.3109/01658107.2015.1044398","authors":["Carmen Chan","Evan Price","John H. Pula","Matthieu Robert","Michael Vaphiades","An-Guor Wang","Sui Wong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-06-17T21:04:14Z","doi":"10.3109/01658107.2015.1044398","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1109/tai.2023.3339091","name":"Continual Learning: A Review of Techniques, Challenges, and Future Directions","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tai.2023.3339091","authors":["Buddhi Wickramasinghe","Gobinda Saha","Kaushik Roy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-04T14:05:54Z","doi":"10.1109/tai.2023.3339091","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.3109/01658108409051093","name":"Ocular motility in Graves' disease: A review","source":"crossref","abstract":"","url":"https://doi.org/10.3109/01658108409051093","authors":["A. Huber"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-11-20T01:04:53Z","doi":"10.3109/01658108409051093","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.4018/978-1-7998-1626-3.ch005","name":"Optimization of Energy Efficiency in Wireless Sensor Networks and Internet of Things","source":"crossref","abstract":"Energy consumption is a constraint in the design architecture of wireless sensor networks (WSNs) and internet of things (IoT). In order to overcome this constraint, many techniques have been proposed to enhance energy efficiency in WSNs. In existing works, several innovative techniques for the physical, the link, and the network layer of OSI model are implemented. Energy consumption in the WSNs is to find the best compromise of energy consumption between the various tasks performed by the objects, the detection, the processing, and the data communication tasks. It is this last task that consumes more energy. As a result, the main objective for the WSNs and the IoT is to minimize the energy consumed during this task. One of the most used solutions is to propose efficient routing techniques in terms of energy consumption. In this chapter, the authors present a review of related works on energy efficiency in WSNs and IoT. The network layer routing protocols are the main concerns in this chapter. The interest is focused on the issue of designing data routing techniques in WSNs and IoT.","url":"https://doi.org/10.4018/978-1-7998-1626-3.ch005","authors":["Hassan El Alami","Abdellah Najid"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-10-25T12:01:11Z","doi":"10.4018/978-1-7998-1626-3.ch005","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/s10586-024-04388-5","name":"Intrusion detection systems for IoT based on bio-inspired and machine learning techniques: a systematic review of the literature","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s10586-024-04388-5","authors":["Rafika Saadouni","Chirihane Gherbi","Zibouda Aliouat","Yasmine Harbi","Amina Khacha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-14T13:01:25Z","doi":"10.1007/s10586-024-04388-5","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-3-319-61316-1_11","name":"Review on Image Enhancement Techniques Using Biologically Inspired Artificial Bee Colony Algorithms and Its Variants","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-61316-1_11","authors":["Rehan Ahmad","Nitin S. Choubey"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-08-17T06:43:54Z","doi":"10.1007/978-3-319-61316-1_11","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.2139/ssrn.4033495","name":"Review on Neuro-Fuzzy System","source":"crossref","abstract":"The artificial intelligence procedure dependent on the fuzzy rationale and neural systems is applied together ordinarily. The thought processes to consolidate these two ideal models emerge out of the challenges and inborn constraints of each separated theory. Artificial Neural Network is a recent technology that combines the features of artificial intelligence and neural networks. ANN widely used in different application areas for different purposes like prediction, recognition, forecasting, and image identification. In this paper a study is conducted on ANN how we emerge two different techniques into one and remove the limitation of one another, auxiliary we study in depth about that two techniques neuro and fuzzy and an assessment has been performed on different applications of ANN in detail with their pros and cons. the use of ANN in different applications has been identified by analysing different research keywords of ANN from 2017 to 2021-08-20.Current scenario shows that ANN performs well in every field(Healthcare, Electrical &amp;amp; Electronic System and Forecasting, etc. ) and will be used in future because of its pros.","url":"https://doi.org/10.2139/ssrn.4033495","authors":["Nishtha Hooda","Meena Malik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-17T22:33:54Z","doi":"10.2139/ssrn.4033495","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-981-13-6569-0_12","name":"Socio-inspired Optimization Metaheuristics: A Review","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-13-6569-0_12","authors":["Meeta Kumar","Anand J. Kulkarni"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-03-29T12:04:59Z","doi":"10.1007/978-981-13-6569-0_12","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.2172/2585871","name":"Bio-Inspired Active Silicon Dendrite for Direction Selectivity","source":"crossref","abstract":"","url":"https://doi.org/10.2172/2585871","authors":["Luke Parker","Scott Koziol","Suma Cardwell","Frances Chance"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-27T02:02:52Z","doi":"10.2172/2585871","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.4018/978-1-7998-8561-0.ch004","name":"Ant Colony Optimization Algorithm for Electrical Power Systems Applications","source":"crossref","abstract":"Optimization has been an active area of research for several decades. As many real-world optimization problems become increasingly complex, better optimization algorithms are always needed. Recently, meta-heuristic global optimization algorithms have become a popular choice for solving complex and intricate problems, which are otherwise difficult to solve by traditional methods. This chapter reviews the recent applications of ant colony optimization (ACO) algorithm in the field of electrical power systems. Also, the progress of the ACO algorithm and its recent developments are discussed. This chapter covers the aspects like (1) basics of ACO algorithm, (2) progress of ACO algorithm, (3) classification of electrical power system applications, and (4) future of ACO for modern power systems application.","url":"https://doi.org/10.4018/978-1-7998-8561-0.ch004","authors":["Ragab A. El-Sehiemy","Almoataz Y. Abdelaziz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-08T08:09:33Z","doi":"10.4018/978-1-7998-8561-0.ch004","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1145/3584954.3584999","name":"SIFT-ONN: SIFT Feature Detection Algorithm Employing ONNs for Edge Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3584954.3584999","authors":["Madeleine Abernot","Sylvain Gauthier","Theophile Gonos","Aida Todri-Sanial"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-12T13:27:54Z","doi":"10.1145/3584954.3584999","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1016/j.asoc.2024.112046","name":"Chaotic Rao3 based adaptive neuro-fuzzy inference system to solve global infrastructure project selection problem","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2024.112046","authors":["G Punnam Chander","Sujit Das"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-08T06:25:08Z","doi":"10.1016/j.asoc.2024.112046","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-3-642-34274-5_41","name":"A Review of Cognitive Architectures for Visual Memory","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-34274-5_41","authors":["Michal Mukawa","Joo-Hwee Lim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-09-30T13:21:47Z","doi":"10.1007/978-3-642-34274-5_41","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-981-99-7227-2_3","name":"Exploring Ant Colony Optimization for Feature Selection: A Comprehensive Review","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-99-7227-2_3","authors":["A. Hashemi","M. B. Dowlatshahi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-15T08:02:31Z","doi":"10.1007/978-981-99-7227-2_3","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1007/978-981-97-1017-1_13","name":"Application of Cuckoo Search Algorithm in Bio-inspired Computing Using HPC Platform","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-1017-1_13","authors":["Tabrej Khan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-20T10:50:56Z","doi":"10.1007/978-981-97-1017-1_13","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.4018/979-8-3693-6303-4.ch003","name":"A Systematic Review of Spiking Neural Networks and Their Applications","source":"crossref","abstract":"These days, there is increasing curiosity regarding the topic of spiking neural networks (SNNs). Compared to artificial neural networks (ANNs), which are the subsequent equivalents, they bear a greater resemblance to the real neural networks found in the brain. SNNs are based on events such as neuromorphic factors; hardware based on SNNs may be less energy-intensive than ANNs. Since the energy usage would be far lower than that of typical deep learning models housed in the cloud today, this could result in a significant reduction in maintenance costs for neural network models. Such gear is still not readily accessible, however. This chapter presents a Systematic Review of Spiking Neural Networks and Their Applications. This study examines the benefits and drawbacks of various neural model types, coding techniques, methods for learning, and Neuromorphic platforms for computing. Based on these analyses, some anticipated developments are suggested, including balancing biological imitation and computing costs for neuron theories, the process of compounding coding techniques, unsupervised algorithms for learning in SNN, and digital-analog computation systems.","url":"https://doi.org/10.4018/979-8-3693-6303-4.ch003","authors":["Tarun Singhal","Ishta Rani","Divya Singh","Bikram Kumar","Vinay Bhatia","Shubhi Gupta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-29T15:16:27Z","doi":"10.4018/979-8-3693-6303-4.ch003","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.3109/01658107.2011.554768","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.3109/01658107.2011.554768","authors":["Carmen K. M. Chan","Simon J. Hickman","Silvia Muñoz","John H. Pula","Matthieu P. Robert","Michael Vaphiades"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-06-18T06:29:14Z","doi":"10.3109/01658107.2011.554768","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1039/d5tc03546e/v1/review2","name":"Review for \"Biomimetic‐Inspired Honeycomb Architecture-Based Flexible Sensors: From Design to Applications\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5tc03546e/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-03T21:28:21Z","doi":"10.1039/d5tc03546e/v1/review2","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.18653/v1/2024.findings-acl.142","name":"NeuroPrune: A Neuro-inspired Topological Sparse Training Algorithm for Large Language Models","source":"crossref","abstract":"","url":"https://doi.org/10.18653/v1/2024.findings-acl.142","authors":["Amit Dhurandhar","Tejaswini Pedapati","Ronny Luss","Soham Dan","Aurelie Lozano","Payel Das","Georgios Kollias"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-20T19:33:08Z","doi":"10.18653/v1/2024.findings-acl.142","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.1109/isvlsi61997.2024.00081","name":"A Memristive Reconfigurable Neuromorphic Array for Neuro-Inspired Dynamic Architectures","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isvlsi61997.2024.00081","authors":["Hritom Das","Nishith N. Chakraborty","Manu Rathore","Sk Hasibul Alam","Catherine D. Schuman","Garrett S. Rose"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-25T17:27:50Z","doi":"10.1109/isvlsi61997.2024.00081","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.2172/2585872","name":"Bio-Inspired Active Silicon Dendrite for Direction Selectivity","source":"crossref","abstract":"","url":"https://doi.org/10.2172/2585872","authors":["Luke Parker","Suma Cardwell","Frances Chance","Scott Koziol"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-27T02:02:51Z","doi":"10.2172/2585872","addedAt":"2026-09-01T01:48:30.047Z","updatedAt":"2026-09-01T01:48:30.047Z"},{"id":"doi:10.4018/978-1-5225-2375-8.ch006","name":"Significance of Biologically Inspired Optimization Techniques in Real-Time Applications","source":"crossref","abstract":"The techniques inspired from the nature based evolution and aggregated nature of social colonies have been promising and shown excellence in handling complicated optimization problems thereby gaining huge popularity recently. These methodologies can be used as an effective problem solving tool thereby acting as an optimizing agent. Such techniques are called Bio inspired computing. Our study surveys the recent advances in biologically inspired swarm optimization methods and Evolutionary methods, which may be applied in various fields. Four real time scenarios are demonstrated in the form of case studies to show the significance of bio inspired algorithms. The techniques that are illustrated here include Differential Evolution, Genetic Search, Particle Swarm optimization and artificial bee Colony optimization. The results inferred by implanting these techniques are highly encouraging.","url":"https://doi.org/10.4018/978-1-5225-2375-8.ch006","authors":["Sushruta Mishra","Brojo Kishore Mishra","Hrudaya Kumar Tripathy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-02-14T10:17:28Z","doi":"10.4018/978-1-5225-2375-8.ch006","addedAt":"2026-09-01T01:48:30.748Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1504/ijbic.2026.10079652","name":"Task Scheduling in Cloud Computing: A multi-objective Bernoulli shift map Antlion-inspired Pelican Optimisation Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1504/ijbic.2026.10079652","authors":["Vishal Vijay Mangave","J. Selvin Paul Peter","Bhagatsingh Dattatray Jitkar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-04T13:00:50Z","doi":"10.1504/ijbic.2026.10079652","addedAt":"2026-09-01T01:48:30.748Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1007/978-3-032-08596-2_8","name":"Implementation of NSGA-III in Solving Constrained Multi-objective Arduous Engineering Design Problems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-08596-2_8","authors":["Osman Tunca","Serdar Carbas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-02T01:52:56Z","doi":"10.1007/978-3-032-08596-2_8","addedAt":"2026-09-01T01:48:30.748Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1007/978-3-032-22193-3_12","name":"Quantum-Inspired Clustering Techniques for Malware Detection in Supply Chain Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-22193-3_12","authors":["Vishal H. Kothavade","Sthefanie J. G. Passo","John J. Prevost"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-17T23:39:50Z","doi":"10.1007/978-3-032-22193-3_12","addedAt":"2026-09-01T01:48:30.748Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.15448/1847.18","name":"Avaliação Neuro-Oftalmológica e Neuro-Otológica","source":"crossref","abstract":"O presente capítulo irá contemplar as avaliações neuro-oftalmológica e neuro-otológica, as quais aplicam-se a queixas recorrentes nos consultórios e emergências neurológicas.","url":"https://doi.org/10.15448/1847.18","authors":["Maria Lúcia Steiernagel Hristonof","Eduarda Kotlinsky Weber","Yuri Ferreira Felloni Borges","Marco Antônio Koff"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T17:54:36Z","doi":"10.15448/1847.18","addedAt":"2026-09-01T01:48:30.748Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1007/978-3-031-92854-3_33","name":"Self-healing Neuromorphic Architecture with Bio-inspired Fault Detection and Adaptive Memristor-Based Reconfiguration","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-92854-3_33","authors":["S. D. Vidya Sagar","Lavanya Addepalli","M. R. Dileep","Sreekanth Rallapalli","Jaime Lloret","Mohamed Ghouse Shukur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-21T10:49:13Z","doi":"10.1007/978-3-031-92854-3_33","addedAt":"2026-09-01T01:48:30.748Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.32614/cran.package.fitplotr","name":"fitPlotR: Plotting Probability Distributions","source":"crossref","abstract":"","url":"https://doi.org/10.32614/cran.package.fitplotr","authors":["Muhammad Osama"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-20T02:15:18Z","doi":"10.32614/cran.package.fitplotr","addedAt":"2026-09-01T01:48:30.748Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1016/b978-0-443-18509-0.00004-9","name":"Software solutions for managing radiomics and radiogenomics in neuro-oncology clinical settings","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-18509-0.00004-9","authors":["Gaurav Das","Soumyaranjan Panda"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-25T05:33:48Z","doi":"10.1016/b978-0-443-18509-0.00004-9","addedAt":"2026-09-01T01:48:30.748Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1039/d5sc02953h/v1/review2","name":"Review for \"Bio-Inspired Total Synthesis of Daphnepapytone A\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5sc02953h/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-20T04:51:40Z","doi":"10.1039/d5sc02953h/v1/review2","addedAt":"2026-09-01T01:48:30.748Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.2139/ssrn.5581710","name":"Causal Inspired Multi Modal Recommendation System","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5581710","authors":["Jie Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-06T16:07:51Z","doi":"10.2139/ssrn.5581710","addedAt":"2026-09-01T01:48:30.748Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1016/b978-0-443-15684-7.00024-5","name":"Ionic molecules","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-15684-7.00024-5","authors":["Songjia Han","Chuan Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-01T11:43:01Z","doi":"10.1016/b978-0-443-15684-7.00024-5","addedAt":"2026-09-01T01:48:30.748Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1513/annalsats.202408-864ip","name":"A Unified Set of Patient-Inspired Health Concepts for Chronic Obstructive Pulmonary Disease: A North Star for Understanding Treatment Benefit","source":"crossref","abstract":"","url":"https://doi.org/10.1513/annalsats.202408-864ip","authors":["Alan Hamilton","Nancy Kline Leidy","Ashley I. Duenas","Soren E. Skovlund","Bruce E. Miller"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-05T14:27:10Z","doi":"10.1513/annalsats.202408-864ip","addedAt":"2026-09-01T01:48:30.748Z","updatedAt":"2026-09-01T01:48:30.748Z"},{"id":"doi:10.1039/d5sc02953h/v2/review1","name":"Review for \"Bio-Inspired Total Synthesis of Daphnepapytone A\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5sc02953h/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-20T04:51:40Z","doi":"10.1039/d5sc02953h/v2/review1","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1016/b978-0-443-15684-7.00029-4","name":"Fluorescent sensors","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-15684-7.00029-4","authors":["V. Wulf","G. Bisker"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-01T11:43:10Z","doi":"10.1016/b978-0-443-15684-7.00029-4","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1101/2025.07.06.663394","name":"Large-scale classification of metagenomic samples: a comparative analysis of classical machine learning techniques vs a novel brain-inspired hyperdimensional computing approach","source":"crossref","abstract":"Abstract Classical machine learning techniques have revolutionized bioinformatics, enabling researchers to extract knowledge from complex biological data. However, these techniques often struggle with high-dimensional data, where the increasing number of features leads to decreased performance, also affecting models accuracy. To address this problem, we explore hyperdimensional computing (HDC), an emerging brain-inspired computational paradigm that leverages high-dimensional vectors and simple arithmetic operations to represent and manipulate complex patterns, as an alternative approach in the context of supervised machine learning. In this work, we present a comprehensive comparative analysis of HDC against established machine learning techniques across a range of classification tasks. As a representative use case, we focus on classifying heterogeneous metagenomic samples based on their quantitative microbial profiles, using publicly available microbiome datasets. Our results demonstrate that HDC achieves comparable, and in some cases, superior classification accuracy to classical methods. Furthermore, our findings highlight the potential of HDC for improved computational efficiency, particularly when dealing with large-scale datasets, suggesting the HDC-based classifier as a promising tool for bioinformatics research, particularly in areas characterized by high-dimensional data. We also offer a Galaxy powered toolset to analyze your own datasets and generate reproducible workflows and adopt these methods in your own research with ease. Our investigation into the application of a HDC-based supervised machine learning technique for classifying microbial profiles in metagenomic samples yielded promising results, demonstrating the potential of this novel computational paradigm to complement and, in some cases, surpass the performances of well established machine learning techniques. Importance The growing complexity and dimensionality of biological data require more efficient and scalable machine learning approaches. HDC offers a novel alternative to conventional methods, showing resilience to high-dimensionality while maintaining competitive accuracy. This study demonstrates the effectiveness of HDC in classifying metagenomic samples based on their microbial composition. Our results suggest that HDC not only matches, but sometimes exceeds the performance of well-established methods. We make this approach accessible to the broader bioinformatics community with an open-source tool fully integrated into the Galaxy platform, facilitating its adoption and reproducibility, with the aim of integrating HDC into mainstream biological data analysis pipelines, especially for complex, high-dimensional tasks in microbiome research.","url":"https://doi.org/10.1101/2025.07.06.663394","authors":["Jayadev Joshi","Fabio Cumbo","Daniel Blankenberg"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-11T11:00:10Z","doi":"10.1101/2025.07.06.663394","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-981-97-5979-8_6","name":"Review of Recent Advances on AI Applications in Civil Engineering","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-5979-8_6","authors":["Yaren Aydın","Gebrail Bekdaş","Sinan Melih Nigdeli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-25T20:57:33Z","doi":"10.1007/978-981-97-5979-8_6","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1093/nop/npaf005","name":"Shared decision-making in neuro-oncology: Existing practices and future steps","source":"crossref","abstract":"","url":"https://doi.org/10.1093/nop/npaf005","authors":["Helle Sorensen von Essen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-07T20:17:28Z","doi":"10.1093/nop/npaf005","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1145/3811628","name":"Proceedings of the 3rd workshop on Quantum Computing and Quantum-Inspired Technology for Data-Intensive Systems and Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3811628","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-04T10:29:31Z","doi":"10.1145/3811628","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1016/j.sasc.2025.200431","name":"Quantum inspired hyperparameter optimization for enhanced deep learning based intrusion detection in wireless sensor networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.sasc.2025.200431","authors":["K. Vinotha","P. Eswaran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-15T16:15:49Z","doi":"10.1016/j.sasc.2025.200431","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1039/d5sc02953h/v1/review1","name":"Review for \"Bio-Inspired Total Synthesis of Daphnepapytone A\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5sc02953h/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-20T04:51:40Z","doi":"10.1039/d5sc02953h/v1/review1","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1093/neuonc/noaf193.595","name":"EP08.01 THE IMMUNE LANDSCAPE OF BRAIN TUMORS: IMPLICATIONS FOR NEUROIMMUNOLOGY AND NEURO-ONCOLOGY THERAPIES","source":"crossref","abstract":"Abstract BACKGROUND Glioblastoma multiforme (GBM) is an aggressive brain tumor with a poor prognosis despite standard treatments. GBM evades immune responses through tumor-associated macrophages (TAMs), myeloid-derived suppressor cells (MDSCs), and immune checkpoints like PD-1/PD-L1. The blood-brain barrier (BBB) further limits immune infiltration and drug delivery. Understanding GBM’s immune landscape is crucial for developing effective immunotherapies. MATERIAL AND METHODS A systematic review was conducted using PubMed and MEDLINE, focusing on GBM immunology and immunotherapies. Relevant clinical trials, meta-analyses, and preclinical studies published in the last 20 years were analyzed. Non-GBM studies and those lacking significant evidence were excluded. RESULTS GBM promotes immune evasion through TAM polarization, MDSC accumulation, and checkpoint upregulation, leading to T-cell suppression. Immune checkpoint inhibitors (ICIs) like nivolumab show limited success, benefiting only a subset of patients. Adoptive T-cell therapy (ACT) and oncolytic viruses show promise but face challenges like T-cell exhaustion and inconsistent clinical responses. Cancer vaccines, particularly targeting EGFRvIII, yield mixed results. Combination therapies, such as ICIs with radiotherapy, improve immune responses and tumor control. CONCLUSION GBM’s immunosuppressive environment remains a major treatment obstacle. Immunotherapies, including ICIs, ACT, and oncolytic viruses, show potential but require further optimization. Future research should focus on combination approaches and strategies to overcome immune resistance and BBB limitations. Advancing personalized immunotherapy and tumor profiling may enhance treatment outcomes for GBM patients.","url":"https://doi.org/10.1093/neuonc/noaf193.595","authors":["M Alnahdi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-03T15:44:11Z","doi":"10.1093/neuonc/noaf193.595","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1016/b978-0-443-18509-0.09990-4","name":"Index","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-18509-0.09990-4","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-25T05:34:21Z","doi":"10.1016/b978-0-443-18509-0.09990-4","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/dchpc69296.2026.11517249","name":"Optimization Methods for Neuro-Fuzzy Systems: A Comprehensive Review of Financial Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/dchpc69296.2026.11517249","authors":["Xuefang Li","Asefeh Asemi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-18T19:44:46Z","doi":"10.1109/dchpc69296.2026.11517249","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1055/s-0045-1802322","name":"Thanks to the Editorial Board of Arquivos de Neuro-Psiquiatria (2024)","source":"crossref","abstract":"","url":"https://doi.org/10.1055/s-0045-1802322","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-01T00:20:01Z","doi":"10.1055/s-0045-1802322","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-981-97-5979-8_2","name":"Structural Optimization of Reinforced Concrete Frames with a Modified Flower Pollination Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-5979-8_2","authors":["Panagiotis E. Mergos","Xin-She Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-25T20:57:33Z","doi":"10.1007/978-981-97-5979-8_2","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1002/spe.3113","name":"Market‐inspired framework for securing assets in cloud computing environments","source":"crossref","abstract":"Abstract Self‐adaptive security methods have been extensively leveraged for securing software systems and users from runtime threats in online and elastic environments, such as the cloud. The existing solutions treat security as an aggregated quality by enforcing “one service for all” without considering the explicit security requirements of each asset or the costs associated with security. Dealing with the security of assets in ultra‐large environments calls for rethinking the way we select and compose services—considering not only the services but the underlying supporting computational resources in the process. We motivate the need for an asset‐centric, self‐adaptive security framework that selects and allocates services and underlying resources in the cloud. The solution leverages learning algorithms and market‐inspired approaches to dynamically manage changes in the runtime security goals/requirements of assets with the provision of suitable services and resources, while catering for monetary and computational constraints. The proposed framework aims to inform the self‐adaptive security efforts of security researchers and practitioners operating in dynamic large‐scale environments, such as the Cloud. To illustrate the utility of the proposed framework it is evaluated using simulation on an application based scenario, involving cloud‐based storage and security services.","url":"https://doi.org/10.1002/spe.3113","authors":["Giannis Tziakouris","Carlos Mera‐Gómez","Francisco Ramírez","Rami Bahsoon","Rajkumar Buyya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-08T06:59:56Z","doi":"10.1002/spe.3113","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1201/9781003658221-42","name":"Nature-inspired metaheuristic algorithm optimized TIDN controller for frequency management in networked power system with storage device and HVDC link","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003658221-42","authors":["Sushanta Kumar Sethy","Pratap Chandra Pradhan","Manoj Kumar Kar","Binod Kumar Sahu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-04T13:38:56Z","doi":"10.1201/9781003658221-42","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.22233/9781913859510.14.4","name":"Neuro-ophthalmology","source":"crossref","abstract":"","url":"https://doi.org/10.22233/9781913859510.14.4","authors":["Roser Tetas-Pont","Abbe Crawford"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-08T13:10:32Z","doi":"10.22233/9781913859510.14.4","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.3390/books978-3-7258-4374-9","name":"Bio-Inspired Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.3390/books978-3-7258-4374-9","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-30T08:01:43Z","doi":"10.3390/books978-3-7258-4374-9","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1201/9781003601555-5","name":"A Task Scheduling Algorithm for Cloud Computing Based on Bio-inspired Multi-objective Manta Rays","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003601555-5","authors":["Abubakr S. Issa","Sajjad Shamkhi Jaber","Yusra H. Ali","Tarik A. Rashid"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-13T16:48:17Z","doi":"10.1201/9781003601555-5","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1093/neuonc/noaf201.0772","name":"DISP-11. Virtual Neuro Oncology Tumor Board and HealthCare Disparity - Syria as an Example","source":"crossref","abstract":"Abstract Virtual neuro-oncological tumor boards have become widely implemented in many US institutions in the post-COVID-19 era. With its convenience and easy application, virtual oncology tumor boards have also been explored nationally and internationally. To investigate the role of such a platform in bridging the gap in neuro-oncological care in developing countries, I conducted a physician survey of those who have actively or recently worked in Syria, a war-torn country under economic constraints. The survey was conducted in December 2024, with 21 participants, including neurosurgeons, oncologists, and neurologists. The idea proposed is to have a weekly neuro-oncological tumor board where local physicians present cases of suspected or confirmed primary brain tumors with a panel of trained physicians in neuro-oncology from the US and Europe. Such a project aims to offer clinical guidance and training to the local team, help prioritize cases for surgery, radiation, or medical therapy, collect data to understand the landscape of primary brain tumors in Syria and help find resources. Overall, ~75% of the surveyed physicians felt it would be helpful. However, it unleashed some technical challenges and widespread healthcare disparities. Among those technical challenges are outdated and limited neuroimaging viewing and sharing applications. Additionally, many routine pathologic diagnostics for glioma, like IDH testing, are only available in a few locations nationwide. More sophisticated testing, like next-generation sequencing or MGMT promoter methylation, is also rare. On the therapeutic level, surgical resection is often delayed for weeks and sometimes omitted. Temozolomide also has limited availability and is expensive, and there are only a few functioning linear accelerator machines. However, exploring such a platform might improve neuro-oncological care disparities, allow data collection, and set a realistic prototype example to encourage initiating similar projects.","url":"https://doi.org/10.1093/neuonc/noaf201.0772","authors":["Anas Alshawa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-11T00:15:32Z","doi":"10.1093/neuonc/noaf201.0772","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/esci68015.2026.11493404","name":"Neuro-Symbolic Optimization for Renewable Planning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/esci68015.2026.11493404","authors":["Shubham Gade"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-28T19:46:14Z","doi":"10.1109/esci68015.2026.11493404","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1201/9781003681151","name":"Bio-Inspired Structures","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003681151","authors":["Srinivasan Chandrasekaran","Basanagouda I Patil"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-27T14:28:06Z","doi":"10.1201/9781003681151","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1063/5.0334481","name":"Coordination of power system stabilizers using bio inspired algorithms in multimachine power system","source":"crossref","abstract":"","url":"https://doi.org/10.1063/5.0334481","authors":["Shivakumar Rangasamy","Harini Sri Suresh Sumathi","Sowranchana Sudhakaran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-28T00:31:14Z","doi":"10.1063/5.0334481","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/tai.2026.3668173","name":"NCRAgent: A Neuro-Inspired Multiagent Framework for Transparent and Explainable Medical VQA","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tai.2026.3668173","authors":["Sirui Liu","Keyu Hou","Ali Anaissi","Ali Braytee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-26T20:47:38Z","doi":"10.1109/tai.2026.3668173","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.4102/aosis.2025.bk565","name":"Ukonga among women in rural spaces: A Nelson Mandela Children’s Fund-inspired community project","source":"crossref","abstract":"Empowering women is at the heart of sustainable development. Ukonga among women in rural spaces: A Nelson Mandela Children’s Fund‑inspired community project showcases how women’s self‑help groups in Eshowe within the uMlalazi Local Municipality in KwaZulu‑Natal, South Africa, have risen as driving forces of change, transforming lives, strengthening families, fostering financial independence and building resilience in rural South African communities. When the Nelson Mandela Children’s Fund was founded in 1995, Nelson Mandela contributed from his own pocket towards establishing an organisation that continues to exist in his honour for nearly 30 years. In the same spirit of self‑reliance and discipline, the Fund introduced the Sustainable Livelihoods Project, implemented in partnership with the KwaZulu‑Natal Christian Council and their community facilitators, supporting these women’s self‑help groups that encourage saving, collective action and sustainable livelihoods. These initiatives enable women to overcome poverty, access education and health care, and develop entrepreneurship skills. The project has directly contributed to strengthening families through community‑based initiatives that improve the care and support of infants, children, youth, expectant mothers and caregivers. Despite limited resources, training and logistical challenges, communities have built homes using locally‑produced cement blocks and initiated income‑generating projects, such as poultry farming, vegetable cultivation and trading, to sustain their livelihoods. This book combines rigorous qualitative and quantitative research from scholars at the University of Zululand, telling the stories of the lived experiences of these women in rural KwaZulu‑Natal, offering real‑world evidence of the positive socioeconomic impact. It is a vital resource for policymakers, practitioners, researchers and all who are committed to supporting women’s empowerment, sustainable community development and reducing dependency on state grants. Above all, the book tells a story of the power of collaboration between communities, civil society and academia, creating lasting change for women, children and families living in rural South African communities.","url":"https://doi.org/10.4102/aosis.2025.bk565","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-21T08:58:26Z","doi":"10.4102/aosis.2025.bk565","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-981-95-2872-1_8","name":"A Hash-Based Nature-Inspired Algorithm for High-Utility Itemset Mining","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-95-2872-1_8","authors":["Nishigandha Mhatre","Srijita Bhattacharjee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-05T10:22:23Z","doi":"10.1007/978-981-95-2872-1_8","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1016/b978-0-443-30046-2.00023-5","name":"Copyright","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-30046-2.00023-5","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-22T09:30:28Z","doi":"10.1016/b978-0-443-30046-2.00023-5","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.20944/preprints202604.0785.v1","name":"Neuro-Symbolic AI with Edge Computing and Reinforcement Learning Optimizing Autonomous Engineering Design Workflows","source":"crossref","abstract":"The convergence of Neuro-Symbolic AI, Edge Computing, and Reinforcement Learning heralds a transformative era in autonomous engineering design, addressing longstanding challenges in optimization efficiency, real-time responsiveness, and interpretability. Traditional design workflows suffer from siloed neural pattern recognition lacking logical rigor, centralized cloud dependencies creating latency bottlenecks, and heuristic optimization struggling with multi-objective trade-offs in vast design spaces. This paper introduces an integrated framework that synergistically combines these paradigms to create self-sustaining, end-to-end autonomous pipelines for complex engineering applications from aerospace structures to precision manufacturing.Neuro-Symbolic AI fuses deep neural networks for perceptual feature extraction with symbolic reasoning engines enforcing hard constraints and generating auditable proofs, enabling systems that both discover novel configurations and validate them against domain physics. Edge Computing decentralizes inference across device-fog-cloud hierarchies, achieving sub-10ms decision cycles critical for real-time applications like robotic assembly or smart grid stability. Reinforcement Learning optimization engines navigate continuous state-action spaces representing design variables, iteratively refining solutions through shaped rewards aligned with Pareto-optimal engineering objectives such as minimizing mass while maximizing strength-to-weight ratios.The proposed architecture orchestrates these components via directed acyclic graphs of containerized microservices, with federated synchronization ensuring data consistency across distributed nodes and human-in-the-loop interfaces providing strategic oversight for safety-critical decisions. Mathematical formulations ground the system hybrid loss functions balance learning objectives, edge partitioning optimizes, and multi-agent RL decomposes collaborative design tasks.Deployed on resource-constrained edge platforms, this framework demonstrates 8-12× acceleration in design cycle times, 25-35% improvements in structural efficiency, and full traceability satisfying aerospace certification standards (DO-178C). By eliminating manual iteration bottlenecks while preserving human insight where needed, the system redefines engineering practice, enabling rapid innovation across domains requiring concurrent optimization of performance, manufacturability, sustainability, and cost.","url":"https://doi.org/10.20944/preprints202604.0785.v1","authors":["V. Thamilarasi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-13T00:41:34Z","doi":"10.20944/preprints202604.0785.v1","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1063/5.0269420","name":"Bio-inspired swarm intelligence-based feature selection and classification for autism spectrum disorder detection","source":"crossref","abstract":"","url":"https://doi.org/10.1063/5.0269420","authors":["Saravana Kumar","Kannapiran Selvakumar","Valluvamani Senthil Murugan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-02T17:00:22Z","doi":"10.1063/5.0269420","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1093/neuonc/noaf201.0308","name":"CNSC-101. CHARACTERIZATION OF GBM INDUCED NEURO-IMMUNE AXIS DYSREGULATION","source":"crossref","abstract":"Abstract Glioblastoma (GBM) is the most common and aggressive form of malignant brain tumor in adults. Although GBM is believed to remain localized within the central nervous system (CNS), it exerts systemic effects; most notably, a profound immune suppression. Patients with GBM frequently exhibit lymphopenia, diminished T cell responsiveness, and elevated levels of immunosuppressive myeloid-derived suppressor cells (MDSCs). Through murine studies, our group has previously shown that intracranial gliomas induce changes in the bone marrow, skewing hematopoiesis toward immunosuppressive myeloid lineages at the expense of lymphoid progenitors. This is a striking observation of altered hematopoietic stem cell dynamics, given the anatomical separation between the brain and bone marrow and in lieu of studies of metastatic spread, suggests the presence of a signaling conduit—potentially neural in nature—that enables a novel form of CNS tumor-host communication. Spinal cord and peripheral nerves—particularly the sciatic nerve—represent major neuroimmune interfaces. These regions contain resident immune cells, including microglia and macrophages, that respond dynamically to neuronal activity and injury. These immune cells are capable of producing cytokines, expressing neurotransmitter receptors, and relaying signals that could influence distal organs, including the bone marrow. Considering this, we hypothesize that GBM induces disruption of neuroimmune signaling pathways that alters the phenotype and function of peripheral immune cells and hematopoietic progenitors. To investigate this, we have identified and characterized genotypic and phenotypic GBM-associated changes in spinal and peripheral nerve tissues. We have also probed the spinal and peripheral nerve tissues to assess variances in population, spatial distribution and expression of key neurotransmitter receptors of the immune cells within them.","url":"https://doi.org/10.1093/neuonc/noaf201.0308","authors":["Alexandra Reid","Dan Jin","Catherine Flores"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-11T00:08:57Z","doi":"10.1093/neuonc/noaf201.0308","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1088/2634-4386/adef76","name":"A retina-inspired pathway to real-time motion prediction inside image sensors for extreme-edge intelligence","source":"crossref","abstract":"Abstract The ability to predict motion in real time is fundamental to many maneuvering activities in animals, particularly those critical for survival, such as attack and escape responses. Given its significance, it is no surprise that motion prediction (MP) in animals begins in the retina. Similarly, autonomous systems utilizing computer vision could greatly benefit from the capability to predict motion in real time. Therefore, for computer vision applications, MP should be integrated directly at the camera pixel level. Towards that end, we present a retina-inspired neuromorphic framework capable of performing real-time, energy-efficient MP directly within camera pixels. Our hardware-algorithm framework, implemented using GlobalFoundries’ 22 nm FDSOI technology, integrates key retinal MP compute blocks, including a biphasic filter, spike adder, non-linear circuit, and a 2D array for multi-directional MP. Additionally, integrating the sensor and MP compute die using a 3D Cu–Cu hybrid bonding approach improves design compactness by minimizing area usage and simplifying routing complexity. Validated on real-world object stimuli, the model delivers efficient, low-latency MP for decision-making scenarios reliant on predictive visual computation, while consuming only 18.56 pJ/MP in our mixed-signal hardware implementation.","url":"https://doi.org/10.1088/2634-4386/adef76","authors":["Subhradip Chakraborty","Shay Snyder","Md Abdullah-Al Kaiser","Maryam Parsa","Gregory Schwartz","Akhilesh R Jaiswal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-14T22:51:06Z","doi":"10.1088/2634-4386/adef76","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1016/b978-0-443-15684-7.00003-8","name":"Plants","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-15684-7.00003-8","authors":["Tan-Phat Huynh","Piyush Sindhu Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-01T11:41:44Z","doi":"10.1016/b978-0-443-15684-7.00003-8","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1016/j.imavis.2026.105940","name":"Attention inspired adversarial network for intratumoral brain regions segmentation","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.imavis.2026.105940","authors":["Nishtha Tomar","Gaurav Bhatnagar","Vandita Agarwal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-23T16:17:13Z","doi":"10.1016/j.imavis.2026.105940","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-90-368-3057-7_22","name":"Neuro-oncologie","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-90-368-3057-7_22","authors":["Marjolein Geurts"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-31T12:46:34Z","doi":"10.1007/978-90-368-3057-7_22","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-3-032-08596-2_6","name":"Ant Colony Optimization Based Approach to Efficiently Identify Suspicious Processes in Memory","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-08596-2_6","authors":["N. K. Sreelaja","N. K. Sreeja"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-02T01:49:29Z","doi":"10.1007/978-3-032-08596-2_6","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1088/2631-8695/adadc7","name":"Synaptic neural circuit inspired by side-gated graphene synaptic transistors for neuromorphic computing","source":"crossref","abstract":"Abstract With the rapid advancement of artificial intelligence, the energy consumption bottleneck inherent in the von Neumann computing architecture poses a significant obstacle to the future development of edge computing, artificial intelligence, and information technology. Consequently, it is crucial to develop synaptic neural circuits that exhibit memory and learning properties through synaptic plasticity. Drawing inspiration from the side-gated graphene synaptic transistor, we have designed a synaptic neural circuit comprising four key components: pre-voltage input, synaptic weight modulation, electric double-layer effect, and post-membrane current response. Through comprehensive simulations, we have successfully mimicked various synaptic behaviours, including long-term and short-term synaptic plasticity, paired-pulse facilitation, spiking-rate-dependent plasticity, spiking time-dependent plasticity, and Pavlovian associative learning. This approach establishes a robust framework for designing synaptic neural network circuits with advanced learning capabilities, thereby enhancing the practical applications of neural networks and machine learning.","url":"https://doi.org/10.1088/2631-8695/adadc7","authors":["Huifeng Wen","Haoran Yong","Xiaoying He","Lan Rao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-23T22:59:20Z","doi":"10.1088/2631-8695/adadc7","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.4102/aosis.2025.bk565.0g","name":"Foreword: University of Zululand","source":"crossref","abstract":"","url":"https://doi.org/10.4102/aosis.2025.bk565.0g","authors":["Xoliswa Mtose"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-21T08:58:26Z","doi":"10.4102/aosis.2025.bk565.0g","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/mind67540.2025.11351609","name":"Why Knowledge Transfer Works in Oracle-Based Optimization: A Brief Analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mind67540.2025.11351609","authors":["Chenming Cao","Xiaoming Xue","Liang Feng","Kay Chen Tan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-27T04:49:35Z","doi":"10.1109/mind67540.2025.11351609","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-981-96-9908-7_6","name":"Autonomous Learning Mobile Robots Inspired by Biological Reward Strategies","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-96-9908-7_6","authors":["Junxiu Liu","Changyong Yang","Qiang Fu","Yuling Luo","Sheng Qin","Xue Ouyang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-24T16:26:46Z","doi":"10.1007/978-981-96-9908-7_6","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-3-032-06494-3_32","name":"Superconducting Components for Brain-Inspired Neural Networks: Spintronic Innovations for Neuromorphic Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-06494-3_32","authors":["Anatolie Sidorenko","Ludmila Sidorenko"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T07:50:58Z","doi":"10.1007/978-3-032-06494-3_32","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/mind67540.2025.11351704","name":"Cross-Feature Imputation and Adaptive Weighted Dual-Channel Graph Neural Network for Stroke Recurrence Prediction","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mind67540.2025.11351704","authors":["Zheng Huang","Mingfan Qiu","Haifan Wu","Zhengyu Li","Lijun Xu","Qing Bin","Meng Pang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-27T04:49:35Z","doi":"10.1109/mind67540.2025.11351704","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/mind67540.2025.11351727","name":"Multi-Modal Semantic Segmentation Based on Spike Encoding and Early Fusion with Events and Images","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mind67540.2025.11351727","authors":["Zhuxi Li","Qiugang Zhan","Ran Tao","Peiming Kan","Zhiguang Qin","Guisong Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-27T04:49:35Z","doi":"10.1109/mind67540.2025.11351727","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1007/978-981-96-9908-7_7","name":"MambaSkill: Mamba-Inspired Robotic Skill Abstraction and Dual-Level Generation for Long-Horizon Control","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-96-9908-7_7","authors":["Weiming Zhu","Yan Ma","Liang He","Bo Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-24T16:26:56Z","doi":"10.1007/978-981-96-9908-7_7","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.4018/979-8-3693-6834-3.ch008","name":"VM Placement in Cloud Computing Using Nature-Inspired Optimization Algorithms","source":"crossref","abstract":"Cloud computing implements various techniques for the efficient utilization of computing resources. These resources are delivered over the internet, allowing users to access and manage them remotely. Often, these resources are provided to the users in the form of virtual machines (VMs). VMs are essentially software-based emulations of physical computers. In a cloud data center, numerous physical machines (PMs), also called servers, host various VMs. Placement of these VMs in Physical Machines is a critical task as there are many factors that need to be considered. Nature-inspired optimization algorithms such as Genetic Algorithms, Particle Swarm Optimization, and Ant Colony Optimization are inspired by natural phenomena and behaviour. These algorithms have been used in the past to generate near-optimal solutions in polynomial time for computationally intractable problems like VM Placement Problems (VPP). This chapter discusses how virtual machines are placed in cloud data centers using Nature-Inspired Optimization Algorithms.","url":"https://doi.org/10.4018/979-8-3693-6834-3.ch008","authors":["Monali Shah","Dipankar Rajwar","Jitendra Pratap Dehury","Dinesh Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-06T15:02:17Z","doi":"10.4018/979-8-3693-6834-3.ch008","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/978-981-97-9622-9_5","name":"Deep Learning-Inspired Multiclass and Multi-label Classifications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-9622-9_5","authors":["Sanjay Chakraborty","Lopamudra Dey"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-22T20:01:39Z","doi":"10.1007/978-981-97-9622-9_5","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/978-981-96-5958-6_47","name":"Advanced YouTube Creator’s Inspired Optimization and Invasive Ductal Carcinoma Algorithm for Factual Power Loss Diminution in Electrical Transmission System","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-96-5958-6_47","authors":["Lenin Kanagasabai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-31T16:53:33Z","doi":"10.1007/978-981-96-5958-6_47","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1093/neuonc/noaf201.0764","name":"DISP-03. Facilitating financial access for pediatric neuro-oncology patients: Lessons from a cancer charity","source":"crossref","abstract":"Abstract BACKGROUND Childhood cancer survival rates in sub-Saharan Africa remain low due to high treatment costs, inadequate pediatric oncology infrastructure, sociocultural barriers, and low awareness. Faraja Cancer Support Trust, a cancer charity provides financial assistance to indigent patients requiring chemotherapy and or radiotherapy through a dedicated childhood cancer fund. This study aims at examining the financial burden of treatment for pediatric neuro-oncology patients seeking financial support from a cancer charity. MATERIALS AND METHODS A retrospective desk review cost analysis of treatment and financial data of neuro-oncology pediatric patients who applied for financial support from a cancer charity over a 12 month period. RESULTS Thirteen pediatric neuro-oncology patients applied for financial support during the study period. 61% had brain tumors of which 50% were Medulloblastoma. The age range was 3–18 years, mean: 10.6 years. All patients received radiotherapy and or chemotherapy. 87% underwent neurosurgical intervention. The total cost of treatment for these patients was USD 56,000 (KES 7,274,175). The Social Health Insurance Fund covered 43% (approximately USD 24,135), leaving a significant financial gap. Patients fundraised or borrowed money to cover part of the cost and the cancer charity supported the remaining costs. At 12 month follow up 92% of the patients who were supported by the cancer charity had completed their treatment and were doing well. CONCLUSIONS The cost of treating childhood cancer remains prohibitive even with social health insurance. Patients and families are forced to incur substantial out-of-pocket expenses or seek help from cancer charities. Financial barriers contribute to treatment abandonment, asserting the important role of cancer charities like Faraja Cancer Support Trust and civil society organizations in enabling access to care. These findings align with global studies on the financial challenges of pediatric oncology treatment in low-resource settings.","url":"https://doi.org/10.1093/neuonc/noaf201.0764","authors":["Maryam Hassan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-11T00:21:24Z","doi":"10.1093/neuonc/noaf201.0764","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1109/mind67540.2025.11351883","name":"NexusSplats: An Efficient Approach for Robust Novel View Synthesis from Unstructured Image Collections","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mind67540.2025.11351883","authors":["Yuzhou Tang","Dejun Xu","Yongjie Hou","Yunpeng Gong","Zhenzhong Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-27T04:49:35Z","doi":"10.1109/mind67540.2025.11351883","addedAt":"2026-09-01T01:48:30.749Z","updatedAt":"2026-09-01T01:48:30.749Z"},{"id":"doi:10.1080/01658107.2024.2431470","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.1080/01658107.2024.2431470","authors":["John J. Chen","Wei-Che Hung","Andrew C. Y. Mak","Michael S. Vaphiades","Rashmi Verma","Xiaojun Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-07T15:56:21Z","doi":"10.1080/01658107.2024.2431470","addedAt":"2026-09-01T01:48:30.830Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1088/1748-3190/ad839f/v2/review1","name":"Review for \"One-shot manufacturable soft-robotic pump inspired by embryonic tubular heart\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1748-3190/ad839f/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-05T17:13:42Z","doi":"10.1088/1748-3190/ad839f/v2/review1","addedAt":"2026-09-01T01:48:30.830Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1080/01658107.2025.2605009","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.1080/01658107.2025.2605009","authors":["David A. Bellows","Wei-Che Hung","Andrew C. Y. Mak","Michael S. Vaphiades","Rashmi Verma","Xiaojun Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-30T15:51:02Z","doi":"10.1080/01658107.2025.2605009","addedAt":"2026-09-01T01:48:30.830Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.21203/rs.3.rs-4847320/v1","name":"Evolutionary optimisation of pixelated IFA inspired antennas","source":"crossref","abstract":"Abstract As wireless communication systems increasingly require compact and efficient antennas, conventional antenna design methods are proving difficult to meet the rigorous demands of modern applications. For this purpose, this study introduces a methodology which uses pixelated Inverted-F Antenna (IFA) inspired designs optimised through genetic algorithms to enhance performance in constrained spatial environments. As pixels the antenna features the exemplary use of Einstein Hat-shaped tiles, enabling the antenna to efficiently utilize space.A with the proposed method optimised antenna is compared to traditional IFA designs and shows improved properties like enhanced antenna gain and efficiency as well as smaller reflection coefficient offering a promising solution for future compact antenna systems in the Internet of Things and beyond. Finally, a prototype was manufactured and the scattering parameters and antenna gain were measured within an anechoic chamber.","url":"https://doi.org/10.21203/rs.3.rs-4847320/v1","authors":["Dominik Mair","Daniel Baumgarten"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-11T04:15:19Z","doi":"10.21203/rs.3.rs-4847320/v1","addedAt":"2026-09-01T01:48:30.830Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.4018/979-8-3693-1131-8.ch001","name":"Bio-Inspired Algorithms Leveraging Blockchain Technology Enhancing Efficiency Security and Transparency","source":"crossref","abstract":"Bio-inspired algorithms, which imitate the actions and procedures seen in biological systems, have proven to be incredibly effective at solving problems in a variety of fields. However, the combination of these algorithms with blockchain technology holds enormous promise for improving their potency while assuring effectiveness, efficiency, and security. This chapter gives a general overview of how bio-inspired algorithms are used effectively with blockchain technology, highlighting their main benefits and prospective uses. Bio-inspired algorithms can gain from improved security and confidence in their execution by utilizing the decentralized and immutable characteristics of blockchain. Blockchain technology offers a transparent and auditable platform that makes it easier to verify algorithmic operations and ensure the accuracy of data. Furthermore, distributed resource allocation and decision-making are made possible by blockchain's decentralized consensus mechanisms, promoting cooperation and collective intelligence.","url":"https://doi.org/10.4018/979-8-3693-1131-8.ch001","authors":["P. Chitra","A. Saleem Raja","V. Sivakumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-29T10:11:06Z","doi":"10.4018/979-8-3693-1131-8.ch001","addedAt":"2026-09-01T01:48:30.830Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1016/j.procs.2024.04.058","name":"Differentiating Parkinson's Disease from other Neuro Diseases and Diagnosis using Deep Learning with Nature Inspired Algorithms and Ensemble Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.procs.2024.04.058","authors":["Anitha Rani Palakayala","Kuppusamy P"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-31T23:45:47Z","doi":"10.1016/j.procs.2024.04.058","addedAt":"2026-09-01T01:48:30.830Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1088/1361-6463/ad7a82/v3/response1","name":"Author response for \"Brain-inspired computing with self-assembled networks of nano-objects\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1361-6463/ad7a82/v3/response1","authors":["Vahl, Alexander","Milano, Gianluca","Kuncic, Zdenka","Brown, Simon A.","Milani, Paolo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-19T17:52:56Z","doi":"10.1088/1361-6463/ad7a82/v3/response1","addedAt":"2026-09-01T01:48:30.830Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1080/01658107.2026.2683331","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.1080/01658107.2026.2683331","authors":["David A. Bellows","Wei-Che Hung","Andrew C. Y. Mak","Michael S. Vaphiades","Rashmi Verma","Xiaojun Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-26T20:32:33Z","doi":"10.1080/01658107.2026.2683331","addedAt":"2026-09-01T01:48:30.830Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.3109/01658107.2011.585278","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.3109/01658107.2011.585278","authors":["Carmen K. M. Chan","Simon J. Hickman","Silvia Muñoz","John H. Pula","Matthieu P. Robert","Michael Vaphiades"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-07-28T01:52:32Z","doi":"10.3109/01658107.2011.585278","addedAt":"2026-09-01T01:48:30.830Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.21203/rs.3.rs-6296233/v1","name":"Harpy Eagle Optimization: Bio-Inspired Metaheuristic for Complex Problems","source":"crossref","abstract":"Abstract This paper presents Harpy Eagle Optimization (HEO), a novel bio-inspired metaheuristic algorithm modeled on the hunting strategies of Harpy Eagles ( Harpia harpyja ), renowned for their agility and precision in rainforests. HEO uses a dual-phase approach—global exploration through soaring and local exploitation via targeted dives—to tackle high-dimensional, non-convex, and multi-modal optimization problems common in engineering, machine learning, and industry. We compare HEO against 15 leading metaheuristics, including PSO, GA, GWO, DE, and HHO, across ten benchmark functions (e.g., Sphere, Rastrigin, Ackley) in dimensions d = 100,50,30,10. HEO excels, converging 40% faster than PSO (70 vs. 115 iterations to 6− 10 on Sphere), achieving a mean fitness of 0.00004 (vs. 0.001 for PSO), and a standard deviation below 0.00002. Wilcoxon (p &lt; 0.001) and Friedman (p &lt; 0.01) tests confirm its robustness. HEO cuts function evaluations by 28% compared to GA while matching PSO’s efficiency. Real-world tests highlight its impact: reducing truss weight by 16%, boosting feature selection accuracy by 8%, cutting scheduling makespan by 13%, and improving fog computing efficiency by 15%. Backed by a solid mathematical framework, extensive analysis, and an open-source Python code, HEO offers a powerful leap forward in optimization, aligning with JOTA ’s rigorous standards and Springer’s Q1 aspirations.","url":"https://doi.org/10.21203/rs.3.rs-6296233/v1","authors":["omid eslami"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-26T02:43:15Z","doi":"10.21203/rs.3.rs-6296233/v1","addedAt":"2026-09-01T01:48:30.830Z","updatedAt":"2026-09-01T01:48:30.830Z"},{"id":"doi:10.1088/2632-2153/ad51ca/v2/review1","name":"Review for \"Machine learning inspired models for Hall effects in non-collinear magnets\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2632-2153/ad51ca/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-30T17:17:15Z","doi":"10.1088/2632-2153/ad51ca/v2/review1","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1108/ilt-04-2021-0103/v2/review2","name":"Review for \"Low friction bio-inspired polydopamine/polytetrafluoroethylene coating performance in hydrodynamic bearings\"","source":"crossref","abstract":"","url":"https://doi.org/10.1108/ilt-04-2021-0103/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-30T16:01:57Z","doi":"10.1108/ilt-04-2021-0103/v2/review2","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1039/d5tc03546e/v1/review1","name":"Review for \"Biomimetic‐Inspired Honeycomb Architecture-Based Flexible Sensors: From Design to Applications\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5tc03546e/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-03T21:28:21Z","doi":"10.1039/d5tc03546e/v1/review1","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1108/ilt-04-2021-0103/v3/review1","name":"Review for \"Low friction bio-inspired polydopamine/polytetrafluoroethylene coating performance in hydrodynamic bearings\"","source":"crossref","abstract":"","url":"https://doi.org/10.1108/ilt-04-2021-0103/v3/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-30T16:01:57Z","doi":"10.1108/ilt-04-2021-0103/v3/review1","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1016/j.asoc.2024.111660","name":"Human-inspired similarity control system: Enhancing line-following robot perception","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2024.111660","authors":["Yukinobu Hoshino","Yuka Nishiyama","Toshimi Yamamoto","Yuki Shinomiya","Namal Rathnayake","Tuan Linh Dang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-04T02:11:27Z","doi":"10.1016/j.asoc.2024.111660","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1088/2053-1591/acf7b1/v2/review1","name":"Review for \"Recent Advances of Mussel-inspired Materials in Osteoarthritis Therapy\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2053-1591/acf7b1/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-08T17:01:11Z","doi":"10.1088/2053-1591/acf7b1/v2/review1","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.3109/01658107.2010.512608","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.3109/01658107.2010.512608","authors":["Carmen K. M. Chan","Simon J. Hickman","Silvia Muñoz","Matthieu P. Robert","Janet C. Rucker","Michael Vaphiades"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-01-16T19:36:19Z","doi":"10.3109/01658107.2010.512608","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1039/d5lc00476d/v1/review2","name":"Review for \"A hybrid flowing water-based energy generator inspired by rotatable waterwheel\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5lc00476d/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-21T21:06:31Z","doi":"10.1039/d5lc00476d/v1/review2","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1108/ilt-04-2021-0103/v3/review2","name":"Review for \"Low friction bio-inspired polydopamine/polytetrafluoroethylene coating performance in hydrodynamic bearings\"","source":"crossref","abstract":"","url":"https://doi.org/10.1108/ilt-04-2021-0103/v3/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-30T16:01:57Z","doi":"10.1108/ilt-04-2021-0103/v3/review2","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1039/d5ee01058f/v1/review3","name":"Review for \"Bio-inspired hormonic electrolyte: negative feedback for ultra-stable zinc anodes\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5ee01058f/v1/review3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-12T17:15:46Z","doi":"10.1039/d5ee01058f/v1/review3","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1039/d5ee01058f/v1/review1","name":"Review for \"Bio-inspired hormonic electrolyte: negative feedback for ultra-stable zinc anodes\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5ee01058f/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-12T17:15:46Z","doi":"10.1039/d5ee01058f/v1/review1","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1039/d5tc03546e/v2/review1","name":"Review for \"Biomimetic‐Inspired Honeycomb Architecture-Based Flexible Sensors: From Design to Applications\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5tc03546e/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-03T21:28:21Z","doi":"10.1039/d5tc03546e/v2/review1","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1039/d6mh00721j/v1/review1","name":"Review for \"Visco-Bits: Temporal-Coding-Inspired Viscoelastic Metamaterial for Mechanical Memory Expansion\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d6mh00721j/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-14T21:11:12Z","doi":"10.1039/d6mh00721j/v1/review1","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1080/01658107.2025.2583048","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.1080/01658107.2025.2583048","authors":["David A. Bellows","Wei-Che Hung","Andrew C. Y. Mak","Michael S. Vaphiades","Rashmi Verma","Xiaojun Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-02T16:54:24Z","doi":"10.1080/01658107.2025.2583048","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1039/d6cc00836d/v1/review2","name":"Review for \"Squaratides: A tunable platform for anion binding in peptide inspired macrocycles\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d6cc00836d/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-26T21:13:43Z","doi":"10.1039/d6cc00836d/v1/review2","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1201/9781003457152-3","name":"Resource Management in Cloud Using Nature-Inspired Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003457152-3","authors":["Pradeep Singh Rawat","Prateek Kumar Soni"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-22T19:39:33Z","doi":"10.1201/9781003457152-3","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1080/01658107.2018.1486060","name":"Neuro-ophthalmic literature review","source":"crossref","abstract":"","url":"https://doi.org/10.1080/01658107.2018.1486060","authors":["Noel Chan","John Chen","Hui-Chen Cheng","Peter MacIntosh","John H Pula","Michael Vaphiades","Konrad P Weber"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-07-13T03:35:11Z","doi":"10.1080/01658107.2018.1486060","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1039/d5lc00476d/v2/review1","name":"Review for \"A hybrid flowing water-based energy generator inspired by rotatable waterwheel\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5lc00476d/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-21T21:06:31Z","doi":"10.1039/d5lc00476d/v2/review1","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1039/d5ra02392k/v1/review1","name":"Review for \"Highly sensitive spider-slit-organ-inspired crack-based flexible temperature sensor\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5ra02392k/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-10T17:06:06Z","doi":"10.1039/d5ra02392k/v1/review1","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1108/ilt-04-2021-0103/v4/review2","name":"Review for \"Low friction bio-inspired polydopamine/polytetrafluoroethylene coating performance in hydrodynamic bearings\"","source":"crossref","abstract":"","url":"https://doi.org/10.1108/ilt-04-2021-0103/v4/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-30T16:01:57Z","doi":"10.1108/ilt-04-2021-0103/v4/review2","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1108/ilt-04-2021-0103/v2/review1","name":"Review for \"Low friction bio-inspired polydopamine/polytetrafluoroethylene coating performance in hydrodynamic bearings\"","source":"crossref","abstract":"","url":"https://doi.org/10.1108/ilt-04-2021-0103/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-30T16:01:57Z","doi":"10.1108/ilt-04-2021-0103/v2/review1","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1088/1361-6463/ad7a82/v2/response1","name":"Author response for \"Brain-inspired computing with self-assembled networks of nano-objects\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1361-6463/ad7a82/v2/response1","authors":["Vahl, Alexander","Milano, Gianluca","Kuncic, Zdenka","Brown, Simon A.","Milani, Paolo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-19T17:52:56Z","doi":"10.1088/1361-6463/ad7a82/v2/response1","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1088/1361-6463/ad7a82/v4/response1","name":"Author response for \"Brain-inspired computing with self-assembled networks of nano-objects\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1361-6463/ad7a82/v4/response1","authors":["Vahl, Alexander","Milano, Gianluca","Kuncic, Zdenka","Brown, Simon A.","Milani, Paolo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-19T17:52:56Z","doi":"10.1088/1361-6463/ad7a82/v4/response1","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1080/01658107.2017.1331656","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.1080/01658107.2017.1331656","authors":["David Bellows","Carmen Chan","John Chen","Panitha Jindahra","Rauan Kaiyrzhanov","Peter MacIntosh","John H. Pula","Michael Vaphiades"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-07-18T15:11:50Z","doi":"10.1080/01658107.2017.1331656","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1086/433821","name":"<i>An Experiment in Education; Also, the Ideas Which Inspired It and Were Inspired by It</i>. Mary R. Alling-Aber","source":"crossref","abstract":"","url":"https://doi.org/10.1086/433821","authors":["C. H. Thurber"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-07-08T20:22:50Z","doi":"10.1086/433821","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1002/2688-8319.12205/v2/review1","name":"Review for \"Building bridges for inspired action: On landscape restoration and social alliances\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/2688-8319.12205/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-19T16:04:33Z","doi":"10.1002/2688-8319.12205/v2/review1","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1098/rspa.2025.0489/v1/review2","name":"Review for \"Collective motion from quantum-inspired dynamics in visual perception\"","source":"crossref","abstract":"","url":"https://doi.org/10.1098/rspa.2025.0489/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-22T06:24:04Z","doi":"10.1098/rspa.2025.0489/v1/review2","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.3109/01658107.2014.969983","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.3109/01658107.2014.969983","authors":["Carmen K. M. Chan","Evan Price","John H. Pula","Matthieu Robert","Michael Vaphiades","An-Guor Wang","Sui Wong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-11-12T19:47:19Z","doi":"10.3109/01658107.2014.969983","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1016/j.asoc.2024.112304","name":"Hierarchical system in conflict scenarios constructed based on cluster analysis-inspired method for attribute significance determination","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2024.112304","authors":["Małgorzata Przybyła-Kasperek","Rafał Deja","Alicja Wakulicz-Deja"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-15T19:04:58Z","doi":"10.1016/j.asoc.2024.112304","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1039/d5ee01058f/v2/review1","name":"Review for \"Bio-inspired hormonic electrolyte: negative feedback for ultra-stable zinc anodes\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5ee01058f/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-12T17:15:46Z","doi":"10.1039/d5ee01058f/v2/review1","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1002/2688-8319.12205/v2/review2","name":"Review for \"Building bridges for inspired action: On landscape restoration and social alliances\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/2688-8319.12205/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-19T16:04:33Z","doi":"10.1002/2688-8319.12205/v2/review2","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1016/j.asoc.2008.01.010","name":"A framework for application of neuro-case-rule base hybridization in medical diagnosis","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2008.01.010","authors":["O.U. Obot","Faith-Michael E. Uzoka"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-04-21T08:33:10Z","doi":"10.1016/j.asoc.2008.01.010","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/978-981-19-6379-7_12","name":"Role of Nature-Inspired Intelligence in Genomic Diagnosis of Antimicrobial Resistance","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-19-6379-7_12","authors":["Priyanka Sharma","Geetika Sethi","Manish Kumar Tripathi","Shweta Rana","Harpreet Singh","Punit Kaur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-31T17:04:10Z","doi":"10.1007/978-981-19-6379-7_12","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.4018/979-8-3693-1131-8.ch004","name":"BIONET","source":"crossref","abstract":"Blockchain technology has revolutionized various industries, offering decentralized and tamper-resistant data storage and transaction capabilities. However, traditional consensus mechanisms, such as proof-of-work (PoW) and proof-of-stake (PoS), face energy consumption, scalability, and security challenges. This chapter proposes a novel consensus mechanism called “BIONET,” a bio-inspired neural network for blockchain systems. BIONET integrates the principles of swarm intelligence and artificial neural networks to achieve efficient, secure, and adaptive consensus in blockchain networks. The authors present the architectural overview of BIONET, highlighting its adaptability and self-organization capabilities. Furthermore, they demonstrate BIONET's effectiveness in PoW, PoS, and practical byzantine fault tolerance (PBFT) consensus mechanisms. Finally, they discuss the future directions and challenges of BIONET, paving the way for bio-inspired optimization techniques in blockchain systems.","url":"https://doi.org/10.4018/979-8-3693-1131-8.ch004","authors":["Ritesh Kumar Jain","Kamal Kant Hiran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-29T10:11:06Z","doi":"10.4018/979-8-3693-1131-8.ch004","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1039/d5lc00476d/v1/review1","name":"Review for \"A hybrid flowing water-based energy generator inspired by rotatable waterwheel\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5lc00476d/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-21T21:06:31Z","doi":"10.1039/d5lc00476d/v1/review1","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1002/2688-8319.12205/v1/review2","name":"Review for \"Building bridges for inspired action: On landscape restoration and social alliances\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/2688-8319.12205/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-19T16:04:33Z","doi":"10.1002/2688-8319.12205/v1/review2","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1088/2632-959x/add7f5/v1/review2","name":"Review for \"Bio inspired nanocontainers: intracellular delivery and controlled cargo release\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2632-959x/add7f5/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-14T17:10:09Z","doi":"10.1088/2632-959x/add7f5/v1/review2","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/ccaa.2017.8229865","name":"A Bee colony inspired clustering protocol for wireless sensor networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ccaa.2017.8229865","authors":["Zaheeruddin","Arana Pathak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-12-21T19:58:50Z","doi":"10.1109/ccaa.2017.8229865","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/ibica.2011.36","name":"A PSO Based Image Disguise Method","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ibica.2011.36","authors":["Shen Wang","Xiamu Niu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-01-06T16:44:03Z","doi":"10.1109/ibica.2011.36","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/bimnics.2007.4610070","name":"Welcome from the industry track co-chairs","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bimnics.2007.4610070","authors":["Mihaela Ulieru","Paul Marrow"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-09-08T16:06:46Z","doi":"10.1109/bimnics.2007.4610070","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/ispdc51135.2020.00017","name":"Evaluation of SIMD Instructions on Bio-Inspired Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ispdc51135.2020.00017","authors":["Natiele Lucca","Claudio Schepke"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-22T23:37:33Z","doi":"10.1109/ispdc51135.2020.00017","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/iscmi.2015.20","name":"Multi-objective Quantum-Inspired Cultural Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscmi.2015.20","authors":["Yi-nan Guo","Pei Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-02-25T16:22:18Z","doi":"10.1109/iscmi.2015.20","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/nabic.2009.5393683","name":"Genetic algorithm based reduction of electromagnetic field pollution","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2009.5393683","authors":["T. Rolich","D. Grundler"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-01-26T12:36:43Z","doi":"10.1109/nabic.2009.5393683","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1145/2980024.2872417","name":"Brain Inspired Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1145/2980024.2872417","authors":["R. Stanley Williams"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-07-29T18:44:37Z","doi":"10.1145/2980024.2872417","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.4018/978-1-59140-984-7.ch033","name":"Ant Colony Optimization and Multiple Knapsack Problem","source":"crossref","abstract":"The ant colony optimization algorithms and their applications on the multiple knapsack problem (MKP) are introduced. The MKP is a hard combinatorial optimization problem with wide application. Problems from different industrial fields can be interpreted as a knapsack problem including financial and other management. The MKP is represented by a graph, and solutions are represented by paths through the graph. Two pheromone models are compared: pheromone on nodes and pheromone on arcs of the graph. The MKP is a constraint problem which provides possibilities to use varied heuristic information. The purpose of the chapter is to compare a variety of heuristic and pheromone models and different variants of ACO algorithms on MKP.","url":"https://doi.org/10.4018/978-1-59140-984-7.ch033","authors":["S. Fidanova"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T13:17:52Z","doi":"10.4018/978-1-59140-984-7.ch033","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1007/bf00151247","name":"Interstitial chemotherapy for brain tumors: review","source":"crossref","abstract":"","url":"https://doi.org/10.1007/bf00151247","authors":["T. Tomita"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2004-11-06T00:48:16Z","doi":"10.1007/bf00151247","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1097/01.wno.0000381786.57261.61","name":"State-of-the-Art Review","source":"crossref","abstract":"","url":"https://doi.org/10.1097/01.wno.0000381786.57261.61","authors":["Randy H Kardon","Grant T Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-05-28T05:41:35Z","doi":"10.1097/01.wno.0000381786.57261.61","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/reconfig.2017.8279780","name":"Biologically inspired hierarchical structure for self-repairing FPGAs","source":"crossref","abstract":"","url":"https://doi.org/10.1109/reconfig.2017.8279780","authors":["David C. Keezer","Jingchi Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-02-05T22:32:24Z","doi":"10.1109/reconfig.2017.8279780","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/iccmc51019.2021.9418315","name":"Bat Inspired Technique for Effective Clustering in Wireless Sensor Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccmc51019.2021.9418315","authors":["B. Pitchaimanickam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-05-06T20:33:08Z","doi":"10.1109/iccmc51019.2021.9418315","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1039/d5ra02392k/v1/review2","name":"Review for \"Highly sensitive spider-slit-organ-inspired crack-based flexible temperature sensor\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5ra02392k/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-10T17:06:06Z","doi":"10.1039/d5ra02392k/v1/review2","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1039/d5ee01058f/v1/review2","name":"Review for \"Bio-inspired hormonic electrolyte: negative feedback for ultra-stable zinc anodes\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5ee01058f/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-12T17:15:46Z","doi":"10.1039/d5ee01058f/v1/review2","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1039/d6mh00721j/v1/review2","name":"Review for \"Visco-Bits: Temporal-Coding-Inspired Viscoelastic Metamaterial for Mechanical Memory Expansion\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d6mh00721j/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-14T21:11:12Z","doi":"10.1039/d6mh00721j/v1/review2","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.21203/rs.3.rs-776630/v1","name":"Application of Ultrasonography to Neuro-COVID-19","source":"crossref","abstract":"Abstract Neurological and psychiatric symptoms are frequently observed in COVID-19, the disease caused by severe acute respiratory syndrome-related coronavirus 2 (SARS-CoV-2), and the term \"Neuro-COVID-19\" has been coined to indicate the plethora of short- and long-term neurologic and psychiatric manifestations. In a significant percentage of cases, neuro-psychiatric symptoms persist after recovery and long-term sequelae have been reported. SARS-CoV-2 can infect the brain through different routes and the damage can be direct, that is due to the virus itself, or indirect, that is associated with abnormal immune responses, inflammation, and hypoxia. Studies of brain specimens obtained from autopsy demonstrated the presence of the virus in a minority of cases and this leads to hypothesize that SARS-CoV-2 may hide in sanctuary sites in the central nervous system in analogy with what observed for HIV. The existence of sanctuary sites for SARS-CoV-2 has the potential to decrease the efficacy of antiviral therapies or vaccination and may even prevent complete eradication of SARS-CoV-2 from the infected organism. In 2017, a diagnostic and therapeutic procedure was proposed with the goal of identifying and treating pathogens hiding in sanctuaries that elude diagnosis and therapy. This procedure is based on clinical evaluation, diagnostic ultrasonography, therapeutic ultrasounds, and laboratory analyses. Here, it is demonstrated that application of ultrasonography to Neuro-COVID-19 requires a specific adaptation that takes into account brain movements synchronous with breathing as well as the sensitivity of SARS-CoV-2 to ultrasounds.","url":"https://doi.org/10.21203/rs.3.rs-776630/v1","authors":["Marco Ruggiero"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-08-02T19:41:21Z","doi":"10.21203/rs.3.rs-776630/v1","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1039/d6mh00721j/v2/review1","name":"Review for \"Visco-Bits: Temporal-Coding-Inspired Viscoelastic Metamaterial for Mechanical Memory Expansion\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d6mh00721j/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-14T21:11:12Z","doi":"10.1039/d6mh00721j/v2/review1","addedAt":"2026-09-01T01:48:30.831Z","updatedAt":"2026-09-01T01:48:30.831Z"},{"id":"doi:10.1109/iitcee67948.2026.11394087","name":"A Privacy-Preserving Multimodal Smart Mirror with Edge AI, Blockchain Security and Quantum-Inspired Optimization for Personalized Wellness","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iitcee67948.2026.11394087","authors":["Harsha M S","Nischala G S","Prajwal H J","Smitha Gayathri D","Manonmaya Tandula S V","Nandish C"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-25T20:53:55Z","doi":"10.1109/iitcee67948.2026.11394087","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/978-3-032-16830-6_14","name":"Advancing Task Offloading in Autonomous Vehicles with Quantum-Inspired Techniques: A Review","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-16830-6_14","authors":["Mamta Kumari","Mayukh Sarkar","Rohit Kumar Nonia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-22T23:29:28Z","doi":"10.1007/978-3-032-16830-6_14","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1016/b978-0-443-33490-0.00002-8","name":"Headache classification","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-33490-0.00002-8","authors":["R. Silva-Néto","Kathleen B. Digre"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-01T00:48:11Z","doi":"10.1016/b978-0-443-33490-0.00002-8","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.55277/researchhub.ngisvjxl","name":"Neuro Serge Review 2026: My Honest Take After Trying It (Focus, Energy, Clarity)","source":"crossref","abstract":"","url":"https://doi.org/10.55277/researchhub.ngisvjxl","authors":["Al Hossain"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-26T20:01:01Z","doi":"10.55277/researchhub.ngisvjxl","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1145/3786168","name":"Proceedings of the 2026 IEEE/ACM 2nd International Workshop on Neuro-Symbolic Software Engineering","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3786168","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-18T07:42:51Z","doi":"10.1145/3786168","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.55277/researchhub.keltkrw8.1","name":"TÉLÉCHARGEMENTS Mon enfant neuro-atypique. Le guide pratique","source":"crossref","abstract":"","url":"https://doi.org/10.55277/researchhub.keltkrw8.1","authors":["Shaun Fernandez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-02T06:46:15Z","doi":"10.55277/researchhub.keltkrw8.1","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1093/neuped/wuag007","name":"Representation in global pediatric neuro-oncology publications: Insights into equity","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuped/wuag007","authors":["Sergio Licona","Margit K Mikkelsen","Ibrahim Qaddoumi","Daniel C Moreira"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-25T11:11:28Z","doi":"10.1093/neuped/wuag007","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1002/9781394355600.fmatter","name":"Front Matter","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9781394355600.fmatter","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-31T21:30:31Z","doi":"10.1002/9781394355600.fmatter","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1145/3807784","name":"Cross-Layer Design of Vector-Symbolic Computing: Bridging Cognition and Brain-Inspired Hardware Acceleration","source":"crossref","abstract":"Vector Symbolic Architectures (VSAs), also known as hyperdimensional (HD) computing, are increasingly deployed in cognitive applications due to their simple and efficient operations. The widespread adoption has, in turn, spurred the development of a diverse set of hardware solutions that optimize VSA performance for embedded and edge AI systems. Despite these advances, there remains a lack of comprehensive, unified discussion on the co-design and co-evolution of VSA algorithms and hardware. This survey aims at bridging that gap by linking theoretical, software-level explorations with efficient hardware architectures and emerging technology fabrics for VSAs, providing co-design insights that are accessible to both algorithm and hardware communities. First, we introduce the principles of vector-symbolic computing, including its core mathematical operations and learning paradigms. Second, we provide an in-depth discussion on hardware technologies for VSAs, analyzing analog, mixed-signal, and digital circuit design styles. We compare hardware implementations of VSAs by carrying out detailed analysis of their performance characteristics and tradeoffs, from which we distill design guidelines that are applicable across arbitrary VSA formulations. Third, we discuss a methodology for cross-layer design of VSAs that identifies synergies across layers and explores key ingredients for hardware/software co-design of VSAs. Finally, as a concrete case study of this methodology, we present an in-memory computing hardware design for VSA-based hierarchical cognition, illustrating how the proposed co-design principles translate into efficient architectures. The article concludes with a discussion of open research challenges and opportunities for future explorations.","url":"https://doi.org/10.1145/3807784","authors":["Shuting Du","Mohamed Ibrahim","Zishen Wan","Luqi Zheng","Boheng Zhao","Zhenkun Fan","Che-kai Liu","Tushar Krishna","Arijit Raychowdhury","Haitong Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-09T11:25:57Z","doi":"10.1145/3807784","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1093/neuonc/noag172.022","name":"54 Access to Prehabilitation in UK Neuro-Oncology: Insights from a UK-wide review of adult brain tumour services (2024-2026)","source":"crossref","abstract":"Abstract Background Prehabilitation aims to optimise physical, psychological and functional health prior to and during cancer treatment. While an increasing focus in neuro-oncology, little is known about its availability or structure across the United Kingdom (UK). Methods As part of the Tessa Jowell Centre of Excellence programme, workforce and service data were collected from 25 UK adult neuro-oncology centres (2024–2026), covering 90+% of the UK population. Responses were extracted from application forms and thematically analysed. Data were self-reported and validated through expert review. Results 17/25 centres (68%) reported involving allied health professionals (AHPs) to prepare patients for surgical/oncological treatment. Only 7 centres (28%) reported providing components of prehabilitation to all patients; a further 10 offered restricted access to specific subgroups (e.g. awake craniotomy, high-risk patients, or tumour subtypes). Service scope varied: 7 centres offered pre-surgical input only, 3 pre-oncology only, and 7 both. Of the 17 centres providing input, 9 delivered active intervention, while the remainder offered assessment alone. Prehabilitation was delivered by AHPs from multiple disciplines, most commonly occupational therapists (12 centres), physiotherapists (10), speech and language therapists (8), neuropsychologists (7) and dietitians (4). Assessment approaches ranged from comprehensive evaluation to clinic-based screening. Barriers were common: 9 centres reported funding and workforce constraints, 2 cited limited time before treatment initiation, and 2 highlighted insufficient data to support further service development. Despite variation, two-thirds of centres (15/25) reported active plans to establish or expand prehabilitation. Conclusions Access to neuro-oncology prehabilitation across the UK is inconsistent, with marked variation in eligibility, scope and workforce. Many services remain assessment-based or limited to specific patient groups. Data collection, workforce investment and clearer definitions may be required to ensure equitable and sustainable prehabilitation access.","url":"https://doi.org/10.1093/neuonc/noag172.022","authors":["Sara Melhuish","Nicola Peat","Andrew Wright","Camille Goetz","Nicky Huskens"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-27T10:02:31Z","doi":"10.1093/neuonc/noag172.022","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1177/29498732261469489","name":"Neuro-LENS: A Neuro-Symbolic Framework Integrating Incomplete Background Knowledge and Deep Learning","source":"crossref","abstract":"In this study, we propose Neuro-LENS, a neuro-symbolic evidence-based logic and symbolic reasoning framework that combines incomplete symbolic knowledge with neural learning to address ambiguity and improve the accuracy and interpretability of the results. We explore three strategies for integrating symbolic reasoning with deep learning and evaluate their effectiveness in practical settings: (i) applying the symbolic component to the neural output (neural-to-symbolic chaining); (ii) generating additional neural input features through symbolic rules (symbolic-to-neural chaining); (iii) creating an ensemble reasoning model (parallel neural-symbolic integration). The potential of the proposed Neuro-LENS framework is demonstrated on two real-world use cases: scene classification with abandoned object detection and prognostic health monitoring in vehicle failure prediction.","url":"https://doi.org/10.1177/29498732261469489","authors":["Giulia Murtas","Veselka Boeva","Elena Tsiporkova"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-24T13:39:45Z","doi":"10.1177/29498732261469489","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1109/icraset63057.2024.10895540","name":"Designing Neuro-Inspired Architectures for Efficient Signal Processing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icraset63057.2024.10895540","authors":["Paramjit Baxi","S Asha","Ashwini Ranjit Nawadkar","V. Dinesh Babu","Nimesh Raj","J Praveena"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-28T18:38:44Z","doi":"10.1109/icraset63057.2024.10895540","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.55277/researchhub.88ehj0li","name":"Best Apollo Neuro Coupon Code STOCKSPROM Save $100","source":"crossref","abstract":"","url":"https://doi.org/10.55277/researchhub.88ehj0li","authors":["Discount Radar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-15T21:50:05Z","doi":"10.55277/researchhub.88ehj0li","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/978-3-032-05988-8_300343","name":"Low Inspired Oxygen (O2) Pressure","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-05988-8_300343","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-12T14:15:25Z","doi":"10.1007/978-3-032-05988-8_300343","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.55277/researchhub.5dxm2qef","name":"Neuro Energizer Review 2026 - Does This 7-Second Brain Program Trick Really Work?","source":"crossref","abstract":"","url":"https://doi.org/10.55277/researchhub.5dxm2qef","authors":["Dn Roney"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-26T17:14:48Z","doi":"10.55277/researchhub.5dxm2qef","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1201/9781003682950-7","name":"Quantum-Inspired Approaches to Computer Vision: Current State and Future Prospects","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003682950-7","authors":["Sara Ali","Polla Fattah","Sanar Fawzi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-20T12:40:36Z","doi":"10.1201/9781003682950-7","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1016/j.pnpbp.2026.111801","name":"Emerging cell death in depression: Mechanisms and therapeutic implications","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.pnpbp.2026.111801","authors":["Chuang Jin","Yuhui Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-24T23:21:41Z","doi":"10.1016/j.pnpbp.2026.111801","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/s11060-025-05380-8","name":"SEER-Medicaid and SEER-Medicare data for neuro-oncology research","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11060-025-05380-8","authors":["Kimberly J. Johnson","Derek S. Brown","Kenton J. Johnston"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-10T15:24:59Z","doi":"10.1007/s11060-025-05380-8","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1080/01658107.2025.2486757","name":"Neuro-Ophthalmic Manifestations of Suprasellar Pilomyxoid Astrocytoma","source":"crossref","abstract":"","url":"https://doi.org/10.1080/01658107.2025.2486757","authors":["Nicholas Panzo","Pamela Davila Siliezar","Noor Noor Laylani","Hamza Memon","Andrew G. Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-30T23:06:27Z","doi":"10.1080/01658107.2025.2486757","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1109/icaect68478.2026.11426018","name":"Deep Learning-Driven Neuro-Pedagogical Interface for Real-Time Brainwave-Adaptive Teaching in Immersive Learning Environments","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icaect68478.2026.11426018","authors":["Abhishek Kumar Mishra","Sai Kumar Reddy Nossam","Mylavarapu Kalyan Ram","Preeti Y Shadangi","S.Suresh Kumar","B.Anitha Vijayalakshmi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-13T19:51:30Z","doi":"10.1109/icaect68478.2026.11426018","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1093/neuonc/noag084","name":"Expanding the scope of collective responsibility in neuro-oncology: The integrity of the published record","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuonc/noag084","authors":["Timothy Daly","Jaime A Teixeira da Silva"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-22T11:50:03Z","doi":"10.1093/neuonc/noag084","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1080/17590914.2026.2673257","name":"CD44 Knockout Alters the Cellular Response and Improves Locomotor Outcome After Spinal Cord Injury","source":"crossref","abstract":"","url":"https://doi.org/10.1080/17590914.2026.2673257","authors":["Dana Creasman","Francisca Benavente","Rebecca Nishi","Aileen Anderson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-27T13:07:06Z","doi":"10.1080/17590914.2026.2673257","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1109/nice61972.2024.10549632","name":"Biological Dynamics Enabling Training of Binary Recurrent Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nice61972.2024.10549632","authors":["G. William Chapman","Corinne Teeter","Sapan Agarwal","T. Patrick Xiao","Park Hays","Srideep S. Musuvathy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-11T17:30:32Z","doi":"10.1109/nice61972.2024.10549632","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.2139/ssrn.5025543","name":"Advancements in Neuromorphic Computing for Bio-Inspired Artificial Vision: A Review","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5025543","authors":["Sharmarke Gabayre","Varuna De Silva","Mindula Illeperuma","Xiyu Shi","Sergey Savel’ev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-19T04:41:22Z","doi":"10.2139/ssrn.5025543","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-981-99-4590-0_5","name":"Implementation of Dew-Inspired Matrix-Mesh Communication Protocol","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-99-4590-0_5","authors":["Minhajur Rahman","Yingwei Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-02T08:02:01Z","doi":"10.1007/978-981-99-4590-0_5","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1063/5.0306671","name":"Imitating neuro-plasticity in SrTiO3 based synaptic optoelectronic memristor for in-memory computing applications","source":"crossref","abstract":"Recently, perovskite oxide-based synaptic optoelectronic memristors (SOMs) present a favorable path toward the advancement of neuromorphic (or in-memory) computing. In this study, we propose a SrTiO3 (STO) functional layer-based simple and transparent two-terminal memristor device stacked with ITO/STO/ITO/glass, which shows improved resistive switching behavior after post-oxide nitrogen annealing treatment at 300 °C. The annealed device shows more stable resistive switching characteristics compared to the unannealed device, with a low set voltage (+0.9 V) and an enhanced memory window (∼35). The presence of nitrogen in the STO layer assists in confining the conductive filament path, which helps to enhance the device's uniformity and stability. The device successfully imitates key biological synaptic behaviors, such as long-term potentiation/depression, paired pulse facilitaion (PPF), and spike timing-dependent plasticity. In addition, artificial neural network models with convolutional layers and vision transformer architectures are simulated for image classification tasks on the extended- and fashion-modified National Institute of Standards and Technology datasets with ∼88% and ∼83% accuracy, respectively. The same device was illuminated with violet light (wavelength: 405 nm) at 40 mW/cm2 and produced the excitatory postsynaptic current response that gradually decayed under a dark environment. The exposure conditions are adjusted to simulate short- to long-term memory transition, optical PPF, and image sharpening functions. Along with the learning phase, the impact of illumination is also analyzed on the forgetting (or memory) phase of the current response, which is further utilized for simulating the image memory function. These findings emphasize the remarkable potential of the STO-based SOM for use in in-memory computing applications.","url":"https://doi.org/10.1063/5.0306671","authors":["Phan Ai Linh Uong","Stephen Ekaputra Limantoro","Saransh Shrivastava","Hans Juliano","Tseung-Yuen Tseng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-09T17:14:46Z","doi":"10.1063/5.0306671","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.36871/26189976.2026.03-4.005","name":"NEURO-FUZZY MODELS OF BUILDING THERMAL INERTIA IN ADAPTIVE CONTROL PROBLEMS OF HEATING AND AIR CONDITIONING SYSTEMS","source":"crossref","abstract":"This article examines the problem of constructing a neurofuzzy model of building thermal inertia for use in adaptive control loops of heating and air conditioning systems. It is shown that the thermal dynamics of building envelopes and interior volumes are characterized by pronounced nonlinearity, parametric uncertainty, and time variability, which limits the applicability of traditional lumped thermal physics models. An approach is proposed that combines fuzzy representations of expert knowledge about the thermal state of an object with the capabilities of neural network parametric tuning. The model structure, input and output variables, fuzzification mechanism, rule identification procedure, and inclusion of the model in a predictive-adaptive control algorithm are discussed. The advantages of the approach in terms of robustness, interpretability, and energy efficiency are substantiated.","url":"https://doi.org/10.36871/26189976.2026.03-4.005","authors":["Airat L. Osipov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-30T11:14:32Z","doi":"10.36871/26189976.2026.03-4.005","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1007/978-3-032-36766-2_4","name":"Detecting Adaptive Wash Trading Behaviors in NFT Marketplaces: A Neuro-Symbolic Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-36766-2_4","authors":["Shamsun Nahar Shatabdy","Rabiul Islam Raihan","Razib Hayat Khan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-28T12:13:02Z","doi":"10.1007/978-3-032-36766-2_4","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.4018/979-8-3693-6303-4.ch001","name":"Introduction to Neuromorphic Computing","source":"crossref","abstract":"Neuromorphic computing is an innovative and fast-evolving field poised to significantly impact human life in the coming decades. By emulating the brain's neural architecture using modern electronic systems, it aims to enhance computer architectures and revolutionize computing and machine learning tasks. Neuromorphic systems transcend traditional computing paradigms by integrating memory and computation in a massively parallel fashion, unlocking unprecedented computational efficiency and performance. This approach promises breakthroughs in pattern recognition, natural language processing, and autonomous decision-making. Additionally, neuromorphic computing could advance electronics and biology integration, leading to innovations like brain-computer interfaces and neuroprosthetic devices that revolutionize healthcare and human augmentation.","url":"https://doi.org/10.4018/979-8-3693-6303-4.ch001","authors":["Supriya Amol Londhe","Sunayana Kundan Shivthare","YogeshKumar Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-29T15:16:27Z","doi":"10.4018/979-8-3693-6303-4.ch001","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1109/nice61972.2024.10548709","name":"jaxsnn: Event-driven Gradient Estimation for Analog Neuromorphic Hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nice61972.2024.10548709","authors":["Eric Müller","Moritz Althaus","Elias Arnold","Philipp Spilger","Christian Pehle","Johannes Schemmel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-11T17:30:32Z","doi":"10.1109/nice61972.2024.10548709","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1093/nsr/nwae144","name":"Human brain computing and brain-inspired intelligence","source":"crossref","abstract":"","url":"https://doi.org/10.1093/nsr/nwae144","authors":["Jianfeng Feng","Viktor Jirsa","Wenlian Lu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-19T12:09:05Z","doi":"10.1093/nsr/nwae144","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1002/9781394409730.ch16","name":"Nature‐Inspired Hybrid Model for Dysgraphia Diagnosis in Educational Settings","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9781394409730.ch16","authors":["A. Devi","B. Elizebeth Caroline","J. Vidhya","D. Sathish Kumar","T.D. Subha","L. Manimegalai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-28T21:21:21Z","doi":"10.1002/9781394409730.ch16","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1080/01658107.2026.2620605","name":"Congenital Optic Tract Hypoplasia","source":"crossref","abstract":"","url":"https://doi.org/10.1080/01658107.2026.2620605","authors":["Moamen Masalha","Hadas Stiebel-Kalish","Omer Y. Bialer"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-03T13:30:35Z","doi":"10.1080/01658107.2026.2620605","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:30.845Z"},{"id":"doi:10.1016/bs.adcom.2023.11.011","name":"Overview of nonlinear interval optimization problems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/bs.adcom.2023.11.011","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-20T23:57:51Z","doi":"10.1016/bs.adcom.2023.11.011","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1016/j.suscom.2023.100947","name":"IoT-digital twin-inspired smart irrigation approach for optimal water utilization","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.suscom.2023.100947","authors":["Ankush Manocha","Sandeep Kumar Sood","Munish Bhatia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-09T21:29:03Z","doi":"10.1016/j.suscom.2023.100947","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-031-27499-2_81","name":"Attempt to Model the Impact of Digitalization on the Economic Growth of Morocco","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-27499-2_81","authors":["Rhaya Fikry","El Ouazzani Yahia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T19:03:17Z","doi":"10.1007/978-3-031-27499-2_81","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1109/bic-ta.2011.41","name":"P Systems with 2D Picture Grammars","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bic-ta.2011.41","authors":["Tao Song","Xiangxiang Zeng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-10-18T11:35:51Z","doi":"10.1109/bic-ta.2011.41","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.4018/ijamc.2018010105","name":"A Modified Bio Inspired","source":"crossref","abstract":"Metaheuristics algorithms are becoming powerful methods for solving many problems of market analysis, data mining, transportation, medical etc. The concept of BAT algorithm, particle swarm optimization, artificial bee colony optimization, cuckoo search, firefly algorithm and harmony search are powerful methods for solving many optimization problems. Here, an effort has been made to propose as modified form of the BAT algorithm based natural echolocation behaviour of bats to solve the optimization problems. The algorithm is also compared other 15 existing benchmark algorithms including statistical methods on five benchmarks data sets. Furthermore, modified BAT algorithm has outperformed the other algorithm in term of robustness and efficiency. The optimality of the algorithm has been also crosscheck with residual analysis and chi (χ2) square testing.","url":"https://doi.org/10.4018/ijamc.2018010105","authors":["Dharmpal Singh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-11-15T10:05:50Z","doi":"10.4018/ijamc.2018010105","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.4018/978-1-59904-002-8.ch011","name":"Bio-Inspired Approach for the Next Generation of Cellular Systems","source":"crossref","abstract":"In the current 3G systems and the upcoming 4G wireless systems, missing neighbor pilot refers to the condition of receiving a high-level pilot signal from a Base Station (BS) that is not listed in the mobile receiver’s neighbor list (LCC International, 2004; Agilent Technologies, 2005). This pilot signal interferes with the existing ongoing call, causing the call to be possibly dropped and increasing the handoff call dropping probability. Figure 1 describes the missing pilot scenario where BS1 provides the highest pilot signal compared to BS1 and BS2’s signals. Unfortunately, this pilot is not listed in the mobile user’s active list. The horizontal and vertical handoff algorithms are based on continuous measurements made by the user equipment (UE) on the Primary Scrambling Code of the Common Pilot Channel (CPICH). In 3G systems, UE attempts to measure the quality of all received CPICH pilots using the Ec/Io and picks a dominant one from a cellular system (Chiung &amp; Wu, 2001; El-Said, Kumar, &amp; Elmaghraby, 2003). The UE interacts with any of the available radio access networks based on its memorization to the neighboring BSs. As the UE moves throughout the network, the serving BS must constantly update it with neighbor lists, which tell the UE which CPICH pilots it should be measuring for handoff purposes. In 4G systems, CPICH pilots would be generated from any wireless system including the 3G systems (Bhashyam, Sayeed, &amp; Aazhang, 2000). Due to the complex heterogeneity of the 4G radio access network environment, the UE is expected to suffer from various carrier interoperability problems. Among these problems, the missing neighbor pilot is considered to be the most dangerous one that faces the 4G industry. The wireless industry responded to this problem by using an inefficient traditional solution relying on using antenna downtilt such as given in Figure 2. This solution requires shifting the antenna’s radiation pattern using a mechanical adjustment, which is very expensive for the cellular carrier. In addition, this solution is permanent and is not adaptive to the cellular network status (Agilent Technologies, 2005; Metawave, 2005).Therefore, a self-managing solution approach is necessary to solve this critical problem. Whisnant, Kalbarczyk, and Iyer (2003) introduced a system model for dynamically reconfiguring application software. Their model relies on considering the application’s static structure and run-time behaviors to construct a workable version of reconfiguration software application. Self-managing applications are hard to test and validate because they increase systems complexity (Clancy, 2002). The ability to reconfigure a software application requires the ability to deploy a dynamically hardware infrastructure in systems in general and in cellular systems in particular (Jann, Browning, &amp; Burugula, 2003).","url":"https://doi.org/10.4018/978-1-59904-002-8.ch011","authors":["M. El-Said"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-05-24T12:45:56Z","doi":"10.4018/978-1-59904-002-8.ch011","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1109/nabic.2013.6617853","name":"Evolution of the weight vectors in Mahjong non-player characters","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nabic.2013.6617853","authors":["Hisashi Handa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-10-10T19:27:30Z","doi":"10.1109/nabic.2013.6617853","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1142/9789812790262_0013","name":"UNDERSTANDING THE BRAIN TO BUILD INTELLIGENT SYSTEMS","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789812790262_0013","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-04-12T00:09:25Z","doi":"10.1142/9789812790262_0013","addedAt":"2026-09-01T01:48:30.845Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1088/2053-1591/acf7b1/v1/review1","name":"Review for \"Recent Advances of Mussel-inspired Materials in Osteoarthritis Therapy\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2053-1591/acf7b1/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-08T17:01:11Z","doi":"10.1088/2053-1591/acf7b1/v1/review1","addedAt":"2026-09-01T01:48:31.301Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.21203/rs.3.rs-7982569/v1","name":"Intelligent Tuning of PID Parameters Using Nature-Inspired Algorithms","source":"crossref","abstract":"Abstract This paper proposes the application of both the Firefly Algorithm (FA) and Particle Swarm Optimization (PSO) for tuning the PID controller parameters of first-, second-, and third-order dynamic systems. FA is distinguished by its simplicity, stable convergence behavior, and superior computational efficiency. Inspired by the bioluminescent behavior of fireflies, the Firefly Algorithm is a well-established meta-heuristic optimization technique [1]. In this study, FA’s performance is benchmarked against the widely used PSO method [2]. Simulation results show that FA yields slightly better improvements in step-response metrics—namely rise time, settling time, and overshoot - while PSO can attain lower fitness values in some scenarios. FA demonstrates the ability to quickly and reliably optimize controller parameters, even for complex system models [3]. Detailed analyses across multiple test cases confirm that FA not only excels at parameter optimization but also provides enhanced stability and robustness in controller design. PSO, on the other hand, sometimes achieves marginally lower fitness values, indicating its potential for fine-tuning in specific cases. This work highlights the applicability of both FA and PSO in academic and industrial control-system design, emphasizing each method’s strengths and trade-offs.","url":"https://doi.org/10.21203/rs.3.rs-7982569/v1","authors":["Ibrahim Mammadov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-31T04:53:03Z","doi":"10.21203/rs.3.rs-7982569/v1","addedAt":"2026-09-01T01:48:31.301Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1088/2632-2153/ad51ca/v1/review1","name":"Review for \"Machine learning inspired models for Hall effects in non-collinear magnets\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2632-2153/ad51ca/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-30T17:17:15Z","doi":"10.1088/2632-2153/ad51ca/v1/review1","addedAt":"2026-09-01T01:48:31.301Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1039/d6cc00836d/v2/review1","name":"Review for \"Squaratides: A tunable platform for anion binding in peptide inspired macrocycles\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d6cc00836d/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-26T21:13:43Z","doi":"10.1039/d6cc00836d/v2/review1","addedAt":"2026-09-01T01:48:31.301Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1097/00041327-199809000-00014","name":"Ocular Motility Review 1996","source":"crossref","abstract":"","url":"https://doi.org/10.1097/00041327-199809000-00014","authors":["Eric R. Eggenberger","David I. Kaufman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-31T06:42:29Z","doi":"10.1097/00041327-199809000-00014","addedAt":"2026-09-01T01:48:31.301Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1080/01658107.2016.1214457","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.1080/01658107.2016.1214457","authors":["Carmen Chan","John Chen","Peter MacIntosh","Matthieu Robert","Evan Price","John H. Pula","Michael Vaphiades","An-Guor Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-08-11T19:06:39Z","doi":"10.1080/01658107.2016.1214457","addedAt":"2026-09-01T01:48:31.301Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1080/01658107.2019.1653059","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.1080/01658107.2019.1653059","authors":["David Bellows","Noel Chan","John Chen","Hui-Chen Cheng","Peter MacIntosh","Jenny Nij Bijvank","Michael Vaphiades","Konrad Weber"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-10-29T23:38:53Z","doi":"10.1080/01658107.2019.1653059","addedAt":"2026-09-01T01:48:31.301Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1080/01658107.2023.2169555","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.1080/01658107.2023.2169555","authors":["David A. Bellows","John J. Chen","Hui-Chen Cheng","Panitha Jindahra","Collin McClelland","Michael S. Vaphiades","Xiaojun Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-02T17:06:49Z","doi":"10.1080/01658107.2023.2169555","addedAt":"2026-09-01T01:48:31.301Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1088/1748-3190/ad839f/v1/review2","name":"Review for \"One-shot manufacturable soft-robotic pump inspired by embryonic tubular heart\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1748-3190/ad839f/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-05T17:13:42Z","doi":"10.1088/1748-3190/ad839f/v1/review2","addedAt":"2026-09-01T01:48:31.301Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1002/2688-8319.12205/v1/review1","name":"Review for \"Building bridges for inspired action: On landscape restoration and social alliances\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/2688-8319.12205/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-19T16:04:33Z","doi":"10.1002/2688-8319.12205/v1/review1","addedAt":"2026-09-01T01:48:31.301Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1039/d5ra02392k/v2/review1","name":"Review for \"Highly sensitive spider-slit-organ-inspired crack-based flexible temperature sensor\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5ra02392k/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-10T17:06:06Z","doi":"10.1039/d5ra02392k/v2/review1","addedAt":"2026-09-01T01:48:31.301Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.3109/01658107.2014.912052","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.3109/01658107.2014.912052","authors":["Carmen K. M. Chan","Axel Petzold","Evan Price","John H. Pula","Matthieu Robert","Michael Vaphiades","An-Guor Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-05-14T14:25:08Z","doi":"10.3109/01658107.2014.912052","addedAt":"2026-09-01T01:48:31.301Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.3109/01658107.2010.499216","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.3109/01658107.2010.499216","authors":["Carmen K. M. Chan","Simon J. Hickman","Silvia Muñoz","Matthieu P. Robert","Janet C. Rucker","Michael Vaphiades"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-10-15T11:01:36Z","doi":"10.3109/01658107.2010.499216","addedAt":"2026-09-01T01:48:31.301Z","updatedAt":"2026-09-01T01:48:31.301Z"},{"id":"doi:10.1080/01658107.2025.2479977","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.1080/01658107.2025.2479977","authors":["David A. Bellows","Wei-Che Hung","Andrew C. Y. Mak","Michael S. Vaphiades","Rashmi Verma","Jim Shenchu Xie"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-04T11:41:29Z","doi":"10.1080/01658107.2025.2479977","addedAt":"2026-09-01T01:48:31.302Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1039/d6cc00836d/v1/review1","name":"Review for \"Squaratides: A tunable platform for anion binding in peptide inspired macrocycles\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d6cc00836d/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-26T21:13:43Z","doi":"10.1039/d6cc00836d/v1/review1","addedAt":"2026-09-01T01:48:31.302Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1039/d5ra02392k/v3/review1","name":"Review for \"Highly sensitive spider-slit-organ-inspired crack-based flexible temperature sensor\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5ra02392k/v3/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-10T17:06:06Z","doi":"10.1039/d5ra02392k/v3/review1","addedAt":"2026-09-01T01:48:31.302Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1891/9780826168535.0008","name":"Neuro-Ophthalmology","source":"crossref","abstract":"","url":"https://doi.org/10.1891/9780826168535.0008","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-12-04T17:35:29Z","doi":"10.1891/9780826168535.0008","addedAt":"2026-09-01T01:48:31.302Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.21203/rs.3.rs-776630/v2","name":"Application of Ultrasonography to Neuro-COVID-19","source":"crossref","abstract":"Abstract Aim: The aim of this study is to evaluate the role of ultrasonography in diagnosis and treatment of COVID-19, the disease caused by severe acute respiratory syndrome-related coronavirus 2 (SARS-CoV-2), with particular reference to the symptoms that are frequently observed in Neuro-COVID-19, a term that indicates the plethora of short- and long-term neurologic and psychiatric manifestations caused by, or associated with the disease. In a significant percentage of cases, neuro-psychiatric symptoms persist after recovery and long-term sequelae have been reported. SARS-CoV-2 can infect the brain through different routes and the damage can be direct, that is due to the virus itself, or indirect, that is associated with abnormal immune responses, inflammation, and hypoxia. Methods: In this study, the brain was studied by transcranial ultrasonography. Analysis of brain specimens obtained from autopsy demonstrated the presence of the virus in a minority of cases and this leads to hypothesize that SARS-CoV-2 may hide in sanctuary sites in the central nervous system in analogy with what observed for HIV. The existence of sanctuary sites for SARS-CoV-2 has the potential to decrease the efficacy of antiviral therapies or vaccination and may even prevent complete eradication of SARS-CoV-2 from the infected organism. Results: Transcranial ultrasonography demonstrated significant movements of the brain associated with the respiratory cycle. In 2017, a diagnostic and therapeutic procedure was proposed with the goal of identifying and treating pathogens hiding in sanctuaries that elude diagnosis and therapy. This procedure is based on clinical evaluation, diagnostic ultrasonography, therapeutic ultrasounds, and laboratory analyses. Conclusions: Here, it is demonstrated that application of transcranial ultrasonography to Neuro-COVID-19 requires a specific adaptation that takes into account brain movements synchronous with breathing as well as the sensitivity of SARS-CoV-2 to ultrasounds.","url":"https://doi.org/10.21203/rs.3.rs-776630/v2","authors":["Marco Ruggiero"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-08-24T03:09:57Z","doi":"10.21203/rs.3.rs-776630/v2","addedAt":"2026-09-01T01:48:31.302Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.3109/01658107.2016.1166813","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.3109/01658107.2016.1166813","authors":["Panitha Jindahra","Axel Petzold","Evan Price","Matthieu Robert","Michael Vaphiades","An-Guor Wang","Sui Wong","John H. Pula"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-04-11T11:16:36Z","doi":"10.3109/01658107.2016.1166813","addedAt":"2026-09-01T01:48:31.302Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1080/01658107.2017.1311137","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.1080/01658107.2017.1311137","authors":["Carmen Chan","John Chen","Rauan Kaiyrzhanov","Peter MacIntosh","Axel Petzold","John Pula","Matthieu Robert","Michael Vaphiades","An-Guor Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-04-25T16:18:07Z","doi":"10.1080/01658107.2017.1311137","addedAt":"2026-09-01T01:48:31.302Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1097/00041327-199806000-00012","name":"Annual Review of Systemic Disease-1997-II","source":"crossref","abstract":"","url":"https://doi.org/10.1097/00041327-199806000-00012","authors":["Paul Lama","Larry Frohman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-31T06:50:40Z","doi":"10.1097/00041327-199806000-00012","addedAt":"2026-09-01T01:48:31.302Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1080/01658107.2016.1238725","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.1080/01658107.2016.1238725","authors":["Carmen Chan","John Chen","Peter MacIntosh","Axel Petzold","Evan Price","John Pula","Michael Vaphiades","An-Guor Wang","Sui Wong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-11-01T18:39:46Z","doi":"10.1080/01658107.2016.1238725","addedAt":"2026-09-01T01:48:31.302Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1080/01658107.2024.2305573","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.1080/01658107.2024.2305573","authors":["David A. Bellows","Noel C.Y. Chan","John J. Chen","Hui-Chen Cheng","Collin McClelland","Michael S. Vaphiades","Xiaojun Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-11T18:43:09Z","doi":"10.1080/01658107.2024.2305573","addedAt":"2026-09-01T01:48:31.302Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1093/neuonc/nou253.13","name":"ED-13 * POSTTRAUMATIC GLIOMA: LITERATURE REVIEW","source":"crossref","abstract":"","url":"https://doi.org/10.1093/neuonc/nou253.13","authors":["K. Kurako","V. Kurako","E. Salgado"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-11-03T10:58:09Z","doi":"10.1093/neuonc/nou253.13","addedAt":"2026-09-01T01:48:31.302Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/bf00165486","name":"Brain metastases: 1995. A brief review","source":"crossref","abstract":"","url":"https://doi.org/10.1007/bf00165486","authors":["Jerome B. Posner"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2004-11-06T01:31:29Z","doi":"10.1007/bf00165486","addedAt":"2026-09-01T01:48:31.302Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1177/1759091416651511","name":"Zinc in Multiple Sclerosis","source":"crossref","abstract":"","url":"https://doi.org/10.1177/1759091416651511","authors":["Mikkel Bredholt","Jette Lautrup Frederiksen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-06-10T01:23:33Z","doi":"10.1177/1759091416651511","addedAt":"2026-09-01T01:48:31.302Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-030-41862-5_165","name":"Review on Spectrum Sharing Approaches Based on Fuzzy and Machine Learning Techniques in Cognitive Radio Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-41862-5_165","authors":["Abdul Sikkandhar Rahamathullah","Merline Arulraj","Guruprakash Baskaran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-27T14:02:38Z","doi":"10.1007/978-3-030-41862-5_165","addedAt":"2026-09-01T01:48:31.302Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1080/01658107.2021.1877990","name":"Neuro-Ophthalmic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.1080/01658107.2021.1877990","authors":["David A. Bellows","Noel C.Y. Chan","John J. Chen","Hui-Chen Cheng","Jenny A. Nij Bijvank","Michael S. Vaphiades"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-08T23:35:11Z","doi":"10.1080/01658107.2021.1877990","addedAt":"2026-09-01T01:48:31.302Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-78946-5_31","name":"Blockchain Technology in Healthcare: Unifying Patient Medical Records - A Survey","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78946-5_31","authors":["Sudip Phuyal","Luís B. Elvas","João C. Ferreira","Rabindra Bista"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-26T03:04:08Z","doi":"10.1007/978-3-031-78946-5_31","addedAt":"2026-09-01T01:48:31.302Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-78943-4_2","name":"Combinatorial Optimization: Application and Comparison of Metaheuristic on Continuous Optimization Problem TSP","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78943-4_2","authors":["Khaoula Cherrat","Mohammed Essaid Riffi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-03T11:08:17Z","doi":"10.1007/978-3-031-78943-4_2","addedAt":"2026-09-01T01:48:31.302Z","updatedAt":"2026-09-01T01:48:31.302Z"},{"id":"doi:10.1007/978-3-031-77392-1_9","name":"An Epithelium-Inspired Deformation Modeling Framework for 4D Sheets","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-77392-1_9","authors":["Joel Pepper","David E. Breen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-21T18:26:45Z","doi":"10.1007/978-3-031-77392-1_9","addedAt":"2026-09-01T01:48:31.441Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1016/b978-0-443-15684-7.00018-x","name":"Molecularly imprinted polymers","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-15684-7.00018-x","authors":["Semra Akgönüllü","Adil Denizli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-01T11:42:39Z","doi":"10.1016/b978-0-443-15684-7.00018-x","addedAt":"2026-09-01T01:48:31.441Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-981-96-3216-9_7","name":"Optimum Solution for System Stability of Interconnected Power Grid Using Hybrid Genetic Firefly Algorithm Optimized PID Controller","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-96-3216-9_7","authors":["D. Boopathi","K. Jagatheesan","Sourav Samanta","Kanendra Naidu","B. Anand"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T18:27:38Z","doi":"10.1007/978-981-96-3216-9_7","addedAt":"2026-09-01T01:48:31.441Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-981-96-9585-0_19","name":"Virtual Machine Migration Algorithm for Energy Consumption Optimization","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-96-9585-0_19","authors":["Yichuan Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-22T09:23:39Z","doi":"10.1007/978-981-96-9585-0_19","addedAt":"2026-09-01T01:48:31.441Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.21203/rs.3.rs-6504704/v1","name":"Bio-Inspired Parallel Error Correction (BPEC): A Transformer-Based AI Algorithm for Robust Space Navigation via DNA-Inspired Consensus Mechanisms","source":"crossref","abstract":"Abstract We propose a novel Bio-Inspired Parallel Error Correction (BPEC) algorithm for spacecraft navigation, which integrates DNA-inspired redundancy mechanisms with transformer-based neural architectures to address the challenges of sensor noise and environmental perturbations in space missions. The core innovation lies in modeling redundant sensor inputs as parallel strands, analogous to biological data fidelity, and employing a masked self-attention mechanism to resolve discrepancies dynamically. The proposed method transforms raw sensor measurements into polarized representations, then processes them through a multi-head self-attention layer to achieve consensus, mimicking DNA repair mechanisms. Furthermore, a neural feedback controller adjusts navigation parameters in real-time, ensuring stability under high-noise conditions. The architecture interfaces seamlessly with conventional navigation systems, replacing traditional Kalman filters and PID controllers while offering inherent fault tolerance. Implemented as a sparse mixture-of-experts network, the system specializes in distinct error modes, such as gyroscopic drift or star tracker occlusion, thereby adapting to diverse mission scenarios. Mathematical analysis demonstrates bounded error propagation, a critical property for robustness in deep-space environments. BPEC represents a significant departure from classical approaches, combining bio-inspired parallelism with modern AI techniques to deliver unprecedented resilience in autonomous space navigation. Experimental validation confirms its superiority over state-of-the-art methods, particularly in scenarios with sensor noise exceeding (33 σ ) thresholds. The algorithm's adaptability and scalability make it a promising candidate for future interplanetary missions, where reliability and autonomy are paramount.","url":"https://doi.org/10.21203/rs.3.rs-6504704/v1","authors":["xiaochen xiao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-23T04:38:34Z","doi":"10.21203/rs.3.rs-6504704/v1","addedAt":"2026-09-01T01:48:31.441Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1093/noajnl/vdaf213.116","name":"SVSC-03 Challenges in Managing Neuro-Oncology Patients Without Health Insurance: A Case Study of Kenya and Uganda","source":"crossref","abstract":"Abstract Access to timely and comprehensive neuro-oncology care remains a significant challenge in East Africa, where health insurance coverage is limited, and out-of-pocket payments dominate healthcare financing. In Kenya and Uganda, uninsured neuro-oncology patients often face catastrophic health expenditures, delayed diagnosis, and poor outcomes. This case study examines the systemic, financial, and clinical challenges of managing neuro-oncology patients without health insurance in these two countries, offering insights into potential solutions for equitable healthcare access. A qualitative case study approach was employed, drawing on a combination of literature review and expert interviews with neurosurgeons, oncologists, and healthcare administrators in Kenya and Uganda. Data sources included peer-reviewed publications, health policy documents, and hospital-based neuro-oncology registries. Thematic analysis was used to identify recurring barriers to care, financial toxicity, and survival outcomes, with a focus on the impact of health insurance status. The analysis revealed several critical challenges, including significant preoperative delays due to unaffordable diagnostic imaging and surgical fees, treatment discontinuation resulting from financial exhaustion, and limited access to postoperative oncology services. Uninsured neuro-oncology patients in both countries were more likely to present with advanced disease, experience longer hospital stays, and have lower 12-month survival rates compared to insured counterparts. Systemic issues such as inadequate public-sector neurosurgical capacity, prolonged referral pathways, and a lack of national cancer financing programs further compounded these difficulties. This case study highlights the urgent need for targeted policy interventions to mitigate financial toxicity and improve access to neuro-oncology care in Kenya and Uganda. Recommendations include expanding national health insurance coverage to include neuro-oncology services, creating cancer-specific financial assistance programs, and establishing regional centers of excellence with streamlined referral networks. A collaborative, multi-sectoral approach is essential to build sustainable, patient-centered neuro-oncology care systems and improve survival outcomes in East Africa.","url":"https://doi.org/10.1093/noajnl/vdaf213.116","authors":["Jalilarah Nassozi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-09T08:40:44Z","doi":"10.1093/noajnl/vdaf213.116","addedAt":"2026-09-01T01:48:31.441Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1016/b978-0-443-18634-9.10000-5","name":"Front Matter","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-18634-9.10000-5","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-18T21:41:44Z","doi":"10.1016/b978-0-443-18634-9.10000-5","addedAt":"2026-09-01T01:48:31.441Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1093/neuonc/noaf193.463","name":"P14.02.A OPTOCHEMOGENETIC MODELING OF NEURO-CANCER CROSSTALK IN VON HIPPEL-LINDAU DISEASE","source":"crossref","abstract":"Abstract BACKGROUND Von Hippel-Lindau (VHL) disease leads to tumors in the nervous system, including cerebellar and spinal cord hemangioblastomas (CBHB, SCHB), and pheochromocytomas (PCC), involving significant neuro-cancer interactions. Understanding these bidirectional interactions is limited by the absence of accurate genetically engineered mouse (GEM) models. Traditional approaches for modeling localized gene recombination face issues such as off-target effects and systemic toxicity. MATERIAL AND METHODS We employed a novel optochemogenetic (OCG) switch technology, using photoactivatable caged 4-hydroxycyclofen (4-OHC) with localized UV illumination, to precisely induce genetic alterations in specific nervous system compartments (cerebellum, spinal cord) and peripheral nervous tissue (adrenal medulla). Using reporter mice (UBC-CreERT2 mTmGf/+), we optimized this UV-driven method to achieve targeted gene recombination. Subsequently, we created GEM models (UBC-CreERT2 Vhlf/f and UBC-CreERT2 Vhlf/f Ptenf/f) to investigate tumor initiation and progression driven by localized neuro-cancer interactions. RESULTS Preliminary findings validated effective localized gene recombination via the OCG switch, demonstrating specificity without systemic side effects. Conventional systemic induction methods caused rapid lethality, highlighting the necessity for spatially controlled gene recombination to study neural-tumor crosstalk accurately. Ongoing experiments focus on refining UV illumination conditions to effectively model the neural influences on cancer initiation and progression. CONCLUSION Our optochemogenetic approach uniquely enables precise investigation of neural influences on tumor formation and tumor-induced neural alterations specific to VHL disease. These GEM models are expected to uncover novel neural-cancer crosstalk mechanisms, advancing our understanding of cancer neuroscience and paving the way for targeted therapeutic strategies.","url":"https://doi.org/10.1093/neuonc/noaf193.463","authors":["X Lu","X Lu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-03T15:40:06Z","doi":"10.1093/neuonc/noaf193.463","addedAt":"2026-09-01T01:48:31.441Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-981-96-3728-7_13","name":"AI inspired Preservation and Recognition of the Brahmi Script","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-96-3728-7_13","authors":["Trang Jain","V. K. Jain","Arpit Jain","Laith H. Jasim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-04T23:23:18Z","doi":"10.1007/978-981-96-3728-7_13","addedAt":"2026-09-01T01:48:31.441Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1016/b978-0-443-18509-0.00011-6","name":"AI in radiomics and radiogenomics for neuro-oncology: Achievements and challenges","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-18509-0.00011-6","authors":["Priyanka Jain","Subrata Kumar Mohanty","Sanjay Saxena"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-25T05:34:18Z","doi":"10.1016/b978-0-443-18509-0.00011-6","addedAt":"2026-09-01T01:48:31.441Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-3-031-72506-7_3","name":"Estimation of High-Order Neuro-Fuzzy TSK-Systems Effectiveness","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-72506-7_3","authors":["Sergey Morozov","Mikhail Kupriyanov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-12T15:07:57Z","doi":"10.1007/978-3-031-72506-7_3","addedAt":"2026-09-01T01:48:31.441Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-981-96-2908-4_2","name":"Bio-inspired Flyers","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-96-2908-4_2","authors":["Shafiq Bin Suhaimi","Solehuddin Shuib","Hamid Yusoff"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-15T08:53:42Z","doi":"10.1007/978-981-96-2908-4_2","addedAt":"2026-09-01T01:48:31.441Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1039/d5sc01777g/v1/review3","name":"Review for \"Role of Chemistry in Nature-Inspired Skin Adhesives\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5sc01777g/v1/review3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-31T17:01:07Z","doi":"10.1039/d5sc01777g/v1/review3","addedAt":"2026-09-01T01:48:31.441Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-981-97-8096-9_27","name":"Neuro-Cybernetics: Enabling Human–Machine Interaction Through Brain Signals","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-8096-9_27","authors":["Mukund Kulkarni","Tanmay Lautawar","Kunal Bhalgat","Kuntesh Nandankar","Yogita Lad","Niranjan Langade"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-24T18:25:50Z","doi":"10.1007/978-981-97-8096-9_27","addedAt":"2026-09-01T01:48:31.441Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.2139/ssrn.5284686","name":"Geometric Adam: Ray Tracing-Inspired Adaptive Optimization","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5284686","authors":["Jaepil Jeong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-19T16:45:38Z","doi":"10.2139/ssrn.5284686","addedAt":"2026-09-01T01:48:31.441Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1002/ntls.70049/v1/review1","name":"Review for \"Bio-Inspired Swarm Robotics Design for Mine Automation\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/ntls.70049/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-25T21:05:39Z","doi":"10.1002/ntls.70049/v1/review1","addedAt":"2026-09-01T01:48:31.441Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1039/d5sc01777g/v1/review2","name":"Review for \"Role of Chemistry in Nature-Inspired Skin Adhesives\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5sc01777g/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-31T17:01:07Z","doi":"10.1039/d5sc01777g/v1/review2","addedAt":"2026-09-01T01:48:31.441Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1007/978-981-95-3739-6_24","name":"A Machine Learning Approach for Medium-Term Electrical Load Forecasting Using Hybrid Neuro-Fuzzy Modeling","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-95-3739-6_24","authors":["Stephen Oladipo","Yanxia Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-10T11:54:21Z","doi":"10.1007/978-981-95-3739-6_24","addedAt":"2026-09-01T01:48:31.441Z","updatedAt":"2026-09-01T01:48:31.441Z"},{"id":"doi:10.1109/gcwcn66157.2025.11448516","name":"Human-in-the-Loop Hybrid Neuro-Symbolic AI Model for Reliable Data Engineering in High-Stakes Industrial Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/gcwcn66157.2025.11448516","authors":["Manikandan Krishnan","Avinash Reddy Aitha","Keerthi Amistapuram","Botlagunta Preethish Nandan","Pallav Kumar Kaulwar","Jeevani Singireddy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-25T19:54:18Z","doi":"10.1109/gcwcn66157.2025.11448516","addedAt":"2026-09-01T01:48:31.442Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1109/icec2nt65402.2025.11380132","name":"An Adaptive Neuro Fuzzy Controller for Multi-Port DC-DC Converter with Dual Input and Output Functions for EV Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icec2nt65402.2025.11380132","authors":["G. Madhuri","Srikant Ganji","V. Villesh","S. Hari","R. Bharath","G. Manoj"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-19T20:54:38Z","doi":"10.1109/icec2nt65402.2025.11380132","addedAt":"2026-09-01T01:48:31.442Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1007/s44227-025-00085-w","name":"Relay Node Selection Based on Adaptive Neuro- Fuzzy Inference System in Delay Tolerant Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s44227-025-00085-w","authors":["Fatemeh Semsarieh","Nahideh Derakhshanfard"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-22T16:07:58Z","doi":"10.1007/s44227-025-00085-w","addedAt":"2026-09-01T01:48:31.442Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1039/d5sc01777g/v1/review1","name":"Review for \"Role of Chemistry in Nature-Inspired Skin Adhesives\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5sc01777g/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-31T17:01:07Z","doi":"10.1039/d5sc01777g/v1/review1","addedAt":"2026-09-01T01:48:31.442Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.36227/techrxiv.170630368.82655420/v1","name":"Quantum-Inspired Differential Evolution with Decoding using Hashing for Efficient User Allocation in Edge Computing Environment","source":"crossref","abstract":"Modern apps require high computing resources for real-time data processing, allowing app users (AUs) to access real-time information. Edge computing (EC) provides dynamic computing resources to AUs for real-time data processing. However, ESs in specific areas can only serve a limited number of AUs due to resource and coverage constraints. Hence, the app user allocation problem (AUAP) becomes challenging in the EC environment. In this paper, a quantum-inspired differential evolution algorithm (QDE-UA) is proposed for efficient user allocation in the EC environment. The quantum vector is designed to provide a complete solution to the AUAP. The fitness function considers factors such as minimum ES required, user allocation rate (UAR), energy consumption, and load balance. Extensive simulations are performed along with hypotheses-based statistical analyses (ANOVA, Friedman test) to show the significance of the proposed QDE-UA. The results indicate that QDE-UA outperforms existing strategies with an average UAR improvement of 116.63%, a 77.35% reduction in energy consumption, and 46.22% enhancement in load balance while utilizing 13.98% fewer ESs.","url":"https://doi.org/10.36227/techrxiv.170630368.82655420/v1","authors":["Marlom Bey","Pratyay Kuila","Banavath Balaji Naik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-26T16:14:48Z","doi":"10.36227/techrxiv.170630368.82655420/v1","addedAt":"2026-09-01T01:48:31.442Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1109/nice61972.2024.10548355","name":"Towards Chip-in-the-loop Spiking Neural Network Training via Metropolis-Hastings Sampling","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nice61972.2024.10548355","authors":["Ali Safa","Vikrant Jaltare","Samira Sebt","Kameron Gano","Johannes Leugering","Georges Gielen","Gert Cauwenberghs"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-11T17:30:32Z","doi":"10.1109/nice61972.2024.10548355","addedAt":"2026-09-01T01:48:31.442Z","updatedAt":"2026-09-01T01:48:31.442Z"},{"id":"doi:10.1101/2025.06.21.660896","name":"Neural Network-Enhanced Investigation of Ferroptosis and Druggability in Early-Onset Alzheimer’s Disease","source":"crossref","abstract":"Abstract Background Alzheimer’s disease (AD) is a complex neurodegenerative disorder which is multifactorial in nature. Some of its characteristics are slow cognitive decline, memory problems and behavioral changes. AD patient brains show a progressive synaptic toxicity, autophagy, neuroinflammation, excess generation of reactive oxygen species (ROS), neuronal death and oxidative stress, which occurs due to disrupted metal homeostasis along with tau and amyloid-β protein deposition. Notably, lipid peroxidation, iron buildup and elevated oxidative stress in AD brains suggest a possible molecular connection between ferroptosis and AD neurodegeneration. Methods This study explores the genetic and bioinformatics perspective on the relationship between ferroptosis and AD aiming to identify potential therapeutic biomarkers using Neural network (NN) and Machine learning models. Six ferroptosis related genes were found to be differentially expressed in AD. Further machine learning analysis shortlisted four key biomarker genes. An NN-based diagnostic prediction model was developed and validated using AUC-ROC anaysis, which gave high diagnostic values (AUC-0.92) in the analysis. Results The findings highlight a strong correlation between ferroptosis and altered metabolic functions in AD. miRNA-gene interaction analysis revealed that two biomarker genes, CYBB and ACSL4 can be regulated by several regulatory miRNAs i.e., hsa-miR-146-5p, hsa-miR-106b-5p, hsa-miR-223-3p, hsa-miR-155-5p, hsa-miR-34a-5p, hsa-miR-125b-5p and hsa-miR-27a-3p suggesting their potential as early diagnostic biomarkers. Immune microenvironment analysis revealed strong neuroinflammatory responses were in AD with increased infiltration of macrophages (M0, M1 and M2), monocytes and multiple T cell subsets. This heightened immune activity may be driven by ferroptosis-induced oxidative stress, contributing to neuronal death. Furthermore, druggability of these targets was evaluated and several drugs were identified that may be potentially repurposed for therapeutic intervention in AD pathogenesis. Conclusion This study presents a diagnostic predictive model integrating gene expression, miRNA regulation and immune infiltration analysis, offering a novel perspective on early AD detection. The identified ferroptosis-related biomarkers and regulatory miRNAs could serve as valuable tools for clinical diagnosis and targeted therapeutic intervention, advancing personalized treatment strategies for Alzheimer’s disease.","url":"https://doi.org/10.1101/2025.06.21.660896","authors":["Pratibha Singh","Soumya Lipsa Rath"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-27T11:05:42Z","doi":"10.1101/2025.06.21.660896","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.32942/x2792n","name":"Anomaly detection in metabarcoding amplicon reads using an LSTM-CNN deep neural network ensemble (MetAnoDe)","source":"crossref","abstract":"Metabarcoding has emerged as a critical tool in ecology and other scientific disciplines, facilitating species identification in diverse samples for biodiversity monitoring, community and microbiome analysis, dietary studies, and understanding species interactions. However, challenges arise from errors and artifacts introduced during laboratory processes such as PCR and sequencing. Manual inspection is impractical due to the vast amount of sequences, necessitating rapid algorithms to clean the data. Thorough bioinformatic data cleanup can reduce such mistakes by removal of low-quality sequences or such classified as non-fitting through alignments. However, in practice some anomalous sequences evade detection, while also normal sequences may be mistakenly removed. Deep neural networks (DNNs) offer a promising solution by recognizing complex DNA sequence patterns. In this study I present a new software MetAnoDe (Metabarcoding Anomaly Detection), featuring development of novel deep-learning LSTM and CNN models for independent application and use as an ensemble model. MetAnoDe employs an alignment-free approach that complements existing tools, enhancing data cleanup efficiency. Here, the three models were trained for bacterial 16S-V4 and plant ITS2 markers which can be readily reused in other studies. Cross-validation and real-world data testing demonstrate high accuracy. Optimal integration into pipelines can also streamline overall runtime, synergizing effectively with current alignment-based methods. It is further adaptable for other markers due to the software's automated model training capability. In conclusion, MetAnoDe enhances metabarcoding by efficiently identifying anomalous sequences. An integration of DNNs with traditional approaches enhances biodiversity estimates by reducing non-target sequence inclusion, ensuring more accurate and comprehensive results.","url":"https://doi.org/10.32942/x2792n","authors":["Alexander Keller"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-20T11:08:48Z","doi":"10.32942/x2792n","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.2139/ssrn.5088827","name":"Banana Leaf Nutrient Deficiency Detection by Canny Edge Detection with Dense Neural Network","source":"crossref","abstract":"Image processing is dominant field for medical, agriculture, industrial image processing. It enhances the quality image and support for diagnosis. Normally it handles images from satellite, x-rays, scans, mobile captures, agriculture captures etc. Image processing offers various types of techniques to process and improve the quality of image. The image pre-processing techniques such as noise reduction, filters, edge detection, thresholding, segmentation, clustering and banana leaf nutrient deficiency detection. This study utilized edge detection technique for banana leaf images before the banana leaf nutrient deficiency detection. Edge detection is a technique identifying edges, points, intensity changes and discontinuities in the image. This study experiments Dense Neural Network for banana leaf detection and attained an accuracy of 95.67%. This research mutually proposed CNN-LSTM model to predict the banana leaf nutrient deficiency detection.","url":"https://doi.org/10.2139/ssrn.5088827","authors":["Rekha V","Uma Shankari Srinivasan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-09T08:29:26Z","doi":"10.2139/ssrn.5088827","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.1016/j.rineng.2025.105876","name":"Optimization of computer network security system based on improved neural network algorithm and low energy data search","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.rineng.2025.105876","authors":["Miao Zhigang","Cao Ying","Wang Tao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-19T02:44:02Z","doi":"10.1016/j.rineng.2025.105876","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.1109/icsec67360.2025.11298121","name":"Neural Network Surrogates for Free Energy Computation of Complex Chemical Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icsec67360.2025.11298121","authors":["Wasut Pornpatcharapong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-23T18:29:39Z","doi":"10.1109/icsec67360.2025.11298121","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.1109/mercon67903.2025.11217043","name":"Distillation-Boosted Spiking Neural Network for Gesture Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mercon67903.2025.11217043","authors":["G.M.M.K. Aponso","J. Thusyanthan","W.I.U.D. Wellahewa","C. Hettiarachchi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-07T18:08:25Z","doi":"10.1109/mercon67903.2025.11217043","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.1007/978-3-031-85056-1","name":"Neural Network Methods for Dynamic Equations on Time Scales","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-85056-1","authors":["Svetlin Georgiev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-29T23:11:50Z","doi":"10.1007/978-3-031-85056-1","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.1109/icipca65645.2025.11138272","name":"Medical Image Classification Based on Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icipca65645.2025.11138272","authors":["Ruihan Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-05T18:05:15Z","doi":"10.1109/icipca65645.2025.11138272","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.2118/224045-ms","name":"Advanced Wireline Conveyance Modeling Powered by Physics-Informed Neural Network","source":"crossref","abstract":"Abstract Accurately estimating the interaction between tool string, cable, and wellbore is essential for wireline conveyance design and operational risk evaluation. Traditional physics-based models suffer from inaccuracies due to simplifications and uncertain parameters, such as friction coefficients. We propose an advanced wireline conveyance model that overcomes these limitations by integrating a neural network with a physics-based model to enhance prediction accuracy of various operational parameters, such as tensions. The solution optimizes wireline conveyance in both planning and real-time phases. The proposed model integrates a multilayer perceptron neural network with a physics-based model, forming a physics-informed neural network (PINN). This fusion of physical simulation and historical data improves prediction accuracy and tolerates input uncertainties. Inputs include cable, tool string, wellbore properties and geometry, along with time series data like cable speed, length, tractor force, and pumping rate. The model is currently tuned to predict surface tension, as it is the dominant indicator and consistently available in historical data. However, with minimal adjustments and additional data, it can be adapted to predict other parameters, such as head tension, open-hole sticking probability, conveyance time, and the effects of temperature and pressure gradients. We collected datasets of wireline conveyance jobs from different geological locations, spanning a wide range of configurations, covering various cables, tool strings, well geometries, winch speeds, and conveyance methods. Representative jobs were selected as validation sets to test the model's prediction accuracy, while the remaining jobs were used as references for manual parameter tuning and training the physics-based and PINN models. After the corresponding parameter tuning or training, both models were used to simulate jobs in the validation set, with errors quantified using root-mean-square error. Surface tension predictions by both models, along with their errors, were compared and analyzed. Results show that the PINN model outperformed the physics-based model in prediction accuracy, even when trained with data from a single trip. The accuracy further improved as more data were incorporated into the training process. These findings highlight the PINN model's robust capability to accurately predict surface tension, where the physics-based model may struggle, indicating its strong potential for broader applications in challenging environments. The proposed PINN wireline conveyance model innovatively simulates complex jobs by fusing data-driven and physical approaches, enhancing prediction accuracy. By relying on data, it reduces the dependency on uncertain inputs for the physics-based model. The improved accuracy offers a competitive advantage by enhancing design and execution, potentially leading to faster conveyance, less human interaction, and reduced anomalies with accurate risk estimation. Furthermore, the model's adaptability to various job configurations and its ability to simulate a range of conveyance scenarios enable broader application through precise tuning across diverse basins.","url":"https://doi.org/10.2118/224045-ms","authors":["J. Wang","N. Baklanov","B. Durand"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-18T04:21:37Z","doi":"10.2118/224045-ms","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.38007/nn.2021.020405","name":"Crop Disease Identification Method Based on Convolution Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2021.020405","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T18:12:48Z","doi":"10.38007/nn.2021.020405","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.38007/nn.2022.030402","name":"Algorithm Research of Neural Network for Feature Target Tracking","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2022.030402","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T06:22:51Z","doi":"10.38007/nn.2022.030402","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.31390/gradschool_dissertations.5270","name":"Identification of Top-down, Bottom-up, and Cement-Treated Reflective Cracks Using Convolutional Neural Network and Artificial Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.31390/gradschool_dissertations.5270","authors":["Nirmal Dhakal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-10T18:32:33Z","doi":"10.31390/gradschool_dissertations.5270","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1016/b978-0-08-102782-0.00019-8","name":"Spiking neural networks for inference and learning: a memristor-based design perspective","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-08-102782-0.00019-8","authors":["Mohammed E. Fouda","Fadi Kurdahi","Ahmed Eltawil","Emre Neftci"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-26T05:29:04Z","doi":"10.1016/b978-0-08-102782-0.00019-8","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/cenim67940.2025.11324452","name":"Vehicle Speed Estimation System Using Drone With Jetson Nano-based using YOLOv8 Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cenim67940.2025.11324452","authors":["Arief Kurniawan","Syahrul Fathoni Ahmad","Diah Puspito Wulandari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-13T20:56:15Z","doi":"10.1109/cenim67940.2025.11324452","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.54216/fpa.170226","name":"Deep Learning for Handwritten Digit Recognition System: A Convolution Neural Network Approach","source":"crossref","abstract":"","url":"https://doi.org/10.54216/fpa.170226","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-20T08:47:33Z","doi":"10.54216/fpa.170226","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.13005/ojps10.02.11","name":"Facial Expression Recognition Method Based on Convolutional Neural Network","source":"crossref","abstract":"Deep learning algorithms are a subset of machine learning algorithms that aim to discover multiple levels of distributed representations of input data. Recently, many deep learning algorithms have been proposed to solve traditional artificial intelligence problems. Now days, deep learning has been extensively studied in the field of computer vision and as such, a large number of related methods have arisen. Today, different algorithms and models of neural network–based research have made their place among the classification of images. The main purpose of these algorithms is to train the machine in artificial networks in a way that ultimately has a diagnosis close to the human brain. Among a variety of neural networks, CNN's channel neural networks usually offer good accuracy in the classification of images. In this article, in the first episode, we will discuss 4 deep learning methods: Convolutional neural network (CNN), Restricted Boltzmann Machines (RBMS), Autoencoders and Sparse coding, which after determining the necessary assumptions and applying a preliminary pre–training using the channel neural network algorithm we need Convolutional to perform a general preprocessing on the entered samples. Therefore, a preprocessing is performed on all data and preprocessed samples are stored in a separate location and then the rest of the processes are applied to these samples. Then, we use deep learning to identify faces and reveal them, and deep learning algorithms to reveal different subjects.","url":"https://doi.org/10.13005/ojps10.02.11","authors":["Alireza Heidari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-02T05:04:30Z","doi":"10.13005/ojps10.02.11","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.1109/iccc68654.2025.11437684","name":"Graph Neural Network Recommendation Algorithm Based on Frequency, Time and Location","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccc68654.2025.11437684","authors":["Qingbo Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-25T19:52:56Z","doi":"10.1109/iccc68654.2025.11437684","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.1109/ijcnn64981.2025.11228689","name":"Uncertainty-guided boundary enhancement network for breast ultrasound image segmentation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn64981.2025.11228689","authors":["Rongsheng Fan","Jun Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T18:46:15Z","doi":"10.1109/ijcnn64981.2025.11228689","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.1016/j.procs.2025.05.097","name":"Interior Design Layout Optimization Based On Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.procs.2025.05.097","authors":["Jing He"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-10T12:34:59Z","doi":"10.1016/j.procs.2025.05.097","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.1201/9781420015454-5","name":"Neural Network Control of Nonlinear Systems and Feedback Linearization","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781420015454-5","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-02T00:22:01Z","doi":"10.1201/9781420015454-5","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.5194/egusphere-egu24-8233","name":"Double Acoustic Emission events detection using U-net Neural Network","source":"crossref","abstract":"In the past decade, the development of the Deep Neural Network formalism has emerged as a promising approach for addressing contemporary task in seismology, particularly in the effective and potentially automated processing of extensive datasets, such as seismograms. In this study, we introduce a 4D Neural Network (NN) based on the U-Net architecture, capable of simultaneously processing data from the entire seismic network. Our dataset comprises records/seismograms of Acoustic Emission (AE) events obtained during a laboratory loading experiment on a rock specimen. While AE event records share similarities with real seismograms, they exhibit simplifications in certain features.To assess the capability of the proposed NN in handling complex data, including occurrences of multiple events observed during experiments, we generated double-event seismograms through the augmentation of unambiguous single-event seismograms. These augmented datasets were employed for training, validation, and testing of the NN. Despite the individual station detection rate being approximately 30%, the simultaneous processing of multiple stations significantly increased efficiency, achieving an overall detection rate of 97%.In this work, we treat seismograms as \"images,\" adopting an approach that proves to be fruitful. The simultaneous processing of seismograms, coupled with this image-based treatment, demonstrates high potential for reliable automatic interpretation of seismic data. This approach (possibly combined with other methodologies), holds promise for seismogram processing.","url":"https://doi.org/10.5194/egusphere-egu24-8233","authors":["Petr Kolar","Matěj Petružálek","Jan Šílený","Tomáš Lokajíček"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-08T18:18:58Z","doi":"10.5194/egusphere-egu24-8233","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.2139/ssrn.5467515","name":"A Unified Kernel for Neural Network Learning","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5467515","authors":["Shao-Qun Zhang","Yong-Ming Tian","Zong-Yi Chen","Xun Lu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-10T13:41:30Z","doi":"10.2139/ssrn.5467515","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.7868/s3034498025060013","name":"REFLECTOR TYPE RECOGNITION USING NEURAL NETWORK BASED ON TOFD ECHOES","source":"crossref","abstract":"In this paper we propose to automate the classification of reflector types by TOFD-echoes using ResNet-18 convolutional neural network. The main focus is on modeling and classification of reflectors such as cracks, pores, non-welds and void areas. Experiments included training the model on TOFD echoes calculated both in a numerical experiment and TOFD echoes measured during ultrasonic inspection. The results showed high classification accuracy: 96.2 % in the numerical experiment, 97 % on experimentally measured TOFD-echoes with different types of reflectors. The study confirmed the possibility of using neural networks to determine the reflector type from TOFD-echo signals, which allows to automate the process of nondestructive testing and reduce the influence of human factor. For further development of the method it is suggested to use segmentation models for processing images with several reflectors","url":"https://doi.org/10.7868/s3034498025060013","authors":["E.G. Bazulin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-04T07:16:57Z","doi":"10.7868/s3034498025060013","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.31705/eru.2025.18","name":"Convolutional neural network–based automated quality grading of cinnamon peel","source":"crossref","abstract":"Ceylon cinnamon, endemic to Sri Lanka, holds significant culinary, medicinal, and economic value, reinforcing the country’s position as the leading global exporter of authentic cinnamon. However, current processing techniques, particularly manual peeling and quill preparation, are highly labor dependent and introduce quality inconsistencies, limiting scalability. While national efforts increasingly promote value addition and product diversification, maintaining consistent export-grade quality remains challenging. Recent research highlights the potential of technological advancement within the cinnamon value chain, with image processing applied for maturity estimation, and diameter-based grading [1], [2]. Additionally, deep learning models, particularly Convolutional Neural Networks (CNNs), have demonstrated strong performance in agricultural applications such as disease diagnosis and adulteration detection [3], [4]. Visual grading of cinnamon based on peel texture, surface defects and residual bark remains subjective and inconsistent. This study addresses this gap by proposing an objective, scalable deep learning–based automated visual inspection framework.","url":"https://doi.org/10.31705/eru.2025.18","authors":["A.A. Darshani","D.C. Hewavitharana","A.D.U.S. Amarasinghe","J.R. Gamage"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-10T09:54:05Z","doi":"10.31705/eru.2025.18","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.1002/eng2.70344/v2/review2","name":"Review for \"Hybrid Neural Network Modeling of Mechanical Alloying Process Parameters and Alloy Performance Using Forward and Reverse Mapping\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/eng2.70344/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T23:45:21Z","doi":"10.1002/eng2.70344/v2/review2","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.31219/osf.io/6kxeb","name":"MCMC-Enhanced Neural Network Operators for Dynamic Systems and Adaptive Control","source":"crossref","abstract":"This paper introduces a novel framework that integrates neural network operators with Markov Chain Monte Carlo (MCMC) methods to model and control stochastic dynamic systems and adaptive control systems. Three foundational theorems are proposed: the stability of stochastic dynamic systems, the convergence of MCMC-based optimization, and the stability of adaptive control systems. These theorems establish the theoretical underpinnings of the integrated framework, focusing on stability, convergence, and optimal parameter adjustment. The stability theorem demonstrates error bounds for neural network approximations in Sobolev spaces, while the MCMC convergence theorem guarantees sampling efficacy for parameter optimization. The stability of adaptive control systems theorem ensures asymptotic tracking of desired trajectories and convergence of adaptive parameters. Numerical simulations validate the theoretical results, highlighting improved precision, robustness, and efficiency in dynamic system modeling and control. The findings provide a robust foundation for enhancing neural network-based approaches in dynamic systems and adaptive control, with significant implications for practical applications in complex, stochastic environments.","url":"https://doi.org/10.31219/osf.io/6kxeb","authors":["Romulo Damasclin Chaves dos Santos"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-20T21:26:46Z","doi":"10.31219/osf.io/6kxeb","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.1002/eng2.70373/v1/review3","name":"Review for \"Enhancing Cardiovascular Disease Analysis in Healthcare Systems With Hybrid Random Forest and Neural Network Algorithm\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/eng2.70373/v1/review3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T23:21:22Z","doi":"10.1002/eng2.70373/v1/review3","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1002/eng2.70373/v2/review3","name":"Review for \"Enhancing Cardiovascular Disease Analysis in Healthcare Systems With Hybrid Random Forest and Neural Network Algorithm\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/eng2.70373/v2/review3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T23:21:22Z","doi":"10.1002/eng2.70373/v2/review3","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.32388/q5ebvl","name":"Review of: \"Synthetic Data Generation of Body Motion Data by Neural Gas Network for Emotion Recognition\"","source":"crossref","abstract":"","url":"https://doi.org/10.32388/q5ebvl","authors":["Dr. Rohan Borgalli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-17T05:29:36Z","doi":"10.32388/q5ebvl","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.32388/8dtly6","name":"Review of: \"Synthetic Data Generation of Body Motion Data by Neural Gas Network for Emotion Recognition\"","source":"crossref","abstract":"","url":"https://doi.org/10.32388/8dtly6","authors":["Shuruq Khalid Abdulredha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-26T07:02:57Z","doi":"10.32388/8dtly6","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1109/ieir67391.2025.11491478","name":"Application of BP Neural Network in Undergraduate Performance Prediction Modeling","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ieir67391.2025.11491478","authors":["Zixuan Gu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-30T19:45:53Z","doi":"10.1109/ieir67391.2025.11491478","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.1109/smartindustrycon65166.2025.10986139","name":"Adversarial Attack on YOLO Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/smartindustrycon65166.2025.10986139","authors":["Nikolai V. Teterev","Vladislav E. Trifonov","Alla B. Levina"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-09T17:56:01Z","doi":"10.1109/smartindustrycon65166.2025.10986139","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.38007/nn.2022.030202","name":"Gymnastic Movement Recognition Based on Depth Convolution Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2022.030202","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T18:14:06Z","doi":"10.38007/nn.2022.030202","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1021/acs.jcim.3c02054.s001","name":"Directional G Neural Network (DrGNet): A Modular Neural Network Approach to Binding Free Energy Prediction","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acs.jcim.3c02054.s001","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-12T14:40:50Z","doi":"10.1021/acs.jcim.3c02054.s001","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1142/9789819814695_0003","name":"Regularized Stochastic Configuration Network Based on Weighted Mean of Vectors","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789819814695_0003","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-01T02:52:26Z","doi":"10.1142/9789819814695_0003","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.2478/arsa-2025-0007","name":"Accelerating Atmosphere Modeling: Neural Network Enhancements for Faster NRLMSISE Calculations","source":"crossref","abstract":"Abstract NRLMSISE is an empirical model that allows us to predict temperatures and densities of the main atmospheric components. The model is widely used to evaluate atmospheric impacts on satellite orbits and laser beam refraction which come through the atmosphere, such as those used for Earth-satellite distance measurements. Model of the atmosphere is a valuable part of the Satellite Laser Ranging processing software like Kyiv Geodynamics (Juliette). Juliette is written in C++ and exploits the C++ clone of NRLMSISE written by the second author. The C++ version produces the same outputs as an official Fortran code. Accurate modeling of atmospheric influences on satellite motion requires performing numerous calculations along satellite orbits or laser beam paths, which are computationally intensive. By decreasing calculation time of NRLMSISE, we would not only save the modeling time but also give a prospect for a wider application of the model due to lowering computational resource demands. Our work demonstrates how the traditional NRLMSISE model can be effectively translated into a neural network. This conversion achieves significant performance gains on both CPU and GPU while maintaining acceptable accuracy when compared to the C++ implementation of NRLMSISE. We demonstrate the process of moving NRLMSISE to a neural network, the resulting accuracy, ease of running the trained model on CUDA-enabled GPUs, and the obtained boost of performance on both CPU and GPU.","url":"https://doi.org/10.2478/arsa-2025-0007","authors":["Volodymyr Kashyn","Vasyl Choliy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-23T08:25:09Z","doi":"10.2478/arsa-2025-0007","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.1109/icaci49185.2020.9177672","name":"Finite-Time Stabilization of Memristor Neural Networks with Time-Varying Delay: Interval Matrix Method","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icaci49185.2020.9177672","authors":["Fei Wei","Guici Chen","Tianqi Cheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-08-26T20:43:42Z","doi":"10.1109/icaci49185.2020.9177672","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/cnna.2012.6331434","name":"Memristor bridge circuit for neural synaptic weighting","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cnna.2012.6331434","authors":["Maheshwar Pd. Sah","Changju Yang","Hyongsuk Kim","Tamás Roska","Leon Chua"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-10-19T16:40:54Z","doi":"10.1109/cnna.2012.6331434","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/nnice64954.2025.11064400","name":"Attention-Driven Interaction Network for E-Commerce Recommendations","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nnice64954.2025.11064400","authors":["Erfan Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-15T17:39:55Z","doi":"10.1109/nnice64954.2025.11064400","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.17559/tv-20240913001988","name":"Prediction of Cities' Digital International Trade Competitiveness based on Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.17559/tv-20240913001988","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-02T05:18:42Z","doi":"10.17559/tv-20240913001988","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.3390/books978-3-7258-7976-2","name":"Image Processing Based on Convolution Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.3390/books978-3-7258-7976-2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-15T05:07:42Z","doi":"10.3390/books978-3-7258-7976-2","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/icee67339.2025.11213861","name":"A Siamese Neural Network for Predicting snoRNA-Disease Association","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icee67339.2025.11213861","authors":["Milad Besharatifard","Fatemeh Zare-Mirakabad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-06T18:48:39Z","doi":"10.1109/icee67339.2025.11213861","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.1109/rusautocon65989.2025.11177336","name":"Indoor Scene Classification Based on Optimized Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/rusautocon65989.2025.11177336","authors":["Lingxue Zhang","Pan Gao","Vadim V. Lukyanov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T17:37:01Z","doi":"10.1109/rusautocon65989.2025.11177336","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.1016/b978-0-12-228640-7.50024-6","name":"Self-Organizing Neural Network Tool Code with Pattern, Run, and Demo Files","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-12-228640-7.50024-6","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-01T08:01:52Z","doi":"10.1016/b978-0-12-228640-7.50024-6","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1504/ijmndi.2025.151006","name":"Analysis of spectrum sensing using convolutional neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1504/ijmndi.2025.151006","authors":["Sankarsan Panda","D. Chitra Devi","M. Madhini","K. PeriyarSelvam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-09T12:30:19Z","doi":"10.1504/ijmndi.2025.151006","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.1504/ijwmc.2025.146629","name":"Optimised recurrent neural network-based localisation in wireless sensor network: a composite approach","source":"crossref","abstract":"","url":"https://doi.org/10.1504/ijwmc.2025.146629","authors":["Shivakumar Kagi","Basavaraj S. Mathapati"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-11T11:30:16Z","doi":"10.1504/ijwmc.2025.146629","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.1016/j.asoc.2025.112921","name":"Forecasting time series using convolutional neural network with multiplicative neuron","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2025.112921","authors":["Shobhit Nigam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-02T14:38:31Z","doi":"10.1016/j.asoc.2025.112921","addedAt":"2026-09-01T01:48:32.244Z","updatedAt":"2026-09-01T01:48:32.244Z"},{"id":"doi:10.5121/csit.2025.150907","name":"Improved Fire Recognition in VTOL UAVs through Convolutional Neural Network Algorithmss","source":"crossref","abstract":"South Korea, with approximately 63% of its land covered by forests, is highly susceptible to wildfires. Traditional fire detection methods—such as satellite imagery and ground-based observation—face significant limitations, including high operational costs, delayed response times, and vulnerability to weather conditions. This paper presents an efficient fire detection system for Vertical Take-Off and Landing (VTOL) Unmanned Aerial Vehicles (UAVs), utilizing Convolutional Neural Networks (CNNs). The integration of CNNs significantly improves detection accuracy, even in complex environments that challenge conventional approaches. In simulations designed to closely mimic real-world scenarios, the optimized algorithm achieved a 93% detection rate with 20% false positives and a frame latency of just 1.2 seconds. Additionally, deploying the model on a Raspberry Pi onboard a VTOL drone demonstrated its practical viability for real-time forest fire surveillance and rapid response. This study highlights the potential of drone-based, AI-powered fire detection systems as a powerful supplement to existing wildfire monitoring and prevention strategies.","url":"https://doi.org/10.5121/csit.2025.150907","authors":["Seo Jun Jayden Lee","Jisoo Oh","Jennifer Choi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-20T08:36:40Z","doi":"10.5121/csit.2025.150907","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.23919/acc63710.2025.11107719","name":"Memristor-Based Dynamic Modeling of Muscle Fatigue","source":"crossref","abstract":"","url":"https://doi.org/10.23919/acc63710.2025.11107719","authors":["Hanz Richter","Adam Mastropieri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-21T18:17:51Z","doi":"10.23919/acc63710.2025.11107719","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1038/s41563-025-02125-w","name":"A cryogenic memristor","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s41563-025-02125-w","authors":["Dennis Meier","Davi Rodrigues"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-11T10:02:33Z","doi":"10.1038/s41563-025-02125-w","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.14311/nnw.2014.24.011","name":"NEURAL NETWORK BASED CRYPTOGRAPHY","source":"crossref","abstract":"","url":"https://doi.org/10.14311/nnw.2014.24.011","authors":["Apdullah Yayik","Yakup Kutlu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-05-06T08:40:22Z","doi":"10.14311/nnw.2014.24.011","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/icist.2018.8426119","name":"Three-Dimensional Memristor-Based Crossbar Architecture for Capsule Network Implementation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icist.2018.8426119","authors":["Yi Huang","Rui Hu","Zhigang Zeng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-08-17T19:55:47Z","doi":"10.1109/icist.2018.8426119","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.18178/wcse.2025.06.033","name":"Travel Behavior of Low-Income Rural Residents: A Multidimensional Analysis Using Artificial Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.18178/wcse.2025.06.033","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-24T08:39:02Z","doi":"10.18178/wcse.2025.06.033","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1145/3747227.3747247","name":"Research on SSE 50 Index Prediction Based on Wavelet Denoising and BP Neural Network with Textual Information Integration","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3747227.3747247","authors":["Xin Sui","Qi Zhang","Haoran Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-13T09:53:11Z","doi":"10.1145/3747227.3747247","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1109/ijcnn.2010.5596698","name":"Compressing a neural network classifier using a Volterra-Neural Network model","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2010.5596698","authors":["M. Rubiolo","G. Stegmayer","D. Milone"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-10-19T18:58:15Z","doi":"10.1109/ijcnn.2010.5596698","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1201/9781420093339-11","name":"Impact Damage Detection in a Composite Structure Using Artificial Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781420093339-11","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-22T23:12:00Z","doi":"10.1201/9781420093339-11","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1201/9781420093339-16","name":"Determining Initial Design Parameters by Using Genetically Optimized Neural Network Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781420093339-16","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-22T23:12:00Z","doi":"10.1201/9781420093339-16","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.38007/nn.2021.020103","name":"Stock Price Forecast Analysis Based on Artificial Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2021.020103","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T18:10:50Z","doi":"10.38007/nn.2021.020103","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.2514/6.2025-0565","name":"Neural Network Based Collision-Free Trajectory Generator for Quadcopters","source":"crossref","abstract":"","url":"https://doi.org/10.2514/6.2025-0565","authors":["Praveen Jawaharlal Ayyanathan","Ehsan Taheri","Tyler C. Flegel","Nan Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-12T09:44:16Z","doi":"10.2514/6.2025-0565","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1088/0954-898x_2_1_004","name":"Recognition and categorization in a structured neural network with attractor dynamics","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_2_1_004","authors":["C Fassnacht","A Zippelius"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:00Z","doi":"10.1088/0954-898x_2_1_004","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/mnet.2025.3542450","name":"Achieving Network Resilience Through Graph Neural Network-Enabled Deep Reinforcement Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mnet.2025.3542450","authors":["Xuzeng Li","Tao Zhang","Jian Wang","Zhen Han","Jiqiang Liu","Jiawen Kang","Dusit Niyato","Abbas Jamalipour"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-14T13:33:06Z","doi":"10.1109/mnet.2025.3542450","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1145/3784013.3784037","name":"Research on Neural Network Algorithms for Predicting Displacement Distribution of Adjacent Shear Walls Under Building Implosion Conditions","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3784013.3784037","authors":["Haohao Li","Hongbo Zhai","Feng Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-09T14:06:06Z","doi":"10.1145/3784013.3784037","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.21203/rs.3.rs-3172508/v1","name":"Heterogeneous 2D Memristor Array and Silicon Selector for Compute-in-Memory Hardware in Convolution Neural Networks","source":"europepmc","abstract":"Abstract Memristor crossbar arrays (CBAs) based on two-dimensional (2D) materials have emerged as a potential solution to overcome the limitations of energy consumption and latency associated with the conventional von Neumann architecture. However, current 2D memristor CBAs encounter specific challenges such as limited array size, high sneak path current, and lack of integration with peripheral circuits for hardware compute-in-memory (CIM) systems. In this work, we demonstrate a novel hardware CIM system that leverages the heterogeneous integration of scalable 2D hafnium diselenide (HfSe2) memristors and silicon (Si) selectors, as well as the integration between memristive CBAs and peripheral control-sensing circuits. The integrated 32 × 32 one-selector-one-memristor (1S1R) array effectively mitigates sneak current, exhibiting a high yield (89%) with notable uniformity. The integrated CBA demonstrates exceptional improvement of energy efficiency and response time comparable to state-of-the-art 2D materials-based memristors. To take advantage of low latency devices for achieving low energy systems, time-domain sensing circuits with the CBA are used, of which the power consumption surpasses that of analog-to-digital converters (ADCs) by 2.5 folds. Moreover, the implemented full-hardware binary convolution neural network (CNN) achieves remarkable accuracy (97.5%) in a pattern recognition task. Additionally, analog computing and in-built activation functions are demonstrated within the system, further augmenting energy efficiency. This silicon-compatible heterogeneous integration approach, along with the energy-efficient CIM system, presents a promising hardware solution for artificial intelligence (AI) applications.","url":"https://doi.org/10.21203/rs.3.rs-3172508/v1","authors":["Kah-Wee Ang","Sifan Li","Samarth Jain","Haofei Zheng","Lingqi Li","Xuanyao Fong"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-3172508/v1","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1109/islped.2013.6629290","name":"A practical low-power memristor-based analog neural branch predictor","source":"crossref","abstract":"","url":"https://doi.org/10.1109/islped.2013.6629290","authors":["Jianxing Wang","Yenni Tim","Weng-Fai Wong","Hai Helen Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-12-17T20:47:27Z","doi":"10.1109/islped.2013.6629290","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.3934/mbe.2024147","name":"Synchronization of inertial complex-valued memristor-based neural networks with time-varying delays","source":"crossref","abstract":"&lt;abstract&gt;&lt;p&gt;The synchronization of inertial complex-valued memristor-based neural networks (ICVMNNs) with time-varying delays was explored in the paper with the non-separation and non-reduced approach. Sufficient conditions required for the exponential synchronization of the ICVMNNs were identified with the construction of comprehensive Lyapunov functions and the design of a novel control scheme. The adaptive synchronization was also investigated based on the derived results, which is easier to implement in practice. What's more, a numerical example that verifies the obtained results was presented.&lt;/p&gt;&lt;/abstract&gt;","url":"https://doi.org/10.3934/mbe.2024147","authors":["Pan Wang","Xuechen Li","Qianqian Zheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-05T12:20:46Z","doi":"10.3934/mbe.2024147","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1088/1742-6596/2032/1/012017","name":"Split signals for a neural model of Bernoulli memristor","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1742-6596/2032/1/012017","authors":["E B Solovyeva","H A Harchuk"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-10-19T08:52:11Z","doi":"10.1088/1742-6596/2032/1/012017","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1088/0954-898x/1/1/006","name":"Neural potentials as stimuli for attractor neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/1/1/006","authors":["Daniel Amit","G Parisi","S Nicolis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-26T20:10:12Z","doi":"10.1088/0954-898x/1/1/006","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1088/0954-898x/10/3/301","name":"Learning model for coupled neural oscillators","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/10/3/301","authors":["Jun Nishii"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/10/3/301","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1088/0954-898x/5/3/005","name":"Macroscopic properties of the cost function of a feed-forward neural network prior to training","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/5/3/005","authors":["M Roberts"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/5/3/005","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/ijcnn.2006.247058","name":"Boosted Modified Probabilistic Neural Network (BMPNN) for Network Intrusion Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.247058","authors":["Tich Phuoc Tran","T. Jan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T15:34:22Z","doi":"10.1109/ijcnn.2006.247058","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1016/j.neucom.2023.126246","name":"Electrical activity and synchronization of memristor synapse-coupled HR network based on energy method","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2023.126246","authors":["Yingchun Lu","Hongmin Li","Chunlai Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-03T21:02:48Z","doi":"10.1016/j.neucom.2023.126246","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1038/s41467-025-58039-3","name":"Heterogeneous integration of 2D memristor arrays and silicon selectors for compute-in-memory hardware in convolutional neural networks","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-58039-3","authors":["Samarth Jain","Sifan Li","Haofei Zheng","Lingqi Li","Xuanyao Fong","Kah-Wee Ang"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-58039-3","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1016/j.neunet.2024.107069","name":"Local interpretable spammer detection model with multi-head graph channel attention network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.107069","authors":["Fuzhi Zhang","Chenghang Huo","Ru Ma","Jinbo Chao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-19T03:12:42Z","doi":"10.1016/j.neunet.2024.107069","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1007/s00521-025-11271-w","name":"Correction: DNACoder: a CNN-LSTM attention-based network for genomic sequence data compression","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-025-11271-w","authors":["K. S. Sheena","Madhu S. Nair"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-21T05:20:22Z","doi":"10.1007/s00521-025-11271-w","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1016/j.neunet.2025.107976","name":"Adaptively trigger memory network with temporal consistency for semi-supervised long video object segmentation","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107976","authors":["Fan Zhang","Xiangxu Cao","Yuqian Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-10T14:16:27Z","doi":"10.1016/j.neunet.2025.107976","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1016/j.neunet.2025.107283","name":"CNN-Transformer and Channel-Spatial Attention based network for hyperspectral image classification with few samples","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107283","authors":["Chuan Fu","Tianyuan Zhou","Tan Guo","Qikui Zhu","Fulin Luo","Bo Du"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-22T11:00:30Z","doi":"10.1016/j.neunet.2025.107283","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1016/j.neunet.2025.107691","name":"Convergent adaptive control based prescribed-time synchronization of switched fuzzy competitive network systems with time-varying delays","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107691","authors":["Dongdong Gao","Fanchao Kong","Tingwen Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-14T11:01:38Z","doi":"10.1016/j.neunet.2025.107691","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1088/0954-898x_7_2_022","name":"A fast, three-layer neural network for path finding","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_7_2_022","authors":["Th Kindermann","H Cruse","K Dautenhahn"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T16:04:30Z","doi":"10.1088/0954-898x_7_2_022","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.5220/0014195100004932","name":"Hybrid Adaptive Neural Network for Classification of Remote Sensing Images","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0014195100004932","authors":["Swapnil Parikh","Poonima Jayaraman","D. Raj","Pravin Bhoyar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-04T19:41:27Z","doi":"10.5220/0014195100004932","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1088/0954-898x_5_4_010","name":"Self-organization in complex pattern spaces using a logic neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_5_4_010","authors":["G Tambouratzis","D Tambouratzis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:38Z","doi":"10.1088/0954-898x_5_4_010","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1016/j.cnsns.2025.109479","name":"A fixed-time convergence robust zeroing neural network for the synchronization of memristor-based chaotic systems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.cnsns.2025.109479","authors":["Jing Fang","Jie Jin","Zuguo Chen","Yi Huang","Chaoyang Chen","Lv Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-03T22:17:24Z","doi":"10.1016/j.cnsns.2025.109479","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1016/j.neucom.2024.128024","name":"Quasi-synchronization of neural networks via non-fragile impulsive control: Multi-layer and memristor-based","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2024.128024","authors":["Lingna Shi","Jiarong Li","Haijun Jiang","Jinling Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-11T16:27:47Z","doi":"10.1016/j.neucom.2024.128024","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1109/icecs46596.2019.8964896","name":"Defect-Tolerant Crossbar Training of Memristor Ternary Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icecs46596.2019.8964896","authors":["Khoa Van Pham","Tien Van Nguyen","Kyeong-Sik Min"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-23T22:15:31Z","doi":"10.1109/icecs46596.2019.8964896","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1063/5.0260140","name":"An efficient prediction of sentiment in social media system based on novel convolutional neural network compared with artificial neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1063/5.0260140","authors":["M. Geetha","Kalimuddin Mondal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-03T18:00:36Z","doi":"10.1063/5.0260140","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1080/0954898x.2025.2472626","name":"Leveraging the internet of things and optimized deep residual networks for improved foliar disease detection in apple orchards","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2025.2472626","authors":["Sameera Kuppam","Swarnalatha Purushotham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-24T22:51:40Z","doi":"10.1080/0954898x.2025.2472626","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1080/0954898x.2025.2452280","name":"Hybrid deep learning based stroke detection using CT images with routing in an IoT environment","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2025.2452280","authors":["Anchana Balakrishnannair Sreekumari","Arul Teen Yesudasan Paulsy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-02T01:21:26Z","doi":"10.1080/0954898x.2025.2452280","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1117/12.3110896","name":"Prediction of online public sentiment based on neural network models","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3110896","authors":["Li Yi","Peng Qiao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-29T18:41:59Z","doi":"10.1117/12.3110896","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1080/0954898x.2025.2513690","name":"Gradient energy valley optimization enabled segmentation and Spinal VGG-16 Net for brain tumour detection","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2025.2513690","authors":["Kishore Bhamidipati","G Anuradha","Satish Muppidi","S Anjali Devi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-23T09:38:55Z","doi":"10.1080/0954898x.2025.2513690","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1109/ijcnn64981.2025.11228384","name":"BCRNet: A Lightweight Branched Convolutional Neural Network Enhanced with Riemannian Geometry for End-to-End EEG-Based Emotion Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn64981.2025.11228384","authors":["Wenxia Qi","Xingfu Wang","Wenjie Yang","Wei Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T18:46:15Z","doi":"10.1109/ijcnn64981.2025.11228384","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1016/j.neunet.2025.107123","name":"Quantum mixed-state self-attention network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107123","authors":["Fu Chen","Qinglin Zhao","Li Feng","Chuangtao Chen","Yangbin Lin","Jianhong Lin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-08T18:16:15Z","doi":"10.1016/j.neunet.2025.107123","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.4018/979-8-3373-0523-3.ch004","name":"Evolutionary Metaheuristics for Neural Network Optimization","source":"crossref","abstract":"Neural networks have numerous hyperparameters, network designs, and weight combinations, making optimization challenging. Traditional methods like grid search and gradient descent often produce suboptimal solutions due to limited exploration. Genetic Algorithms (GAs), inspired by natural selection, provide an alternative by evolving populations across generations. Key GA operators include selection (e.g., Roulette Wheel, Tournament), crossover (e.g., Single-Point, Multi-Point), and mutation (e.g., Bit-Flip, Gaussian), which maintain diversity and avoid premature convergence. This chapter explores the use of GAs in neural network optimization, focusing on weight evolution, architectural search, and hyperparameter tuning. It also discusses GAs in medical image processing, improving tasks like disease detection, feature selection, and segmentation. GAs enhance diagnostic accuracy and treatment planning, especially in medical image analysis, offering effective optimization solutions in neural network training.","url":"https://doi.org/10.4018/979-8-3373-0523-3.ch004","authors":["Sridevi Tharanidharan","Prasanalakshmi Balaji","Gabriel Xiao-Guang Yue","Renuka Devi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-06T15:00:02Z","doi":"10.4018/979-8-3373-0523-3.ch004","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1007/s11063-025-11740-2","name":"WACSO: Wolf Crow Search Optimizer for Convolutional Neural Network Hyperparameter Optimization","source":"crossref","abstract":"Abstract Convolutional Neural Networks (CNNs) experience performance and training efficiency changes according to the selection of correct hyperparameters. The research presents WACSO which combines Crow Search Optimization with Grey Wolf Optimizer to improve Convolutional Neural Networks hyperparameter selection through a hybrid metaheuristic algorithm. The hybrid algorithm WACSO uses exploration parts from CSO together with GWO exploitation mechanics to obtain optimized performance. WACSO reaches higher classification accuracy than traditional optimization algorithms when performing tests on the MNIST and CIFAR-10 datasets along with Random Search and particle swarm optimization and genetic algorithms and standalone CSO and standalone GWO. The best classification results reached 98.9% accuracy levels on MNIST along with 91.5% accuracy levels on CIFAR-10. The final outcomes of this system depend on the combination of model structure along with dataset challenges and available computational power. The investigation demonstrates that mixing algorithms drawn from nature can lead to successful CNN hyperparameter optimization. The promising outcomes of WACSO depend on multiple variables including computation expenses and sensitive parameter adjustments and universal result adaptability between different datasets and network setups. Research into WACSO should expand to involve longer evaluations across multiple datasets and various models to confirm widespread usage.","url":"https://doi.org/10.1007/s11063-025-11740-2","authors":["Rahul Rajendra Papalkar","Jayendra Jadhav","Tareek Pattewar","Vivek Thorat","Pallavi Morey","Mayur Deshmukh","Rajkumar Jagdale"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-18T11:07:47Z","doi":"10.1007/s11063-025-11740-2","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.5220/0013733200004664","name":"Genetic Algorithm Based Optimization of Convolutional Neural Network for Respiratory Disease Detection","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0013733200004664","authors":["Vishwachetan D","Nandini S B","Pranjal Shrivastava","Nihal Jahagirdar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-26T09:33:50Z","doi":"10.5220/0013733200004664","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1080/0954898x.2024.2393746","name":"Transformer-based deep learning networks for fault detection, classification, and location prediction in transmission lines","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2024.2393746","authors":["Bousaadia Baadji","Soufiane Belagoune","Sif Eddine Boudjellal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-03T04:06:37Z","doi":"10.1080/0954898x.2024.2393746","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1080/0954898x.2025.2480294","name":"HUNHODRL: Energy efficient resource distribution in a cloud environment using hybrid optimized deep reinforcement model with HunterPlus scheduler","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2025.2480294","authors":["Senthilkumar Chellamuthu","Kalaivani Ramanathan","Rajesh Arivanandhan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-25T01:22:55Z","doi":"10.1080/0954898x.2025.2480294","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.17816/dv642028-4323920","name":"Fig. 1. Study design. Stages of training and analysis of the performance of neural networks for classification and detection of skin neoplasms. НС ― neural network. Source: Uskova K.A. et al., 2025.","source":"crossref","abstract":"","url":"https://doi.org/10.17816/dv642028-4323920","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-06T11:14:34Z","doi":"10.17816/dv642028-4323920","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1109/rsae65932.2025.11488105","name":"Bearing Remaining Useful Life Prediction Based on Dynamic Multiscale Spatio-Temporal Implicit Neural Differential Graph Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/rsae65932.2025.11488105","authors":["Jiayang Zhao","Chao Liu","Yuan Xu","Yang Fu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-28T19:46:03Z","doi":"10.1109/rsae65932.2025.11488105","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1007/978-3-032-04315-3_1","name":"Graph Neural Network Architectures and Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-04315-3_1","authors":["Farhana Yasmin","Mahade Hasan","Yu Xue","Md. Mehedi Hassan","Bernard-Marie Onzo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-31T15:28:08Z","doi":"10.1007/978-3-032-04315-3_1","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1016/0893-6080(88)90173-6","name":"Attention in a neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90173-6","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T01:05:53Z","doi":"10.1016/0893-6080(88)90173-6","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.17816/dv642028-4391760","name":"Fig. 1. Study design. Stages of training and analysis of the performance of neural networks for classification and detection of skin neoplasms. НС ― neural network. Source: Uskova K.A. et al., 2025.","source":"crossref","abstract":"","url":"https://doi.org/10.17816/dv642028-4391760","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-30T09:33:08Z","doi":"10.17816/dv642028-4391760","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1007/s00521-024-10811-0","name":"Analyzing feature importance with neural-network-derived trees","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-024-10811-0","authors":["Ernesto Vieira-Manzanera","Miguel A. Patricio","Antonio Berlanga","José M. Molina"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-13T10:39:40Z","doi":"10.1007/s00521-024-10811-0","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/nnice64954.2025.11063871","name":"Enhanced Physics-Informed Neural Network with Coarse Mesh Finite Element Pretraining","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nnice64954.2025.11063871","authors":["Ziwen Wang","Qimin Wang","Weisheng Zhang","Sheng Zhang","Shanmei Chen","Chao Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-15T17:39:55Z","doi":"10.1109/nnice64954.2025.11063871","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1007/s11063-017-9594-6","name":"Delay-Dependent Passivity and Stability Analysis for a Class of Memristor-Based Neural Networks with Time Delay in the Leakage Term","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11063-017-9594-6","authors":["Jian Liu","Rui Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-02-11T12:53:54Z","doi":"10.1007/s11063-017-9594-6","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.5220/0014688200005061","name":"An Advanced Cataract Detection Approach Using Deep Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0014688200005061","authors":["M. Vinesh","J. Praveenchandar","D. Linett Sophia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-31T15:51:38Z","doi":"10.5220/0014688200005061","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1109/mlsp62443.2025.11204270","name":"An Alternating Algorithm for Neural Collapse in Deep Classifier Neural Network with Arbitrary Number of Classes","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mlsp62443.2025.11204270","authors":["Rebero Musana Mayoelton","Thuan Nguyen","Thinh Nguyen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-24T17:15:52Z","doi":"10.1109/mlsp62443.2025.11204270","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1016/j.snr.2024.100269","name":"Recent progress in memristor-based gas sensors (Gasistor; gas sensor + memristor): Device modeling, mechanisms, performance, and prospects","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.snr.2024.100269","authors":["Mohsin Ali","Doowon Lee","Ibtisam Ahmad","Hee-Dong Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-07T11:39:29Z","doi":"10.1016/j.snr.2024.100269","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1080/0954898x.2024.2404915","name":"A novel approach for heart disease prediction using hybridized AITH\n                    <sup>2</sup>\n                    O algorithm and SANFIS classifier","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2024.2404915","authors":["Jayachitra Sekar","Prasanth Aruchamy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-25T12:21:52Z","doi":"10.1080/0954898x.2024.2404915","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1016/0893-6080(88)90430-3","name":"A hypercube compact neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90430-3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T05:05:53Z","doi":"10.1016/0893-6080(88)90430-3","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/edtm61175.2025.11041336","name":"Low-Complexity Method for Shortest Path Optimization Problems Based on Nanowire Memristor Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/edtm61175.2025.11041336","authors":["Yanming Liu","Shenghao Wu","Ming Jian","Daixuan Wu","Yanxi Long","He Tian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-30T17:36:02Z","doi":"10.1109/edtm61175.2025.11041336","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1117/12.3065219","name":"IoT device recognition based on variational autoencoder and multiscale convolutional network","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3065219","authors":["Jiawei Chang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-11T23:42:31Z","doi":"10.1117/12.3065219","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1007/978-3-319-76375-0_12","name":"Synapse as a Memristor","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-76375-0_12","authors":["Weiran Cai","Ronald Tetzlaff"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-11-12T22:03:43Z","doi":"10.1007/978-3-319-76375-0_12","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.25126/jtiik.2025128085","name":"Perbandingan Kinerja Arsitektur Convolutional Neural Network Pada Deteksi Malaria Menggunakan Citra Sel Darah","source":"crossref","abstract":"Malaria masih menjadi salah satu penyebab kematian tertinggi di dunia, terutama di daerah yang berstatus endemi. Standar emas penegakan diagnosis malaria adalah berbasis citra apusan atau sel darah yang diperoleh dengan menggunakan mikroskop. Kendala utama dalam penegakan diagnosis ini adalah kurangnya tenaga ahli untuk melakukan asesmen citra sel darah. Oleh karena itu, dilakukan diagnosis malaria berbasis citra sel darah menggunakan Artificial Intelligent (AI) / kecerdasan buatan. Deteksi malaria berbasis AI yang dilakukan pada studi-studi sebelumnya telah menghasilkan kinerja yang sudah baik. Namun, kinerja deteksi ini masih dapat ditingkatkan. Studi ini menggunakan 27.558 citra sel darah yang terdiri dari 13.779 sel darah terinfeksi dan 13.779 tidak terinfeksi. Citra-citra sel darah ini dibagi menjadi tiga kelompok, yaitu pelatihan (80%); validasi (10%); dan pengujian (10%). Pada studi ini, digunakan ResNet50; ResNet101; ResNet152; ResNet50V2; ResNet101V2; ResNet152V2; DenseNet121; DenseNet169; DenseNet201; InceptionV3; InceptionResNetV2; VGG16; VGG19; dan MobileNetV2. Tujuan utama dari studi ini adalah mencari arsitektur CNN yang memiliki kinerja terbaik dalam deteksi malaria berbasis citra sel darah. Perbandingan kinerja diases dengan menggunakan nilai akurasi, sensitivitas, spesifisitas, skor F1, dan Area Under the Curve (AUC). Arsitektur MobileNetV2 memberikan kinerja paling baik dengan nilai rata-rata pelatihan, validasi, dan pengujian tertinggi. Nilai rata-rata akurasi mencapai 97,68%; spesifisitas 98,61%; sensitivitas 96,75%; Skor F1 97,70%; dan AUC sebesar 99,65%. Selain itu, waktu pembuatan model arsitektur MobileNetV2 hanya sekitar 2,5 jam. Selain itu, jumlah lapisan convolutional tidak memengaruhi kinerja deteksi malaria. Dengan lapisan convolutional berjumlah 53, MobileNetV2 berkinerja lebih baik dibandingkan dengan arsitektur-arsitektur lain dengan jumlah lapisan convolutional lebih banyak. Abstract Malaria is still one of the highest causes of death in the world, especially in the endemic areas. The gold standard for diagnosing malaria is based on smears blood smears or cells image which is obtained using a microscope. The main challenge in detecting malaria is the lack of experts to assess the blood smears. Therefore, the detection is carried out using Artificial Intelligence (AI). Previous studies that used AI to detect malaria have a good performance. However, the detection performance can still be improved. Furthermore, previous studies only used one or two or three performance metrics. This study used 27,558 blood cell images consisting of 13,779 infected and 13,779 uninfected blood cells. These blood cell images are divided into three groups, i.e. training (80%); validation (10%); and testing (10%). In this study, several CNN architectures are used, such as ResNet50; ResNet101; ResNet152; ResNet50V2; ResNet101V2; ResNet152V; DenseNet121; DenseNet169; DenseNet201; InceptionV3; InceptionResNetV2; VGG16: VGG19: and MobileNetV2. The main objective of this study is to find the CNN architecture that has the best performance in blood cell image-based malaria detection. Comparison of performance of CNN architectures are assessed using accuracy, sensitivity, specificity, F1 score, and Area Under the Curve (AUC) values. The MobileNetV2 architecture provides the best performance with the highest average values of training, validation, and testing. The average accuracy value of 97.68%; specificity of 98.61%; sensitivity of 96,75%; F1 Score of 97.70%; and AUC of 0.9965. In addition, the time to build the MobileNetV2 model is about 2.5 hours, the fastest one. This study shows that the number of convolutional layers does not affect malaria detection performance. With 53 convolutional layers, MobileNetV2 has the best performance.","url":"https://doi.org/10.25126/jtiik.2025128085","authors":["Agung Wahyu Setiawan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-01T02:10:29Z","doi":"10.25126/jtiik.2025128085","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.52202/085713-3114","name":"You Only Spectralize Once: Taking a Spectral Detour to Accelerate Graph Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.52202/085713-3114","authors":["Yi Li","Zhichun Guo","Guanpeng Li","Bingzhe Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-06T14:44:29Z","doi":"10.52202/085713-3114","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.5220/0013457000003967","name":"3D Convolutional Neural Network to Predict the Energy Consumption of Milling Processes","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0013457000003967","authors":["Christoph Wald","Thomas Jung","Frank Schirmeier"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-03T11:17:03Z","doi":"10.5220/0013457000003967","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1016/j.neucom.2014.04.034","name":"Passivity and passification of memristor-based complex-valued recurrent neural networks with interval time-varying delays","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2014.04.034","authors":["R. Rakkiyappan","K. Sivaranjani","G. Velmurugan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-06-04T12:32:46Z","doi":"10.1016/j.neucom.2014.04.034","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1080/0954898x.2025.2483342","name":"User behaviour based insider threat detection model using an LSTM integrated RF model","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2025.2483342","authors":["S. K. Uma Maheswaran","L. Rajasekar","Ziaul Haque Choudhury","Makarand Shahade"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-08T10:51:32Z","doi":"10.1080/0954898x.2025.2483342","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1080/0954898x.2025.2453032","name":"JLeNeT: Jaccard LeNet for Parkinson’s disease detection and severity level classification using voice signal in IoT environment","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2025.2453032","authors":["Sundaresan Pragadeeswaran","Subramanian Kannimuthu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-12T03:20:11Z","doi":"10.1080/0954898x.2025.2453032","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.55248/gengpi.6.0525.18118","name":"Eletricity Theft Detection In Smart Grids  Based On Deep Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.55248/gengpi.6.0525.18118","authors":["K. Naresh","C. Krishnachaitantya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-01T04:46:23Z","doi":"10.55248/gengpi.6.0525.18118","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.29303/ijasds.v2i1.5855","name":"Peramalan Nilai Tukar Petani Kalimantan Timur Menggunakan Metode Neural Network","source":"crossref","abstract":"Nilai tukar petani (NTP) merupakan indikator yang sangat penting untuk mengukur daya beli para petani Indonesia, yang dimana mereka merupakan pelaku utama dalam sektor pertanian. Hal tersebut dikarenakan sektor pertanian adalah salah satu sektor utama di Indonesia, salah satunya di Provinsi Kalimantan Timur. Penelitian ini bertujuan untuk memprediksi dan meramalkan NTP Provinsi Kalimantan Timur menggunakan metode Neural Network (NN) dengan algoritma backpropagation. Data yang digunakan adalah data NTP Provinsi Kalimantan Timur periode Januari 2020 sampai dengan September 2024 yang diperoleh dari BPS Provinsi Kalimantan Timur. Penelitian ini menguji 5 model arsitektur NN yang berbeda jumlah lapisan pada hidden layer, yaitu 1, 2, 3, 4, dan 5 lapisan pada hidden layer. Penelitian dilakukan dengan menggunakan 1 variabel input, learning rate sebesar 0,01, maksimal 10.000 iterasi, dan threshold sebesar 0,5, Berdasarkan proses pelatihan yang telah dilakukan, diperoleh kesimpulan bahwa arsitektur NN terbaik yang dapat digunakan untuk meramalkan NTP Provinsi Kalimantan Timur adalah NN dengan 5 lapisan pada hidden layer dengan MAPE sebesar 2,087%.","url":"https://doi.org/10.29303/ijasds.v2i1.5855","authors":["Putri Aulia Rahmah","Memi Nor Hayati","Ariyanti Cahyaningsih"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-02T01:36:29Z","doi":"10.29303/ijasds.v2i1.5855","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1016/j.neunet.2023.08.041","name":"Chaos and multi-layer attractors in asymmetric neural networks coupled with discrete fractional memristor","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2023.08.041","authors":["Shaobo He","D. Vignesh","Lamberto Rondoni","Santo Banerjee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-01T02:34:34Z","doi":"10.1016/j.neunet.2023.08.041","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.32920/26883595","name":"Network Anomaly Detection Scheme Using Graph Neural Network","source":"crossref","abstract":"&lt;p&gt;Traditional intrusion detection systems (IDSs) and intrusion prevention systems (IPSs) focus on detecting, preventing, and blocking known attacks and obvious threats. Contrary to these systems, the Activity and Event Network (AEN) model is a newly proposed framework capable of identifying long-term threats and novel attack patterns such as custom crafted, multi-stage attack vectors, that the above-mentioned tools cannot detect as its design relies on a large random time varying graph model. In this thesis, the structural foundations of AEN graph are used as a basis to design a graph neural network (GNN)-based network anomaly detection scheme. This work is the first ever application of AEN to build a GNN model for anomaly detection purpose. The proposed model is evaluated using five different labelled datasets, namely, the DDoS, Tor-nonTor, Portmap, UDPLag, and SYN datasets, yielding preliminary promising results in terms of precision, recall, F1 score, and accuracy, chosen as performance metrics.&lt;/p&gt;","url":"https://doi.org/10.32920/26883595","authors":["Patrice Kisanger"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-05T16:37:05Z","doi":"10.32920/26883595","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1109/nnice64954.2025.11063784","name":"Construction of an Urban Transportation Safety Evaluation Model Based on AHP and Backpropagation Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nnice64954.2025.11063784","authors":["Fei Peng","Hui Wang","Lingli Han","Ziru Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-15T17:39:55Z","doi":"10.1109/nnice64954.2025.11063784","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.52202/085713-2911","name":"Asymptotically Stable Quaternion-valued Hopfield-structured Neural Network with Periodic Projection-based Supervised Learning Rules","source":"crossref","abstract":"","url":"https://doi.org/10.52202/085713-2911","authors":["Tianwei Wang","Xinhui Ma","Wei Pang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-06T14:44:29Z","doi":"10.52202/085713-2911","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.5220/0013351700003905","name":"Deep Neural Network Architectures for Advanced Hiking Map Generation","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0013351700003905","authors":["Olivier Schirm","Maxime Devanne","Jonathan Weber","Arnaud Lecus","Germain Forestier","Cédric Wemmert"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-28T12:43:00Z","doi":"10.5220/0013351700003905","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1109/ssitcon66133.2025.11342161","name":"Stock Market Price Prediction Using Neural Prophet with Deep Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ssitcon66133.2025.11342161","authors":["Navin Chhibber","Sunil Khemka","Navneet Kumar Tyagi","Rohit Tewari","Bireswar Banerjee","Piyush Ranjan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-22T20:58:23Z","doi":"10.1109/ssitcon66133.2025.11342161","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1109/coconet.2018.8476907","name":"Notice of Retraction: A Linear-Logarithmic CMOS-Memristor Vision Sensor","source":"crossref","abstract":"","url":"https://doi.org/10.1109/coconet.2018.8476907","authors":["Timur Malikov","Kamilya Smagulova","Alex Pappachen James"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-10-30T06:31:38Z","doi":"10.1109/coconet.2018.8476907","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.25126/jtiik.20258085","name":"Perbandingan Kinerja Arsitektur Convolutional Neural Network Pada Deteksi Malaria Menggunakan Citra Sel Darah","source":"crossref","abstract":"Malaria masih menjadi salah satu penyebab kematian tertinggi di dunia, terutama di daerah yang berstatus endemi. Standar emas penegakan diagnosis malaria adalah berbasis citra apusan atau sel darah yang diperoleh dengan menggunakan mikroskop. Kendala utama dalam penegakan diagnosis ini adalah kurangnya tenaga ahli untuk melakukan asesmen citra sel darah. Oleh karena itu, dilakukan diagnosis malaria berbasis citra sel darah menggunakan Artificial Intelligent (AI) / kecerdasan buatan. Deteksi malaria berbasis AI yang dilakukan pada studi-studi sebelumnya telah menghasilkan kinerja yang sudah baik. Namun, kinerja deteksi ini masih dapat ditingkatkan. Studi ini menggunakan 27.558 citra sel darah yang terdiri dari 13.779 sel darah terinfeksi dan 13.779 tidak terinfeksi. Citra-citra sel darah ini dibagi menjadi tiga kelompok, yaitu pelatihan (80%); validasi (10%); dan pengujian (10%). Pada studi ini, digunakan ResNet50; ResNet101; ResNet152; ResNet50V2; ResNet101V2; ResNet152V2; DenseNet121; DenseNet169; DenseNet201; InceptionV3; InceptionResNetV2; VGG16; VGG19; dan MobileNetV2. Tujuan utama dari studi ini adalah mencari arsitektur CNN yang memiliki kinerja terbaik dalam deteksi malaria berbasis citra sel darah. Perbandingan kinerja diases dengan menggunakan nilai akurasi, sensitivitas, spesifisitas, skor F1, dan Area Under the Curve (AUC). Arsitektur MobileNetV2 memberikan kinerja paling baik dengan nilai rata-rata pelatihan, validasi, dan pengujian tertinggi. Nilai rata-rata akurasi mencapai 97,68%; spesifisitas 98,61%; sensitivitas 96,75%; Skor F1 97,70%; dan AUC sebesar 99,65%. Selain itu, waktu pembuatan model arsitektur MobileNetV2 hanya sekitar 2,5 jam. Selain itu, jumlah lapisan convolutional tidak memengaruhi kinerja deteksi malaria. Dengan lapisan convolutional berjumlah 53, MobileNetV2 berkinerja lebih baik dibandingkan dengan arsitektur-arsitektur lain dengan jumlah lapisan convolutional lebih banyak. Abstract Malaria is still one of the highest causes of death in the world, especially in the endemic areas. The gold standard for diagnosing malaria is based on smears blood smears or cells image which is obtained using a microscope. The main challenge in detecting malaria is the lack of experts to assess the blood smears. Therefore, the detection is carried out using Artificial Intelligence (AI). Previous studies that used AI to detect malaria have a good performance. However, the detection performance can still be improved. Furthermore, previous studies only used one or two or three performance metrics. This study used 27,558 blood cell images consisting of 13,779 infected and 13,779 uninfected blood cells. These blood cell images are divided into three groups, i.e. training (80%); validation (10%); and testing (10%). In this study, several CNN architectures are used, such as ResNet50; ResNet101; ResNet152; ResNet50V2; ResNet101V2; ResNet152V; DenseNet121; DenseNet169; DenseNet201; InceptionV3; InceptionResNetV2; VGG16: VGG19: and MobileNetV2. The main objective of this study is to find the CNN architecture that has the best performance in blood cell image-based malaria detection. Comparison of performance of CNN architectures are assessed using accuracy, sensitivity, specificity, F1 score, and Area Under the Curve (AUC) values. The MobileNetV2 architecture provides the best performance with the highest average values of training, validation, and testing. The average accuracy value of 97.68%; specificity of 98.61%; sensitivity of 96,75%; F1 Score of 97.70%; and AUC of 0.9965. In addition, the time to build the MobileNetV2 model is about 2.5 hours, the fastest one. This study shows that the number of convolutional layers does not affect malaria detection performance. With 53 convolutional layers, MobileNetV2 has the best performance.","url":"https://doi.org/10.25126/jtiik.20258085","authors":["Agung Wahyu Setiawan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-01T01:45:39Z","doi":"10.25126/jtiik.20258085","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.7717/peerj.19393/fig-3","name":"Figure 3: Neural network architecture.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj.19393/fig-3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-09T04:36:47Z","doi":"10.7717/peerj.19393/fig-3","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.261Z"},{"id":"doi:10.7717/peerj-cs.2552/fig-1","name":"Figure 1: LSTM neural network.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.2552/fig-1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-12T03:21:59Z","doi":"10.7717/peerj-cs.2552/fig-1","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.261Z"},{"id":"doi:10.1109/dicct64131.2025.10986648","name":"Bounded Flux-Based Modelling of the Memristor and Implementation of Hybrid CMOS-Memristor Read-Write Circuit","source":"crossref","abstract":"","url":"https://doi.org/10.1109/dicct64131.2025.10986648","authors":["Bachina Vamsi Krishna","Manas Ranjan Tripathy","Jogendra Singh Rana","Prince Kumar Singh","Deep Chandra Upadhyay","Satyabrata Jit"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-12T17:41:43Z","doi":"10.1109/dicct64131.2025.10986648","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.4018/979-8-3693-7250-0.ch014","name":"Artificial Neural Network Predictions of Heat Transfer of Flat Plate Collector With Hybrid Nanofluids","source":"crossref","abstract":"The Nusselt number, heat transfer, and friction factor of a flat plate collector operating with hybrid nanofluids of Al2O3-CuO and water are utilized in the Support Vector Regression method of artificial neural networks. The volume loadings used in the experiments were 0.048%, 0.096%, 0.144%, 0.192%, and 0.24%. The experiments ran from 09:00 to 16:30 hours. Time zone 1 (09:00 to 13:00 hr) and time zone 2 (13:00 to 16:30) are applied. Nusselt number is increased by 20.43% at time zone-1, at 13:00 hours, at 0.24% vol. and at a Reynolds number of 364.66, and by 14.08% at time zone-2, at 16:30 hours, at 0.24% vol. and at a Reynolds number of 211.23, respectively, above the base fluid. Similarly, the friction factor is increased by 15.34% and 11.50% above the base fluid for time zones 1 and 2, respectively, at 13:00 and 16:30, at 0.24% vol. and Reynolds numbers 364.66 and 211.23. The support vector regression algorithm in use makes accurate predictions about the values. Nusselt number, heat transfer, and friction factor have correlation values of 0.99497, 0.9947, and 0.9995.","url":"https://doi.org/10.4018/979-8-3693-7250-0.ch014","authors":["Lingala Syam","Solomon Mesfin","Veeredhi Vasudeva Rao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-05T12:23:32Z","doi":"10.4018/979-8-3693-7250-0.ch014","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.38007/nn.2021.020106","name":"Emotion Analysis of Shopping Software Reviews Based on Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2021.020106","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T18:10:50Z","doi":"10.38007/nn.2021.020106","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.4018/978-1-6684-2408-7.ch004","name":"Artificial Neural Network Research in Online Social Networks","source":"crossref","abstract":"Artificial neural networks are a machine learning method ideal for solving classification and prediction problems using Big Data. Online social networks and virtual communities provide a plethora of data. Artificial neural networks have been used to determine the emotional meaning of virtual community posts, determine age and sex of users, classify types of messages, and make recommendations for additional content. This article reviews and examines the utilization of artificial neural networks in online social network and virtual community research. An artificial neural network to predict the maintenance of online social network “friends” is developed to demonstrate the applicability of artificial neural networks for virtual community research.","url":"https://doi.org/10.4018/978-1-6684-2408-7.ch004","authors":["Steven Walczak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-17T11:47:50Z","doi":"10.4018/978-1-6684-2408-7.ch004","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.54914/jtt.v11i2.1900","name":"Deteksi Penyakit Kulit dengan Metode Convolutional Neural Network Menggunakan Arsitektur VGG19","source":"crossref","abstract":"Deteksi dini penyakit kulit merupakan tantangan signifikan, khususnya di daerah dengan keterbatasan layanan medis dermatologis. Masalah ini diperparah oleh kurangnya tenaga medis spesialis serta maraknya informasi kesehatan yang tidak akurat di internet. Tujuan dari penelitian ini adalah mengembangkan sistem klasifikasi otomatis berbasis citra digital guna mengidentifikasi lima jenis penyakit kulit: Eczema, Melanocytic Nevus, Melanoma, Benign Keratosis, dan Basal Cell Carcinoma. Metode yang digunakan adalah Convolutional Neural Network (CNN) dengan arsitektur VGG19 melalui pendekatan transfer learning dan fine-tuning parsial pada layer block4_conv1. Dataset terdiri dari 10.000 gambar berformat .jpg yang telah melalui tahap normalisasi, augmentasi, deteksi tepi, dan penyeimbangan kelas. Evaluasi dilakukan menggunakan metrik akurasi, presisi, recall, F1-score, dan confusion matrix. Hasil eksperimen menunjukkan bahwa model mencapai akurasi hingga 84% pada skenario terbaik, dengan keseimbangan metrik lainnya yang menunjukkan kinerja klasifikasi multi-kelas yang andal. Kesimpulan dari penelitian ini menunjukkan bahwa arsitektur VGG19 efektif untuk mendeteksi berbagai penyakit kulit berbasis citra. Implikasi dari hasil ini membuka peluang pengembangan sistem deteksi awal berbasis aplikasi mobile, terutama untuk membantu masyarakat di daerah dengan keterbatasan layanan medis.","url":"https://doi.org/10.54914/jtt.v11i2.1900","authors":["Ainunnisa Indah Rizqya","Nanda Martyan Anggadimas","Muhammad Misdram"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-19T09:05:45Z","doi":"10.54914/jtt.v11i2.1900","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1109/icrc64395.2024.10937007","name":"Compressed vector-matrix multiplication for Memristor-based ensemble neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icrc64395.2024.10937007","authors":["Phan Anh Vu","François Rummens","Marielle Malfante","Bertrand Rivet","Thomas Dalgaty"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-28T03:23:48Z","doi":"10.1109/icrc64395.2024.10937007","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1016/j.chaos.2023.113807","name":"Discrete memristor applied to construct neural networks with homogeneous and heterogeneous coexisting attractors","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.chaos.2023.113807","authors":["Qiang Lai","Liang Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-17T06:39:18Z","doi":"10.1016/j.chaos.2023.113807","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.261Z"},{"id":"doi:10.52202/085713-3149","name":"Shortcut Features as Top Eigenfunctions of NTK: A Linear Neural Network Case and More","source":"crossref","abstract":"","url":"https://doi.org/10.52202/085713-3149","authors":["Jinwoo Lim","Suhyun Kim","Soo-Mook Moon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-06T14:44:29Z","doi":"10.52202/085713-3149","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.5220/0013143000003912","name":"Neural Network Meta Classifier: Improving the Reliability of Anomaly Segmentation","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0013143000003912","authors":["Jurica Runtas","Tomislav Petković"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-03T22:55:07Z","doi":"10.5220/0013143000003912","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1080/0954898x.2024.2349275","name":"Hybrid deep learning approach for sentiment analysis using text and emojis","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2024.2349275","authors":["Arjun Kuruva","C. Nagaraju Chiluka"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-29T06:38:04Z","doi":"10.1080/0954898x.2024.2349275","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/tnn.2011.2163318","name":"Zhang Neural Network Versus Gradient Neural Network for Solving Time-Varying Linear Inequalities","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnn.2011.2163318","authors":["Lin Xiao","Yunong Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-08-16T15:15:49Z","doi":"10.1109/tnn.2011.2163318","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.261Z"},{"id":"doi:10.7717/peerjcs.1671/fig-3","name":"Figure 3: Recurrent neural network.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerjcs.1671/fig-3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-16T03:24:13Z","doi":"10.7717/peerjcs.1671/fig-3","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.261Z"},{"id":"doi:10.51903/jgn2sd35","name":"IDENTIFICATION OF ROAD DAMAGE USING THE CONVOLUTIONAL NEURAL NETWORK (CNN) METHOD","source":"crossref","abstract":"Kerusakan jalan merupakan permasalahan umum yang berdampak langsung terhadap keselamatan dan kenyamanan pengguna jalan, serta terhadap efisiensi transportasi. Selama ini, proses inspeksi jalan masih dilakukan secara manual, yang memerlukan waktu, biaya, dan sumber daya yang tidak sedikit. Penelitian ini bertujuan untuk mengembangkan sistem klasifikasi otomatis guna mendeteksi kerusakan jalan berdasarkan citra permukaan, dengan memanfaatkan metode Convolutional Neural Network (CNN). Dataset yang digunakan dalam penelitian ini terdiri dari 400 gambar dengan distribusi seimbang, yaitu 200 gambar kategori Cracks (jalan retak) dan 200 gambar kategori non-Cracks (jalan tidak retak), yang diambil dari sumber dataset terbuka di platform Mendeley Data. Arsitektur CNN dirancang secara khusus dengan empat lapisan konvolusi yang dilengkapi fungsi aktivasi ReLU, pooling layer, dropout layer untuk mengurangi overfitting, serta fully connected layer pada tahap akhir klasifikasi. Proses pelatihan dilakukan menggunakan TensorFlow dan Keras di platform Google Colab, dengan pembagian data sebesar 80% untuk data pelatihan dan 20% untuk data validasi. Hasil evaluasi menunjukkan bahwa model memiliki performa klasifikasi yang sangat baik. Berdasarkan rata-rata dari seluruh skenario pelatihan (epoch 30, 40, dan 50), model CNN yang dikembangkan mampu mencapai akurasi keseluruhan sebesar 97,50%, presisi rata-rata 96,77%, recall rata-rata 99,37%, dan F1-score rata-rata 97,72%. Dengan kinerja yang konsisten dan tingkat kesalahan yang rendah, model CNN ini memiliki potensi besar untuk diterapkan sebagai alat bantu dalam proses identifikasi kerusakan jalan berbasis citra secara otomatis dan efisien, sehingga dapat mempercepat inspeksi, mengurangi beban kerja manual, dan membantu instansi terkait dalam pengambilan keputusan pemeliharaan infrastruktur jalan secara tepat waktu.","url":"https://doi.org/10.51903/jgn2sd35","authors":["Ahmad Syafiq Maulana Zuhri","Nur Nafiiyah","Agus Setia Budi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-30T20:24:39Z","doi":"10.51903/jgn2sd35","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.2172/2432449","name":"NuGraph2: A Graph Neural Network for Neutrino Event Reconstruction","source":"crossref","abstract":"","url":"https://doi.org/10.2172/2432449","authors":["Giuseppe Cerati"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-23T03:10:37Z","doi":"10.2172/2432449","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1115/1.859599.paper13","name":"Monitoring Artificial Neural Network Performance Degradation under Network Damage","source":"crossref","abstract":"","url":"https://doi.org/10.1115/1.859599.paper13","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-11-15T10:59:57Z","doi":"10.1115/1.859599.paper13","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.26226/morressier.612f6735bc9810372410076a","name":"Artificial Neural Network and Recurrent Neural Network Approaches for Isotropic and Anisotropic Plastic Material Modeling","source":"crossref","abstract":"","url":"https://doi.org/10.26226/morressier.612f6735bc9810372410076a","authors":["Jing Bi","Zhenyuan Gao","Victor Oancea"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-10T20:26:32Z","doi":"10.26226/morressier.612f6735bc9810372410076a","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.12732/ijam.v38i4s.1530","name":"GRAPHSECNET: A GRAPH NEURAL NETWORK FRAMEWORK FOR PREDICTIVE CYBERSECURITY INTELLIGENCE IN DYNAMIC NETWORK ENVIRONMENTS","source":"crossref","abstract":"Contemporary cybersecurity threats exploit complex network topologies and temporal attack patterns that traditional detection systems fail to adequately model. This paper presents GraphSecNet, a novel Graph Neural Network framework that transforms network security data into dynamic graph representations for enhanced threat detection. The framework integrates Temporal Graph Attention Networks, self-supervised contrastive learning, and multi-perspective anomaly detection to capture both spatial network relationships and temporal attack evolution. Comprehensive evaluation on established cybersecurity datasets (CICIDS2017, UNSW-NB15, NSL-KDD) demonstrates significant performance improvements: 91.7% F1-score representing 9.8% improvement over state-of-the-art methods, 46% reduction in false positive rates, and scalable processing at 25,000 events per second. Graph attention mechanisms provide interpretable explanations for threat decisions, addressing critical gaps in explainable AI for cybersecurity. Statistical analysis confirms significance across all datasets (p &lt; 0.001, Cohen's d &gt; 1.8), validating the effectiveness of graph-based approaches for network threat intelligence.","url":"https://doi.org/10.12732/ijam.v38i4s.1530","authors":["Yogish Pai U"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-20T09:26:12Z","doi":"10.12732/ijam.v38i4s.1530","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1109/asns67347.2025.11345720","name":"Research on Real-time DDoS Attack Detection System Based on One-dimensional Deep Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/asns67347.2025.11345720","authors":["Youce Wang","Qingquan Liu","Peng Liang","Chengxuan Sui"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-19T20:53:15Z","doi":"10.1109/asns67347.2025.11345720","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.3934/era.2021041","name":"Synchronization for a class of complex-valued memristor-based competitive neural networks(CMCNNs) with different time scales","source":"crossref","abstract":"","url":"https://doi.org/10.3934/era.2021041","authors":["Yong Zhao","Shanshan Ren"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-06-04T00:16:40Z","doi":"10.3934/era.2021041","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1007/s11063-017-9675-6","name":"Synchronization Control of Coupled Memristor-Based Neural Networks with Mixed Delays and Stochastic Perturbations","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11063-017-9675-6","authors":["Chuan Chen","Lixiang Li","Haipeng Peng","Yixian Yang","Tao Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-07-18T15:48:55Z","doi":"10.1007/s11063-017-9675-6","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1007/s11071-025-11357-z","name":"Initial condition-induced synchronization and chimera state in memristor synapse-coupled memristive Hopfield neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11071-025-11357-z","authors":["Chengjie Chen","Fuhong Min","Yunzhen Zhang","Han Bao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-22T11:04:17Z","doi":"10.1007/s11071-025-11357-z","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1109/icdsns65743.2025.11168624","name":"Design and Development of an Intelligent Digital Marketing System Using Hybrid Collaborative Filtering with Context-Aware Deep Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icdsns65743.2025.11168624","authors":["Yanling Liu","Zhenhua Xiao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-29T17:50:45Z","doi":"10.1109/icdsns65743.2025.11168624","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1080/0954898x.2025.2503791","name":"BUBMO-based Bi-GRU-CNN model for crop classification with improved feature set: A bigdata perspective","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2025.2503791","authors":["Shivi Sharma","D D Sharma","Ashish Sharma","Munish Manas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-03T06:57:06Z","doi":"10.1080/0954898x.2025.2503791","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1109/icdsns65743.2025.11168538","name":"Backpropagation Neural Network for Science and Technology Finance Evaluation Model for Citylevel Stf Assessment","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icdsns65743.2025.11168538","authors":["Yufei Ye","Xuerong Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-29T17:50:45Z","doi":"10.1109/icdsns65743.2025.11168538","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1016/j.mssp.2024.109203","name":"A flexible artificial synapse based on the two-dimensional CuInS2 memristor for neural morphology calculation","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.mssp.2024.109203","authors":["Zhong-Jie Chen","Zhenhua Tang","Zhao-Yuan Fan","Jun-Lin Fang","Fan Qiu","Yan-Ping Jiang","Xin-Gui Tang","Yi-Chun Zhou","Xiujuan Jiang","Ju Gao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-10T17:45:15Z","doi":"10.1016/j.mssp.2024.109203","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.4018/979-8-3373-0735-0.ch001","name":"Introduction to Neural Networks","source":"crossref","abstract":"Neural networks, inspired by the biological neural structures in the human brain, are computational models that are central to many modern artificial intelligence applications. These networks consist of interconnected layers of nodes, or neurons, that process data through weighted connections and activation functions. The flexibility of neural networks enables them to solve a wide range of complex problems, including pattern recognition, classification, and prediction tasks. This abstract provides a concise overview of the fundamental principles behind neural networks, their architecture, training methodologies, and their application across diverse fields such as computer vision, natural language processing, and autonomous systems. Neural networks' ability to learn from large datasets and adapt to various input patterns has revolutionized fields such as machine learning and deep learning, making them indispensable tools for solving real-world challenges.","url":"https://doi.org/10.4018/979-8-3373-0735-0.ch001","authors":["D. Pavunraj","K. Anbumaheshwari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-29T17:14:01Z","doi":"10.4018/979-8-3373-0735-0.ch001","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.7498/aps.73.20231888","name":"A novel compound exponential locally active memristor coupled Hopfield neural network","source":"crossref","abstract":"The neural network model coupled with memristors has been extensively studied due to its ability to more accurately represent the complex dynamic characteristics of the biological nervous system. Currently, the mathematical model of memristor used to couple neural networks mainly focuses on primary function, absolute value function, hyperbolic tangent function, etc. To further enrich the memristor-coupled neural network model and take into account the motion law of particles in some doped semiconductors, a new compound exponential local active memristor is proposed and used as a coupling synapse in the Hopfield neural network. Using the basic dynamic analysis method, the system’s dynamic behaviors are studied under different parameters and the coexistence of multiple bifurcation modes under different initial values. In addition, the influence of frequency change of external stimulation current on the system is also studied. The experimental results show that the internal parameters of memristor synapses regulate the system, and the system has a rich dynamic behavior, including symmetric attractor coexistence, asymmetric attractor coexistence, large-scale chaos as shown in attached figure, and bursting oscillation. Finally, the hardware of the system is realized by the STM32 microcontroller, and the experimental results verify the realization of the system.","url":"https://doi.org/10.7498/aps.73.20231888","authors":["Meng-Jiao Wang","Chen Yang","Shao-Bo He","Zhi-Jun Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-17T09:41:05Z","doi":"10.7498/aps.73.20231888","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1145/3765612.3767779","name":"Novel Graph Neural Network Method for Differential Network Analysis in Biological Data","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3765612.3767779","authors":["Marianna Milano","Pietro Hiram Guzzi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-10T17:45:59Z","doi":"10.1145/3765612.3767779","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.59879/ty0kz","name":"DEEP LEARNING BASED AGRICULTURE TRAFFIC PREDICTION USING GATED RECURSIVE DEEP NEURAL NETWORK IOT ENVIRONMENT","source":"crossref","abstract":"IoT traffic data can be used to apply deep learning technology to agriculture. The application of deep learning algorithms in agriculture has improved, resource management, and decisionmaking with positive outcomes. Precision agriculture can assist regulate crop yields by applying nutrients only when necessary to enhance crop quality and lessen adverse environmental effects. This is made possible by IoT capabilities. Identifying redundant data traffic remains a major research challenge in the field of IoT-based agricultural automation, despite the fact that numerous solutions have been offered. Additionally, farmers do not receive the necessary information about water levels, soil conditions, etc.","url":"https://doi.org/10.59879/ty0kz","authors":["M. Sofiya","M. Arulmozhi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-15T15:52:21Z","doi":"10.59879/ty0kz","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1109/dsp65409.2025.11075102","name":"Robust Neural Network Revived for Adaptive Blind Separation of Complex Wireless Signals","source":"crossref","abstract":"","url":"https://doi.org/10.1109/dsp65409.2025.11075102","authors":["Marek Klemes"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-15T17:41:05Z","doi":"10.1109/dsp65409.2025.11075102","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1016/j.dsp.2025.105243","name":"Convolutional neural network-based spectrum sensing for NOMA cognitive radio networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.dsp.2025.105243","authors":["Saikat Majumder"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-14T11:08:06Z","doi":"10.1016/j.dsp.2025.105243","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.11648/j.ajnna.20251102.13","name":"A Fuzzy Neural Network System for Denoising Magnetic Resonance Images","source":"crossref","abstract":"Image acquisition is an essential step in image processing. When the image acquisition is done the image that is generated is subjected to Impulse noise, Gaussian noise etc. We have performed the image denoising on images inflicted with impulse noise. Image denoising is an essential step in all types of image processing. Traditional techniques reduce the noise in the image but it also reduces the quality of the image. Traditional filters like gaussian filter, median filter is analyzed which work in the spatial domain and filters working in the frequency domain are also considered like Butterworth filters, Weiner filter. A Deep residual Neural Network filter is proposed which is compared with the Fuzzy Neural Network denoiser. Their performance is compared on the metrics PSNR and SSIM. The Fuzzy Neural Network system improves the SSIM significantly compared to a deep residual neural network and a comparison is made with traditional image denoising methods. We also compare the performance of the deep residual neural network, Fuzzy Neural Network system and Median denoising algorithm on impulse noise has been compared. The performance of deep neural networks depends on the total number of examples used and the performance can be improved if we have more image pairs.","url":"https://doi.org/10.11648/j.ajnna.20251102.13","authors":["Shubhajoy Das","Debashis Das"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-12T12:05:14Z","doi":"10.11648/j.ajnna.20251102.13","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1080/0954898x.2024.2395375","name":"RP squeeze U-SegNet model for lesion segmentation and optimization enabled ShuffleNet based multi-level severity diabetic retinopathy classification","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2024.2395375","authors":["Zulaikha Beevi Sulaiman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-25T13:37:15Z","doi":"10.1080/0954898x.2024.2395375","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/access.2025.3603403","name":"A Hybrid Graph Neural Network Model for Predicting Cyber Attacks From Heterogeneous and Dynamic Network Data","source":"crossref","abstract":"","url":"https://doi.org/10.1109/access.2025.3603403","authors":["Mücahit Soylu","Resul Das"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-27T18:32:22Z","doi":"10.1109/access.2025.3603403","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.7717/peerj-cs.773/fig-5","name":"Figure 5: Simplified neural network.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.773/fig-5","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-17T04:36:01Z","doi":"10.7717/peerj-cs.773/fig-5","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.3934/era.2024156","name":"Synchronization analysis of delayed quaternion-valued memristor-based neural networks by a direct analytical approach","source":"crossref","abstract":"&lt;abstract&gt;&lt;p&gt;This issue discusses the asymptotic synchronization and the exponential synchronization for memristor-based quaternion-valued neural networks under the time-varying delays. Some criteria for synchronization of the memristor-based quaternion-valued neural networks are given by exploiting the set-valued theory, the differential inclusion theory, some analytic techniques, as well as constructing novel controllers, It is worth noting that the synchronization problem about the memristor-based quaternion-valued neural networks were studied by the direct analysis method in this paper. Finally, the main theoretical results were verified by numerical simulations.&lt;/p&gt;&lt;/abstract&gt;","url":"https://doi.org/10.3934/era.2024156","authors":["Jun Guo","Yanchao Shi","Shengye Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-29T06:52:57Z","doi":"10.3934/era.2024156","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.38007/nn.2020.010306","name":"Intelligent Monitoring of Cabin Temperature Based on Recurrent Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2020.010306","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T18:09:49Z","doi":"10.38007/nn.2020.010306","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.23919/chicc.2017.8027984","name":"H&lt;inf&gt;∞&lt;/inf&gt; control design for memristor-based neural networks subject to actuator saturation","source":"crossref","abstract":"","url":"https://doi.org/10.23919/chicc.2017.8027984","authors":["Xiao-Wei Zhang","Huai-Ning Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-09-29T19:54:00Z","doi":"10.23919/chicc.2017.8027984","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.22541/au.161522093.39767392/v1","name":"Supporting Information for “Self-adaptive Learning in Memristor Convolutional Neural Networks”   ","source":"crossref","abstract":"","url":"https://doi.org/10.22541/au.161522093.39767392/v1","authors":["Mingqiang Huang","Wei Zhang","Lunshuai Pan","Xuelong Yan","Guangchao Zhao","Hong Chen","Xingli Wang","Beng Kang Tay","Gaokuo Zhong","Jiangyu Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-08T11:29:05Z","doi":"10.22541/au.161522093.39767392/v1","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1016/j.knosys.2025.114301","name":"Cascade stacked autoencoder neural network for intrusion detection in CAN-FD vehicular network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.knosys.2025.114301","authors":["V. Anjana Devi","P.V. Bhaskar Reddy","Sreenu Ponnada","K. Suresh Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-18T07:36:33Z","doi":"10.1016/j.knosys.2025.114301","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1504/ijdsde.2025.10072674","name":"The Information Perception Analysis of Complex Network based on Local Similar Clustering and BP Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1504/ijdsde.2025.10072674","authors":["Meijing Song","Yajing Lu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-31T13:00:15Z","doi":"10.1504/ijdsde.2025.10072674","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1109/iccss.2017.8091463","name":"Intermittent control of memristor-based recurrent neural networks with time-varying delays","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccss.2017.8091463","authors":["Fengqiu Liu","Min Qiu","Sitian Qin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-11-22T12:46:21Z","doi":"10.1109/iccss.2017.8091463","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1080/0954898x.2023.2279973","name":"RETRACTED ARTICLE: A clustering approach for attack detection and data transmission in vehicular ad-hoc networks","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2023.2279973","authors":["Atul Barve","Pushpinder Singh Patheja"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-18T21:19:02Z","doi":"10.1080/0954898x.2023.2279973","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1007/s12668-020-00807-0","name":"Fault Tolerance of Memristor-Based Perceptron Network for Neural Interface","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s12668-020-00807-0","authors":["Sergey Shchanikov","Ilya Bordanov","Anton Zuev","Sergey Danilin","Dmitry Korolev","Alexey Belov","Alexey Mikhaylov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-11-12T02:02:39Z","doi":"10.1007/s12668-020-00807-0","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1007/978-3-540-48125-6_3","name":"Qualitative Characteristics of Neural Network Architectures","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-540-48125-6_3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-10-28T00:36:19Z","doi":"10.1007/978-3-540-48125-6_3","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.7717/peerj.19645/fig-3","name":"Figure 3: Convolutional neural network.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj.19645/fig-3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-30T04:41:36Z","doi":"10.7717/peerj.19645/fig-3","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1117/12.3064986","name":"Reinforcement learning-based MTC random access and heterogeneous network resource allocation","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3064986","authors":["Ying Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-11T19:42:35Z","doi":"10.1117/12.3064986","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.38007/nn.2022.030403","name":"Enterprise Risk Early Warning Model Based on Recurrent Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2022.030403","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T06:22:51Z","doi":"10.38007/nn.2022.030403","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1088/0954-898x/3/3/004","name":"Analysis of the equilibrium properties of a continuous neural network made of excitatory and inhibitory neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/3/3/004","authors":["Antônio Filho"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-24T22:35:54Z","doi":"10.1088/0954-898x/3/3/004","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1088/0954-898x/5/3/002","name":"Modelling the effect of the missing fundamental with an attractor neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/5/3/002","authors":["Lubica Be&nbreve;u&sbreve;ková"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/5/3/002","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1201/9781420015454-12","name":"Neural Network Output Feedback Controller Design and Embedded Hardware Implementation","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781420015454-12","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-01T19:22:01Z","doi":"10.1201/9781420015454-12","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1007/978-3-319-12436-0_4","name":"Anti-Synchronization Control for Memristor-Based Recurrent Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-12436-0_4","authors":["Ning Li","Jinde Cao","Mengzhe Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-11-21T13:16:45Z","doi":"10.1007/978-3-319-12436-0_4","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.4018/978-1-5225-2317-8.les2","name":"Multilayer Neural Network Architectures","source":"crossref","abstract":"","url":"https://doi.org/10.4018/978-1-5225-2317-8.les2","authors":["Siddhartha Bhattacharyya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-01-24T16:04:07Z","doi":"10.4018/978-1-5225-2317-8.les2","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.38007/nn.2020.010102","name":"Face Recognition System in Intelligent Building Based on Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2020.010102","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T03:35:42Z","doi":"10.38007/nn.2020.010102","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1007/978-3-031-95111-4_16","name":"Traffic Speed Prediction Using MAB-STGNN: Graph Neural Network Built-In Model for Spatial–Temporal Graph Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-95111-4_16","authors":["Renuka Mandlik","Saiedeh Razavi","Susan Tighe"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-01T00:19:59Z","doi":"10.1007/978-3-031-95111-4_16","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1016/j.knosys.2024.112698","name":"Optimized high-dimensional memristive hopfield neural network for DoS attack detection in Mobile Adhoc Network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.knosys.2024.112698","authors":["Gayathri Devi S","Chandia S","Savithri V","Saraswathi K"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-19T17:44:59Z","doi":"10.1016/j.knosys.2024.112698","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1109/iccasit66611.2025.11348733","name":"Research on the Integration and Optimization Strategies of Artificial Intelligence and Neural Network Technologies in Communication Network Security Management","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccasit66611.2025.11348733","authors":["Mingqi Meng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-29T21:18:30Z","doi":"10.1109/iccasit66611.2025.11348733","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1109/acdsa65407.2025.11166127","name":"LBM-GNN: Graph Neural Network Enhanced Lattice Boltzmann Method","source":"crossref","abstract":"","url":"https://doi.org/10.1109/acdsa65407.2025.11166127","authors":["Yue Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-24T17:31:35Z","doi":"10.1109/acdsa65407.2025.11166127","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1007/978-94-009-0643-3_137","name":"A Modular and Expandable Analog Integrated Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-94-009-0643-3_137","authors":["O. Rossetto","C. Jutten"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-12-09T03:06:39Z","doi":"10.1007/978-94-009-0643-3_137","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.38007/nn.2022.030107","name":"Clothing Feature Recognition and Classification Based on Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2022.030107","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T18:13:37Z","doi":"10.38007/nn.2022.030107","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.38007/nn.2021.020104","name":"Enterprise Financial Risk Early Warning Based on Deep Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2021.020104","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T18:10:50Z","doi":"10.38007/nn.2021.020104","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.2139/ssrn.5255540","name":"A Physics-Informed Neural Network Model to Predict Thermo-Oxidative/Thermal Aging of Viscoelastic Materials","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5255540","authors":["Hossein Naderi","Roozbeh Dargazany"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-15T12:40:26Z","doi":"10.2139/ssrn.5255540","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.21203/rs.3.rs-6213558/v1","name":"BioLogicalNeuron: A Biologically Inspired Neural Network Layer with Homeostatic Regulation and Adaptive Repair Mechanism","source":"crossref","abstract":"Abstract Neural networks face persistent challenges in maintaining stability and robustness during training, particularly in noisy or high-dimensional domains like molecular analysis. Inspired by biological neural systems that leverage homeostasis and self-repair to sustain functionality, this paper proposes BioLogicalNeuron—a novel neural network layer that integrates calcium-driven homeostatic regulation, adaptive repair mechanisms, and dynamic stability monitoring. The layer mimics biological calcium dynamics to maintain neuronal activity within optimal ranges, proactively triggers targeted synaptic repair and adaptive noise injection to counteract degradation, and modulates learning rates via real-time health metrics. Extensive experiments across multiple molecular and chemical datasets show that BioLogicalNeuron achieves state-of-the-art break performance. The layer's performance is particularly strong on molecular datasets, where its biological mechanisms naturally align with molecular structure learning. Through detailed analysis of calcium dynamics and health-stability relationships, this work demonstrate that BioLogicalNeuron achieves a biologically plausible balance between stability and plasticity, offering insights into both artificial and biological neural networks. This results suggest that incorporating biological mechanisms into neural architectures can lead to more robust and effective learning systems, particularly for molecular and chemical analysis tasks.","url":"https://doi.org/10.21203/rs.3.rs-6213558/v1","authors":["MD Hakim","Mohammad Alam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-13T23:08:37Z","doi":"10.21203/rs.3.rs-6213558/v1","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.2139/ssrn.5082130","name":"Deep Convolutional Neural Network and Enhanced Wavelet Transform for Single Image De-Hazing","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5082130","authors":["Naresh Malothu","Prof. Ravi kumar Jatoth"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-04T07:40:17Z","doi":"10.2139/ssrn.5082130","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.2139/ssrn.5385607","name":"Ultra-Compact Neural Network Adc Exploiting Ferroelectric Fets","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5385607","authors":["Ayan Banerjee","Sagnik Bhattacharya","Arka Chakraborty","Yogesh  Singh Chauhan","Shubham Sahay"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-09T18:42:39Z","doi":"10.2139/ssrn.5385607","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1088/2634-4386/addee7/v2/review1","name":"Review for \"A spiking photonic neural network of 40,000 neurons, trained with latency and rank-order coding for leveraging sparsity\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2634-4386/addee7/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-31T17:07:02Z","doi":"10.1088/2634-4386/addee7/v2/review1","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1002/eng2.70373/v1/decision1","name":"Decision letter for \"Enhancing Cardiovascular Disease Analysis in Healthcare Systems With Hybrid Random Forest and Neural Network Algorithm\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/eng2.70373/v1/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T23:21:22Z","doi":"10.1002/eng2.70373/v1/decision1","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:32.245Z"},{"id":"doi:10.1038/s41598-026-48581-5","name":"Stochastic fractional-order memristive fuzzy bam neural networks with time delays and leakage term for finite-time stability analysis.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-48581-5","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-48581-5","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acsomega.5c13576","name":"Programmable Speech Recognition Based on Cu/CuBiSe&lt;sub&gt;2&lt;/sub&gt;/SrNbO&lt;sub&gt;3&lt;/sub&gt;/W Memristors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsomega.5c13576","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsomega.5c13576","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1126/sciadv.adx6227","name":"Piezoelectric surface acoustic wave memristor neural network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.adx6227","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1126/sciadv.adx6227","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.3390/mi17040393","name":"A Dual-Mode Memristor-Based Oscillator for Energy-Efficient Biomedical Wireless Systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/mi17040393","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/mi17040393","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/tcyb.2025.3597576","name":"Memristor-Based CMAC Neural Network Circuit of Artificial Fish Behavioral Decision With Fuzzy Emotion and Its Application.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tcyb.2025.3597576","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1109/tcyb.2025.3597576","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1038/s41467-025-66240-7","name":"Error-aware probabilistic training for memristive neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-66240-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-66240-7","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1002/advs.202511801","name":"An Ultrathin, Cyano-Functionalized Copolymeric Memristor by iCVD Process for Driving Convolutional Neural Networks of High-Resolution Images.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202511801","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.202511801","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.22541/au.176313996.66970346/v2","name":"Physics-Driven In-House Memristor Cross-Bar Array Model for Image Classification","source":"europepmc","abstract":"","url":"https://doi.org/10.22541/au.176313996.66970346/v2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.22541/au.176313996.66970346/v2","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1038/s41467-025-65233-w","name":"Memristor-based adaptive analog-to-digital conversion for efficient and accurate compute-in-memory.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-65233-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-65233-w","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1002/advs.202517588","name":"Dual Bipolar Resistive Switching in Wafer-Scalable 2D Perovskite Oxide Nanosheets-Based Memristor.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202517588","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.202517588","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1038/s41467-026-69958-0","name":"A hardware-adaptive learning algorithm for superlinear-capacity associative memory on memristor crossbars.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-69958-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-69958-0","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.3389/fnins.2025.1729354","name":"Editorial: Novel memristor-based devices and circuits for neuromorphic and AI applications, volume II.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2025.1729354","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3389/fnins.2025.1729354","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1063/5.0296052","name":"Firing dynamics and phase synchronization in a memristor-coupled heterogeneous neuron network under electromagnetic radiation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1063/5.0296052","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1063/5.0296052","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1021/acsnano.5c16967","name":"Feature-Selective Preprocessing with Electrically Robust Boron Nitride-Based Dynamic Memristors for Reliable Lightweight Neural Networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.5c16967","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsnano.5c16967","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acsami.5c14275","name":"Magnetic-Field Controlled Organic Spintronic Memristor for Neural Network Computation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c14275","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c14275","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1126/sciadv.ady5485","name":"Privacy-preserving data analysis using a memristor chip with colocated authentication and processing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.ady5485","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1126/sciadv.ady5485","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1038/s41467-026-70806-4","name":"High-speed energy-efficient memristor confined in sub-5 nm space with elemental oxygen reservoir layer.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-70806-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-70806-4","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/tnnls.2025.3581229","name":"Generating Simple Cyclic Memristive Neural Network Circuit With Controllable Multiscroll Attractors and Multivariable Amplitude Control.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tnnls.2025.3581229","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1109/tnnls.2025.3581229","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1038/s41928-025-01454-7","name":"A ferroelectric-memristor memory for both training and inference.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41928-025-01454-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41928-025-01454-7","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1038/s41467-026-71844-8","name":"Intrinsic annealing in a hybrid memristor-magnetic tunnel junction Ising machine.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-71844-8","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-71844-8","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1371/journal.pone.0339866","name":"Generalized FitzHugh-Nagumo equations with Caputo gH-differentiability: A novel fuzzy fractional approach to digital memristor networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pone.0339866","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1371/journal.pone.0339866","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1007/s11571-025-10365-4","name":"Tunable synchronization control of coupled neural dual-capacitance circuits via switchable components.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-025-10365-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1007/s11571-025-10365-4","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1016/j.neunet.2025.107878","name":"Robust full-parameter control method: Constructing multiscroll HNN via memristor.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107878","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.neunet.2025.107878","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.3390/mi17030328","name":"A DTMOS-Based Memristor Emulator Circuit for Low-Power Biomedical Signal Conditioning.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/mi17030328","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/mi17030328","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1063/5.0288853","name":"Multi-mechanism driven geometric control of discrete memristive dual-neuron HNN: Modulation analysis and hardware implementation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1063/5.0288853","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1063/5.0288853","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1038/s42256-025-01149-w","name":"Actor-critic networks with analogue memristors mimicking reward-based learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s42256-025-01149-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s42256-025-01149-w","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.34133/research.0870","name":"Fiber Memristor-Based Physical Reservoir Computing for Multimodal Sleep Monitoring.","source":"europepmc","abstract":"Real-time wearable sleep monitors process diverse biological signals while operating under tight energy and computation budgets. The existing algorithms are facing problems of high energy consumption due to separate hardware storage and computation units. In this work, textile-integrated in-memory neuromorphic computing electronics based on MoS 2 quantum dot fiber memristors was proposed for physical reservoir computing for the first time. Textile electronics convert raw electroencephalogram (EEG)and snoring audio directly into rich, high-dimensional state vectors based on intrinsic nonlinear dynamics. Leveraging 16 pulse-programmable conductance levels, the reservoir realizes an accuracy of 94.8%, 95.4%, and 93.5% in snoring events, sleep stages, and multimodal fusion, respectively. To enhance the robustness of feature extraction and improve classification performance under noisy conditions, the linear readout layer was replaced with a lightweight convolutional neural network. The hybrid neural network is 6 times faster than traditional deep-learning methods in 24-h segment EEG analysis. The memristors switch at ±1 V and sub-nanoampere currents, providing picowatt energy consumption suited to continuous on-body use. The results establish fiber memristor reservoir computing as an energy-efficient path to in-fabric, multimodal intelligence for next-generation home sleep analysis and wearable health care.","url":"https://doi.org/10.34133/research.0870","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.34133/research.0870","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1007/s11571-025-10323-0","name":"Memristor-based RDBO-CNN circuit design and application of image multi-classification recognition.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-025-10323-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1007/s11571-025-10323-0","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1038/s41467-026-73217-7","name":"Full vision adaptation in mixed-light conditions enabled by dynamic water adsorption/desorption.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-73217-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-73217-7","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acs.jpclett.5c02883","name":"Molecular-Layer-Deposited Amino Acid Hybrid Memristor: Bilayer Design Enabling Robust Synaptic Plasticity and Image Recognition.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.jpclett.5c02883","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acs.jpclett.5c02883","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1038/s41467-026-69805-2","name":"Feedback neurons based on perovskite memristor with nickel single-atom engineered reduced graphene oxide cathode.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-69805-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-69805-2","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.21203/rs.3.rs-7906180/v1","name":"Robust distillation for compute-in-memory: Realizing reliable intelligence using imperfect memristors","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-7906180/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7906180/v1","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1021/acs.jpclett.5c02109","name":"Artificial Electric Synapse of CuI-Based Memristor for Neuromorphic Emotion Recognition and Neural Networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.jpclett.5c02109","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acs.jpclett.5c02109","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1002/advs.202513646","name":"High-Endurance STO:YSZ Optoelectronic Memristors with Vertically Aligned Nanocomposite Structure for Edge Detection.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202513646","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.202513646","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1126/sciadv.adv3436","name":"Real-time signal processing enabled by fused networks on a memristor-based system on a chip.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.adv3436","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1126/sciadv.adv3436","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1021/acsami.5c14010","name":"An Implantable System Design Based on Neuromorphic Memristor for Post-Craniotomy Intracranial Pressure Monitoring.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c14010","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c14010","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1038/s41377-025-01928-5","name":"A facile photonics reconfigurable memristor with dynamically allocated neurons and synapses functions.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41377-025-01928-5","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41377-025-01928-5","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1002/advs.202523162","name":"Infrared Machine Vision System Based on Te NWs-Au NPs Plasmonic Optoelectronic Memristor for Motion Detection.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202523162","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.202523162","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1093/nsr/nwaf546","name":"Local active memristive oscillator enables controllable complex behaviours and frequency domain extraction.","source":"europepmc","abstract":"Physical non-linearities near the Mott transition exhibit substantial potential for neuromorphic computing. The complex computational behaviour stems from their intrinsic local active characteristics. Most studies focus on decay dynamics or regular oscillations, treating Mott devices primarily as simple threshold elements. Challenges remain in connecting measurable material properties to more complex device dynamics and their control methods through a unified theoretical model. Here, we develop a thermodynamic compact model for vanadium oxide devices based on electrical measurements and the local active principle. Utilizing the non-linearities near the Mott transition, we propose an injection-based control method to regulate behaviours of non-linear oscillators, such as frequency division, stochastic oscillations and frequency locking. Finally, a single device operating at the edge of chaos demonstrates exceptional capability in extracting information in the frequency domain within a physical computing framework, achieving performance equivalent to a two-layer convolutional neural network on the same task. This work facilitates a paradigm shift from traditional local passive devices to local active devices, bridging the physical non-linearities, circuit dynamics and computational theory to advance dynamic neuromorphic computing.","url":"https://doi.org/10.1093/nsr/nwaf546","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1093/nsr/nwaf546","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/advs.202504706","name":"Perovskite Neuromorphic Engine for Transformer Architectures.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202504706","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/advs.202504706","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1021/acsami.5c21337","name":"The Influence of Different Nanoscale Channel Lengths in Low-Temperature-Grown Lateral MoS&lt;sub&gt;2&lt;/sub&gt; Memristors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c21337","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c21337","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1002/smll.202504294","name":"Chalcogenide-Based Brain-Inspired Photo-Synapses for Neuromorphic Vision Sensor: An Experimental and Theoretical Study.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.202504294","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/smll.202504294","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1016/j.neunet.2025.107672","name":"Finite time dynamic analysis of memristor-based fuzzy NNs with inertial term: Nonreduced-order approach.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107672","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.neunet.2025.107672","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1126/sciadv.adv4446","name":"Memristive floating-point Fourier neural operator network for efficient scientific modeling.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.adv4446","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1126/sciadv.adv4446","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1007/s11571-025-10265-7","name":"A memristive synaptic circuit and optimization algorithm for synaptic control.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-025-10265-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1007/s11571-025-10265-7","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/tnnls.2025.3539842","name":"A Memristor-Based Neural Network Circuit With Retrospective Revaluation Effect and Application in Intelligent Household Robots.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tnnls.2025.3539842","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1109/tnnls.2025.3539842","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1126/sciadv.adr7571","name":"Continuous-time digital twin with analog memristive neural ordinary differential equation solver.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.adr7571","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1126/sciadv.adr7571","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.3390/mi16020228","name":"Dynamics Research of the Hopfield Neural Network Based on Hyperbolic Tangent Memristor with Absolute Value.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/mi16020228","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/mi16020228","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1109/tnnls.2024.3477432","name":"Relaxed Stability Criteria for Delayed Memristor-Based Neural Network Systems via a Novel Matrix-Separation Legendre Inequality.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tnnls.2024.3477432","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1109/tnnls.2024.3477432","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1039/d5nr02683k","name":"Graphene quantum dots covalently functionalized with zinc porphyrin for digital-analog dual-mode memristors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5nr02683k","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1039/d5nr02683k","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1038/s41467-026-71697-1","name":"Massively parallel in-sensor skinomorphic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-71697-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-71697-1","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1371/journal.pone.0328965","name":"Sustainable memristors from shiitake mycelium for high-frequency bioelectronics.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pone.0328965","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1371/journal.pone.0328965","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1002/smll.202500062","name":"High Rectification Ratio Self-Rectifying Memristor Crossbar Array for Convolutional Neural Network Operations.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.202500062","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/smll.202500062","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1002/smll.202505337","name":"Fusion of Near-Infrared and UV Light Image via Artificial Visual Neurons Based on Mott Memristor.","source":"europepmc","abstract":"Multi-band image fusion in biological systems aims to integrate image data from various spectral bands to obtain more comprehensive, accurate, and effective image information. However, developing efficient and low-power artificial vision multi-band image fusion systems inspired by biological vision systems remains a challenge. Here, an artificial visual neuron based on the integration of In 2 O 3 /PY-IT phototransistor and NbO x Mott memristor is proposed, which can simultaneously sense optical signals in the UV and near-infrared bands and achieve pulse encoding of different frequencies through light stimulation of different intensities. In addition, the pulse signals encoded by artificial neurons are processed through a Pulse Coupled Neural Network for image fusion, which successfully integrates image information under different lighting scenes and demonstrates the bionic functionality of the artificial vision fusion system. Such artificial visual neurons provide a solid foundation for constructing integrated, functional, and low-power artificial visual systems and serve as building blocks for hardware-based multi-band perception.","url":"https://doi.org/10.1002/smll.202505337","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/smll.202505337","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1002/smsc.202500424","name":"Versatile Metal Phthalocyanine-Based Memristive Nanowire Network: Unraveling the Dynamics of Digital to Analog Switching.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smsc.202500424","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smsc.202500424","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.neunet.2025.107473","name":"Multiscroll hidden attractor in memristive autapse neuron model and its memristor-based scroll control and application in image encryption.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107473","authors":["Zhiqiang Wan","Yi-Fei Pu","Qiang Lai"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.neunet.2025.107473","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1016/j.neunet.2025.107213","name":"What is the impact of discrete memristor on the performance of neural network: A research on discrete memristor-based BP neural network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107213","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.neunet.2025.107213","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1126/sciadv.ady0336","name":"A flexible spiking hair sensillum for ultralow power density noncontact perception.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.ady0336","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1126/sciadv.ady0336","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1038/s41598-025-21035-0","name":"Recording and modeling of pinched hysteresis loops, the fingerprint of a memristor, in neurons.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-21035-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-21035-0","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1063/5.0273802","name":"CdS/CZTSSe heterojunction synaptic memristor: Enabling efficient handwritten digit recognition.","source":"europepmc","abstract":"","url":"https://doi.org/10.1063/5.0273802","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1063/5.0273802","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1126/sciadv.ads5340","name":"Topology optimization of random memristors for input-aware dynamic SNN.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.ads5340","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1126/sciadv.ads5340","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1126/sciadv.adw8513","name":"In situ observation of oxygen ion dynamics in topological phase change memristors through self-assembled interface design.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.adw8513","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1126/sciadv.adw8513","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.3390/gels11060423","name":"Starch-Glycerol-Based Hydrogel Memristors for Bio-Inspired Auditory Neuron Applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/gels11060423","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/gels11060423","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1002/advs.202513647","name":"2D Tellurene-Based Optoelectronic Memristor with Temporal Dynamics for Multimodal Reservoir Computing System.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202513647","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/advs.202513647","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.3390/s25206429","name":"Total Solution-Processed Zr: HfO&lt;sub&gt;2&lt;/sub&gt; Flexible Memristor with Tactile Sensitivity: From Material Synthesis to Application in Wearable Electronics.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s25206429","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/s25206429","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.3390/mi16070818","name":"Memristor Emulator Circuits: Recent Advances in Design Methodologies, Healthcare Applications, and Future Prospects.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/mi16070818","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/mi16070818","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1002/advs.202505688","name":"Integrated Design of Electrically Configurable Ferroelectric and Redox-Based Memristors for Hardware-Implemented Reservoir Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202505688","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/advs.202505688","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1038/s41598-025-07564-8","name":"A merged fuzzy system and neural network for improving management method and strategy in scientific research and education.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-07564-8","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-07564-8","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1038/s41467-025-64579-5","name":"Scalable transition metal dichalcogenide memtransistor arrays with Schottky-barrier control for energy-efficient artificial neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-64579-5","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-64579-5","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1021/acsami.5c13200","name":"Hydrothermal Synthesis of Vinylidene-Linked Ionic Covalent Organic Frameworks for Robust Biomimetic Memristors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c13200","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c13200","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1016/j.mbm.2025.100133","name":"Neuromorphic chips for biomedical engineering.","source":"europepmc","abstract":"The modern medical field faces two critical challenges: the dramatic increase in data complexity and the explosive growth in data size. Especially in current research, medical diagnostic, and data processing devices relying on traditional computer architecture are increasingly showing limitations when faced with dynamic temporal and spatial processing requirements, as well as high-dimensional data processing tasks. Neuromorphic devices provide a new way for biomedical data processing due to their low energy consumption and high dynamic information processing capabilities. This paper aims to reveal the advantages of neuromorphic devices in biomedical applications. First, this review emphasizes the urgent need of biomedical engineering for diversify clinical diagnostic techniques. Secondly, the feasibility of the application in biomedical engineering is demonstrated by reviewing the historical development of neuromorphic devices from basic modeling to multimodal signal processing. In addition, this paper demonstrates the great potential of neuromorphic chips for application in the fields of biosensing technology, medical image processing and generation, rehabilitation medical engineering, and brain-computer interfaces. Finally, this review provides the pathways for constructing standardized experimental protocols using biocompatible technologies, personalized treatment strategies, and systematic clinical validation. In summary, neuromorphic devices will drive technological innovation in the biomedical field and make significant contributions to life health.","url":"https://doi.org/10.1016/j.mbm.2025.100133","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.mbm.2025.100133","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1002/adma.202502168","name":"Brain-Inspired In-Memory Data Pruning and Computing with TaO&lt;sub&gt;x&lt;/sub&gt; Mem-Selectors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202502168","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/adma.202502168","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1093/nsr/nwaf499","name":"A memristor-based energy-efficient compressed sensing accelerator with hardware-software co-optimization for edge computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1093/nsr/nwaf499","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1093/nsr/nwaf499","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.3390/mi16080848","name":"Design of a Current-Mode OTA-Based Memristor Emulator for Neuromorphic Medical Application.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/mi16080848","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/mi16080848","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.21203/rs.3.rs-7072754/v1","name":"Dynamics and Image Encryption Application of Fractional-Order Memristive Bridge-Type Crosstalk-Coupled HR-FN Neurons","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-7072754/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-7072754/v1","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1109/tnnls.2023.3348553","name":"Memristor-Based Neural Network Circuit of Associative Memory With Overshadowing and Emotion Congruent Effect.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tnnls.2023.3348553","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1109/tnnls.2023.3348553","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.3390/ma18143210","name":"Associative Learning Emulation in HZO-Based Ferroelectric Memristor Devices.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/ma18143210","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/ma18143210","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1371/journal.pone.0318009","name":"Low-power artificial neuron networks with enhanced synaptic functionality using dual transistor and dual memristor.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pone.0318009","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1371/journal.pone.0318009","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1038/s41598-026-45027-w","name":"Artificial intelligence technology for music teaching reform mode under DCNN algorithm.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-45027-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-45027-w","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.3390/mi16070769","name":"Tunable Active Wien Filters Based on Memristors.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/mi16070769","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/mi16070769","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.21203/rs.3.rs-5934729/v1","name":"Dynamical Behaviour and Applications of Master-slave Fractional-order Non-volatile Memristor Chaotic Hopfield Neural Network","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-5934729/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-5934729/v1","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1063/5.0292369","name":"Electrical wave propagation in memristive cardiac tissue under electric field.","source":"europepmc","abstract":"","url":"https://doi.org/10.1063/5.0292369","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1063/5.0292369","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1021/acsami.5c09911","name":"A Study on the Synaptic Behavior of Al/ZrO&lt;sub&gt;2&lt;/sub&gt;/TiO&lt;sub&gt;2&lt;/sub&gt;/Al Electronic Bipolar Resistance Switching Memristor.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.5c09911","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsami.5c09911","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1002/adma.202510635","name":"Spatiotemporal Reservoir Computing with a Reconfigurable Multifunctional Memristor Array.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202510635","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202510635","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1038/s41467-025-63494-z","name":"Next-generation graph computing with electric current-based and quantum-inspired approaches.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-63494-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-63494-z","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1371/journal.pone.0318075","name":"Intelligent classification of computer vulnerabilities and network security management system: Combining memristor neural network and improved TCNN model.","source":"europepmc","abstract":"","url":"https://doi.org/10.1371/journal.pone.0318075","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1371/journal.pone.0318075","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1038/s41467-025-63115-9","name":"Biomimetic microstructure design for ultrasensitive piezoionic mechanoreceptors in multimodal object recognition.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-63115-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-63115-9","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1038/s41467-025-61025-4","name":"A near-threshold memristive computing-in-memory engine for edge intelligence.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-61025-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-61025-4","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1063/5.0273574","name":"Echo state and band-pass networks with aqueous memristors: Leaky reservoir computing with a leaky substrate.","source":"europepmc","abstract":"","url":"https://doi.org/10.1063/5.0273574","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1063/5.0273574","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.3390/nano15221707","name":"Flexible Inorganic/Organic Memristor Based on W-Doped MoO&lt;sub&gt;x&lt;/sub&gt;/Poly(methyl methacrylate) Heterostructure.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/nano15221707","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/nano15221707","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1002/advs.202417461","name":"Bioinspired Adaptive Neuron Enabled by Self-powered Optoelectronic Memristor and Threshold Switching Memory for Neuromorphic Visual System.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202417461","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/advs.202417461","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1021/acsnano.5c11481","name":"Thermally Activated Negative Differential Resistance VO&lt;sub&gt;&lt;i&gt;x&lt;/i&gt;&lt;/sub&gt; Memristor with Switchable Rate and Leaky Integrate-and-Fire Spiking Dynamics.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.5c11481","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsnano.5c11481","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1016/j.neunet.2024.106780","name":"Memristor-based circuit design of BiLSTM network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106780","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.neunet.2024.106780","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1002/smll.202504507","name":"Analog Switching in Hexagonal Boron Nitride Memristors via Multiple Nano-Filaments Confinement.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.202504507","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/smll.202504507","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1016/j.neunet.2024.107049","name":"Plane coexistence behaviors for Hopfield neural network with two-memristor-interconnected neurons.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.107049","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.neunet.2024.107049","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1038/s41467-025-56286-y","name":"Memristor-based feature learning for pattern classification.","source":"europepmc","abstract":"Inspired by biological processes, feature learning techniques, such as deep learning, have achieved great success in various fields. However, since biological organs may operate differently from semiconductor devices, deep models usually require dedicated hardware and are computation-complex. High energy consumption has made deep model growth unsustainable. We present an approach that directly implements feature learning using semiconductor physics to minimize disparity between model and hardware. Following this approach, a feature learning technique based on memristor drift-diffusion kinetics is proposed by leveraging the dynamic response of a single memristor to learn features. The model parameters and computational operations of the kinetics-based network are reduced by up to 2 and 4 orders of magnitude, respectively, compared with deep models. We experimentally implement the proposed network on 180 nm memristor chips for various dimensional pattern classification tasks. Compared with memristor-based deep learning hardware, the memristor kinetics-based hardware can further reduce energy and area consumption significantly. We propose that innovations in hardware physics could create an intriguing solution for intelligent models by balancing model complexity and performance.","url":"https://doi.org/10.1038/s41467-025-56286-y","authors":["Tuo Shi","Lili Gao","Yang Tian","Shuangzhu Tang","Jinchang Liu","Yiqi Li","Ruixi Zhou","Shiyu Cui","Hui Zhang","Yu Li","Zuheng Wu","Xumeng Zhang"],"tags":["Memristor","Deep learning","Computer science","Feature (linguistics)","Artificial intelligence"],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-56286-y","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"doi:10.1002/advs.202408133","name":"Novel Solution-Processed Fe&lt;sub&gt;2&lt;/sub&gt;O&lt;sub&gt;3&lt;/sub&gt;/WS&lt;sub&gt;2&lt;/sub&gt; Hybrid Nanocomposite Dynamic Memristor for Advanced Power Efficiency in Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202408133","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/advs.202408133","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.3390/nano15030213","name":"Defect-Tolerant Memristor Crossbar Circuits for Local Learning Neural Networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/nano15030213","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/nano15030213","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1038/s41467-024-55701-0","name":"Refreshable memristor via dynamic allocation of ferro-ionic phase for neural reuse.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-024-55701-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-024-55701-0","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.bios.2025.117496","name":"Heterojunction nanofluidic memristors based on peptide chain valves for neuromorphic applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.bios.2025.117496","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.bios.2025.117496","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1038/s41598-025-21604-3","name":"A novel memristor-based hyperchaotic hybrid encryption system with DNA for image encryption on the Jetson TX2.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-21604-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-21604-3","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1063/5.0293317","name":"Dynamics of a nonlinear resistor-coupled memristive neuron with double membrane.","source":"europepmc","abstract":"","url":"https://doi.org/10.1063/5.0293317","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1063/5.0293317","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.3390/polym17233174","name":"Advances in Polymeric Semiconductors for Next-Generation Electronic Devices.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/polym17233174","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/polym17233174","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1016/j.neunet.2025.107276","name":"Memristor-based circuit design of interweaving mechanism of emotional memory in a hippocamp-brain emotion learning model.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107276","authors":["Yunlai Zhu","Yongjie Zhao","Junjie Zhang","Xi Sun","Ying Zhu","Xu Zhou","Xuming Shen","Zuyu Xu","Zuheng Wu","Yuehua Dai"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.neunet.2025.107276","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1038/s41467-025-57183-0","name":"A full-stack memristor-based computation-in-memory system with software-hardware co-development.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-57183-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-57183-0","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.21203/rs.3.rs-6187057/v1","name":"Memristor-based adaptive analog-to-digital conversion for efficient and accurate compute-in-memory","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-6187057/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.21203/rs.3.rs-6187057/v1","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1038/s41377-024-01703-y","name":"Nonlinear memristive computational spectrometer.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41377-024-01703-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41377-024-01703-y","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.3390/mi16080882","name":"Composite Behavior of Nanopore Array Large Memristors.","source":"europepmc","abstract":"Synthetic nanopores were recently demonstrated with memristive and nonlinear voltage-current behaviors, akin to ion channels in a cell membrane. Such ionic devices are considered a promising candidate for the development of brain-inspired neuromorphic computing techniques. In this work, we show the composite behavior of nanopore-array large memristors, formed with different membrane materials, pore sizes, electrolytes, and device arrangements. Anodic aluminum oxide (AAO) membranes with 5 nm and 20 nm diameter pores and track-etched polycarbonate (PCTE) membranes with 10 nm diameter pores are tested and shown to demonstrate memristive and nonlinear behaviors with approximately 107–1010 pores in parallel when electrolyte concentration across the membranes is asymmetric. Ion diffusion through the large number of channels induces time-dependent electrolyte asymmetry that drives the system through different memristive states. The behaviors of series composite memristors with different configurations are also presented. In addition to helping understand fluidic devices and circuits for neuromorphic computing, the results also shed light on the development of field-assisted ion-selection-membrane filtration techniques as well as the investigations of large neurons and giant synapses. Further work is needed to de-embed parasitic components of the measurement setup to obtain intrinsic large memristor properties.","url":"https://doi.org/10.3390/mi16080882","authors":["Ian Reistroffer","Jaden Tolbert","Jeffrey A. Osterberg","Pingshan Wang"],"tags":["Memristor","Nanopore","Composite number","Materials science","Nanotechnology"],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/mi16080882","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"doi:10.1038/s41467-024-55293-9","name":"Ultra robust negative differential resistance memristor for hardware neuron circuit implementation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-024-55293-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-024-55293-9","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1038/s41467-025-62151-9","name":"Artificial transneurons emulate neuronal activity in different areas of brain cortex.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-62151-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-62151-9","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1016/j.neunet.2024.106925","name":"Analysis and fully memristor-based reservoir computing for temporal data classification.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106925","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.neunet.2024.106925","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1016/j.neunet.2025.107502","name":"Generalization and differentiation of affective associative memory circuit based on memristive neural network with emotion transfer.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107502","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.neunet.2025.107502","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1002/advs.202411925","name":"Weighted Echo State Graph Neural Networks Based on Robust and Epitaxial Film Memristors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202411925","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/advs.202411925","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1038/s41598-026-45010-5","name":"Barrier Lyapunov function-based robust adaptive neural network control with dynamically adjusted activation functions for Euler-Lagrange systems under position constraints.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-45010-5","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-45010-5","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acsnano.4c18145","name":"Decoupling Strategy to Separate Training and Inference with Three-Dimensional Neuromorphic Hardware Composed of Neurons and Hybrid Synapses.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.4c18145","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsnano.4c18145","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1038/s41467-025-59589-2","name":"Flexible self-rectifying synapse array for energy-efficient edge multiplication in electrocardiogram diagnosis.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-59589-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-59589-2","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1039/d4nh00623b","name":"Enhancing memristor multilevel resistance state with linearity potentiation &lt;i&gt;via&lt;/i&gt; the feedforward pulse scheme.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d4nh00623b","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1039/d4nh00623b","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1002/adma.202513907","name":"Neuromorphic Visual Receptive Field Hardware with Vertically Integrated Indium-Gallium-Zinc-Oxide Optoelectronic Memristors over Silicon Neuron Transistors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202513907","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202513907","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1038/s41377-025-01986-9","name":"Optoelectronic polymer memristors with dynamic control for power-efficient in-sensor edge computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41377-025-01986-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41377-025-01986-9","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1002/advs.202516379","name":"Devices, Functions, and Applications of Artificial Neuromorphic Visual Systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202516379","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/advs.202516379","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.34133/research.0580","name":"All-Optically Controlled Memristive Device Based on Cu<sub>2</sub>O/TiO<sub>2</sub> Heterostructure Toward Neuromorphic Visual System.","source":"europepmc","abstract":"","url":"https://doi.org/10.34133/research.0580","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.34133/research.0580","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1002/smtd.202500203","name":"Short-Term Bienenstock-Cooper-Munro Learning in Optoelectrically-Driven Flexible Halide Perovskite Single Crystal Memristors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smtd.202500203","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/smtd.202500203","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:34.126Z"},{"id":"doi:10.1038/s41467-025-63640-7","name":"Constructing artificial neurons with functional parameters comprehensively matching biological values.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-63640-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-63640-7","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1038/s41467-025-57043-x","name":"Temporal Contrastive Learning through implicit non-equilibrium memory.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-57043-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-57043-x","addedAt":"2026-09-01T01:48:32.245Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.4018/978-1-6684-2408-7.ch058","name":"Comparative Analysis of Proposed Artificial Neural Network (ANN) Algorithm With Other Techniques","source":"crossref","abstract":"The mortality rate among women is increasing progressively due to cancer. Generally, women around 45 years old are vulnerable from this disease. Early detection is hope for patients to survive otherwise it may reach to unrecoverable stage. Currently, there are numerous techniques available for diagnosis of such a disease out of which mammography is the most trustworthy method for detecting early cancer stage. The analysis of these mammogram images are difficult to analyze due to low contrast and nonuniform background. The mammogram images are scanned and digitized for processing that further reduces the contrast between Region of Interest and background. Presence of noise, glands and muscles leads to background contrast variations. Boundaries of suspected tumor area are fuzzy &amp; improper. Aim of paper is to develop robust edge detection technique which works optimally on mammogram images to segment tumor area. Output results of proposed technique on different mammogram images of MIAS database are presented and compared with existing techniques in terms of both Qualitative &amp; Quantitative parameters.","url":"https://doi.org/10.4018/978-1-6684-2408-7.ch058","authors":["Deepak Chatha","Alankrita Aggarwal","Rajender Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-17T11:47:50Z","doi":"10.4018/978-1-6684-2408-7.ch058","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/b978-0-12-741251-1.50021-7","name":"Neural Network Approaches to Color Vision","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-12-741251-1.50021-7","authors":["ANYA C. HURLBERT"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-01T11:41:47Z","doi":"10.1016/b978-0-12-741251-1.50021-7","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1021/acsomega.5c02700.s001","name":"Flexible Neural Probe with an Optimized Electrode Density for Neural Network Investigations","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acsomega.5c02700.s001","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-11T15:21:50Z","doi":"10.1021/acsomega.5c02700.s001","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/j.neucom.2025.129475","name":"Global Mittag-Leffler synchronization of discontinuous memristor-based fractional-order fuzzy inertial neural networks with mixed delays","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2025.129475","authors":["Haihe Pan","Chengdai Huang","Jinde Cao","Heng Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-24T03:56:51Z","doi":"10.1016/j.neucom.2025.129475","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1088/0954-898x_9_3_009","name":"The influence of neural activity and intracortical connectivity on the periodicity of ocular dominance stripes","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_9_3_009","authors":["Geoffrey J Goodhill"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:56Z","doi":"10.1088/0954-898x_9_3_009","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1088/0954-898x_1_2_006","name":"Neural implementation of a method for solving systems of linear equations","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_1_2_006","authors":["A B Forbes","A J Mansfield"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:03Z","doi":"10.1088/0954-898x_1_2_006","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/j.neunet.2026.108688","name":"SmooNet: Smooth operator neural network and functional differential equation","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.108688","authors":["Ruiyan Luo","Xin Qi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-12T16:43:47Z","doi":"10.1016/j.neunet.2026.108688","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.2172/900191","name":"Tampa Electric Neural Network Sootblowing","source":"crossref","abstract":"","url":"https://doi.org/10.2172/900191","authors":["Mark A. Rhode"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-03-14T02:24:41Z","doi":"10.2172/900191","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1109/neurel.2004.1416507","name":"2004 Seventh Seminar on Neural Network Applications in Electrical Engineering - NEUREL 2004 - Title Page","source":"crossref","abstract":"","url":"https://doi.org/10.1109/neurel.2004.1416507","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-06-01T13:01:21Z","doi":"10.1109/neurel.2004.1416507","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.2139/ssrn.5231738","name":"Benchmarking Convolutional Neural Network and Graph Neural Network Based Surrogate Models on a Real-World Car External Aerodynamics Dataset","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5231738","authors":["Sam Jacob Jacob","Markus Mrosek","Carsten Othmer","Harald Köstler"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-26T14:36:53Z","doi":"10.2139/ssrn.5231738","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.37200/ijpr/v24i5/pr2020283","name":"Plant Leaf Perception Using Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.37200/ijpr/v24i5/pr2020283","authors":["Eldho Paul"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-04-30T17:30:42Z","doi":"10.37200/ijpr/v24i5/pr2020283","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.3390/electronics12122715","name":"Embedding-Based Deep Neural Network and Convolutional Neural Network Graph Classifiers","source":"crossref","abstract":"One of the most significant graph data analysis tasks is graph classification, as graphs are complex data structures used for illustrating relationships between entity pairs. Graphs are essential in many domains, such as the description of chemical molecules, biological networks, social relationships, etc. Real-world graphs are complicated and large. As a result, there is a need to find a way to represent or encode a graph’s structure so that it can be easily utilized by machine learning models. Therefore, graph embedding is considered one of the most powerful solutions for graph representation. Inspired by the Doc2Vec model in Natural Language Processing (NLP), this paper first investigates different ways of (sub)graph embedding to represent each graph or subgraph as a fixed-length feature vector, which is then used as input to any classifier. Thus, two supervised classifiers—a deep neural network (DNN) and a convolutional neural network (CNN)—are proposed to enhance graph classification. Experimental results on five benchmark datasets indicate that the proposed models obtain competitive results and are superior to some traditional classification methods and deep-learning-based approaches on three out of five benchmark datasets, with an impressive accuracy rate of 94% on the NCI1 dataset.","url":"https://doi.org/10.3390/electronics12122715","authors":["Sarah G. Elnaggar","Ibrahim E. Elsemman","Taysir Hassan A. Soliman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-19T01:59:51Z","doi":"10.3390/electronics12122715","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1109/tcsii.2023.3298910","name":"Efficient Low-Bit Neural Network With Memristor-Based Reconfigurable Circuits","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tcsii.2023.3298910","authors":["He Xiao","Xiaofang Hu","Tongtong Gao","Yue Zhou","Shukai Duan","Yiran Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-26T18:56:55Z","doi":"10.1109/tcsii.2023.3298910","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1109/tase.2025.3585935","name":"Dual Memristor-Coupled Hopfield Neural Network With Any Multi-Scroll Amplitude Control and Its Application for Medical Image Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tase.2025.3585935","authors":["Sen Zhang","Dazhe He","Yongxin Li","Daorong Lu","Chunbiao Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-04T13:53:18Z","doi":"10.1109/tase.2025.3585935","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1088/0954-898x/15/2/002","name":"Quantifying variability in neural responses and its application for the validation of model predictions","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/15/2/002","authors":["Anne Hsu","Alexander Borst","Frédéric Theunissen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2004-04-22T03:14:09Z","doi":"10.1088/0954-898x/15/2/002","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.14711/thesis-b536650","name":"Robustness of cellular neural network implementations","source":"crossref","abstract":"","url":"https://doi.org/10.14711/thesis-b536650","authors":["Kwok Fai Hui"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-12-20T01:25:21Z","doi":"10.14711/thesis-b536650","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.15760/etd.8196","name":"Toward Efficient Rendering: A Neural Network Approach","source":"crossref","abstract":"","url":"https://doi.org/10.15760/etd.8196","authors":["Qiqi Hou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-04T22:38:56Z","doi":"10.15760/etd.8196","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/c2009-0-22399-3","name":"Practical Neural Network Recipies in C++","source":"crossref","abstract":"","url":"https://doi.org/10.1016/c2009-0-22399-3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-08-03T21:21:39Z","doi":"10.1016/c2009-0-22399-3","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1109/ijcnn.1991.155504","name":"Spreadsheet simulation of artificial neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.1991.155504","authors":["R. Antonini"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-12-09T23:24:26Z","doi":"10.1109/ijcnn.1991.155504","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1017/cbo9780511624216.009","name":"Vapnik-Chervonenkis Dimension Bounds for Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1017/cbo9780511624216.009","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-03-02T18:08:05Z","doi":"10.1017/cbo9780511624216.009","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.7490/f1000research.1118293.1","name":"Convolutional neural network architectures for CAFA4","source":"crossref","abstract":"Introduction The Critical Assessment of protein Function Annotation (CAFA) challenge concerns the prediction of annotated ontology terms for given protein sequences [Radivojac et al., 2013]. In the current CAFA 4 challenge, the goal is to predict terms from the Gene Ontology (GO), the Human Phenotype Ontology (HPO) and the Disorder Ontology (DO) ontologies for a set of ~100k sequences provided as prediction targets. In this work, different convolutional neural network architectures were examined for the task of protein function prediction. UniProt protein sequence data was enriched with additional information from protein taxonomical hierarchies and InterProScan sequence analyses before being processed with the networks, predicting the different ontologies' terms in a multi-label classification task. Data Preprocessing The same data preprocessing approach was applied with all ontologies. The used protein sequences consisted of the ~560k union of the UniProt XML release and the set of sequences provided as CAFA4 prediction targets [UniProt Consortium, 2019]. GO annotations and protein lineage information were imported from the UniProt release. HPO and DO annotations were extracted from their respective databases and added to the sequence information. All annotated terms were propagated using the GOA Tools package, so that all of their ancestor terms were included as individual labels [Klopfenstein et al., 2018]. InterProScan sequence analyses were imported from the dataset release and added to the protein sequence information [Jones et al., 2014]. Neural Architectures All neural network methods were implemented with the Keras package and were based on a one-dimensional, convolutional approach [Chollet et al., 2015, LeCun et al., 1995]. Both parallel and nested convolutional architectures were tested. In the parallel convolution approach, the outputs of the convolutional layers were concatenated together, whereas in the nested approach each convolutional layer produced the output of the next layer. In addition, the suitability of a one-dimensional variant of the MobileNet V2 image recognition network was tested, as well as a network based on the DeepGOPlus architecture [Kulmanov and Hoehndorf, 2020, Sandler et al., 2018]. All networks received as inputs sequences of a maximum of 1000 elements, where each element corresponded to a single amino acid. Each element contained an 8-dimensional embedding of an amino acid, as well as optionally 8-dimensional embeddings for InteProScan domain , family and homologous superfamily features, with a maximum of 1000 most common unique features included in each category. These sequences were processed by the convolutional layers and merged together with 4-dimensional embeddings representing five levels of the protein's organism's taxonomy lineage, before being finally processed with a dense layer followed by a multi-label prediction layer, which generated individual predictions for up to 1000 of the most common annotated terms. A dropout of 0.1 was used after the inputs and the convolutional layers to improve regularization. Several optimizers were tested, with the Adam and SGD ones achieving the most promising results. The models were trained with a learning rate of 1e-5 and with early stopping, for 10-100 epochs depending on the computational complexity of the model, the size of the dataset and the available resources. Experimental Setup The entire dataset was randomly divided into six approximately equal subsets so that all homologs of a protein were in the same subset. Training was done by cross-validation, so that four subsets at a time were used for training, one for parameter optimization and one for prediction. The final predictions were acquired by joining the six predicted subsets together, thus covering the whole dataset. Finally, the CAFA4 targets were separated from the whole set of predicted sequences, and converted to the submission format. Experiments were performed with using e","url":"https://doi.org/10.7490/f1000research.1118293.1","authors":["Jari Björne"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-21T21:17:08Z","doi":"10.7490/f1000research.1118293.1","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1109/ijcnn.1992.226871","name":"A neural-network-based approach for routing in a packet switching network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.1992.226871","authors":["S. Cavalieri","A. di Stefano","O. Mirabella"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-01-02T16:19:33Z","doi":"10.1109/ijcnn.1992.226871","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1088/0954-898x/2/2/003","name":"Competitive learning, natural images and cortical cells","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/2/2/003","authors":["C Webber"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-24T22:35:54Z","doi":"10.1088/0954-898x/2/2/003","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.2139/ssrn.6878407","name":"Accelerating gas-network feasibility screening with a physics-informed graph neural network surrogate","source":"crossref","abstract":"Large-scale gas-network scenario evaluation is a computational bottleneck in integrated energy-system planning, particularly when gas infrastructure interacts with power, heat, hydrogen, and sector-coupling pathways. Conventional nonlinear hydraulic solvers provide reliable feasibility assessment but are costly for stochastic screening, whereas unconstrained learning-based surrogates may produce hydraulically infeasible states. This study develops a physics-informed graph neural network surrogate for steady-state gas-network simulation and feasibility screening. The model uses an edge-centric architecture to predict pipe-level squared-pressure differences and flows. A differentiable projection layer enforces nodal mass conservation on predicted flows, while a Laplacian reconstruction maps edge pressure differences to topologically consistent nodal pressures.The framework is evaluated on GasLib-134, GasLib-135, and GasLib-582 using stochastically generated operating scenarios. On the meshed 582-node benchmark trained with 5000 scenarios, the surrogate achieves a pressure mean absolute error of 1.05~bar, corresponding to 1.3% of the realized pressure range, with R2 = 0.981. Projected-flow predictions reach R2 = 0.972, and mass-balance residuals are reduced to numerical precision, on the order of 10-5--10-4 Nm3/s. Compared with the MYNTS reference solver, inference is reduced from seconds to milliseconds, with the largest benchmark evaluated in less than 40ms. Loadability and out-of-distribution stress-test evaluations demonstrate robust feasibility screening under high-load conditions, while strongly localized demand concentrations are identified as cases requiring solver-based verification near feasibility limits. The framework provides a physically constrained planning accelerator for high-volume scenario screening and prioritization.","url":"https://doi.org/10.2139/ssrn.6878407","authors":["Dongrui Jiang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-04T12:43:42Z","doi":"10.2139/ssrn.6878407","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1109/icnn.1993.298686","name":"Towards an event-space self-configurable neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnn.1993.298686","authors":["D.K.Y. Chiu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-12-30T17:49:31Z","doi":"10.1109/icnn.1993.298686","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1109/ijcnn.2006.1716275","name":"Comparison of Artificial Neural Network Architectures and Training Algorithms for Solving the Knight's Tours","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.1716275","authors":["R.G. Escalante","H.A. Malki"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-30T17:35:23Z","doi":"10.1109/ijcnn.2006.1716275","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1109/ijcnn.2006.246888","name":"A New Unsupervised Neural Network for Pattern Recognition with Spiking Neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.246888","authors":["R. Lorenzo","R. Riccardo","C. Antonio"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T15:34:22Z","doi":"10.1109/ijcnn.2006.246888","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1109/neurel.2012.6419970","name":"FPGA implementation of neural network as processing element in ice detector","source":"crossref","abstract":"","url":"https://doi.org/10.1109/neurel.2012.6419970","authors":["Matteo Marouf","Jelena Popovic-Bozovic","Ivan Popovic"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-01-31T12:22:27Z","doi":"10.1109/neurel.2012.6419970","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.4018/978-1-6684-2408-7.ch040","name":"Analyzing Intraductal Papillary Mucinous Neoplasms Using Artificial Neural Network Methodologic Triangulation","source":"crossref","abstract":"Intraductal papillary mucinous neoplasms (IPMN) are a type of mucinous pancreatic cyst. IPMN have been shown to be pre-malignant precursors to pancreatic cancer, which has an extremely high mortality rate with average survival less than 1 year. The purpose of this analysis is to utilize methodological triangulation using artificial neural networks and regression to examine the impact and effectiveness of a collection of variables believed to be predictive of malignant IPMN pathology. Results indicate that the triangulation is effective in both finding a new predictive variable and possibly reducing the number of variables needed for predicting if an IPMN is malignant or benign.","url":"https://doi.org/10.4018/978-1-6684-2408-7.ch040","authors":["Steven Walczak","Jennifer B. Permuth","Vic Velanovich"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-17T11:47:50Z","doi":"10.4018/978-1-6684-2408-7.ch040","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/j.neunet.2008.05.002","name":"Neural network learning of optimal Kalman prediction and control","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2008.05.002","authors":["Ralph Linsker"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-05-29T06:22:56Z","doi":"10.1016/j.neunet.2008.05.002","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.7717/peerj.18192/supp-1","name":"Supplemental Information 1: Code for the Pix2Pix Neural Network.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj.18192/supp-1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-23T03:33:33Z","doi":"10.7717/peerj.18192/supp-1","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.7717/peerj-cs.3012/supp-1","name":"Supplemental Information 1: Working of Recurrent Neural Network (RNN).","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.3012/supp-1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-22T08:06:20Z","doi":"10.7717/peerj-cs.3012/supp-1","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.7551/mitpress/3163.003.0015","name":"Neural Network Modeling of Executive Functioning with the Tower of Hanoi Test in Frontal Lobe-Lesioned Patients","source":"crossref","abstract":"","url":"https://doi.org/10.7551/mitpress/3163.003.0015","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-12-14T02:49:52Z","doi":"10.7551/mitpress/3163.003.0015","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.21275/v4i12.nov152218","name":"Computerised Tuberculosis Detection Using Artificial Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.21275/v4i12.nov152218","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-04-28T07:20:51Z","doi":"10.21275/v4i12.nov152218","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.37473/fic/10.1002/ima.22562","name":"COVID\n            ‐19 vs influenza viruses: A cockroach optimized deep neural network classification approach","source":"crossref","abstract":"","url":"https://doi.org/10.37473/fic/10.1002/ima.22562","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-08T01:44:30Z","doi":"10.37473/fic/10.1002/ima.22562","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/s0893-6080(99)00072-6","name":"Accelerating neural network training using weight extrapolations","source":"crossref","abstract":"","url":"https://doi.org/10.1016/s0893-6080(99)00072-6","authors":["S.V. Kamarthi","S. Pittner"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-25T12:59:42Z","doi":"10.1016/s0893-6080(99)00072-6","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/0893-6080(96)00039-1","name":"Time Intervals Comparing Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(96)00039-1","authors":["JURAJ PAVLÁSEK","JURAJ POLEDNA","FEDOR JAGLA"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-25T23:57:31Z","doi":"10.1016/0893-6080(96)00039-1","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/j.neunet.2014.08.004","name":"Logarithmic learning for generalized classifier neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2014.08.004","authors":["Buse Melis Ozyildirim","Mutlu Avci"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-08-19T13:01:22Z","doi":"10.1016/j.neunet.2014.08.004","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/s0893-6080(01)00127-7","name":"A methodology to explain neural network classification","source":"crossref","abstract":"","url":"https://doi.org/10.1016/s0893-6080(01)00127-7","authors":["Raphael Féraud","Fabrice Clérot"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-25T10:36:15Z","doi":"10.1016/s0893-6080(01)00127-7","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1109/icipnp62754.2023.00043","name":"Design and Implementation of Series-Parallel Connectable Memristor Simulators Based on Combination of Virtuality and Reality","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icipnp62754.2023.00043","authors":["Yijia Chen","Penghao Liu","Michel Kadoch"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-23T17:50:59Z","doi":"10.1109/icipnp62754.2023.00043","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1007/978-3-319-76375-0_23","name":"Cellular Nonlinear Networks with Memristor Synapses","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-76375-0_23","authors":["Fernando Corinto","Alon Ascoli","Young-Su Kim","Kyeong-Sik Min"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-11-12T22:03:43Z","doi":"10.1007/978-3-319-76375-0_23","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.5220/0009908902660271","name":"Neural Network with Principal Component Analysis for Malware Detection using Network Traffic Features","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0009908902660271","authors":["Ventje Jeremias Lewi Engel","Mychael Maoeretz Engel","Evan Joshua"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-07-10T16:45:02Z","doi":"10.5220/0009908902660271","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.2172/1959815","name":"Neural network accelerator for quantum control","source":"crossref","abstract":"","url":"https://doi.org/10.2172/1959815","authors":["David Xu","A. Barış Özgüler","Giuseppe Di Guglielmo","Nhan Tran","Gabriel Perdue","Luca Carloni","Farah Fahim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-08T03:26:52Z","doi":"10.2172/1959815","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.37473/dac/10.1002/ima.22562","name":"COVID\n            ‐19 vs influenza viruses: A cockroach optimized deep neural network classification approach","source":"crossref","abstract":"","url":"https://doi.org/10.37473/dac/10.1002/ima.22562","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-07T20:45:23Z","doi":"10.37473/dac/10.1002/ima.22562","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1109/ijcnn.2006.247387","name":"A Dynamic Neural Network-based Reaction Wheel Fault Diagnosis for Satellites","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.247387","authors":["Z.Q. Li","L. Ma","K. Khorasani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T11:34:22Z","doi":"10.1109/ijcnn.2006.247387","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.22266/ijies2023.0228.33","name":"Hybrid Convolutional Neural Network with Residual Neural Network for Breast Cancer Prediction Using Mammography Images","source":"crossref","abstract":"","url":"https://doi.org/10.22266/ijies2023.0228.33","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-29T20:00:39Z","doi":"10.22266/ijies2023.0228.33","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1088/0954-898x_1_3_002","name":"Exploiting prior knowledge in network optimization: an illustration from medical prognosis","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_1_3_002","authors":["David Lowe","Andrew R Webb"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:02Z","doi":"10.1088/0954-898x_1_3_002","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1088/0954-898x_10_1_001","name":"Leap-frog is a robust algorithm for training neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_10_1_001","authors":["Johann E W Holm","Elizabeth C Botha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:03:49Z","doi":"10.1088/0954-898x_10_1_001","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1109/ijcnn.2006.246895","name":"A Multi-layer ADaptive FUnction Neural Network (MADFUNN) for Analytical Function Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.246895","authors":["Miao Kang","D. Palmer-Brown"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T15:34:22Z","doi":"10.1109/ijcnn.2006.246895","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1080/net.12.3.271.287","name":"Beats, kurtosis and visual coding","source":"crossref","abstract":"","url":"https://doi.org/10.1080/net.12.3.271.287","authors":["M.G.A. Thomson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-12-09T01:33:28Z","doi":"10.1080/net.12.3.271.287","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1021/acs.jctc.5c01228.s001","name":"Hybrid Tensor Network and Neural Network Quantum States for Quantum Chemistry","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acs.jctc.5c01228.s001","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-09T14:40:41Z","doi":"10.1021/acs.jctc.5c01228.s001","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.7717/peerj.12127/fig-3","name":"Figure 3: Sleep scoring performance of artificial neural network.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj.12127/fig-3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-09T03:43:31Z","doi":"10.7717/peerj.12127/fig-3","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1109/nnat.1993","name":"Workshop on Neural Network Applications and Tools","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nnat.1993","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-02-05T15:33:16Z","doi":"10.1109/nnat.1993","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/j.neunet.2009.10.007","name":"A neural network model of Borderline Personality Disorder","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2009.10.007","authors":["Carl H. Berdahl"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-11-12T05:35:33Z","doi":"10.1016/j.neunet.2009.10.007","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1002/adfm.202270169","name":"Demonstration of Neuromodulation‐inspired Stashing System for Energy‐efficient Learning of Spiking Neural Network using a Self‐Rectifying Memristor Array (Adv. Funct. Mater. 29/2022)","source":"crossref","abstract":"","url":"https://doi.org/10.1002/adfm.202270169","authors":["Woon Hyung Cheong","Jae Bum Jeon","Jae Hyun In","Geunyoung Kim","Hanchan Song","Janho An","Juseong Park","Young Seok Kim","Cheol Seong Hwang","Kyung Min Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-07-18T08:39:23Z","doi":"10.1002/adfm.202270169","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1109/mocast70204.2026.11626373","name":"Towards Optical Memristor-Based Cellular Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mocast70204.2026.11626373","authors":["I. Messaris","D. Prousalis","A. S. Demirkol","R. Tetzlaff","V. Ntinas","A. H. Jaafar","S. Lethbridge","N. Kemp"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-31T18:16:20Z","doi":"10.1109/mocast70204.2026.11626373","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.17816/gc623428","name":"Design of a memristor-based neuron for spiking neural networks","source":"crossref","abstract":"The primary objective of neuromorphic system design is to surpass limitations in energy efficiency and scaling of classical von Neumann computing systems, through the emulation of animals’ nervous systems. This is achieved by conducting calculations in memory and encoding information in impulse signals, ultimately leading to enhanced adaptability. Adhering to these principles allows for improved energy efficiency and computational speed when solving machine learning problems, encompassing biomedical applications, embedded systems, and cyber-physical systems. Functional blocks modeling the main elements of the central nervous system, namely neurons and synapses, offer an advantage in implementing learning on a chip. The use of memristive electronic components, capable of altering their resistance based on the charge flowing through them, opens new doors for hardware implementation of neuromorphic systems. These devices offer advantages over conventional transistor electronics with respect to power consumption, component density, and performance. To achieve optimal results, the architecture of neuromorphic systems should be optimized at the device level. Memristive components are utilized to create neurons and synapses. This thesis is specifically focused on producing memristive neuron-like spike signal generators. Previously, memristive neurons were crafted using a locally active element comprised of vanadium dioxide VO2, which incorporated a negative differential resistance section of the IV-curve. One of the recent advancements in this field is a spiking neuron with frequency adaptation [1]. Its drawbacks, however, involve separating the memristive and locally active elements physically, resulting in higher energy consumption and decreased integration quality. In [2], models of memristive neurons with minimal complexity are introduced, which incorporate the Leaky Integrate-and-Fire principle. However, the circuits presented require the application of negative voltage pulses to a DC battery to reset the memristor to its initial high-resistance state. This limitation restricts its sphere of application in neuromorphic systems. This paper proposes a model of a neuron that overcomes these limitations by using the negative differential resistance of the memristor to generate spikes, along with integrating supplementary circuit components to sustain the resistive switching cycles of the memristor. The neuron model under consideration is implemented using the NI Multisim 14.2 SPICE environment and has been verified in the NI LabVIEW 2022 tool environment. The equations of the modified model of the generalized mean metastable switch of the memristor with self-directed channel [3] represent the current in the memristor branch of the neuron equivalent circuit. The simplicity of the equivalent circuitry of the neuron is attained by merging all the nonlinear features necessary for spike generation into one memristor model. The experimental phase of the study employed obtainable memristors from Knowm Corporation and the laboratory prototyping platform NI ELVIS III. The investigation of the proposed neuron model was accomplished through the application of sinusoidal and rectangular input signals. The refractory time of the neuron model was calculated. The chosen stack of computer simulation and semi-natural modeling technologies is applied within the research-driven design concept of electronic devices. This approach considers the importance of refining the properties and identification of the design object or its components during the development cycle.","url":"https://doi.org/10.17816/gc623428","authors":["V. Yu. Ostrovskii","O. S. Druzhina","O. Kamal","T. I. Karimov","D. N. Butusov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-06T08:05:41Z","doi":"10.17816/gc623428","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/j.aeue.2019.152894","name":"Non-ideal memristor synapse-coupled bi-neuron Hopfield neural network: Numerical simulations and breadboard experiments","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.aeue.2019.152894","authors":["Chengjie Chen","Han Bao","Mo Chen","Quan Xu","Bocheng Bao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-08-31T10:58:38Z","doi":"10.1016/j.aeue.2019.152894","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1063/5.0312026","name":"Dual-function Sb2S3/HfO2 memristor for reservoir computing and neural network learning via decoupled short- and long-term memory","source":"crossref","abstract":"Conventional computing architectures typically rely on separate devices to achieve dynamic sensing and long-term storage, leading to low integration density, high energy consumption, and significant data movement bottlenecks. Here, a biomimetic dual-function memristor based on an Sb2S3/HfO2 heterostructure is proposed, in which synergistic regulation of ion migration and electronic transport enables the materials-assisted decoupling and coordinated integration of short-term memory (STM) and long-term memory (LTM) functions within a single device. The device successfully emulates various biological synaptic behaviors, including paired-pulse facilitation/depression, tunable excitatory postsynaptic currents (EPSCs), and highly linear long-term potentiation/depression. Subsequently, utilizing the LTM characteristics of the device, a nonvolatile synaptic array is built to implement a fully connected neural network, achieving 94.5% accuracy. Meanwhile, a physical reservoir computing system is constructed using the STM dynamics to directly encode and recognize spatiotemporal features in iris image sequences, achieving 98% accuracy. Through coordinated innovation in materials, devices, and architecture, this work advances memristors from single-function memory elements toward multifunctional, all-electrical intelligent processing units.","url":"https://doi.org/10.1063/5.0312026","authors":["Mengru Song","Lele Li","Han Gu","Ziyang Hu","Yegang Lu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-09T13:16:47Z","doi":"10.1063/5.0312026","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/0893-6080(94)90017-5","name":"Oscillatory neural network and learning of continuously transformed patterns","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(94)90017-5","authors":["Yukio Hayashi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T03:25:55Z","doi":"10.1016/0893-6080(94)90017-5","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1109/72.97934","name":"A general regression neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/72.97934","authors":["D.F. Specht"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-24T15:16:32Z","doi":"10.1109/72.97934","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1088/0954-898x_5_4_002","name":"Attractor neural networks with excitatory neurons and fast inhibitory interneurons at low spike rates","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_5_4_002","authors":["Anthony N Burkitt"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T16:04:14Z","doi":"10.1088/0954-898x_5_4_002","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.3109/0954898x.2012.677095","name":"Learning stable, regularised latent models of neural population dynamics","source":"crossref","abstract":"","url":"https://doi.org/10.3109/0954898x.2012.677095","authors":["Lars Buesing","Jakob H. Macke","Maneesh Sahani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-04-30T12:13:42Z","doi":"10.3109/0954898x.2012.677095","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1007/978-3-319-02630-5_13","name":"Cellular Nonlinear Networks with Memristor Synapses","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-02630-5_13","authors":["Fernando Corinto","Alon Ascoli","Young-Su Kim","Kyeong-Sik Min"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-12-18T10:27:01Z","doi":"10.1007/978-3-319-02630-5_13","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.15760/etd.899","name":"Memristor-based Reservoir Computing","source":"crossref","abstract":"","url":"https://doi.org/10.15760/etd.899","authors":["Manjari Kulkarni"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-01-20T20:14:44Z","doi":"10.15760/etd.899","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.2172/896963","name":"Tampa Electric Neural Network Sootblowing","source":"crossref","abstract":"","url":"https://doi.org/10.2172/896963","authors":["Mark A. Rhode"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-04-09T17:10:21Z","doi":"10.2172/896963","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.7717/peerjcs.1084/table-3","name":"Table 3: Performance comparison with other neural network methods.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerjcs.1084/table-3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-08-30T03:45:01Z","doi":"10.7717/peerjcs.1084/table-3","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.7717/peerj-cs.1977/fig-5","name":"Figure 5: The neural network architecture of E-MFNN.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.1977/fig-5","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-19T03:43:31Z","doi":"10.7717/peerj-cs.1977/fig-5","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.2139/ssrn.3804294","name":"Neural Network: A to Z","source":"crossref","abstract":"An artificial neural network is a basic building block for deep learning. Understanding the neural network and making intuitive sense of them is a major challenge for anyone who wants to use them. This is partly due to incomplete articles and highly technical and mathematical papers. Although understanding papers are the best way to completely grasp the ideas, it's very intimidating to beginners. Most of the articles available online are not complete in the sense that they fail to provide intuition about nuances of neural networks at a deeper level. It is important to understand the neural network at a deeper level to make practical use of it. With partial knowledge application of neural networks falls apart at multiple levels from choosing cost function to the learning rate. In this paper, we have covered major concepts of neural networks which is important to fully understand neural networks functionality. This paper also contains a zoomed-in view of each part of mathematics through equations and python code.","url":"https://doi.org/10.2139/ssrn.3804294","authors":["Ayush Singh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-04-02T23:03:45Z","doi":"10.2139/ssrn.3804294","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.7717/peerj-cs.2802/fig-4","name":"Figure 4: Simple neural network with activation function “relu”.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.2802/fig-4","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-07T04:48:57Z","doi":"10.7717/peerj-cs.2802/fig-4","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1080/0954898x.2024.2374852","name":"MLNAS: Meta-learning based neural architecture search for automated generation of deep neural networks for plant disease detection tasks","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2024.2374852","authors":["Sahil Verma","Prabhat Kumar","Jyoti Prakash Singh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-12T06:09:53Z","doi":"10.1080/0954898x.2024.2374852","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1088/0954-898x/4/1/001","name":"Dynamics of neural networks with non-monotone activation function","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/4/1/001","authors":["P De Felice","C Marangi","G Nardulli","G Pasquariello","L Tedesco"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-24T22:35:54Z","doi":"10.1088/0954-898x/4/1/001","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1109/tce.2026.3676405","name":"Memristor-Based Neural Network Circuit of Learning Conflict and Context-Dependent Memory and Its Application in Intelligent Nursing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tce.2026.3676405","authors":["Kefan Tao","Yanfeng Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-23T20:07:18Z","doi":"10.1109/tce.2026.3676405","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1134/s001249662201001x","name":"Neural Network-Based Decoding Input Stimulus Data Based on Recurrent Neural Network Neural Activity Pattern","source":"crossref","abstract":"Abstract The paper reports the assessment of the possibility to recover information obtained using an artificial neural network via inspecting neural activity patterns. A simple recurrent neural network forms dynamic excitation patterns for storing data on input stimulus in the course of the advanced delayed match to sample test with varying duration of pause between the received stimuli. Information stored in these patterns can be used by the neural network at any moment within the specified interval (three to six clock cycles), whereby it appears possible to detect invariant representation of received stimulus. To identify these representations, the neural network-based decoding method that shows 100% efficiency of received stimuli recognition has been suggested. This method allows for identification the minimum subset of neurons, the excitation pattern of which contains comprehensive information about the stimulus received by the neural network.","url":"https://doi.org/10.1134/s001249662201001x","authors":["S. I. Bartsev","P. M. Baturina","G. M. Markova"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-17T04:04:56Z","doi":"10.1134/s001249662201001x","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1080/09548980903161241","name":"Stability criteria for the contextual emergence of macrostates in neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1080/09548980903161241","authors":["Peter beim Graben","Adam Barrett","Harald Atmanspacher"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-09-03T22:56:54Z","doi":"10.1080/09548980903161241","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/j.amc.2023.128110","name":"Function matrix projection synchronization for the multi-time delayed fractional order memristor-based neural networks with parameter uncertainty","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.amc.2023.128110","authors":["Jin-Man He","Li-Jun Pei"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-17T13:27:48Z","doi":"10.1016/j.amc.2023.128110","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/j.jfranklin.2013.05.026","name":"Passivity analysis of memristor-based recurrent neural networks with time-varying delays","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.jfranklin.2013.05.026","authors":["Shiping Wen","Zhigang Zeng","Tingwen Huang","Yiran Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-06-05T00:04:00Z","doi":"10.1016/j.jfranklin.2013.05.026","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1080/09548980500533461","name":"The importance of different timings of excitatory and inhibitory pathways in neural field models","source":"crossref","abstract":"","url":"https://doi.org/10.1080/09548980500533461","authors":["Carlo Laing","Stephen Coombes"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-05-25T20:08:33Z","doi":"10.1080/09548980500533461","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1088/0954-898x/7/3/004","name":"Retrieval properties of attractor neural networks that obey Dale's law using a self-consistent signal-to-noise analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/7/3/004","authors":["Anthony Burkitt"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-24T22:35:54Z","doi":"10.1088/0954-898x/7/3/004","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/b978-0-12-228640-7.50004-0","name":"CONTRIBUTORS","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-12-228640-7.50004-0","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-01T08:04:18Z","doi":"10.1016/b978-0-12-228640-7.50004-0","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/b978-0-12-228640-7.50003-9","name":"Dedication","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-12-228640-7.50003-9","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-01T04:02:55Z","doi":"10.1016/b978-0-12-228640-7.50003-9","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1007/978-94-007-4491-2_13","name":"Memristor Models for Pattern Recognition Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-94-007-4491-2_13","authors":["Fernando Corinto","Alon Ascoli","Marco Gilli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-06-27T17:03:30Z","doi":"10.1007/978-94-007-4491-2_13","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.2172/896964","name":"Tampa Electric Neural Network Sootblowing","source":"crossref","abstract":"","url":"https://doi.org/10.2172/896964","authors":["Mark  A. Rhode"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-08-03T13:32:47Z","doi":"10.2172/896964","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.7717/peerj-cs.2594/table-5","name":"Table 5: Convolutional neural network summary on blink detection.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.2594/table-5","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-14T03:30:26Z","doi":"10.7717/peerj-cs.2594/table-5","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.14264/90adad5","name":"Federated graph neural network-based recommender systems","source":"crossref","abstract":"","url":"https://doi.org/10.14264/90adad5","authors":["Liang Qu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-18T17:28:11Z","doi":"10.14264/90adad5","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/j.neunet.2017.05.003","name":"Pinning synchronization of memristor-based neural networks with time-varying delays","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2017.05.003","authors":["Zhanyu Yang","Biao Luo","Derong Liu","Yueheng Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-05-18T14:02:16Z","doi":"10.1016/j.neunet.2017.05.003","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/0893-6080(88)90337-1","name":"A neural network approach to speech recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90337-1","authors":["Y.C. Lee","H.H. Chen","G.Z. Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T05:05:53Z","doi":"10.1016/0893-6080(88)90337-1","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.21203/rs.3.rs-2245407/v1","name":"Image Steganography of convolutional neural network based on neural architecture search","source":"crossref","abstract":"Abstract Recent studies show that the performance of deep convolutional neural network (CNN) applied to Steganography is better than that of traditional methods. We propose NAS-Stego to solve the problem of static network structure of the model in steganography algorithm based on deep learning. Different from the existing steganography algorithm based on deep learning, NAS-Stego uses a controller which is a LSTM[18] to generate the architecture of the encoder. We use reinforcement learning and Monte Carlo to train that controller. We have conducted experiments on BOSSBase dataset, and the results show that NAS-Stego has achieved better performance. We use steganalysis analyzer StegExpose to test the anti-steganalysis capability of NAS-Stego, the experiments show that NAS-Stego has achieved good performance.","url":"https://doi.org/10.21203/rs.3.rs-2245407/v1","authors":["Yanger Meng","Jingtao Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-07T14:41:15Z","doi":"10.21203/rs.3.rs-2245407/v1","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1023/a:1018621308457","name":"Orthogonal RBF Neural Network Approximation","source":"crossref","abstract":"","url":"https://doi.org/10.1023/a:1018621308457","authors":["Péter András"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-02-19T20:24:24Z","doi":"10.1023/a:1018621308457","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1109/tnnls.2014.2383395","name":"Memristor-Based Multilayer Neural Networks With Online Gradient Descent Training","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnnls.2014.2383395","authors":["Daniel Soudry","Dotan Di Castro","Asaf Gal","Avinoam Kolodny","Shahar Kvatinsky"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-01-14T19:43:06Z","doi":"10.1109/tnnls.2014.2383395","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/b978-0-444-89178-5.50038-5","name":"ON NEURAL NETWORK ALGORITHM FOR GRAPH MATCHING","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-444-89178-5.50038-5","authors":["Igor Yu. POTERYAIKO"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-01T02:49:16Z","doi":"10.1016/b978-0-444-89178-5.50038-5","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1039/d3nh00121k","name":"Linear conductance update improvement of CMOS-compatible second-order memristors for fast and energy-efficient training of a neural network using a memristor crossbar array","source":"crossref","abstract":"The linear conductance update of a CMOS-compatible HfO 2 memristor is improved by introducing a second-order memristor effect and connecting a voltage divider to the device, which makes the memristor crossbar array more energy- and time-efficient.","url":"https://doi.org/10.1039/d3nh00121k","authors":["See-On Park","Taehoon Park","Hakcheon Jeong","Seokman Hong","Seokho Seo","Yunah Kwon","Jongwon Lee","Shinhyun Choi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-27T02:02:25Z","doi":"10.1039/d3nh00121k","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1109/icras.2019.8809044","name":"H<sub>∞</sub> State Estimation of Memristor-based Recurrent Neural Networks with Mixed Delay","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icras.2019.8809044","authors":["Xiangxiang Wang","Yongbin Yu","Nijing Yang","Haowen Tang","Shouming Zhong","Tashi Nyima"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-08-23T00:18:44Z","doi":"10.1109/icras.2019.8809044","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/j.eswa.2023.119938","name":"New Criteria of Event-triggered Exponential State Estimation for Delayed semi-Markovian Memristor-based Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.eswa.2023.119938","authors":["Xiaoman Liu","Lianglin Xiong","Haiyang Zhang","Jinde Cao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-03-27T02:01:15Z","doi":"10.1016/j.eswa.2023.119938","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1109/tnnls.2021.3096963","name":"Adaptive Synchronization for Delayed Chaotic Memristor-Based Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnnls.2021.3096963","authors":["Youming Xin","Zunshui Cheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-07-26T21:27:21Z","doi":"10.1109/tnnls.2021.3096963","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1088/0954-898x_8_1_006","name":"A neural net model of the adaptation of binocular vertical eye alignment","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_8_1_006","authors":["Jeffrey W Mccandless","Clifton M Schor"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:05:00Z","doi":"10.1088/0954-898x_8_1_006","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/0893-6080(88)90419-4","name":"Fault simulation of a wafer-scale integrated neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90419-4","authors":["N. May","D. Hammerstrom"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T01:05:53Z","doi":"10.1016/0893-6080(88)90419-4","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/j.neunet.2006.07.005","name":"Neural network explanation using inversion","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2006.07.005","authors":["Emad W. Saad","Donald C. Wunsch"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-07T07:24:25Z","doi":"10.1016/j.neunet.2006.07.005","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/s0893-6080(98)00130-0","name":"Matrix logarithm parametrizations for neural network covariance models","source":"crossref","abstract":"","url":"https://doi.org/10.1016/s0893-6080(98)00130-0","authors":["Peter M Williams"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-25T23:57:31Z","doi":"10.1016/s0893-6080(98)00130-0","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/b978-0-444-88400-8.50024-8","name":"THE PYGMALION NEURAL NETWORK PROGRAMMING ENVIRONMENT","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-444-88400-8.50024-8","authors":["B. Angéniol","P. Treleaven"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-01T02:37:43Z","doi":"10.1016/b978-0-444-88400-8.50024-8","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1142/9789812796851_0008","name":"General Regression Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789812796851_0008","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-07-18T16:55:18Z","doi":"10.1142/9789812796851_0008","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1109/72.80238","name":"Standardization of neural network terminology","source":"crossref","abstract":"","url":"https://doi.org/10.1109/72.80238","authors":["R.C. Eberhart"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-24T19:16:32Z","doi":"10.1109/72.80238","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/s0893-6080(05)80144-3","name":"Optical character recognition by a neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/s0893-6080(05)80144-3","authors":["Michael Sabourin","Amar Mitiche"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-10-19T13:38:58Z","doi":"10.1016/s0893-6080(05)80144-3","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1088/0954-898x_4_1_007","name":"Modelling chemical modulation of neural processes","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_4_1_007","authors":["A C C Coolen","A J Noest","G B de Vries"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T16:04:11Z","doi":"10.1088/0954-898x_4_1_007","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/j.neunet.2013.07.009","name":"Multivariate neural network operators with sigmoidal activation functions","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2013.07.009","authors":["Danilo Costarelli","Renato Spigler"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-08-06T04:35:02Z","doi":"10.1016/j.neunet.2013.07.009","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1109/tnn.2004.823448","name":"Nonlinear Dynamical Systems: Feedforward Neural Network Perspective","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnn.2004.823448","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2004-02-24T21:01:05Z","doi":"10.1109/tnn.2004.823448","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/0893-6080(95)00141-7","name":"New rigorous results for the Hopfield's neural network model","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(95)00141-7","authors":["Olivier François"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-25T19:57:31Z","doi":"10.1016/0893-6080(95)00141-7","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/0893-6080(88)90317-6","name":"Effects of network topology on speech categorization","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90317-6","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T01:05:53Z","doi":"10.1016/0893-6080(88)90317-6","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1201/9780367813239-2","name":"Challenges for Neural Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9780367813239-2","authors":["Antony Browne"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-09-26T04:16:27Z","doi":"10.1201/9780367813239-2","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1109/neurel.2010.5644085","name":"Session 6: Realizations of neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/neurel.2010.5644085","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-12-09T10:34:50Z","doi":"10.1109/neurel.2010.5644085","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/b978-0-444-89488-5.50147-0","name":"NEURAL NETWORK IMAGE SEGMENTATION FOR AUTOMATED VISUAL INSPECTION","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-444-89488-5.50147-0","authors":["Ullrich Schramm"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-01T07:02:44Z","doi":"10.1016/b978-0-444-89488-5.50147-0","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/b978-0-444-89488-5.50088-9","name":"Neural Network Programming Environments","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-444-89488-5.50088-9","authors":["M.L. Recce","P.V. Rocha","P.C. Treleaven"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-01T03:04:07Z","doi":"10.1016/b978-0-444-89488-5.50088-9","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1088/0954-898x_11_4_302","name":"Persistent activity and the single-cell frequency–current curve in a cortical network model","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_11_4_302","authors":["Nicolas Brunel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:03:55Z","doi":"10.1088/0954-898x_11_4_302","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1515/9781400850785.31","name":"Chapter Two. Fundamentals of Neural Network Models","source":"crossref","abstract":"","url":"https://doi.org/10.1515/9781400850785.31","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-12-01T14:10:04Z","doi":"10.1515/9781400850785.31","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1080/0954898x.2024.2358957","name":"Support vector machine-based stock market prediction using long short-term memory and convolutional neural network with aquila circle inspired optimization","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2024.2358957","authors":["J. Karthick Myilvahanan","N. Mohana Sundaram"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-10T07:10:42Z","doi":"10.1080/0954898x.2024.2358957","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.4103/abr.abr_407_23","name":"Predicting Pregnant Women’s Abortion: Artificial Neural Network, Wavelet Neural Network and Adaptive Neural Fuzzy Inference System","source":"crossref","abstract":"Background: Abortion is an important and controversial issue and one of the important reasons for the mortality of pregnant women worldwide. This study aimed to predict the risk factors of abortion in pregnant women using artificial neural network, wavelet neural network, and adaptive neural fuzzy inference system. Materials and Methods: The study is an analytical-comparative modeling and data of 4437 pregnant women from the Ravansar Non-Communicable Disease (RaNCD) cohort study from 2014 to 2016 was used. First, six variables were chosen through the genetic algorithm approach, then artificial neural network (ANN), wavelet neural network (WNN), and adaptive neural fuzzy inference system (ANFIS) were run. Finally, the performance of the models was compared based on the evaluation criteria. All analyses were done in MATLAB R2019b software. Results: ANN with RMSE of 0.019 showed better performance than ANFIS and WNN with 0.42 and 1.445, respectively. Further, the accuracy, sensitivity, and specificity in ANN were 100%, 99%, and 100%, while in WNN, they were 76.2%, 76.4%, and 66.7%. However, when the researchers used three selected variables, the accuracy, sensitivity, and specificity as well as RMSE in ANFIS were 100%, 100% 100%, and 0; 100%, 99%, 100%, and 0.021 in ANN; and finally 76.2%, 76.4%, 38.5%, and 1.553 in WNN. Conclusion: The models with six input variables indicated that the artificial neural network has a better performance than the other two models, but based on the three variables, the fuzzy neural inference system performed better than the other two models.","url":"https://doi.org/10.4103/abr.abr_407_23","authors":["Amir Hossein Hashemian","Behzad Mahaki","Mansour Rezaei","Leila Solouki","Mohammad Amin Sohrabi Cheqabaleki","Somayeh Sohrabi Cheqabaleki"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-31T02:00:22Z","doi":"10.4103/abr.abr_407_23","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.5194/gi-2018-53","name":"OzoNet: Atmospheric Ozone Interpolation with Deep Convolutional\nNeural Networks","source":"crossref","abstract":"Abstract. We propose a deep learning method for Atmospheric Ozone Interpolation. Our method directly learns an end-to-end mapping between classically interpolated satellite ozone images and the real ozone measurements. The model's architecture represents a deep stack of convolutions (CNN) that takes the already interpolated images (Using the classical state-of-the-art interpolation method) as Input and outputs a more precise Interpolation of the Region of Interest. Our deep CNN has a lightweight structure, yet demonstrates state-of-the-art interpolation quality, and achieves optimal data processing latency (∆T) for production-ready near-real-time Atmospheric Image Interpolation, which has a big advantage over the state of the art classical interpolation algorithms. We explore different network structures and parameter settings to achieve trade-offs between performance and speed. This method showcases the potential applications of deep learning in Remote Sensing and Climate Science.","url":"https://doi.org/10.5194/gi-2018-53","authors":["Mohamed Akram Zaytar","Chaker El Amrani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-06-03T03:32:40Z","doi":"10.5194/gi-2018-53","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1142/9789812796851_0013","name":"Other Neural Network Models","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789812796851_0013","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-07-18T16:55:18Z","doi":"10.1142/9789812796851_0013","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1887/0750303123/b365c116","name":"A neural network for recognizing distantly related protein sequences","source":"crossref","abstract":"","url":"https://doi.org/10.1887/0750303123/b365c116","authors":["Dmitrij Frishman","Patrick Argos"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2004-11-26T10:22:37Z","doi":"10.1887/0750303123/b365c116","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1088/0954-898x_3_4_007","name":"Recombination and unsupervised learning: effects of crossover in the genetic optimization of neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_3_4_007","authors":["Filippo Menczer","Domenico Parisi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:12Z","doi":"10.1088/0954-898x_3_4_007","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1088/0954-898x/9/3/005","name":"Autonomous development of decorrelation filters in neural networks with recurrent inhibition","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/9/3/005","authors":["H Jonker","A Coolen","J Denier van der Gon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/9/3/005","addedAt":"2026-09-01T01:48:32.344Z","updatedAt":"2026-09-01T01:48:32.344Z"},{"id":"doi:10.1016/b978-0-08-051433-8.50015-x","name":"Designing Feedforward Network Architectures","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-08-051433-8.50015-x","authors":["Timothy Masters"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-01T17:48:56Z","doi":"10.1016/b978-0-08-051433-8.50015-x","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.21203/rs.3.rs-610265/v1","name":"FuzzSemNIC: A Deep Fuzzy Neural Network Semantic-enhanced Approach of Neural Image Captioning","source":"crossref","abstract":"Abstract Neural image captioning (NIC) is considered as a primitive problem artificial intelligence (AI) in which creates a connection between computer vision (CV) and natural language processing (NLP). However, recent attribute-based and textual semantic attention based models in NIC still encounter challenges related to irrelevant concentration of the designed attention mechanism on the relationship between extracted visual features and textual representations of corresponding image’s caption. Moreover, recent NIC-based models also suffer from the uncertainties and noises of extracted visual latent features from images which sometime leads to the disruption of the given image captioning model to sufficiently attend on the correct visual concepts. To solve these challenges, in this paper, we proposed an end-to-end integrated deep fuzzy-neural network with the unified attention-based semantic-enhanced vision-language approach, called as FuzzSemNIC. To alleviate noises and ambiguities from the extracted visual features, we apply a fused deep fuzzy-based neural network architecture to effectively learn and generate the visual representations of images. Then, the learnt fuzzy-based visual embedding vectors are combined with selective attributes/concepts of images via a recurrent neural network (RNN) architecture to incorporate the fused latent visual features into captioning task. Finally, the fused visual representations are integrated with a unified vision-language encoder-decoder for handling caption generation task. Extensive experiments in benchmark NIC-based datasets demonstrate the effectiveness of our proposed FuzzSemNIC model.","url":"https://doi.org/10.21203/rs.3.rs-610265/v1","authors":["Tham Vo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-07-12T19:01:55Z","doi":"10.21203/rs.3.rs-610265/v1","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1016/b978-0-08-051433-8.50024-0","name":"Evaluating Performance of Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-08-051433-8.50024-0","authors":["Timothy Masters"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-01T13:48:43Z","doi":"10.1016/b978-0-08-051433-8.50024-0","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1101/2022.06.06.494909","name":"Artificial neural network modelling of the neural population code underlying mathematical operations","source":"crossref","abstract":"Abstract Mathematical operations have long been regarded as a sparse, symbolic process in neuroimaging studies. In contrast, advances in artificial neural networks (ANN) have enabled extracting distributed representations of mathematical operations. Recent neuroimaging studies have compared distributed representations of the visual, auditory and language domains in ANNs and biological neural networks (BNNs). However, such a relationship has not yet been examined in mathematics. Here we used the fMRI data of a series of mathematical problems with nine different combinations of operators to construct voxel-wise encoding models using both sparse operator and latent ANN features. Representational similarity analysis demonstrated shared representations between ANN and BNN, an effect particularly evident in the intraparietal sulcus. Feature-brain similarity analysis served to reconstruct a sparse representation of mathematical operations based on distributed ANN features. Such reconstruction was more efficient when using features from deeper ANN layers. Moreover, latent ANN features allowed the decoding of novel operators not used during model training from brain activity. The current study provides novel insights into the neural code underlying mathematical thought.","url":"https://doi.org/10.1101/2022.06.06.494909","authors":["Tomoya Nakai","Shinji Nishimoto"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-06T21:50:10Z","doi":"10.1101/2022.06.06.494909","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1016/j.neucom.2020.09.039","name":"New criteria for finite-time stability of fractional order memristor-based neural networks with time delays","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2020.09.039","authors":["Feifei Du","Jun-Guo Lu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-30T06:39:41Z","doi":"10.1016/j.neucom.2020.09.039","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1109/iscas.2014.6865255","name":"Analytic modeling of memristor variability for robust memristor systems designs","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas.2014.6865255","authors":["Sami Smaili","Yehia Massoud"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-30T17:16:29Z","doi":"10.1109/iscas.2014.6865255","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.3109/0954898x.2011.566303","name":"Analyzing multicomponent receptive fields from neural responses to natural stimuli","source":"crossref","abstract":"","url":"https://doi.org/10.3109/0954898x.2011.566303","authors":["Ryan J. Rowekamp","Tatyana O. Sharpee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-04-30T12:15:08Z","doi":"10.3109/0954898x.2011.566303","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1016/j.aeue.2021.154041","name":"Design and implementation of four-color conjecture circuit based on memristor neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.aeue.2021.154041","authors":["Junwei Sun","Xiao Xiao","Peng Liu","Yanfeng Wang","Yingcong Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-17T21:36:19Z","doi":"10.1016/j.aeue.2021.154041","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1109/ijcnn.1992.227166","name":"Massively parallel neural network recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.1992.227166","authors":["C.L. Wilson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-01-02T16:19:33Z","doi":"10.1109/ijcnn.1992.227166","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1109/ijcnn.1989.118536","name":"Artificial neural network for mapping","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.1989.118536","authors":["J. Stojanovski"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-01-13T18:46:33Z","doi":"10.1109/ijcnn.1989.118536","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1109/icnn.1995.487374","name":"Neural network-based regions detection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnn.1995.487374","authors":["T. Ohyama"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-11-19T13:30:57Z","doi":"10.1109/icnn.1995.487374","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1016/b978-0-444-89488-5.50055-5","name":"A Recurrent Neural Network Model","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-444-89488-5.50055-5","authors":["Abhay B. Bulsari","Henrik Saxén"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-01T06:59:27Z","doi":"10.1016/b978-0-444-89488-5.50055-5","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1016/b978-0-12-546090-3.50009-7","name":"DYNAMICS OF NEURAL NETWORK OPERATIONS","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-12-546090-3.50009-7","authors":["Alianna J. Maren"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-06-30T08:00:47Z","doi":"10.1016/b978-0-12-546090-3.50009-7","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1109/tcsii.2020.3000492","name":"A Multi-Stable Memristor and its Application in a Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tcsii.2020.3000492","authors":["Hairong Lin","Chunhua Wang","Qinghui Hong","Yichuang Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-08T21:18:21Z","doi":"10.1109/tcsii.2020.3000492","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1109/tii.2024.3450081","name":"A Memristor-Based Neural Network Circuit With Latent Inhibition and Transient Forgetting Effects and Application in Industrial Intelligent Grasping","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tii.2024.3450081","authors":["Junwei Sun","Yijin Shen","Peng Liu","Yanfeng Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-19T13:32:44Z","doi":"10.1109/tii.2024.3450081","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1016/0893-6080(88)90249-3","name":"Backward conditioning: A neural network model which exhibits both excitatory and inhibitory conditioning","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90249-3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T01:05:53Z","doi":"10.1016/0893-6080(88)90249-3","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1109/ijcnn.2006.247029","name":"A Neural Network Model for Maximizing Prediction Accuracy in Haplotype Tagging SNP Selection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.247029","authors":["Jae-Yoon Jung","P.H. Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T11:34:22Z","doi":"10.1109/ijcnn.2006.247029","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.3390/app14083471","name":"Improved Convolutional Neural Network–Time-Delay Neural Network Structure with Repeated Feature Fusions for Speaker Verification","source":"crossref","abstract":"The development of deep learning greatly promotes the progress of speaker verification (SV). Studies show that both convolutional neural networks (CNNs) and dilated time-delay neural networks (TDNNs) achieve advanced performance in text-independent SV, due to their ability to sufficiently extract the local feature and the temporal contextual information, respectively. Also, the combination of the above two has achieved better results. However, we found a serious gridding effect when we apply the 1D-Res2Net-based dilated TDNN proposed in ECAPA-TDNN for SV, which indicates discontinuity and local information losses of frame-level features. To achieve high-resolution process for speaker embedding, we improve the CNN–TDNN structure with proposed repeated multi-scale feature fusions. Through the proposed structure, we can effectively improve the channel utilization of TDNN and achieve higher performance under the same TDNN channel. And, unlike previous studies that have all converted CNN features to TDNN features directly, we also studied the latent space transformation between CNN and TDNN to achieve efficient conversion. Our best method obtains 0.72 EER and 0.0672 MinDCF on VoxCeleb-O test set, and the proposed method performs better in cross-domain SV without additional parameters and computational complexity.","url":"https://doi.org/10.3390/app14083471","authors":["Miaomiao Gao","Xiaojuan Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-19T10:53:17Z","doi":"10.3390/app14083471","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1088/0954-898x_5_4_006","name":"The statistics of natural images","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_5_4_006","authors":["Daniel L Ruderman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:07Z","doi":"10.1088/0954-898x_5_4_006","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1080/09548980600774619","name":"Attractor dynamics in a modular network model of neocortex","source":"crossref","abstract":"","url":"https://doi.org/10.1080/09548980600774619","authors":["Mikael Lundqvist","Martin Rehn","Mikael Djurfeldt","Anders Lansner"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-12-08T19:07:18Z","doi":"10.1080/09548980600774619","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1016/b978-0-444-89488-5.50180-9","name":"The Neural Composer: A Network for Musical Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-444-89488-5.50180-9","authors":["B. Freisleben"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-01T06:58:40Z","doi":"10.1016/b978-0-444-89488-5.50180-9","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.5220/0014343200004052","name":"A Novel Graph Neural Network Approach for Social Network Fake News Identification in Arabic","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0014343200004052","authors":["Fériel Ben Fraj","Yathreb Mannai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-13T01:03:07Z","doi":"10.5220/0014343200004052","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1016/b978-0-444-89330-7.50011-9","name":"Storage and Recognition Methods for The Random Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-444-89330-7.50011-9","authors":["Myriam Mokhtari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-06-30T23:02:54Z","doi":"10.1016/b978-0-444-89330-7.50011-9","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1007/978-3-642-83740-1_10","name":"A Hierarchical Neural Network Model for Selective Attention","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-83740-1_10","authors":["Kunihiko Fukushima"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-12-16T22:15:03Z","doi":"10.1007/978-3-642-83740-1_10","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1016/0893-6080(88)90113-x","name":"Bounds on capacity of multi-threshold network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90113-x","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T01:05:53Z","doi":"10.1016/0893-6080(88)90113-x","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.21203/rs.3.rs-37412/v2","name":"The Key Technology of Computer Network Vulnerability Assessment Based on Neural Network","source":"crossref","abstract":"Abstract With the wide application of computer network, network security has attracted more and more attention. The main reason why all kinds of attacks on the network can pose a great threat to the network security is the vulnerability of the computer network system itself. Introducing neural network technology into computer network vulnerability assessment can give full play to the advantages of neural network in network vulnerability assessment. The purpose of this article is by organizing feature map neural network and the combination of multilayer feedforward neural network, the training samples using SOM neural network clustering, the result of clustering are added to the original training samples and set a certain weight, based on the weighted iterative update ceaselessly, in order to improve the convergence speed of BP neural network. On the BP neural network algorithm for LM algorithm was improved, the large matrix inversion in the LM algorithm using the parallel algorithm method is improved for solving system of linear equations, and use of computer network vulnerability assessment as the computer simulation and analysis on the actual example, design a set of computer network vulnerability assessment scheme, finally the vulnerability is lower than 0.75, which is beneficial to research on related theory and application to provide the reference and help.","url":"https://doi.org/10.21203/rs.3.rs-37412/v2","authors":["Shaoqiang Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-11T23:24:52Z","doi":"10.21203/rs.3.rs-37412/v2","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1016/b978-0-12-228640-7.50014-3","name":"Network Analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-12-228640-7.50014-3","authors":["Vincent G. Sigillito","Russell C. Eberhart"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-01T08:02:41Z","doi":"10.1016/b978-0-12-228640-7.50014-3","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.2991/cisia-15.2015.183","name":"A Memristor-Crossbar/CMOS Integrated Network for Pattern Classification and Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.2991/cisia-15.2015.183","authors":["L. Zhang","Z.J Chang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-05-26T10:32:06Z","doi":"10.2991/cisia-15.2015.183","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1002/admt.202400965","name":"Au‐Nanodots Embedded Self‐Rectifying Analog Charge Trap Memristor with Modified Bias Voltage Application Method for Stable Multi‐Bit Hardware‐Based Neural Network","source":"crossref","abstract":"Abstract The self‐rectifying memristor with a bilayer of trap‐rich HfO 2 and insulating Ta 2 O 5 oxide layers is considered one of the most promising candidates for the memristive crossbar array due to its superior switching performance, scalability with 3D stacking, and low operating power. However, the output current variation due to the electron detrapping from trap states can cause the failure of critical operations in neuromorphic applications. This work suggests two solutions to mitigate the switching variations and insufficient data retention time by embedding gold nanodots and modifying the bias voltage application methods for read, write, and erase operations in the crossbar array. The switching mechanism is studied by varying the embedded position of the gold nanodots across the thickness direction of the bilayered oxides, which helped to optimize device performance further. Combining the two solutions into the proposed self‐rectifying memristor enables a single device to have the 7‐possible, stable states by preventing interstate overlap and securing the retention. Consequently, the hardware neural network consisting of self‐rectifying memristors with gold nanodots with the modified bias voltage application methods demonstrates a high inference accuracy of 93.1% in MNIST handwritten digit classification, comparable to the software‐based accuracy of 93.4%, benefiting from the enhanced multi‐state uniformity.","url":"https://doi.org/10.1002/admt.202400965","authors":["Taegyun Park","Jihun Kim","Young Jae Kwon","Han Joon Kim","Seong Pil Yim","Dong Hoon Shin","Yeong Rok Kim","Hae Jin Kim","Cheol Seong Hwang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-13T09:37:42Z","doi":"10.1002/admt.202400965","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1109/tii.2025.3556069","name":"Memristor-Based Feature Recall Neural Network Circuit With Temporal Differentiation of Emotion and its Application in Parts Inspection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tii.2025.3556069","authors":["Junwei Sun","Peilong Gao","Peng Liu","Yanfeng Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-11T14:08:36Z","doi":"10.1109/tii.2025.3556069","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1142/9789812796851_0007","name":"Probabilistic Neural Network Classifier","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789812796851_0007","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-07-18T16:55:18Z","doi":"10.1142/9789812796851_0007","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1007/s11571-023-10025-5","name":"Dynamic analysis of FN–HR neural network coupled of bistable memristor and encryption application based on Fibonacci Q-Matrix","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-023-10025-5","authors":["Junwei Sun","Chuangchuang Li","Yanfeng Wang","Zicheng Wang"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1007/s11571-023-10025-5","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1109/tcad.2025.3567534","name":"Memristor-Based Brain Emotional Learning Neural Network With Attention Mechanism and Its Application","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tcad.2025.3567534","authors":["Quanli Deng","Chunhua Wang","Yichuang Sun","Xu Cong","Hairong Lin","Zekun Deng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-06T13:03:21Z","doi":"10.1109/tcad.2025.3567534","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1088/0954-898x_7_4_007","name":"Topology selection for self-organizing maps","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_7_4_007","authors":["A Utsugi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:32Z","doi":"10.1088/0954-898x_7_4_007","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.23883/ijrter.2017.3384.anwnb","name":"CANCER GENE DETECTION USING ARTIFICIAL NEURAL NETWORK","source":"crossref","abstract":"","url":"https://doi.org/10.23883/ijrter.2017.3384.anwnb","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-08-08T12:46:10Z","doi":"10.23883/ijrter.2017.3384.anwnb","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1080/0954898x.2020.1759833","name":"Modelling monthly mean air temperature using artificial neural network, adaptive neuro-fuzzy inference system and support vector regression methods: A case of study for Turkey","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2020.1759833","authors":["Emre Yakut","Seval Süzülmüş"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-05-13T07:33:03Z","doi":"10.1080/0954898x.2020.1759833","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1080/0954898x.2024.2358950","name":"Deep demosaicking convolution neural network and quantum wavelet transform-based image denoising","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2024.2358950","authors":["Anitha Mary Chinnaiyan","Boyed Wesley Alfred Sylam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-11T06:50:06Z","doi":"10.1080/0954898x.2024.2358950","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1016/b978-0-323-90793-4.00007-6","name":"Memristor-based devices for hardware security applications","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-323-90793-4.00007-6","authors":["Syed Jafar Mustafa","Mohammad Mubashshir Hasan Farooqi","M. Nizamuddin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-21T05:58:49Z","doi":"10.1016/b978-0-323-90793-4.00007-6","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1016/0893-6080(89)90006-3","name":"A new environment for interactive neural network experiments","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(89)90006-3","authors":["Granino A. Korn"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T01:05:53Z","doi":"10.1016/0893-6080(89)90006-3","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1109/ijcnn.2006.246957","name":"Single compartment fire risk analysis using a fuzzy neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.246957","authors":["W. Becker","Xinghuo Yu","Jiyuan Tu","E. Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T11:34:22Z","doi":"10.1109/ijcnn.2006.246957","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1109/iconip.2002.1198196","name":"K-Means Fast Learning Artificial Neural Network, an alternative network for classification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iconip.2002.1198196","authors":["A.T.L. Phuan","S. Prakash"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2004-04-23T14:38:15Z","doi":"10.1109/iconip.2002.1198196","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1145/106965.106969","name":"A neural network for target classification using passive sonar","source":"crossref","abstract":"","url":"https://doi.org/10.1145/106965.106969","authors":["Robert H. Baran","James P. Coughlin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2004-02-05T16:00:56Z","doi":"10.1145/106965.106969","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1088/0954-898x_6_2_006","name":"Autonomous neuromodulatory control of associative processes","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_6_2_006","authors":["Bo Cartling"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:28Z","doi":"10.1088/0954-898x_6_2_006","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1109/icnn.1993.298518","name":"A neural network based edge detector","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnn.1993.298518","authors":["K. Etemad","R. Chelappa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-12-30T17:49:31Z","doi":"10.1109/icnn.1993.298518","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.7551/mitpress/4703.003.0004","name":"Gene Network Models and Neural Development","source":"crossref","abstract":"","url":"https://doi.org/10.7551/mitpress/4703.003.0004","authors":["George Marnellos","Eric D. Mjolsness"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-21T14:47:21Z","doi":"10.7551/mitpress/4703.003.0004","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1109/ijcnn.2018.8489215","name":"Random Projection Neural Network Approximation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2018.8489215","authors":["Peter Andras"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-10-19T22:25:09Z","doi":"10.1109/ijcnn.2018.8489215","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.23919/fusion45008.2020.9190400","name":"Two-Step Surface Damage Detection Scheme using Convolutional Neural Network and Artificial Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.23919/fusion45008.2020.9190400","authors":["Alice Yi Yang","Ling Cheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-10T21:24:07Z","doi":"10.23919/fusion45008.2020.9190400","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.17798/bitlisfen.662816","name":"Classifying Protein Sequences Using Convolutional Neural Network","source":"crossref","abstract":"One of the major challenges in bioinformatics is the classification and identification of protein structure and function. Large amounts of RNA data cannot be managed using traditional laboratory methods. For this, proteins should be separated according to their structure and families. Therefore, proteins need to be classified to define their biological families and functions. In traditional machine learning approaches, various feature extraction algorithms are used to classify proteins. In manual feature extraction, the selected features directly affect performance. Therefore, in the proposed method of this study, protein sequences were digitized by amino acid composition technique. The digitized protein sequences were converted to spectrograms, and automatic feature extraction was performed using 2D CNN models (VGG19, ResNet). The extracted features were classified with SVM and kNN. As a result, the accuracy with 95.03% was achieved in the classification of protein sequences using ResNet.","url":"https://doi.org/10.17798/bitlisfen.662816","authors":["Bihter DAŞ","Suat TORAMAN"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-25T06:51:22Z","doi":"10.17798/bitlisfen.662816","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1016/j.neunet.2015.04.015","name":"Finite-time synchronization for memristor-based neural networks with time-varying delays","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2015.04.015","authors":["Abdujelil Abdurahman","Haijun Jiang","Zhidong Teng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-05-11T17:16:36Z","doi":"10.1016/j.neunet.2015.04.015","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.3109/0954898x.2011.638695","name":"Neurobiological correlates of imaging","source":"crossref","abstract":"","url":"https://doi.org/10.3109/0954898x.2011.638695","authors":["Scott A. Small"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-04-30T12:15:08Z","doi":"10.3109/0954898x.2011.638695","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1007/978-3-319-20505-2_3","name":"Fractional Neural Network Operators Approximation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-20505-2_3","authors":["George A. Anastassiou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-06-23T09:56:55Z","doi":"10.1007/978-3-319-20505-2_3","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1088/0954-898x/6/4/006","name":"Nonlinear Hebbian training of the perceptron","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/6/4/006","authors":["D Bolle","G Shim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-24T22:35:54Z","doi":"10.1088/0954-898x/6/4/006","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1007/978-94-009-0643-3_30","name":"Implementing Semantic Networks in an Electronic Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-94-009-0643-3_30","authors":["Yuzo Hirai","Qing Ma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-12-09T03:06:39Z","doi":"10.1007/978-94-009-0643-3_30","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1016/b978-0-444-89488-5.50179-2","name":"Teaching a Neural Network to Play GO–MOKU","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-444-89488-5.50179-2","authors":["B. Freisleben"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-01T06:58:40Z","doi":"10.1016/b978-0-444-89488-5.50179-2","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1007/978-94-009-0643-3_111","name":"Matrix Computations and Neural Associative Memories","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-94-009-0643-3_111","authors":["Vladimir Cherkassky"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-12-08T22:06:39Z","doi":"10.1007/978-94-009-0643-3_111","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1201/9781439821992-7","name":"Neural Network Learning in a Travel Reservation Domain","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781439821992-7","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-11-19T05:12:42Z","doi":"10.1201/9781439821992-7","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1016/j.bica.2018.07.019","name":"A biological brain-inspired fuzzy neural network: Fuzzy emotional neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.bica.2018.07.019","authors":["Ehsan Zamirpour","Mohammad Mosleh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-08-29T21:26:01Z","doi":"10.1016/j.bica.2018.07.019","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1109/ijcnn.2006.1716655","name":"Content-based Video Adaptation in Low/Variable Bandwidth Communication Networks Using Adaptable Neural Network Structures","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.1716655","authors":["A. Doulamis","G. Tziritas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-30T17:35:23Z","doi":"10.1109/ijcnn.2006.1716655","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1201/9781420015454.ch6","name":"Neural Network Control of Nonstrict Feedback Nonlinear Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781420015454.ch6","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-07-19T15:41:39Z","doi":"10.1201/9781420015454.ch6","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.3109/0954898x.2010.531884","name":"Dynamics of Visual Motion Processing","source":"crossref","abstract":"","url":"https://doi.org/10.3109/0954898x.2010.531884","authors":["Colin Clifford"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-04-30T12:12:02Z","doi":"10.3109/0954898x.2010.531884","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1109/ijcnn.2006.1716605","name":"Neural Network-based Actuator Fault Diagnosis for Attitude Control Subsystem of an Unmanned Space Vehicle","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.1716605","authors":["I.A. AlZyoud","K. Khorasani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-30T12:35:23Z","doi":"10.1109/ijcnn.2006.1716605","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1109/ijcnn.2006.247089","name":"Unsupervised Learning Neural Network for Classification of Ship-Hull Fouling Conditions","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.247089","authors":["Pei-Fang Wang","S. Lieberman","Liyen Ho"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T15:34:22Z","doi":"10.1109/ijcnn.2006.247089","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1088/0954-898x_6_2_009","name":"Stochastic dynamics of reinforcement learning","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_6_2_009","authors":["P C Bressloff"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:47Z","doi":"10.1088/0954-898x_6_2_009","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1007/s11063-020-10249-0","name":"Fixed-Time Lag Synchronization Analysis for Delayed Memristor-Based Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11063-020-10249-0","authors":["Xiahedan Haliding","Haijun Jiang","Abdujelil Abdurahman","Cheng Hu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-05-21T17:02:41Z","doi":"10.1007/s11063-020-10249-0","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.5772/intechopen.85176","name":"Coexistence of Bipolar and Unipolar Memristor Switching Behavior","source":"crossref","abstract":"","url":"https://doi.org/10.5772/intechopen.85176","authors":["Sami Ghedira","Faten Ouaja Rziga","Khaoula Mbarek","Kamel Besbes"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-03T02:25:06Z","doi":"10.5772/intechopen.85176","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.14311/nnw.2017.27.032","name":"A MODIFIED HIGHER-ORDER FEED FORWARD NEURAL NETWORK WITH SMOOTHING REGULARIZATION","source":"crossref","abstract":"","url":"https://doi.org/10.14311/nnw.2017.27.032","authors":["Khidir Shaib Mohamed","Wei Wu","Yan Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-01-17T07:46:25Z","doi":"10.14311/nnw.2017.27.032","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1007/s10291-005-0011-7","name":"Comparing DGPS corrections prediction using neural network, fuzzy neural network, and Kalman filter","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s10291-005-0011-7","authors":["M. R. Mosavi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-09-23T08:35:32Z","doi":"10.1007/s10291-005-0011-7","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1088/0954-898x/8/1/003","name":"Nitric oxide: what can it compute?","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/8/1/003","authors":["B Krekelberg","J Taylor"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/8/1/003","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.345Z"},{"id":"doi:10.1109/neurel.2004.1416527","name":"Control of heating, ventilation and air conditioning system based on neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/neurel.2004.1416527","authors":["Z.M. Durovic","B.D. Kovadevic"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-04-12T10:25:58Z","doi":"10.1109/neurel.2004.1416527","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/ijcnn.2006.1716193","name":"A Neural Network based Technique for Automatic Classification of Road Cracks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.1716193","authors":["J. Bray","B. Verma","Xue Li","W. He"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-30T17:35:23Z","doi":"10.1109/ijcnn.2006.1716193","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/tbcas.2022.3216112","name":"Memristor Neural Network Circuit Based on Operant Conditioning With Immediacy and Satiety.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tbcas.2022.3216112","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.1109/tbcas.2022.3216112","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.3390/mi10060384","name":"Memristor Neural Network Training with Clock Synchronous Neuromorphic System.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/mi10060384","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2019","doi":"10.3390/mi10060384","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1016/j.neunet.2026.109297","name":"Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.109297","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.109297","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.neunet.2026.109337","name":"Predefined-time synchronization of memristor-based competitive neural networks with time-varying delays and application in image encryption.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.109337","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.109337","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.neunet.2026.109104","name":"Memristor-based reconfigurable architecture for binarized neural networks: Implementation and robustness analysis.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.109104","authors":["Xiaoyang Liu","Xu Xie","Banghu Yin","Rusheng Ju"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.109104","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1007/s11571-026-10479-3","name":"Memristor-based neuromorphic circuit for visual emotional non-associative learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-026-10479-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s11571-026-10479-3","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1007/s11571-026-10448-w","name":"Ternary quantitative neural network implemented with tri-valued memristors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-026-10448-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s11571-026-10448-w","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.neunet.2026.108953","name":"A discrete memristive cyclic Hopfield neural network with multi-cavity-like attractors and application in secure communication.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.108953","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.108953","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.21203/rs.3.rs-10466288/v1","name":"Optimized Dual Temporal Gated Multi-Graph Convolution Network for Land Use and Land Cover Classification Incorporating Temporal Feature Tracking and High Resolution Satellite Imagery Analysis","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-10466288/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.21203/rs.3.rs-10466288/v1","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.1016/j.neunet.2026.109097","name":"A bio-inspired neuromorphic system for fusing visual features and autonomous learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.109097","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.109097","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/adma.73462","name":"Light-Modulated Xylan-Reinforced Nanofluidic Memristor for Ionic Neural Network-Based Robot Movement Modulation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.73462","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.73462","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.neunet.2026.109326","name":"Dynamical behavior and applications of fractional-order bicyclic crossed memristive neural networks with Neimark-Sacker bifurcation: Synchronization and image encryption.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.109326","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.109326","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/smtd.70740","name":"Solution-Processed Submicron-Channel Organic Ferroelectric Memristors with a Low Operation Voltage of 1 V.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smtd.70740","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smtd.70740","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1007/s11571-026-10432-4","name":"Coexistence of infinitely many attractors in cosine-type memristor-driven hopfield neural networks and its application to image encryption.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-026-10432-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s11571-026-10432-4","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1038/s41598-026-55199-0","name":"Physics-informed neural networks with caputo-fabrizio derivatives for nonlinear fractal-fractional delay equations and chaotic systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-55199-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-55199-0","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.neunet.2026.108837","name":"Memristor-based neural network for dual-channel and temporal order memory with application in fault detection.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.108837","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.108837","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/tcyb.2026.3699736","name":"Memristor-Based FBM Circuit of Collaboration Among Multiple Brain Regions and Its Application in Rescue Robot.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tcyb.2026.3699736","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1109/tcyb.2026.3699736","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.neunet.2026.108887","name":"Discrete bidirectional memristive neural network-based hyperchaotic system and its FPGA implementation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.108887","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.108887","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/adma.74781","name":"Atomically Precise Ag&lt;sub&gt;11&lt;/sub&gt; and Ag&lt;sub&gt;12&lt;/sub&gt; Nanocluster-Assembled 2D Materials for Memristive and Neuromorphic Functionality.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.74781","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.74781","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.3390/e28070753","name":"A Low-Complexity 4D Discrete Chaotic System for Secure Image Encryption Based on Reversible Neural Network.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/e28070753","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/e28070753","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1007/s11571-026-10431-5","name":"Modular memristor circuits for Pavlov associative memory with scalability.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-026-10431-5","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s11571-026-10431-5","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acsenergylett.6c00713","name":"Dynamical Symbiosis of Solar Cell and Memristor.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsenergylett.6c00713","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsenergylett.6c00713","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.jcis.2026.141016","name":"Synergistic defect-interface-photocarrier modulation based on IGZO/HfO&lt;sub&gt;2&lt;/sub&gt; heterojunction memristors for neuromorphic visual processing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.jcis.2026.141016","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.jcis.2026.141016","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.neunet.2025.108291","name":"A novel memristor-based bionic neural network circuit with crossmodal integration and forgetting effects.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.108291","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2025.108291","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.neunet.2025.108340","name":"Discrete Memristive Hopfield Neural Network with Grid-Polyhedral Hyperchaos for FPGA-Based Pseudorandom Number Generator.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.108340","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2025.108340","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/smll.75437","name":"Interface Engineered Perovskite-Oxide Heterojunction All-Photonic Synapses for Multibit Memory, Optical Logic, and Wearable Neuromorphic Vision.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/smll.75437","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/smll.75437","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/tcyb.2025.3607140","name":"Universal Method for Enhancing Dynamics in Neural Networks via Memristor and Application in IoT-Based Robot Navigation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tcyb.2025.3607140","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1109/tcyb.2025.3607140","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1007/s11571-026-10451-1","name":"Exploring electromagnetic induction and astrocyte influence in excitatory-inhibitory coupling neuron network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-026-10451-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s11571-026-10451-1","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.neunet.2026.108547","name":"A memristive fuzzy neural network with applications to classification task: A programmable circuit system.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.108547","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2026.108547","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/adma.202517859","name":"Mechanically Gated Vertical Ion Channels for Fast Strain-Sensitive Neuromorphic Memristor.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202517859","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202517859","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/tcyb.2026.3664460","name":"Reconfigurable Multiscroll Memristive Neural Network With Application to Telemedicine Privacy Protection.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tcyb.2026.3664460","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1109/tcyb.2026.3664460","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acs.nanolett.5c05639","name":"SnNb&lt;sub&gt;2&lt;/sub&gt;O&lt;sub&gt;6&lt;/sub&gt;-Based Capacitive Memristive Synapses with Intrinsic LIF Dynamics for Neuromorphic Epilepsy Detection.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.5c05639","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acs.nanolett.5c05639","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.isci.2026.114642","name":"Efficient next-generation reservoir computing: An analog in-memory implementation using memristor crossbar arrays.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.isci.2026.114642","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.isci.2026.114642","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acsami.6c03660","name":"Low-Voltage Resistive Switching and Synaptic Plasticity in Cs2AgBiBr6 Memristors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.6c03660","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.6c03660","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.neunet.2025.108285","name":"A general approach to multistability analysis for fuzzy multidimensional-valued NNs with memristor.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.108285","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2025.108285","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.20944/preprints202603.1727.v1","name":"Exploiting Static Conductance and Dynamic Switching of Memristors for Artificial Intelligence Applications","source":"europepmc","abstract":"","url":"https://doi.org/10.20944/preprints202603.1727.v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.20944/preprints202603.1727.v1","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.1021/acsami.6c00756","name":"Heterogeneous 3D Integration Based on Atomic-Level Electronics.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.6c00756","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsami.6c00756","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1039/d5mh02154e","name":"Memristive behavior of a V&lt;sub&gt;2&lt;/sub&gt;C MXene/PANI:PSS composite and its applications in ammonia detection.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d5mh02154e","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1039/d5mh02154e","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.neunet.2025.108266","name":"Unified analysis of stability and dissipativity for inertial memristive multidimensional-valued neural networks with time-varying delays via non-reduced order method.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.108266","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1016/j.neunet.2025.108266","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/adma.202516342","name":"A Pupillary Light Reflex Inspired Self-Adaptive Spiking Visual Neuron.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202516342","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202516342","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1007/s00422-026-01036-6","name":"The active role of non-synaptic electromagnetic induction in modulating absence epilepsy: a kinetic modeling study.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s00422-026-01036-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1007/s00422-026-01036-6","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/adma.73440","name":"Stable Analog Weight Programming in Single-Crystalline van der Waals Ferroelectric Transistors for Reliable Computing-in-Memory.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.73440","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.73440","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/adma.202516115","name":"Robust Metal and Semiconductor Phase Transition Memristor Using Ag-Intercalated Transition Metal Dichalcogenide.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202516115","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202516115","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1186/s40580-026-00552-2","name":"Advances in neuroprostheses: interfaces, materials, and applications.","source":"europepmc","abstract":"Neuroprostheses have become a pivotal technology for restoring sensory, motor, and cognitive functions, offering transformative therapeutic strategies for neurological disorders by bridging or bypassing damaged neural pathways through electronic systems. However, achieving long-term stability and high-fidelity interaction between biological and electronic systems remains a significant challenge due to the mismatch at the neural interface. This review examines the critical role of nanotechnology in building high performance neuroprostheses across six key classes: motor, visual, tactile, language, memory and olfactory. A system architecture of the neuroprostheses is proposed that highlights two critical interfaces, namely, \"neural-electronic\" and \"environment-electronic\" interfaces. We survey recent advances in materials and devices that shape better neural electrodes and novel sensors, and discuss the potential utilization of neuromorphic computing for efficient edge processing in neuroprostheses. This review aims to outline future trajectories toward high-throughput bidirectional interaction, biomimetic encoding, and adaptive closed-loop systems, aspiring to achieve seamless integration between electronic systems and biological neural circuitry.","url":"https://doi.org/10.1186/s40580-026-00552-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1186/s40580-026-00552-2","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.21203/rs.3.rs-4875279/v1","name":"Unified Ferroelectric/Memristive Memory for Neural Network Inference and Training","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4875279/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4875279/v1","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.32388/yhpftt","name":"Quantization of Nonlinear Transmission Line Dynamics With Noise: Some Remarks on Noise in Quantum Field and Quantum Neural Network Theories","source":"europepmc","abstract":"","url":"https://doi.org/10.32388/yhpftt","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.32388/yhpftt","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.22541/au.171836004.44823963/v1","name":"Memristor Crossbar Scaling Limits and the Implementation of a Large Neural Network Using 3D Stacked Crossbars","source":"europepmc","abstract":"","url":"https://doi.org/10.22541/au.171836004.44823963/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.22541/au.171836004.44823963/v1","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.21203/rs.3.rs-5168542/v1","name":"A Neuronal Circuit Based on a Second-Order Memristor","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-5168542/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-5168542/v1","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.21203/rs.3.rs-5310485/v1","name":"Influence of Memristive Activated Gradient on Chaotic Dynamics In Discrete Neural Networks","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-5310485/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-5310485/v1","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.21203/rs.3.rs-3908984/v1","name":"Clinically Validated Classification of Chronic WoundsMethod with Memristor-Based Cellular Neural Network","source":"europepmc","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3908984/v1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-3908984/v1","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.21203/rs.3.rs-3404393/v1","name":"Memristor Crossbar Scaling Limits and the Implementation of Large Neural Networks","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3404393/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-3404393/v1","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.21203/rs.3.rs-4022926/v1","name":"Global Dissipative Examination of Delayed Memristive Inertial Neural Networks with Uncertain Parameters","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4022926/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4022926/v1","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.21203/rs.3.rs-3186801/v1","name":"Dynamics analysis and image encryption application of Hopfield neural network with a novel multistable and highly tunable memeristor","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3186801/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-3186801/v1","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.22541/au.170709088.85277279/v1","name":"BITLITE: Light Bit-wise Operative Vector Matrix Multiplication for Low-Resolution Platforms","source":"preprints","abstract":"","url":"https://doi.org/10.22541/au.170709088.85277279/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.22541/au.170709088.85277279/v1","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.21203/rs.3.rs-3546552/v1","name":"SAFMem: Accelerating Transformer Self-Attention Functionality via Memristor-Based Hardware","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3546552/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-3546552/v1","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.21203/rs.3.rs-4505525/v1","name":"Nonlinear Memristive Computational Spectrometer","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-4505525/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.21203/rs.3.rs-4505525/v1","addedAt":"2026-09-01T01:48:32.345Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.21203/rs.3.rs-3192094/v1","name":"Electrical activity and synchronization of HR-tabu neuron network coupled by Chua corsage memristor","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3192094/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-3192094/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.21203/rs.3.rs-2858774/v1","name":"An Efficient Full-Size Convolutional Computing Method Based on Memristor Crossbar","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-2858774/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-2858774/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.21203/rs.3.rs-3123961/v1","name":"Stability of coupled memristive reaction-diffusion neural networks with time-varying delay","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-3123961/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-3123961/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.20944/preprints202305.2195.v1","name":"A Novel Programming Circuit for Memristors","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202305.2195.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.20944/preprints202305.2195.v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.21203/rs.3.rs-2458251/v1","name":"Bringing uncertainty quantification to the extreme-edge with memristor-based Bayesian neural networks","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-2458251/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-2458251/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.20944/preprints202312.2330.v1","name":"Exploring Entropy-Based Classification of Time Series Using Visibility Graphs from Chaotic Maps","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202312.2330.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.20944/preprints202312.2330.v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.22541/au.166135864.41433544/v1","name":"Design of a dynamic S-box with chaotic neural network based on LiNbO3 memristor","source":"preprints","abstract":"","url":"https://doi.org/10.22541/au.166135864.41433544/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.22541/au.166135864.41433544/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.21203/rs.3.rs-1769222/v1","name":"Long-term and Short-term Memory Networks Based on Forgetting Memristors","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-1769222/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.21203/rs.3.rs-1769222/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.21203/rs.3.rs-1931386/v1","name":"Global Mittag-Leffler stability and synchronization control of fractional-order memristor-based neural networks with proportional delays","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-1931386/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.21203/rs.3.rs-1931386/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.21203/rs.3.rs-1782553/v1","name":"An improved fixed-time stabilization problem of delayed coupled memristor-based neural networks with pinning control and indefinite derivative approach","source":"preprints","abstract":"Abstract In this brief, we propose a generalized memristor-based neural networks with nonlinear coupling. Based on the set-valued mapping theory, novel Lyapunov indefinite derivative and Memristor theory, the coulped memristor-based neural networks(CMNNs) can achieve fixed-time stabilization(FTS) by designing a proper pinning controller, which randomly control a few neuron nodes of system. Different from the traditional Lyapunov method, this paper uses the implementation method of indefinite derivative to deal with the non-autonomous neural network system with nonlinear coupling topology between different neurons. The system can obtain synchronization in a fixed time and requires fewer conditions. Moreover, the fixed stable setting time estimation of the system is given through a few conditions, which can eliminate the dependence on the initial value. Finally, we give two numerical examples to verify the correctness of our results.","url":"https://doi.org/10.21203/rs.3.rs-1782553/v1","authors":["Chao Yang","Yicheng Liu","Lihong Huang","Le Li"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.21203/rs.3.rs-1782553/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.22541/au.167727732.20256861/v1","name":"HESSPROP: Mitigating Memristive DNN Weight Mapping Errors with Hessian Backpropagation","source":"preprints","abstract":"","url":"https://doi.org/10.22541/au.167727732.20256861/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.22541/au.167727732.20256861/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.20944/preprints202305.0661.v1","name":"Red-Ox Front Propagation in Polyaniline-Polymer Electrolyte System as a Basis for Spiking and Rate-Based Neural Networks and Multibit ReRAM","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints202305.0661.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.20944/preprints202305.0661.v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.21203/rs.3.rs-1939455/v1","name":"Thousands of conductance levels in memristors monolithically integrated on CMOS","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-1939455/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.21203/rs.3.rs-1939455/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.22541/au.167543650.04886551/v1","name":"SEVDA: Singular Value Decomposition Based Parallel Write Scheme for Memristive CNN Accelerators","source":"preprints","abstract":"","url":"https://doi.org/10.22541/au.167543650.04886551/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.22541/au.167543650.04886551/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.21203/rs.3.rs-973554/v1","name":"Stability Analysis of  Fractional Order Memristor Synapse-coupled Hopfield Neural Network with Ring Structure","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-973554/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.21203/rs.3.rs-973554/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.21203/rs.3.rs-1281602/v1","name":"Firing Mechanism Based on Single Memristive Neuron and Double Memristive Coupled Neurons","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-1281602/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.21203/rs.3.rs-1281602/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.21203/rs.3.rs-2649834/v1","name":"Multi-filamentary switching of Cu/SiOx memristive devices with a Ge-implanted a-Si under-layer for analog synaptic devices","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-2649834/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.21203/rs.3.rs-2649834/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.21203/rs.3.rs-1821052/v1","name":"Experimentally realized memristive memory augmented neural network","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-1821052/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.21203/rs.3.rs-1821052/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.21203/rs.3.rs-722277/v1","name":"Memristive Electromagnetic Induction Effects on Hopfield Neural Network","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-722277/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.21203/rs.3.rs-722277/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.21203/rs.3.rs-1322588/v1","name":"A Neural Network Accelerator to Avoid Inference Inaccuracy","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-1322588/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.21203/rs.3.rs-1322588/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.21203/rs.3.rs-950992/v1","name":"A Dynamic AES Encryption Based on Memristive Chaos Neural Network","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-950992/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.21203/rs.3.rs-950992/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.21203/rs.3.rs-43977/v1","name":"Hybrid memristor-CMOS neurons for in situ learning in fully hardware memristive spiking neural networks","source":"preprints","abstract":"Abstract Spiking neural network, consisting of spiking neurons and plastic synapses, is a promising but relatively underdeveloped neural network for neuromorphic computing. Inspired by the human brain, it provides a unique solution for highly efficient data processing. Recently, memristor-based neurons and synapses are becoming intriguing candidates to build spiking neural networks in hardware, owing to the close resemblance between their device dynamics and the biological counterparts. However, the functionalities of memristor-based neurons are currently very limited, and a hardware demonstration of fully memristor-based spiking neural networks supporting in situ learning is very challenging. Here, a hybrid spiking neuron by combining the memristor with simple digital circuits is designed and implemented in hardware to enhance the neuron functions. The hybrid neuron with memristive dynamics not only realizes the basic leaky integrate-and-fire neuron function but also enables the in situ tuning of the connected synaptic weights. Finally, a fully hardware spiking neural network with the hybrid neurons and memristive synapses is experimentally demonstrated for the first time, with which in situ Hebbian learning is achieved. This work opens up a way towards the implementation of spiking neurons, supporting in situ learning for future neuromorphic computing systems.","url":"https://doi.org/10.21203/rs.3.rs-43977/v1","authors":["Xumeng Zhang","Jian Lu","Rui Wang","Jinsong Wei","Tuo Shi","Chunmeng Dou","zuheng Wu","Dashan Shang","Guozhong Xing","Qi Liu","Ming Liu"],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2020","doi":"10.21203/rs.3.rs-43977/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.21203/rs.3.rs-1196768/v1","name":"Hardware Acceleration of Bayesian Network based on Two-dimensional Memtransistors","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-1196768/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.21203/rs.3.rs-1196768/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.21203/rs.3.rs-1507544/v1","name":"In-sensor image memorization and encoding via optical neurons for bio-stimulus domain reduction towards visual cognitive processing","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-1507544/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.21203/rs.3.rs-1507544/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.21203/rs.3.rs-990982/v1","name":"A Spiking Visual Neuron for Depth Perceptual Systems","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-990982/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2021","doi":"10.21203/rs.3.rs-990982/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.21203/rs.3.rs-1328791/v1","name":"Reconfigurable Compute-In-Memory on Field-Programmable Ferroelectric Diodes","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-1328791/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.21203/rs.3.rs-1328791/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.21203/rs.3.rs-40717/v1","name":"Dynamic Memristor-based Reservoir Computing for High-Efficiency Spatiotemporal Signal Processing","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-40717/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2020","doi":"10.21203/rs.3.rs-40717/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.20944/preprints201901.0319.v1","name":"A Memristor-Based Cascaded Neural Networks for Specific Target Recognition","source":"preprints","abstract":"","url":"https://doi.org/10.20944/preprints201901.0319.v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2019","doi":"10.20944/preprints201901.0319.v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.1101/2024.09.26.615172","name":"Lumen charge governs gated ion transport in β-barrel nanopores","source":"preprints","abstract":"","url":"https://doi.org/10.1101/2024.09.26.615172","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1101/2024.09.26.615172","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.21203/rs.3.rs-1414520/v1","name":"A Study of a Fractional-order Model of Coronavius Disease 2019(COVID-19) after Mass Caccination","source":"preprints","abstract":"","url":"https://doi.org/10.21203/rs.3.rs-1414520/v1","authors":[],"tags":[],"confidence":0.74,"sites":["neuromorphic"],"publishedDate":"2022","doi":"10.21203/rs.3.rs-1414520/v1","addedAt":"2026-09-01T01:48:32.346Z","updatedAt":"2026-09-01T01:48:33.594Z"},{"id":"doi:10.1109/ijcnn.2006.1716408","name":"Boosted Modified Probabilistic Neural Network (BMPNN) for Network Intrusion Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.1716408","authors":["Tich Phuoc Tran","T. Jan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-30T12:35:23Z","doi":"10.1109/ijcnn.2006.1716408","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1016/j.neunet.2018.10.004","name":"Passivity analysis of delayed reaction–diffusion memristor-based neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2018.10.004","authors":["Yanyi Cao","Yuting Cao","Shiping Wen","Tingwen Huang","Zhigang Zeng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-10-29T03:25:49Z","doi":"10.1016/j.neunet.2018.10.004","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1088/0954-898x/6/4/007","name":"Neural modelling of psychiatric disorders","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/6/4/007","authors":["Eytan Ruppin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/6/4/007","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.2514/6.2024-85984","name":"Predicting Low Velocity Impact Damage of Laminated Composites using Artificial Neural Network Machine Learning Models","source":"crossref","abstract":"","url":"https://doi.org/10.2514/6.2024-85984","authors":["Andrew Kovac","Kwek Tan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-06T13:13:41Z","doi":"10.2514/6.2024-85984","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1088/0954-898x_4_3_003","name":"Propagation of excitation in neural network models","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_4_3_003","authors":["M A P Idiart","L F Abbott"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T16:04:09Z","doi":"10.1088/0954-898x_4_3_003","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1016/0893-6080(88)90183-9","name":"A neural network for the optimization of communications network design","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90183-9","authors":["G. Vichniac","M.(Gard.ner) Lepp","M. Steenstrup"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T01:05:53Z","doi":"10.1016/0893-6080(88)90183-9","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1088/0954-898x_6_1_003","name":"Synchronization in an oscillator neural network model with time-delayed coupling","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_6_1_003","authors":["T B Luzyanina"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:26Z","doi":"10.1088/0954-898x_6_1_003","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1109/mocast61810.2024.10615437","name":"A Simple Memristor Model for Memory Devices","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mocast61810.2024.10615437","authors":["Stoyan Kirilov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-06T17:25:21Z","doi":"10.1109/mocast61810.2024.10615437","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1002/rnc.7112","name":"Unified synchronization and fault‐tolerant anti‐disturbance control for synchronization of multiple memristor‐based neural networks","source":"crossref","abstract":"Summary This work primarily concentrates on the design of fault‐tolerant anti‐disturbance control for synchronization of multiple memristor‐based neural networks subject to time delay, matched and mismatched disturbances. Moreover, in the addressed network model, we consider parameter uncertainties and actuator faults. Firstly in order to estimate the matched disturbances generated by the exogenous system, a disturbance observer is devised. Whereas, the mismatched part is tackled by employing the mixed and passivity performance indexes. Subsequently, a unified controller is designed by incorporating error feedback control and the disturbance estimate. Further, with the assistance of Lyapunov stability theory and linear matrix inequality technique, an adequate criteria is procured to ascertain the required synchronization criteria for the assayed network model with the mixed and passivity performance indexes. Following this, by basing on the established conditions, the explicit form of the controller and observer gain matrices is obtained. In the end, a numerical example with simulation results is shown to confirm the potential and usefulness of the conclusions acquired from the theoretical analysis.","url":"https://doi.org/10.1002/rnc.7112","authors":["T. Satheesh","R. Sakthivel","N. Aravinth","H.R. Karimi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-28T02:06:53Z","doi":"10.1002/rnc.7112","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1007/978-981-97-4399-5_34","name":"Circuit Implementation of Fixed-Time Zeroing Neural Network for Time-Varying Equality Constrained Quadratic Programming","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-4399-5_34","authors":["Ruiqi Zhou","Xingxing Ju","Hangjun Che","Qian Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-06T16:01:52Z","doi":"10.1007/978-981-97-4399-5_34","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1007/978-3-031-72344-5_15","name":"Virtual Nodes based Heterogeneous Graph Convolutional Neural Network for Efficient Long-Range Information Aggregation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-72344-5_15","authors":["Ranhui Yan","Jia Cai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-16T14:03:01Z","doi":"10.1007/978-3-031-72344-5_15","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/nanoarch.2017.8053706","name":"SkyNet: Memristor-based 3D IC for artificial neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nanoarch.2017.8053706","authors":["Sachin Bhat","Sourabh Kulkarni","Jiajun Shi","Mingyu Li","Csaba Andras Moritz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-10-02T20:24:16Z","doi":"10.1109/nanoarch.2017.8053706","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1142/s0218127413500521","name":"MEMRISTOR MODELS IN A CHAOTIC NEURAL CIRCUIT","source":"crossref","abstract":"The peculiar features of the memristor, a fundamental passive two-terminal element characterized by a nonlinear relationship between charge and flux, promise to revolutionize integrated circuit design in the next few decades. Besides its most popular potential application, ultra-dense nonvolatile memories, much research has been lately devoted to their use in chaotic neural networks for the emulation of brain activity. In the studies on neuromorphic circuits, it is common to characterize each memristor with a theoretical model based upon a single-valued odd-symmetric charge-flux nonlinearity. Memristive nano-films exhibit different dynamics depending on the way they behave at boundaries. We recently developed a mathematical model, applicable to memristive nano-structures of various nature, offering the opportunity to tune the boundary conditions so as to capture a wide gamut of distinct nonlinear behaviors. However, in general the proposed model exhibits a multivalued charge-flux nonlinearity dependent on input and initial state condition. In this paper, we first derive the necessary and sufficient set of boundary conditions under which single-valuedness is observed in this nonlinearity for any input/state initial condition combination. Then, after proving that, under such boundary conditions, the asymmetrical nonlinearities of memristors with opposite orientation are the odd-symmetric function of the other, we devise a pair of suitable memristor arrangements with odd-symmetric charge-flux characteristics. This analysis is confirmed by showing how a chaotic neural circuit employing one of such arrangements behaves similarly to its counterpart with the theoretically-modeled memristor.","url":"https://doi.org/10.1142/s0218127413500521","authors":["ALON ASCOLI","FERNANDO CORINTO"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-04-16T05:59:58Z","doi":"10.1142/s0218127413500521","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1109/ijcnn.2011.6033651","name":"Analysis of a memristor based 1T1M crossbar architecture","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2011.6033651","authors":["Chris Yakopcic","Tarek M. Taha","Guru Subramanyam","Robinson E. Pino","Stanley Rogers"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-10-06T17:24:17Z","doi":"10.1109/ijcnn.2011.6033651","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1007/978-3-031-72359-9_1","name":"Combinatorial Library Neural Network (CoLiNN) for Combinatorial Library Visualization Without Compound Enumeration","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-72359-9_1","authors":["Regina Pikalyova","Tagir Akhmetshin","Dragos Horvath","Alexandre Varnek"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-18T12:28:54Z","doi":"10.1007/978-3-031-72359-9_1","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/icecs46596.2019.8964918","name":"A Continuous-time Learning Rule for Memristor–based Recurrent Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icecs46596.2019.8964918","authors":["Gianluca Zoppo","Francesco Marrone","Fernando Corinto"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-23T22:15:31Z","doi":"10.1109/icecs46596.2019.8964918","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1088/0954-898x/15/3/003","name":"Neural network model to generate head swing in locomotion of Caenorhabditis elegans","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/15/3/003","authors":["Kazumi Sakata","Ryuzo Shingai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2004-06-24T03:14:10Z","doi":"10.1088/0954-898x/15/3/003","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1088/0954-898x_2_4_005","name":"Neural network models of list learning","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_2_4_005","authors":["Neil Burgess","J L Shapiro","M A Moore"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T16:04:00Z","doi":"10.1088/0954-898x_2_4_005","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1007/s11063-024-11466-7","name":"A Prototype-Based Neural Network for Image Anomaly Detection and Localization","source":"crossref","abstract":"Abstract Image anomaly detection and localization perform not only image-level anomaly classification but also locate pixel-level anomaly regions. Recently, it has received much research attention due to its wide application in various fields. This paper proposes ProtoAD, a prototype-based neural network for image anomaly detection and localization. First, the patch features of normal images are extracted by a deep network pre-trained on nature images. Then, the prototypes of the normal patch features are learned by non-parametric clustering. Finally, we construct an image anomaly localization network (ProtoAD) by appending the feature extraction network with L 2 feature normalization, a $$1\\times 1$$ 1 × 1 convolutional layer, a channel max-pooling, and a subtraction operation. We use the prototypes as the kernels of the $$1\\times 1$$ 1 × 1 convolutional layer; therefore, our neural network does not need a training phase and can conduct anomaly detection and localization in an end-to-end manner. Extensive experiments on two challenging industrial anomaly detection datasets, MVTec AD and BTAD, demonstrate that ProtoAD achieves competitive performance compared to the state-of-the-art methods with a higher inference speed. The code and pre-trained models are publicly available at https://github.com/98chao/ProtoAD .","url":"https://doi.org/10.1007/s11063-024-11466-7","authors":["Chao Huang","Zhao Kang","Hong Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-08T14:02:17Z","doi":"10.1007/s11063-024-11466-7","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.38007/nn.2021.020403","name":"A Bank Credit Risk Model Integrating Artificial Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2021.020403","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T18:12:48Z","doi":"10.38007/nn.2021.020403","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1016/0893-6080(88)90495-9","name":"An application of a multiple neural network system with modifiable network topology (GENSEP) to online character recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90495-9","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T01:05:53Z","doi":"10.1016/0893-6080(88)90495-9","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1016/0893-6080(88)90462-5","name":"Neural network machine vision","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90462-5","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T01:05:53Z","doi":"10.1016/0893-6080(88)90462-5","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1109/ijcnn60899.2024.10649923","name":"A Lightweight Convolutional Neural Network for Personalized Blood Pressure Estimation Based on Photoplethysmography","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn60899.2024.10649923","authors":["Jin Zhao","Qi Zhang","Caijie Qin","Tao Lu","Zhaoyi Ning","Qiang Guan","Xibo Ma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T17:35:05Z","doi":"10.1109/ijcnn60899.2024.10649923","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1007/s00521-024-09527-y","name":"A 3D-convolutional-autoencoder embedded Siamese-attention-network for classification of hyperspectral images","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-024-09527-y","authors":["Pallavi Ranjan","Rajeev Kumar","Ashish Girdhar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-20T09:03:54Z","doi":"10.1007/s00521-024-09527-y","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1016/j.neunet.2024.106285","name":"A novel interactive deep cascade spectral graph convolutional network with multi-relational graphs for disease prediction","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106285","authors":["Sihui Li","Rui Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-01T15:21:46Z","doi":"10.1016/j.neunet.2024.106285","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.38007/nn.2022.030303","name":"Print Character Recognition Method Based on Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2022.030303","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T18:14:38Z","doi":"10.38007/nn.2022.030303","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1016/b978-0-44-329202-6.00007-9","name":"Neural network algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-44-329202-6.00007-9","authors":["Chao Huang","Hailong Huang","Yiying Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-31T19:14:30Z","doi":"10.1016/b978-0-44-329202-6.00007-9","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1007/s00521-023-09165-w","name":"Breast lesion classification from mammograms using deep neural network and test-time augmentation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-023-09165-w","authors":["Parita Oza","Paawan Sharma","Samir Patel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-20T14:01:45Z","doi":"10.1007/s00521-023-09165-w","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1007/s10994-024-06516-z","name":"Neural network relief: a pruning algorithm based on neural activity","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s10994-024-06516-z","authors":["Aleksandr Dekhovich","David M. J. Tax","Marcel H. F. Sluiter","Miguel A. Bessa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-05T17:02:04Z","doi":"10.1007/s10994-024-06516-z","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1088/0954-898x/6/1/001","name":"Local dynamic interactions in the collicular motor map: a neural network model","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/6/1/001","authors":["Lina Massone","Tony Khoshaba"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/6/1/001","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.38007/nn.2021.020207","name":"Convolutional Neural Network in Face Recognition in Online Classroom","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2021.020207","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T05:28:48Z","doi":"10.38007/nn.2021.020207","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1007/s00521-024-10134-0","name":"EGANet: Elevation-guided attention network for scene classification in panchromatic remote sensing images","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-024-10134-0","authors":["Rajeshreddy Datla","G. Swetha","C. Gayathri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-24T17:02:17Z","doi":"10.1007/s00521-024-10134-0","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/ijcnn60899.2024.10649975","name":"SleepCVT: Combination of Convolution Neural Network and Vision Transformer for Automatic Sleep Scoring","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn60899.2024.10649975","authors":["Chih-En Kuo","Hao-Hsiang Wang","Tsung-Hua Lu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T17:35:05Z","doi":"10.1109/ijcnn60899.2024.10649975","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1016/j.neunet.2024.106555","name":"Dual-stage feedback network for lightweight color image compression artifact reduction","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106555","authors":["Zhengxin Chen","Xiaohai He","Tingrong Zhang","Shuhua Xiong","Chao Ren"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-22T23:23:35Z","doi":"10.1016/j.neunet.2024.106555","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1117/12.3049595","name":"A heterogeneous graph neural network model with multi-head attention integrating review information for recommendation","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3049595","authors":["Chenyun Li","Guanhong Zhang","Odbal H"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-08T16:11:55Z","doi":"10.1117/12.3049595","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1007/s00521-024-10321-z","name":"AI for industrial: automate the network design for 5G URLLC services","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-024-10321-z","authors":["Jiao Wang","Jay Weitzen","Oguz Bayat","Volkan Sevindik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T17:02:27Z","doi":"10.1007/s00521-024-10321-z","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/ijcnn60899.2024.10650488","name":"Graph Self-Attention Residual Connection Neural Network for Session-Based Recommendation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn60899.2024.10650488","authors":["Senpeng Chen","Huan Li","Wenhong Wei","Ani Dong","Jie Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T17:35:05Z","doi":"10.1109/ijcnn60899.2024.10650488","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1007/s10791-026-10260-4","name":"Network intrusion anomaly detection based on BAS-SSAE and CNN-BiGRU-attention fusion model","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s10791-026-10260-4","authors":["Nan Li","Yu Wang","Haibo Zhang","Zhiqiang Li","Weina Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-24T12:11:35Z","doi":"10.1007/s10791-026-10260-4","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.38007/nn.2022.030401","name":"Neural Network Classifier Improvements Based on Ant Colony Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2022.030401","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T06:22:51Z","doi":"10.38007/nn.2022.030401","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1007/978-94-009-0643-3_39","name":"Artificial Neural Network on a Massively Parallel Associative Architecture","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-94-009-0643-3_39","authors":["A. Krikelis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-12-08T22:06:39Z","doi":"10.1007/978-94-009-0643-3_39","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.2172/2427319","name":"Impact of Oxidation Layer in the Resistive Switching Behavior of Nitride-Based Memristor Devices","source":"crossref","abstract":"","url":"https://doi.org/10.2172/2427319","authors":["Di Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-10T02:16:44Z","doi":"10.2172/2427319","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1016/j.neucom.2017.10.003","name":"Finite-time stability for memristor based switched neural networks with time-varying delays via average dwell time approach","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2017.10.003","authors":["M. Syed Ali","S. Saravanan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-10-12T12:51:33Z","doi":"10.1016/j.neucom.2017.10.003","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.4018/979-8-3693-2073-0.ch009","name":"Neural Network and Neural Computing","source":"crossref","abstract":"Deep learning, a subset of AI, has gained popularity in various fields, including computer vision and NLP. It is based on artificial neural networks, which process multiple layers of data and extract high-level features automatically. Unlike traditional ML algorithms, deep learning can process large unstructured data and complex algorithms better than traditional methods. The human brain inspires neural networks, which contain artificial neurons similar to biological neurons. These networks are made up of three layers: input, hidden, and output. Deep learning maps inputs to outputs and finds correlations, making it a “universal approximator.” It can be combined with other AI methods to perform more complex tasks, such as deep reinforcement learning. Top companies using ANN include Nvidia Corp., Alphabet, Salesforce.com, Amazon.com, Microsoft Corp., Twilio, IBM, and Facebook. Deep learning uses ANN to analyze data and make predictions and has found applications in almost every business sector.","url":"https://doi.org/10.4018/979-8-3693-2073-0.ch009","authors":["Partha Ghosh","Suradhuni Ghosh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-15T14:46:13Z","doi":"10.4018/979-8-3693-2073-0.ch009","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/ecnct63103.2024.10704325","name":"Back Propagation Neural Network Model for Railway Risk Warning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ecnct63103.2024.10704325","authors":["Baofu Duan","Yunqian Yang","Zhe Jing","Yuguan Wei","Anni Chu","Liankai Bu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-09T17:45:15Z","doi":"10.1109/ecnct63103.2024.10704325","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1587/nolta.15.796","name":"Spatiotemporal contextual learning network with excitatory and inhibitory synapses for spiking neural network hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1587/nolta.15.796","authors":["Takemori Orima","Yoshihiko Horio","Takeru Tsuji"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-30T22:19:43Z","doi":"10.1587/nolta.15.796","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/cenim64038.2024.10882777","name":"Continuous Cuffless Non-Invasive Blood Pressure Detection from ECG and PPG Signals Using Artificial Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cenim64038.2024.10882777","authors":["Aushaf Cintya Wanda","Muhammad Yazid","Rachmad Setiawan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-19T18:39:16Z","doi":"10.1109/cenim64038.2024.10882777","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/nnice61279.2024.10498833","name":"An Attack Prediction and Recognition Method for Water Treatment System Based on One-dimensional Convolutional Neural Network and Cumulative Sum","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nnice61279.2024.10498833","authors":["Xiangdong Hu","Lang Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-22T17:33:49Z","doi":"10.1109/nnice61279.2024.10498833","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.38007/nn.2020.010105","name":"Algorithm of Fusion Convolution Neural Network in Animal Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2020.010105","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T03:35:42Z","doi":"10.38007/nn.2020.010105","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/iscas.2019.8702519","name":"Non-Ideal Effects of Memristor-CMOS Hybrid Circuits for Realizing Multiple-Layer Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas.2019.8702519","authors":["Khoa Van Pham","Kyeong-Sik Min"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-05-01T21:02:28Z","doi":"10.1109/iscas.2019.8702519","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1016/j.chbah.2024.100104","name":"Behavioral and neural evidence for the underestimated attractiveness of faces synthesized using an artificial neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.chbah.2024.100104","authors":["Satoshi Nishida"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-08T02:14:44Z","doi":"10.1016/j.chbah.2024.100104","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/atigb63471.2024.10717662","name":"Analysis Of Traffic Sign Recognition Using Artificial Neural Network Algorithm Compared With Accuracy Of Recurrent Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/atigb63471.2024.10717662","authors":["P. Amos","S Narendran","M Keerthivasan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-22T17:25:30Z","doi":"10.1109/atigb63471.2024.10717662","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1007/s00521-024-09496-2","name":"Robust deep image-watermarking method by a modified Siamese network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-024-09496-2","authors":["Ako Bartani","Fardin Akhlaghian Tab","Alireza Abdollahpouri","Mohsen Ramezani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-20T14:02:45Z","doi":"10.1007/s00521-024-09496-2","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1007/s00521-023-09141-4","name":"Prediction and classification of minerals using deep residual neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-023-09141-4","authors":["Prasannavenkatesan Theerthagiri","A. Usha Ruby","J. George Chellin Chandran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-09T19:01:55Z","doi":"10.1007/s00521-023-09141-4","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/ijcnn60899.2024.10650655","name":"Generalized Gaze-Vector Estimation in Low-light with Encoded Event-driven Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn60899.2024.10650655","authors":["Abeer Banerjee","Naval Kishore Mehta","Shyam Sunder Prasad","Himanshu Kumar","Sumeet Saurav","Sanjay Singh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T17:35:05Z","doi":"10.1109/ijcnn60899.2024.10650655","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.52202/079017-1372","name":"DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity","source":"crossref","abstract":"","url":"https://doi.org/10.52202/079017-1372","authors":["Baekrok Shin","Junsoo Oh","Hanseul Cho","Chulhee Yun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-03T11:20:56Z","doi":"10.52202/079017-1372","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.32493/jtsi.v7i1.34168","name":"Deteksi Leukemia Limfoblastik Akut menggunakan Convolutional Neural Network","source":"crossref","abstract":"Leukemia limfoblastik akut merupakan jenis leukemia anak yang paling penting, dan menyumbang 25% dari kanker anak. Membedakan secara akurat prekursor sel normal dari sel kanker adalah kunci diagnosis leukemia limfoblastik akut. Namun, di bawah mikroskop, sel kanker sangat mirip dengan sel normal sehingga sulit untuk mengklasifikasikannya. Artikel ini menyajikan deteksi sel leukemia limfoblastik akut menggunakan Convolutional Neural Network (CNN). Dataset diperoleh dari ALL_IDB sejumlah 582 data citra berwarna yang dibagi menjadi 482 data citra latih dan 100 data citra uji. Data citra tersebut akan diubah ukurannya menjadi 128x128x3 sebelum akhirnya menjadi masukan dari model CNN. Model CNN yang digunakan adalah multi-scale CNN yang terdiri dari 3 lapisan konvolusi (ukuran filter 3x3, jumlah filter untuk masing-masing lapisan konvolusi yakni berurutan 32, 64, dan 128, dan fungsi aktivasi ReLU), 3 lapisan subsampling menggunakan maxpool dengan ukuran filter 2x2, 1 lapisan penggabungan yang digunakan untuk menggabungkan keluaran dari masing-masing lapisan subsampling, 1 lapisan fully-connected dengan fungsi aktivasi softmax dan fungsi galat cross-entropy, dan terakhir lapisan keluaran dengan jumlah kelas 2 yakni sel normal dan sel kanker. Model CNN akan dilatih menggunakan algoritma pelatihan Adam optimizer dengan laju pelatihan 0.0002 dan dilakukan iterasi sebanyak 20 kali. Berdasarkan hasil pelatihan setelah diiterasi sebanyak 20 kali, didapatkan nilai galat terkecil yakni 0,0001 dan nilai akurasi terbesar yakni 100% pada epoch ke-20. Model CNN kemudian diuji dengan 100 data citra uji dan menghasilkan tingkat akurasi 98% dan nilai galat 0,0482.","url":"https://doi.org/10.32493/jtsi.v7i1.34168","authors":["Mutaqin Akbar","Putri Taqwa Prasetyaningrum","Putry Wahyu Setyaningsih","Moh Ahsan","Alexius Endy Budianto"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-05T13:11:31Z","doi":"10.32493/jtsi.v7i1.34168","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1117/12.3037091","name":"Secure multiple image steganography based on invertible neural network and neural style transfer","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3037091","authors":["Weibin Feng","Yijun Liu","Wujian Ye","Dongjun Tan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-22T17:27:06Z","doi":"10.1117/12.3037091","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/ijcnn60899.2024.10650747","name":"Incremental Soft Pruning to Get the Sparse Neural Network During Training","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn60899.2024.10650747","authors":["Kehan Zhu","Fuyi Hu","Yuanbin Ding","Yunyun Dong","Ruxin Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T17:35:05Z","doi":"10.1109/ijcnn60899.2024.10650747","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1016/j.device.2024.100329","name":"Enabling reliable two-terminal memristor network by exploiting the dynamic reverse recovery in a diode selector","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.device.2024.100329","authors":["Tianda Fu","Shuai Fu","Siqi Wang","Jun Yao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-21T01:18:04Z","doi":"10.1016/j.device.2024.100329","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1587/elex.21.20240095","name":"Ergodic sequential logic spiking neural network: reproductions of biologically plausible spatio-temporal phenomena and low-power implementation towards neural prosthesis","source":"crossref","abstract":"","url":"https://doi.org/10.1587/elex.21.20240095","authors":["Yuta Shiomi","Hiroyuki Torikai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-13T22:13:46Z","doi":"10.1587/elex.21.20240095","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/ijcnn60899.2024.10651440","name":"Regularized artificial neural network based patent value interval prediction model","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn60899.2024.10651440","authors":["Weidong Liu","Kaiyang Xiao","Jiamin Zhang","Bo Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T17:35:05Z","doi":"10.1109/ijcnn60899.2024.10651440","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/icceic64099.2024.10775835","name":"Research on Network Space Asset Data Aggregation and Fusion Technology Based on Neural Network Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icceic64099.2024.10775835","authors":["Siwei Li","Liang Meng","Lina Chen","Junbing Pan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-11T22:21:58Z","doi":"10.1109/icceic64099.2024.10775835","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1007/s11063-024-11471-w","name":"A Vision Enhancement and Feature Fusion Multiscale Detection Network","source":"crossref","abstract":"Abstract In the field of object detection, there is often a high level of occlusion in real scenes, which can very easily interfere with the accuracy of the detector. Currently, most detectors use a convolutional neural network (CNN) as a backbone network, but the robustness of CNNs for detection under cover is poor, and the absence of object pixels makes conventional convolution ineffective in extracting features, leading to a decrease in detection accuracy. To address these two problems, we propose VFN (A Vision Enhancement and Feature Fusion Multiscale Detection Network), which first builds a multiscale backbone network using different stages of the Swin Transformer, and then utilizes a vision enhancement module using dilated convolution to enhance the vision of feature points at different scales and address the problem of missing pixels. Finally, the feature guidance module enables features at each scale to be enhanced by fusing with each other. The total accuracy demonstrated by VFN on both the PASCAL VOC dataset and the CrowdHuman dataset is better than that of other methods, and its ability to find occluded objects is also better, demonstrating the effectiveness of our method.The code is available at https://github.com/qcw666/vfn .","url":"https://doi.org/10.1007/s11063-024-11471-w","authors":["Chengwu Qian","Jiangbo Qian","Chong Wang","Xulun Ye","Caiming Zhong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-07T12:02:22Z","doi":"10.1007/s11063-024-11471-w","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.30714/j-ebr.2024.222","name":"Investigating the neural correlates of stroop effect using the multilayer perceptron neural network","source":"crossref","abstract":"","url":"https://doi.org/10.30714/j-ebr.2024.222","authors":["Elif Uğurgöl","Miray Altınkaynak","Demet Yeşilbaş","Turgay Batbat","Aysegül Güven"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-06T05:41:06Z","doi":"10.30714/j-ebr.2024.222","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.5220/0012469300003636","name":"Hybrid Mechanistic Neural Network Modelling of the Degree of Cure of Polymer Composite","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0012469300003636","authors":["Samuel Sells","Jie Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-29T05:30:53Z","doi":"10.5220/0012469300003636","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1007/s11063-024-11533-z","name":"FTUNet: A Feature-Enhanced Network for Medical Image Segmentation Based on the Combination of U-Shaped Network and Vision Transformer","source":"crossref","abstract":"Abstract Semantic Segmentation has been widely used in a variety of clinical images, which greatly assists medical diagnosis and other work. To address the challenge of reduced semantic inference accuracy caused by feature weakening, a pioneering network called FTUNet (Feature-enhanced Transformer UNet) was introduced, leveraging the classical Encoder-Decoder architecture. Firstly, a dual-branch Encoder is proposed based on the U-shaped structure. In addition to employing convolution for feature extraction, a Layer Transformer structure (LTrans) is established to capture long-range dependencies and global context information. Then, an Inception structural module focusing on local features is proposed at the Bottleneck, which adopts the dilated convolution to amplify the receptive field to achieve deeper semantic mining based on the comprehensive information brought by the dual Encoder. Finally, in order to amplify feature differences, a lightweight attention mechanism of feature polarization is proposed at Skip Connection, which can strengthen or suppress feature channels by reallocating weights. The experiment is conducted on 3 different medical datasets. A comprehensive and detailed comparison was conducted with 6 non-U-shaped models, 5 U-shaped models, and 3 Transformer models in 8 categories of indicators. Meanwhile, 9 kinds of layer-by-layer ablation and 4 kinds of other embedding attempts are implemented to demonstrate the optimal structure of the current FTUNet.","url":"https://doi.org/10.1007/s11063-024-11533-z","authors":["Yuefei Wang","Xi Yu","Yixi Yang","Shijie Zeng","Yuquan Xu","Ronghui Feng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-04T06:02:20Z","doi":"10.1007/s11063-024-11533-z","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.2139/ssrn.4777411","name":"Hyperspectral Image Analysis for Water Quality Classification: A Hybrid Network Model Based on 3d Convolutional Neural Network and Capsule Network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4777411","authors":["Hongran Li","Hui Zhao","Chao Wei","Min Cao","Jian Zhang","Heng Zhang","Dongqing Yuan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-29T02:26:41Z","doi":"10.2139/ssrn.4777411","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1007/s42979-024-03507-8","name":"Effects of the Flatness Network Parameter Threshold on the Performance of the Rectified Linear Unit Memristor-Like Activation Function in Deep Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s42979-024-03507-8","authors":["Marcelle Tchepgoua Mbakop","Justin Roger Mboupda Pone","Priva Chassem Kamdem","Romanic Kengne"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-10T03:52:25Z","doi":"10.1007/s42979-024-03507-8","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.12688/f1000research.136097.2","name":"Graph neural network-based anomaly detection for river network systems","source":"crossref","abstract":"Background Water is the lifeblood of river networks, and its quality plays a crucial role in sustaining both aquatic ecosystems and human societies. Real-time monitoring of water quality is increasingly reliant on in-situ sensor technology. Anomaly detection is crucial for identifying erroneous patterns in sensor data, but can be a challenging task due to the complexity and variability of the data, even under typical conditions. This paper presents a solution to the challenging task of anomaly detection for river network sensor data, which is essential for accurate and continuous monitoring. Methods We use a graph neural network model, the recently proposed Graph Deviation Network (GDN), which employs graph attention-based forecasting to capture the complex spatio-temporal relationships between sensors. We propose an alternate anomaly threshold criteria for the model, GDN+, based on the learned graph. To evaluate the model’s efficacy, we introduce new benchmarking simulation experiments with highly-sophisticated dependency structures and subsequence anomalies of various types. We also introduce software called gnnad. Results We further examine the strengths and weaknesses of this baseline approach, GDN, in comparison to other benchmarking methods on complex real-world river network data. Conclusions Findings suggest that GDN+ outperforms the baseline approach in high-dimensional data, while also providing improved interpretability.","url":"https://doi.org/10.12688/f1000research.136097.2","authors":["Katie Buchhorn","Edgar Santos-Fernandez","Kerrie Mengersen","Robert Salomone"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-28T12:30:06Z","doi":"10.12688/f1000research.136097.2","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.5220/0012961500004508","name":"Advancements in Pancreatic Cancer Detection: A Comprehensive Investigation of Convolutional Neural Network Applications","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0012961500004508","authors":["Wenhan Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-19T12:37:25Z","doi":"10.5220/0012961500004508","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.5220/0012707900003687","name":"Automated Software Vulnerability Detection Using CodeBERT and Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0012707900003687","authors":["Rabaya Mim","Abdus Satter","Toukir Ahammed","Kazi Sakib"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-01T12:36:46Z","doi":"10.5220/0012707900003687","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/iccre61448.2024.10589790","name":"Finite-Time Neural Network Controllers for Nonlinear Dynamical Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccre61448.2024.10589790","authors":["Kraisak Phothongkum","Suwat Kuntanapreeda"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-16T17:19:44Z","doi":"10.1109/iccre61448.2024.10589790","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/cac63892.2024.10865178","name":"Mathematical Model and Adaptive Neural Network Flight Control of Wing-in Ground-Effect Vehicle","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cac63892.2024.10865178","authors":["Qifeng Liu","Xiangyuan Jiang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-13T18:29:08Z","doi":"10.1109/cac63892.2024.10865178","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/acoit62457.2024.10940003","name":"Neural Network Prediction of CFG Pile Composite Foundation Bearing Capacity based on BP Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/acoit62457.2024.10940003","authors":["Jia Caifeng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-02T23:13:49Z","doi":"10.1109/acoit62457.2024.10940003","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.23977/infse.2024.050413","name":"The Security and Economic Evaluation Method of Industrial Control System Based on BP Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.23977/infse.2024.050413","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-17T08:25:56Z","doi":"10.23977/infse.2024.050413","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/incet61516.2024.10593292","name":"Using Neural Network for Financial Forecasting","source":"crossref","abstract":"","url":"https://doi.org/10.1109/incet61516.2024.10593292","authors":["Atika Gupta","Divya Kapil","Abhishek Jain","Harender Singh Negi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-26T17:21:23Z","doi":"10.1109/incet61516.2024.10593292","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/icitsi65188.2024.10929317","name":"Convolutional Neural Network In Human Eye Disease Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icitsi65188.2024.10929317","authors":["Muhammad Giat","Setiawan Hadi","Akmal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-26T06:37:35Z","doi":"10.1109/icitsi65188.2024.10929317","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/iconstem60960.2024.10568893","name":"Improving Accuracy in 5G Network Using Novel Neural Network Conjugate Gradient and Comparison With Stepwise Linear Regression","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iconstem60960.2024.10568893","authors":["Ravanala Subhashini","Amudha V","S. Jency"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-28T17:54:40Z","doi":"10.1109/iconstem60960.2024.10568893","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/iist62526.2024.00098","name":"Abnormal Network Traffic Detection Algorithm Based on Improved Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iist62526.2024.00098","authors":["Lu Chen","Tao Zhang","Yuanyuan Ma","Mu Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-04T18:31:50Z","doi":"10.1109/iist62526.2024.00098","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/icnc-fskd64080.2024.10702204","name":"An Enhanced Fault Localization Method in Distribution Network Using Graph Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc-fskd64080.2024.10702204","authors":["Jun Shang","Zhen Qiu","Mingwei Gao","Jinsheng Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-08T13:34:48Z","doi":"10.1109/icnc-fskd64080.2024.10702204","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.17587/it.30.32-41","name":"A Technique for Creating and Training an Artificial Neural Network to Detect Network Traffic Anomalies","source":"crossref","abstract":"The article presents a technique for creating and training an artificial neural network to recognize network traffic anomalies using relatively small samples of collected data to generate training data. Various data sources for machine learning and approaches to network traffic analysis are considered. There are data format and the method of generating them from the collected network traffic is described, as well as the steps of the methodology in detail. Using the technique, an artificial neural network was created and trained for the task of recognizing anomalies in the network traffic of the ICMP protocol. The results of testing and comparing various artificial neural network configurations and learning conditions for a given task are presented. The artificial neural network trained according to the method was tested on real network traffic. The presented technique can be applied without requiring changes to detect anomalies of various network protocols and network traffic using a suitable parameterizer and data markup.","url":"https://doi.org/10.17587/it.30.32-41","authors":["S. O. Ivanov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-19T06:25:28Z","doi":"10.17587/it.30.32-41","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1007/978-981-97-1900-6_7","name":"Application of Neural Network-Based Techniques to Network Intrusion Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-1900-6_7","authors":["Ashalata Panigrahi","Manas Ranjan Patra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-20T13:01:53Z","doi":"10.1007/978-981-97-1900-6_7","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/cnteie66268.2024.00030","name":"Research on Prediction of Freshness of Frozen Yellow Croaker Based on PCL Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cnteie66268.2024.00030","authors":["Xu E","Song Wang","Chenkao Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-12T17:41:47Z","doi":"10.1109/cnteie66268.2024.00030","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.52202/079017-1872","name":"Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit","source":"crossref","abstract":"","url":"https://doi.org/10.52202/079017-1872","authors":["Jason Lee","Kazusato Oko","Taiji Suzuki","Denny Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-03T11:20:56Z","doi":"10.52202/079017-1872","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1142/s0218127424501062","name":"Dynamics and Implementation of FPGA for Memristor-Coupled Fractional-Order Hopfield Neural Networks","source":"crossref","abstract":"The coupling between neurons can lead to diverse neural network architectures, with the Hopfield neural network (HNN) being particularly noteworthy for its resemblance to human brain function and its potential in modeling chaotic systems. This paper introduces a novel approach: a fractional-order HNN coupled with a hyperbolic tangent-type memristor. Initially, we propose a new model for the hyperbolic tangent-type memristor and fingerprints. Subsequently, we construct a memristor-coupled fractional-order Hopfield neural network (mFOHNN) and explore its dynamic behavior using various analytical tools, including phase diagrams, bifurcation diagrams, Lyapunov exponent diagrams, Poincaré maps, and attractor basins. Our findings reveal rich coexisting bifurcation behavior in the neural network model, influenced by different initial values of coexisting attractors. Finally, we validate the model through analysis and implementation using Multisim circuit simulation software and FPGA hardware, respectively.","url":"https://doi.org/10.1142/s0218127424501062","authors":["Ningning Yang","Jiahao Liang","Chaojun wu","Zhenshuo Guo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-30T04:53:20Z","doi":"10.1142/s0218127424501062","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1063/5.0190861","name":"A temperature sensing based Na0.5Bi0.5TiO3 ferroelectric memristor device for artificial neural systems","source":"crossref","abstract":"With the development of artificial intelligence technology, it remains a challenge to improve the resistive switching performance of next-generation nonvolatile ferroelectric memristor device (FMD). Here, we report an epitaxial Na0.5Bi0.5TiO3 ferroelectric memristor device (NBT-FMD) with temperature sensing. The NBT epitaxial films with strong polarization strength and suitable oxygen vacancy concentration were obtained by temperature adjustment (700 °C). In addition, the function of the spiking-time-dependent plasticity and paired-pulse facilitation is simulated in ferroelectric memristor devices of Pt/NBT/SrRuO3 (SRO)/SrTiO3 (STO). More importantly, we have designed a neuronal circuit to confirm that NBT-FMD can serve as temperature receptors on the human skin, paving the way for bio-inspired application.","url":"https://doi.org/10.1063/5.0190861","authors":["Lei Zhou","Yifei Pei","Changliang Li","Hui He","Chao Liu","Yue Hou","Haoyuan Tian","Jianxin Guo","Baoting Liu","Xiaobing Yan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-28T11:36:39Z","doi":"10.1063/5.0190861","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/iccsc62074.2024.10616720","name":"Memristor-based efficient Combinational circuit designs using Material Implication","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccsc62074.2024.10616720","authors":["Sourav Mukherjee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-06T17:29:56Z","doi":"10.1109/iccsc62074.2024.10616720","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1016/b978-0-323-90793-4.00011-8","name":"Techniques for crossbar array read operation","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-323-90793-4.00011-8","authors":["Adeyemo Adedotun","Saurabh Khandelwal","Abusaleh Jabir"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-18T14:07:54Z","doi":"10.1016/b978-0-323-90793-4.00011-8","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.52202/079017-2124","name":"Slack-Free Spiking Neural Network Formulation for Hypergraph Minimum Vertex Cover","source":"crossref","abstract":"","url":"https://doi.org/10.52202/079017-2124","authors":["Tam Nguyen","Anh-Dzung Doan","Zhipeng Cai","Tat-Jun Chin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-03T11:20:56Z","doi":"10.52202/079017-2124","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.46824/megasains.v14i2.140","name":"PREDIKSI KEJADIAN PETIR DENGAN ARTIFICIAL NEURAL NETWORK DI WILAYAH KABUPATEN KEPULAUAN TANIMBAR","source":"crossref","abstract":"Various research efforts have been made to determine thunderstorm prediction methods, one of which involves using upper air data. However, the use of atmospheric stability threshold values as a reference does not always apply uniformly to all locations due to differences in the characteristics of each region. Therefore, a more objective and precise approach is needed in predicting thunderstorm events, including the application of artificial neural network (ANN) techniques. In this study, the Artificial Neural Network (ANN) method, which is an implementation of artificial intelligence, is used to predict thunderstorm events in the Saumlaki region. The ANN input not only relies on raw data in the form of atmospheric instability index values but also uses feature selection processing to reduce the dimensionality of multivariate input data, minimizing the loss of input data. This process focuses only on essential information and eliminates linear dependencies between features, a technique known as Principal Component Analysis (PCA). The research results indicate that ANN with PCA technique has a higher level of accuracy in predicting thunderstorm events in the Saumlaki region.","url":"https://doi.org/10.46824/megasains.v14i2.140","authors":["Indra Prawiro Adiredjo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-05T12:42:34Z","doi":"10.46824/megasains.v14i2.140","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.32664/j-intech.v12i1.1273","name":"Identifikasi Tanda Tangan Dengan Menggunakan Metode Convolution Neural Network (CNN)","source":"crossref","abstract":"This research aims to develop and evaluate a Convolutional Neural Network (CNN) model for signature identification. The CNN method is chosen for its capability to extract and analyze complex visual features from signature images. The data used in this study consists of a collection of signature images divided into training and testing sets. The proposed CNN model comprises several convolutional, pooling, and fully connected layers optimized for classification tasks. Evaluation results indicate that the CNN model achieves excellent performance with an accuracy of 0.97, demonstrating high accuracy and precision in signature recognition. With these results, CNN proves to be an effective and reliable method for signature identification, making a significant contribution to the field of biometric identity verification. These findings open opportunities for further applications in security and authentication systems requiring automatic signature recognition.","url":"https://doi.org/10.32664/j-intech.v12i1.1273","authors":["Dechy Deswita Indriani.S","Elya Juni Arta Sinaga","Grace Oktavia","Hermawan Syahputra","Fanny Ramadhani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-12T05:23:41Z","doi":"10.32664/j-intech.v12i1.1273","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/icicm63644.2024.10814587","name":"A Flexible Routing Strategy Based on Region Manager in Network-on-Chip for Neural Network Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icicm63644.2024.10814587","authors":["Yaohui Lv","Xuefei Bai","Song Chen","Yi Kang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-31T19:22:54Z","doi":"10.1109/icicm63644.2024.10814587","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1016/j.spasta.2023.100801","name":"A flexible likelihood-based neural network extension of the classic spatio-temporal model","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.spasta.2023.100801","authors":["Malte Jahn"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-19T12:01:28Z","doi":"10.1016/j.spasta.2023.100801","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/icsintesa62455.2024.10748189","name":"Lightweight Convolutional Neural Network (CNN) and Long Short-Term Memory Network (LSTM) for Dynamic Hand Gesture Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icsintesa62455.2024.10748189","authors":["Leander Lizo","Jheanel Estrada"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-14T18:35:39Z","doi":"10.1109/icsintesa62455.2024.10748189","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1063/5.0206650","name":"Turbulence modeling of stratified turbulence using a constrained artificial neural network","source":"crossref","abstract":"For large eddy simulations (LES) of stratified turbulence in the strongly stratified regime, an artificial neural network (ANN) with five hidden layers is used to construct a sub-grid scale (SGS) model. The ANN is assessed by comparing it to the Smagorinsky model, the dynamic Smagorinsky model, the gradient model, and filtered direct numerical simulation data. In the a priori test, the SGS model using ANN performed better than the Smagorinsky model and the gradient model in terms of the correlation coefficient and relative error of the energy transfer rate. However, the ANN does not provide sufficient energy dissipation when it is applied to LES with a larger filter width because it overpredicts backscatter. To address this problem, we also trained a constrained ANN using a custom loss function that penalizes excessive backscatter. It is shown that the constrained ANN successfully predicts less backscatter, maintaining the high correlation coefficient without ad hoc clipping. These results show that ANN is a promising tool for realizing a highly accurate and stable SGS model for stratified turbulence.","url":"https://doi.org/10.1063/5.0206650","authors":["Daisuke Nishiyama","Yuji Hattori"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-13T09:56:35Z","doi":"10.1063/5.0206650","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1007/978-3-031-78732-4_10","name":"Working Memory","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78732-4_10","authors":["Theodore Wasserman","Lori Drucker Wasserman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-30T22:57:57Z","doi":"10.1007/978-3-031-78732-4_10","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/isctech63666.2024.10845486","name":"Multi View Learning-Based Graph Neural Network for Rumor Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isctech63666.2024.10845486","authors":["Linen Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-22T18:47:22Z","doi":"10.1109/isctech63666.2024.10845486","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/icce59016.2024.10444250","name":"An Efficient Convolutional Neural Network Accelerator on FPGA Platform","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icce59016.2024.10444250","authors":["Yeong-Kang Lai","Ling-Cheng Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-28T13:47:20Z","doi":"10.1109/icce59016.2024.10444250","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1007/s10462-024-10826-y","name":"Heterogeneous wireless network selection using feed forward double hierarchy linguistic neural network","source":"crossref","abstract":"Abstract Network selection in heterogeneous wireless networks (HWNs) is a complex issue that requires a thorough understanding of service features and user preferences. This is because the various wireless access technologies have varying capabilities and limitations, and the best network for a voice, video, and data service depends on a variety of factors. For selecting the optimal network in HWNs, varying factors such as the user’s position, accessible network resources, service quality requirements, and user preferences must be considered. The classical decision making procedure is very difficult and uncertain to select the desirable HWNs for voice, video, and data. Therefore, we develop a novel decision making model based on feed-forward neural networks under the double hierarchy linguistic information for the selection of the best HWNs for voice, video, and data. In this article, we introduce a novel feed-forward double hierarchy linguistic neural network using the Hamacher t-norm and t-conorm. Further, the feed-forward double hierarchy linguistic neural network applies to the decision making model for the selection of the best HWNs for voice, video, and data. In this novel decision making model, we first take the given data about HWNs and use the converting function to convert the given data into a double hierarchy linguistic term set. We calculate the hidden layer and output layer information by using Hamacher aggregation operations. Finally, we use the sigmoid activation function on the output layer information to decide on the best HWNs for voice, video, and data according to ranking. The proposed approach is compared with other existing models of decision making and the results of the comparison show that the proposed technique is applicable and reliable for the decision support model.","url":"https://doi.org/10.1007/s10462-024-10826-y","authors":["Saleem Abdullah","Ihsan Ullah","Fazal Ghani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-02T13:02:19Z","doi":"10.1007/s10462-024-10826-y","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1039/d5tc01371b/v1/review2","name":"Review for \"Amorphous Ta&lt;sub&gt;2&lt;/sub&gt;O&lt;sub&gt;5&lt;/sub&gt; memristor with excellent self-selective and artificial synaptic properties for artificial neural networks\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5tc01371b/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-16T17:06:47Z","doi":"10.1039/d5tc01371b/v1/review2","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.30574/wjaets.2024.12.2.0309","name":"Optimization of solar energy using artificial neural network vs recurrent neural network controller with ultra lift Luo converter","source":"crossref","abstract":"In today's society, the demand for clean energy is essential. Traditionally, renewable sources such as hydropower, wind, and solar have provided sustainable solutions. Photovoltaic (PV) systems generate electricity from sunlight using semiconductor PV cells, which have been effective for over 30 years. The efficiency of PV cells depends on irradiance (solar photon intensity) and temperature. Higher irradiance boosts efficiency, while higher temperatures reduce it. Despite their low voltage outputs, PV systems can be optimized with DC-DC Ultra Lift Luo converters to meet load requirements, improving system efficiency. The Ultra Lift Luo converter, a type of DC-DC converter, offers a higher voltage conversion gain than conventional boost converters. This converter belongs to the Luo converter family, which uses advanced techniques to achieve high voltage gain and efficiency. Solar irradiance fluctuates throughout the day, impacting PV cell output. Maximum Power Point Trackers (MPPTs) adjust the system's operating point to sustain peak efficiency. This study aims to design AI controllers for MPPT management. We will evaluate the performance of Artificial Neural Networks (ANN) and Recurrent Neural Networks (RNN) with three datasets to determine the most efficient AI controller for optimizing solar energy systems.","url":"https://doi.org/10.30574/wjaets.2024.12.2.0309","authors":["Kasim Ali Mohammad","Sarhan M. Musa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-26T01:18:48Z","doi":"10.30574/wjaets.2024.12.2.0309","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.17163/ings.n32.2024.08","name":"Neural network-based robot localization using visual features","source":"crossref","abstract":"This paper outlines the development of a module capable of constructing a map-building algorithm using inertial odometry and visual features. It incorporates an object recognition module that leverages local features and unsupervised artificial neural networks to identify non-dynamic elements in a room and assign them positions. The map is modeled using a neural network, where each neuron corresponds to an absolute position in the room. Once the map is constructed, capturing just a couple of images of the environment is sufficient to estimate the robot's location. The experiments were conducted using both simulation and a real robot. The Webots environment with the virtual humanoid robot NAO was used for the simulations. Concurrently, results were obtained using a real NAO robot in a setting with various objects. The results demonstrate notable precision in localization within the two-dimensional maps, achieving an accuracy of ± (0.06, 0.1) m in simulations contrasted with the natural environment, where the best value achieved was ± (0.25, 0.16) m.","url":"https://doi.org/10.17163/ings.n32.2024.08","authors":["Felipe Trujillo-Romero"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-01T14:30:21Z","doi":"10.17163/ings.n32.2024.08","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.4018/ijisscm.345654","name":"Physical Delivery Network Optimization Based on Ant Colony Optimization Neural Network Algorithm","source":"crossref","abstract":"The development of modern logistics chains is not just simple cargo transportation, it has become a cross-integrated industry that integrates many emerging technologies such as IoT technology, intelligent transportation, cloud computing and mobile Internet. Based on the ant colony algorithm (ACA), this paper optimizes the physical delivery network of the optimized neural network algorithm, establishes a mathematical model for the constraints and optimization objectives in the optimization of the physical delivery path, and proposes some improvements to the ACA to improve the convergence of the algorithm. speed and global search ability, so as to use the improved algorithm to solve the physical delivery path optimization problem. Experiments show that the optimal distance of physical delivery path planning calculated by traditional ACA is 207.8544km, while the optimal distance of improved ACA path planning is 197.9879km. The performance of the improved ACA is improved by analyzing the results of solving typical examples.","url":"https://doi.org/10.4018/ijisscm.345654","authors":["Shujuan Wu","Hanlie Cheng","Qiang Qin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-16T11:20:57Z","doi":"10.4018/ijisscm.345654","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.46632/jdaai/3/2/14","name":"Provisional Diagnosis and Prognosis of Burn Skin Using Convolutional Neural Network","source":"crossref","abstract":"This paper explores the use of a convolutional neural network (CNN) in burn skin diagnosis and prognosis. Leveraging a variety of labelled medical images, the model integrates to acquire comprehensive features. By enhancing diagnostic and prognostic accuracy, the model aims to boost the outcomes of dermatological care. When compared to conventional techniques, the CNN performs better for provisional diagnosis, obtaining high accuracy in classifying burn severity. By estimating possible outcomes based on the original evaluation, the model is further expanded to offer a prediction of the healing process. In relation to treatment plans and long-term patient care, this expertise allows plastic surgeons to make informed decisions. Considering consideration of different clinical settings and patient demographics, we assess the suggested method on an extensive dataset of burn skin photos. The outcomes demonstrate that the CNN can diagnose and predict burn skin damage. Our results imply that using advanced deep learning methods in the plastic surgery workflow can greatly improve the accuracy and effectiveness of burn-related analyses.","url":"https://doi.org/10.46632/jdaai/3/2/14","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-13T11:02:30Z","doi":"10.46632/jdaai/3/2/14","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.54254/2755-2721/42/20230786","name":"A hybrid neural network based on the small-world network for inner speech recognition","source":"crossref","abstract":"This study is devoted to the identification of human inner speech using an electroencephalogram (EEG), where inner speech refers to an individual's subjective experience of language, disconnected from discernible audible articulation. The core aim of this system is the rapid and precise classification of signals via human inner speech, thus facilitating enhanced control and interaction functionalities. The research entails a comprehensive analysis of 10 volunteers' brain activity across 128 channels from OpenNeuro's Inner speech dataset. A hybrid neural network, which incorporates the small-world network structure, is employed to model neural activity within the brain. This approach outperforms random chance and aligns with current research expectations.","url":"https://doi.org/10.54254/2755-2721/42/20230786","authors":["Sichu Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-21T21:19:38Z","doi":"10.54254/2755-2721/42/20230786","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/ist64061.2024.10843561","name":"Frame Synchronization In Underwater Acoustic Communication Based on Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ist64061.2024.10843561","authors":["Ali Sedaghat Khankahdani","Ali Jamshidi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-21T18:23:03Z","doi":"10.1109/ist64061.2024.10843561","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/powerafrica61624.2024.10759484","name":"Data Driven Artificial Neural Network Fault Classification by Bayesian Optimization","source":"crossref","abstract":"","url":"https://doi.org/10.1109/powerafrica61624.2024.10759484","authors":["Sipho P Lafleni","Mbuyu Sumbwanyambe","Tlotlollo S Hlalele"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-09T19:31:59Z","doi":"10.1109/powerafrica61624.2024.10759484","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/iccece61317.2024.10504174","name":"Design Implementation of FPGA-Based Neural Network Acceleration","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccece61317.2024.10504174","authors":["Lizhao Zhang","Zhongliang Pan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-24T17:23:01Z","doi":"10.1109/iccece61317.2024.10504174","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1016/j.ins.2024.121003","name":"Spatio-temporal communication network traffic prediction method based on graph neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.ins.2024.121003","authors":["Liang Qin","Huaxi Gu","Wenting Wei","Zhe Xiao","Zexu Lin","Lu Liu","Ning Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-13T18:55:51Z","doi":"10.1016/j.ins.2024.121003","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.21203/rs.3.rs-3957770/v1","name":"D-GAN: An Automatic Acne Detection, Severity, and Assessment Framework using Generative Adversarial Network with Deep Neural Network","source":"crossref","abstract":"Abstract With the robust development of Artificial Intelligence (AI), especially image processing has made information technology more efficient and effective in the sense to evaluate facial features, even though there has been masked on the face. However, the accuracy of acne detection and related severity analysis is becoming a significant prospect for the precise treatment of patients. Due to this, close severity is one of the features that need to be added first, while it is considered a highly challenging aspect for dermatologists because the similar appearance of acne in the face reduces the rate of accuracy when examining. It poses a serious problem in the domain of biomedical processing and controls. In this paper, we contribute to four different folds. Initially, this paper presents a novel framework that provides a platform in order to measure localization and segmentation. In this process, consultants receive better accuracy and efficiency during the process of acne detection and severity analysis. Second, this paper utilizes deep neural networks (DNNs) as a backend process to lightning the extraction of multi-scale features through a multi-hierarchy neural net for regionalized facial features to investigate distinction and localization. Third, a class-based segmentation approach customizes and integrates with the proposed framework to examine the background and facial skin separation to distinguish different classes to obtain severity marking. Fourth, the facial skin segmentation classes are built as a cluster segment using Generative Adversarial Network (GAN). It provides a high-resolution network that enhances severity masking awareness and related attentions, including shuffle and conditional channels like an update in weight block. Although, the simulation illustrates that the technological collaboration achieves promising results and elaborates on the accuracy and efficiency while the detection of acne as compared to other state-of-the-art baseline methods. In addition, the proposed framework illustrates good results in severity analysis for acne detection comparably far better than the previously published articles with a performance rate of 3.112% (accuracy), 1.131% (segmentation), 2.317% (localization), and 1.573% (GAN-based high-resolution network management), respectively.","url":"https://doi.org/10.21203/rs.3.rs-3957770/v1","authors":["Umara Khalid","Li Chen","Abdullah Ayub Khan","Faisal Mehmood"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-19T19:41:40Z","doi":"10.21203/rs.3.rs-3957770/v1","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.21741/9781644903131-162","name":"Neural network-based estimation and compensation of friction for enhanced deep drawing process control","source":"crossref","abstract":"Abstract. Fluctuating process conditions, such as lubrication, can disturb the production process and lead to faulty components that have cracks or wrinkles. Real-time identification of process parameters can detect deviations in sheet forming operations and enable the process parameters to be adjusted. To increase process robustness, closed-loop control is often used to monitor and influence the material draw-in, which corresponds to the material flow and can be measured by camera systems inside the deep-drawing press. The aim of this work is to develop a control concept that can predict the optimum blank holder force by estimating the coefficient of friction based on the material draw-in of the last stroke. Using a cross-die geometry, it is shown how the material draw-in can be determined experimentally by means of a camera system and numerically by FE simulations. Finally, artificial neural network-based models are trained through simulations and are subsequently tested on a numerical case study in which the coefficient of friction is changed as a disturbance variable and must be compensated for. The widely applicable control concept has the potential to incorporate additional softsensors, for example to determine material properties, and other target variables, such as the punch force, into the optimization algorithm.","url":"https://doi.org/10.21741/9781644903131-162","authors":["Sebastian THIERY"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-19T16:10:26Z","doi":"10.21741/9781644903131-162","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1016/j.chaos.2024.115960","name":"Introducing a neural network approach to memristor dynamics: A comparative study with traditional compact models","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.chaos.2024.115960","authors":["D. Zhevnenko","F. Meshchaninov","V. Shmakov","E. Kharchenko","V. Kozhevnikov","A. Chernova","A. Belov","A. Mikhaylov","E. Gornev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-30T10:11:16Z","doi":"10.1016/j.chaos.2024.115960","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.23880/ijoac-16000315","name":"The Demand Prediction of Water Capacity for Drinking Water Plant by Artificial Neural Network","source":"crossref","abstract":"With the constant progress of the times and the rapid economic and social development, the demand for water consumption in the Hexi area of Xiangtan City is continuously rising. Ensuring the safety of urban water supply has become a crucial task. In this paper, we explore the effectiveness of the artificial neural network model in predicting water demand, leveraging the operational data from a water plant in Xiangtan. Thirty-three parameters are employed in this study to forecast water capacity. The results of our analysis reveal that the back propagation (BP) neural network model offers a more accurate and reliable prediction of water demand. This model, through its iterative learning process, is able to capture the complex relationships and patterns inherent in the water demand data. By adjusting its weights and thresholds based on the error between predicted and actual values, the BP neural network continuously improves its predictive accuracy. The application of the BP neural network in water demand prediction not only enhances the precision of forecasts but also contributes to better water resource management and allocation. It enables authorities to make informed decisions regarding water supply planning, ensuring the reliability and sustainability of the urban water system. The BP neural network model demonstrates its potential in accurately predicting water demand in Xiangtan’s Hexi area, thus contributing to the safety and efficiency of the urban water supply system.","url":"https://doi.org/10.23880/ijoac-16000315","authors":["Wei Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-24T09:14:46Z","doi":"10.23880/ijoac-16000315","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.3390/su16083474","name":"A Time Series Prediction Model for Wind Power Based on the Empirical Mode Decomposition–Convolutional Neural Network–Three-Dimensional Gated Neural Network","source":"crossref","abstract":"In response to the global challenge of climate change and the shift away from fossil fuels, the accurate prediction of wind power generation is crucial for optimizing grid operations and managing energy storage. This study introduces a novel approach by integrating the proportional–integral–derivative (PID) control theory into wind power forecasting, employing a three-dimensional gated neural (TGN) unit designed to enhance error feedback mechanisms. The proposed empirical mode decomposition (EMD)–convolutional neural network (CNN)–three-dimensional gated neural network (TGNN) framework starts with the pre-processing of wind data using EMD, followed by feature extraction via a CNN, and time series forecasting using the TGN unit. This setup leverages proportional, integral, and differential control within its architecture to improve adaptability and response to dynamic wind patterns. The experimental results show significant improvements in forecasting accuracy; the EMD–CNN–TGNN model outperforms both traditional models like autoregressive integrated moving average (ARIMA) and support vector regression (SVR), and similar neural network approaches, such as EMD–CNN–GRU and EMD–CNN–LSTM, across several metrics including mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), and coefficient of determination (R2). These advancements substantiate the model’s effectiveness in enhancing the precision of wind power predictions, offering substantial implications for future renewable energy management and storage solutions.","url":"https://doi.org/10.3390/su16083474","authors":["Zhiyong Guo","Fangzheng Wei","Wenkai Qi","Qiaoli Han","Huiyuan Liu","Xiaomei Feng","Minghui Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-22T07:44:09Z","doi":"10.3390/su16083474","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1007/978-981-97-9933-6_1","name":"Introduction","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-9933-6_1","authors":["Weibin Liu","Huaqing Hao","Hui Wang","Zhiyuan Zou","Weiwei Xing"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-03T07:07:27Z","doi":"10.1007/978-981-97-9933-6_1","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1115/gt2024-127933","name":"The Parameter Augmentation Pretraining Neural Network Model of Aero-Engine Thrust Prediction","source":"crossref","abstract":"Abstract Accurately predicting the thrust of aero-engine is important for engine health management and engine performance control. Thrust prediction neural network models have been widely applied in recent years. This paper proposes a parameter augmentation pretraining method and designs an aero-engine neural network model with physical significance. It is known that ground test system measures more engine parameters compared to onboard system. Due to the limitations of using onboard models, typically only the parameters measured by both systems are used as training parameters, which may lead to incomplete training. In this study, a 0-1 encoded vector is utilized to distinguish ground test system data and onboard system data. The model is first pretrained using the measurable parameters from the ground test system, following by retraining using parameters measured by both the ground test system and the onboard system. The parameter augmentation pretrain method allows the model to learn more mapping relationships of aero-engine and resolves the issue of parameter dimension matching. Furthermore, this study investigates the impact of the weight loss function on the prediction accuracy of the model. This research provides guidance for engine performance evaluation and further studies.","url":"https://doi.org/10.1115/gt2024-127933","authors":["Rui You","Hong Xiao","Guo Chen","Yufeng Liang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-28T19:31:35Z","doi":"10.1115/gt2024-127933","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.36074/logos-01.03.2024.065","name":"SOURCE BASE FOR THE STUDY OF NEURAL NETWORK MODELING OF LINGUISTIC UNITS: PROBLEM STATEMENT","source":"crossref","abstract":"","url":"https://doi.org/10.36074/logos-01.03.2024.065","authors":["Oleksii Dovhan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-13T20:50:57Z","doi":"10.36074/logos-01.03.2024.065","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1016/j.asoc.2023.111209","name":"Asynchronous evolution of deep neural network architectures","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.asoc.2023.111209","authors":["Jason Liang","Hormoz Shahrzad","Risto Miikkulainen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-30T02:30:13Z","doi":"10.1016/j.asoc.2023.111209","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1016/j.neucom.2024.127524","name":"Recurrent context layered radial basis function neural network for the identification of nonlinear dynamical systems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2024.127524","authors":["Rajesh Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-05T22:33:44Z","doi":"10.1016/j.neucom.2024.127524","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/coa58979.2024.10723512","name":"Underwater Acoustic Target Recognition based on Preemphasis Filter Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/coa58979.2024.10723512","authors":["Xiaopeng Kong","Yan Huang","Jingyi Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-25T17:20:34Z","doi":"10.1109/coa58979.2024.10723512","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.59277/romjist.2024.1.08","name":"Neural Network-based Pattern Recognition in the Framework of Edge Computing","source":"crossref","abstract":"Neural network (NN) model has been widely used in pattern recognition (PR), speech recognition, image processing and other fields, but its application in edge computing (EC) environment faces performance and energy consumption problems. This article first introduced the basic structure and training process of NN, including backpropagation algorithms. Then, this article presented a NN modeling approach based on EC, including NN model compression, distributed NN model and knowledge distillation approach. Finally, this article implemented a PR model for the MNIST (Mixed National Institute of Standards and Technology database) dataset and analyzed the experimental results. The experimental outcomes indicated that the presented approach can significantly enhance the performance of the NN model in the EC environment, while ensuring a high recognition accuracy. The NN modeling approach based on EC can reduce the amount of computation and storage of the NN, thus improving the operating efficiency of the NN in the EC environment by 6%-12%. The NN modeling approach based on EC can optimize the performance and efficiency of the NN model in the EC environment, and provide new ideas and approaches for the application of NN in the EC environment.","url":"https://doi.org/10.59277/romjist.2024.1.08","authors":["Jing NING"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-04T07:59:36Z","doi":"10.59277/romjist.2024.1.08","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1016/j.compbiomed.2024.108371","name":"Prediction of systemic lupus erythematosus-related genes based on graph attention network and deep neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.compbiomed.2024.108371","authors":["Fang Fang","Yizhou Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-25T16:57:12Z","doi":"10.1016/j.compbiomed.2024.108371","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.36499/psnst.v14i1.12035","name":"KLASIFIKASI GENDER BERDASARKAN CITRA MATA MANUSIA MENGGUNAKAN ALGORITMA CONVOLUTION NEURAL NETWORK","source":"crossref","abstract":"Teknologi otentikasi biometrik yang memanfaatkan karakteristik manusia seperti wajah, sidik jari, suara, dan iris mata semakin banyak digunakan untuk seperti wajah, sidik jari, suara, dan iris mata semakin banyak digunakan untuk identifikasi individu. Meskipun efektif dalam memastikan keaslian, sistem-sistem ini umumnya tidak memberikan informasi tambahan seperti jenis kelamin atau etnis dari individu yang diverifikasi. Penelitian sebelumnya telah meneliti klasifikasi jenis kelamin berdasarkan citra wajah, sedangkan penggunaan citra iris mata masih terbatas. Penelitian ini bertujuan untuk mengklasifikasikan jenis kelamin manusia berdasarkan citra iris mata dengan menerapkan pendekatan deep learning, khususnya menggunakan algoritma Convolutional Neural Network (CNN). Pengujian dilakukan pada sejumlah besar data untuk mengukur kinerja. Hasil penelitian menunjukkan bahwa model CNN mampu mencapai akurasi hingga 92% dalam mengklasifikasikan jenis kelamin berdasarkan citra iris mata. Penelitian ini membuka peluang baru untuk pengembangan lebih lanjut dalam biometrik berbasis iris mata.","url":"https://doi.org/10.36499/psnst.v14i1.12035","authors":["Rizky Dwi Wicaksono","Fandy Indra Pratama","Avira Budianita"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-16T09:58:16Z","doi":"10.36499/psnst.v14i1.12035","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1103/physrevb.110.115124","name":"Unifying view of fermionic neural network quantum states: From neural network backflow to hidden fermion determinant states","source":"crossref","abstract":"","url":"https://doi.org/10.1103/physrevb.110.115124","authors":["Zejun Liu","Bryan K. Clark"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-12T11:49:16Z","doi":"10.1103/physrevb.110.115124","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/ims40175.2024.10600239","name":"Order Reduction Using Laguerre-FDTD with Embedded Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ims40175.2024.10600239","authors":["Yifan Wang","Yiliang Guo","Rahul Kumar","Madhavan Swaminathan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-30T17:46:43Z","doi":"10.1109/ims40175.2024.10600239","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.23919/ccc63176.2024.10662130","name":"Neural Network Design Based on Differentiable Attention Module Search","source":"crossref","abstract":"","url":"https://doi.org/10.23919/ccc63176.2024.10662130","authors":["Mingzhe Yang","Yuan Zhou","Haiyang Wang","Shuoshi Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-17T18:46:36Z","doi":"10.23919/ccc63176.2024.10662130","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1504/ijbm.2024.10063379","name":"Basketball player action recognition based on improved LSTM neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1504/ijbm.2024.10063379","authors":["Xudong Yang N.A."],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-04T13:00:38Z","doi":"10.1504/ijbm.2024.10063379","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.25236/ajcis.2024.070203","name":"A scene-text feature enhanced halftone method based on invertible neural network","source":"crossref","abstract":"","url":"https://doi.org/10.25236/ajcis.2024.070203","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-15T02:54:05Z","doi":"10.25236/ajcis.2024.070203","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.52202/079017-3732","name":"Pruning neural network models for gene regulatory dynamics using data and domain knowledge","source":"crossref","abstract":"","url":"https://doi.org/10.52202/079017-3732","authors":["Intekhab Hossain","Jonas Fischer","Rebekka Burkholz","John Quackenbush"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-03T11:20:56Z","doi":"10.52202/079017-3732","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/inocon60754.2024.10512218","name":"Galaxy Classification Using Dilated-Separable Convolution Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/inocon60754.2024.10512218","authors":["Ajay Waghumbare","Shubham Kasera","Upasna Singh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-06T17:20:54Z","doi":"10.1109/inocon60754.2024.10512218","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/icdv61346.2024.10616823","name":"Ultra-Low Power Neural Network Processors using Analog-Based Computation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icdv61346.2024.10616823","authors":["Hiroshi Fuketa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-06T17:34:36Z","doi":"10.1109/icdv61346.2024.10616823","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/icccnt61001.2024.10724930","name":"Smart Healthcare - IoT and Artificial Neural Network(ANN)","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icccnt61001.2024.10724930","authors":["Laxmikanta Sutar","Suchismita Chinara"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-04T23:06:46Z","doi":"10.1109/icccnt61001.2024.10724930","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/icpects62210.2024.10780360","name":"ECG Biometric Human Identification using Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icpects62210.2024.10780360","authors":["Mageshbabu M","Mohana J"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-12T19:07:09Z","doi":"10.1109/icpects62210.2024.10780360","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/icmla61862.2024.00189","name":"Gaussian Process Neural Network Embeddings for Collaborative Filtering","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icmla61862.2024.00189","authors":["Wei Zhang","Brian Barr","John Paisley"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-04T18:39:11Z","doi":"10.1109/icmla61862.2024.00189","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/ccsb63463.2024.10735542","name":"YOLOv10 Tomato Ripening Detection Enhanced by Convolutional Neural Network Attention Mechanism","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ccsb63463.2024.10735542","authors":["Ruiyang Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-04T18:32:14Z","doi":"10.1109/ccsb63463.2024.10735542","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/laedc61552.2024.10555739","name":"Artificial Neural Network Driven Optimization for Analog Circuit Performance","source":"crossref","abstract":"","url":"https://doi.org/10.1109/laedc61552.2024.10555739","authors":["Anant Singhal","Priyanshi Goyal","Harshit Agarwal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-17T17:59:04Z","doi":"10.1109/laedc61552.2024.10555739","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.23919/acc60939.2024.10644877","name":"Lyapunov Neural Network with Region of Attraction Search","source":"crossref","abstract":"","url":"https://doi.org/10.23919/acc60939.2024.10644877","authors":["Zili Wang","Sean B. Andersson","Roberto Tron"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-05T17:56:19Z","doi":"10.23919/acc60939.2024.10644877","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1016/j.isatra.2024.07.002","name":"Neural network-based adaptive fault-tolerant control for nonlinear systems with uncertainties","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.isatra.2024.07.002","authors":["A.H. Tahoun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-03T21:13:21Z","doi":"10.1016/j.isatra.2024.07.002","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/icscss60660.2024.10625032","name":"Detection and Classification of Skin Cancer Using Binary Classifier, Residual Network, and Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icscss60660.2024.10625032","authors":["Urmila Pilania","Manoj Kumar","Priyam Garg","Reet Kaur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-20T15:34:43Z","doi":"10.1109/icscss60660.2024.10625032","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/icmiii62623.2024.00066","name":"Momentum Analysis Based on BP Neural Network and Topsis Model","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icmiii62623.2024.00066","authors":["Wen Teng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-10T18:23:27Z","doi":"10.1109/icmiii62623.2024.00066","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1007/978-3-031-78732-4_7","name":"Attentional Control","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-78732-4_7","authors":["Theodore Wasserman","Lori Drucker Wasserman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-30T22:57:52Z","doi":"10.1007/978-3-031-78732-4_7","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1038/s41592-024-02227-4","name":"Building an automated three-dimensional flight agent for neural network reconstruction","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s41592-024-02227-4","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-01T10:02:39Z","doi":"10.1038/s41592-024-02227-4","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/bdai62182.2024.10692924","name":"Enhancing Arabic Audio Quality through Neural Network-Based Upscaling","source":"crossref","abstract":"","url":"https://doi.org/10.1109/bdai62182.2024.10692924","authors":["Mohammed Alsuhaibani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-01T17:24:04Z","doi":"10.1109/bdai62182.2024.10692924","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.21595/vp.2024.24004","name":"Sliding mode controller with neural network compensation for tank","source":"crossref","abstract":"The control effectiveness of the all-electric tank stabilizers directly affects the firing accuracy of the tank gun. In order to improve the firing accuracy of the moving tank, this paper proposes a sliding mode control (SMC) strategy using neural network feed-forward compensation for the tank bidirectional stabilizers. SMC technology can quickly and effectively deal with uncertainties, unmodeled terms, and external disturbances in complex tank systems. Neural networks possess the advantage of approximating arbitrary continuous functions in finite time, realizing the estimation of SMC control errors with feed-forward compensation. The Lyapunov stability analysis proves that the designed controller can achieve asymptotic stabilization in finite time. Finally, both co-simulation and physical experiments are conducted. The results show that the proposed control strategy possesses better tracking speed and tracking accuracy compared to the conventional controller and exhibits strong robustness.","url":"https://doi.org/10.21595/vp.2024.24004","authors":["Yimin Wang","Guolai Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-04T04:36:58Z","doi":"10.21595/vp.2024.24004","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.2174/9789815256864124010011","name":"Neural Network Models for Feature Extraction and Empirical Thresholding","source":"crossref","abstract":"Neural Network Models for Feature Extraction and Empirical Thresholding study the combination of neural network models and empirical thresholding methods to improve the procedure for extracting features. For researchers and practitioners working in the fields of feature extraction and machine learning, it illustrates the advantages, approaches, and difficulties connected with this integration and offers helpful insights. The basic concepts of feature extraction are covered in this book chapter, along with an overview of the several neural network models that can be used to accomplish this task, such as auto-encoders, convolutional neural networks (CNNs), and recurrent neural networks (RNNs). This book chapter emphasizes the benefits, methodologies, and challenges associated with this integration, providing valuable insights for researchers and practitioners in the fields of feature extraction and machine learning. This book chapter is useful for statistical analysis, domain expertise-driven threshold selection, and validation metrics-based threshold choice as efficient techniques for enhancing feature quality and lowering noise.","url":"https://doi.org/10.2174/9789815256864124010011","authors":["Krupali Dhawale"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-15T07:57:41Z","doi":"10.2174/9789815256864124010011","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.14529/jcem240305","name":"Suppressing of Image Digital Noise Using a Neural Network Based on U-Net","source":"crossref","abstract":"","url":"https://doi.org/10.14529/jcem240305","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-19T13:29:25Z","doi":"10.14529/jcem240305","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/icdsis61070.2024.10594154","name":"Financial Analysis of Classifier Model Based on BP Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icdsis61070.2024.10594154","authors":["Yue Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-18T17:25:52Z","doi":"10.1109/icdsis61070.2024.10594154","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/cec60901.2024.10611953","name":"Neural network agents trained by declarative programming tutors","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cec60901.2024.10611953","authors":["Julian Szymanski","Jan Dobrosolski","Higinio Mora","Karol Draszawka"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-08T17:55:15Z","doi":"10.1109/cec60901.2024.10611953","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1016/j.heliyon.2024.e26870","name":"Neural network control of fractional-order chaotic systems with unknown control direction","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.heliyon.2024.e26870","authors":["Suxia Wang","Yong Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-27T12:28:18Z","doi":"10.1016/j.heliyon.2024.e26870","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.18267/j.aip.241","name":"The Fairness Stitch: A Novel Approach for Neural Network Debiasing","source":"crossref","abstract":"","url":"https://doi.org/10.18267/j.aip.241","authors":["Modar Sulaiman","Kallol Roy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-22T06:55:13Z","doi":"10.18267/j.aip.241","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.5121/csit.2024.140601","name":"Knowledge-Augmented Dynamic Neural Network Model and its Application in Credit Evaluation","source":"crossref","abstract":"Credit risk is the most significant risk faced by credit businesses. Currently, various approaches are widely used in credit evaluation. However, methods based on expert knowledge exhibit obvious subjective cognitive bias, while both statistical and machine learning methods require a substantial amount of historical data. In cases with limited data, the machine-learning effect is poor. Inspired by the structural similarity between neural networks (NN) and the Analytic Hierarchy Process (AHP), we propose a knowledge-augmented dynamic neural network model called KADNN to construct an effective credit evaluation model. This composite architecture will help effectively utilize existing data to alleviate the initial low-data dilemma and can be further utilized for training neural networks. Subsequent data updates can be dynamically incorporated to improve model accuracy. Additionally, this approach improves the comprehensibility and premature convergence issues of the NN model. The proposed approach is validated and evaluated through credit evaluation simulation.","url":"https://doi.org/10.5121/csit.2024.140601","authors":["Qingyue Xiong","Liwei Zhang","Qiujun Lan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-27T04:32:32Z","doi":"10.5121/csit.2024.140601","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/asiancomnet63184.2024.10810512","name":"Convolutional Neural Network and Haversine Formula in Presence System for Easy Attendance","source":"crossref","abstract":"","url":"https://doi.org/10.1109/asiancomnet63184.2024.10810512","authors":["Andy Victor Pakpahan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-30T19:20:26Z","doi":"10.1109/asiancomnet63184.2024.10810512","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/icnc64304.2024.10987878","name":"Event-Based Prescribed-Time Adaptive Neural Network Control for Uncertain Nonlinear Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc64304.2024.10987878","authors":["Yilin Chen","Yingnan Pan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-19T17:52:05Z","doi":"10.1109/icnc64304.2024.10987878","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1016/j.heliyon.2024.e40035","name":"The analysis of regional ice and snow tourist destinations under back propagation neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.heliyon.2024.e40035","authors":["Fuxue Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-01T06:53:56Z","doi":"10.1016/j.heliyon.2024.e40035","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/sibircon63777.2024.10758541","name":"Neural Network Model of Traffic Flow Forecasting","source":"crossref","abstract":"","url":"https://doi.org/10.1109/sibircon63777.2024.10758541","authors":["Roman Morozov","Anton Mikhalev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-26T18:45:18Z","doi":"10.1109/sibircon63777.2024.10758541","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/icassp48485.2024.10446976","name":"Emohrnet: High-Resolution Neural Network Based Speech Emotion Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icassp48485.2024.10446976","authors":["Akshay Muppidi","Martin Radfar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-18T18:56:31Z","doi":"10.1109/icassp48485.2024.10446976","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1088/1742-5468/ad0a8c","name":"A simple probabilistic neural network for machine understanding","source":"crossref","abstract":"Abstract We discuss the concept of probabilistic neural networks with a fixed internal representation being models for machine understanding. Here, ‘understanding’ is interpretted as the ability to map data to an already existing representation which encodes an a priori organisation of the feature space. We derive the internal representation by requiring that it satisfies the principles of maximal relevance and of maximal ignorance about how different features are combined. We show that, when hidden units are binary variables, these two principles identify a unique model—the hierarchical feature model—which is fully solvable and provides a natural interpretation in terms of features. We argue that learning machines with this architecture possess a number of interesting properties, such as the continuity of the representation with respect to changes in parameters and data, the possibility of controlling the level of compression and the ability to support functions that go beyond generalisation. We explore the behaviour of the model with extensive numerical experiments and argue that models in which the internal representation is fixed reproduce a learning modality which is qualitatively different from that of traditional models, such as restricted Boltzmann machines.","url":"https://doi.org/10.1088/1742-5468/ad0a8c","authors":["Rongrong Xie","Matteo Marsili"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-20T10:30:20Z","doi":"10.1088/1742-5468/ad0a8c","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:32.529Z"},{"id":"doi:10.1109/ecnct63103.2024.10704546","name":"Internal Short-Circuit Detection of Li-Ion Battery Based on EIS and Elman Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ecnct63103.2024.10704546","authors":["Yanbang Chen","Jingxiao Zhu","Bokang Ding"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-09T13:45:15Z","doi":"10.1109/ecnct63103.2024.10704546","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.2139/ssrn.4833317","name":"Prediction of Particle Size Distribution of Grinding Products Using Artificial Neural Network Approach","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4833317","authors":["Donwoo Lee","Jinyoung Je","Jihoe Kwon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-19T05:18:29Z","doi":"10.2139/ssrn.4833317","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.58190/imiens.2024.104","name":"Classification of Raisin Grains Using Different Artificial Neural Network Methods","source":"crossref","abstract":"In addition to its nutritional properties, raisins are also a beneficial food in terms of health due to its vitamins, minerals, antioxidants and phenolic compounds. Turkey ranks first in global raisin production with a production capacity of 24%. Many problems are encountered in the classification of raisins according to their type and quality by traditional methods. In order to overcome these problems, artificial intelligence systems, whose usage area is increasing day by day, are utilized. In this study, raisin grains were classified using 3 different Artificial Neural Network (ANN) methods using the ‘Raisin’ dataset from the UCI Machine Learning Repository. Performance measurements of Competitive Layer Neural Network (CLNN), Pattern Recognition Artificial Neural Network (PRNN) and Self-Organizing Map (SOM) methods used in classification were performed. In the obtained performance measurements, PRNN has the highest success, while SOM is weaker compared to the other two methods. CLNN, on the other hand, remains at similar levels to PRNN and offers a good alternative to PRNN.","url":"https://doi.org/10.58190/imiens.2024.104","authors":["Hayri Incekara"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-17T06:43:03Z","doi":"10.58190/imiens.2024.104","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.2139/ssrn.5005158","name":"Gated Recurrent Neural Network with Tree-Structured Parzen Estimator Bayesian Optimization for Enhancing Stock Index Prediction Accuracy","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5005158","authors":["Bivas Dinda"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-30T20:39:07Z","doi":"10.2139/ssrn.5005158","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.5750/ijme.v1i1.1382","name":"Study on Talent Cultivation Management Model of Universities Based on Fuzzy Neural Network Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.5750/ijme.v1i1.1382","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-27T16:25:21Z","doi":"10.5750/ijme.v1i1.1382","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.2139/ssrn.5014988","name":"Advanced Friction Modelling for Cold Forging Using a Feed Forward Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5014988","authors":["Stefan  Jonas Volz","Jonas Launhardt","Peter Groche"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-09T02:42:03Z","doi":"10.2139/ssrn.5014988","addedAt":"2026-09-01T01:48:32.529Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1021/acsami.4c10687","name":"Integration of CeO<sub>2</sub>-Based Memristor with Vertically Aligned Nanocomposite Thin Film: Enabling Selective Conductive Filament Formation for High-Performance Electronic Synapses.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.4c10687","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1021/acsami.4c10687","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1007/s11571-024-10173-2","name":"A memristor-based circuit design of avoidance learning with time delay and its application.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-024-10173-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1007/s11571-024-10173-2","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1038/s41598-024-78290-w","name":"Probabilistic metaplasticity for continual learning with memristors in spiking networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-024-78290-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41598-024-78290-w","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1007/s11571-024-10172-3","name":"The dynamical behavior effects of different numbers of discrete memristive synaptic coupled neurons.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-024-10172-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1007/s11571-024-10172-3","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.3390/mi15101258","name":"Study of Weight Quantization Associations over a Weight Range for Application in Memristor Devices.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/mi15101258","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3390/mi15101258","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1016/j.isci.2024.111327","name":"Optimization strategy of the emerging memristors: From material preparation to device applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.isci.2024.111327","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.isci.2024.111327","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.3390/biomimetics9090543","name":"Dynamic Effects Analysis in Fractional Memristor-Based Rulkov Neuron Model.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/biomimetics9090543","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3390/biomimetics9090543","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1038/s41598-024-81521-9","name":"Clinically validated classification of chronic wounds method with memristor-based cellular neural network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-024-81521-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41598-024-81521-9","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1002/advs.202405768","name":"Configurable Synaptic and Stochastic Neuronal Functions in ZnTe-Based Memristor for an RBM Neural Network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202405768","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1002/advs.202405768","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1038/s41598-024-75021-z","name":"Efficient memristor accelerator for transformer self-attention functionality.","source":"europepmc","abstract":"The adoption of transformer networks has experienced a notable surge in various AI applications. However, the increased computational complexity, stemming primarily from the self-attention mechanism, parallels the manner in which convolution operations constrain the capabilities and speed of convolutional neural networks (CNNs). The self-attention algorithm, specifically the matrix-matrix multiplication (MatMul) operations, demands a substantial amount of memory and computational complexity, thereby restricting the overall performance of the transformer. This paper introduces an efficient hardware accelerator for the transformer network, leveraging memristor-based in-memory computing. The design targets the memory bottleneck associated with MatMul operations in the self-attention process, utilizing approximate analog computation and the highly parallel computations facilitated by the memristor crossbar architecture. Remarkably, this approach resulted in a reduction of approximately 10 times in the number of multiply-accumulate (MAC) operations in transformer networks, while maintaining 95.47% accuracy for the MNIST dataset, as validated by a comprehensive circuit simulator employing NeuroSim 3.0. Simulation outcomes indicate an area utilization of 6895.7 $$\\mu m^2$$ , a latency of 15.52 seconds, an energy consumption of 3 mJ, and a leakage power of 59.55 $$\\mu W$$ . The methodology outlined in this paper represents a substantial stride towards a hardware-friendly transformer architecture for edge devices, poised to achieve real-time performance.","url":"https://doi.org/10.1038/s41598-024-75021-z","authors":["Meriem Bettayeb","Yasmin Halawani","Muhammad Umair Khan","Hani Saleh","Baker Mohammad"],"tags":["Memristor","Computer science","Transformer","Computer architecture","Electrical engineering"],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41598-024-75021-z","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"doi:10.1021/acsnano.4c12884","name":"Two-Terminal Neuromorphic Devices for Spiking Neural Networks: Neurons, Synapses, and Array Integration.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.4c12884","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1021/acsnano.4c12884","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1021/acsomega.4c05529","name":"Insights of BDAPbI<sub>4</sub>-Based Flexible Memristor for Artificial Synapses and In-Memory Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsomega.4c05529","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1021/acsomega.4c05529","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1016/j.neunet.2024.106728","name":"Deep brain stimulation and lag synchronization in a memristive two-neuron network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106728","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.neunet.2024.106728","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1126/sciadv.ado1058","name":"Semantic memory-based dynamic neural network using memristive ternary CIM and CAM for 2D and 3D vision.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.ado1058","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1126/sciadv.ado1058","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.3389/fnins.2024.1467935","name":"A neuromorphic event data interpretation approach with hardware reservoir.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnins.2024.1467935","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3389/fnins.2024.1467935","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1002/advs.202505016","name":"Electric Field-Driven Conformational Changes in Molecular Memristor and Synaptic Behavior.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202505016","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/advs.202505016","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1002/advs.202409291","name":"Advances in Metal Halide Perovskite Memristors: A Review from a Co-Design Perspective.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202409291","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/advs.202409291","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/tcyb.2024.3377011","name":"Constructing Multiscroll Memristive Neural Network With Local Activity Memristor and Application in Image Encryption.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tcyb.2024.3377011","authors":["Qiang Lai","Liang Yang","Genwen Hu","Zhi-Hong Guan","Herbert Ho-Ching Iu"],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1109/tcyb.2024.3377011","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1021/acsami.4c12956","name":"Modulation of Phase-Locking Characteristics of NbO<sub>x</sub> Memristor by Ag Doping.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.4c12956","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1021/acsami.4c12956","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1016/j.neunet.2024.106408","name":"Dynamics of heterogeneous Hopfield neural network with adaptive activation function based on memristor.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106408","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.neunet.2024.106408","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1016/j.neunet.2024.106545","name":"Input-to-state stability of delayed memristor-based inertial neural networks via non-reduced order method.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106545","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.neunet.2024.106545","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.3390/mi15121451","name":"Recent Advancements in 2D Material-Based Memristor Technology Toward Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/mi15121451","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3390/mi15121451","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1038/s43588-024-00744-y","name":"Deep Bayesian active learning using in-memory computing hardware.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s43588-024-00744-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s43588-024-00744-y","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acs.jpclett.4c02548","name":"Synaptic Properties of an Interfacial Memristor Based on a Ga<sub>2</sub>O<sub>3</sub>/Nb:SrTiO<sub>3</sub> Heterojunction.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.jpclett.4c02548","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1021/acs.jpclett.4c02548","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1021/acsomega.4c09401","name":"Light-Mediated Multilevel Neuromorphic Switching in a Hybrid Organic-Inorganic Memristor.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsomega.4c09401","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1021/acsomega.4c09401","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1007/s11571-024-10165-2","name":"Stability of synchronization manifolds and its nonlinear behaviour in memristive coupled discrete neuron model.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-024-10165-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1007/s11571-024-10165-2","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1038/s41467-024-51093-3","name":"Single neuromorphic memristor closely emulates multiple synaptic mechanisms for energy efficient neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-024-51093-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41467-024-51093-3","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1038/s41598-025-93423-5","name":"A keyword-based approach to analyzing scientific research trends: ReRAM present and future.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-93423-5","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-93423-5","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1038/s41598-024-73839-1","name":"Resilience evaluation of memristor based PUF against machine learning attacks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-024-73839-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41598-024-73839-1","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.1016/j.isci.2025.112596","name":"Improved all photonics diffraction neural network based on multi-channel integrated optical fibers.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.isci.2025.112596","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.isci.2025.112596","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1038/s41467-025-60970-4","name":"Self-rectifying memristors with high rectification ratio for attack-resilient autonomous driving systems.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-60970-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-60970-4","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.3390/s25113388","name":"Analysis of a Novel Amplitude-Controlled Memristive Hyperchaotic Map and Its Utilization in Image Encryption.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/s25113388","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/s25113388","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1007/s11571-024-10133-w","name":"Memristive leaky integrate-and-fire neuron and learnable straight-through estimator in spiking neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-024-10133-w","authors":["Tao Chen","Chunyan She","Lidan Wang","Shukai Duan"],"tags":["Spiking neural network","Computer science","Neuromorphic engineering","Benchmark (surveying)","Estimator"],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1007/s11571-024-10133-w","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"doi:10.3390/nano15010075","name":"Nanoscale Titanium Oxide Memristive Structures for Neuromorphic Applications: Atomic Force Anodization Techniques, Modeling, Chemical Composition, and Resistive Switching Properties.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/nano15010075","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/nano15010075","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.3390/nano14171412","name":"Audio Signal-Stimulated Multilayered HfO<sub>x</sub>/TiO<sub>y</sub> Spiking Neuron Network for Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/nano14171412","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3390/nano14171412","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1109/tnnls.2022.3231298","name":"Coupled Memristor Oscillators for Neuromorphic Locomotion Control: Modeling and Analysis.","source":"europepmc","abstract":"","url":"https://doi.org/10.1109/tnnls.2022.3231298","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1109/tnnls.2022.3231298","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1002/advs.202403150","name":"Optical-Electrical Coordinately Modulated Memristor Based on 2D Ferroelectric RP Perovskite for Artificial Vision Applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202403150","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1002/advs.202403150","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.3390/mi15020253","name":"A Compact Memristor Model Based on Physics-Informed Neural Networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/mi15020253","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3390/mi15020253","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.1038/s41467-025-60854-7","name":"All-printed chip-less wearable neuromorphic system for multimodal physicochemical health monitoring.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-60854-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-60854-7","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1002/adma.202417793","name":"A Multimodal Humidity Adaptive Optical Neuron Based on a MoWS&lt;sub&gt;2&lt;/sub&gt;/VO&lt;sub&gt;x&lt;/sub&gt; Heterojunction for Vision and Respiratory Functions.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202417793","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/adma.202417793","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1063/5.0233031","name":"Enhanced analog switching and neuromorphic performance of ZnO-based memristors with indium tin oxide electrodes for high-accuracy pattern recognition.","source":"europepmc","abstract":"","url":"https://doi.org/10.1063/5.0233031","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1063/5.0233031","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1016/j.neunet.2024.106355","name":"Threshold learning algorithm for memristive neural network with binary switching behavior.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106355","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.neunet.2024.106355","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1002/adma.202414430","name":"Modulating Trapping in Low-Dimensional Lead-Tin Halides for Energy-Efficient Neuromorphic Electronics.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202414430","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/adma.202414430","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1021/acsnano.4c06942","name":"Memristive Architectures Exploiting Self-Compliance Multilevel Implementation on 1 kb Crossbar Arrays for Online and Offline Learning Neuromorphic Applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.4c06942","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1021/acsnano.4c06942","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1038/s44172-024-00315-z","name":"Stress-induced artificial neuron spiking in diffusive memristors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s44172-024-00315-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s44172-024-00315-z","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1007/s11571-024-10178-x","name":"Collective behavior of an adapting synapse-based neuronal network with memristive effect and randomness.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-024-10178-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1007/s11571-024-10178-x","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1088/1361-6528/ad750a","name":"A linear compensation method for inference accuracy improvement of memristive in-memory computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1088/1361-6528/ad750a","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1088/1361-6528/ad750a","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1038/s41467-025-61536-0","name":"PZT optical memristors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-61536-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-61536-0","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.020Z"},{"id":"doi:10.1002/advs.202416305","name":"Residual Stresses and Micro-voids Propel Metal Diffusion for Filament-Based Memristors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202416305","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/advs.202416305","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1016/j.neunet.2024.106402","name":"Sliding mode control for uncertain fractional-order reaction-diffusion memristor neural networks with time delays.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106402","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.neunet.2024.106402","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1007/s40820-024-01550-x","name":"Recent Advances in Artificial Sensory Neurons: Biological Fundamentals, Devices, Applications, and Challenges.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s40820-024-01550-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1007/s40820-024-01550-x","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.3390/mi15030390","name":"A Phase Model of the Bio-Inspired NbOx Local Active Memristor under Weak Coupling Conditions.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/mi15030390","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3390/mi15030390","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.3390/nano14231884","name":"High-Performance Memristive Synapse Based on Space-Charge-Limited Conduction in LiNbO<sub>3</sub>.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/nano14231884","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3390/nano14231884","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.1002/anie.202413311","name":"Dual Redox-active Covalent Organic Framework-based Memristors for Highly-efficient Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/anie.202413311","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1002/anie.202413311","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1126/sciadv.adr5337","name":"Ultralow-pressure mechanical-motion switching of ferroelectric polarization.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.adr5337","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1126/sciadv.adr5337","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1088/1361-6528/ad857f","name":"Artificial synapses based on HfO<i><sub>x</sub></i>/TiO<i><sub>y</sub></i>memristor devices for neuromorphic applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1088/1361-6528/ad857f","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1088/1361-6528/ad857f","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1016/j.neunet.2024.106268","name":"Memristor-based circuit design of episodic memory neural network and its application in hurricane category prediction.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106268","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.neunet.2024.106268","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.3390/jfb15080214","name":"Recent Progress in Artificial Neurons for Neuromodulation.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/jfb15080214","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3390/jfb15080214","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1007/s11571-024-10069-1","name":"Enhancing in-situ updates of quantized memristor neural networks: a Siamese network learning approach.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-024-10069-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1007/s11571-024-10069-1","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1038/s41467-024-51609-x","name":"Crossmodal sensory neurons based on high-performance flexible memristors for human-machine in-sensor computing system.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-024-51609-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41467-024-51609-x","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1002/advs.202402582","name":"A Human-Computer Interaction Strategy for An FPGA Platform Boosted Integrated \"Perception-Memory\" System Based on Electronic Tattoos and Memristors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202402582","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1002/advs.202402582","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.1038/s41467-025-56254-6","name":"Efficient nonlinear function approximation in analog resistive crossbars for recurrent neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-56254-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-56254-6","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1016/j.neunet.2024.106412","name":"Heterogeneous coexisting attractors, large-scale amplitude control and finite-time synchronization of central cyclic memristive neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106412","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.neunet.2024.106412","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1002/advs.202402667","name":"The 3D Monolithically Integrated Hardware Based Neural System with Enhanced Memory Window of the Volatile and Non-Volatile Devices.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202402667","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1002/advs.202402667","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.3390/nano15090659","name":"Scindapsus Aureus Resistive Random-Access Memory with Synaptic Plasticity and Sound Localization Function.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/nano15090659","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/nano15090659","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1038/s41467-025-56393-w","name":"Mechano-gated iontronic piezomemristor for temporal-tactile neuromorphic plasticity.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-56393-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-56393-w","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1126/sciadv.adp7613","name":"Single-trial detection of auditory cues from the rat brain using memristors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.adp7613","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1126/sciadv.adp7613","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1021/acsami.4c15598","name":"Enhancing Uniformity, Read Voltage Margin, and Retention in Three-Dimensional and Self-Rectifying Vertical Pt/Ta<sub>2</sub>O<sub>5</sub>/Al<sub>2</sub>O<sub>3</sub>/TiN Memristors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.4c15598","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1021/acsami.4c15598","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1021/acs.jpclett.4c00945","name":"Capacitive and Inductive Characteristics of Volatile Perovskite Resistive Switching Devices with Analog Memory.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.jpclett.4c00945","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1021/acs.jpclett.4c00945","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1038/s41467-024-44766-6","name":"Powering AI at the edge: A robust, memristor-based binarized neural network with near-memory computing and miniaturized solar cell.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-024-44766-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41467-024-44766-6","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1016/j.neunet.2024.106279","name":"Observer-based resilient dissipativity control for discrete-time memristor-based neural networks with unbounded or bounded time-varying delays.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106279","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1016/j.neunet.2024.106279","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1039/d3mh01950k","name":"Affective computing for human-machine interaction <i>via</i> a bionic organic memristor exhibiting selective <i>in situ</i> activation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d3mh01950k","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1039/d3mh01950k","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1021/acsami.4c05112","name":"An Artificial Universal Tactile Nociceptor Based on 2D Polymer Film Memristor Arrays with Tunable Resistance Switching Behaviors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsami.4c05112","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1021/acsami.4c05112","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1088/1361-6528/ad3c4b","name":"Mott memristor based stochastic neurons for probabilistic computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1088/1361-6528/ad3c4b","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1088/1361-6528/ad3c4b","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1126/sciadv.adt3068","name":"Self-powered artificial vibrissal system with anemotaxis behavior.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.adt3068","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1126/sciadv.adt3068","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1039/d4nh00421c","name":"A stochastic photo-responsive memristive neuron for an in-sensor visual system based on a restricted Boltzmann machine.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d4nh00421c","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1039/d4nh00421c","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1126/sciadv.adp3710","name":"Adapting magnetoresistive memory devices for accurate and on-chip-training-free in-memory computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.adp3710","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1126/sciadv.adp3710","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1002/advs.202408648","name":"Energy Efficient Memristor Based on Green-Synthesized 2D Carbonyl-Decorated Organic Polymer and Application in Image Denoising and Edge Detection: Toward Sustainable AI.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202408648","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1002/advs.202408648","addedAt":"2026-09-01T01:48:32.530Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1021/acsnano.3c10559","name":"Oscillatory Neural Network-Based Ising Machine Using 2D Memristors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.3c10559","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1021/acsnano.3c10559","addedAt":"2026-09-01T01:48:32.531Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1038/s41467-025-61576-6","name":"A neuromorphic processor with on-chip learning for beyond-CMOS device integration.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-61576-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-61576-6","addedAt":"2026-09-01T01:48:32.531Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.3390/nano14231864","name":"TCAD Simulation of Resistive Switching Devices: Impact of ReRAM Configuration on Neuromorphic Computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/nano14231864","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3390/nano14231864","addedAt":"2026-09-01T01:48:32.531Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1038/s41467-025-56319-6","name":"Layer ensemble averaging for fault tolerance in memristive neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-56319-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-56319-6","addedAt":"2026-09-01T01:48:32.531Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1039/d3nr06521a","name":"Human somatosensory systems based on sensor-memory-integrated technology.","source":"europepmc","abstract":"","url":"https://doi.org/10.1039/d3nr06521a","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1039/d3nr06521a","addedAt":"2026-09-01T01:48:32.531Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1038/s41377-024-01516-z","name":"Towards mixed physical node reservoir computing: light-emitting synaptic reservoir system with dual photoelectric output.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41377-024-01516-z","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41377-024-01516-z","addedAt":"2026-09-01T01:48:32.531Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1021/acs.nanolett.4c02470","name":"Electronically Reconfigurable Memristive Neuron Capable of Operating in Both Excitation and Inhibition Modes.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.4c02470","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1021/acs.nanolett.4c02470","addedAt":"2026-09-01T01:48:32.531Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1038/s41598-024-58947-2","name":"Enhanced read resolution in reconfigurable memristive synapses for Spiking Neural Networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-024-58947-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41598-024-58947-2","addedAt":"2026-09-01T01:48:32.531Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.3390/mi15020217","name":"MARR-GAN: Memristive Attention Recurrent Residual Generative Adversarial Network for Raindrop Removal.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/mi15020217","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.3390/mi15020217","addedAt":"2026-09-01T01:48:32.531Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.1038/s44172-025-00360-2","name":"The logarithmic memristor-based Bayesian machine.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s44172-025-00360-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s44172-025-00360-2","addedAt":"2026-09-01T01:48:32.531Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1038/s41598-025-19408-6","name":"Research on parallel computing of the olfactory neural network based on multithreading.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-19408-6","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-19408-6","addedAt":"2026-09-01T01:48:32.531Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1073/pnas.2320242121","name":"Brain-inspired computing with fluidic iontronic nanochannels.","source":"europepmc","abstract":"","url":"https://doi.org/10.1073/pnas.2320242121","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1073/pnas.2320242121","addedAt":"2026-09-01T01:48:32.531Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1021/jacs.4c01218","name":"Single-Pore Nanofluidic Logic Memristor with Reconfigurable Synaptic Functions and Designable Combinations.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/jacs.4c01218","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1021/jacs.4c01218","addedAt":"2026-09-01T01:48:32.531Z","updatedAt":"2026-09-01T01:48:33.837Z"},{"id":"doi:10.1109/ijcnn.2006.246864","name":"Comparison of Artificial Neural Network Architectures and Training Algorithms for Solving the Knight's Tours","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.246864","authors":["R.G. Escalante","H.A. Malki"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T15:34:22Z","doi":"10.1109/ijcnn.2006.246864","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/ijcnn.2006.1716157","name":"A Fully CMOS Low-Cost Chaotic Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.1716157","authors":["J.L. Rossello","S. Bota","V. Canals","I. de Paul","J. Segura"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-30T17:35:23Z","doi":"10.1109/ijcnn.2006.1716157","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1088/0954-898x_4_4_005","name":"Pruning Divide &amp; Conquer networks","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_4_4_005","authors":["Steve G Romaniuk"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T16:04:19Z","doi":"10.1088/0954-898x_4_4_005","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.14311/nnw.2011.21.001","name":"AN IMPROVED E-MODEL USING ARTIFICIAL NEURAL NETWORK VoIP QUALITY PREDICTOR","source":"crossref","abstract":"","url":"https://doi.org/10.14311/nnw.2011.21.001","authors":["Mousa Al-Akhras","Iman Almomani","Azzam Sleit"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-10-17T08:37:18Z","doi":"10.14311/nnw.2011.21.001","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1088/0954-898x_8_4_005","name":"Generalisation and discrimination emerge from a self-organising componential network: a speech example","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_8_4_005","authors":["Chris J S Webber"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:51Z","doi":"10.1088/0954-898x_8_4_005","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/ijcnn.2006.246684","name":"Qubit Inspired Neural Network towards Its Practical Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.246684","authors":["K. Mori","T. Isokawa","N. Kouda","N. Matsui","H. Nishimura"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T15:27:21Z","doi":"10.1109/ijcnn.2006.246684","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/neurel.2000.902397","name":"A neural network FPGA implementation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/neurel.2000.902397","authors":["S. Coric","I. Latinovic","A. Pavasovic"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-11-11T09:58:51Z","doi":"10.1109/neurel.2000.902397","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.23919/iccas.2017.8204323","name":"Robust neural network control of neural synchronization in the mutually coupled network","source":"crossref","abstract":"","url":"https://doi.org/10.23919/iccas.2017.8204323","authors":["Jung E. Son","Seo Young Nam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-12-14T17:13:46Z","doi":"10.23919/iccas.2017.8204323","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/icnn.1995.487356","name":"A modular design of fuzzy neural network with application to telecommunication network management control","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnn.1995.487356","authors":["Lin Yu Tseng","Tzu Han Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-11-19T13:30:57Z","doi":"10.1109/icnn.1995.487356","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.59188/eduvest.v2i8.514","name":"Covid-19 Sentiment Analysis Using Convolutional Neural Network / Reccurent Neural Network Method","source":"crossref","abstract":"Social media is a very important tool in this modern era , one of which is namely twitter. Twitter allows user for give opinion / opinion to various issues and topics hot / viral trending . Trending on twitter is so so fast in the process of spreading so that Twitter becomes a medium of information that often become a media issue conspiracy . Covid-19 is a moderate epidemic / disease _ experienced the whole world when this . Issues circulating in the population , they believe that Covid-19 is a real pandemic and a conspiracy , issue this make population confused differentiate Among second issue that . Because of that required a fast and accurate analysis _ for produce valid results , that Covid-19 a real thing _ or conspiracy seen from opinion population and corner views written on Twitter. CNN/RNN or combined from RNN(LSTM) and CNN methods are method used _ for classify opinion population about Covid-19 issues . Study this also done with compare is correct RNN/CNN accuracy same like deep RNN even more fast for in the process . Research results state that accuracy from combined RNN/CNN no different remote , even RNN/CNN in the process more fast than deep RNNs. Research results about opinion / opinion residents on twitter who believe about Covid-19 is conspiracy more low than residents who have confidence about Covid-19 is something the real thing . Percentage classification opinion / opinion from sentiment positive by 63.15% and opinion / opinion sentiment negative by 28.60%, this is results calculation use RNN/CNN method , with accuracy reached 58%. Accuracy from method used _ make Covid-19 issues that exist in the population no Becomes hoax news so population more alert against the ongoing Covid-19 pandemic happen.","url":"https://doi.org/10.59188/eduvest.v2i8.514","authors":["Ravensca Matatula","Danny Manongga","Hendry Hendry"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-06T04:33:58Z","doi":"10.59188/eduvest.v2i8.514","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.14311/nnw.2014.24.008","name":"MASS LOSS PREDICTION OF NEWLY DEVELOPED ALUMINIUM-BASED ALLOYS USING ARTIFICIAL NEURAL NETWORK","source":"crossref","abstract":"","url":"https://doi.org/10.14311/nnw.2014.24.008","authors":["T. Ramesh Kumar","I. Rajendran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-05-06T08:40:22Z","doi":"10.14311/nnw.2014.24.008","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.15388/namc.2026.31.45269","name":"Finite-time matrix projective synchronization of fractional-order memristor-based delayed neural networks with parameter uncertainty","source":"crossref","abstract":"This research examines the phenomenon of finite-time matrix projective synchronization (FTMPS) in the context of two distinct fractional-order memristor-based delayed neural networks (FOMDNNs). For the FOMDNNs with indeterminate parameters, some suitable controllers are structured, and sufficient conditions for implementing the FTMPS are demonstrated through some inequality techniques and relevant lemmas pertaining to fractional calculus. The synchronization issues under two different norm cases are fully considered. Subsequently, two numerical examples of the FTMPS are revealed and the discrepancies in their synchronization gradually tend to zero, which shows the validity and accuracy of the obtained synchronization results.","url":"https://doi.org/10.15388/namc.2026.31.45269","authors":["Shangbin Xu","Bo Hu","Hai Zhang","Xinbin Chen","Jinde Cao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-07T16:59:15Z","doi":"10.15388/namc.2026.31.45269","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/aicas59952.2024.10595966","name":"Dynamic Detection and Mitigation of Read-disturb for Accurate Memristor-based Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aicas59952.2024.10595966","authors":["Sumit Diware","Mohammad Amin Yaldagard","Anteneh Gebregiorgis","Rajiv V. Joshi","Said Hamdioui","Rajendra Bishnoi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-19T17:30:48Z","doi":"10.1109/aicas59952.2024.10595966","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1186/s12859-022-04798-5","name":"DeepPN: a deep parallel neural network based on convolutional neural network and graph convolutional network for predicting RNA-protein binding sites","source":"crossref","abstract":"Abstract Background Addressing the laborious nature of traditional biological experiments by using an efficient computational approach to analyze RNA-binding proteins (RBPs) binding sites has always been a challenging task. RBPs play a vital role in post-transcriptional control. Identification of RBPs binding sites is a key step for the anatomy of the essential mechanism of gene regulation by controlling splicing, stability, localization and translation. Traditional methods for detecting RBPs binding sites are time-consuming and computationally-intensive. Recently, the computational method has been incorporated in researches of RBPs. Nevertheless, lots of them not only rely on the sequence data of RNA but also need additional data, for example the secondary structural data of RNA, to improve the performance of prediction, which needs the pre-work to prepare the learnable representation of structural data. Results To reduce the dependency of those pre-work, in this paper, we introduce DeepPN, a deep parallel neural network that is constructed with a convolutional neural network (CNN) and graph convolutional network (GCN) for detecting RBPs binding sites. It includes a two-layer CNN and GCN in parallel to extract the hidden features, followed by a fully connected layer to make the prediction. DeepPN discriminates the RBP binding sites on learnable representation of RNA sequences, which only uses the sequence data without using other data, for example the secondary or tertiary structure data of RNA. DeepPN is evaluated on 24 datasets of RBPs binding sites with other state-of-the-art methods. The results show that the performance of DeepPN is comparable to the published methods. Conclusion The experimental results show that DeepPN can effectively capture potential hidden features in RBPs and use these features for effective prediction of binding sites.","url":"https://doi.org/10.1186/s12859-022-04798-5","authors":["Jidong Zhang","Bo Liu","Zhihan Wang","Klaus Lehnert","Mark Gahegan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-29T04:03:13Z","doi":"10.1186/s12859-022-04798-5","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1101/842369","name":"Neural Gene Network Constructor: A Neural Based Model for Reconstructing Gene Regulatory Network","source":"crossref","abstract":"Summary Reconstructing gene regulatory networks (GRNs) and inferring the gene dynamics are important to understand the behavior and the fate of the normal and abnormal cells. Gene regulatory networks could be reconstructed by experimental methods or from gene expression data. Recent advances in Single Cell RNA sequencing technology and the computational method to reconstruct trajectory have generated huge scRNA-seq data tagged with additional time labels. Here, we present a deep learning model “Neural Gene Network Constructor” (NGNC), for inferring gene regulatory network and reconstructing the gene dynamics simultaneously from time series gene expression data. NGNC is a model-free heterogenous model, which can reconstruct any network structure and non-linear dynamics. It consists of two parts: a network generator which incorporating gumbel softmax technique to generate candidate network structure, and a dynamics learner which adopting multiple feedforward neural networks to predict the dynamics. We compare our model with other well-known frameworks on the data set generated by GeneNetWeaver, and achieve the state of the arts results both on network reconstruction and dynamics learning.","url":"https://doi.org/10.1101/842369","authors":["Zhang Zhang","Lifei Wang","Shuo Wang","Ruyi Tao","Jingshu Xiao","Muyun Mou","Jun Cai","Jiang Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-11-15T01:05:43Z","doi":"10.1101/842369","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1088/0954-898x/1/2/007","name":"Cortex, spikes and waves: the silent areas revisited","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/1/2/007","authors":["Hilton Stowell"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-26T15:51:19Z","doi":"10.1088/0954-898x/1/2/007","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1088/0954-898x/6/3/012","name":"Reply to Pearlmutter's comments on Tsai et al","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/6/3/012","authors":["Thomas Brown"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-24T22:35:54Z","doi":"10.1088/0954-898x/6/3/012","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1201/9781420093339-c2","name":"Neural Network Approaches for Defect Detection in Composite Materials","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781420093339-c2","authors":["T D‚ÄôOrazio","M Leo","C Guaragnella"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-04-15T18:39:16Z","doi":"10.1201/9781420093339-c2","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1088/0954-898x_8_4_003","name":"Dynamics of a recurrent network of spiking neurons before and following learning","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_8_4_003","authors":["Daniel J Amit","Nicolas Brunel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:05:01Z","doi":"10.1088/0954-898x_8_4_003","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1088/0954-898x/8/4/006","name":"Unsupervised discovery of invariances","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/8/4/006","authors":["Stephen Eglen","Alistair Bray","Jim Stone"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/8/4/006","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/ijcnn.2006.247223","name":"A Two-Phase Genetic Local Search Algorithm for Feedforward Neural Network Training","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.247223","authors":["Lin-Yu Tseng","Wen-Ching Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T15:34:22Z","doi":"10.1109/ijcnn.2006.247223","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/nnat.1993.586061","name":"Development Of A Neural Network Model Based Controller For A Non-linear Process Application","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nnat.1993.586061","authors":["J.B. Gomm","J.T. Evans","D. Williams","P.J.G. Lisboa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-08-24T16:29:31Z","doi":"10.1109/nnat.1993.586061","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1007/978-3-030-51882-0_5","name":"Generic and Practical Emulators for the Voltage-Controlled Memristor Models","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-51882-0_5","authors":["Abdullah G. Alharbi","Masud H. Chowdhury"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-01T19:06:16Z","doi":"10.1007/978-3-030-51882-0_5","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/neurel.2010.5644102","name":"Adaptive neural network workflow management for Utility Management Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/neurel.2010.5644102","authors":["Srdan Vukmirovic","Aleksandar Erdeljan","Lendak Imre","Darko Capko","Nemanja Nedic"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-12-09T15:34:50Z","doi":"10.1109/neurel.2010.5644102","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.33395/sinkron.v8i1.11944","name":"Comparison of Convolutional Neural Network and Artificial Neural Network for Rice Detection","source":"crossref","abstract":"Rice is a staple food for people in tropical countries. Indonesia is a country that needs a lot of rice for its people in providing food. This country has implemented various ways to plant rice properly. Many agricultural fields have implemented harvests up to three times a year, due to the role of technology which has helped a lot in agriculture. Planting to harvest already uses advanced technology and tools. A good rice harvest can improve the welfare of the surrounding community. Meanwhile with lots of rice products because many rice plants produce with lots of rice. The type of rice from different regions of origin, the yield of rice is also different from other regions of origin. But with advances in technology, it is possible to plant rice whose types of plants come from other regions. The rice sold to the public varies, so that people who are unfamiliar with the types of rice find it difficult to detect the types of rice. Machine learning is present in detecting various kinds of rice. Machine learning, especially deep learning can make better detection, because one of the deep learning methods works similar to the human brain. In the human brain there are millions or even billions of neurons. This research uses neural networks in experiments using public datasets. Experiments using Artificial Neural Networks achieve an training accuracy of 98.2%, loss: 0.2351. It takes about 10 minutes of training. Testing accuracy reaches accuracy: 96%, loss: 0.6641. By conducting experiments using the Convolution Neural Network, it achieves an accuracy of 99.3% and the training time requires around 18 hours. The purpose of this research is to classify the rice image dataset and detect the rice image.","url":"https://doi.org/10.33395/sinkron.v8i1.11944","authors":["Endang Suherman","Djarot Hindarto","Amelia Makmur","Handri Santoso"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-17T16:24:46Z","doi":"10.33395/sinkron.v8i1.11944","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.36418/eduvest.v2i8.514","name":"Covid-19 Sentiment Analysis Using Convolutional Neural Network / Reccurent Neural Network Method","source":"crossref","abstract":"Social media is a very important tool in this modern era , one of which is namely twitter. Twitter allows user for give opinion / opinion to various issues and topics hot / viral trending . Trending on twitter is so so fast in the process of spreading so that Twitter becomes a medium of information that often become a media issue conspiracy . Covid-19 is a moderate epidemic / disease _ experienced the whole world when this . Issues circulating in the population , they believe that Covid-19 is a real pandemic and a conspiracy , issue this make population confused differentiate Among second issue that . Because of that required a fast and accurate analysis _ for produce valid results , that Covid-19 a real thing _ or conspiracy seen from opinion population and corner views written on Twitter. CNN/RNN or combined from RNN(LSTM) and CNN methods are method used _ for classify opinion population about Covid-19 issues . Study this also done with compare is correct RNN/CNN accuracy same like deep RNN even more fast for in the process . Research results state that accuracy from combined RNN/CNN no different remote , even RNN/CNN in the process more fast than deep RNNs. Research results about opinion / opinion residents on twitter who believe about Covid-19 is conspiracy more low than residents who have confidence about Covid-19 is something the real thing . Percentage classification opinion / opinion from sentiment positive by 63.15% and opinion / opinion sentiment negative by 28.60%, this is results calculation use RNN/CNN method , with accuracy reached 58%. Accuracy from method used _ make Covid-19 issues that exist in the population no Becomes hoax news so population more alert against the ongoing Covid-19 pandemic happen.","url":"https://doi.org/10.36418/eduvest.v2i8.514","authors":["Ravensca Matatula","Danny Manongga","Hendry Hendry"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-21T04:28:18Z","doi":"10.36418/eduvest.v2i8.514","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/ijcnn.2006.1716579","name":"Incremental Gain Analysis of Chaotic Recurrent Neural Network and Applications in Pattern Association","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.1716579","authors":["Wu Yilei","Song Qing","Liu Sheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-30T17:35:23Z","doi":"10.1109/ijcnn.2006.1716579","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/ijcnn.2006.1716612","name":"Recurrent Neural Network Based Gating for Natural Gas Load Prediction System","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.1716612","authors":["P. Musilek","E. Pelikan","T. Brabec","M. Simunek"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-30T17:35:23Z","doi":"10.1109/ijcnn.2006.1716612","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1016/b978-0-12-815254-6.00014-9","name":"Neural Network Black Box Modeling of Nonlinear Dynamical Systems: Aircraft Controlled Motion","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-12-815254-6.00014-9","authors":["Yury V. Tiumentsev","Mikhail V. Egorchev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-06-21T11:36:07Z","doi":"10.1016/b978-0-12-815254-6.00014-9","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1007/978-3-319-76375-0_31","name":"Behavior of Multiple Memristor Circuits","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-76375-0_31","authors":["Ram Kaji Budhathoki","Maheshwar Pd. Sah","Shyam Prasad Adhikari","Hyongsuk Kim","Leon Chua"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-11-12T17:03:43Z","doi":"10.1007/978-3-319-76375-0_31","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.5772/intechopen.97808","name":"Functional Capabilities of Coupled Memristor-Based Reactance-Less Oscillators","source":"crossref","abstract":"New functionalities of reactance-less memristor based oscillators are discussed which arise when two elementary oscillators are connected. It is shown that the system of coupled memristor based oscillators can be used for converting analog and analog-digital signals into binary pulse sequences. The approach to control the thresholds in memristor based oscillators is discussed. Standard control approach in memristor based oscillators is the exploitation of input signal to drive the rate of change in the state of the memristor. In contrast, the main idea of the considered controlling approach is to send the input signal not directly to the memristor device but to the comparator circuit and as result to control oscillator circuit behavior by change of interval of memristor resistor variation. The capabilities of coupled memristor based oscillators with control thresholds are sufficient for constructing the simple circuit elements of oscillatory computing architectures.","url":"https://doi.org/10.5772/intechopen.97808","authors":["Vladimir V. Rakitin","Sergey G. Rusakov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-05-28T08:19:49Z","doi":"10.5772/intechopen.97808","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1088/0954-898x/8/3/001","name":"Hebbian learning, its correlation catastrophe, and unlearning","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/8/3/001","authors":["J van Hemmen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-09-18T03:15:26Z","doi":"10.1088/0954-898x/8/3/001","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.14311/nnw.2014.24.034","name":"HYBRID NEURAL NETWORK-PARTICLE SWARM ALGORITHM TO DESCRIBE CHAOTIC TIME SERIES","source":"crossref","abstract":"","url":"https://doi.org/10.14311/nnw.2014.24.034","authors":["Juan A. Lazzús","Ignacio Salfate","Sonia Montecinos"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-01-22T04:02:26Z","doi":"10.14311/nnw.2014.24.034","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/tii.2026.3689313","name":"Memristor-Based Immune Neural Network Circuit With Neuromorphic Learning and Self-Repairing and its Application in Industrial Fault Diagnosis","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tii.2026.3689313","authors":["Kefan Tao","Yanfeng Wang","Junwei Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-13T19:53:30Z","doi":"10.1109/tii.2026.3689313","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1016/b978-0-12-815651-3.00003-1","name":"Methods for the selection of parameters and structure of the neural network model","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-12-815651-3.00003-1","authors":["Dmitriy Tarkhov","Alexander Vasilyev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-11-29T11:14:11Z","doi":"10.1016/b978-0-12-815651-3.00003-1","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/rissp.2003.1285766","name":"A new neural network-intelligence increasing neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/rissp.2003.1285766","authors":["Ni Zheng","Su Guang-da","Wang Jun-yan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2004-07-08T20:06:22Z","doi":"10.1109/rissp.2003.1285766","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.4018/978-1-6684-2408-7.ch065","name":"Artificial Neural Network for Pre-Simulation Training of Air Traffic Controller","source":"crossref","abstract":"In this chapter, the four layers neural network model for evaluating correctness and timeliness of decision making by the specialist of air traffic services during the pre-simulation training has been presented. The first layer (input) includes exercises that cadet/listener performs to solve a potential conflict situation; the second layer (hidden) depends physiological characteristics of cadet/listener; the third layer (hidden) takes into account the complexity of the exercise depending on the number of potential conflict situations; the fourth layer (output) is assessment of cadet/listener during performance of exercise. Neural network model also has additional inputs (bias) that including restrictions on calculating parameters. The program “Fusion” of visualization of the state of execution of an exercise by a cadet/listener has been developed. Three types of simulation training exercises for CTR (control zone), TMA (terminal control area), and CTA (control area) with different complexity have been analyzed.","url":"https://doi.org/10.4018/978-1-6684-2408-7.ch065","authors":["Tetiana Shmelova","Yuliya Sikirda","Togrul Rauf Oglu Jafarzade"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-17T11:47:50Z","doi":"10.4018/978-1-6684-2408-7.ch065","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1002/mma.10574","name":"Stability analysis of stochastic Lyapunov functions: Applications to memristor neural networks","source":"crossref","abstract":"This paper investigates the mean square exponential stability of stochastic neural networks relying on memristor with leakage delay with different types of activation functions. To this aim, we introduce a new suitable stochastic Lyapunov‐Krasovskii functional (SLKF) and employ Filippov solutions to derive stability criteria using It 's formula. We encounter with a nonlinear matrix inequality which should be converted to a linear matrix inequality (LMI) problem by using Schur complement lemma. The proposed problem is handled by using the CVX toolbox in MATLAB software. In the numerical examples section, we bring two examples related to two‐ and three‐dimentional memristor‐based neural networks whose coefficients satisfy in the Schur complement lemma. The figures show that the employed stochastic Lyapunov functions can capture the exponential stability conditions.","url":"https://doi.org/10.1002/mma.10574","authors":["Vaz'he Rahimi","Davood Ahmadian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-09T05:11:04Z","doi":"10.1002/mma.10574","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/asicon52560.2021.9620330","name":"Training, Programming, and Correction Techniques of Memristor-Crossbar Neural Networks with Non-Ideal Effects such as Defects, Variation, and Parasitic Resistance","source":"crossref","abstract":"","url":"https://doi.org/10.1109/asicon52560.2021.9620330","authors":["Tien Van Nguyen","Jiyong An","Seokjin Oh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-12-01T20:53:36Z","doi":"10.1109/asicon52560.2021.9620330","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.3788/irla20230667","name":"忆阻神经网络自适应滑模控制及其应用","source":"crossref","abstract":"","url":"https://doi.org/10.3788/irla20230667","authors":["林俤 LIN Di","吴易明 WU Yiming","杨森 YANG Sen","张垠 ZHANG Yin","赵铭姝 ZHAO Mingshu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T08:00:42Z","doi":"10.3788/irla20230667","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1088/0954-898x/10/1/003","name":"Do cortical maps adapt to optimize information density?","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/10/1/003","authors":["M Plumbley"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-24T22:35:54Z","doi":"10.1088/0954-898x/10/1/003","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1088/0954-898x_13_3_301","name":"Neuroanatomical algorithms for dendritic modelling","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_13_3_301","authors":["Giorgio A Ascoli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T16:03:55Z","doi":"10.1088/0954-898x_13_3_301","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.21741/9781644903131-251","name":"Comparative study of artificial neural network and physics-informed neural network application in sheet metal forming","source":"crossref","abstract":"Abstract. Accurate prediction of the resultant geometry in sheet metal forming simulation is necessary to achieve zero-defect production. To quantify the effect of process parameters on the final geometry, numerical methods are used to simulate the process outputs for a given set of process variables. Finite element methods are employed in process optimization and design exploration. However, these computationally expensive models are unhelpful for process control applications. Surrogate models allowing fast prediction of resultant geometry or stress distribution can be plausible solutions. In the current study, we propose a sequential surrogate model to fit the stress field as a function of the process variable and the initial spatial coordinates. The framework is composed of two surrogate models. First, an artificial neural network (ANN) evaluates the displacement and the strain. Then, a second surrogate is employed to fit the stress using input strain and displacement. Here, ANN and physics-informed neural networks (PINN) are compared concerning prediction accuracy for the second surrogate model. The PINN is enhanced with the equilibrium equations. The developed method is demonstrated using a v-bending process. The results show that both surrogate models return good approximations, with ANN showing slightly better results.","url":"https://doi.org/10.21741/9781644903131-251","authors":["Francesco MUNZONE"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-19T16:10:26Z","doi":"10.21741/9781644903131-251","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1080/net.12.1.33.46","name":"Global dynamics of a network of stochastic neurons maximizes local mutual information","source":"crossref","abstract":"","url":"https://doi.org/10.1080/net.12.1.33.46","authors":["F.B. Rodrguez","R. Huerta","V. Lpez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-12-08T20:33:27Z","doi":"10.1080/net.12.1.33.46","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.15388/namc.2020.25.20557","name":"A switching control for finite-time synchronization of memristor-based BAM neural networks with stochastic disturbances","source":"crossref","abstract":"This paper deals with the finite-time stochastic synchronization for a class of memristorbased bidirectional associative memory neural networks (MBAMNNs) with time-varying delays and stochastic disturbances. Firstly, based on the physical property of memristor and the circuit of MBAMNNs, a MBAMNNs model with more reasonable switching conditions is established. Then, based on the theory of Filippov’s solution, by using Lyapunov–Krasovskii functionals and stochastic analysis technique, a sufficient condition is given to ensure the finite-time stochastic synchronization of MBAMNNs with a certain controller. Next, by a further discussion, an errordependent switching controller is given to shorten the stochastic settling time. Finally, numerical simulations are carried out to illustrate the effectiveness of theoretical results.","url":"https://doi.org/10.15388/namc.2020.25.20557","authors":["Liangchen Li","Rui Xu","Qintao Gan","Jiazhe Lin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-11-01T08:05:47Z","doi":"10.15388/namc.2020.25.20557","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1088/0954-898x_3_1_006","name":"Connectionist technique for on-line parsing","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_3_1_006","authors":["Ronan Reilly"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:17Z","doi":"10.1088/0954-898x_3_1_006","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1016/0893-6080(89)90016-6","name":"Noise modulation of synaptic weights in a biological neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(89)90016-6","authors":["Daniel Gardner"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T05:05:53Z","doi":"10.1016/0893-6080(89)90016-6","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/ijcnn.2006.1716584","name":"Medical Image Segmentation using a Self-organizing Neural Network and Clifford Geometric Algebra","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.1716584","authors":["J. Rivera-Rovelo","E. Bayro-Corrochano"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-30T12:35:23Z","doi":"10.1109/ijcnn.2006.1716584","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1002/cem.70088/v1/decision1","name":"Decision letter for \"In-Situ Detection of Microplastic Particles on Food Using Hyperspectral Imaging with one-dimensional convolutional neural network (1D-CNN) and artificial neural network (ANN)\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/cem.70088/v1/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-23T21:04:57Z","doi":"10.1002/cem.70088/v1/decision1","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/ijcnn.2006.246651","name":"Implementing Synaptic Plasticity in a VLSI Spiking Neural Network Model","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.246651","authors":["J. Schemmel","A. Grubl","K. Meier","E. Mueller"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T15:27:21Z","doi":"10.1109/ijcnn.2006.246651","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/ijcnn.2006.247033","name":"Forecasting Time Series with a New Architecture for Polynomial Artificial Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.247033","authors":["A. Flores-Mendez","E. Gomez-Ramirez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T15:34:22Z","doi":"10.1109/ijcnn.2006.247033","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1088/0954-898x/7/2/001","name":"Using computation to help relate neurobiology and behaviour","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/7/2/001","authors":["J Movshon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-09-18T03:15:26Z","doi":"10.1088/0954-898x/7/2/001","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1088/0954-898x/2/2/001","name":"Minimum-entropy coding with Hopfield networks","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/2/2/001","authors":["H Hentschel","H Barlow"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-24T22:35:54Z","doi":"10.1088/0954-898x/2/2/001","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/ijcnn.2006.1716130","name":"Multilayer Neural Network based on Multi-Valued Neurons and the Blur Identification Problem","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.1716130","authors":["I. Aizenberg","D. Paliy","J.T. Astola"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-30T12:35:23Z","doi":"10.1109/ijcnn.2006.1716130","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1088/0954-898x/9/1/008","name":"Hebbian learning, its correlation catastrophe, and unlearning","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/9/1/008","authors":["J van Hemmen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/9/1/008","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/neurel.2004.1416590","name":"Power transformer differential protection scheme based on symmetrical component and artificial neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/neurel.2004.1416590","authors":["H. Khorashadi-Zadeh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-04-12T10:25:58Z","doi":"10.1109/neurel.2004.1416590","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1007/978-94-009-0643-3_10","name":"DNNA: A Digital Neural Network Architecture","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-94-009-0643-3_10","authors":["Max Stanford Tomlinson","Dennis J. Walker"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-12-09T03:06:39Z","doi":"10.1007/978-94-009-0643-3_10","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/neurel.2004.1416585","name":"Mechanism for automated neural network based transport system with learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/neurel.2004.1416585","authors":["T. Srinivasan","J.B.S. Jonathan","A. Chandrasekhar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-04-12T10:25:58Z","doi":"10.1109/neurel.2004.1416585","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1088/0954-898x/2/4/008","name":"A cell assembly model of language","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/2/4/008","authors":["Friedemann Pulvermüller","Hubert Preibl"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-24T22:35:54Z","doi":"10.1088/0954-898x/2/4/008","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1162/089976600300015538","name":"A Neural Network Architecture for Visual Selection","source":"crossref","abstract":"This article describes a parallel neural net architecture for efficient and robust visual selection in generic gray-level images. Objects are represented through flexible star-type planar arrangements of binary local features which are in turn star-type planar arrangements of oriented edges. Candidate locations are detected over a range of scales and other deformations, using a generalized Hough transform. The flexibility of the arrangements provides the required invariance. Training involves selecting a small number of stable local features from a predefined pool, which are well localized on registered examples of the object. Training therefore requires only small data sets. The parallel architecture is constructed so that the Hough transform associated with any object can be implemented without creating or modifying any connections. The different object representations are learned and stored in a central module. When one of these representations is evoked, it “primes” the appropriate layers in the network so that the corresponding Hough transform is computed. Analogies between the different layers in the network and those in the visual system are discussed. Furthermore, the model can be used to explain certain experiments on visual selection reported in the literature.","url":"https://doi.org/10.1162/089976600300015538","authors":["Yali Amit"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-27T11:57:56Z","doi":"10.1162/089976600300015538","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/neurel.2002.1057988","name":"Control for neural prostheses: neural networks for determining biological synergies","source":"crossref","abstract":"","url":"https://doi.org/10.1109/neurel.2002.1057988","authors":["P.B. Dejan","P.B. Mirjana"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-06-26T00:51:07Z","doi":"10.1109/neurel.2002.1057988","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/neurel.2010.5644110","name":"Automatic spleen segmentation in MRI images using a combined neural network and recursive watershed transform","source":"crossref","abstract":"","url":"https://doi.org/10.1109/neurel.2010.5644110","authors":["Alireza Behrad","Hassan Masoumi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-12-09T15:34:50Z","doi":"10.1109/neurel.2010.5644110","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.3109/0954898x.2011.638696","name":"Alzheimer’s disease","source":"crossref","abstract":"","url":"https://doi.org/10.3109/0954898x.2011.638696","authors":["Adam Gazzaley","Scott A. Small"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-04-30T12:15:08Z","doi":"10.3109/0954898x.2011.638696","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/ijcnn.1991.155142","name":"The pi-sigma network: an efficient higher-order neural network for pattern classification and function approximation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.1991.155142","authors":["Y. Shin","J. Ghosh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-12-09T18:24:26Z","doi":"10.1109/ijcnn.1991.155142","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1080/0954898x.2024.2426580","name":"Kruskal Szekeres generative adversarial network augmented deep autoencoder for colorectal cancer detection","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2024.2426580","authors":["Suresh Kumar Krishnamoorthy","Vanitha CN"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-17T01:25:58Z","doi":"10.1080/0954898x.2024.2426580","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1088/0954-898x_9_2_006","name":"A model of cortical associative memory based on a horizontal network of connected columns","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_9_2_006","authors":["Erik Fransén","Anders Lansner"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T16:04:57Z","doi":"10.1088/0954-898x_9_2_006","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.3233/jifs-191397","name":"Global dissipativity and finite-time synchronization of mixed time-varying delayed memristor-based neural networks with discontinuous activations","source":"crossref","abstract":"In this paper, the matters of dissipativity and finite time synchronization for memristor-based neural networks (MNNs) with mixed time-varying discontinuities are investigated. Firstly, under the framework of extending Filippov differential inclusion theory, several effective new criteria are derived. Then, the global dissipativity of Filippov solution to neural networks is proved by using generalized Halanay inequality and matrix measure method. Secondly, some novel sufficient conditions are introduced to guarantee the finite-time synchronization of the drive-response MNNs based on a simple Lyapunov function and two different feedback controllers. Finally, several numerical examples are given to verify the validity of the theoretical results.","url":"https://doi.org/10.3233/jifs-191397","authors":["Kaifang Fei","Minghui Jiang","Yadan Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-10-20T10:53:38Z","doi":"10.3233/jifs-191397","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1002/mma.9488","name":"Globally asymptotic stability analysis for memristor‐based competitive systems of reaction–diffusion delayed neural networks","source":"crossref","abstract":"The main aim of this investigation is to present a mathematical criterion that guarantees the global asymptotic stability of special class of nonlinear neural systems. Indeed, a memristor‐based competitive nonlinear reaction–diffusion Cohen–Grossberg neural network system is chosen to be investigated. Chasing the accuracy and comprehensiveness, our model has to be improved with the following elements: neutrality of the nonlinear part and being effected under time delays in the both of straight and neutral parts of the nonlinearity. Since the proposed neural network is novel, so we need to make use of a novel Lyapunov functional correspondingly to globally asymptotic stabilization of the neural network under investigation. Prior to this process, it is necessary to present a uniqueness criterion for solutions of the proposed neural network. To this aim, the well‐known M‐matrix technique of the linear algebra is applied that guarantees existence of a unique equilibrium point of the considered Cohen–Grossberg neural network. Numerical perspective of this investigation leads us to some numerical prototypes that justify our stability criterion is applicable. This investigation will be finalized with interesting discussion on the nature of time delays that are characterized as fundamental elements in modeling of the neural networks.","url":"https://doi.org/10.1002/mma.9488","authors":["Yousef Gholami"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-26T10:01:22Z","doi":"10.1002/mma.9488","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1088/0954-898x_9_3_008","name":"Learning viewpoint-invariant face representations from visual experience in an attractor network","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_9_3_008","authors":["Marian Stewart Bartlett","Terrence J Sejnowski"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:53Z","doi":"10.1088/0954-898x_9_3_008","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1016/0893-6080(88)90564-3","name":"Parallel neural network simulation machine: Neuman","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90564-3","authors":["Nobuki Kajihara","Satoshi Matsushita","Toshiyuki Nakata","Nobuhiko Koike"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T05:05:53Z","doi":"10.1016/0893-6080(88)90564-3","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1007/978-1-4842-4421-0_10","name":"Using Neural Networks to Classify Objects","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4842-4421-0_10","authors":["Igor Livshin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-04-12T15:05:25Z","doi":"10.1007/978-1-4842-4421-0_10","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1016/0893-6080(88)90459-5","name":"Resource allocation using a constraint optimizing adaptive neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90459-5","authors":["George W. Earle","Harold Szu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T01:05:53Z","doi":"10.1016/0893-6080(88)90459-5","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1016/0893-6080(94)00086-2","name":"A neural network-like critic for reinforcement learning","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(94)00086-2","authors":["Hiroshi Yamakawa","Yoichi Okabe"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-25T09:54:11Z","doi":"10.1016/0893-6080(94)00086-2","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1016/0893-6080(88)90488-1","name":"Study of real-time weld seam tracking visual image analysis using a neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90488-1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T05:05:53Z","doi":"10.1016/0893-6080(88)90488-1","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1016/0893-6080(95)00082-8","name":"On the match tracking anomaly of the ARTMAP neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(95)00082-8","authors":["Guszti Bartfai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-25T23:57:31Z","doi":"10.1016/0893-6080(95)00082-8","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1007/978-3-319-76375-0_46","name":"Autowaves in a Lattice of Memristor-Based Cells","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-76375-0_46","authors":["Viet-Thanh Pham","Arturo Buscarino","Mattia Frasca","Luigi Fortuna"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-11-12T22:03:43Z","doi":"10.1007/978-3-319-76375-0_46","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1023/a:1019747726343","name":"A Neural Network with Evolutionary Neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1023/a:1019747726343","authors":["Alberto Alvarez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-03-15T13:06:01Z","doi":"10.1023/a:1019747726343","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1515/9783110584974-030","name":"Global Mean Square Exponential Stability of Memristor-Based Stochastic Neural Networks with Time-Varying Delays","source":"crossref","abstract":"","url":"https://doi.org/10.1515/9783110584974-030","authors":["Xiao-Lin Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-12-22T22:20:11Z","doi":"10.1515/9783110584974-030","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.14311/nnw.2024.34.012","name":"Understanding Travel Behavior: A Deep Neural Network and SHAP Approach to Mode Choice Determinants","source":"crossref","abstract":"Understanding individual travel behavior is crucial for developing effective travel demand management strategies and informed transportation policies. This study investigates the factors influencing individuals’ mode choices by analyzing data from a comprehensive travel survey. We employ a deep neural network model to explore the relationships between survey variables and respondents’ transportation mode preferences, focusing on both observable and latent factors. The SHAP method is applied to interpret the model’s outputs, providing global and local explanations that offer detailed insights into the contribution of each variable to mode choice decisions. By identifying the key determinants of mode selection and uncovering the complex interactions between these factors, this research provides valuable insights for designing targeted policies that can better address transportation needs and influence sustainable travel behavior.","url":"https://doi.org/10.14311/nnw.2024.34.012","authors":["Halil Çevik","Ondřej Přibyl","Shoaib Samandar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-27T13:28:39Z","doi":"10.14311/nnw.2024.34.012","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/ijcnn.2006.1716497","name":"The Modified Differential Evolution and the RBF (MDE-RBF) Neural Network for Time Series Prediction","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.1716497","authors":["H. Dhahri","Adel.M. Alimi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-30T12:35:23Z","doi":"10.1109/ijcnn.2006.1716497","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/ijcnn.2006.246843","name":"Neural-Network-based Metalearning for Distributed Text Information Retrieval","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.246843","authors":["Kin Keung Lai","Lean Yu","Shouyang Wang","Wei Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T15:34:22Z","doi":"10.1109/ijcnn.2006.246843","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.21070/ups.8589","name":"Intelligent Driver System Based on Convolutional Neural Network for Detecting Unsafe Driving Conditions","source":"crossref","abstract":"","url":"https://doi.org/10.21070/ups.8589","authors":["Prawira Putra","Yunianita Rahmawati"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-05T06:30:59Z","doi":"10.21070/ups.8589","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/mwscas.2010.5548803","name":"A memristor SPICE model for designing memristor circuits","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mwscas.2010.5548803","authors":["Mohammad Mahvash","Alice C. Parker"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-08-19T10:51:39Z","doi":"10.1109/mwscas.2010.5548803","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1088/0954-898x/14/3/304","name":"Convergence properties of three spike-triggered analysis techniques","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/14/3/304","authors":["Liam Paninski12"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2004-01-09T05:18:59Z","doi":"10.1088/0954-898x/14/3/304","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1016/0893-6080(88)90328-0","name":"Random field and tonotopy: Simulation of an auditory neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90328-0","authors":["T. Herve","J. Demongeot"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T05:05:53Z","doi":"10.1016/0893-6080(88)90328-0","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1016/j.neunet.2018.05.002","name":"Coupled convolution layer for convolutional neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2018.05.002","authors":["Kazutaka Uchida","Masayuki Tanaka","Masatoshi Okutomi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-05-16T12:11:24Z","doi":"10.1016/j.neunet.2018.05.002","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1007/978-3-319-02630-5_15","name":"Behavior of Multiple Memristor Circuits","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-02630-5_15","authors":["Ram Kaji Budhathoki","Maheshwar P. Sah","Shyam Prasad Adhikari","Hyongsuk Kim","Leon Chua"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-12-18T10:27:01Z","doi":"10.1007/978-3-319-02630-5_15","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1007/978-3-319-76375-0_32","name":"A Memristor-Based Chaotic System with Boundary Conditions","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-76375-0_32","authors":["Xiaofang Hu","Guanrong Chen","Shukai Duan","Gang Feng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-11-12T17:03:43Z","doi":"10.1007/978-3-319-76375-0_32","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1504/ijamechs.2010.033044","name":"Perception neural network versus fuzzy neural network for controlling the inverted pendulum","source":"crossref","abstract":"","url":"https://doi.org/10.1504/ijamechs.2010.033044","authors":["Mohamed A. Belal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-05-08T11:30:25Z","doi":"10.1504/ijamechs.2010.033044","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/ijcnn.2006.246796","name":"The Time Adaptive Self-Organizing Map is a Neural Network Based on Artificial Immune System","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.246796","authors":["H. Shah-Hosseini"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T11:34:22Z","doi":"10.1109/ijcnn.2006.246796","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1088/0954-898x_3_3_001","name":"On the classification of learning machines","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_3_3_001","authors":["Giorgio Parisi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T16:04:20Z","doi":"10.1088/0954-898x_3_3_001","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1088/0954-898x/14/3/001","name":"Sensory coding in the natural environment","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/14/3/001","authors":["B Olshausen","P Reinagel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2004-01-09T05:18:59Z","doi":"10.1088/0954-898x/14/3/001","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.22541/au.171309702.22057241/v1","name":"Improvement the classification of a nanocomposite using nanoparticules based on a meta-analysis study, Recurrent Neural Network and Recurrent Neural Network Monte-Carlo algorithms","source":"crossref","abstract":"This paper may be the first meta-analysis that presents a comprehensive synthesis of scientific works spanning the last five years, focusing on methodologies and results related to the analysis of nanocomposite using nanoparticules. The primary objective is to identify the optimal algorithm using software information and leading to better classification methodology. Specifically, this study come up with the advantages and the drawbacks of the most used algorithms and proposes an enhancement and performance of Recurrent Neural Networks based Long Short Term Memory (LSTM) neurons. Besides, a comparaison of Deep Learning methods for the classification of polymeric nanoparticles, with polypropylene serving as a case study will be implemented. Experiment comparison were conducted to assess with one physical property, later expanded to four properties and finally to eight properties. Neural networks, including Artificial Neural Networks (ANN), Recurrent Neural Networks (RNN), and Recurrent Neural Networks-Monte Carlo, were employed for simulations. The evaluation criteria encompassed accuracy, calculation time, mean square error (MSE) and other metrics. The findings contribute to the selection of an optimal algorithm for the analysis of polymeric nanoparticles, emphasizing the potential of Deep Learning methodologies, particularly Recurrent Neural Networks Monte Carlo, in advancing classification accuracy and efficiency.","url":"https://doi.org/10.22541/au.171309702.22057241/v1","authors":["Rania LOUKIL","Wejdene GAZEHI","Mongi BESBES"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-14T08:17:05Z","doi":"10.22541/au.171309702.22057241/v1","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1039/d5tc01371b/v1/decision1","name":"Decision letter for \"Amorphous Ta&lt;sub&gt;2&lt;/sub&gt;O&lt;sub&gt;5&lt;/sub&gt; memristor with excellent self-selective and artificial synaptic properties for artificial neural networks\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5tc01371b/v1/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-16T17:06:47Z","doi":"10.1039/d5tc01371b/v1/decision1","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/tnnls.2019.2915353","name":"Global Stabilization of Fractional-Order Memristor-Based Neural Networks With Time Delay","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnnls.2019.2915353","authors":["Jia Jia","Xia Huang","Yuxia Li","Jinde Cao","Ahmed Alsaedi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-06-03T15:23:21Z","doi":"10.1109/tnnls.2019.2915353","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1162/089976601300014501","name":"Learning Hough Transform: A Neural Network Model","source":"crossref","abstract":"A single-layered Hough transform network is proposed that accepts image coordinates of each object pixel as input and produces a set of outputs that indicate the belongingness of the pixel to a particular structure (e.g., a straight line). The network is able to learn adaptively the parametric forms of the linear segments present in the image. It is designed for learning and identification not only of linear segments in two-dimensional images but also the planes and hyperplanes in the higher-dimensional spaces. It provides an efficient representation of visual information embedded in the connection weights. The network not only reduces the large space requirement, as in the case of classical Hough transform, but also represents the parameters with high precision.","url":"https://doi.org/10.1162/089976601300014501","authors":["Jayanta Basak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-27T11:55:01Z","doi":"10.1162/089976601300014501","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1162/089976601317098565","name":"Feedforward Neural Network Construction Using Cross Validation","source":"crossref","abstract":"This article presents an algorithm that constructs feedforward neural networks with a single hidden layer for pattern classification. The algorithm starts with a small number of hidden units in the network and adds more hidden units as needed to improve the network's predictive accuracy. To determine when to stop adding new hidden units, the algorithm makes use of a subset of the available training samples for cross validation. New hidden units are added to the network only if they improve the classification accuracy of the network on the training samples and on the cross-validation samples. Extensive experimental results show that the algorithm is effective in obtaining networks with predictive accuracy rates that are better than those obtained by state-of-the-art decision tree methods.","url":"https://doi.org/10.1162/089976601317098565","authors":["Rudy Setiono"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-27T11:56:30Z","doi":"10.1162/089976601317098565","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1016/j.neunet.2023.01.042","name":"A feedforward unitary equivariant neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2023.01.042","authors":["Pui-Wai Ma","T.-H. Hubert Chan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-02-01T11:37:47Z","doi":"10.1016/j.neunet.2023.01.042","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1016/0893-6080(88)90014-7","name":"Neocognitron: A hierarchical neural network capable of visual pattern recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90014-7","authors":["Kunihiko Fukushima"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T01:05:53Z","doi":"10.1016/0893-6080(88)90014-7","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1007/978-1-4471-2001-8_20","name":"Structural Properties of Proteins Predicted by Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4471-2001-8_20","authors":["H. Bohr"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-12-26T11:23:28Z","doi":"10.1007/978-1-4471-2001-8_20","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1016/s0893-6080(03)00077-7","name":"Global asymptotic stability of Hopfield neural network involving distributed delays","source":"crossref","abstract":"","url":"https://doi.org/10.1016/s0893-6080(03)00077-7","authors":["Hongyong Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-05-19T18:45:52Z","doi":"10.1016/s0893-6080(03)00077-7","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1016/0893-6080(94)90113-9","name":"A model-based neural network for transient signal processing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(94)90113-9","authors":["Leonid I. Perlovsky"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-24T23:25:55Z","doi":"10.1016/0893-6080(94)90113-9","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1016/s0893-6080(01)00035-1","name":"Pattern classification by a condensed neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/s0893-6080(01)00035-1","authors":["A Mitiche","M Lebidoff"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-10-14T22:58:33Z","doi":"10.1016/s0893-6080(01)00035-1","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1016/j.neunet.2005.08.016","name":"A neural network model of Parkinson's disease bradykinesia","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2005.08.016","authors":["Vassilis Cutsuridis","Stavros Perantonis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-12-15T18:00:20Z","doi":"10.1016/j.neunet.2005.08.016","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/tnn.2009.2024203","name":"Wavelet Differential Neural Network Observer","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnn.2009.2024203","authors":["I. Chairez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-08-12T14:56:52Z","doi":"10.1109/tnn.2009.2024203","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/72.298230","name":"A neural network model of causality","source":"crossref","abstract":"","url":"https://doi.org/10.1109/72.298230","authors":["R. Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-24T19:16:32Z","doi":"10.1109/72.298230","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1016/s0893-6080(98)00074-4","name":"State space neural network. Properties and application","source":"crossref","abstract":"","url":"https://doi.org/10.1016/s0893-6080(98)00074-4","authors":["Jesús M. Zamarreño","Pastora Vega"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-25T23:57:31Z","doi":"10.1016/s0893-6080(98)00074-4","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1016/j.neunet.2009.05.003","name":"A probabilistic neural network for earthquake magnitude prediction","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2009.05.003","authors":["Hojjat Adeli","Ashif Panakkat"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-05-22T11:20:19Z","doi":"10.1016/j.neunet.2009.05.003","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1007/978-3-030-51882-0_3","name":"Generic and Practical Emulators for the Current-Controlled Memristor Models","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-51882-0_3","authors":["Abdullah G. Alharbi","Masud H. Chowdhury"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-01T19:06:16Z","doi":"10.1007/978-3-030-51882-0_3","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1016/0893-6080(88)90133-5","name":"Constraint optimization neural network for adaptive early vision","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90133-5","authors":["B. Furman","J. Liang","H. Szu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T01:05:53Z","doi":"10.1016/0893-6080(88)90133-5","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.23919/mixdes55591.2022.9838321","name":"Analytical Calculation of Inference in Memristor-based Stochastic Artificial Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.23919/mixdes55591.2022.9838321","authors":["Nicolas Bogun","Emilio Perez-Bosch Quesada","Eduardo Perez","Christian Wenger","Alexander Kloes","Mike Schwarz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-07-29T15:38:30Z","doi":"10.23919/mixdes55591.2022.9838321","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.2139/ssrn.5114402","name":"Cluster-Type Conductive Path-Based Selector-Less 1r Memristor Array for Spiking Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5114402","authors":["Ji Eun Kim","Suman Hu","Ju Young Kwon","Suk Yeop Chun","Keunho Soh","Hwanhui Yun","Seung-Hyub Baek","Sahn Nahm","YeonJoo Jeong","Jung Ho Yoon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-28T07:45:48Z","doi":"10.2139/ssrn.5114402","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1016/0893-6080(88)90028-7","name":"Memory capacity in neural network models: Rigorous lower bounds","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90028-7","authors":["Charles M Newman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T05:05:53Z","doi":"10.1016/0893-6080(88)90028-7","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1162/neco.1993.5.6.928","name":"Rational Function Neural Network","source":"crossref","abstract":"In this paper we observe that a particular class of rational function (RF) approximations may be viewed as feedforward networks. Like the radial basis function (RBF) network, the training of the RF network may be performed using a linear adaptive filtering algorithm. We illustrate the application of the RF network by considering two nonlinear signal processing problems. The first problem concerns the one-step prediction of a time series consisting of a pair of complex sinusoid in the presence of colored non-gaussian noise. Simulated data were used for this problem. In the second problem, we use the RF network to build a nonlinear dynamic model of sea clutter (radar backscattering from a sea surface); here, real-life data were used for the study.","url":"https://doi.org/10.1162/neco.1993.5.6.928","authors":["Henry Leung","Simon Haykin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-04-04T19:26:28Z","doi":"10.1162/neco.1993.5.6.928","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/csci58124.2022.00066","name":"Spoken Digits Classification Based on Spiking Neural Networks with Memristor-Based STDP","source":"crossref","abstract":"","url":"https://doi.org/10.1109/csci58124.2022.00066","authors":["Danila Vlasov","Yury Davydov","Alexey Serenko","Roman Rybka","Alexander Sboev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-25T17:17:05Z","doi":"10.1109/csci58124.2022.00066","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1039/d5tc01371b/v2/decision1","name":"Decision letter for \"Amorphous Ta&lt;sub&gt;2&lt;/sub&gt;O&lt;sub&gt;5&lt;/sub&gt; memristor with excellent self-selective and artificial synaptic properties for artificial neural networks\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5tc01371b/v2/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-16T17:06:47Z","doi":"10.1039/d5tc01371b/v2/decision1","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/iscas.2017.8050531","name":"Ziksa: On-chip learning accelerator with memristor crossbars for multilevel neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas.2017.8050531","authors":["Abdullah M. Zyarah","Nicholas Soures","Lydia Hays","Robin B Jacobs-Gedrim","Sapan Agarwal","Matthew Marinella","Dhireesha Kudithipudi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-09-28T16:33:32Z","doi":"10.1109/iscas.2017.8050531","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1109/ijcnn.1993.714356","name":"Novel impulse neural circuits for pulsed neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.1993.714356","authors":["Jong-Han Shin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-08-24T17:15:33Z","doi":"10.1109/ijcnn.1993.714356","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1088/1361-6528/acebf5","name":"Unsupervised learning in hexagonal boron nitride memristor-based spiking neural networks","source":"crossref","abstract":"Abstract Resistive random access memory (RRAM) is an emerging non-volatile memory technology that can be used in neuromorphic computing hardware to exceed the limitations of traditional von Neumann architectures by merging processing and memory units. Two-dimensional (2D) materials with non-volatile switching behavior can be used as the switching layer of RRAMs, exhibiting superior behavior compared to conventional oxide-based devices. In this study, we investigate the electrical performance of 2D hexagonal boron nitride (h-BN) memristors towards their implementation in spiking neural networks (SNN). Based on experimental behavior of the h-BN memristors as artificial synapses, we simulate the implementation of unsupervised learning in SNN for image classification on the Modified National Institute of Standards and Technology dataset. Additionally, we propose a simple spike-timing-dependent-plasticity (STDP)-based dropout technique to enhance the recognition rate in h-BN memristor-based SNN. Our results demonstrate the viability of using 2D-material-based memristors as artificial synapses to perform unsupervised learning in SNN using hardware-friendly methods for online learning.","url":"https://doi.org/10.1088/1361-6528/acebf5","authors":["Sahra Afshari","Jing Xie","Mirembe Musisi-Nkambwe","Sritharini Radhakrishnan","Ivan Sanchez Esqueda"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-31T18:22:08Z","doi":"10.1088/1361-6528/acebf5","addedAt":"2026-09-01T01:48:32.728Z","updatedAt":"2026-09-01T01:48:32.728Z"},{"id":"doi:10.1007/978-3-030-22808-8_55","name":"A Novel Memristor-CMOS Hybrid Full-Adder and Its Application","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-22808-8_55","authors":["Hui Yang","Shukai Duan","Lidan Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-06-26T00:02:30Z","doi":"10.1007/978-3-030-22808-8_55","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1016/j.neunet.2021.03.002","name":"Parallel orthogonal deep neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2021.03.002","authors":["Peyman Sheikholharam Mashhadi","Sławomir Nowaczyk","Sepideh Pashami"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-13T21:54:47Z","doi":"10.1016/j.neunet.2021.03.002","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1016/j.neunet.2005.06.039","name":"Neural network model for extracting optic flow","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2005.06.039","authors":["Kazuya Tohyama","Kunihiko Fukushima"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-08-20T11:18:48Z","doi":"10.1016/j.neunet.2005.06.039","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1016/0893-6080(88)90467-4","name":"Neural network identification and extraction of repetitive superimposed pulses in noisy 1-D signals","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90467-4","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T05:05:53Z","doi":"10.1016/0893-6080(88)90467-4","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1016/s0893-6080(97)00007-5","name":"Neural Network Smoothing in Correlated Time Series Context","source":"crossref","abstract":"","url":"https://doi.org/10.1016/s0893-6080(97)00007-5","authors":["F. Badran","S. Thiria"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-25T12:59:42Z","doi":"10.1016/s0893-6080(97)00007-5","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1016/s0893-6080(96)00075-5","name":"HAVNET: A New Neural Network Architecture for Pattern Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1016/s0893-6080(96)00075-5","authors":["Ryan G. Rosandich"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-25T15:25:37Z","doi":"10.1016/s0893-6080(96)00075-5","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1016/s0893-6080(00)00069-1","name":"Towards a neural network based therapy for hallucinatory disorders","source":"crossref","abstract":"","url":"https://doi.org/10.1016/s0893-6080(00)00069-1","authors":["J.Ropero Peláez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-25T17:31:48Z","doi":"10.1016/s0893-6080(00)00069-1","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1109/icnn.1996.549010","name":"An autonomously controlled chaos neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnn.1996.549010","authors":["M. Nakagawa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-12-24T01:16:22Z","doi":"10.1109/icnn.1996.549010","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1109/icaci58115.2023.10146155","name":"Convergence analysis of the nontrivial stationary solution of the memristor-based neural networks with reaction-diffusion terms","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icaci58115.2023.10146155","authors":["Helin Wang","Xinrui Jiang","Sitian Qin","Wei Zhang","Yuming Feng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-12T17:57:06Z","doi":"10.1109/icaci58115.2023.10146155","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1109/neurel.2012.6419960","name":"Special session 1: Neural networks in robotics","source":"crossref","abstract":"","url":"https://doi.org/10.1109/neurel.2012.6419960","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-01-31T12:22:27Z","doi":"10.1109/neurel.2012.6419960","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1109/neurel.2012.6419991","name":"Regular session 3: Neural networks for classification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/neurel.2012.6419991","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-01-31T17:22:27Z","doi":"10.1109/neurel.2012.6419991","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1109/icnn.1988.23950","name":"A continuous-time optical neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnn.1988.23950","authors":["Stoll","Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-01-06T21:42:02Z","doi":"10.1109/icnn.1988.23950","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1016/j.neunet.2010.07.004","name":"Modeling cognitive and emotional processes: A novel neural network architecture","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2010.07.004","authors":["Adnan Khashman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-07-15T04:59:33Z","doi":"10.1016/j.neunet.2010.07.004","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1016/j.neunet.2024.106135","name":"SecBERT: Privacy-preserving pre-training based neural network inference system","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106135","authors":["Hai Huang","Yongjian Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-17T16:25:21Z","doi":"10.1016/j.neunet.2024.106135","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1016/0893-6080(91)90068-g","name":"Visual navigation with a neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(91)90068-g","authors":["Nicholas G. Hatsopoulos","William H. Warren"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T05:05:53Z","doi":"10.1016/0893-6080(91)90068-g","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.5772/5554","name":"Recurrent Neural Network Identification and Adaptive Neural Control of Hydrocarbon Biodegradation Processes","source":"crossref","abstract":"","url":"https://doi.org/10.5772/5554","authors":["Ieroham Baruch","Carlos Mariaca-Gaspar","Josefina Barrera-Cortes"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-03-23T19:28:04Z","doi":"10.5772/5554","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1109/72.80269","name":"Neural network classification: a Bayesian interpretation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/72.80269","authors":["E.A. Wan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-24T19:16:32Z","doi":"10.1109/72.80269","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1016/b978-0-444-88400-8.50048-0","name":"DAS LERNFAHRZEUG NEURAL NETWORK APPLICATION FOR AUTONOMOUS MOBILE ROBOTS","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-444-88400-8.50048-0","authors":["Rigobert OPITZ"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-01T06:37:30Z","doi":"10.1016/b978-0-444-88400-8.50048-0","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1016/b978-0-444-89488-5.50176-7","name":"A Neural Network for Hyphenation","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-444-89488-5.50176-7","authors":["Walter Daelemans","Antal van den Bosch"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-01T03:02:01Z","doi":"10.1016/b978-0-444-89488-5.50176-7","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1016/b978-0-444-89178-5.50069-5","name":"GENETICALLY PROGRAMMED NEURAL NETWORK FOR SOLVING POLE-BALANCING PROBLEM","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-444-89178-5.50069-5","authors":["Borut Maričić"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-01T06:49:32Z","doi":"10.1016/b978-0-444-89178-5.50069-5","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1109/ijcnn.1989.118350","name":"On interpretations of a feed-forward neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.1989.118350","authors":["Tamura"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-01-13T13:46:33Z","doi":"10.1109/ijcnn.1989.118350","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1109/ijcnn.2003.1223379","name":"Extension neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2003.1223379","authors":["M.H. Wang","C.P. Hung"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2004-03-02T02:26:50Z","doi":"10.1109/ijcnn.2003.1223379","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1016/s0893-6080(98)00005-7","name":"A hybrid neural network model in handwritten word recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1016/s0893-6080(98)00005-7","authors":["Jung-Hsien Chiang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-25T22:54:47Z","doi":"10.1016/s0893-6080(98)00005-7","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1016/0893-6080(88)90505-9","name":"Optimization of rotationally invariant object recognition in a neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90505-9","authors":["Stavros Busenberg","Louis Rossi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T01:05:53Z","doi":"10.1016/0893-6080(88)90505-9","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1016/j.neunet.2025.108361","name":"Addressing common misinterpretations of KART and UAT in neural network literature","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.108361","authors":["Vugar E. Ismailov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-22T23:38:13Z","doi":"10.1016/j.neunet.2025.108361","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1007/s11063-020-10417-2","name":"Network-Based $$H_\\infty $$ Filtering for Descriptor Markovian Jump Systems with a Novel Neural Network Event-Triggered Scheme","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11063-020-10417-2","authors":["Yuzhong Wang","Tie Zhang","Si Chen","Junchao Ren"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-01-08T15:03:19Z","doi":"10.1007/s11063-020-10417-2","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.14311/nnw.2012.22.020","name":"ADDING DECAYING SELF-FEEDBACK CONTINUOUS HOPFIELD NEURAL NETWORK CONVERGENCE ANALYSIS IN THE HYPER-CUBE SPACE","source":"crossref","abstract":"","url":"https://doi.org/10.14311/nnw.2012.22.020","authors":["Chunguo Fei","Baili Su"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-04T08:48:51Z","doi":"10.14311/nnw.2012.22.020","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1109/iita.2008.73","name":"Simulation and Comparison of Zhang Neural Network and Gradient Neural Network Solving for Time-Varying Matrix Square Roots","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iita.2008.73","authors":["Yunong Zhang","Yiwen Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-01-14T22:41:27Z","doi":"10.1109/iita.2008.73","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.5151/meceng-wccm2012-19128","name":"A CONCURRENT FUZZY NEURAL NETWORK APPROACH FOR A FUZZY GAUSSIAN NEURAL NETWORK","source":"crossref","abstract":"","url":"https://doi.org/10.5151/meceng-wccm2012-19128","authors":["I. F. Iatan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-05-28T13:41:35Z","doi":"10.5151/meceng-wccm2012-19128","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1016/j.neunet.2023.12.008","name":"Memristor-induced hyperchaos, multiscroll and extreme multistability in fractional-order HNN: Image encryption and FPGA implementation","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2023.12.008","authors":["Xinxin Kong","Fei Yu","Wei Yao","Shuo Cai","Jin Zhang","Hairong Lin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-05T02:22:35Z","doi":"10.1016/j.neunet.2023.12.008","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1007/s00521-017-3246-7","name":"Artificial neural network based screening of cervical cancer using a hierarchical modular neural network architecture (HMNNA) and novel benchmark uterine cervix cancer database","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-017-3246-7","authors":["Mehbob Ali","Abid Sarwar","Vinod Sharma","Jyotsna Suri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-11-01T08:51:56Z","doi":"10.1007/s00521-017-3246-7","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1016/b978-0-12-546090-3.50008-5","name":"NEURAL NETWORK STRUCTURES: FORM FOLLOWS FUNCTION","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-12-546090-3.50008-5","authors":["Alianna J. Maren"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-06-30T12:00:51Z","doi":"10.1016/b978-0-12-546090-3.50008-5","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1007/978-1-4842-5648-0_16","name":"Exposing Neural Network Models","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4842-5648-0_16","authors":["Nemanja Milosevic"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-02-05T12:02:45Z","doi":"10.1007/978-1-4842-5648-0_16","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.53347/rid-71408","name":"Fully connected neural network","source":"crossref","abstract":"","url":"https://doi.org/10.53347/rid-71408","authors":["Candace Moore","Andrew Murphy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-10-25T02:31:31Z","doi":"10.53347/rid-71408","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.7717/peerjcs.1680/fig-8","name":"Figure 8: Results of neural network training, iterations 1–2,000.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerjcs.1680/fig-8","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-13T04:21:26Z","doi":"10.7717/peerjcs.1680/fig-8","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1109/tnano.2018.2821131","name":"Learning in Memristor Crossbar-Based Spiking Neural Networks Through Modulation of Weight-Dependent Spike-Timing-Dependent Plasticity","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnano.2018.2821131","authors":["Nan Zheng","Pinaki Mazumder"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-30T18:09:58Z","doi":"10.1109/tnano.2018.2821131","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.23919/aces-china66523.2025.11332829","name":"Temperature-Drift Compensation for Memristor Crossbar In-Memory Computing by Bayesian Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.23919/aces-china66523.2025.11332829","authors":["Ao Du","Xingyu Zhai","Bo Pu","Hao Xie","Wenchao Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-20T20:37:20Z","doi":"10.23919/aces-china66523.2025.11332829","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1142/s0129065721500222","name":"A Deep Fourier Neural Network for Seizure Prediction Using Convolutional Neural Network and Ratios of Spectral Power","source":"crossref","abstract":"Epileptic seizure prediction is one of the most used therapeutic adjuvant strategies for drug-resistant epilepsy. Conventional methods usually adopt handcrafted features and manual parameter setting. The over-reliance on the expertise of specialists may lead to weak exploitation of features and low popularization of clinical application. This paper proposes a novel parameterless patient-specific method based on Fourier Neural Network (FNN), where the Fourier transform and backpropagation learning are synthesized to make the predictor more efficient and practical. The employment of FNN is the first attempt in the field of seizure prediction due to its automatic extraction of immanent spectra in epileptic signals. Despite the self-adaptive superiority of FNN, we introduce Convolutional Neural Network (CNN) to further improve its search capability in high-dimensional feature spaces. The study also develops a multi-layer module to estimate spectral power ratios of raw recordings, which optimizes the prediction by enhancing feature diversity. Based on these modules, this paper proposes a two-channel deep neural network: Fourier Ratio Convolutional Neural Network (FRCNN). To demonstrate the reliability of the model, we explain the mathematical meaning of hidden-layer neurons in FRCNN theoretically. This approach is evaluated on both intracranial and scalp EEG datasets. It shows that the predictor achieved a sensitivity of 91.2% and a false prediction rate (FPR) of 0.06[Formula: see text]h[Formula: see text] across intracranial subjects and a sensitivity of 85.4% and an FPR of 0.14[Formula: see text]h[Formula: see text] over scalp subjects. The results indicate that FRCNN enables the convenience of epilepsy treatments while preserving a high degree of precision. In the end, a detailed comparison with the previous methods demonstrates that FRCNN has achieved higher performance and generalization ability.","url":"https://doi.org/10.1142/s0129065721500222","authors":["Peizhen Peng","Liping Xie","Haikun Wei"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-31T03:17:14Z","doi":"10.1142/s0129065721500222","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.3103/s1060992x24601787","name":"Combination of Convolutional Neural Network and Long Short Term Memory Network for Arabic Handwritten Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.3103/s1060992x24601787","authors":["Mamouni El Mamoun","Bouhouia Slimane","Zaouak Omar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-26T17:36:33Z","doi":"10.3103/s1060992x24601787","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1007/s12555-022-1090-8","name":"Exponential Synchronization of Stochastic Time-delayed Memristor-based Neural Networks via Pinning Impulsive Control","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s12555-022-1090-8","authors":["Yao Cui","Pei Cheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-29T07:02:18Z","doi":"10.1007/s12555-022-1090-8","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1016/j.amc.2017.05.021","name":"Existence, uniqueness, and exponential stability analysis for complex-valued memristor-based BAM neural networks with time delays","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.amc.2017.05.021","authors":["Runan Guo","Ziye Zhang","Xiaoping Liu","Chong Lin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-05-16T11:45:13Z","doi":"10.1016/j.amc.2017.05.021","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1049/cp:19950566","name":"A neural-network-based flexible assembly controller","source":"crossref","abstract":"","url":"https://doi.org/10.1049/cp:19950566","authors":["M.D. Majors"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2005-11-09T21:40:06Z","doi":"10.1049/cp:19950566","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.70675/dcef4edez91f2z4abcz91b3z66d244e29bfc","name":"Modeling and design of neural network architectures for neural artificial-biological hybridization based on synchronous approach","source":"crossref","abstract":"Modélisation et conception par approche synchrone d'architectures neuronales hybrides biologique-artificiel Alors que les Réseaux de Neurones Artificiels (RNA) continuent de progresser dans des domaines tels que l'apprentissage automatique, la robotique, les véhicules autonomes et le diagnostic de santé, un nouveau cadre d'application gagne du terrain à la fois dans les secteurs académique et industriel : la Neurobiohybridation. Ce domaine cherche à établir des connexions entre des neurones artificiels et biologiques dans le but de comprendre et potentiellement de réparer ou remplacer des fonctions cérébrales perdues suite à des maladies ou des accidents. Dans cette perspective, le développement de réseaux de neurones artificiels inspirés biologiquement, souvent appelés Réseaux de Neurones à Spikes (SNNs), est essentiel pour améliorer la compatibilité entre les systèmes neuronaux artificiels et biologiques. Notre thèse s'inscrit dans ce contexte en utilisant l'approche synchrone pour modéliser, mettre en œuvre et simuler des SNNs bio-inspirés et biomimétiques. En utilisant des vérificateurs de modèles, qui permettent de prouver ou d'extraire des propriétés des systèmes de manière formelle, notre objectif est d'acquérir une compréhension plus complète des comportements biologiques dans le future. Pour la première fois dans ce contexte, nous utilisons le langage Light Esterel pour atteindre nos objectifs. Nous démontrons son potentiel dans la mise en oeuvre de modèles neuronaux, initiant une bibliothèque de modèles pour explorer différents types de SNNs. Tout au long de cette thèse, nous avons développé un cadre complet basé sur Light Esterel pour modéliser, simuler et mettre en oeuvre divers modèles de SNNs. Pour aborder les expériences de neurobiohybridation, nous avons développé notre propre architecture matérielle, SynchNN, capable d'exécuter en temps réel des SNNs récurrents en utilisant notre bibliothèque de modèles. Le cadre que nous avons développé est complété par un framework de simulation en cours de développement, visant à réaliser des expériences de neurobiohybridation à l'avenir.","url":"https://doi.org/10.70675/dcef4edez91f2z4abcz91b3z66d244e29bfc","authors":["Marino Rasamuel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-07T17:53:57Z","doi":"10.70675/dcef4edez91f2z4abcz91b3z66d244e29bfc","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1088/0954-898x_4_1_001","name":"Dynamics of neural networks with non-monotone activation function","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_4_1_001","authors":["P De Felice","C Marangi","G Nardulli","G Pasquariello","L Tedesco"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T16:04:20Z","doi":"10.1088/0954-898x_4_1_001","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1007/s00521-022-07829-7","name":"Simulating a complete Tritonia escape swim network using a novel event-based spiking neural network algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-022-07829-7","authors":["Fatemehossadat Miri","Carol I. Miles","Harold W. Lewis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-03T03:24:50Z","doi":"10.1007/s00521-022-07829-7","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.21070/ups.2354","name":"Convolutional Neural Network Implementation Using the TensorFlow Library for Freshness Detection in Apples","source":"crossref","abstract":"","url":"https://doi.org/10.21070/ups.2354","authors":["Diana Cindy Agustin","Mochamad Alfan Rosid"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-16T09:00:38Z","doi":"10.21070/ups.2354","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1109/icmcce48743.2019.00097","name":"Comparative Study of BP Neural Network and RBF Neural Network in Surface Reconstruction","source":"crossref","abstract":"Aiming at the surface reconstruction problem, the surface reconstruction methods based on BP and RBF neural networks are studied respectively, and the two neural network models are compared. The results show that both network models can effectively reconstruct the surface. The BP model has a short running time, but the randomness of the weights and thresholds make the model stable. The RBF model has high reconstruction stability, but the fitting time is longer than the BP model. Both have their own advantages. The specific application should be determined according to the specific research object.","url":"https://doi.org/10.1109/icmcce48743.2019.00097","authors":["Hai-jun Wang","Tao Jin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-31T02:15:47Z","doi":"10.1109/icmcce48743.2019.00097","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1109/ijcnn.2006.246719","name":"Multilayer Neural Network based on Multi-Valued Neurons and the Blur Identification Problem","source":"crossref","abstract":"A multilayer neural network based on multi-valued neurons (MLMVN) is a neural network with a traditional feedforward architecture. At the same time this network has a number of specific properties and advantages. Its backpropagation learning algorithm does not require differentiability of the activation function. The functionality of MLMVN is higher than the ones of the traditional feedforward neural networks and a variety of kernel-based networks. Its higher flexibility and faster adaptation to the mapping implemented make possible an accomplishment of complex problems using a simpler network. The MLMVN can be used to solve those non-standard recognition and classification problems that cannot be solved using other techniques. In this paper we use the MLMVN as a tool for the blur identification problem. A prior knowledge about the distorting operator and its parameter is of crucial importance in blurred image restoration.","url":"https://doi.org/10.1109/ijcnn.2006.246719","authors":["I. Aizenberg","D. Paliy","J.T. Astola"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T11:27:21Z","doi":"10.1109/ijcnn.2006.246719","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1007/978-3-319-28495-8_17","name":"Sentiment Analysis on Morphologically Rich Languages: An Artificial Neural Network (ANN) Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-28495-8_17","authors":["Nishantha Medagoda"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-02-03T07:15:08Z","doi":"10.1007/978-3-319-28495-8_17","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1007/s10854-015-2848-z","name":"Overview of emerging memristor families from resistive memristor to spintronic memristor","source":"crossref","abstract":"Abstract Memristor is a fundamental circuit element in addition to resistor, capacitor, and inductor. As it can remember its resistance state even encountering a power off, memristor has recently received widespread applications from non-volatile memory to neural networks. The current memristor family mainly comprises resistive memristor, polymeric memristor, ferroelectric memristor, manganite memristor, resonant-tunneling diode memristor, and spintronic memristor in terms of the materials the device is made of. In order to help researcher better understand the physical principles of the memristor, and thus to provide a promising prospect for memristor devices, this paper presents an overview of memristor materials properties, switching mechanisms, and potential applications. The performance comparison among different memristor members is also given.","url":"https://doi.org/10.1007/s10854-015-2848-z","authors":["Lei Wang","CiHui Yang","Jing Wen","Shan Gai","YuanXiu Peng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-02-28T02:26:17Z","doi":"10.1007/s10854-015-2848-z","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.5194/amt-2018-436-rc2","name":"Review of \"Neural Network Radiative Transfer for Imaging Spectroscopy\"","source":"crossref","abstract":"The paper presents a neural network developed to calculate radiative transfer for the solar spectral region in clear sky.The model is applied to retrieve the surface spectral reflectance function from PRISM (airborne imaging spectrometer) data.As examples the retrieved surface reflectance spectra for 5 different surface types are shown to demonstrate that the method works well.The neural network method highly accelerates the atmospheric correction methodology, thus it is certainly an interesting approach which might become standard since the data to be processed increases rapidly with improvements in spatial and spectral resolution of sensors.The topic of the paper fits well in the scope of AMT, however, it needs to be revised, because the methodology needs to be described more precisely.Further the authors need to point, what makes their approach novel compared to other neural networks based approaches.I","url":"https://doi.org/10.5194/amt-2018-436-rc2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-02-22T11:57:07Z","doi":"10.5194/amt-2018-436-rc2","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.31274/rtd-180813-7649","name":"Neural network approach for solving inverse problems","source":"crossref","abstract":"","url":"https://doi.org/10.31274/rtd-180813-7649","authors":["Ibrahim Mohamed Elshafiey"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-08-13T15:00:58Z","doi":"10.31274/rtd-180813-7649","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.17816/dd624022-4204465","name":"Fig. 3. Diagram of the final-iteration artificial neural network.","source":"crossref","abstract":"","url":"https://doi.org/10.17816/dd624022-4204465","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-27T13:35:58Z","doi":"10.17816/dd624022-4204465","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1109/aiars59518.2023.00071","name":"A Prediction Model Combining Convolutional Neural Network and LSTM Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aiars59518.2023.00071","authors":["Ao Liu","Jing Li","Han Ye"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-20T17:42:53Z","doi":"10.1109/aiars59518.2023.00071","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1201/9781420015454.ch3","name":"Neural Network Control of Nonlinear Systems and Feedback Linearization","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781420015454.ch3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-07-19T15:41:39Z","doi":"10.1201/9781420015454.ch3","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1002/asjc.70135","name":"Predefined‐time synchronization of memristor‐based bidirectional associative memory neural networks with time‐varying delays","source":"crossref","abstract":"Abstract In this paper, two novel and general predefined‐time stability (PTSt) lemmas are introduced and applied to address the predefined‐time synchronization (PTSy) problem in memristor‐based bidirectional associative memory (BAM) neural networks. Unlike traditional finite‐time synchronization (FinTS) or fixed‐time synchronization (FixTS) approaches, the synchronization time in this study is independent of the initial states (InSts) and system parameters. It can be predetermined according to task requirements without any estimation. Two effective and innovative controllers are designed to achieve synchronization in time‐delayed memristor‐based BAM neural networks (MBAMNNs) based on PTSt. The proposed controllers employ general PTSy analysis to ensure robust synchronization performance. These diverse predefined‐time controllers (PTCos) design facilitates the practical implementation of synchronization control in neural networks. By employing the fraction‐order power function and exponential function, the PTCos offer flexibility and adaptability in controller design. The results are validated through two numerical examples using MATLAB simulations.","url":"https://doi.org/10.1002/asjc.70135","authors":["Yan Chen","Ravie Chandren Muniyandi","Shahnorbanun Sahran","Zuowei Cai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-30T00:26:00Z","doi":"10.1002/asjc.70135","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.3390/math10193699","name":"Bipartite Synchronization of Fractional-Order Memristor-Based Coupled Delayed Neural Networks with Pinning Control","source":"crossref","abstract":"This paper investigates the bipartite synchronization of memristor-based fractional-order coupled delayed neural networks with structurally balanced and unbalanced concepts. The main result is established for the proposed model using pinning control, fractional-order Jensen’s inequality, and the linear matrix inequality. Further, new sufficient conditions are derived using the Lyapunov–Krasovskii functional with delay-dependent criteria. Finally, numerical simulations are provided including two numerical examples to show the effectiveness of the theoretical results.","url":"https://doi.org/10.3390/math10193699","authors":["P. Babu Dhivakaran","A. Vinodkumar","S. Vijay","S. Lakshmanan","J. Alzabut","R. A. El-Nabulsi","W. Anukool"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-09T23:31:43Z","doi":"10.3390/math10193699","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1016/j.neucom.2019.09.117","name":"Adaptive finite-time synchronization of stochastic mixed time-varying delayed memristor-based neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2019.09.117","authors":["Tianliang Zhang","Feiqi Deng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-27T00:41:35Z","doi":"10.1016/j.neucom.2019.09.117","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1101/2023.11.09.566399","name":"SPREd: A simulation-supervised neural network tool for gene regulatory network reconstruction","source":"crossref","abstract":"Abstract Reconstruction of gene regulatory networks (GRNs) from expression data is a significant open problem. Common approaches train a machine learning (ML) model to predict a gene’s expression using transcription factors’ (TFs’) expression as features and designate important features/TFs as regulators of the gene. Here, we present an entirely different paradigm, where GRN edges are directly predicted by the ML model. The new approach, named “SPREd” is a simulation-supervised neural network for GRN inference. Its inputs comprise expression relationships (e.g., correlation, mutual information) between the target gene and each TF and between pairs of TFs. The output includes binary labels indicating whether each TF regulates the target gene. We train the neural network model using synthetic expression data generated by a biophysics-inspired simulation model that incorporates linear as well as non-linear TF-gene relationships and diverse GRN configurations. We show SPREd to outperform state-of-the-art GRN reconstruction tools GENIE3, ENNET, PORTIA and TIGRESS on synthetic datasets with high co-expression among TFs, similar to that seen in real data. A key advantage of the new approach is its robustness to relatively small numbers of conditions (columns) in the expression matrix, which is a common problem faced by existing methods. Finally, we evaluate SPREd on real data sets in yeast that represent gold standard benchmarks of GRN reconstruction and show it to perform significantly better than or comparably to existing methods. In addition to its high accuracy and speed, SPREd marks a first step towards incorporating biophysics principles of gene regulation into ML-based approaches to GRN reconstruction.","url":"https://doi.org/10.1101/2023.11.09.566399","authors":["Zijun Wu","Saurabh Sinha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-13T18:30:16Z","doi":"10.1101/2023.11.09.566399","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1002/2050-7038.12538/v1/review2","name":"Review for \"The nonlinear autoregressive network with exogenous inputs (NARX) neural network to damp power system oscillations\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/2050-7038.12538/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-07-27T17:06:47Z","doi":"10.1002/2050-7038.12538/v1/review2","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.38007/nn.2022.030201","name":"Fuzzy Neural Networks to Multi-source Information","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2022.030201","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T18:14:06Z","doi":"10.38007/nn.2022.030201","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1109/ijcnn.1989.118326","name":"Neural network based heuristics for transitive closure derivation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.1989.118326","authors":["Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-01-13T18:46:33Z","doi":"10.1109/ijcnn.1989.118326","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.7554/elife.106871.1","name":"Neural signatures of motor memories emerge in neural network models","source":"crossref","abstract":"Abstract Animals can learn and seamlessly perform a great number of behaviors. However, it is unclear how neural activity can accommodate new behaviors without interfering with those an animal has already acquired. Recent studies in monkeys performing motor and brain-computer interface (BCI) learning tasks have identified neural signatures—so-called “memory traces” and “uniform shifts”—that appear in the neural activity of a familiar task after learning a new task. Here we asked when these signatures arise and how they are related to continual learning. By modeling a BCI learning paradigm, we show that both signatures emerge naturally as a consequence of learning, without requiring a specific mechanism. In general, memory traces and uniform shifts reflected savings by capturing how information from different tasks coexisted in the same neural activity patterns. Yet, although the properties of these two different signatures were both indicative of savings, they were uncorrelated with each other. When we added contextual inputs that separated the activity for the different tasks, these signatures decreased even when savings were maintained, demonstrating the challenges of defining a clear relationship between neural activity changes and continual learning.","url":"https://doi.org/10.7554/elife.106871.1","authors":["Joanna C Chang","Claudia Clopath","Juan A Gallego"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-27T14:30:53Z","doi":"10.7554/elife.106871.1","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.55529/jaimlnn.52.58.68","name":"Fedgraphnet: a federated graph neural network framework for privacy-preserving traffic forecasting in heterogeneous IOT networks","source":"crossref","abstract":"However, in fifth-generation (5G) and beyond networks, where mobile systems support non-communication applications and act as heterogeneous Internet of Things (IoT) environments, accurate forecasting is essential for proactive resource management, network slicing optimisation, and Quality of Service (QoS) assurance. However, the distributed and privacy-sensitive nature of IoT data limits centralised learning approaches. This paper proposes FedGraphNet, a federated learning (FL) framework integrating a spatio-temporal graph neural network (ST-GNN) with differential privacy (DP) for collaborative traffic prediction without sharing raw data among distributed IoT nodes. FedGraphNet introduces the Adaptive Graph Attention Aggregation (AGAA) module to dynamically construct adjacency matrices from partial network observations, addressing structural heterogeneity in real-world IoT deployments. A communication-efficient TopK-SVD gradient compression strategy reduces uplink overhead by 68.4% with less than 1.2% accuracy loss. A calibrated Gaussian mechanism ensures (ε=1.0, δ=10-5)-differential privacy during aggregation. Experiments on TaxiBJ21, Metr-LA, and PEMS-BAY datasets show that FedGraphNet reduces Mean Absolute Error (MAE) by 2.84, 3.11, and 1.96 respectively compared with six baselines, including FedAvg-GCN, Diffusion Convolutional Recurrent Neural Network (DCRNN), and Graph-WaveNet. The framework also reduces communication cost by 3.1× and accelerates convergence by 54.4% over FedAvg-GCN. Notably, FedGraphNet with ε=1.0 DP outperforms the FedGNN baseline without privacy protection, indicating that calibrated noise injection can serve as an effective regulariser for non-independent and identically distributed (non-IID) IoT traffic distributions. These results demonstrate the trade-offs among spatio-temporal accuracy, communication efficiency, and formal privacy, validating FedGraphNet as a deployable solution for next-generation 5G IoT network management.","url":"https://doi.org/10.55529/jaimlnn.52.58.68","authors":["Zaripova Mukaddas Djumayozovna"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-30T06:20:58Z","doi":"10.55529/jaimlnn.52.58.68","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.31274/cc-20240624-1320","name":"Sphere decoding based on Deep Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.31274/cc-20240624-1320","authors":["Yangyue Ma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-26T18:23:20Z","doi":"10.31274/cc-20240624-1320","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.33915/etd.4169","name":"Validating a neural network-based online adaptive system","source":"crossref","abstract":"","url":"https://doi.org/10.33915/etd.4169","authors":["Yan Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-10-03T13:31:22Z","doi":"10.33915/etd.4169","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.1007/3-540-29719-0_1086","name":"Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/3-540-29719-0_1086","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-02-21T14:00:32Z","doi":"10.1007/3-540-29719-0_1086","addedAt":"2026-09-01T01:48:32.729Z","updatedAt":"2026-09-01T01:48:32.729Z"},{"id":"doi:10.2139/ssrn.5402089","name":"A Physics-Informed Neural Network Model to Predict Thermo-Oxidative/Thermal Aging of Viscoelastic Materials","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5402089","authors":["Hossein Naderi","Roozbeh Dargazany"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-22T18:39:18Z","doi":"10.2139/ssrn.5402089","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.13168/cs.2025.0005","name":"MIX RATIO DESIGN AND PERFORMANCE OF PERMEABLE CONCRETE BASED ON A BP NEURAL NETWORK","source":"crossref","abstract":"","url":"https://doi.org/10.13168/cs.2025.0005","authors":["Shaoka Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-24T08:08:09Z","doi":"10.13168/cs.2025.0005","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1016/j.istruc.2025.109242","name":"Equations and artificial neural network models for predicting displacement of lead rubber isolation systems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.istruc.2025.109242","authors":["Nhan Dinh Dao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-20T12:37:58Z","doi":"10.1016/j.istruc.2025.109242","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.56042/jsir.v84i1.14112","name":"Hybrid Quantum Graph Neural Network for Brain Tumor MR Image Classification","source":"crossref","abstract":"","url":"https://doi.org/10.56042/jsir.v84i1.14112","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-20T10:44:41Z","doi":"10.56042/jsir.v84i1.14112","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1016/j.measurement.2025.118586","name":"Neural network-enhanced dynamic light scattering for accurate sizing of large microparticles","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.measurement.2025.118586","authors":["Faezeh Torabi","Saeed Ghavami Sabouri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-29T23:32:31Z","doi":"10.1016/j.measurement.2025.118586","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1109/icdsg67714.2025.11381310","name":"Bot Detection on Twitter Using Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icdsg67714.2025.11381310","authors":["Muhammad Affiq Fikri","Fitriyani","Abdullah Hanifan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-14T19:33:02Z","doi":"10.1109/icdsg67714.2025.11381310","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1109/piers-spring66516.2025.11276246","name":"Deep Neural Network Based Microwave GaAs pHEMT Model","source":"crossref","abstract":"","url":"https://doi.org/10.1109/piers-spring66516.2025.11276246","authors":["C. I. Lee","I. Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-15T18:36:03Z","doi":"10.1109/piers-spring66516.2025.11276246","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.14311/nnw.2018.28.023","name":"Q LEARNING REGRESSION NEURAL NETWORK","source":"crossref","abstract":"","url":"https://doi.org/10.14311/nnw.2018.28.023","authors":["Mehmet Sarigül","Mutlu Avci"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-11-08T08:47:45Z","doi":"10.14311/nnw.2018.28.023","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.35314/rxd38a11","name":"Network Intrusion Detection System Using Convolutional Neural Network and Random Forest Classifiers","source":"crossref","abstract":"Network Intrusion Detection Systems (NIDS) play a crucial role in protecting networks from various forms of cyberattacks. However, conventional signature-based methods often fail to detect new or unknown threats and are prone to generating high false positive rates. This study proposes a hybrid approach combining Convolutional Neural Network (CNN) and Random Forest (RF) to develop a more adaptive and accurate intrusion detection system. CNN is employed to extract features from raw network traffic data, while RF serves as the primary classifier. The UNSW-NB15 dataset is used for training and testing the model. Evaluation results show that the hybrid model achieves an accuracy of 93.0%, average precision of 94%, recall of 90%, F1-score of 92%, and a false positive rate of 19.2%. These results demonstrate that the CNN–RF hybrid approach effectively improves intrusion detection performance and offers a promising solution for modern network security systems","url":"https://doi.org/10.35314/rxd38a11","authors":["Viky Luffiandi Rismawan","Elkaf Rahmawan Pramudya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-03T04:51:52Z","doi":"10.35314/rxd38a11","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1109/peeec67807.2025.00170","name":"Research on Tourism Recommendation Algorithm Based on Combined Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/peeec67807.2025.00170","authors":["Hongli Yi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-31T19:50:30Z","doi":"10.1109/peeec67807.2025.00170","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1049/icp.2024.3970","name":"Research of FPGA-based neural network accelerators","source":"crossref","abstract":"","url":"https://doi.org/10.1049/icp.2024.3970","authors":["Anqi Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-09T05:24:27Z","doi":"10.1049/icp.2024.3970","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1017/dce.2025.10034","name":"Making global sensitivity analysis feasible using neural network surrogates – ERRATUM","source":"crossref","abstract":"","url":"https://doi.org/10.1017/dce.2025.10034","authors":["Gihan Weerasinghe","Ramaseshan Kannan","Samila Bandara"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-18T05:30:43Z","doi":"10.1017/dce.2025.10034","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.15199/48.2025.07.18","name":"Artificial neural network approach for gas concentration determination using wavelength modulation spectroscopy","source":"crossref","abstract":"","url":"https://doi.org/10.15199/48.2025.07.18","authors":["Filip MUSIAŁEK"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-14T09:07:32Z","doi":"10.15199/48.2025.07.18","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1190/geo2024-0152.1","name":"A convolutional neural network-accelerated workflow for stochastic seismic property estimation","source":"crossref","abstract":"ABSTRACT As one of the major tools in resolving the nonuniqueness challenge in subsurface interpretation and reservoir characterization, stochastic inversion from post- and prestack seismic data remains challenging, which not only requires heavy computational resources but also relies on intensive manual supervision. Inspired by the recent advances in deep learning, particularly convolutional neural networks (CNNs) for interdisciplinary data integration, we develop a deep-learning workflow that enables stochastic property estimation by efficiently integrating seismic images with sparse wells. It starts with sampling a set of property prior models (PPMs) from densely measured properties at well locations and corrupting local seismic patterns with Gaussian noise. The core idea is to train a structure-guided CNN by mapping the contaminated seismic data with the sampled PPMs while enforcing structural consistency to avoid overfitting in the presence of sparse wells. Finally, the baseline and uncertainty of target properties are estimated by running multiple realizations of the trained CNN. As demonstrated by three examples, with minimum efforts of CNN architecture customization according to data availability, our workflow can accommodate various use cases, such as rock acoustic/elastic property estimation from 3D post-/angle-stack seismic data and soil geotechnical properties from 2D ultrahigh-resolution seismic data. In all examples, the machine predictions match seismic patterns well and are of high lateral consistency.","url":"https://doi.org/10.1190/geo2024-0152.1","authors":["Haibin Di","Aria Abubakar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-15T08:12:22Z","doi":"10.1190/geo2024-0152.1","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1016/j.neucom.2017.05.064","name":"Passivity of memristor-based recurrent neural networks with multi-proportional delays","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2017.05.064","authors":["Lijuan Su","Liqun Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-06-02T01:10:17Z","doi":"10.1016/j.neucom.2017.05.064","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1007/s40314-022-02097-6","name":"Synchronization of memristor-based complex-valued neural networks with time-varying delays","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s40314-022-02097-6","authors":["Yanzhao Cheng","Yanchao Shi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-09T15:02:52Z","doi":"10.1007/s40314-022-02097-6","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1201/9780367813239-5","name":"Information-Theoretic Approaches to Neural Network Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9780367813239-5","authors":["Mark D Plumbley"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-09-26T04:16:27Z","doi":"10.1201/9780367813239-5","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1088/0954-898x/7/2/003","name":"Introduction","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/7/2/003","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/7/2/003","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1007/978-94-007-4491-2_1","name":"Prolog: Memristor Minds","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-94-007-4491-2_1","authors":["Greg Snider"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-06-27T13:03:30Z","doi":"10.1007/978-94-007-4491-2_1","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1109/icamechs49982.2020.9310094","name":"Global Stability Criterion of Memristor-Based Recurrent Neural Networks with Time Delays","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icamechs49982.2020.9310094","authors":["Wudai Liao","Chaochuan Zhang","Jinhuan Chen","Xiaosong Liang","Jun Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-01-07T17:34:14Z","doi":"10.1109/icamechs49982.2020.9310094","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1109/9780470546826.ch3","name":"Neural Network Paradigms","source":"crossref","abstract":"","url":"https://doi.org/10.1109/9780470546826.ch3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-02-04T21:31:07Z","doi":"10.1109/9780470546826.ch3","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1088/0954-898x/4/2/004","name":"History-dependent attractor neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/4/2/004","authors":["Isaac Meilijson","Eytan Ruppin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/4/2/004","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1109/icgmrs66001.2025.11064958","name":"A Spiking Neural Network for Hyperspectral Image Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icgmrs66001.2025.11064958","authors":["Zhengda Han","Yu Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-11T17:41:59Z","doi":"10.1109/icgmrs66001.2025.11064958","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1364/lsc.2025.lsw4c.3","name":"Neural Network-Based Feature Tracking Models for Studying Atmospheric Refraction","source":"crossref","abstract":"Field measurements of scenes viewed through the lower atmosphere are made by using a time-lapse camera system. We develop and employ neural network models for the precise tracking of subtle feature shifts between frames due to atmospheric refraction.","url":"https://doi.org/10.1364/lsc.2025.lsw4c.3","authors":["Haoxin Tian","Hanyu Zhan","Jizhou Lai","Cheng Yuan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-29T11:07:43Z","doi":"10.1364/lsc.2025.lsw4c.3","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.25236/ajets.2025.080103","name":"Recognition of Oil and Gas Reservoir Space Based on Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.25236/ajets.2025.080103","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-06T12:57:22Z","doi":"10.25236/ajets.2025.080103","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1109/ncc63735.2025.10983005","name":"oSWNN: Optimized Small World Neural Network for Predictive Analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ncc63735.2025.10983005","authors":["Shubham Dwivedi","Om Jee Pandey","Rajesh M Hegde"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-13T13:43:35Z","doi":"10.1109/ncc63735.2025.10983005","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1109/ijcnn64981.2025.11227712","name":"MVBMR: Multi-View Breast Mass Recognition Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn64981.2025.11227712","authors":["Hua Yuan","Ning Zhao","Shoubin Dong","Yimao Yan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T18:46:15Z","doi":"10.1109/ijcnn64981.2025.11227712","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.4236/oalib.1113925","name":"Research on LiDAR Point Cloud Terrain Classification Based on Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.4236/oalib.1113925","authors":["Yifan Guo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-14T10:49:22Z","doi":"10.4236/oalib.1113925","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.14311/nnw.2021.31.007","name":"Normalized data barrier amplifier for feed-forward neural network","source":"crossref","abstract":"","url":"https://doi.org/10.14311/nnw.2021.31.007","authors":["Piyabute Fuangkhon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-07-07T07:32:47Z","doi":"10.14311/nnw.2021.31.007","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.4018/978-1-6684-2408-7.ch068","name":"Predicting Stock Market Price Using Neural Network Model","source":"crossref","abstract":"The present article predicts the movement of daily Indian stock market (S&amp;P CNX Nifty) price by using Feedforward Neural Network Model over a period of eight years from January 1st 2008 to April 8th 2016. The prediction accuracy of the model is accessed by normalized mean square error (NMSE) and sign correctness percentage (SCP) measure. The study indicates that the predicted output is very close to actual data since the normalized error of one-day lag is 0.02. The analysis further shows that 60 percent accuracy found in the prediction of the direction of daily movement of Indian stock market price after the financial crises period 2008. The study indicates that the predictive power of the feedforward neural network models reasonably influenced by one-day lag stock market price. Hence, the validity of an efficient market hypothesis does not hold in practice in the Indian stock market. This article is quite useful to the investors, professional traders and regulators for understanding the effectiveness of Indian stock market to take appropriate investment decision in the stock market.","url":"https://doi.org/10.4018/978-1-6684-2408-7.ch068","authors":["Naliniprava Tripathy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-17T11:47:50Z","doi":"10.4018/978-1-6684-2408-7.ch068","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1109/imas66694.2025.11387680","name":"Design of a Compact Dual-Frequency Impedance Matching Network Using Artificial Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/imas66694.2025.11387680","authors":["Abdulrasaq O. Amuda","Tologon Karataev","Omotayo Oshiga","Tahir Aja Zarma","Yahaya A. Aliyu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-20T21:13:37Z","doi":"10.1109/imas66694.2025.11387680","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.56042/ijct.v32i5.14716","name":"Synthesis of ternary nanofluids and optimization of their thermophysical properties using artificial neural network","source":"crossref","abstract":"","url":"https://doi.org/10.56042/ijct.v32i5.14716","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-27T05:59:26Z","doi":"10.56042/ijct.v32i5.14716","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1109/iwceaa68605.2025.11352188","name":"Fatigue Driving Detection by Fusing Neural Network and Physiological Indicator","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iwceaa68605.2025.11352188","authors":["Muze Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-28T20:56:39Z","doi":"10.1109/iwceaa68605.2025.11352188","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1109/eei67650.2025.11334851","name":"Design and Application of Memristor-CMOS Ternary Comparator","source":"crossref","abstract":"","url":"https://doi.org/10.1109/eei67650.2025.11334851","authors":["Jiangtao Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-22T20:57:57Z","doi":"10.1109/eei67650.2025.11334851","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.32920/26883595.v1","name":"Network Anomaly Detection Scheme Using Graph Neural Network","source":"crossref","abstract":"&lt;p&gt;Traditional intrusion detection systems (IDSs) and intrusion prevention systems (IPSs) focus on detecting, preventing, and blocking known attacks and obvious threats. Contrary to these systems, the Activity and Event Network (AEN) model is a newly proposed framework capable of identifying long-term threats and novel attack patterns such as custom crafted, multi-stage attack vectors, that the above-mentioned tools cannot detect as its design relies on a large random time varying graph model. In this thesis, the structural foundations of AEN graph are used as a basis to design a graph neural network (GNN)-based network anomaly detection scheme. This work is the first ever application of AEN to build a GNN model for anomaly detection purpose. The proposed model is evaluated using five different labelled datasets, namely, the DDoS, Tor-nonTor, Portmap, UDPLag, and SYN datasets, yielding preliminary promising results in terms of precision, recall, F1 score, and accuracy, chosen as performance metrics.&lt;/p&gt;","url":"https://doi.org/10.32920/26883595.v1","authors":["Patrice Kisanger"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-05T16:37:00Z","doi":"10.32920/26883595.v1","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.7717/peerj-cs.3394/fig-4","name":"Figure 4: Neural network architecture.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.3394/fig-4","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-02T08:33:42Z","doi":"10.7717/peerj-cs.3394/fig-4","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.7717/peerj-cs.2802/fig-3","name":"Figure 3: Simple neural network.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.2802/fig-3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-07T04:48:57Z","doi":"10.7717/peerj-cs.2802/fig-3","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.38007/nn.2020.010404","name":"Intelligent Speech Recognition and Sentiment Analysis Considering LSTM Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2020.010404","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T03:55:33Z","doi":"10.38007/nn.2020.010404","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1109/icepe65965.2025.11139507","name":"Artificial Neural Network Classifier for Dynamic Load Alteration Analysis in Active Distribution Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icepe65965.2025.11139507","authors":["Angana Dasgupta","Syamasree Biswas Raha","Kuntal Das","Shaimanti Das","Nabanita Sen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-05T18:04:32Z","doi":"10.1109/icepe65965.2025.11139507","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1117/12.3070322","name":"BTSEG-Nas: a neural network architecture search-based multimodal MRI segmentation network for brain tumors","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3070322","authors":["lingxiao zhao","xianwen zeng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-05T05:59:47Z","doi":"10.1117/12.3070322","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1145/3765325.3765364","name":"MFAN: Attention-Based Neural Network for Course Completion Forecasting","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3765325.3765364","authors":["Wanlei Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-01T07:41:51Z","doi":"10.1145/3765325.3765364","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.15199/48.2025.09.27","name":"Application of the ResNet50 Neural Network for RGB and IR image fusion","source":"crossref","abstract":"","url":"https://doi.org/10.15199/48.2025.09.27","authors":["Jarosław KOZIK"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-06T07:07:30Z","doi":"10.15199/48.2025.09.27","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.28925/2663-4023.2025.27.764","name":"INTELLIGENT RISK ASSESSMENT MODELS IN DISTRIBUTED SYSTEMS BASED ON THE NEURAL NETWORK APPROACH","source":"crossref","abstract":"In modern conditions of information systems functioning, the rapid growth of scale, complexity and distribution of computing resources is becoming one of the defining trends in the development of digital infrastructure. Within the framework of the widespread implementation of complex multi-component information systems that are distributed in nature and contain a large number of nodes, as well as a significant increase in the number and complexity of cyber threats focused on scalable systems, cybersecurity risks should be considered as a key factor in strategic planning of business processes. Regular analysis and assessment of cybersecurity risks allows determining the necessary and sufficient set of information protection tools, regulatory and organizational mechanisms to reduce information security threats, and ensures the process of building the most effective architecture of a comprehensive information security management system. Existing tools and assessment methodologies, which are mostly conceptual in nature and based on statistical approaches, are ineffective in analysis of large arrays of high-dimensional heterogeneous data and metrics of distributed systems. The article focuses on the current trends and existing approaches to information security risk assessment in distributed information systems. It analyzes the importance of risk management in the process of ensuring information security, and also describes a core principles of intelligent security risk assessment in distributed information systems based on the neural network approach. Research also presents a dynamic and comprehensive model of cyber risk assessment in distributed information systems based on back propagation neural network architecture and several methods of its optimization, which provides sufficient accuracy and reliability of risk assessment in the conditions of analysis of large arrays of heterogeneous input data.","url":"https://doi.org/10.28925/2663-4023.2025.27.764","authors":["Dmytro Palko"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-02T11:50:06Z","doi":"10.28925/2663-4023.2025.27.764","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.62476/amma.102409","name":"An Artificial Neural Network Solution to the Space-Time Fractional Partial Differential-Difference Toda Lattice Equation","source":"crossref","abstract":"","url":"https://doi.org/10.62476/amma.102409","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-03T20:58:08Z","doi":"10.62476/amma.102409","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1109/geoinformatics67279.2025.11173554","name":"Based on a Novel Hierarchical Convolutional Neural Network for Forest Fire Spread Research","source":"crossref","abstract":"","url":"https://doi.org/10.1109/geoinformatics67279.2025.11173554","authors":["Tianming Yang","Qingxiang Meng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-29T17:51:19Z","doi":"10.1109/geoinformatics67279.2025.11173554","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.63789/icatces.2025.26","name":"Performance Analysis of Original and Encrypted Data in Artificial Neural Network Training","source":"crossref","abstract":"","url":"https://doi.org/10.63789/icatces.2025.26","authors":["Rabia Günbaş","Merve Yılmaz","Mustafa Servet Kıran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-12T08:03:16Z","doi":"10.63789/icatces.2025.26","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1109/iciscn64258.2025.10934685","name":"Research on Ecotourism Recommendation using Graph Embedding based Graph Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iciscn64258.2025.10934685","authors":["Chenglong Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-27T22:45:26Z","doi":"10.1109/iciscn64258.2025.10934685","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.56952/arma-2025-0234","name":"Physics-Informed Neural Network Surrogate Modeling of Pressurized Cavity In Homogeneous and Bilayered Media","source":"crossref","abstract":"ABSTRACT: The theory of cavity expansion can explain the mechanical response induced by the expansion or contraction of cylindrical cavities that underpin a wide range of geotechnical applications. While analytical methods often impose restrictive assumptions of homogeneity and isotropy, numerical approaches like the Finite Element Method (FEM) offer greater flexibility but can be computationally prohibitive. To address these limitations, we propose a novel Physics-Informed Neural Network (PINN) framework as a surrogate model for pressurized cavity expansion problems in homogeneous and bilayered isotropic and linear-elastic host media, with arbitrary boundary conditions and constitutive parameters. The proposed model combines known governing equations with observational data, which ensures physical consistency while providing mesh-free, high-fidelity solutions for both homogeneous and bi-layered media. FEM simulations were taken as ground truth and prediction results demonstrate robust predictive accuracy across heterogeneous domains. The proposed PINN significantly accelerates the prediction process, achieving up to 160 times faster computation compared to FEM while maintaining competitive accuracy, though discrepancies in shear stress and boundary errors persist due to the non-convexity of the loss function. These challenges can be mitigated by refining the weights of the loss function terms, improving the network architecture, and using advanced optimization techniques.","url":"https://doi.org/10.56952/arma-2025-0234","authors":["Yulong Liu","Chloé Arson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-05T14:29:22Z","doi":"10.56952/arma-2025-0234","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.2139/ssrn.5208204","name":"Neural Network Permanent Magnet Synchronous Motor Modeling Capable of Self-Optimization","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5208204","authors":["Ruibo Hu","Liangyao Yu","Jiatong Leng","Dawei Gao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-07T16:05:43Z","doi":"10.2139/ssrn.5208204","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.31449/inf.v49i13.7154","name":"Attention-Based Bimodal Neural Network Speech Recognition System on FPGA","source":"crossref","abstract":"To further improve the accuracy of speech recognition technology, a neural network speech recognition system based on field programmable gate array was designed. Firstly, a neural network audiovisual bimodal speech recognition algorithm based on attention mechanism was designed. Then, a speech recognition platform based on on-site programmable gate arrays was built. The proposed algorithm is proved to have the lowest word error rate and character error rate of 3.17% and 1.56%, with the fastest convergence speed and lower final loss value. The algorithm converges quickly when the raining rounds are less than 10, and tends to stabilize when it is 20. The proposed speech recognition platform uses many DSP units in its design, with a utilization rate of 83.2%, the lowest power consumption of 2.21W, the highest energy efficiency ratio of 26.15, and the shortest processing time and faster running speed. In summary, the research algorithm can reasonably allocate learning weights, improve training speed, and has certain feasibility and effectiveness because of introducing attention mechanism. It has good application effects in speech recognition, which helps to improve the accuracy of language recognition algorithms and promote communication between humans and machines.","url":"https://doi.org/10.31449/inf.v49i13.7154","authors":["Aiwu Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-27T04:33:30Z","doi":"10.31449/inf.v49i13.7154","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.26434/chemrxiv-2025-w5npj","name":"Structure and Dynamics of CO2 at the Air-Water Interface from Classical and Neural Network Potentials","source":"crossref","abstract":"The accurate description of the structure and dynamics of CO2 at the instantaneous air-water interface, along with the effects of surface fluctuations on the CO2-transport processes, is essential for the development of negative emission technologies aimed to mitigate climate change. In this study, we performed molecular dynamics simulations of CO2 at the air-water interface using neural network potentials (NNPs) trained on ab initio data generated through density functional theory-based molecular dynamics simulations. We compared these results with classical force fields to assess their performance in modeling interfacial CO2 behavior. Our findings revealed that the asymmetric interactions, coupled with thermal surface fluctuations at the air-water interface signif- icantly influence CO2 transport into the aqueous phase. The simulations demonstrate that classical force fields underestimate both the free energy of CO2 transport and the strength of its interactions at the interface compared to the neural network potentials. The free energy and the interfacial dynamics of CO2 are primarily influenced by the distribution of water within the instantaneous interfacial water layer, responsible for creating asymmetric intermolecular interaction environment within the interfacial region.","url":"https://doi.org/10.26434/chemrxiv-2025-w5npj","authors":["Nitesh Kumar","Vyacheslav Bryantsev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-10T05:14:21Z","doi":"10.26434/chemrxiv-2025-w5npj","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1145/3747227.3747252","name":"TeethNet: Dual-Stream Attention Network for 3D Tooth Segmentation","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3747227.3747252","authors":["Yuquan Jing"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-13T09:53:11Z","doi":"10.1145/3747227.3747252","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.38007/nn.2022.030106","name":"Deep Learning Algorithm Based on Multi-layer Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2022.030106","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T18:13:37Z","doi":"10.38007/nn.2022.030106","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.38007/nn.2021.020202","name":"Intelligent Identification of Logistics Packaging Products Based on Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2021.020202","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T05:28:48Z","doi":"10.38007/nn.2021.020202","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.38007/nn.2022.030301","name":"Online Clothing Brand Recognition Based on Fully Connected Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2022.030301","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T18:14:38Z","doi":"10.38007/nn.2022.030301","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1109/cinti.2014.7028684","name":"The memristor-based associative learning network with retention loss","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cinti.2014.7028684","authors":["Xiao Yang","Wanlong Chen","Frank Z. Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-03-07T17:05:47Z","doi":"10.1109/cinti.2014.7028684","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1145/3768740.3768771","name":"Neural Network-Based Expert System for Identification of Safety Hazards in Distribution Network Equipment","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3768740.3768771","authors":["Jiageng Qiao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-01T06:47:01Z","doi":"10.1145/3768740.3768771","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.7717/peerj-cs.3097/fig-6","name":"Figure 6: Recurrent neural network.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.3097/fig-6","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-25T08:06:26Z","doi":"10.7717/peerj-cs.3097/fig-6","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.35658/1445-016-002-013","name":"Using Artificial Intelligence Models To Predict Bitcoin Prices:, Artificial Neural Network Model","source":"crossref","abstract":"","url":"https://doi.org/10.35658/1445-016-002-013","authors":["Hamida Seffahlou","Zohra Boudriche","Chouireb Djelloul"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-25T11:02:14Z","doi":"10.35658/1445-016-002-013","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1109/iciscn64258.2025.10934319","name":"Optimization of Museum Exhibition Space Design based on Graph Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iciscn64258.2025.10934319","authors":["Yuqin She"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-28T02:45:26Z","doi":"10.1109/iciscn64258.2025.10934319","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1109/cac67268.2025.11487899","name":"Power Quality Disturbance Classification Based on Markov Transition Field and Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cac67268.2025.11487899","authors":["Kaile Liu","Zhihao Zhang","Shuangyuan Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-28T19:45:57Z","doi":"10.1109/cac67268.2025.11487899","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1109/icm66518.2025.11322468","name":"Fast and Resource-Aware Implementation of Recurrent Neural Network Accelerators on FPGAs","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icm66518.2025.11322468","authors":["Tom Xaviour","Xiaofang Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-12T18:21:00Z","doi":"10.1109/icm66518.2025.11322468","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.21203/rs.3.rs-7254889/v1","name":"Spectral Neural Network Compression via Discrete Fourier Transform: A Post Hoc and Lightweight Approach","source":"crossref","abstract":"Abstract We introduce a spectral post hoc compression method for neural networks based on Discrete Fourier Transform (DFT) of complex weights. The approach filters low-magnitude frequencies to obtain sparse spectral representations while preserving accuracy. Theoretical results quantify energy preservation and output perturbation. We propose a principled thresholding rule, and demonstrate competitive performance compared to DCT and wavelets. Experiments on MNIST, CIFAR-10 and ResNet show 10–15× compression with negligible loss. Hardware metrics confirm reduced memory usage and improved inference latency. The method is lightweight, requires no retraining , and suits embedded AI.","url":"https://doi.org/10.21203/rs.3.rs-7254889/v1","authors":["Sghaier Samia","Nfata Houda"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-16T02:33:18Z","doi":"10.21203/rs.3.rs-7254889/v1","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.2139/ssrn.5812335","name":"A physics-informed neural network with muti-source constraints for phase-field models","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5812335","authors":["Lan Shang","Yong Zhang","Jie Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-26T19:39:07Z","doi":"10.2139/ssrn.5812335","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1101/2025.06.20.660661","name":"Learning, sleep replay and consolidation of contextual fear memories: A neural network model","source":"crossref","abstract":"Abstract Contextual fear conditioning is an experimental framework widely used to investigate how aversive experiences affect the valence an animal associates with an environment. While the initial formation of associative context-fear memories is well studied – dependent on plasticity in hippocampus and amygdala – the neural mechanisms underlying their subsequent consolidation remain less understood. Recent evidence suggests that the recall of contextual fear memories shifts from hippocampal-amygdalar to amygdalo-cortical networks as they age. This transition is thought to rely on sleep. In particular, neural replay during hippocampal sharp-wave ripple events seems crucial, though open questions regarding the involved neural interactions remain. Here, we propose a biologically informed neural network model of context-fear learning. It expands the scope of previous models through the addition of a sleep phase. Hippocampal representations of context, formed during wakefulness, are replayed in conjunction with cortical and amygdalar activity patterns to establish long-term encodings of learned fear associations. Additionally, valence-coding synapses within the amygdala undergo overnight adjustments consistent with the synaptic homeostasis hypothesis of sleep. The model reproduces experimentally observed phenomena, including context-dependent fear renewal and time-dependent increases in fear generalisation. Few neural network models have addressed fear memory consolidation and to our knowledge, ours is the first to incorporate a neural mechanism enabling it. Our framework yields testable predictions about how disruptions in synaptic homeostasis may lead to pathological fear sensitization and generalisation, thus potentially bridging computational models of fear learning and mechanisms underlying anxiety symptoms in disorders such as PTSD. Author Summary How do we learn to fear certain environments? Why do some fear memories fade while others persist or even grow stronger over time? Scientists have long used laboratory experiments to study how animals associate danger with a particular context. These studies have helped identify brain regions involved in fear learning, including the amygdala, hippocampus, and cortex, and have inspired many computational models of how fear is acquired in the brain. However, most models focus only on what happens when fear is first learned, overlooking how these memories evolve in the days that follow and the role of sleep in this process. In this work, we present a neural network model that captures how fear memories are strengthened or reshaped during sleep. It builds on earlier models by incorporating memory replay and synaptic homeostasis, two brain processes believed to support emotional memory consolidation. Our model identifies neural processes that help make fear memories persistent, suggests that sleep is necessary to maintain adaptive behaviour after threatening experiences, and proposes that sleep disruptions mediate the harmful impact of stress on emotional regulation. By extending amygdala-based models of fear learning to include post-learning dynamics, our work offers new insight into how emotional memories are stabilised.","url":"https://doi.org/10.1101/2025.06.20.660661","authors":["Lars Werne","Angus Chadwick","Peggy Seriès"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-26T11:25:18Z","doi":"10.1101/2025.06.20.660661","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1039/d5dd00210a/v2/decision1","name":"Decision letter for \"Mol2Raman: a graph neural network model for predicting Raman spectra from SMILES representations\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5dd00210a/v2/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-26T02:49:16Z","doi":"10.1039/d5dd00210a/v2/decision1","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1016/j.procs.2025.05.182","name":"Electromagnetic interference signal recognition based on neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.procs.2025.05.182","authors":["Wenxiu Li","Qiuping Luan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-10T12:37:50Z","doi":"10.1016/j.procs.2025.05.182","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.59671/rt89a","name":"Assessment of Improved Artificial Neural Network Models for Urban Air Quality Forecasting by Transboundary Pollutants","source":"crossref","abstract":"The assessment of artificial neural network models-sigmoid (ANN-sigmoid) and hyperbolic tangent (ANN-tanh) for real-time air pollution forecasting in a Korean coastal city was performed using 15 input independent variables (3 hours' earlier PM, gas and meteorological data influenced by 48 hours' earlier PM and gas data of a Chinese city). A feed-forward ANN technique of multilayer perception (MLP) with back-propagation training algorithm for error calculation was adopted with 15 hidden nodes and each prediction formula on four output variables was suggested. Root mean square error (RMSE) and the coefficient of determination (R2 ) assess each model's prediction ability between the predicted and measured values, before, during, and after the Yellow Dust period (March 18~27). Pearson R coefficients from the ANN-sigmoid (or ANN-tanh) model on PM10, PM2.5, NO2, and O3 were 0.907 (0.935), 0.860 (0.942), 0.860 (0.925), and 0.957 (0.946) before the dust period, 0.917 (0.943), 0.959 (0.969), 0.855 (0.853), and 0.954 (0.949) during its period, and 0.920 (0.947), 0.928 (0.938), 0.917 (0.896), and 0.923 (0.952) after its period, showing very high prediction accuracy overall. Scatter plots with empirical formulae and temporal distributions between the predicted and measured values showed excellent prediction performance by two models, and the ANN-tanh model produced more accurate results.","url":"https://doi.org/10.59671/rt89a","authors":["Soo-Min CHOI"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-11T20:03:59Z","doi":"10.59671/rt89a","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1109/rusautocon65989.2025.11177285","name":"Hybrid Neural Network Approach for Customer Churn Prediction in Web Services","source":"crossref","abstract":"","url":"https://doi.org/10.1109/rusautocon65989.2025.11177285","authors":["Aleksandra Vatian","Anton Kharitonov","Maxim Kardakov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T17:37:01Z","doi":"10.1109/rusautocon65989.2025.11177285","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.17559/tv-20250312002461","name":"Neural Network Identification of the Parameters of Ultra-High-Performance Concrete Bridges","source":"crossref","abstract":"","url":"https://doi.org/10.17559/tv-20250312002461","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-30T13:05:58Z","doi":"10.17559/tv-20250312002461","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1109/powerafrica65840.2025.11289165","name":"An Improved Multilayer Perceptron Neural Network Approach for Solar Irradiance Forecasting in Ghana","source":"crossref","abstract":"","url":"https://doi.org/10.1109/powerafrica65840.2025.11289165","authors":["Sheila Adjana Banawe","Mostafa Abdelaziz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-19T18:55:21Z","doi":"10.1109/powerafrica65840.2025.11289165","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1109/aann66429.2025.11257626","name":"A Multiscale Feature Fusion Network for Handwritten Chinese Character Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aann66429.2025.11257626","authors":["Sihan Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-01T18:23:40Z","doi":"10.1109/aann66429.2025.11257626","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.23919/acc63710.2025.11107540","name":"Co-state Neural Network for Real-time Nonlinear Optimal Control with Input Constraints","source":"crossref","abstract":"","url":"https://doi.org/10.23919/acc63710.2025.11107540","authors":["Lihan Lian","Uduak Inyang-Udoh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-21T18:17:51Z","doi":"10.23919/acc63710.2025.11107540","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1109/iccar64901.2025.11072979","name":"RBF Neural Network Adaptive Compensation Control for Robotic Arms","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccar64901.2025.11072979","authors":["Jun Hao","Jiacheng Lou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-15T17:40:06Z","doi":"10.1109/iccar64901.2025.11072979","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.51470/plantarchives.2025.v25.sp.ictpairs-105","name":"PRECISE CROP CLASSIFICATION OF HYPERSPECTRAL IMAGES USING NEURAL NETWORK-BASED FEATURE EXTRACTION AND CLASSIFICATION MODEL","source":"crossref","abstract":"","url":"https://doi.org/10.51470/plantarchives.2025.v25.sp.ictpairs-105","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-10T07:58:13Z","doi":"10.51470/plantarchives.2025.v25.sp.ictpairs-105","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1109/iciscn64258.2025.10934198","name":"3D Reconstruction Method of Indoor Scene Layout based on Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iciscn64258.2025.10934198","authors":["Yingying Lin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-28T02:45:26Z","doi":"10.1109/iciscn64258.2025.10934198","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1109/aann66429.2025.11257668","name":"Transformer-Driven Offset Convolutional Network for Brain Tumor MRI Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aann66429.2025.11257668","authors":["Mingrui Qi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-01T18:23:40Z","doi":"10.1109/aann66429.2025.11257668","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.1109/icoct64433.2025.11118434","name":"An Enhanced Intrusion Detection and Prevention using Artificial Neural Network Technique","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icoct64433.2025.11118434","authors":["Kathirvel P","B. Mary Reni"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-15T18:12:04Z","doi":"10.1109/icoct64433.2025.11118434","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:32.917Z"},{"id":"doi:10.38007/nn.2020.010202","name":"Facial Expression Recognition Based on Neural Network and Feature Extraction","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2020.010202","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T18:08:52Z","doi":"10.38007/nn.2020.010202","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.21203/rs.3.rs-6904582/v1","name":"Tourism Ecological Efficiency Assessment Based on Multi-Source Data Fusion and Graph Neural Network","source":"crossref","abstract":"Abstract Currently, research on the evaluation of tourism ecological efficiency based on multi-source data fusion and graph neural networks has significant limitations: at the data level, the integration of multi-source data faces challenges related to format, quality, and semantic differences; the complexity of cleaning and preprocessing may lead to information loss, and the limitations of a single data source are prominent, making it difficult to comprehensively cover the complex features of the tourism ecosystem; at the model level, traditional evaluation models cannot accurately identify ineffective sources, the handling of expected vs. unexpected outputs is not sufficiently scientific, and adapting to the dynamic demands of tourism ecological efficiency evaluation is challenging, which restricts the accuracy and application value of the evaluation results. This paper proposes a tourism eco-efficiency assessment method based on multi-source data fusion and graph neural networks. First, a comprehensive dataset is constructed by integrating multi-source information such as tourism statistics, environmental monitoring data, and socio-economic data. Then, the GNN model is used to mine the intrinsic connections and patterns in the data to more accurately evaluate the impact of tourism activities on the ecological environment. In addition, the distribution characteristics of tourism eco-efficiency in different periods and geographical regions were analyzed by considering spatial and temporal factors. Through case studies of typical tourism destinations, the effectiveness of the proposed method is verified, and its application value in practical tourism management and planning is discussed. Regression analysis was used to estimate tourism eco-efficiency based on a single data source. The data from 2015 to 2020 are selected to calculate the correlation coefficient between the growth rate of tourism revenue and environmental quality indicators. Based on the regression analysis of a single data source, the resulting tourism eco-efficiency score was 72 points in 2020. Using multi-source data fusion and graph neural network, the tourism eco-efficiency score was 85 points in the same year, 13 points higher than the traditional method. This study not only provides a new method for tourism eco-efficiency assessment but also helps to deepen our understanding of the complexity of tourism ecosystems and provides scientific support for the sustainable development of tourism destinations.","url":"https://doi.org/10.21203/rs.3.rs-6904582/v1","authors":["Luoyanzi Lin","Jiehua Lv"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-02T05:04:57Z","doi":"10.21203/rs.3.rs-6904582/v1","addedAt":"2026-09-01T01:48:32.917Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.20944/preprints202512.0715.v1","name":"Wind Power Forecast Using Multilevel Adaptive Graph Convolution Neural Network","source":"crossref","abstract":"Accurate forecasting of wind power is essential for maintaining the stability and efficiency of power networks as renewable energy sources become more integrated. This study proposes a multilevel spatial-temporal graph convolution network (MLAGCN) for wind power forecasting. The framework combines a multilevel adaptive graph convolution (MLAGC) and a lightweight temporal transformer (LWTT) to jointly model complex spatial-temporal relationships in wind power data. MLAGC is constructed using three adaptive graphs: a local-aware graph, a global-aware graph, and a structure-aware graph. These components form a flexible graph structure that effectively represents dynamic spatial interactions while LWTT learns short- and long-term sequential patterns. Experiments on real wind farm datasets demonstrated that the proposed model outperforms existing baselines. The model achieved an improved prediction accuracy and generalization, as indicated by a lower score of 43.44, mean absolute error (38.83), root mean square error (48.05) and a forecast loss of 0.22. These results demonstrates the effectiveness of temporal modeling and multilevel attention-based adaptive graph learning for high-resolution wind power forecasting.","url":"https://doi.org/10.20944/preprints202512.0715.v1","authors":["Oluwaseun E. Duntoye","Kowovi C. Alowonou","Do-Hoon Kwon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-10T03:06:26Z","doi":"10.20944/preprints202512.0715.v1","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.2139/ssrn.5162809","name":"Physics-Informed Neural Network (Pinn)-Based Numerical Simulation of Concrete Mechanical Responses","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5162809","authors":["Y. Ke","C.W. Liu","Shi-Shun Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-03T16:06:57Z","doi":"10.2139/ssrn.5162809","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1098/rsos.251278/v1/decision1","name":"Decision letter for \"Performance-Based Egress Safety Assessment of Underground Tunnels: Simulation and Artificial Neural Network Approaches\"","source":"crossref","abstract":"","url":"https://doi.org/10.1098/rsos.251278/v1/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-19T15:21:29Z","doi":"10.1098/rsos.251278/v1/decision1","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.36227/techrxiv.174114593.34611655/v1","name":"Fast Acquisition of Sensor Array Geometry of Whole-head Magnetoencephalograph Systems Using Neural Network","source":"crossref","abstract":"Acquiring position, orientation, and sensitivity of magnetometers in a helmet-shaped sensor array is crucial for accurate current source reconstruction in magnetoencephalography. To determine these parameters for each magnetometer, we utilize a spherical calibration coil array. In our previous study, the position and orientation of each magnetometer were determined as the solution of an inverse problem through a numerical search that minimized the difference between the theoretical magnetic field signals from each coil and the measured signals detected by the magnetometer. In this study, we applied a deep neural network to estimate the position and orientation of each magnetometer in the helmet-shaped sensor array without solving inverse problem. A total of 223 million pairs of a given magnetometer's five parameters (x, y, z, θ, and φ) and the corresponding theoretical magnetic field signals from the coils were used to train the neural network. The training process required approximately 53 hours using a commercially available GPU-equipped computer. The trained neural network was then applied to acquire the sensor geometry from magnetic field data obtained during the conventional calibration procedure for a 160-channel whole-head magnetoencephalograph system using a spherical calibration coil array. The position and orientation of each magnetometer estimated by this method deviated by an average of 0.65 mm and 0.51 degree, respectively, from those obtained via the conventional inverse problem approach. The acquisition of the geometry for all 160 magnetometers required less than 8 ms. With such high-speed acquisition, this approach opens possibilities for future applications in acquiring positional information of wearable sensor arrays whose structures change in real-time.","url":"https://doi.org/10.36227/techrxiv.174114593.34611655/v1","authors":["Yoshiaki Adachi","Daisuke Oyama","Gen Uehara"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-04T22:38:57Z","doi":"10.36227/techrxiv.174114593.34611655/v1","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1002/eng2.70258/v1/review2","name":"Review for \"Transfer Learning-Based Domain-Adaptive One-Dimensional Convolutional Neural Network for Fault Diagnosis of Rotating Machines\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/eng2.70258/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-01T00:21:31Z","doi":"10.1002/eng2.70258/v1/review2","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1039/d5ya00093a/v1/review2","name":"Review for \"A Sampling Fault Diagnosis Method for Power Battery Data in Cloud Platform Based on ResNet-BiLSTM Neural Network\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5ya00093a/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-25T21:09:14Z","doi":"10.1039/d5ya00093a/v1/review2","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-6581715/v1","name":"DiffNet-A Diffusion Convolutional Neural Network for Classification of Epileptic Seizure","source":"crossref","abstract":"Abstract Epileptic seizure detection using electroencephalogram (EEG) signals remains a challenging problem in neuroscience and biomedical engineering. In this study, we propose DiffNet, a novel Diffusion Convolutional Neural Network (DCNN) designed for accurate and automated classification of epileptic seizures. DiffNet combines spatial and temporal feature extraction capabilities, leveraging graph-based diffusion processes and convolutional layers to enhance classification performance. The model was evaluated on multiple benchmark EEG datasets, including Bonn, ResearchGate, and Mendeley Data, achieving an average accuracy of 99.7% during training and 98.3% during validation. Additionally, DiffNet outperformed existing state-of-theart algorithms across various statistical metrics such as precision (97.2%), sensitivity (96.8%), and F1-score (97.5%). These results highlight the robustness and reliability of DiffNet in addressing variability in EEG signal patterns. The proposed architecture also demonstrates reduced computational complexity, making it suitable for real-time seizure detection applications.","url":"https://doi.org/10.21203/rs.3.rs-6581715/v1","authors":["Laxmi Shaw","D. Ajitha","Sai Chakradhar Induvasi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-06T12:01:51Z","doi":"10.21203/rs.3.rs-6581715/v1","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.2139/ssrn.5082694","name":"A Graph Neural Network Explainability Strategy Driven by Key Subgraph Connectivity","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5082694","authors":["N.  L. Dai","D.  H. Xu","Yufei Gao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-04T19:41:37Z","doi":"10.2139/ssrn.5082694","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.21203/rs.3.rs-6461595/v1","name":"Prediction and Attribution Analysis of Surface Upward Longwave Radiation Based on a Hybrid Neural Network Model","source":"crossref","abstract":"Abstract Accurate prediction of surface upward longwave radiation (SULR) is crucial for understanding Earth’s energy balance and climate dynamics. Traditional approaches, such as physical models and empirical regressions, often fail to handle the complexity and variability of environmental data. To overcome these challenges, this study introduces a hybrid neural network model integrating several advanced techniques: the Alpha Evolution (AE) optimizer, a Transformer-LSTM neural network, Adaptive Bandwidth Kernel Density Estimation (ABKDE), and SHAP-based interpretability analysis. The AE optimizer fine-tunes model parameters to enhance convergence and efficiency. The Transformer-LSTM architecture uses self-attention and long short-term memory to capture complex temporal patterns in the data. ABKDE delivers reliable interval predictions for SULR, while SHAP uncovers feature importance and the rationale behind model decisions. Using datasets from two stations in the Taihu region, the hybrid model was compared with LSTM, GRU, Transformer, and theoretical models. Results indicate that the hybrid model notably outperforms traditional methods, as evidenced by improvements in R², RMSE, and MAE. Furthermore, ABKDE shows high accuracy in interval predictions, while SHAP analysis identifies water temperature, air temperature, and downward longwave radiation as the most influential factors affecting SULR. By offering a robust, interpretable SULR prediction model, this study advances Earth’s energy balance research and presents promising applications in climate modeling and environmental monitoring.","url":"https://doi.org/10.21203/rs.3.rs-6461595/v1","authors":["Kun Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-29T10:11:03Z","doi":"10.21203/rs.3.rs-6461595/v1","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.21428/594757db.9a835c96","name":"Fast Graph Neural Network for Image Classification","source":"crossref","abstract":"","url":"https://doi.org/10.21428/594757db.9a835c96","authors":["Mustafa Mohammadi Gharasuie","Luis Rueda"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-27T23:27:43Z","doi":"10.21428/594757db.9a835c96","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1002/itl2.650/v2/decision1","name":"Decision letter for \"Hybrid Convolutional Neural Network for Robust Attack Detection in Wireless Sensor Networks\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/itl2.650/v2/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-24T16:05:47Z","doi":"10.1002/itl2.650/v2/decision1","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.21667/978-5-7722-0427-6-160-166","name":"RECURRENT NEURAL NETWORK WITH COMBINE TRAINING","source":"crossref","abstract":"Recurrent neural network for identification of dynamic objects is proposed. The network uses weigh sum of neural network output signal and dynamic object output signal (teacher forcing). Such combine training guarantees a reduction of time learning and a safety of identification accuracy. The experimental results of nonlinear dynamic object identification are presented.","url":"https://doi.org/10.21667/978-5-7722-0427-6-160-166","authors":["V.P. Kuznetsov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-03T07:25:27Z","doi":"10.21667/978-5-7722-0427-6-160-166","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1145/3774791.3774805","name":"Novel Tensor Norm Optimization for Neural Network Training Acceleration","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3774791.3774805","authors":["Mridul Banik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-08T09:41:57Z","doi":"10.1145/3774791.3774805","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.7717/peerj.8854/fig-1","name":"Figure 1: Network structure of the region-based convolutional neural network.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj.8854/fig-1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-04-01T05:07:37Z","doi":"10.7717/peerj.8854/fig-1","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1145/3728199.3728242","name":"Ecological civilization evaluation model based on neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3728199.3728242","authors":["Xiwen Gao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-28T16:35:44Z","doi":"10.1145/3728199.3728242","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1109/igarss55030.2025.11242614","name":"Evaluating a Convolutional Neural Network Calibration Model with Laboratory Data","source":"crossref","abstract":"","url":"https://doi.org/10.1109/igarss55030.2025.11242614","authors":["John Bradburn","Mustafa Aksoy","Lennox Apudo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-25T18:26:49Z","doi":"10.1109/igarss55030.2025.11242614","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1109/iwcsn.2017.8276507","name":"Synchronization of memristor-based fractional-order neural networks with time-varying delays via pinning and adaptive control","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iwcsn.2017.8276507","authors":["Yi Xiang","Biwen Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-02-07T20:44:10Z","doi":"10.1109/iwcsn.2017.8276507","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1109/coconet.2018.8476905","name":"Notice of Retraction: Analysis of Hyperbolic Tangent Passive Resistive Neuron With CMOS-Memristor Circuit","source":"crossref","abstract":"","url":"https://doi.org/10.1109/coconet.2018.8476905","authors":["Madina Kenzhina","Irina Dolzhikova"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-10-30T06:31:38Z","doi":"10.1109/coconet.2018.8476905","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1088/0954-898x_5_3_002","name":"Modelling the effect of the missing fundamental with an attractor neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_5_3_002","authors":["Lubica Ben˘us˘ková"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:22Z","doi":"10.1088/0954-898x_5_3_002","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1088/0954-898x_6_3_004","name":"Learning internal representations in an attractor neural network with analogue neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_6_3_004","authors":["Daniel J Amit","Nicolas Brunel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:50Z","doi":"10.1088/0954-898x_6_3_004","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1039/d5tc02764k/v2/response1","name":"Author response for \"Tuneable Ionic Memristor Based on Bipolar Electrochemistry\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5tc02764k/v2/response1","authors":["Kin Wa Kwan","Alfonso Hing Wan Ngan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-15T21:06:09Z","doi":"10.1039/d5tc02764k/v2/response1","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.7717/peerj.9885/fig-4","name":"Figure 4: Neural network models.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj.9885/fig-4","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-01T03:15:22Z","doi":"10.7717/peerj.9885/fig-4","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.2139/ssrn.5929612","name":"Gated Recurrent Neural Network Enhanced Wind Power Prediction Accuracy Using TPE Bayesian Optimization","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5929612","authors":["Mohsin  Ali Qazi","Dong  Hsiao Chiang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-17T09:50:19Z","doi":"10.2139/ssrn.5929612","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1002/eng2.70373/v2/decision1","name":"Decision letter for \"Enhancing Cardiovascular Disease Analysis in Healthcare Systems With Hybrid Random Forest and Neural Network Algorithm\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/eng2.70373/v2/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T23:21:22Z","doi":"10.1002/eng2.70373/v2/decision1","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.2139/ssrn.5500803","name":"Modeling gamma radiation intensity in monazite rich coastal environments using neural network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5500803","authors":["Miriam  Mathias Gigi","Jacyra Soares","Marcos Orlando"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-18T01:36:57Z","doi":"10.2139/ssrn.5500803","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1364/opticaopen.28902587","name":"Q-factor Analysis in Free Space Optical Communication and Neural Network-Based Prediction","source":"crossref","abstract":"Free Space Optics (FSO) provides a promising alternative where fiber-optic deployment is impractical due to cost or fragility. However, FSO performance is highly vulnerable to atmospheric disturbances such as fog, rain, and dust, which can significantly degrade signal quality. To optimize system performance under varying conditions, it is crucial to understand how the Q-factor responds to changes in system parameters. This study investigates the effects of bit rate, filter type, transmitter and receiver aperture diameters, and transmission range on the Q-factor in FSO systems. We developed a detailed simulation model using OptiSystem to generate data, which was then used to train a feedforward neural network via MATLAB’s Neural Network Tool (NN-Tool) using the Levenberg–Marquardt algorithm. This model effectively captures complex, nonlinear relationships between input parameters and Q-factor outcomes, allowing accurate predictions without further simulations. The hybrid approach of combining simulation data with neural network-based modeling offers a practical and user-friendly tool for performance prediction and system planning. This research contributes to the design and optimization of high-data-rate FSO systems by addressing existing limitations in modeling and parameter tuning.","url":"https://doi.org/10.1364/opticaopen.28902587","authors":["Mohammad Sikder","Fahim Sakib","Md Lokman Hossen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-06T10:25:23Z","doi":"10.1364/opticaopen.28902587","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1002/eng2.70373/v4/review2","name":"Review for \"Enhancing Cardiovascular Disease Analysis in Healthcare Systems With Hybrid Random Forest and Neural Network Algorithm\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/eng2.70373/v4/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T23:21:22Z","doi":"10.1002/eng2.70373/v4/review2","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.21203/rs.3.rs-6654555/v1","name":"Research on the Performance Evaluation of Agricultural Product Distribution Supply Chain Based on BP Neural Network","source":"crossref","abstract":"Abstract Supply chain management is in a period of rapid development, and future competition in the distribution industry will be centered around competition between supply chains. Agricultural product distribution, as an important part of modern distribution, plays a positive role in ensuring people's daily lives and improving the modernization level of agricultural distribution. Therefore, clarifying the performance of the supply chain is the key to enhancing its development level and market competitiveness. Given that most current supply chain performance evaluation studies focus on the industrial sector and there are limited methods for evaluating the performance of agricultural product distribution supply chains, this paper attempts to analyze the performance evaluation system of agricultural product supply chains centered on supermarkets. In terms of research methodology, it is based on the BP neural network and considers five aspects of the agricultural product distribution supply chain: financial situation, operational capability, growth capability, customer satisfaction, and agility. A corresponding evaluation index system is established. Finally, Yonghui Supermarket and its suppliers are used to apply this performance evaluation system in practice, further identifying beneficial ways to improve the performance level of agricultural product distribution supply chains.","url":"https://doi.org/10.21203/rs.3.rs-6654555/v1","authors":["lu zheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-09T04:41:20Z","doi":"10.21203/rs.3.rs-6654555/v1","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.2139/ssrn.5048252","name":"Advancing Autonomous Vehicle Navigation through Hybrid Fuzzy-Neural Network Training Systems","source":"crossref","abstract":"In the evolving realm of autonomous vehicle navigation, the integration of fuzzy logic and neural networks presents a formidable challenge, particularly in the context of real-time, on-the-fly neural network training. This paper addresses the gap in dynamic and adaptable training methods necessary for navigating unpredictable environments with limited computational resources. The primary objective of our study is to empirically validate a hybrid training approach that combines&amp;nbsp;fuzzy logic with back-propagation learning algorithms, aiming to optimize neural network performance under hardware constraints. Our methodology leverages a fuzzy logic trainer to provide initial training sets dynamically, which guide the neural network in adjusting its weights in real time, thus facilitating adaptive learning during navigation tasks. The findings reveal that this integrated approach not only enhances the learning efficiency of neural networks but also significantly improves navigation accuracy in real-time scenarios. These advancements contribute to the field by demonstrating the feasibility of deploying more adaptable and robust autonomous navigation systems, potentially expanding their application in more diverse and challenging environments.","url":"https://doi.org/10.2139/ssrn.5048252","authors":["Ammar Alzaydi","Kahtan Abedalrhman","Ibrahim Alotaibi","Fahad Alessa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-27T13:16:57Z","doi":"10.2139/ssrn.5048252","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.23977/autml.2025.060208","name":"Design and Implementation of a Flower Image Classification System Based on Convolutional Neural Network (CNN)","source":"crossref","abstract":"","url":"https://doi.org/10.23977/autml.2025.060208","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-15T09:34:17Z","doi":"10.23977/autml.2025.060208","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1109/ssitcon66133.2025.11342027","name":"Bayesian-Optimized Backpropagation Neural Network for Enterprise Training Management System","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ssitcon66133.2025.11342027","authors":["Quan Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-22T20:58:23Z","doi":"10.1109/ssitcon66133.2025.11342027","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1364/cleo_si.2025.ss169_7","name":"32-input Optical Neural Network Chip based on Multi-Plane Light Conversion","source":"crossref","abstract":"We demonstrate silicon-photonic 32-input optical neural network based on multi-plane light conversion (MPLC). Thanks to the superior scalability of MPLC, image classification task is achieved with &gt;90% accuracy using one-tenth the number of phase shifters.","url":"https://doi.org/10.1364/cleo_si.2025.ss169_7","authors":["Chun Ren","Ryota Tanomura","Kazuki Ichinose","Yoshiaki Nakano","Takuo Tanemura"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-24T20:07:18Z","doi":"10.1364/cleo_si.2025.ss169_7","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1021/acssensors.3c00541","name":"Correlation between Sensing Accuracy and Read Margin of a Memristor-Based NO Gas Sensor Array Estimated by Neural Network Analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acssensors.3c00541","authors":["Doowon Lee","Myoungsu Chae","Jinsu Jung","Hee-Dong Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-10T20:46:27Z","doi":"10.1021/acssensors.3c00541","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.24874/qf.25.132","name":"COMPREHENSIVE REVIEW OF CONVOLUTIONAL NEURAL NETWORK (CNN) MODELS FOR DRUG DETECTION USING IMAGE PROCESSING","source":"crossref","abstract":"","url":"https://doi.org/10.24874/qf.25.132","authors":["Youa Raj Chettri","Dheeraj Kumar Prasad","Rahul Shah"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-23T15:22:31Z","doi":"10.24874/qf.25.132","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.48047//ijiee.2025.15.4.35","name":"AI-Powered Money Laundering Detection in Institutional Trading Using Advanced Neural Network Algorithms in Financial Institutions 2025","source":"crossref","abstract":"","url":"https://doi.org/10.48047//ijiee.2025.15.4.35","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-05T09:24:51Z","doi":"10.48047//ijiee.2025.15.4.35","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1109/ic3it66137.2025.11341096","name":"Evaluation of English Translation Quality based on Hybrid Neural Network Model","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ic3it66137.2025.11341096","authors":["Shiyu Zheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-22T20:58:29Z","doi":"10.1109/ic3it66137.2025.11341096","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1007/978-981-96-0332-9_7","name":"Dynamic Analysis of Memristive Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-96-0332-9_7","authors":["Yongbin Yu","Xiangxiang Wang","Xiao Feng","Jiarun Shen","Nyima Tashi","Pinaki Mazumder"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-26T14:14:47Z","doi":"10.1007/978-981-96-0332-9_7","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1016/b978-0-443-26482-5.00005-5","name":"Web-based brain tumor classification app using convolutional neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-26482-5.00005-5","authors":["Olusegun O. Odewole","Fadi Al-Turjman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-18T22:36:33Z","doi":"10.1016/b978-0-443-26482-5.00005-5","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.62072/acm.2025.080107","name":"General Multiple Sigmoid Functions Relied Complex Valued Multivariate Trigonometric and Hyperbolic Neural Network Approximations","source":"crossref","abstract":"Here we research the multivariate quantitative approximation of complex valued continuous functions on a box of RN , N ∈ N, by the multivariate normalized type neural network operators. We investigate also the case of approximation by iterated multilayer neural network operators. These approximations are achieved by establishing multidimensional Jackson type inequalities involving the multivariate moduli of continuity of the engaged function and its partial derivatives. Our multivariate operators are defined by using a multidimensional density function induced by general multiple sigmoid func- tions. The approximations are pointwise and uniform. The related feed-forward neural network are with one or multi hidden layers. The basis of our theory are the introduced multivariate Taylor formulae of trigonometric and hyperbolic type.","url":"https://doi.org/10.62072/acm.2025.080107","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-30T13:45:13Z","doi":"10.62072/acm.2025.080107","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.30525/978-9934-26-597-6-26","name":"Text Recognition in Challenging Conditions Using Neural Network-Based Computer Vision Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.30525/978-9934-26-597-6-26","authors":["Vladyslav Khotunov","Maksym Lutsenko","Stanislav Marchenko"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-06T20:18:06Z","doi":"10.30525/978-9934-26-597-6-26","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1109/neurel.2002.1057978","name":"Neural network control of shared ATM buffer","source":"crossref","abstract":"","url":"https://doi.org/10.1109/neurel.2002.1057978","authors":["I.S. Reljin","B.D. Reljin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-06-26T00:51:07Z","doi":"10.1109/neurel.2002.1057978","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.5194/egusphere-egu24-7272","name":"Estimation of Hydraulic and Thermal Parameters Using Convolutional Neural Network and Hydraulic Tomography","source":"crossref","abstract":"The ground-source heat pump (GSHP) is an efficient thermal exchange system that utilizes natural environmental heat for heating and cooling. Heat exchange efficiency depends not only on factors such as pipe material and diameter but also on groundwater's flow field and soil's thermal parameters. This study aims to estimate hydraulic and geothermal parameters by utilizing convolutional encoder-decoder architecture neural networks and hydraulic tomography, a data collection strategy. The proposed method is named THT-NN. To examine the capability of the THT-NN on parameter estimation, we developed numerical experiments to test THT-NN. Further, to produce the training and validation data pairs, we create a two-dimensional heterogeneous groundwater and heat transport model by TOUGH2 with constant injection patterns and 10000+ realizations of parameter fields. The groundwater heads and temperature collected from the monitoring well groups are used to develop two channels of the input layers, and four parameters' fields (hydraulic conductivity, porosity, heat conductivity, and specific heat) are used to develop four channels of the output layers. Subsequently, the estimated parameters results are examined by R2 and root mean squared error. The performance of the proposed THT-NN is discussed in this study.","url":"https://doi.org/10.5194/egusphere-egu24-7272","authors":["Che-Wei Liang","Jui-Pin Tsai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-08T16:44:50Z","doi":"10.5194/egusphere-egu24-7272","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.2139/ssrn.5262669","name":"Comprehensive Analysis of Partition Methods and Neural Network Architectures for Prediction in Cryptocurrencies Time Series","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5262669","authors":["Leon Beleña","Pablo Hidalgo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-21T01:39:03Z","doi":"10.2139/ssrn.5262669","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1109/tgrs.2025.3602030/v2/decision1","name":"Decision letter for \"Physics-Inspired Neural Network for Joint Inversion of Multialtitude 3-D Gravity and Vertical Gradient\"","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tgrs.2025.3602030/v2/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-21T22:59:05Z","doi":"10.1109/tgrs.2025.3602030/v2/decision1","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.2139/ssrn.5255545","name":"A Physics-Informed Neural Network Model to Predict Thermo-Oxidative/Thermal Aging of Viscoelastic Materials","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5255545","authors":["Hossein Naderi","Roozbeh Dargazany"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-15T12:40:54Z","doi":"10.2139/ssrn.5255545","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1101/2025.02.03.25321462","name":"Miniaturization of Epileptic Abnormal Electrocorticogram Detector Using 3D Convolutional Neural Network","source":"crossref","abstract":"Abstract Epilepsy is a neurological disorder characterized by sudden and recurrent seizures caused by abnormal electrical activity in the brain. Responsive Neurostimulation (RNS) offers a promising treatment option for patients with drug-resistant epilepsy. Responsive Neurostimulation (RNS) is an implantable device that employs a closed-loop system. It continuously monitors brain activity through electro-corticogram (ECoG) recordings. When the system detects seizure activity, it delivers direct electrical stimulation to the brain to suppress the seizure. Seizure detection algorithms require patient-specific optimization, leading to increased interest in deep learning approaches in recent years. While deeper network architectures generally improve detection accuracy, their implementation in implantable devices is constrained by limited hardware resources and the restricted number of electrode channels available for ECoG monitoring. To ensure the practical feasibility of RNS, it is crucial to systematically minimize both the computational costs of patient-specific deep learning models and the number of connected ECoG electrodes. This study systematically reduced the number of electrode channels and computational costs in seizure detection models by analyzing the spatiotemporal kernels learned by the first convolutional layer of a 3D convolutional neural network (3D CNN) trained on 3D ECoG data. This approach capitalizes on the network’s ability to learn spatial relationships between grid electrodes and the temporal dynamics of ECoG signals. The performance comparison between the downsized seizure detection CNN model and the original CNN model revealed that, for at least some patients, it is possible to maintain inference performance while reducing the model size.","url":"https://doi.org/10.1101/2025.02.03.25321462","authors":["Moemi Yamaji","Shinjiro Yamamasu","Yuto Hirano","Yuki Hayashida"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-05T18:55:21Z","doi":"10.1101/2025.02.03.25321462","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.2139/ssrn.5770518","name":"PETNN: Recurrent Neural Network Meets Energy Transition Model","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5770518","authors":["Zhou Wu","Junyi An","Baile Xu","Jian Zhao","Fu-rao Shen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-19T11:57:19Z","doi":"10.2139/ssrn.5770518","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1088/2634-4386/addee7/v1/review1","name":"Review for \"A spiking photonic neural network of 40,000 neurons, trained with latency and rank-order coding for leveraging sparsity\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2634-4386/addee7/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-31T17:07:02Z","doi":"10.1088/2634-4386/addee7/v1/review1","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1039/d5dd00210a/v1/decision1","name":"Decision letter for \"Mol2Raman: a graph neural network model for predicting Raman spectra from SMILES representations\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5dd00210a/v1/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-26T02:49:16Z","doi":"10.1039/d5dd00210a/v1/decision1","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1109/icces67310.2025.11336239","name":"GraphPest: A Graph Neural Network Framework for Pest Detection in Agricultural Environment","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icces67310.2025.11336239","authors":["Rajasekaran Arunachalam","J Mohana"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-21T21:06:29Z","doi":"10.1109/icces67310.2025.11336239","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.2514/6.2025-3228","name":"Graph Neural Network-Guided Aerodynamic Shape Optimization for Conceptual Design of Supersonic Transport Wings","source":"crossref","abstract":"","url":"https://doi.org/10.2514/6.2025-3228","authors":["Yiren Shen","Juan Alonso"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-16T21:24:43Z","doi":"10.2514/6.2025-3228","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1109/icip55913.2025.11084309","name":"FGA-NN: Film Grain Analysis Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icip55913.2025.11084309","authors":["Zoubida Ameur","Frédéric Lefebvre","Philippe Delagrange","Miloš Radosavljević"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-18T19:41:38Z","doi":"10.1109/icip55913.2025.11084309","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.21203/rs.3.rs-7246244/v1","name":"Leveraging Quantum Superposition to Infer the Dynamic Behavior of a Spatial-Temporal Neural Network Signaling Model","source":"crossref","abstract":"Abstract The exploration of new problem classes for quantum computation is an active area of research. In this paper, we introduce and solve a novel problem class related to dynamics on large-scale networks relevant to neurobiology and machine learning. Specifically, we ask if a network can sustain inherent dynamic activity beyond some arbitrary observation time or if the activity ceases through quiescence or saturation via an ’epileptic’-like state. We show that this class of problems can be formulated and structured to take advantage of quantum superpo- sition and solved efficiently using a coupled workflow between the Grover and Deutsch–Jozsa quantum algorithms. To do so, we extend their functionality to address the unique requirements of how input (sub)sets into the algorithms must be mathematically structured while simulta- neously constructing the inputs so that measurement outputs can be interpreted as meaningful properties of the network dynamics. This, in turn, allows us to answer the question we pose.","url":"https://doi.org/10.21203/rs.3.rs-7246244/v1","authors":["Gabriel Silva"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-25T14:29:20Z","doi":"10.21203/rs.3.rs-7246244/v1","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.21203/rs.3.rs-7376845/v1","name":"Geometric Fault-Tolerant Neural Network Tracking Control of Unknown Systems on Matrix Lie Groups","source":"crossref","abstract":"Abstract We present a geometric neural network-based tracking controller for systems evolving on matrix Lie groups under unknown dynamics, actuator faults, and bounded disturbances. Leveraging the left-invariance of the tangent bundle of matrix Lie groups, viewed as an embedded submanifold of the vector space RN×N , we propose a set of learning rules for neural network weights that are intrinsically compatible with the Lie group structure and do not require explicit parameterization. Exploiting the geometric properties of Lie groups, this approach circumvents parameterization singularities and enables a global search for optimal weights. The ultimate boundedness of all error signals—including the neural network weights, the coordinate-free configuration error function, and the tracking velocity error—is established using Lyapunov’s direct method. To validate the effectiveness of the proposed method, we choose to present illustrative simulation results for decentralized formation control of multi-agent systems on the Special Euclidean group, where accurate control with fast adaptation is critical.","url":"https://doi.org/10.21203/rs.3.rs-7376845/v1","authors":["Robin Chhabra","Farzaneh Abdollahi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-02T03:45:06Z","doi":"10.21203/rs.3.rs-7376845/v1","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.2139/ssrn.5145096","name":"A Thesaurus Constructing Method in Electric Power Domain Based On Word2vec Model and Quantum Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5145096","authors":["Hongying He"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-19T16:42:12Z","doi":"10.2139/ssrn.5145096","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.3850/978-981-09-4424-7_work3","name":"The Memristor Circuits and Applications","source":"crossref","abstract":"","url":"https://doi.org/10.3850/978-981-09-4424-7_work3","authors":["Alex Pappachen James"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-06-02T15:08:38Z","doi":"10.3850/978-981-09-4424-7_work3","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1109/iciscn64258.2025.10934202","name":"Audit Risk Identification based on Mutual Information with Backpropagation Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iciscn64258.2025.10934202","authors":["Di Su"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-28T02:45:26Z","doi":"10.1109/iciscn64258.2025.10934202","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1109/iciscn64258.2025.10934631","name":"Heart Disease Classification using Adaptive Recurrent Neural Network Method","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iciscn64258.2025.10934631","authors":["M. Divya","A. Karthikeyan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-28T02:45:26Z","doi":"10.1109/iciscn64258.2025.10934631","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1109/idap68205.2025.11222368","name":"Predicting Happiness Index with Neural Network-Based Learning Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1109/idap68205.2025.11222368","authors":["İlker Gür","Ferhat Atasoy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-11T18:26:25Z","doi":"10.1109/idap68205.2025.11222368","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.23919/ccc64809.2025.11178355","name":"Adaptive Backstepping Fault-Tolerant Control of Continuum Robots Based on RBF Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.23919/ccc64809.2025.11178355","authors":["Hongyun Liu","Weidong Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-10T17:34:54Z","doi":"10.23919/ccc64809.2025.11178355","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1109/iciscn64258.2025.10934506","name":"College Physical Health Analysis System Based on Apriori - Deep Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iciscn64258.2025.10934506","authors":["Lei Cui"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-28T02:45:26Z","doi":"10.1109/iciscn64258.2025.10934506","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1109/ijcnn64981.2025.11227716","name":"HGMamba: Enhancing 3D Human Pose Estimation with a HyperGCN-Mamba Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn64981.2025.11227716","authors":["Hu Cui","Tessai Hayama"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T18:46:15Z","doi":"10.1109/ijcnn64981.2025.11227716","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1109/ccsb66722.2025.11154216","name":"Application of Lightweight Neural Network Model in Garbage Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ccsb66722.2025.11154216","authors":["Zhe Zhang","XingYu Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-17T17:29:13Z","doi":"10.1109/ccsb66722.2025.11154216","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1016/b978-1-85617-120-5.50013-9","name":"Neural Network Semiconductors","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-1-85617-120-5.50013-9","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-01T03:02:21Z","doi":"10.1016/b978-1-85617-120-5.50013-9","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1140/epjp/s13360-026-07682-w","name":"A neural circuit without consuming Joule heat, and synchronization coupled by a memristor","source":"crossref","abstract":"","url":"https://doi.org/10.1140/epjp/s13360-026-07682-w","authors":["Qi Cao","Binchi Wang","Chunni Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-28T04:07:10Z","doi":"10.1140/epjp/s13360-026-07682-w","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1088/0954-898x_8_1_008","name":"Stereo vision using a microcanonical mean field annealing neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_8_1_008","authors":["Jeng-Sheng Huang","Hsiao-Chung Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T16:04:59Z","doi":"10.1088/0954-898x_8_1_008","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.20944/preprints202510.0488.v1","name":"Matignon-Based Stability and Weight Synchronization of a Fractional Time Delay Neural Network Model","source":"crossref","abstract":"Artificial neural networks (ANNs) are powerful models inspired by the structure and function of the human brain. They are widely used for tasks such as classification, prediction, and model recognition. This study examines the stability of fractional-order neural networks with neuronal conditions, dynamic behavior, synchronization, and delays of time. Synchronization and stability for delayed neural network models are two important aspects of dynamic behavior. For a calculated fractionalorder, the state of the state variable wi(t) are synchronized with each other. Weight synchronization of wi (i = 1, 2, 3, . . . ,6) provides coherent updates during training, helping neural networks to study stable models. The incommensurate fractional-orders are linked to a system where each dynamic component develops with a different value, i.e. qi ≠ qj (i ≠ j) is inconsistent. These fractionalorders are calculated for the system’s eigenvalues and their singular points within the stability region defined by the Matignon-based stability. As the time delay decreases, more activation functions are induced, and the variable state of w3(t) requires longer relaxation times to be more stable than the variable state of w4(t). The Grunwald-Letnikov method is used to solve a fractional neural network system numerically and effectively handle fractional derivatives. This approach helps to more accurately simulate memory in neural networks.","url":"https://doi.org/10.20944/preprints202510.0488.v1","authors":["Asif Ullah","Muhammad Shuaib"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-10T00:18:26Z","doi":"10.20944/preprints202510.0488.v1","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1098/rsos.251278/v2/decision1","name":"Decision letter for \"Performance-Based Egress Safety Assessment of Underground Tunnels: Simulation and Artificial Neural Network Approaches\"","source":"crossref","abstract":"","url":"https://doi.org/10.1098/rsos.251278/v2/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-19T15:21:29Z","doi":"10.1098/rsos.251278/v2/decision1","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.21203/rs.3.rs-6504224/v1","name":"Adaptive Multi-Agent Graph Neural Network (AMAGNN) for Congestion Control in VANET","source":"crossref","abstract":"Abstract Similar approaches are very useful in Vehicular Ad Hoc Networks in which: a flood of traffic and events occurs, especially in Intelligent Transportation Systems (ITS), as congestion control can have a huge impact in efficient traffic field and communication. The existing congestion control mechanisms are not suitable for this type of dynamic network topology and vehicle mobility. In response to these challenges, we propose an Adaptive Multi-Agent Graph Neural Network (AMAGNN), which utilizes graph neural networks (GNNs) and multi-agent reinforcement learning (MARL) for congestion control in vehicular ad hoc networks (VANETs). Institute, “AMAGNN models VANETs as dynamic graphs, with vehicles being intelligent agents that cooperatively learn to optimize data propagation and alleviate network congestion. Optimizes for scalability and adaptability by dynamically responding to network topology changes and traffic density variation. Results show that the proposed AMAGNN model outperforms current practices in congestion control for VANETs on all the key performance metrics. It attains Packet Delivery Ratio (92.5%), lowest delay (28.4 ms), and maximum throughput (275.6 kbps) which shows reliability and efficiency in communication. It also achieves the lowest congestion level (0.35) and average waiting time (0.31 s), highlighting its ability to reduce traffic and delay. AMAGNN achieves the best performance, compared with methods such as GCN-RL, DQN Adaptive, and MA-PPO, highlighting the effectiveness of adaptive multi-agent graph neural networks in the ever-changing vehicular environment.","url":"https://doi.org/10.21203/rs.3.rs-6504224/v1","authors":["Santosh Kumar Maharana","Prashanta Kumar Patra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-07T11:51:59Z","doi":"10.21203/rs.3.rs-6504224/v1","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.2139/ssrn.5318102","name":"Weak Transnet: A Petrov-Galerkin Based Neural Network Method for Solving Elliptic Pdes","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5318102","authors":["Zhihang Xu","Min Wang","Zhu Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-24T14:51:49Z","doi":"10.2139/ssrn.5318102","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.2139/ssrn.5717405","name":"High-Throughput Screening of Violet-Light-Excitable Phosphors Driven by Graph Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5717405","authors":["Zichun Zhou","Chen Ming","Yiyang Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-07T14:43:13Z","doi":"10.2139/ssrn.5717405","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.2139/ssrn.5439838","name":"CRINET: Enhanced Intrusion Detection through Optimized Convolutional Neural Network-Reformer Integration","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5439838","authors":["Pinghao Wang","Normalia Samian","Azizol ABDULLAH","Winston Seah"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-04T12:39:39Z","doi":"10.2139/ssrn.5439838","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1039/d5dd00210a/v3/decision1","name":"Decision letter for \"Mol2Raman: a graph neural network model for predicting Raman spectra from SMILES representations\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5dd00210a/v3/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-26T02:49:16Z","doi":"10.1039/d5dd00210a/v3/decision1","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.36227/techrxiv.174123177.79937220/v1","name":"A Residual Neural Network Approach to Transmitter Localization","source":"crossref","abstract":"This paper presents a method for locating a wireless signal source using signal strength measurements taken along the border of a 256x256-m 2 area. The method leverages a deep Residual Neural Network (ResNet) to predict the location of the transmitter within the area of interest. This approach reduces data collection and computational overhead associated with traditional localization methods. The method is validated through simulated data as well as measurements at 2.7 GHz, with an average error of 7.23 m and a standard deviation of 3.32 m.","url":"https://doi.org/10.36227/techrxiv.174123177.79937220/v1","authors":["Arash Ahmadi","Abhiroop Bhattacharya","Fabrice Vaussenat","Sylvain G. Cloutier","Richard Al Hadi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-05T22:29:54Z","doi":"10.36227/techrxiv.174123177.79937220/v1","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1002/eng2.70373/v5/decision1","name":"Decision letter for \"Enhancing Cardiovascular Disease Analysis in Healthcare Systems With Hybrid Random Forest and Neural Network Algorithm\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/eng2.70373/v5/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T23:21:22Z","doi":"10.1002/eng2.70373/v5/decision1","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.2139/ssrn.5134235","name":"Bike-Sharing Ridership Prediction for Network Expansion Using Graph Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5134235","authors":["Ghazaleh Mohseni Hosseinabadi","Mehdi Nourinejad","Peter  Y. Park"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-12T08:49:01Z","doi":"10.2139/ssrn.5134235","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.55277/researchhub.rwpbjj07.1","name":"PENGENALAN ALFABET BAHASA ISYARAT TANGAN PADA CITRA DIGITAL MENGGUNAKAN PENDEKATAN CONVEX HULL DAN CONVOLUTIONAL NEURAL NETWORK  (CNN)","source":"crossref","abstract":"","url":"https://doi.org/10.55277/researchhub.rwpbjj07.1","authors":["Widianto Eka Saputro"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-09T21:56:08Z","doi":"10.55277/researchhub.rwpbjj07.1","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.20944/preprints202503.2355.v1","name":"Enhancing Neural Network Interpretability Through Deep Prior-Guided Expected Gradients","source":"crossref","abstract":"The increasing adoption of deep neural networks (DNNs) in critical domains such as healthcare, finance, and autonomous systems underscores the growing importance of explainable artificial intelligence (XAI). In these high-stakes applications, understanding the decision-making processes of models is essential for ensuring trust and safety. However, traditional DNNs often function as \"black boxes,\" delivering accurate predictions without providing insight into the factors driving their outputs. Expected Gradients (EG) is a prominent method for making such explanations by calculating the contribution of each input feature to the final decision. Despite its effectiveness, conventional baselines used in state-of-the-art implementations of EG often lack a clear definition of what constitutes \"missing\" information. In this work, we propose DeepPrior-EG, a deep prior-guided EG framework for leveraging prior knowledge to more accurately align with the concept of missingness and enhance interpretive fidelity. It resolves the baseline misalignment by initiating gradient path integration from learned prior baselines, which derived from the deep features of CNN layers. This approach not only mitigates feature absence artifacts but also amplifies critical feature contributions through adaptive gradient aggregation. We further introduce two probabilistic prior modeling strategies: a multivariate Gaussian model (MGM) to capture high-dimensional feature interdependencies and a Bayesian nonparametric Gaussian mixture model (BGMM) that autonomously infers mixture complexity for heterogeneous feature distributions. We also develop an explanation-driven model retraining paradigm to valid the robustness of the proposed framework. Comprehensive evaluations across various qualitative and quantitative metrics demonstrate the its superior interpretability. The BGMM variant achieves state-of-the-art performance in attribution quality and faithfulness against existing methods. DeepPrior-EG advances the interpretability of complex models within the XAI landscape and unlocks its potential in safety-critical applications.","url":"https://doi.org/10.20944/preprints202503.2355.v1","authors":["Su-Ying Guo","Xiu-Jun Gong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-01T01:29:14Z","doi":"10.20944/preprints202503.2355.v1","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.2139/ssrn.5611233","name":"Statically Scheduled Interconnect for Neural Network Inter-Layer Accelerating","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5611233","authors":["Qimin Zhou","Hui Xv","Jingyu Li","Weiping Yang","Changlin Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-15T21:40:32Z","doi":"10.2139/ssrn.5611233","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.21203/rs.3.rs-6787728/v1","name":"Forecasting the residual stress components in wires using an artificial neural network","source":"crossref","abstract":"Abstract In this paper, a computer simulation of round wire drawing processes with different equations of state for steel A12 has been carried out. In addition, the methods of improving the configuration of neural networks based on multilayer perceptron (MLP) for estimating the distributions of residual stress tensor components have been investigated. The study demonstrated that the strain rate exerted a significant influence on the character of the processes, particularly within the central region (0r–0.4r) of the investigated specimens. In addition, the employment of software tools for the purpose of tuning the hyperparameters of trained machine learning models, including Optuna, BayesianOpt, and Skopt, has been demonstrated to enhance the predictive capability of the models. Consequently, this results in an improvement in the accuracy of the obtained distributions of the required characteristics.","url":"https://doi.org/10.21203/rs.3.rs-6787728/v1","authors":["Dmitriy Demin","Ilya Grebenkin","Alexey Barinov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-06T14:23:29Z","doi":"10.21203/rs.3.rs-6787728/v1","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.4071/001c.147292","name":"Prediction of Cross-Sectional Images and Proposing Processes with Neural Network","source":"crossref","abstract":"We developed a novel system that quickly predicts cross-sectional images from experimental conditions to minimize cross-sectional processing. This has become a bottleneck in observing pattern shapes of materials used in substrate manufacturing. This system can predict cross-sectional images from experimental conditions and propose process conditions to form the desired pattern shape. We consider that using this system will improve the development speed of overall semiconductor packages.","url":"https://doi.org/10.4071/001c.147292","authors":["Kohei Motojima","Hayato Sugiyama","Kaede Ameyama","Chiho Ueta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-17T19:49:47Z","doi":"10.4071/001c.147292","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/ijcnn64981.2025.11227401","name":"NeckLymphNet: An Efficient Neck Lymph Node Detection Network for Ultrasound Images","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn64981.2025.11227401","authors":["Weitao Tan","Zhang Yi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T18:46:15Z","doi":"10.1109/ijcnn64981.2025.11227401","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.3901/jme.2025.04.355","name":"Neural Network Control of Electrohydrostatic Actuator Based on Flow Pulsation Compensation","source":"crossref","abstract":"","url":"https://doi.org/10.3901/jme.2025.04.355","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-19T06:14:56Z","doi":"10.3901/jme.2025.04.355","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.23919/ccc64809.2025.11178841","name":"Nonlinear Predictive Trajectory Tracking Control of USV with Neural Network Model","source":"crossref","abstract":"","url":"https://doi.org/10.23919/ccc64809.2025.11178841","authors":["Jian Huang","Wenhui Zhang","Bin Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-10T17:34:54Z","doi":"10.23919/ccc64809.2025.11178841","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/icsece65727.2025.11256937","name":"Enterprise bankruptcy prediction algorithm based on graph neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icsece65727.2025.11256937","authors":["Zhiyi He"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-02T18:44:58Z","doi":"10.1109/icsece65727.2025.11256937","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/etis64005.2025.10961873","name":"A Modified Convolutional Neural Network Model for Automatic Modulation Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/etis64005.2025.10961873","authors":["Yogesh Beeharry","Didier Gael Daryl Emilien"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-21T17:36:15Z","doi":"10.1109/etis64005.2025.10961873","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/dapic66097.2025.00020","name":"Novel Character Representation and Application Research Based on Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/dapic66097.2025.00020","authors":["Xuehua Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-16T17:41:28Z","doi":"10.1109/dapic66097.2025.00020","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1109/metroaerospace64938.2025.11114563","name":"Retention Mechanism Based Neural Network Model for Measuring Aircraft Landing Distance","source":"crossref","abstract":"","url":"https://doi.org/10.1109/metroaerospace64938.2025.11114563","authors":["Paweł Tomiło"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-14T18:34:36Z","doi":"10.1109/metroaerospace64938.2025.11114563","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.14428/esann/2025.es2025-48","name":"Towards Adaptive and Stable Compositional Assemblies of Recurrent Neural Network Modules","source":"crossref","abstract":"","url":"https://doi.org/10.14428/esann/2025.es2025-48","authors":["Valerio De Caro","Andrea Ceni","Davide Bacciu","Claudio Gallicchio"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-15T14:43:24Z","doi":"10.14428/esann/2025.es2025-48","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1109/khpiweek61436.2025.11288649","name":"Audio Forgery Detection via Combined Recurrent-Convolutional Neural Network Architecture","source":"crossref","abstract":"","url":"https://doi.org/10.1109/khpiweek61436.2025.11288649","authors":["Artem Khovrat","Volodymyr Kobziev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-18T18:30:51Z","doi":"10.1109/khpiweek61436.2025.11288649","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1109/ecce58356.2025.11259526","name":"Neural Network-Integrated Kalman Filtering for Supercapacitor SOC Estimation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ecce58356.2025.11259526","authors":["Islam A. Sayed","Yousef Mahmoud"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-03T18:38:34Z","doi":"10.1109/ecce58356.2025.11259526","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.21667/1995-4565-2025-92-160-169","name":"COMPLEX RECURRENT NEURAL NETWORK","source":"crossref","abstract":"","url":"https://doi.org/10.21667/1995-4565-2025-92-160-169","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-07T12:38:27Z","doi":"10.21667/1995-4565-2025-92-160-169","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1109/ijcnn64981.2025.11228829","name":"Dynamic Multi-Scale Spatial-Temporal Feature Network for Traffic Flow Forecasting","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn64981.2025.11228829","authors":["Daming Liu","Chunlin Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T18:46:15Z","doi":"10.1109/ijcnn64981.2025.11228829","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1109/oceans58557.2025.11104361","name":"A Neural Network Approach to Estimate Modal Propagation in Coastal Oceanic Waveguides","source":"crossref","abstract":"","url":"https://doi.org/10.1109/oceans58557.2025.11104361","authors":["Arthur Varon","Jérôme Mars","Rémi Emmetière","Julien Bonnel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-11T17:40:45Z","doi":"10.1109/oceans58557.2025.11104361","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1109/ijcnn64981.2025.11227332","name":"A weighted converging and radiating feature pyramid network for object detection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn64981.2025.11227332","authors":["Taizhe Tan","Guiming Pan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T18:46:15Z","doi":"10.1109/ijcnn64981.2025.11227332","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.23919/eusipco63237.2025.11226768","name":"Gradient Clipping Improves Neural Network Optimization for Perceptual Sound Matching","source":"crossref","abstract":"","url":"https://doi.org/10.23919/eusipco63237.2025.11226768","authors":["Han Han","Vincent Lostanlen","Mathieu Lagrange"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-05T18:36:04Z","doi":"10.23919/eusipco63237.2025.11226768","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.7868/s3034548025040058","name":"Training of a Spiking Neural Network with Consideration of Memristive Crossbar Array Characteristics","source":"crossref","abstract":"A model, methodology and software tools for simulating a spiking neural network in the training mode considering the features of the operation of memristive crossbar arrays were developed. The impact of voltage drops on interconnects, the discrete step of adjusting the conductivity levels of memristive elements and the nonlinearity of their volt-ampere characteristics on the effectiveness of implementing spiking neural network training algorithms was studied. Results of testing the spiking neural network in the training mode and inference mode in the task of image recognition using the developed simulation method, taking into account the characteristics of experimentally fabricated memristive structures, are presented.","url":"https://doi.org/10.7868/s3034548025040058","authors":["A.P. Dudkin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-16T16:41:03Z","doi":"10.7868/s3034548025040058","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1115/1.4068110","name":"Abrasive Wear Prediction of Three-Dimensional Printed PEEK Using Artificial Neural Network","source":"crossref","abstract":"Abstract Machine learning is a cutting-edge technology that stands out among the various artificial intelligence offerings with its exceptional ability to comprehend intricate processes in computational tools. The optimization of input parameters for polyetheretherketone (PEEK) to print samples of any geometry provides insight for fabricated samples. The samples were fabricated using the extrusion method of additive manufacturing with varying layer thickness, which was tested under abrasive wear conditions using 120-grade sandpaper. The surface properties affect the wear response and rate of the 3D-printed PEEK sample, and the wear loss is high when subjected to abrasive wear conditions. Increasing layer thickness (more than 0.2 mm) reduces the hardness, and a rougher surface causes higher wear loss. To quantify the wear loss and avoid any mishappening during the operation, when the 3D-printed PEEK part is used as a journal bearing under unfavorable conditions, the mechanical and tribological properties emerge as significant measures defining a material's worth. These properties measure a material's capacity to endure external forces and the nonuniformity of relative motion. The article aims to predict wear loss using artificial neural networks (ANNs) under such conditions to avoid system failure and timely replacement with new components. The ReLU (rectified linear unit) activation function fits the actual wear trend and predicts the wear loss with 98% accuracy.","url":"https://doi.org/10.1115/1.4068110","authors":["Sunil Kumar Prajapati"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-05T14:54:36Z","doi":"10.1115/1.4068110","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1109/tensymp63728.2025.11145006","name":"NeuroPump: Predictive Modeling of Charge Pump Performance Parameters Using Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tensymp63728.2025.11145006","authors":["Ashutosh Singh","Abhsiehk Jain","Anuj Grover"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-04T18:18:11Z","doi":"10.1109/tensymp63728.2025.11145006","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1109/icmc64879.2025.11102673","name":"Neural Network Augmented RDSMOD for Parasitic Resistances in BSIM-CMG","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icmc64879.2025.11102673","authors":["M. Ehteshamuddin","Musaibh Farooq Dar","Avirup Dasgupta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-05T18:00:21Z","doi":"10.1109/icmc64879.2025.11102673","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1109/nnice64954.2025.11063853","name":"Research on Network Security Algorithms Based on Association Rules","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nnice64954.2025.11063853","authors":["Rong Qiang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-15T17:39:55Z","doi":"10.1109/nnice64954.2025.11063853","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.1109/iciscn64258.2025.10934190","name":"Urban Landscape Recognition and Classification Method using Improved Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iciscn64258.2025.10934190","authors":["Lifeng Jiang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-28T02:45:26Z","doi":"10.1109/iciscn64258.2025.10934190","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:32.918Z"},{"id":"doi:10.38007/nn.2022.030306","name":"Psychological Prediction of Digital Economy Consumption Considering Deep Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2022.030306","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T18:14:38Z","doi":"10.38007/nn.2022.030306","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.7717/peerj-cs.2637/table-5","name":"Algorithm 1: Neural network workflow.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.2637/table-5","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-31T03:09:14Z","doi":"10.7717/peerj-cs.2637/table-5","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.7717/peerj.12752/fig-2","name":"Figure 2: Neural network architecture.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj.12752/fig-2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-01-04T03:57:18Z","doi":"10.7717/peerj.12752/fig-2","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.7717/peerj-cs.2642/fig-14","name":"Figure 14: Neural network architecture.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.2642/fig-14","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-12T03:00:28Z","doi":"10.7717/peerj-cs.2642/fig-14","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.47852/bonview52022956","name":"Medicinal Plant Recognition Using Shallow Convolutional Neural Network","source":"crossref","abstract":"Ayurvedic medicine plays an essential role in the overall care that is provided for the physical and mental wellbeing of people. It is vital to correctly identify and categorize medicinal herbs to be able to provide better therapy. Medicinal herbs come in a wide variety of forms. It is a challenging task that requires a significant amount of professional medical experience to correctly name and classify the many distinct kinds of medicinal plants. Because of this, having an approach to the identification of medicinal plants that is completely automated is something that is highly desirable. In this study, a straightforward four-layer shallow Convolutional Neural Network (S-CNN) is proposed for the aim of classifying medicinal herbs. The potential utility of S-CNN is evaluated with the help of four distinct leaf datasets such as the Swedish Leaf, Flavia Leaf, MepcoTropicalLeaf Dataset, and Medicinal Leaf Dataset. Our model is capable of achieving a level of classification accuracy of 98.22%, 96.18% and 92.89% on Swedish, Flavia and Medicinal Leaf datasets respectively and that is comparable to that of other state-of-art methodologies in this field. Received: 28 March 2024 | Revised: 13 March 2025 | Accepted: 6 June 2025 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available in Swedish Leaf Dataset at https://www.cvl.isy.liu.se/en/research/datasets/swedish-leaf/, reference number [47]; in Medicinal Leaf Dataset at https://data.mendeley.com/datasets/nnytj2v3n5/1, reference number [48]. Author Contribution Statement Ramar Ahila Priyadharshini: Conceptualization, Methodology, Software, Validation, Investigation, Data curation, Writing - original draft, Visualization, Supervision, Project administration. M. Arun: Software, Formal analysis, Data curation, Writing - review &amp; editing, Visualization.","url":"https://doi.org/10.47852/bonview52022956","authors":["Ramar Ahila Priyadharshini","M. Arun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-05T02:37:43Z","doi":"10.47852/bonview52022956","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5155949","name":"Aerodynamic Recovery in a Solar-Gas Turbine Power Plant, Performance Prediction Via Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5155949","authors":["mohamadreza sabzeali","Saeed Karimian Aliabadi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-26T11:38:13Z","doi":"10.2139/ssrn.5155949","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5624512","name":"Modeling gamma radiation intensity in monazite rich coastal environments using neural network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5624512","authors":["Miriam  Mathias Gigi","Marcos Orlando","Jacyra Soares"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-18T22:44:24Z","doi":"10.2139/ssrn.5624512","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/iciscn64258.2025.10934296","name":"Financial Risk Prediction Model based on Deep Reinforcement Learning Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iciscn64258.2025.10934296","authors":["Qianhan Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-28T02:45:26Z","doi":"10.1109/iciscn64258.2025.10934296","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/ictc67375.2025.11292346","name":"MAC Protocol Recognition using Transformer-based Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ictc67375.2025.11292346","authors":["Yifan Lin","Jinlong Zhuang","Jiyan Lan","Shengliang Peng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-19T18:56:32Z","doi":"10.1109/ictc67375.2025.11292346","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.14529/jcem250305","name":"Forecasting the Volume of Residential Real Estate Sales in a Neural Network Basis","source":"crossref","abstract":"","url":"https://doi.org/10.14529/jcem250305","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-17T12:25:26Z","doi":"10.14529/jcem250305","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/punecon67554.2025.11378861","name":"Project Synapse: Building the Neural Network of Your Enterprise","source":"crossref","abstract":"","url":"https://doi.org/10.1109/punecon67554.2025.11378861","authors":["Hemant Arvind Mandge","Somen Sarangi","Manisha Dash"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-17T21:04:14Z","doi":"10.1109/punecon67554.2025.11378861","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5382268","name":"A Physics-Informed Neural Network Framework for Magnetohydrodynamic Oldroyd-B Fluid Flow","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5382268","authors":["RISANA K P","DAVID MAXIM GURURAJ A"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-07T01:37:42Z","doi":"10.2139/ssrn.5382268","addedAt":"2026-09-01T01:48:32.918Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1111/ejn.16332/v2/review1","name":"Review for \"ArcheD, a residual neural network for prediction of cerebrospinal fluid amyloid-beta from amyloid PET images\"","source":"crossref","abstract":"","url":"https://doi.org/10.1111/ejn.16332/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-15T08:06:42Z","doi":"10.1111/ejn.16332/v2/review1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1109/tgrs.2024.3466952/v3/decision1","name":"Decision letter for \"Optimizing Satellite-Based Latent Heating Rate Profiling Using a Convolutional Neural Network Heating (CNNH) Algorithm\"","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tgrs.2024.3466952/v3/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-21T22:51:12Z","doi":"10.1109/tgrs.2024.3466952/v3/decision1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.65286/icic.v20i1.74624","name":"Spatial-Temporal Attention Simple Graph Neural Network","source":"crossref","abstract":"The growth of the autonomous driving industry in recent years has spurred research on intelligent transportation systems. However, predicting long-term traffic patterns is a complex task that can lead to overfitting and fluctuations in model predictions.To address these challenges, this paper proposes a spatio-temporal modeling approach that captures both the spatial and temporal features of traffic data. The method fuses these features using a gated fusion mechanism and then applies feedforward neural networks to transform the spatio-temporal data into predictions for future time steps.To mitigate overfitting, the paper introduces a novel loss function called the mean loss function. By minimizing fluctuations in model predictions, this approach aims to improve the accuracy of long-term traffic forecasts.Overall, this paper presents a promising approach to improving the performance of intelligent transportation systems, particularly in the area of long-term traffic prediction. The proposed method combines several techniques, including spatio-temporal modeling, neural networks, and a new loss function,to address the challenges of overfitting and prediction fluctuations.After conducting multiple experiments on the publicly available transportation network datasets, METR-LA and PEMS-Bay, our proposed model demonstrated improved performance in long-term traffic flow prediction","url":"https://doi.org/10.65286/icic.v20i1.74624","authors":["Jiaxin Ai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-04T08:08:02Z","doi":"10.65286/icic.v20i1.74624","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.5220/0012430200003636","name":"F4D: Factorized 4D Convolutional Neural Network for Efficient Video-Level Representation Learning","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0012430200003636","authors":["Mohammad Al-Saad","Lakshmish Ramaswamy","Suchendra Bhandarkar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-29T05:30:53Z","doi":"10.5220/0012430200003636","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1038/s42005-024-01837-w","name":"Generalization of neural network models for complex network dynamics","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s42005-024-01837-w","authors":["Vaiva Vasiliauskaite","Nino Antulov-Fantulin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-25T09:02:18Z","doi":"10.1038/s42005-024-01837-w","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/iacis61494.2024.10721706","name":"Classification of Cervical Cancer using Artificial Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iacis61494.2024.10721706","authors":["K. Shanthi","S. Manimekalai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-24T17:23:48Z","doi":"10.1109/iacis61494.2024.10721706","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/iccea62105.2024.10604276","name":"Control of One-arm Robot Based on RBF Neural Network Model","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccea62105.2024.10604276","authors":["Qinqin Dou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-29T19:06:05Z","doi":"10.1109/iccea62105.2024.10604276","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1016/j.heliyon.2024.e37495","name":"Air passenger carbon offset and carbon neutrality strategies: Implementation mechanism by convolutional neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.heliyon.2024.e37495","authors":["Hongwei Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-06T15:07:40Z","doi":"10.1016/j.heliyon.2024.e37495","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.46719/dsa2024.33.07","name":"Discrete Epidemic Models: Neural Network Approach","source":"crossref","abstract":"","url":"https://doi.org/10.46719/dsa2024.33.07","authors":["N Begashaw","Gurcan Comert","N. G Medhin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-19T04:07:23Z","doi":"10.46719/dsa2024.33.07","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/qce60285.2024.10348","name":"Hybrid Quantum-Classical Neural Network for Diagnosis of Autism Spectrum Disorder","source":"crossref","abstract":"","url":"https://doi.org/10.1109/qce60285.2024.10348","authors":["Anthony Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-10T20:12:42Z","doi":"10.1109/qce60285.2024.10348","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1145/3675249.3675297","name":"Design of Neural Network-Based Smart City Security Monitoring System","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3675249.3675297","authors":["Yao Yao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-01T14:26:06Z","doi":"10.1145/3675249.3675297","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/ijcnn60899.2024.10651126","name":"Effective and Efficient: Deeper and Faster Fusion Network for Multimodal Summarization","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn60899.2024.10651126","authors":["Zhenyu Guan","Xun Liang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T17:35:05Z","doi":"10.1109/ijcnn60899.2024.10651126","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1364/cleo_at.2024.jth2a.146","name":"High-speed Classification by Optical Information Processing Based on Diffractive Deep Neural Network","source":"crossref","abstract":"High-speed processing of sub-millimeter-particle images by optical neural network is demonstrated. The apparatus processes light directly from samples flowing across the laser. &gt;98% accuracy was achieved for the classification of different sizes of particles.","url":"https://doi.org/10.1364/cleo_at.2024.jth2a.146","authors":["Shun Miura","Mamoru Otake","Hiroyuki Kusaka","Masahiro Kashiwagi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-05T16:13:11Z","doi":"10.1364/cleo_at.2024.jth2a.146","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/icodsa62899.2024.10652165","name":"Prediction of Student Work Readiness Using Recurrent Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icodsa62899.2024.10652165","authors":["Vannes","Kemas Muslim Lhaksmana"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-05T17:57:11Z","doi":"10.1109/icodsa62899.2024.10652165","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/icos63634.2024.10775672","name":"Light Neural Network for Pipeline Segmentation on a Side-Scan Sonar Images","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icos63634.2024.10775672","authors":["Konstanin Shilin","Alexander Pavin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-12T19:05:17Z","doi":"10.1109/icos63634.2024.10775672","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1115/detc2024-143313","name":"On the Prediction of Tremor Dynamics Motion Using Neural Network","source":"crossref","abstract":"Abstract Pathological tremors significantly affect the quality of life for patients worldwide. Rehabilitation exoskeletons serve as one of the solutions to alleviate these pathological tremors, and voluntary motion prediction-based motion planning has been employed to enhance the performance of these devices. This paper presents a method for predicting future voluntary movement in tremor-alleviating rehabilitation exoskeletons that use voluntary motion prediction-based motion planning. In this study, a Convolutional Neural Network and Transformer architecture based neural network work with EMG sensors to predict future voluntary movements. The results show that approach performs well in predicting future voluntary movements, but there is still a limitation to filter out the tremors completely. In summary, we provide a concept for predicting future voluntary movement, which has the potential to improve the effectiveness of rehabilitation exoskeletons in tremor alleviation.","url":"https://doi.org/10.1115/detc2024-143313","authors":["Zijian Ding","Oumar Barry"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-13T21:48:01Z","doi":"10.1115/detc2024-143313","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.2514/6.2024-4459","name":"A Neural Network Approach for Data Assimilation in Traffic Flow Management","source":"crossref","abstract":"","url":"https://doi.org/10.2514/6.2024-4459","authors":["Tyler Manderfield","Erik Vargo","Christine P. Taylor"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-20T08:30:37Z","doi":"10.2514/6.2024-4459","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.2478/amns-2024-0336","name":"Improved single target identification tracking algorithm based on IPSO-BP neural network","source":"crossref","abstract":"Abstract Driven by deep learning techniques in recent years, single target recognition and tracking techniques have developed significantly, but face challenges of real-time and accuracy. In this study, an improved IPSO-BP network is formed by optimizing three critical aspects of the IPSO algorithm: adjusting the inertia weight calculation formula, improving the learning factor, and creating a new iterative formula for particle updating, which in turn is combined with a BP neural network. After iterative training, this paper constructs a single target recognition tracking algorithm with higher efficiency. The Algorithm’s performance is comprehensively tested through experimental simulation in terms of real-time, accuracy and stability. The results show that the improved Algorithm can achieve a frame rate (FPS) of up to 31 in single target recognition and tracking. The IOU value is as high as about 83% in some tests. The tracking success rate in different scenarios averages approximately 98.50%, the position error is controlled within 0.7 m, and the speed error averages 2.75 m/s. This improved IPSO-BP neural network effectively solves the problems of the current technology in the areas of real-time and accuracy, showing high stability and accuracy.","url":"https://doi.org/10.2478/amns-2024-0336","authors":["Ting Xie"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-27T15:06:53Z","doi":"10.2478/amns-2024-0336","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/iciscae62304.2024.10761754","name":"An Improved BP Neural Network Anomaly Detection Method","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iciscae62304.2024.10761754","authors":["Long Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-03T18:51:17Z","doi":"10.1109/iciscae62304.2024.10761754","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.21437/interspeech.2024-958","name":"Dynamic Gated Recurrent Neural Network for Compute-efficient Speech Enhancement","source":"crossref","abstract":"","url":"https://doi.org/10.21437/interspeech.2024-958","authors":["Longbiao Cheng","Ashutosh Pandey","Buye Xu","Tobi Delbruck","Shih-Chii Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-01T07:10:12Z","doi":"10.21437/interspeech.2024-958","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1093/mam/ozae044.194","name":"Aberration Measurement from Crystalline Ronchigrams with an Attention Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1093/mam/ozae044.194","authors":["Jingrui Wei","Paul M Voyles"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-25T03:21:39Z","doi":"10.1093/mam/ozae044.194","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.2139/ssrn.5011179","name":"Hydraconv: A Novel Graph Neural Network for Finite Element Emulation in Biomechanical Modeling","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5011179","authors":["Igor  A. P. Nobrega","Wenbin Mao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-21T19:12:31Z","doi":"10.2139/ssrn.5011179","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.36227/techrxiv.171436020.02962844/v1","name":"Hierarchical Physics-Informed Neural Network Framework for 3D Magnetic Modeling of Medium Frequency Transformers","source":"crossref","abstract":"Neural Network (NN) technology is revolutionizing the modeling paradigm in the engineering arena, enhancing simultaneously model precision and process speed. Nevertheless, the deficiency of physical interpretability in current NN models causes an unattainable demand for the quantity of training data, especially when dealing with high-dimension physical behaviours. In this work, a Hierarchical Physics-Informed Neural Network (HPINN) framework is proposed to address the 3D magnetic modeling issue of Medium Frequency Transformers (MFTs). By establishing the knowledge transfer channel between the cross section and the equivalent space, the inferior 2D model parameter search space, which is restricted by Dowell’s equation and accessible 2D magnetic data information, can be mapped into the superior 3D search space. Accordingly, with limited 3D training data, the performance of the HPINN framework is still guaranteed around the optimal state. The structural embedding of physics knowledge reduces the model's reliance on 3D training data, thereby relieving the strict computing requirement at the data generation stage. Finally, according to the training results and experiment verifications, with only one-third computational burden used in the classic NN model, the average error of this proposed HPINN framework is reduced to 1%, and the maximum error does not exceed 10%.","url":"https://doi.org/10.36227/techrxiv.171436020.02962844/v1","authors":["Xiao Yang","Liangcai Shu","Dongsheng Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-28T23:10:08Z","doi":"10.36227/techrxiv.171436020.02962844/v1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/tgrs.2024.3466952/v2/decision1","name":"Decision letter for \"Optimizing Satellite-Based Latent Heating Rate Profiling Using a Convolutional Neural Network Heating (CNNH) Algorithm\"","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tgrs.2024.3466952/v2/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-21T22:51:12Z","doi":"10.1109/tgrs.2024.3466952/v2/decision1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.2139/ssrn.4852090","name":"Few-Shot Wind Power Prediction Using Sample Transfer and Imbalanced Evolved Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4852090","authors":["Hao Yin","Chen Li","Anbo Meng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-03T14:22:00Z","doi":"10.2139/ssrn.4852090","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1002/we.2976/v2/review2","name":"Review for \"Volt/VAr Regulation of the West Mediterranean Regional Electrical Grids Using SVC/STATCOM Devices With Neural Network Algorithms\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/we.2976/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-25T16:09:21Z","doi":"10.1002/we.2976/v2/review2","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.20944/preprints202406.0933.v1","name":"Evolutionary Reinforcement Learning of Binary Neural Network Controllers for Pendulum Task—Part2: Genetic Algorithm","source":"crossref","abstract":"Evolutionary algorithms and swarm intelligence algorithms find applicability in reinforcement learning of neural networks due to their independence from gradient-based methods. To achieve successful training of neural networks using these algorithms, careful considerations must be made to select appropriate algorithms due to the availability of various algorithmic variations. In Part1, the author previously reported experimental evaluations on Evolution Strategy for reinforcement learning of binary neural networks, utilizing the Pendulum control task. This article constitutes Part2 of the series of comparative research. In this study, Genetic Algorithm is adopted as another evolutionary algorithm. Wilcoxon signed rank test revealed that there was no statistically significant difference between the fitness scores obtained using GA and those using ES. However, the p-value 0.11 indicated that GA worked better than ES on this training task. As the values of binary weights, {-1, 1} were significantly superior to {0, 1} (p &amp;lt; .01). The motion of the pendulum controlled by the binary MLP after the training showed that the binary MLP successfully swung the pendulum swiftly into an inverted position and maintained its stability after inversion.","url":"https://doi.org/10.20944/preprints202406.0933.v1","authors":["Hidehiko Okada"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-17T09:05:08Z","doi":"10.20944/preprints202406.0933.v1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1002/we.70052/v1/review2","name":"Review for \"Scaled Physical Modelling of Floating Offshore Wind Turbines Using a Neural Network‐Based Surrogate Model for Aerodynamic Emulation\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/we.70052/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-01T00:12:43Z","doi":"10.1002/we.70052/v1/review2","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.31673/2409-7292.2024.040014","name":"Neural network-based chatbot for providing information support to businesses from a cybersecurity perspective","source":"crossref","abstract":"","url":"https://doi.org/10.31673/2409-7292.2024.040014","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-30T19:02:03Z","doi":"10.31673/2409-7292.2024.040014","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/eebda60612.2024.10485705","name":"Lightweight Heterogeneous Convolutional Neural Network for Trash Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/eebda60612.2024.10485705","authors":["Tingrou Zhu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-08T20:33:34Z","doi":"10.1109/eebda60612.2024.10485705","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1016/b978-0-323-85622-5.00016-x","name":"Physics-informed neural network-based control of power electronic converters","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-323-85622-5.00016-x","authors":["Subham Sahoo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-01T03:45:53Z","doi":"10.1016/b978-0-323-85622-5.00016-x","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1016/b978-0-443-27318-6.00006-1","name":"Position-specific convolutional neural network to accurately match iris and periocular images","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-27318-6.00006-1","authors":["Ajay Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-14T10:11:12Z","doi":"10.1016/b978-0-443-27318-6.00006-1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.18494/sam4784","name":"Prediction Model of Residual Current Based on Grey Association and Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.18494/sam4784","authors":["Guoyu Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-29T22:17:19Z","doi":"10.18494/sam4784","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/lascas60203.2024.10506129","name":"Light Siamese Neural Network Architecture for Image Comparison","source":"crossref","abstract":"","url":"https://doi.org/10.1109/lascas60203.2024.10506129","authors":["Fathi Souaker","Mounir Boukadoum"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-26T17:30:14Z","doi":"10.1109/lascas60203.2024.10506129","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.3365/kjmm.2024.62.3.212","name":"Simulation Study of Interfacial Switching Memristor Structure and Neural Network Performance","source":"crossref","abstract":"In this study, the architecture of an interfacial switching memristor, which has a metal-insulatormetal structure of Pt/SrTiO&lt;sub&gt;3&lt;/sub&gt;/Nb-SrTiO&lt;sub&gt;3&lt;/sub&gt; was investigated. The performance of a neural network that uses memristors as its synapse components was also examined with system-level simulations. A finite element solver, COMSOL Multiphysics, was used to simulate synaptic device characteristics, specifically, the conductance change, using a series of pulses for a given architecture. An open-source software, NeuroSim, was used to simulate the ability of the neural network to recognize and identify handwritten digits. Electrostatics, mass transport, and thermionic emission equations were numerically solved in a fully coupled manner to model the Schottky barrier height modulation at the Pt/SrTiO&lt;sub&gt;3&lt;/sub&gt; contact using the applied bias. The barrier height is a function of the oxygen vacancy concentration in the SrTiO&lt;sub&gt;3&lt;/sub&gt; near the contact. The gradual change of the oxygen vacancy concentration profile caused by successive pulses results in the gradual change of conductance. Utilizing the simulations, the influences of device structure modification, and more specifically, changing the size of the Schottky contact, on long-term potentiation and depression were analyzed for planar devices. The results show that a smaller Schottky contact yields a higher digit recognition rate. Based on this finding, a three-dimensional device architecture that is vertically stackable was designed.","url":"https://doi.org/10.3365/kjmm.2024.62.3.212","authors":["Yun Hyeok Song","Ji Min Lim","Sagar Khot","Dongmyung Jung","Yongwoo Kwon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-28T07:07:11Z","doi":"10.3365/kjmm.2024.62.3.212","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1016/j.neunet.2024.106328","name":"Solving the non-submodular network collapse problems via Decision Transformer","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106328","authors":["Kaili Ma","Han Yang","Shanchao Yang","Kangfei Zhao","Lanqing Li","Yongqiang Chen","Junzhou Huang","James Cheng","Yu Rong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-21T17:08:10Z","doi":"10.1016/j.neunet.2024.106328","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/ijcnn60899.2024.10650026","name":"Implicit Neural Alignment Network for Arbitrary-scale Space-Time Video Super-Resolution","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn60899.2024.10650026","authors":["Qin Jiang","Qinglin Wang","Lihua Chi","Jie Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T17:35:05Z","doi":"10.1109/ijcnn60899.2024.10650026","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1061/9780784485538.027","name":"Prediction of Thermal Cracks in Pavements Using Artificial Neural Network Modeling","source":"crossref","abstract":"","url":"https://doi.org/10.1061/9780784485538.027","authors":["Mohammad I. Hossain","Reema Sweidan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-13T06:01:19Z","doi":"10.1061/9780784485538.027","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.37766/inplasy2024.10.0030","name":"Advancing Meta-Analysis of Post-Radiotherapy Nasopharyngeal Carcinoma Complications through Recurrent Neural Network-Enabled Natural Language Processing","source":"crossref","abstract":"","url":"https://doi.org/10.37766/inplasy2024.10.0030","authors":["Tsair-Fwu Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-08T18:23:07Z","doi":"10.37766/inplasy2024.10.0030","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.20944/preprints202411.0183.v2","name":"Neural Network for Enhancing Robot Assisted Rehabilitation: A Systematic Review","source":"crossref","abstract":"The integration of neural networks into robotic exoskeletons for physical rehabilitation has become popular due to their ability to interpret complex physiological signals. Surface electromyography (sEMG), electromyography (EMG), electroencephalography (EEG), and other physiological signals enable communication between the human body and robotic systems. Utilizing physiological signals for communicating with robots plays a crucial role in robot assisted neurorehabilitation. This systematic review synthesizes 44 peer-reviewed studies, exploring how neural networks can improve exoskeleton robot assisted rehabilitation for individuals with impaired upper limbs. By categorizing the studies based on robot assisted joints, sensor systems, and control methodologies, we offer a comprehensive overview of neural network applications in this field. Our findings demonstrate that neural networks, such as Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and Radial Basis Function Neural Networks (RBFNN), and other forms of neural network significantly contribute to patient specific rehabilitation by enabling adaptive learning and personalized therapy. CNNs improve motion intention estimation and control accuracy, while LSTM networks capture temporal muscle activity patterns for real-time rehabilitation. RBFNNs improve human-robot interaction by adapting to individual movement patterns, leading to more personalized and efficient therapy. This review highlights the potential of neural networks to revolutionize upper limb rehabilitation, improving motor recovery and patient outcomes in both clinical and home-based settings. It also recommends the future direction to customize existing neural networks for robot assisted rehabilitation applications.","url":"https://doi.org/10.20944/preprints202411.0183.v2","authors":["Sk Hasan","Nafizul Alam","Gazi Abdullah Mashud","Subodh Bhujel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-26T01:01:46Z","doi":"10.20944/preprints202411.0183.v2","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.1002/prot.26700/v2/review1","name":"Review for \"&lt;scp&gt;ProBAN&lt;/scp&gt;: Neural network algorithm for predicting binding affinity in protein–protein complexes\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/prot.26700/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-10T21:55:48Z","doi":"10.1002/prot.26700/v2/review1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.1017/qpb.2024.2.pr12","name":"Recommendation: Quantitative analysis of lateral root development with time-lapse imaging and deep neural network — R2/PR12","source":"crossref","abstract":"","url":"https://doi.org/10.1017/qpb.2024.2.pr12","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-13T03:07:40Z","doi":"10.1017/qpb.2024.2.pr12","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.2478/amns-2024-0741","name":"Application of improved RBF neural network algorithm in hierarchical management of enterprise","source":"crossref","abstract":"Abstract The grade division of enterprises is conducive to their needs of green development, and the continuous strengthening of computer innovation technology provides an excellent platform for grading the regional management of enterprises. Owing to the differences in energy consumption, labour, land use area, GDP, etc., most of the data collected by the enterprises are unstable, and the data with a small number of samples in categories cannot be ignored. Therefore, based on the related data of basic development in a development area, Guangdong Province within the past 15 years, in this paper, according to the theory of hierarchical management in enterprise, four factors, such as land use, personnel, energy consumption and regional GDP, are used as the relevant attributes, and the grades of enterprises in this region are managed and divided. In addition, the structure of RBF neural network algorithm optimised by similarity relation matrix and the accuracy of enterprise classification under different neural network algorithms are compared. The results show that the hierarchical management of enterprises based on the improved RBF neural network algorithm has high efficiency and accuracy, which is of great significance to the green development of enterprises.","url":"https://doi.org/10.2478/amns-2024-0741","authors":["JianMing Ye"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-23T14:55:07Z","doi":"10.2478/amns-2024-0741","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1093/sleep/zsae067.0526","name":"0526 Deep Convolutional Neural Network for Groaning and Snoring Sounds Classification","source":"crossref","abstract":"Abstract Introduction Catathrenia is a rare sleep-related breathing disorder characterized by recurrent monotonous groaning during sleep. The acoustic characteristics of groaning and snoring sounds have been investigated. This study aims to propose a deep convolutional neural network (CNN) for automatic binary classification. Methods This study consisted of 3728 episodes of groaning sounds and 4577 episodes of snoring sounds obtained from synchronized audio of full-night polysomnography. Four features extracted from log-scaled mel-spectrograms were used as input. The background gaussian noise and the time-shifting were used to augment the dataset. The dataset was randomly split into training (70%), validation (15%), and testing datasets (15%). A deep learning convolutional neural network architecture was trained and evaluated. Results The proposed CNN model achieves an accuracy of 95.0% on the binary classification of groaning and snoring sounds. The model attains a sensitivity/recall of 96.4%, a specificity of 93.4%, and an F1 score of 94.84%. Conclusion The proposed CNN architecture has performed well in the automatic binary classification of groaning and snoring sounds, which could reduce difficulties in acoustic analyses of groaning episode detection. The model needs to be verified with more audio data before it can be put into clinical use better. Support (if any)","url":"https://doi.org/10.1093/sleep/zsae067.0526","authors":["Min Yu","Xuemei Gao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-20T05:25:20Z","doi":"10.1093/sleep/zsae067.0526","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/icca62237.2024.10928167","name":"Pedestrian-Collision Avoidance Strategy Using Deep Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icca62237.2024.10928167","authors":["Gowresh Rajagobal","Mohamed Al-Musleh","Nidhal Abdulaziz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-27T02:16:27Z","doi":"10.1109/icca62237.2024.10928167","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.23919/ecc64448.2024.10591223","name":"A Physics-Informed Neural Network Method to Approximate Homogeneous Lyapunov Functions","source":"crossref","abstract":"","url":"https://doi.org/10.23919/ecc64448.2024.10591223","authors":["Danilo R. Lima","Rosane Ushirobira","Denis Efimov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-24T17:48:23Z","doi":"10.23919/ecc64448.2024.10591223","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/iacis61494.2024.10721939","name":"PSO-BP Neural Network Model in Stock Prediction","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iacis61494.2024.10721939","authors":["Beibei Wen","Yuanyuan Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-24T17:23:48Z","doi":"10.1109/iacis61494.2024.10721939","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1007/s00780-024-00538-0","name":"Deep neural network expressivity for optimal stopping problems","source":"crossref","abstract":"Abstract This article studies deep neural network expression rates for optimal stopping problems of discrete-time Markov processes on high-dimensional state spaces. A general framework is established in which the value function and continuation value of an optimal stopping problem can be approximated with error at most $\\varepsilon $ ε by a deep ReLU neural network of size at most $\\kappa d^{\\mathfrak{q}} \\varepsilon ^{-\\mathfrak{r}}$ κ d q ε − r . The constants $\\kappa ,\\mathfrak{q},\\mathfrak{r} \\geq 0$ κ , q , r ≥ 0 do not depend on the dimension $d$ d of the state space or the approximation accuracy $\\varepsilon $ ε . This proves that deep neural networks do not suffer from the curse of dimensionality when employed to approximate solutions of optimal stopping problems. The framework covers for example exponential Lévy models, discrete diffusion processes and their running minima and maxima. These results mathematically justify the use of deep neural networks for numerically solving optimal stopping problems and pricing American options in high dimensions.","url":"https://doi.org/10.1007/s00780-024-00538-0","authors":["Lukas Gonon"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-14T14:02:16Z","doi":"10.1007/s00780-024-00538-0","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.21741/9781644903254-54","name":"Electroshock plastic constitutive modelling of high strength aluminum alloy based on GA-BP neural network","source":"crossref","abstract":"Abstract. Electrically-assisted forming is an effective way to improve the difficult-to-form materials. On basis of electro- and magneto- plastic effects, our team put forward a novel electroshock treatment (EST) process, which can not only improve the formability of the material but also improve the service performance of the formed parts. However, electrically-assisted forming involves nonlinear deformation with multi-physics coupling, the microstructural evolution and plastic mechanical response of materials under the coupling of electric current field and stress field are highly intricate, posing significant challenges in predicting macroscopic deformation behavior. The study of the characterization and precise control of plastic deformation's constitutive relation is therefore highly significant. In this work, the stress-strain curves of AA7075 under, different current densities, periods and power duration are obtained by means of the pulse electric current assisted tension test, and the intelligent prediction of the electroshock plastic constitutive relationship of AA7075 is realized based on the Genetic Algorithm (GA) optimized Back Propagation (BP) (GA-BP) neural network. The results show that the proposed algorithm can reduce the input parameters of the constitutive model to current, temperature and strain, and improve the computational efficiency. GA is used to optimize the initial weight and threshold of BP neural network, and the best hidden node number was selected as 12 by error verification to train the network. Compared with the traditional BP neural network, the neural network optimized by GA has higher accuracy, and in the plastic deformation stage, the coefficient of determination R2 between the predicted results and the experimental results is basically 99%, which is about 20% higher than that of the BP neural network. At the same time, it solves the data fluctuation in the long-term prediction due to the standard of satisfying the error in the prediction.","url":"https://doi.org/10.21741/9781644903254-54","authors":["Yanli SONG"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-26T16:54:12Z","doi":"10.21741/9781644903254-54","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.21203/rs.3.rs-3828635/v1","name":"Heat transfer in material having random thermal conductivity using Monte Carlo simulation and deep neural network","source":"crossref","abstract":"Abstract Stochastic heat transfer simulations play a pivotal role in capturing real-world uncertainties, where randomness in material properties and boundary conditions are present. Traditional methods, such as Monte Carlo simulation , perturbation methods, and polynomial chaos expansion, have provided valuable insights but face challenges in efficiency and accuracy, particularly in high-dimensional systems. This paper introduces a methodology for one-dimensional heat transfer modeling that incorporates random boundary conditions and treats thermal conductivity as a random process The proposed approach integrates Monte Carlo simulation with Cholesky decomposition to generate a vector of thermal conductivity realizations, capturing the inherent randomness in material properties. Finite Element Method (FEM) simulations based on these realizations yield rich datasets of temperatures at various locations. A deep neural network (DNN) is then trained on this FEM data, enabling not only rapid and accurate temperature predictions but also bidirectional computations—predicting temperatures based on thermal conductivity and inversely estimating thermal conductivity from observed temperatures.","url":"https://doi.org/10.21203/rs.3.rs-3828635/v1","authors":["rakesh kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-04T09:50:07Z","doi":"10.21203/rs.3.rs-3828635/v1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.2139/ssrn.4785075","name":"Unsupervised End-to-End Multiscale Neural Network for Multi-Focus Microled Image Fusion","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4785075","authors":["Wenlin Yu","Jinbiao Chen","Cheng Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-05T04:18:05Z","doi":"10.2139/ssrn.4785075","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.2139/ssrn.5066377","name":"Weighted Neural Network for Imbalanced Dataset with Undersampling","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5066377","authors":["Yuichi Motai","Simegnew  Yihunie Alaba","Nahian Siddique","Emrah Benli","Dominik Enns"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-20T21:38:29Z","doi":"10.2139/ssrn.5066377","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.20944/preprints202401.1875.v1","name":"Pattern Augmented Lightweight Convolutional Neural Network for Intrusion Detection System","source":"crossref","abstract":"As the world increasingly becomes more interconnected, the demand for safety and security is ever-increasing, particularly for industrial networks. This has prompted numerous researchers to investigate different methodologies and techniques suitable for intrusion detection systems (IDS) requirements. Over the years, many studies have proposed various solutions in this regard including signature-based and machine-learning (ML) based systems. More recently, researchers are considering deep learning (DL) based anomaly detection approaches. Most proposed works in this research field aimed to achieve either one or a combination of high accuracy, considerably low false alarm rates (FARs), high classification specificity and detection sensitivity, achieving lightweight DL models, or other ML and DL-related performance measurement metrics. In this study, we propose a novel method to convert a raw dataset to an image dataset to magnify patterns. Based on this we devise an anomaly detection for IDS using a lightweight convolutional neural network (CNN) that classifies denial of service and distributed denial of service. The proposed methods were evaluated using a modern dataset, CSE-CIC-IDS2018, and a legacy dataset, NSL-KDD. We have also applied a combined dataset to assess the generalization of the proposed model across various datasets. Our experimental results have demonstrated that the proposed methods achieved high accuracy and considerably low FARs with high specificity and sensitivity. The resulting loss and accuracy curves have also demonstrated the excellent generalization of the proposed lightweight CNN model, effectively avoiding overfitting. This holds for both the modern and legacy datasets, including their mixed version.","url":"https://doi.org/10.20944/preprints202401.1875.v1","authors":["Yonatan Embiza Tadesse","Young-June Choi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-29T02:26:03Z","doi":"10.20944/preprints202401.1875.v1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1088/2632-2153/ad7e7a/v2/review1","name":"Review for \"A PNP ion channel deep learning solver with local neural network and finite element input data\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2632-2153/ad7e7a/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-24T17:15:02Z","doi":"10.1088/2632-2153/ad7e7a/v2/review1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1109/raiic61787.2024.10671201","name":"Fraud Detection Based on Graph Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/raiic61787.2024.10671201","authors":["Youxin Luo","Guiping Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-17T18:47:41Z","doi":"10.1109/raiic61787.2024.10671201","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/icmlant63295.2024.00009","name":"Deep Convolutional Neural Networks Structured Pruning via Gravity Regularization","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icmlant63295.2024.00009","authors":["Abdesselam Ferdi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-05T13:41:54Z","doi":"10.1109/icmlant63295.2024.00009","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/vtc2024-spring62846.2024.10683123","name":"Graph-Based Untrained Neural Network Detector for OTFS Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/vtc2024-spring62846.2024.10683123","authors":["Hao Chang","Branka Vucetic","Wibowo Hardjawana"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-25T17:28:12Z","doi":"10.1109/vtc2024-spring62846.2024.10683123","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1016/j.fraope.2024.100192","name":"Semantic communication-based convolutional neural network for enhanced image classification","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.fraope.2024.100192","authors":["Nivine Guler","Zied Ben Hazem"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-23T17:54:59Z","doi":"10.1016/j.fraope.2024.100192","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/iconstem60960.2024.10568797","name":"Human Facial Emotion Recognition Using Graphical Cascaded Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iconstem60960.2024.10568797","authors":["M. Tamilselvi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-28T17:54:40Z","doi":"10.1109/iconstem60960.2024.10568797","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1002/brb3.70085/v2/decision1","name":"Decision letter for \"Neural Determinants of Sedentary Lifestyle in Older Adults: A Brain Network Analysis\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/brb3.70085/v2/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-09T16:04:23Z","doi":"10.1002/brb3.70085/v2/decision1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1039/d4sc07858f/v1/review2","name":"Review for \"IMPRESSION Generation 2 – Accurate, fast and generalised neural network model for predicting NMR parameters in place of DFT\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d4sc07858f/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-31T17:20:23Z","doi":"10.1039/d4sc07858f/v1/review2","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.32604/cmc.2024.055538","name":"Virtual Assembly Collision Detection Algorithm Using Backpropagation Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.32604/cmc.2024.055538","authors":["Baowei Wang","Wen You"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-25T20:40:12Z","doi":"10.32604/cmc.2024.055538","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1115/imece2024-145599","name":"A Deep Convolutional Neural Network Approach to Automate Drilling Tool Lateral Motion Video Interpretation","source":"crossref","abstract":"Abstract Mitigating the risks associated with the effect of whirl on measurement quality and health of the drilling tools requires a solid understanding of drilling tool lateral motion dynamics. A full-scale roll test system (i.e., a tubular assembly rolling along the inner wall of an impact ring while being spun with a drive motor), which intends to mimic lateral dynamics that the tool could undergo while drilling in a controlled laboratory environment, is believed to be the closest to the real drilling exercises. This study is concerned with leveraging artificial intelligence (AI) techniques to advance the results interpretation of such roll test system that is instrumented with accelerometers and high-speed cameras. Specifically, deep convolutional neural network models using transfer learning are developed to automate detection of rolling shock impacts based on the digital images collected from the recorded slow-motion video. The developed model is trained and validated with the video data recorded at one rotational speed. The robustness of the developed model is finally tested and evaluated on the unseen video dataset, which describe drilling tool whirl dynamics at different rotational speeds. High F1 Score about 0.9 is achieved for the selected model with hyperparameter-tuning and fine-tuning techniques. The developed AI model expects to play a vital role in the modernization of the roll test system development for downhole drilling tools, and reducing cost, time and risks in new product development and validation and verification.","url":"https://doi.org/10.1115/imece2024-145599","authors":["Fei Song","Ke Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-23T12:58:18Z","doi":"10.1115/imece2024-145599","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/aicsip65423.2025.11427230","name":"Emotion Recognition With Memristor Cross Array Convolutional Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aicsip65423.2025.11427230","authors":["Jiqi Yu","Yan Yang","Dongqing Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-17T20:18:06Z","doi":"10.1109/aicsip65423.2025.11427230","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.36227/techrxiv.24425536.v2","name":"Fast Selection of Indoor Wireless Transmitter Locations with Generalizable Neural Network Propagation Models","source":"crossref","abstract":"","url":"https://doi.org/10.36227/techrxiv.24425536.v2","authors":["Aristeidis Seretis","Charley Xu","Costas Sarris"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-07T18:48:01Z","doi":"10.36227/techrxiv.24425536.v2","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1101/2024.05.24.595714","name":"Electroencephalogram (EEG) Classification using a bio-inspired Deep Oscillatory Neural Network","source":"crossref","abstract":"Abstract In this paper, we propose two models of oscillatory neural networks - the Deep Oscillatory Neural Network (DONN) and a convolutional variation of it named Oscillatory Convolutional Neural Network (OCNN) – and apply the models to a variety of problems involving the classification and prediction of Electroencephalogram (EEG) signals. Deep neural networks applied to signal processing problems will have to incorporate various architectural features to remember the history of the input signals e.g., loops between the layers, “gated” neurons, and tapped delay lines. But real brains have rich dynamics expressed in terms of frequency bands like alpha, beta, gamma, delta, etc. To incorporate this aspect of brain dynamics in a Recurrent Neural Network (RNN) we propose to use nonlinear oscillators as dynamic neuron models in the hidden layers. The two oscillatory deep neural networks proposed are applied to the following EEG classification and prediction problems: Prediction of nearby EEG channels, classification of single-channel EEG data (healthy vs. epileptic, different stages of sleep stage classification), and multi-channel EEG data (Epileptic vs. Normal, Left vs. right-hand Motor imagery movement, and healthy vs. Claustrophobic EEG).","url":"https://doi.org/10.1101/2024.05.24.595714","authors":["Sayan Ghosh","C. Vigneswaran","NR Rohan","V.Srinivasa Chakravarthy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-30T05:25:30Z","doi":"10.1101/2024.05.24.595714","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/imbioc60287.2024.10590541","name":"Neural Network Model for Breast Tissue Thickness Estimation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/imbioc60287.2024.10590541","authors":["Henna Jethani","Milica Popović","Zoya Popović"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-15T17:20:33Z","doi":"10.1109/imbioc60287.2024.10590541","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1212/wnl.0000000000208311","name":"Classification of Subvocalized Letters with a Neural Network Algorithm (P10-4.003)","source":"crossref","abstract":"","url":"https://doi.org/10.1212/wnl.0000000000208311","authors":["Shaumprovo Debnath"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-09T16:15:06Z","doi":"10.1212/wnl.0000000000208311","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/iccc62609.2024.10941946","name":"Hardware-Accelerated 1-Bit Quantization Using PyRTL for Efficient Neural Network Design","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccc62609.2024.10941946","authors":["Shoufeng Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-03T00:01:20Z","doi":"10.1109/iccc62609.2024.10941946","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.14359/51740776","name":"Artificial Neural Network Model for Concrete Strength Predictions Based on Ultrasonic Pulse Velocity Measurement","source":"crossref","abstract":"","url":"https://doi.org/10.14359/51740776","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-26T09:04:26Z","doi":"10.14359/51740776","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1016/j.neucom.2024.128411","name":"Tensor product model transformation-based reinforcement learning neural network controller with guaranteed stability","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2024.128411","authors":["Kraisak Phothongkum","Suwat Kuntanapreeda"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-17T15:45:01Z","doi":"10.1016/j.neucom.2024.128411","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/iccpct61902.2024.10672654","name":"Cataracts Detection Using Convolution Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccpct61902.2024.10672654","authors":["Menaka.M","V.P.Kolanchinathan","Yogaraj.A","N.VenkataAbhiram","V.Kirubesh","S.Hariharan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-16T17:36:05Z","doi":"10.1109/iccpct61902.2024.10672654","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/icmee63700.2024.11025391","name":"Prediction model of UAV damage efficiency based on GRU neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icmee63700.2024.11025391","authors":["Yuhang Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-12T17:39:15Z","doi":"10.1109/icmee63700.2024.11025391","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1039/d5tc01371b/v2/review1","name":"Review for \"Amorphous Ta&lt;sub&gt;2&lt;/sub&gt;O&lt;sub&gt;5&lt;/sub&gt; memristor with excellent self-selective and artificial synaptic properties for artificial neural networks\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5tc01371b/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-16T17:06:47Z","doi":"10.1039/d5tc01371b/v2/review1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.2139/ssrn.4944640","name":"A Cepstrum-Informed Neural Network for Structural Damage Assessment","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4944640","authors":["Lechen Li","Adrian Brügger","Raimondo Betti","Zhenzhong Shen","Lei Gan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-02T23:23:23Z","doi":"10.2139/ssrn.4944640","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.20944/preprints202401.1285.v1","name":"Predictive Neural Network Modeling for Almond Harvest Dust Control","source":"crossref","abstract":"This study introduces a neural network-based approach to predict dust emission, specifically PM2.5 particles, during almond harvesting in California. Using a feedforward neural network (FNN), the research predicts PM2.5 emissions by analyzing key operational parameters of an advanced almond harvester. The model is trained on extensive field data from the almond pickup system, including variables like brush speed, angular velocity, and harvester forward speed. The results demonstrate a notable predictive accuracy of the FNN model, with a Mean Squared Error (MSE) of 0.02 and a Mean Absolute Error (MAE) of 0.01, indicating a high degree of precision in forecasting PM2.5 levels. The study also finds a strong correlation between certain operational parameters and PM2.5 emissions, highlighting specific areas for optimization in harvesting techniques. By integrating machine learning with agricultural practices, this research provides a significant tool for environmental management in almond production, offering a method to reduce harmful emissions while maintaining operational efficiency. This model presents a solution for the almond industry and sets a precedent for applying predictive analytics in sustainable agriculture.","url":"https://doi.org/10.20944/preprints202401.1285.v1","authors":["Reza Serajian","Jian-Qiao Sun","JEANETTE COBIAN-IÑIGUEZ","Reza Ehsani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-18T04:52:36Z","doi":"10.20944/preprints202401.1285.v1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.21203/rs.3.rs-3825788/v1","name":"Physics-informed two-tier neural network for non-linear model order reduction","source":"crossref","abstract":"Abstract In recent years, machine learning (ML) has had a great impact in the area of non-intrusive, non-linear model order reduction (MOR). However, the offline training phase often still entails high computational costs since it requires numerous, expensive, full-order solutions as the training data. Furthermore, in state-of-the-art methods, neural networks trained by a small amount of training data cannot be expected to generalize sufficiently well, and the training phase often ignores the underlying physical information when it is applied with MOR. Moreover, state-of-the-art MOR techniques that ensure an efficient online stage, such as hyper reduction techniques, are either intrusive or entail high offline computational costs. To resolve these challenges, inspired by recent developments in physics-informed and physics-reinforced neural networks, we propose a non-intrusive, physics-informed, two-tier deep network (TTDN) method. The proposed network, in which the first tier achieves the regression of the unknown quantity of interest and the second tier rebuilds the physical constitutive law between the unknown quantities of interest and derived quantities, is trained using pretraining and semi-supervised learning strategies. To illustrate the efficiency of the proposed approach, we perform numerical experiments on challenging non-linear and non-affine problems, including multi-scale mechanics problems.","url":"https://doi.org/10.21203/rs.3.rs-3825788/v1","authors":["Yankun Hong","Harshit Bansal","Karen Veroy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-23T13:05:47Z","doi":"10.21203/rs.3.rs-3825788/v1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.2139/ssrn.4869576","name":"A Generalized Artificial Neural Network Approach to Model Multiple-Extraction Humidification-Dehumidification Systems","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4869576","authors":["Mohamed  Ali Ahmed","Syed  M. Zubair"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-18T15:45:13Z","doi":"10.2139/ssrn.4869576","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1201/9781003428473-32","name":"Retinal Image Classification Using Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003428473-32","authors":["R. Kaladevi","T. Dinesh","R. Kishore"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-03T14:22:32Z","doi":"10.1201/9781003428473-32","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.21203/rs.3.rs-4199827/v1","name":"Constitutive Artificial Neural Network espoused Plant Leaf Disease Detection","source":"crossref","abstract":"Abstract The emergence of new diseases on plant leaves poses a substantial threat to global food safety and agricultural productivity. To mitigate this risk, accurate and swift detection of plant illnesses is crucial, reducing unnecessary expenses and minimizing financial losses and environmental damage. This study proposes a method called Plant Leaf Disease Detection with a Constitutive Artificial Neural Network (PLDD-CANN) to provide advancements in deep learning. The approach begins by gathering data from the Plant Village dataset and subjecting it to pre-processing techniques. This includes noise removal and image enhancement using a Variational Marginalized Particle Filter (AVMPF). Next, an Adaptive Convex Clustering (ACC) method is employed for image segmentation, followed by feature extraction using Fast Fourier and Continuous Wavelet (FFCWT) transforms. Finally, a Constitutive Artificial Neural Network (CANN) is utilized to categorize the input image to one of several categories, including healthy and various disease types like Yellow Leaf Curl Virus, Septoria Leaf Spot, Two-Spotted Spider Mite, Bacterial Spot, Target Spot, Leaf Mold, Mosaic Virus, Early Blight, and Late Blight. Then, the proposed technique is simulated using Python under several performance metrics including precision, f1-score, error rate accuracy, sensitivity, specificity and ROC. The proposed PLDD-CANN method provides 26.75%, 25.83% and 27.46% higher accuracy comparing with existing methods an enhanced CNN technique for plant leaves disease diagnosis in tomato (CNN-PLDD), A Novel Approach for Plant Leaf Disease Predictions with Recurrent Neural Network RNN Classification Method (RNN-PLDD), Detection of tomato leaf diseases for agro-based industries (FRCNN-PLDD) respectively.","url":"https://doi.org/10.21203/rs.3.rs-4199827/v1","authors":["Kaavya Kanagaraj","Madhumitha Kulandaivel","F. H. Shajin","Salini Prabhakaran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-04T06:32:35Z","doi":"10.21203/rs.3.rs-4199827/v1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.20944/preprints202407.0808.v1","name":"A Hybrid Forecasting Structure Based On Arima And Artificial Neural Network Models","source":"crossref","abstract":"This study involves the development of a hybrid forecasting framework that integrates two different models in a framework to improve prediction capability. Although the concept of hybridization is not a new issue in forecasting, our approach presents a new structure that combines two standard simple forecasting models uniquely for superior performance. Hybridization is significant for complex data sets with multiple patterns. Such data sets do not respond well to simple models, and hybrid models based on the integration of various forecasting tools often lead to better forecasting performance. The proposed architecture includes serially connected ARIMA and ANN models. The original data set is first processed by ARIMA. The error (i.e., residuals) of the ARIMA is sent to the ANN for secondary processing. Between these two models, there is a classification mechanism where the raw output of the ARIMA is categorized into three groups before they are sent to the secondary model. The algorithm is tested on well-known forecasting cases from the literature. The proposed model performs better than existing methods in most cases.","url":"https://doi.org/10.20944/preprints202407.0808.v1","authors":["Adil Atesongun","Mehmet Gulsen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-11T11:34:19Z","doi":"10.20944/preprints202407.0808.v1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/icsece61636.2024.10729324","name":"Research on Injury Identification Based on Analytical Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icsece61636.2024.10729324","authors":["Minghan Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-29T17:28:51Z","doi":"10.1109/icsece61636.2024.10729324","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/i3ceet61722.2024.10993758","name":"Sign Language Recognition Using Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/i3ceet61722.2024.10993758","authors":["R.Elankavi","A.Bhavya","G.Bharath","K.S.Amrutha","T.R.Geethika","M.Anand"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-13T17:44:24Z","doi":"10.1109/i3ceet61722.2024.10993758","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.20944/preprints202412.0113.v1","name":"Reinforcement Neural Network-Based Grid Integrated PV System with the Battery Management System","source":"crossref","abstract":"A Reinforcement Neural Network-Based Grid Integrated PV System with a Battery Management System (BMS) aims to enhance the efficiency and reliability of renewable energy systems. In such a setup, the photovoltaic (PV) system generates electricity, which can be used immediately, stored in batteries, or fed into the grid. The challenge lies in dynamically optimizing the power flow between these components to minimize energy costs, maximize the use of renewable energy, and maintain grid stability. Reinforcement learning (RL), combined with neural networks, offers a powerful solution by enabling the system to learn and adapt its energy management strategy in real time. The RL agent interacts with the environment (i.e., the grid, PV system, and battery), continuously improving its decisions on when to store energy, draw from the battery, and supply power to the grid. This intelligent control approach ensures optimal performance, contributing to a more sustainable and resilient energy system.","url":"https://doi.org/10.20944/preprints202412.0113.v1","authors":["Salah Mahdi Thajeel","Doğu Çağdaş Atilla"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-04T00:57:32Z","doi":"10.20944/preprints202412.0113.v1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1002/we.70052/v1/review1","name":"Review for \"Scaled Physical Modelling of Floating Offshore Wind Turbines Using a Neural Network‐Based Surrogate Model for Aerodynamic Emulation\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/we.70052/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-01T00:12:43Z","doi":"10.1002/we.70052/v1/review1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.21203/rs.3.rs-4153832/v1","name":"Compare Neural Network and Linear Regression when there exist outliers or sensitive data; Advantage and Disadvantages","source":"crossref","abstract":"Abstract This paper examines a particular type of neural network architecture characterized by having just one hidden layer. Our motivation stems from the fact that this configuration offers both flexibility and strength in approximating continuous functions. Specifically, we shall contrast its performance against that of linear regression when dealing with the presence of outliers or influence data. To gain further insights into this model's merits and limitations, we delve deeper into analyzing its advantages and disadvantages.","url":"https://doi.org/10.21203/rs.3.rs-4153832/v1","authors":["Mohammad Zare"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-27T04:37:31Z","doi":"10.21203/rs.3.rs-4153832/v1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.36227/techrxiv.21946139.v3","name":"A novel neural network-based data acquisition system targeting high-speed electrical impedance tomography systems","source":"crossref","abstract":"**Note:** This preprint has been accepted for publication in [ IEEE Transactions on Circuits and Systems--I: Regular Papers ]. The published version is available on IEEE Xplore: [DOI link]( https://ieeexplore.ieee.org/document/10607897 ). The paper presents a design for a high-speed data acquisition (DAQ) system for electrical impedance tomography (EIT). The proposed solution involves using a high-speed analog-to-digital converter (ADC) to digitize the analog signals corresponding to multiple pairs of electrodes within the same cycle in a time-multiplexed manner. The extracted samples are fed to an artificial neural network (ANN) to estimate the peak amplitudes of the signals for every channel, which are then used for image reconstruction. Various ANN models with customized loss functions were assessed, and the optimal model selection approach using the grid search technique is presented. Unlike other multi-frequency based techniques, the suggested approach does not require a multi-frequency current source, thus simplifying the data acquisition system by not requiring high-quality narrow-band pass-band filters for different frequencies. The proposed approach allows EIT systems to operate at a very high throughput that can exceed 2,800 frames per second for a 50 kHz excitation signal using 32 or more electrodes. Extensive experimental testing showed that peak estimation accuracy can be achieved with more than 98%, even for signals with 40 dB SNRs. The suggested approach has thus promising potential for EIT applications requiring high SNR and fast data acquisition.","url":"https://doi.org/10.36227/techrxiv.21946139.v3","authors":["Varun Kumar Tiwari","Mahmoud Meribout"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-01T15:48:04Z","doi":"10.36227/techrxiv.21946139.v3","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.2139/ssrn.4954550","name":"Modeling of a Delayed Coking Unit Using Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4954550","authors":["Olga Kharitonova","Veronika Bronskaya","Dmitry Bashkirov","Denis Balzamov","Tatiana Ignashina"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-12T14:24:36Z","doi":"10.2139/ssrn.4954550","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.2139/ssrn.4985629","name":"Hourglass Pattern Matching for Deep Aware Neural Network Text Recommendation Model","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4985629","authors":["Li Gao","Hongjun Li","Qingkui Chen","Dunlu Peng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-12T23:37:26Z","doi":"10.2139/ssrn.4985629","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.2139/ssrn.4873350","name":"Mr-Gcn:A Graph Convolutional Neural Network Approach for Decoding Eeg Motor Imagery Signals","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4873350","authors":["Xiaojing Hao","Xiaoqi Lu","Dahua Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-22T14:17:10Z","doi":"10.2139/ssrn.4873350","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1002/2688-8319.12394/v2/review2","name":"Review for \"A novel method for estimating avian roost sizes using passive acoustic recordings using deep neural network\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/2688-8319.12394/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-02T09:49:20Z","doi":"10.1002/2688-8319.12394/v2/review2","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.14311/nnw.2024.34.017","name":"Post-Pandemic Road Accident Analysis: Patterns and Impacts","source":"crossref","abstract":"This study analyzes the impact of COVID-19 restrictions on road accident trends in the Czech Republic from 2015 to 2024, utilizing a comprehensive dataset of over one million recorded accidents. The research highlights a significant decline in accident rates during the strict lockdown periods, correlating reduced mobility with fewer traffic incidents. As restrictions eased, accident rates rose again, revealing seasonal variations and regional disparities, particularly in urban areas like Prague. Findings suggest that the pandemic has reshaped commuting patterns and could influence future traffic management strategies. The analysis underscores the need for targeted policies to enhance road safety, especially during high-risk seasons.","url":"https://doi.org/10.14311/nnw.2024.34.017","authors":["Igor Gavrilov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-06T10:28:13Z","doi":"10.14311/nnw.2024.34.017","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.2139/ssrn.4643560","name":"Textual Changes in 10-Ks and Stock Price Crash Risk: Evidence from Neural Network Embeddings","source":"crossref","abstract":"Previous research attributes stock price crash risk to managerial bad news hoarding. Contrary to this notion, we find evidence that stock price crash risk is determined by investor inattention to textual changes in corporate disclosures. Using a large sample of 10-K filings, we estimate neural network embeddings to quantify the degree of textual changes in successive 10-Ks. We find that changes in 10-Ks have a positive and economically meaningful impact on one-year-ahead stock price crash risks. Our results suggest that investor inattention to textual changes in 10-Ks can have broader capital market consequences than previously documented.","url":"https://doi.org/10.2139/ssrn.4643560","authors":["Yahya Yilmaz","Milan Reichmann"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-22T12:59:22Z","doi":"10.2139/ssrn.4643560","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.2514/6.2024-1638","name":"Artificial Neural Network based Vapor-Liquid Equilibrium Modeling for Simulation of Transcritical Multiphase Flows","source":"crossref","abstract":"","url":"https://doi.org/10.2514/6.2024-1638","authors":["Navneeth Srinivasan","Hongyuan Zhang","Suo Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-29T22:03:51Z","doi":"10.2514/6.2024-1638","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1145/3662739.3672323","name":"Convolutional Neural Network Image Recognition in Architectural Landscape Visualization Technology","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3662739.3672323","authors":["Xiaoli He","Hong Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-03T10:41:34Z","doi":"10.1145/3662739.3672323","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/vdat63601.2024.10705716","name":"A Deep Insight into Frequency and Voltage Variation Impact on Memristor Performance and Applications of Memristor-NMOS Hybrid Structure in the Digital Domain","source":"crossref","abstract":"","url":"https://doi.org/10.1109/vdat63601.2024.10705716","authors":["Gummuluri Pavan Kumar","Manas Ranjan Tripathy","Jogendra Singh Rana","Harshit Srivastava","BSS Tejesh","Satyabrata Jit"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-09T17:45:58Z","doi":"10.1109/vdat63601.2024.10705716","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1016/j.ecoinf.2024.102792","name":"A hyperspectral metal concentration inversion method using attention mechanism and graph neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.ecoinf.2024.102792","authors":["Lei Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-25T00:16:40Z","doi":"10.1016/j.ecoinf.2024.102792","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/ijcnn60899.2024.10651544","name":"LNPT: Label-free Network Pruning and Training","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn60899.2024.10651544","authors":["Xiao Jinying","Ping Li","Zhe Tang","Jie Nie"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T13:35:05Z","doi":"10.1109/ijcnn60899.2024.10651544","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1364/cleo_at.2024.jth2a.212","name":"The Memory Bottleneck in Photonic Neural Network Accelerators","source":"crossref","abstract":"Photonic Tensor Cores are a competitive accelerator for Neural Networks, offering high throughput, but requiring large bandwidths to operate at their maximum efficiency. Here we offer an analysis of the memory bottleneck for PTC.","url":"https://doi.org/10.1364/cleo_at.2024.jth2a.212","authors":["Russell L. T. Schwartz","Belal Jahannia","Nicola Peserico","Hamed Dalir","Volker J. Sorger"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-05T16:17:50Z","doi":"10.1364/cleo_at.2024.jth2a.212","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/fit63703.2024.10838413","name":"Handwritten Hindko Text Recognition Using Deep Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/fit63703.2024.10838413","authors":["Tanveer Ahmed","Sohail Khan","Khalil Khan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-17T18:32:11Z","doi":"10.1109/fit63703.2024.10838413","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/iconat61936.2024.10775042","name":"Research on the Financial Status of Companies Based on Neural Network Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iconat61936.2024.10775042","authors":["Gu Yun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-10T20:01:10Z","doi":"10.1109/iconat61936.2024.10775042","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1504/ijbm.2024.10063905","name":"Dynamic emotion recognition of human face based on convolutional neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1504/ijbm.2024.10063905","authors":["Lanbo Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-04T13:00:08Z","doi":"10.1504/ijbm.2024.10063905","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/pesgm51994.2024.10689047","name":"Microgrid Optimal Energy Scheduling Considering Neural Network based Battery Degradation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/pesgm51994.2024.10689047","authors":["Cunzhi Zhao","Xingpeng Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-04T17:30:03Z","doi":"10.1109/pesgm51994.2024.10689047","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/icde60146.2024.00451","name":"PR-GNN: Enhancing PoC Report Recommendation with Graph Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icde60146.2024.00451","authors":["Jiangtao Lu","Song Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-23T17:38:03Z","doi":"10.1109/icde60146.2024.00451","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.23919/eumc61614.2024.10732352","name":"Joint Communication and Computation Using RF Amplifier-based Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.23919/eumc61614.2024.10732352","authors":["Siqi Wang","Ayça Özçelikkale","Aziz Benlarbi-Delai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-31T17:32:14Z","doi":"10.23919/eumc61614.2024.10732352","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/piers62282.2024.10618502","name":"AE-D2NN: Autoencoder in Diffractive Neural Network Form","source":"crossref","abstract":"","url":"https://doi.org/10.1109/piers62282.2024.10618502","authors":["Peijie Feng","Zongkun Zhang","Mingzhe Chong","Yunhua Tan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-09T17:18:24Z","doi":"10.1109/piers62282.2024.10618502","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/incowoco64194.2024.10863778","name":"Universal Approximation Theorem for Bipolar Fuzzy Madaline Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/incowoco64194.2024.10863778","authors":["S. Anita Shanthi","R. Preethi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-06T18:31:47Z","doi":"10.1109/incowoco64194.2024.10863778","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/isctis63324.2024.10699234","name":"Linux log Dimension Reduction Method based on Recurrent Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isctis63324.2024.10699234","authors":["Dawei Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-04T17:33:11Z","doi":"10.1109/isctis63324.2024.10699234","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/iccect60629.2024.10545697","name":"Application of PSO Algorithm in Optimizing BP Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccect60629.2024.10545697","authors":["Zihao Cai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-07T17:23:08Z","doi":"10.1109/iccect60629.2024.10545697","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1364/cleo_si.2024.sf2a.7","name":"Multi-layer Optical Convolutional Neural Network with Nonlinear Activation","source":"crossref","abstract":"We present a compact multi-layer optical convolutional neural network for pre-sensor computing with nonlinear activation by masks and an image intensifier. This can off-load 83.1% computation to optics and achieve competitive accuracies for classification tasks.","url":"https://doi.org/10.1364/cleo_si.2024.sf2a.7","authors":["Zheng Huang","Conghe Wang","Wanxin Shi","Shukai Wu","Sigang Yang","Hongwei Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-05T18:27:50Z","doi":"10.1364/cleo_si.2024.sf2a.7","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.23919/eusipco63174.2024.10715217","name":"Universal End-to-End Neural Network for Lossy Image Compression","source":"crossref","abstract":"","url":"https://doi.org/10.23919/eusipco63174.2024.10715217","authors":["Bouzid Arezki","Fangchen Feng","Anissa Mokraoui"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-21T14:01:48Z","doi":"10.23919/eusipco63174.2024.10715217","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1007/s00521-024-09575-4","name":"Deep graph-level clustering using pseudo-label-guided mutual information maximization network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-024-09575-4","authors":["Jinyu Cai","Yi Han","Wenzhong Guo","Jicong Fan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-07T12:48:45Z","doi":"10.1007/s00521-024-09575-4","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.2139/ssrn.4711477","name":"Topology Optimization for Self-Adjoint Problems Using Neural Network-Based Analysis and Design","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4711477","authors":["Kyuwon Lee","Cheolwoong Kim","Jeonghoon Yoo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-31T08:18:35Z","doi":"10.2139/ssrn.4711477","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.2139/ssrn.4743240","name":"Utilizing Artificial Neural Network Sets for Ship Design Optimization to Reduce Added Wave Resistance and Co2 Emissions","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4743240","authors":["Tomasz Cepowski"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-29T19:47:16Z","doi":"10.2139/ssrn.4743240","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.21203/rs.3.rs-3933137/v1","name":"Real-time siamese neural network based algorithm for user recognition by their eye blinking","source":"crossref","abstract":"Abstract The article proposes a new method for user recognition based on a unique eyelid blinking pattern. Our research aimed to develop a user recognition method using eyelid blinking that is resistant to shoulder surfing and brute force attacks, while also not requiring complex recording devices. Most user authentication methods utilizing eyelid blinking patterns are vulnerable to pattern replication attacks. On the other hand, methods using EEG sometimes require the use of complicated equipment to record the blinking event. In our study, we utilized the publicly available mEBAL database. The temporal eyelid movement patterns extracted from the samples in the database are analyzed by a Siamese neural network. Our achieved results of 98.20% accuracy and 0.11 EER unequivocally demonstrate the superiority of the proposed method over other methods using eyelid blinking for user authentication.","url":"https://doi.org/10.21203/rs.3.rs-3933137/v1","authors":["Kamil Malinowski","Khalid Saeed"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-08T08:15:15Z","doi":"10.21203/rs.3.rs-3933137/v1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.21203/rs.3.rs-4218442/v1","name":"Prediction of COD in Industrial Wastewater Treatment Plant using an Artificial Neural Network","source":"crossref","abstract":"Abstract In this investigation, the modeling of the Aksaray industrial wastewater treatment plant was performed using artificial neural networks with various architectures in the MATLAB software. The dataset utilized in this study was collected from the Aksaray wastewater treatment plant over a nine-month period through daily records. The treatment efficiency of the plants was assessed based on the output values of chemical oxygen demand (COD) output. Principal component analysis (PCA) was applied to furnish input for the artificial neural network (ANN). The model's performance was evaluated using the mean squared error (MSE) and correlation coefficient (R 2 ) parameters. The optimal architecture for the neural network model was determined through several trial and error iterations. According to the modeling results, the ANN exhibited a high predictive capability for plant performance, with an R 2 reaching up to 0.9997 when comparing the observed and predicted output variables.","url":"https://doi.org/10.21203/rs.3.rs-4218442/v1","authors":["Özgül Çimen Mesutoğlu","Oğuzhan Gök"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-17T08:20:25Z","doi":"10.21203/rs.3.rs-4218442/v1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.2139/ssrn.4978049","name":"Morphological Aesthetic Evaluation of Cervical Traction Device Based on K-Means and BP Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4978049","authors":["Kai Zhang","Qingxue Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-07T12:47:10Z","doi":"10.2139/ssrn.4978049","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1002/we.2976/v1/review2","name":"Review for \"Volt/VAr Regulation of the West Mediterranean Regional Electrical Grids Using SVC/STATCOM Devices With Neural Network Algorithms\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/we.2976/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-25T16:09:21Z","doi":"10.1002/we.2976/v1/review2","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.21203/rs.3.rs-4746910/v1","name":"Acquisition of similar properties by filters in the same stream of a multistream convolutional neural network","source":"crossref","abstract":"Abstract Functional modular organization is observed in a variety of cortical areas in the brain. In the visual cortex of primates, adjacent neurons often respond to the same visual submodality, such as color or orientation, and have a similar preferred orientation or preferred color. However, it remains unclear why functional modular organization emerges in the cerebral cortex. In the present study, I constructed and trained a multistream convolutional neural network to examine whether filters in the same stream acquire similar properties. Although filters in the same stream were able to develop any structures, they acquired similar degrees of stimulus selectivity and similar stimulus preferences. The deletion of filters in a single stream that had similar degrees of stimulus selectivity resulted in larger decreases in classification accuracy than the deletion of those that did not. By contrast, the deletion of filters in a single stream that shared a preferred stimulus resulted in similar decreases in classification accuracy to the deletion of those that did not. Together, these findings suggest that filters with similar degrees of stimulus selectivity in the same stream are required for optimal task performance of the neural network, and probably of the brain.","url":"https://doi.org/10.21203/rs.3.rs-4746910/v1","authors":["Hiroshi Tamura"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-12T11:38:16Z","doi":"10.21203/rs.3.rs-4746910/v1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/access.2024.3461366","name":"Retraction Notice: Image Recognition Technology Based on Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/access.2024.3461366","authors":["Jianqiu Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-01T17:29:43Z","doi":"10.1109/access.2024.3461366","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.36227/techrxiv.171340674.46899326/v1","name":"Massive MIMO Channel Estimation with Convolutional Neural Network Structures","source":"crossref","abstract":"","url":"https://doi.org/10.36227/techrxiv.171340674.46899326/v1","authors":["Leopoldo Carro-Calvo","Alejandro de la Fuente","Antonio Melgar","Eduardo Morgado"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-17T22:19:24Z","doi":"10.36227/techrxiv.171340674.46899326/v1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1007/s00521-023-09403-1","name":"Neural network classification of eigenmodes in the magnetohydrodynamic spectroscopy code Legolas","source":"crossref","abstract":"Abstract A neural network is employed to address a non-binary classification problem of plasma instabilities in astrophysical jets, calculated with the code. The trained models exhibit reliable performance in the identification of the two instability types supported by these jets. We also discuss the generation of artificial data and refinement of predictions in general eigenfunction classification problems.","url":"https://doi.org/10.1007/s00521-023-09403-1","authors":["J. De Jonghe","M. D. Kuczyński"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-16T11:02:59Z","doi":"10.1007/s00521-023-09403-1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.2139/ssrn.4926745","name":"Forecasting Building Operation Dynamics Using a Physics-Informed Spatio-Temporal Graph Neural Network (Pistgnn) Ensemble","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4926745","authors":["Jongseo Lee","Sungzoon Cho"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-19T09:47:41Z","doi":"10.2139/ssrn.4926745","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.2139/ssrn.5030777","name":"MR-GCN:A Graph Convolutional Neural Network Approach for Decoding EEG Motor Imagery Signals","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5030777","authors":["Xiaojing Hao","Xiaoqi Lu","Dahua Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-07T03:09:47Z","doi":"10.2139/ssrn.5030777","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.20944/preprints202404.0565.v1","name":"Convolution Neural Network Based Multi- Label Disease Detection using Tongue Images","source":"crossref","abstract":"ABSTRACT Purpose: Tongue image analysis for disease diagnosis is an ancient traditional non-invasive diagnosis technique widely used by traditional medicine practitioners. Deep Learning based multi-label disease detection models offer tremendous potential to clinical decision support systems, by facilitating preliminary diagnosis. Methods: In this work, we propose a multi-label disease detection pipeline, where in observation and analysis of tongue images captured and received via smartphones assist in predicting the health status of an individual. All images are voluntarily given by subjects consulting collaborating physicians. Images thus acquired are first and foremost classified either into a diseased or a normal category by a 5-fold cross-validation algorithm using a convolution neural network (MobileNetV2) model for binary classification. Once the diseased label is predicted, the image is used to diagnose multiple diseases using the prediction algorithm based on DenseNet121. Results: Average accuracy of 93 % was achieved in classifying diseased from normal healthy tongue by detection model with MobileNetV2 architecture. Multilabel disease classification produced more than 90% accurate results for the seven class labels considered. Conclusion: AI based image analysis shows promising results and an extensive dataset could provide further improvements to this approach. Rather than employing high-cost sophisticated image capturing setup, experimenting with smartphone images opens opportunity to provide preliminary health status to individuals on smartphone prior to further line of treatment and diagnosis.","url":"https://doi.org/10.20944/preprints202404.0565.v1","authors":["Vibha Bhatnagar","Prashant P Bansod"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-10T09:22:36Z","doi":"10.20944/preprints202404.0565.v1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.7554/elife.90597.2.sa1","name":"Reviewer #2 (Public Review): Hippocampome.org v2.0: a knowledge base enabling data-driven spiking neural network simulations of rodent hippocampal circuits","source":"crossref","abstract":"","url":"https://doi.org/10.7554/elife.90597.2.sa1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-26T06:25:53Z","doi":"10.7554/elife.90597.2.sa1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1101/2024.12.11.627386","name":"Classification of Visual Imagery and Imagined Speech EEG based Brain Computer Interfaces using 1D Convolutional Neural Network","source":"crossref","abstract":"Abstract Non-invasive brain-computer interfaces (BCI) utilising electroencephalogram (EEG) signals are a current popular, affordable and accessible method for establishing communication paths between the mind and external devices. However, the challenges faced are inter-subject variability, BCI illiteracy and poor machine learning decoding performance. Two emerging intuitive mental paradigms, Visual Imagery (VI) and Imagined Speech (IS) show promise to optimise the development of non-invasive BCIs, which involves the extraction of corresponding neural patterns during the imagined tasks. This study took a comprehensive user-centric approach to build on the current foundation of knowledge on VI and IS EEG-BCIs utilising an adapted 1D-CNN to optimise the classification decoding performance. Twenty healthy participants were assessed for their ability to visualise imagery in their minds and performed the VI and IS mental paradigms in two class conditions “push” and “relax”. It was shown that alpha and beta suppression was observed during the “push” condition of VI compared to the “relax” condition, and those that scored higher in the VVIQ had better VI classification accuracy than those who did not. The adapted 1D-CNN model performed well for classification between the two classes “push” and “relax” at 89.3% and 77.87% performance accuracy for VI and IS, respectively. These findings contribute to the current body of work on VI BCI, that it is a dynamic and plausible option compared to standard BCI paradigms, and VI BCI illiteracy could potentially be controlled by VVIQ. It also demonstrated the potential of the 1D-CNN model in classification of VI and IS EEG-BCIs.","url":"https://doi.org/10.1101/2024.12.11.627386","authors":["Diane Le"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-14T06:30:14Z","doi":"10.1101/2024.12.11.627386","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.2139/ssrn.4992815","name":"Adversarially Robust Neural Network Decision Boundaries Via Tropical Geometry","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4992815","authors":["Kurt Pasque","Christopher Teska","Ruriko Yoshida","Keiji Miura","Jefferson Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-19T11:37:26Z","doi":"10.2139/ssrn.4992815","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.2139/ssrn.4892319","name":"Seismic Metamaterial Prediction Design Based on Joint Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4892319","authors":["Nannan SHI","Weichen Zhang","Han Liu","Fanyin Meng","Liutao Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-16T12:10:33Z","doi":"10.2139/ssrn.4892319","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.21275/sr24908221149","name":"Predicting Market Capitalization of Large Global Companies using Ordinary Least Square, Feedforward and Bayesian Neural Network Models","source":"crossref","abstract":"","url":"https://doi.org/10.21275/sr24908221149","authors":["Vasu Padmanabhan","S Nirmala"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-15T04:42:50Z","doi":"10.21275/sr24908221149","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.20944/preprints202407.0392.v1","name":"Enhanced Brain-to-Brain Communication Security via Adversarial Neural Network Training","source":"crossref","abstract":"Brain-to-brain communication (B2B-C) is rapidly expanding, integrating communication technology and neuroscience to enable direct neural data transfer between people. Nonetheless, because neural data is susceptible to noise, interference, and hostile attacks, guaranteeing the security and resilience of B2B-C systems continues to be difficult. This work aims to use Adversarial Neural Network Training (ANNT) to improve the security of B2B-C systems by using Steady-State Visually Evoked Potentials (SSVEP) EEG data. We use two large SSVEP datasets for a thorough analysis: Lee2019_SSVEP and Nakanishi2015. We use the Fast Gradient Sign Method (FGSM) to create adversarial instances and ANNT to train the model on clean and adversarially perturbed data. The system&amp;#039;s accuracy and resilience are significantly improved by ANNT, as seen by the up to 17% increase in adversarial accuracy and the average 0.03 point improvement in the Area Under the Curve (AUC). This work demonstrates how ANNT may strengthen B2B-C systems against advanced cyberattacks, opening the door for dependable and safe neural communication technologies.","url":"https://doi.org/10.20944/preprints202407.0392.v1","authors":["Hossein Ahmadi","Ali Kuhestani","MohammadReza Keshavarzi","Luca Mesin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-09T06:39:07Z","doi":"10.20944/preprints202407.0392.v1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.2139/ssrn.5044669","name":"Image-Based Wavefront Distortion Compensation for Segmented Mirror Telescope Via Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5044669","authors":["yong wu","Tianbao Tao","Mei Hui"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-05T01:40:58Z","doi":"10.2139/ssrn.5044669","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.21203/rs.3.rs-3951476/v1","name":"VISTA: Vision Improvement via Split and Reconstruct Deep Neural Network for Fundus Image Quality Assessment","source":"crossref","abstract":"Abstract Widespread eye conditions such as cataracts, diabetic retinopathy, and glaucoma impact people worldwide. Ophthalmology uses fundus photography for diagnosing these retinal disorders, but fundus images are prone to image quality challenges. Accurate diagnosis hinges on high-quality fundus images. Therefore, there is a need for image quality assessment methods to evaluate fundus images before diagnosis. Consequently, this paper introduces a deep-learning model tailored for fundus images that supports large images. Our division method centres on preserving the original image’s high-resolution features while maintaining low computing and high accuracy. The proposed approach encompasses two fundamental components: an autoencoder model for input image reconstruction and image classification to classify the image quality based on the latent features extracted by the autoencoder, all performed at the original image size, without alteration, before reassembly for decoding networks. Through post-hoc interpretability methods, we verified that our model focuses on key elements of fundus image quality. Additionally, an intrinsic interpretability module has been designed into the network that allows decomposing class scores into underlying concepts quality such as brightness or presence of anatomical structures. Experimental results in our model with EyeQ, a fundus image dataset with three categories ( Good , Usable , and Rejected ) demonstrate that our approach produces competitive outcomes compared to other deep learning-based methods with an overall Accuracy of 0.91 , a precision of 0.88 , a recall of 0.89 , and an impressive F1-score of 0.89 . The code is publicly available at https://github.com/saifalkhaldiurv/VISTA_Image - Quality - Assessment.","url":"https://doi.org/10.21203/rs.3.rs-3951476/v1","authors":["Saif Khalid musluh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-13T03:08:42Z","doi":"10.21203/rs.3.rs-3951476/v1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.2139/ssrn.4719887","name":"Information Orientation-Based Modular Type-2 Fuzzy Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4719887","authors":["Chenxuan Sun","Zheng Liu","Xiaolong Wu","Hongyan Yang","Honggui Han"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-07T18:52:50Z","doi":"10.2139/ssrn.4719887","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.21203/rs.3.rs-5556309/v1","name":"A Novel Multi-Input Neural Network Model for MicroRNA Target-Site Detection","source":"crossref","abstract":"Abstract Purpose: MicroRNAs are tiny non-coding RNA sequences that regulate gene expressions and play crucial roles in controlling cell activities. They function by binding to their target messenger RNAs (mRNAs) and suppressing protein synthesis. Detecting the binding location of a microRNA is an important step towards discovering microRNA functions. Given the many possibilities that a microRNA can bind to an mRNA, microRNA target-site detection is a challenging task in vivo and in vitro; from time and cost limitations of experimental methods to high false positive rates of computational methods. Methods: In this paper, we propose a multi-input neural network-based algorithm that yields high recall and precision results simultaneously. Moreover, we designed a Dynamic Programming(DP) algorithm to predict the duplex structure of microRNA target-site, specific to the context of these sequences. The predicted duplex structures, substructures resulting from the DP algorithm, minimum free energy (MFE) of the substructures, and a probabilistic image of possible base pairs in the duplex are all fed in parallel into our algorithm to learn a comprehensive and precise model. Results and Conclusions: Our method on an experimentally validated test set, detects target-sites with AUPRC of 0.9373, Precision of 0.8725, Recall of 0.8703, and outperforms several commonly used computational methods of microRNA target predictions. In addition, using the duplex structure, MFE, and binding probabilities, rather than the nucleotide sequences of the microRNA and targetsites, enables our model to generalize beyond specific sequence contexts and perform well on sequentially distant samples. The source code for our algorithm and the accompanying datasets are freely accessible on Github at: https://github.com/mohebbimg/minn.git","url":"https://doi.org/10.21203/rs.3.rs-5556309/v1","authors":["Mohammad Mohebbi","Ethan Bennett","Phillip Williams"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-04T13:29:59Z","doi":"10.21203/rs.3.rs-5556309/v1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.21203/rs.3.rs-4124194/v1","name":"Out of Model Zoo: Towards Selecting the Best Deep Neural Network with Cognitive Analysis","source":"crossref","abstract":"Abstract Deep neural networks have achieved impressive performance on a huge amount of tasks and many model zoos are available that provide pre-trained models for free download. Despite the convenience, it is still difficult for the resource-constrained companies, especially startups, to select the best model from many candidates for their own tasks. Due to the lack of training data, the main challenges are to (1) evaluate the robustness of models with a test dataset and (2) optimize the prediction to maximize the usage of the model zoo. To address these challenges, we propose a robust model selector, Miss DL , which incorporates cognitive analysis and a series of criteria to select robust models from a given model zoo. We first propose a systemic method to simulate the distortions of new data points and calculate the dominant labels of the new data points. Then, we propose a metric to measure the robustness of models and select the best model. Motivated by the low confidence scores of the selected model on certain data points, we select a complementary model for each class for optimization. We evaluate the proposed Miss DL on popular deep neural networks and image datasets, including CIFAR-10, CIFAR-100, and ImageNet. Extensive experiments are performed to show the robustness and efficiency of Miss DL in different settings.","url":"https://doi.org/10.21203/rs.3.rs-4124194/v1","authors":["Ying Yang","Xiao Lv"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-21T17:59:17Z","doi":"10.21203/rs.3.rs-4124194/v1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.36227/techrxiv.170492238.85381351/v1","name":"ConGCNet: Convex Geometric Constructive Neural Network with Fast Constraint for Industrial Internet of Things","source":"crossref","abstract":"","url":"https://doi.org/10.36227/techrxiv.170492238.85381351/v1","authors":["Jing Nan","Yan Qin","Wei Dai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-10T16:33:10Z","doi":"10.36227/techrxiv.170492238.85381351/v1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.7490/f1000research.1119976.1","name":"TA-RNN: an attention-based time-aware recurrent neural network architecture for electronic health records","source":"crossref","abstract":"Time-Aware RNN (TA-RNN) and TA-RNN-Autoencoder (TA-RNN-AE) are two deep learning architectures for early predicting of clinical outcomes in Electronic Health Record (EHR) at the next visit and multiple visits ahead for patients, respectively. To mitigate the impact of the irregular time intervals between visits, we incorporate time embedding of the elapsed times between consecutive visits. For results interpretability, a dual-level attention mechanism that operates between visits and features within each visit is introduced.","url":"https://doi.org/10.7490/f1000research.1119976.1","authors":["Mohammad Al Olaimat","Serdar Bozdag"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-21T15:12:06Z","doi":"10.7490/f1000research.1119976.1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1145/3673277.3673369","name":"Quantum circuit output prediction based on time-series neural network integration","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3673277.3673369","authors":["Xiang Li","Xueyun Cheng","Xinyu Chen","Zhijin Guan","Pengcheng Zhu","Hui Gu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-30T18:34:42Z","doi":"10.1145/3673277.3673369","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.21203/rs.3.rs-3943271/v1","name":"Quantum neural network with ensemble learning to mitigate barren plateaus and cost function concentration","source":"crossref","abstract":"Abstract The rapid development of quantum computers promises transformative impacts across diverse fields of science and technology. Quantum neural networks (QNNs), as a forefront application, hold substantial potential. Despite the multitude of proposed models in the literature, persistent challenges, notably the vanishing gradient (VG) and cost function concentration (CFC) problems, impede their widespread success. In this study, we introduce a novel approach to quantum neural network construction, specifically addressing the issues of VG and CFC.Our methodology employs ensemble learning, advocating for the simultaneous deployment of multiple quantum circuits with a depth equal to 1, a departure from the conventional use of a single quantum circuit with depth L . We assess the efficacy of our proposed model through a comparative analysis with a conventionally constructed QNN. The evaluation unfolds in the context of a classification problem, yielding valuable insights into the potential advantages of our innovative approach.","url":"https://doi.org/10.21203/rs.3.rs-3943271/v1","authors":["Lucas Friedrich","Jonas Maziero"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-12T04:00:45Z","doi":"10.21203/rs.3.rs-3943271/v1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1101/2024.02.15.580574","name":"A Neural Network Approach to Identify Left-Right Orientation of Anatomical Brain MRI","source":"crossref","abstract":"Abstract Left-right orientation misidentification in brain MRIs presents significant challenges due to several factors, including metadata loss or ambiguity, which often occurs during the de-identification of medical images for research, conversion between image formats, software operations that strip or overwrite metadata, and the use of older imaging systems that stored orientation differently. This study presents a novel application of deep-learning to enhance the accuracy of left-right orientation identification in anatomical brain MRI scans. A three-dimensional Convolutional Neural Network model was trained using 350 MRIs and evaluated on eight distinct brain MRI databases, totaling 3,384 MRIs, to assess its performance across various conditions, including neurodegenerative diseases. The proposed deep-learning framework demonstrated a 99.6% accuracy in identifying the left-right orientation, thus addressing challenges associated with the loss of orientation metadata. GradCAM was used to visualize areas of the brain where the model focused, demonstrating the importance of the right planum temporale and surrounding areas in judging left-right orientation. The planum temporale is known to exhibit notable left-right asymmetry related to language functions, underscoring the biological validity of the model. More than half of the ten left-right misidentified MRIs involved notable brain feature variations, such as severe temporal lobe atrophy, arachnoidal cysts adjacent to the temporal lobe, or unusual cerebral torque, indicating areas for further investigation. This approach offers a potential solution to the persistent issue of left-right misorientation in brain MRIs and supports the reliability of neuroscientific research by ensuring accurate data interpretation.","url":"https://doi.org/10.1101/2024.02.15.580574","authors":["Kei Nishimaki","Hitoshi Iyatomi","Kenichi Oishi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-27T13:24:35Z","doi":"10.1101/2024.02.15.580574","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.20944/preprints202411.0183.v1","name":"Neural Network for Enhancing Robot Assisted Rehabilitation: A Systematic Review","source":"crossref","abstract":"Recently, the integration of neural networks into robotic exoskeletons for physical rehabilitation has become popular due to their ability to interpret complex physiological signals. Surface electromyography (sEMG), electromyography (EMG), electroencephalography (EEG), and other physiological signals enable communication between the human body and robotic systems. Utilizing physiological signals for communicating with robots plays a crucial role in robot assisted neurorehabilitation. This systematic review synthesizes 44 peer-reviewed studies, exploring how neural networks can improve exoskeleton robot assisted rehabilitation for individuals with impaired upper limbs. By categorizing the studies based on robot assisted joints, sensor systems, and control methodologies, we offer a comprehensive overview of neural network applications in this field. Our findings demonstrate that neural networks, such as Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and Radial Basis Function Neural Networks (RBFNN), and other forms of neural network significantly contribute to patient specific rehabilitation by enabling adaptive learning and personalized therapy. CNNs improve motion intention estimation and control accuracy, while LSTM networks capture temporal muscle activity patterns for real-time rehabilitation. RBFNNs improve human-robot interaction by adapting to individual movement patterns, leading to more personalized and efficient therapy. This review highlights the potential of neural networks to revolutionize upper limb rehabilitation, improving motor recovery and patient outcomes in both clinical and home-based settings. It also recommends the future direction to customize existing neural networks for robot assisted rehabilitation applications.","url":"https://doi.org/10.20944/preprints202411.0183.v1","authors":["Sk Hasan","Nafizul Alam","Gazi Abdullah Mashud","Subodh Bhujel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-05T19:52:06Z","doi":"10.20944/preprints202411.0183.v1","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1002/cjce.25556/v1/review2","name":"Review for \"Development of a deep neural network and empirical model for predicting local gas holdup profiles in bubble columns\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/cjce.25556/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-22T01:07:19Z","doi":"10.1002/cjce.25556/v1/review2","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1017/qpb.2024.2.pr11","name":"Author comment: Quantitative analysis of lateral root development with time-lapse imaging and deep neural network — R2/PR11","source":"crossref","abstract":"","url":"https://doi.org/10.1017/qpb.2024.2.pr11","authors":["Hironaka Tsukagoshi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-13T03:07:40Z","doi":"10.1017/qpb.2024.2.pr11","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1109/nnice61279.2024.10499022","name":"Analysis of logistics cargo turnover prediction based on artificial neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nnice61279.2024.10499022","authors":["Yanfang Pan","Huan Xiong","Shiyu Wang","Benxiao Lou","Bote Liu","Jianqiu Chen","Guobin Gu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-22T17:33:49Z","doi":"10.1109/nnice61279.2024.10499022","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1016/j.jfranklin.2023.11.037","name":"Generalized state estimation criteria for additive delayed memristor neural networks including leakage delay effect-flux-charge domain applications in energy storage systems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.jfranklin.2023.11.037","authors":["R. Manivannan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-08T02:31:37Z","doi":"10.1016/j.jfranklin.2023.11.037","addedAt":"2026-09-01T01:48:33.260Z","updatedAt":"2026-09-01T01:48:33.260Z"},{"id":"doi:10.1145/3662739.3670225","name":"Short-term Traffic Flow Prediction Based on Improved BP Neural Network Optimized by Grasshopper Optimization Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3662739.3670225","authors":["Dong Luo","Xiaoxue Guo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-03T10:41:34Z","doi":"10.1145/3662739.3670225","addedAt":"2026-09-01T01:48:33.261Z","updatedAt":"2026-09-01T01:48:33.261Z"},{"id":"doi:10.21203/rs.3.rs-4741063/v1","name":"Segmentation of Breast Cancer Masses in Mammography Images Using Deep Convolutional Neural Network (DCNN)","source":"crossref","abstract":"Abstract Mammography is one of the most important and effective ways to detect breast cancer, especially in the early stages of the disease. However, due to the complexity of breast tissue, the similarity between cancerous masses and natural tissues, the different sizes and shapes of masses, and the use of low-density X-ray radiation, mammogram images often have poor quality. Therefore, detecting lesions, especially in the early stages, is a challenging task. In this study, we address the improvement of breast cancer mass segmentation in mammography images. Accurate mass segmentation on mammograms is an important step in computer-aided diagnosis systems, which is also a challenging task because some mass lesions are embedded in natural tissues and have weak or ambiguous margins. The proposed method in this study presents an improved algorithm for segmenting cancerous masses in mammography images using a Deep Convolutional Neural Network (DCNN), which ultimately leads to mass classification into benign and malignant classes. Deep convolutional neural networks extract high-level concepts from low-level features, and are appropriate for handling large volumes of data. In fact, in deep learning, high-level concepts are defined by low-level features. Segmentation based on the proposed method with preprocessed images achieves more accurate delineation in high-resolution images, and ultimately improves the accuracy and sensitivity of mass tissue separation in the breast. In this study, we used three different architectures for deep convolutional neural networks. The proposed DCNNs were validated on mammography images of INbreast dataset. The reliability of the system's performance is ensured by applying 5-fold cross-validation. The proposed method has been evaluated based on accuracy, precision, sensitivity, and ROC criteria. The results obtained with an accuracy of 97.76% for the third proposed deep model indicate an improvement in the accuracy of the diagnosis as well as a reduction in the cost of the diagnostic process. Results showed that our proposed algorithm is significantly more accurate than other methods due to its deep and hierarchical extraction.","url":"https://doi.org/10.21203/rs.3.rs-4741063/v1","authors":["Farnaz Hoseini","Abbas Mirzaei"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-08T06:23:14Z","doi":"10.21203/rs.3.rs-4741063/v1","addedAt":"2026-09-01T01:48:33.261Z","updatedAt":"2026-09-01T01:48:33.261Z"},{"id":"doi:10.2139/ssrn.5012233","name":"Reliability-Based Design Optimization (Rbdo) Framework for High-Energy Laser Weapons (Helws) Using Artificial Neural Network Ensemble","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5012233","authors":["Ungki Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-06T19:39:06Z","doi":"10.2139/ssrn.5012233","addedAt":"2026-09-01T01:48:33.261Z","updatedAt":"2026-09-01T01:48:33.261Z"},{"id":"doi:10.1101/2024.04.02.587669","name":"Recurrent issues with deep neural network models of visual recognition","source":"crossref","abstract":"Abstract Object recognition requires flexible and robust information processing, especially in view of the challenges posed by naturalistic visual settings. The ventral stream in visual cortex is provided with this robustness by its recurrent connectivity. Recurrent deep neural networks (DNNs) have recently emerged as promising models of the ventral stream, surpassing feedforward DNNs in the ability to account for brain representations. In this study, we asked whether recurrent DNNs could also better account for human behaviour during visual recognition. We assembled a stimulus set that included manipulations that are often associated with recurrent processing in the literature, like occlusion, partial viewing, clutter, and spatial phase scrambling. We obtained a benchmark dataset from human participants performing a categorisation task on this stimulus set. By applying a wide range of model architectures to the same task, we uncovered a nuanced relationship between recurrence, model size, and performance. While recurrent models reach higher performance than their feedforward counterpart, we could not dissociate this improvement from that obtained by increasing model size. We found consistency between humans and models patterns of difficulty across the visual manipulations, but this was not modulated in an obvious way by the specific type of recurrence or size added to the model. Finally, depth/size rather than recurrence makes model confusion patterns more human-like. Contrary to previous assumptions, our findings challenge the notion that recurrent models are better models of human recognition behaviour than feedforward models, and emphasise the complexity of incorporating recurrence into computational models.","url":"https://doi.org/10.1101/2024.04.02.587669","authors":["Tim Maniquet","Hans Op de Beeck","Andrea Ivan Costantino"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-02T07:40:11Z","doi":"10.1101/2024.04.02.587669","addedAt":"2026-09-01T01:48:33.261Z","updatedAt":"2026-09-01T01:48:33.261Z"},{"id":"doi:10.22541/au.172114776.66144810/v1","name":"Machine tool operating vibration prediction based on multi-sensor fusion and LSTM neural network","source":"crossref","abstract":"In this study, a machine tool operating vibration prediction method based on multi-sensor fusion and long short-term memory (LSTM) network is proposed. Machine tool vibration has a significant impact on machining quality, workpiece surface roughness, dimensional accuracy, and tool’s wear. This study combines deep learning technology with industrial applications to achieve high-precision machine tool vibration prediction by fusing multiple sensor data. The real-time data is input into the LSTM model to predict the vibration situation at the next moment. The experimental results show that the method has strong prediction ability for the periodic vibration of the machine tool and the vibration error specific to the machining action. And it can effectively predict machine vibration and improve machining accuracy.","url":"https://doi.org/10.22541/au.172114776.66144810/v1","authors":["Zhonglou Shi","jinjie duan","faquan li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-16T12:36:12Z","doi":"10.22541/au.172114776.66144810/v1","addedAt":"2026-09-01T01:48:33.261Z","updatedAt":"2026-09-01T01:48:33.261Z"},{"id":"doi:10.1007/s00521-024-10347-3","name":"IRAM–NET model: image residual agnostics meta-learning-based network for rare de novo glioblastoma diagnosis","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-024-10347-3","authors":["Kuljeet Singh","Deepti Malhotra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-28T19:02:09Z","doi":"10.1007/s00521-024-10347-3","addedAt":"2026-09-01T01:48:33.261Z","updatedAt":"2026-09-01T01:48:33.261Z"},{"id":"doi:10.1109/icceic64099.2024.10775821","name":"Multi-Scale Convolutional Neural Network Based Ear- Electroencephalograph Identity Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icceic64099.2024.10775821","authors":["Rongze Han"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-11T22:21:58Z","doi":"10.1109/icceic64099.2024.10775821","addedAt":"2026-09-01T01:48:33.261Z","updatedAt":"2026-09-01T01:48:33.261Z"},{"id":"doi:10.1016/j.displa.2024.102860","name":"Multi-scale attention in attention neural network for single image deblurring","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.displa.2024.102860","authors":["Ho Sub Lee","Sung In Cho"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-19T20:11:53Z","doi":"10.1016/j.displa.2024.102860","addedAt":"2026-09-01T01:48:33.261Z","updatedAt":"2026-09-01T01:48:33.261Z"},{"id":"doi:10.1007/s11071-024-10203-y","name":"Odor pattern recognition of olfactory neural network based on neural energy","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11071-024-10203-y","authors":["Zhen Wang","Ning Liu","Rubin Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T20:24:35Z","doi":"10.1007/s11071-024-10203-y","addedAt":"2026-09-01T01:48:33.261Z","updatedAt":"2026-09-01T01:48:33.261Z"},{"id":"doi:10.1039/d4sc07858f/v1/review1","name":"Review for \"IMPRESSION Generation 2 – Accurate, fast and generalised neural network model for predicting NMR parameters in place of DFT\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d4sc07858f/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-31T17:20:23Z","doi":"10.1039/d4sc07858f/v1/review1","addedAt":"2026-09-01T01:48:33.261Z","updatedAt":"2026-09-01T01:48:33.261Z"},{"id":"doi:10.21577/0100-4042.20230127","name":"STRUCTURAL OPTIMIZATION OF JET PUMP BASED ON BP NEURAL NETWORK","source":"crossref","abstract":"With the increasing drilling depth, problems follow, such as the lifting height of the liquid in the well and increased pump operation. Therefore, improving the production efficiency of deep wells is a hot spot in the current oil drilling and production industry. This paper designs a new jet pump that can be mined for high and low-pressure oil layers according to the oil wells’ inter-layer contradiction. The FLUENT software is used to simulate the new jet pump, analyze the pump efficiency factors of the jet pump and the physical properties of the fluid, and the BP neural network is used to optimize the structure of the jet pump. The results show that the maximum pump efficiency of spout distance, duct diameter, duct distance, and spread angle is 2.61-5.22 mm, 6.393-8 mm, 42.5-53.2 mm, and 6-9°, respectively. The best spout distance, duct diameter, duct distance, and spread angle are 2.74 mm, 6.80 mm, 46.5 mm, and 7.4°after being optimized by the BP neural network model presented in this paper and the optimized pump efficiency is improved by 9.45%.","url":"https://doi.org/10.21577/0100-4042.20230127","authors":["Bo Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-16T17:09:09Z","doi":"10.21577/0100-4042.20230127","addedAt":"2026-09-01T01:48:33.261Z","updatedAt":"2026-09-01T01:48:33.261Z"},{"id":"doi:10.21203/rs.3.rs-4618247/v1","name":"Multi-path Hybrid Attention Deep Neural Network for Valve Detection","source":"crossref","abstract":"Abstract Valves Detection is a basic function of rescue robots in various disaster situations. However, due to the small differences between similar valves, rescue robots suffer great challenges in valve detection in complex environments. To address this challenge, this paper proposes a multi-path hybrid attention deep neural network (MHADNN). By weighting features at different scales and spatial positions, the MHADNN can help valve detection models focus on more discriminative subtle features, thereby enhancing the ability to distinguish similar valves. This paper combines the MHADNN with the YOLOv5n to develop a valve detection model. The comparative experiments are conducted on a similar valve dataset collected in the simulated environment of a chemical industrial park. The experimental results show that compared with YOLOv5n, the proposed valve detection model has an average precision improvement of 4.20%. It has excellent performance in distinguishing similar valves.","url":"https://doi.org/10.21203/rs.3.rs-4618247/v1","authors":["First Xuefeng Zhang","Second Yonghe Huang","Xiwen Qu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-12T10:36:57Z","doi":"10.21203/rs.3.rs-4618247/v1","addedAt":"2026-09-01T01:48:33.261Z","updatedAt":"2026-09-01T01:48:33.261Z"},{"id":"doi:10.2139/ssrn.4813564","name":"Medical Image Synthesis Algorithm Based on Vision Graph Neural Network with Manifold Matching","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4813564","authors":["Xianhua Zeng","bowen lu","jian zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-01T13:20:57Z","doi":"10.2139/ssrn.4813564","addedAt":"2026-09-01T01:48:33.261Z","updatedAt":"2026-09-01T01:48:33.261Z"},{"id":"doi:10.21203/rs.3.rs-3824277/v1","name":"CryoNeFEN: High-resolution reconstruction of cryo-EM structures using neural field network","source":"crossref","abstract":"Abstract The elucidation of three-dimensional (3D) structures is crucial to unraveling protein function and illuminating mechanisms in structural biology. Cryogenic electron microscopy (cryo-EM) single-particle analysis provides direct measurements to determine the structures of macromolecules. However, the main challenge is reconstructing high-resolution 3D structures from extremely noisy and randomly oriented 2D projection images. Most existing methods primarily involve the optimization of multiple 2D slices in the Fourier domain but ignore the anisotropy among these slices, thus limiting the reconstruction of high-frequency structures. In this paper, we propose a cryo-EM neural field reconstruction network (cryoNeFEN), a new 3D spatial domain optimization paradigm, that learns a directional isotropic representation of the cryo-EM structure by mapping spatial coordinates to corresponding density values. We qualitatively and quantitatively evaluate cryoNeFEN on four experimental datasets. The results demonstrate the improved directional isotropy and 3D density resolution beyond the limits of existing algorithms in homogeneous reconstruction and resolve the missing elements of SARS-CoV-2 distinctly in heterogeneous reconstruction.","url":"https://doi.org/10.21203/rs.3.rs-3824277/v1","authors":["Manhua Liu","Yue Huang","Zhu Chengguang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-17T06:48:17Z","doi":"10.21203/rs.3.rs-3824277/v1","addedAt":"2026-09-01T01:48:33.261Z","updatedAt":"2026-09-01T01:48:33.261Z"},{"id":"doi:10.36227/techrxiv.171197744.44687303/v1","name":"SegNet: A Segmented Deep Learning based Convolutional Neural Network Approach for Drones Wildfire Detection","source":"crossref","abstract":"This research addresses the pressing challenge of enhancing processing times and detection capabilities in Unmanned Aerial Vehicle (UAV)/drone imagery for global wildfire detection, despite limited datasets. Proposing a Segmented Neural Network (SegNet) selection approach, we focus on reducing feature maps to boost both time resolution and accuracy significantly advancing processing speeds and accuracy in real-time wildfire detection. This paper contributes to increased processing speeds enabling real-time detection capabilities for wildfire, increased detection accuracy of wildfire, and improved detection capabilities of early wildfire, through proposing a new direction for image classification of amorphous objects like fire, water, smoke, etc. Employing Convolutional Neural Networks (CNNs) for image classification, emphasizing on the reduction of irrelevant features vital for deep learning processes, especially in live feed data for fire detection. Amidst the complexity of live feed data in fire detection, our study emphasizes on image feed, highlighting the urgency to enhance real-time processing. Our proposed algorithm combats feature overload through segmentation, addressing challenges arising from diverse features like objects, colors, and textures. Notably, a delicate balance of feature map size and dataset adequacy is pivotal. Several research papers use smaller image sizes, compromising feature richness which necessitating a new approach. We illuminate the critical role of pixel density in retaining essential details, especially for early wildfire detection. By carefully selecting number of filters during training, we underscore the significance of higher pixel density for proper feature selection. The proposed SegNet approach is rigorously evaluated using real-world dataset obtained by a drone flight and compared to state-of-the-art literature.","url":"https://doi.org/10.36227/techrxiv.171197744.44687303/v1","authors":["Aditya V Jonnalagadda","Hashim A. Hashim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-01T09:17:32Z","doi":"10.36227/techrxiv.171197744.44687303/v1","addedAt":"2026-09-01T01:48:33.261Z","updatedAt":"2026-09-01T01:48:33.261Z"},{"id":"doi:10.7753/ijcatr1308.1011","name":"The Performance of Convolutional Neural Network Architecture in Classification","source":"crossref","abstract":"","url":"https://doi.org/10.7753/ijcatr1308.1011","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-08T08:41:29Z","doi":"10.7753/ijcatr1308.1011","addedAt":"2026-09-01T01:48:33.261Z","updatedAt":"2026-09-01T01:48:33.261Z"},{"id":"doi:10.2139/ssrn.4866148","name":"Ensemble Rnn Deep Neural Network Methods for Time Series Forecasting Electrical Power Systems","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4866148","authors":["hendri dwiputra","Busono Soerowirdjo","Rudi Irawan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-15T02:19:02Z","doi":"10.2139/ssrn.4866148","addedAt":"2026-09-01T01:48:33.261Z","updatedAt":"2026-09-01T01:48:33.261Z"},{"id":"doi:10.2139/ssrn.4796545","name":"Predicting Energy Budgets in Droplet Dynamics: A Recurrent Neural Network Approach","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4796545","authors":["Diego de Aguiar","Hugo França","Cassio  Machiaveli Oishi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-16T17:18:13Z","doi":"10.2139/ssrn.4796545","addedAt":"2026-09-01T01:48:33.261Z","updatedAt":"2026-09-01T01:48:33.261Z"},{"id":"doi:10.1007/978-3-031-66051-1_13","name":"A Metaheuristic-Based Artificial Neural Network for Plastic Limit Analysis of Frames","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-66051-1_13","authors":["Ali Kaveh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-29T06:01:41Z","doi":"10.1007/978-3-031-66051-1_13","addedAt":"2026-09-01T01:48:33.261Z","updatedAt":"2026-09-01T01:48:33.261Z"},{"id":"doi:10.2139/ssrn.4756204","name":"Uncertainty-Aware Hand Gesture Recognition Based on Fmcw Mimo Radar and Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4756204","authors":["The Tuan Trinh","Minhhuy Le"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-12T07:22:05Z","doi":"10.2139/ssrn.4756204","addedAt":"2026-09-01T01:48:33.261Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.2139/ssrn.4869583","name":"Learning Path Recommendation Based on Deep Learning Based Vector Spacing Word Net Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4869583","authors":["Bhuvana Raja","Arun Prasad V"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-18T15:47:46Z","doi":"10.2139/ssrn.4869583","addedAt":"2026-09-01T01:48:33.261Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.2139/ssrn.4809865","name":"Study on Rop Prediction Based on Improved BP Neural Network Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4809865","authors":["Li Meng","xin liu","Xinyue Wang","Qingsong Wei"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-27T18:18:24Z","doi":"10.2139/ssrn.4809865","addedAt":"2026-09-01T01:48:33.261Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1016/0893-6080(88)90329-2","name":"Phonetic discrimination experiments with a spatiotemporal recognition network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90329-2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T05:05:53Z","doi":"10.1016/0893-6080(88)90329-2","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1007/978-94-009-0643-3_105","name":"LEP — A Neural Model learning Reliably","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-94-009-0643-3_105","authors":["Jian- Kang Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-12-08T22:06:39Z","doi":"10.1007/978-94-009-0643-3_105","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.1989.118402","name":"A virtual network for reorganizable neural architectures","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.1989.118402","authors":["Wong","Lursinsap"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-01-13T13:46:33Z","doi":"10.1109/ijcnn.1989.118402","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.1989.118356","name":"A neural network for 3-satisfiability problems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.1989.118356","authors":["Chen","Hsieh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-01-13T18:46:33Z","doi":"10.1109/ijcnn.1989.118356","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1007/s13042-014-0257-x","name":"State estimation for memristor-based neural networks with time-varying delays","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s13042-014-0257-x","authors":["Hongzhi Wei","Ruoxia Li","Chunrong Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-05-03T08:58:02Z","doi":"10.1007/s13042-014-0257-x","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1016/j.neucom.2015.08.088","name":"Impulsive controller design for exponential synchronization of delayed stochastic memristor-based recurrent neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2015.08.088","authors":["A. Chandrasekar","R. Rakkiyappan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-09-11T17:41:55Z","doi":"10.1016/j.neucom.2015.08.088","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1007/s40435-018-0435-x","name":"A plethora of behaviors in a memristor based Hopfield neural networks (HNNs)","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s40435-018-0435-x","authors":["Z. T. Njitacke","J. Kengne","H. B. Fotsin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-05-03T04:49:08Z","doi":"10.1007/s40435-018-0435-x","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.38007/nn.2026.050106","name":"Research on Early Warning Model of Credit Risk Transmission of Enterprise Group Based on Graph Neural Network and Knowledge Graph","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2026.050106","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-25T08:46:27Z","doi":"10.38007/nn.2026.050106","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1063/5.0211178","name":"Effect of neural firing pattern on NbOx/Al2O3 memristor-based reservoir computing system","source":"crossref","abstract":"The implementation of reservoir computing using resistive random-access memory as a physical reservoir has attracted attention due to its low training cost and high energy efficiency during parallel data processing. In this work, a NbOx/Al2O3-based memristor device was fabricated through a sputter and atomic layer deposition process to realize reservoir computing. The proposed device exhibits favorable resistive switching properties (&amp;gt;103 cycle endurance) and demonstrates short-term memory characteristics with current decay. Utilizing the controllability of the resistance state and its variability during cycle repetition, electrical pulses are applied to investigate the synapse-emulating properties of the device. The results showcase the functions of potentiation and depression, the coexistence of short-term and long-term plasticity, excitatory post-synaptic current, and spike-rate dependent plasticity. Building upon the functionalities of an artificial synapse, pulse spikes are categorized into three distinct neural firing patterns (normal, adapt, and boost) to implement 4-bit reservoir computing, enabling a significant distinction between “0” and “1.”","url":"https://doi.org/10.1063/5.0211178","authors":["Dongyeol Ju","Hyeonseung Ji","Jungwoo Lee","Sungjun Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-23T15:52:57Z","doi":"10.1063/5.0211178","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1016/j.mee.2024.112201","name":"Neural networks based on in-sensor computing of optoelectronic memristor","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.mee.2024.112201","authors":["Zhang Zhang","Qifan Wang","Gang Shi","Yongbo Ma","Jianmin Zeng","Gang Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-08T16:17:33Z","doi":"10.1016/j.mee.2024.112201","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/aicas59952.2024.10595913","name":"The Ouroboros of Memristors: Neural Networks Facilitating Memristor Programming","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aicas59952.2024.10595913","authors":["Zhenming Yu","Ming-Jay Yang","Jan Finkbeiner","Sebastian Siegel","John Paul Strachan","Emre Neftci"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-19T13:30:48Z","doi":"10.1109/aicas59952.2024.10595913","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.1989.118707","name":"Neural network algorithms for motion stereo","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.1989.118707","authors":["Zhou","Chellappa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-01-13T13:46:33Z","doi":"10.1109/ijcnn.1989.118707","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1016/0893-6080(88)90168-2","name":"Unsupervised learning in the N-dimensional Coulomb network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90168-2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T05:05:53Z","doi":"10.1016/0893-6080(88)90168-2","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.2003.1223378","name":"The H1 neural network trigger","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2003.1223378","authors":["C. Kiesling"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2004-03-02T02:26:50Z","doi":"10.1109/ijcnn.2003.1223378","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1016/0893-6080(95)00110-7","name":"Network generalization differences quantified","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(95)00110-7","authors":["Derek Partridge"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-25T12:59:42Z","doi":"10.1016/0893-6080(95)00110-7","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1016/s0893-6080(98)00057-4","name":"The extended piecewise quadratic neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/s0893-6080(98)00057-4","authors":["David M. Weber","David P. Casasent"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-25T22:54:47Z","doi":"10.1016/s0893-6080(98)00057-4","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1016/0893-6080(91)90062-a","name":"DEFAnet—A deterministic neural network concept for function approximation","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(91)90062-a","authors":["Wolfgang J. Daunicht"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T01:05:53Z","doi":"10.1016/0893-6080(91)90062-a","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1088/0954-898x_4_4_006","name":"Informational characteristics of neural networks capable of associative learning based on Hebbian plasticity","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_4_4_006","authors":["A A Frolov","I P Murav'ev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:23Z","doi":"10.1088/0954-898x_4_4_006","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/icieam57311.2023.10139237","name":"Automated Generation of SPICE Models of Memristor-Based Neural Networks from Python Models","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icieam57311.2023.10139237","authors":["Daniil Nikishov","Alexander Antonov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-05T17:43:26Z","doi":"10.1109/icieam57311.2023.10139237","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1088/0954-898x/7/3/005","name":"Divergence measures based on entropy families: a tool for guiding the growth of neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/7/3/005","authors":["H Andree","A Lodder","A Taal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/7/3/005","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1088/0954-898x_4_3_009","name":"The Patch algorithm: fast design of binary feedforward neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_4_3_009","authors":["G T Barkema","H M A Andree","A Taal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:17Z","doi":"10.1088/0954-898x_4_3_009","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1016/j.neunet.2012.04.004","name":"Advancing interconnect density for spiking neural network hardware implementations using traffic-aware adaptive network-on-chip routers","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2012.04.004","authors":["Snaider Carrillo","Jim Harkin","Liam McDaid","Sandeep Pande","Seamus Cawley","Brian McGinley","Fearghal Morgan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-04-23T23:10:49Z","doi":"10.1016/j.neunet.2012.04.004","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.7717/peerjcs.2276/fig-9","name":"Figure 9: Evaluation metrics for artificial neural network (DNN-EdgeIIoTset).","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerjcs.2276/fig-9","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-28T01:48:06Z","doi":"10.7717/peerjcs.2276/fig-9","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.7554/elife.28932.023","name":"Source code 3. qPCR 7-miRNA neural network source code.","source":"crossref","abstract":"","url":"https://doi.org/10.7554/elife.28932.023","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-11-03T11:01:58Z","doi":"10.7554/elife.28932.023","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.58837/chula.the.2022.88","name":"Leverage graph neural network for molecular properties prediction","source":"crossref","abstract":"During the age of deep learning technologies, which have exhibited significant potential in reducing costs and expediting medical development, predicting molecular properties has become a prevalent task that capitalizes on the capabilities of deep learning. This thesis proposed a multimodal Graph Neural Network (GNN) model that utilizes the topology information obtained from molecular graphs through a baseline GNN, facilitating precise property predictions. The thesis improves the baseline CMPNN model by exploring various methods to address potential missing gaps. These methods include incorporating the multimodal module, such as a Bidirectional LSTM module capable of processing text sequences in SMILES format or a spectral graph convolution module. Moreover, self-attention integration into the CMPNN model was implemented using the alpha coefficient method from GATConv. The experimental results show that the proposed multimodal GNN models performed better than the baseline model for predicting molecular properties in seven out of eight datasets from MoleculeNet, including five classification and three regression tasks. These findings show the potential of this methodology across various domains within the field of chemistry, with particular relevance to drug discovery.","url":"https://doi.org/10.58837/chula.the.2022.88","authors":["Kamol Punnachaiya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-15T06:01:19Z","doi":"10.58837/chula.the.2022.88","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.17816/dd108982-72900","name":"Fig. 2. Images (a, b) generated by the neural network.","source":"crossref","abstract":"","url":"https://doi.org/10.17816/dd108982-72900","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-17T06:41:35Z","doi":"10.17816/dd108982-72900","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.7717/peerj-cs.3541/fig-10","name":"Figure 10: (A) Neural network training phase (B) Validation epochs.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.3541/fig-10","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-27T08:54:27Z","doi":"10.7717/peerj-cs.3541/fig-10","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.7717/peerj-cs.1140/fig-2","name":"Figure 2: Framework of the proposed dual branch neural network.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.1140/fig-2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-14T03:16:13Z","doi":"10.7717/peerj-cs.1140/fig-2","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1049/pbce053e_fm","name":"Front Matter","source":"crossref","abstract":"","url":"https://doi.org/10.1049/pbce053e_fm","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-10-06T10:14:16Z","doi":"10.1049/pbce053e_fm","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.70675/51cf5234z10f7z42b2z8d46z13894170c780","name":"Low-rank network models of neural computations","source":"crossref","abstract":"Réseaux de neurones de bas rang et calculs neuronaux À tout instant, des myriades de neurones coopèrent au sein d’un système nerveux, produisant des motifs d’activité collectifs qui forment un substrat biologique pour la perception, la cognition, et le comportement. Les enregistrements in vivo de centaines voire milliers de neurones chez l’animal suggèrent que ces motifs d’activité s’organisent souvent selon des géométries particulières, dites à basse dimensionnalité, à partir desquelles les représentations mentales peuvent être extraites. Ainsi, un paradigme actuel influent en neurosciences postule que les fonctions cognitives émergent à partir des dynamiques de réseaux de neurones dont l’activité forme des motifs de basse dimensionnalité. Une question essentielle qui demeure est de comprendre comment la structure d’un réseau neuronal génère ces dynamiques particulières de l’activité collective liées à sa fonction. Une voie prometteuse pour éclairer cette question consiste à étudier des réseaux récurrents dont les connexions sont organisées dans une matrice de bas-rang. Il a été montré précédemment que cette propriété mathématique du réseau y induit naturellement des dynamiques de basse dimensionnalité qui encodent des représentations utiles, telles qu’observées dans les expériences sur réseaux biologiques et artificiels. De tels réseaux de bas-rang peuvent-ils alors nous permettre d’ouvrir la « boîte noire » des réseaux récurrents, et de comprendre comment leur fonctionnalité émerge de leur structure ? Et peuvent-ils s’appliquer à des enregistrements de neurones biologiques, afin d’en extraire des hypothèses sur la structure sous-jacente des réseaux observés ? Cette thèse vise à répondre à ces questions, à travers de nouvelles méthodes pour entraîner les réseaux de bas-rang, ainsi qu’à travers une nouvelle théorie qui relie une description statistique de ces réseaux à leurs dynamiques et leur fonction. Nous allons dans un premier temps exposer notre théorie et nos méthodes, expliquant comment les matrices de bas-rang nous permettent de relier structure et fonction dans un réseau récurrent. Nous allons ensuite étudier des réseaux entraînés à réaliser de nombreuses tâches cognitives, construisant une compréhension systémique de leur fonctionnement. Ces réseaux de bas-rang seront ensuite reliés à une classe de méthodes statistiques communes dans l’interprétation d’enregistrements neuronaux, les systèmes dynamiques latents. Pour terminer, nous démontrerons les capacités des réseaux de bas-rang pour disséquer le fonctionnement de réseaux artificiels récurrents non-contraints, ainsi que pour interpréter des enregistrements corticaux in vivo.","url":"https://doi.org/10.70675/51cf5234z10f7z42b2z8d46z13894170c780","authors":["Adrian Valente"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-07T08:08:14Z","doi":"10.70675/51cf5234z10f7z42b2z8d46z13894170c780","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/icnn.1993.298592","name":"A neural network model for real-time adaptive clustering","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnn.1993.298592","authors":["L. Fu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-12-30T22:49:31Z","doi":"10.1109/icnn.1993.298592","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1016/b978-0-12-741251-1.50032-1","name":"A Neural Network for Motion Processing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-12-741251-1.50032-1","authors":["Y.T. ZHOU","R. CHELLAPPA"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-01T11:42:25Z","doi":"10.1016/b978-0-12-741251-1.50032-1","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1142/9789812796851_0009","name":"The Modified Probabilistic Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1142/9789812796851_0009","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-07-18T16:55:18Z","doi":"10.1142/9789812796851_0009","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1201/9780203024119-16","name":"A Neural Network Approach to Rainfall Forecasting in Urban Environments","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9780203024119-16","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-06T08:48:56Z","doi":"10.1201/9780203024119-16","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.2003.1223981","name":"Neural network models for vision","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2003.1223981","authors":["K. Fukushima"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2004-06-22T16:27:43Z","doi":"10.1109/ijcnn.2003.1223981","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.1989.118392","name":"Convergence properties of a pulsed neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.1989.118392","authors":["Mian","Cotter"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-01-13T13:46:33Z","doi":"10.1109/ijcnn.1989.118392","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.14311/nnw.2023.33.024","name":"Upgrading the JANET neural network by introducing a new storage buffer of working memory","source":"crossref","abstract":"Recurrent neural networks (RNNs), along with long short-term memory networks (LSTMs), have been successfully used on a wide range of sequential data problems and have been entitled as extraordinarily powerful tools for learning and processing such data. However, the search for a new or derived architecture that would model very long-term dependencies is still an active area of research. In this paper, a relatively psychologically plausible architecture named event buffering JANET (EB-JANET) is proposed. The architecture is derived from the forgetgate- only version of the LSTM, which is also called just another network (JANET). The new architecture implements a new working memory mechanism that operates on information represented as dynamic events. The event buffer, as a container of events, is a reference to the state of the relevant pre-activation values on the basis of which historical candidate values were generated relative to the current timestep. The buffer is emptied as needed and depending on the context of information. The proposed architecture has achieved world-class results and it outperforms JANET on multiple benchmark datasets. Moreover, the new architecture is applicable to a wider class of problems and showed superior resilience when processing longer sequences, as opposed to JANET which experienced catastrophic failures on certain tasks.","url":"https://doi.org/10.14311/nnw.2023.33.024","authors":["Antonio Tolic","Biljana Mileva Boshkoska","Sandro Skansi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-27T07:58:30Z","doi":"10.14311/nnw.2023.33.024","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1088/0954-898x_5_2_002","name":"Designing receptive fields for highest fidelity","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_5_2_002","authors":["Daniel L Ruderman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:15Z","doi":"10.1088/0954-898x_5_2_002","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.37200/ijpr/v24i5/pr201929","name":"Detection of Pathological Myopia Using Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.37200/ijpr/v24i5/pr201929","authors":["Ananth Kalyanasundaram"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-04-28T14:58:51Z","doi":"10.37200/ijpr/v24i5/pr201929","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/72.788658","name":"Neural-network prediction with noisy predictors","source":"crossref","abstract":"","url":"https://doi.org/10.1109/72.788658","authors":["A.A. Ding"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-24T19:16:32Z","doi":"10.1109/72.788658","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1201/9781420015454-9","name":"System Identification Using Discrete-Time Neural Networks","source":"crossref","abstract":"System identification is the process of determining a dynamic model for an unknown system that can subsequently be used for feedback control purposes. On the other hand, state estimation involves determining the unknown internal states of a dynamic system. System identification provides one technique for estimating the states. The area of system identification has received significant attention over the past decades and now it is a fairly mature field with many powerful methods available at the disposal of control engineers. Online system identification methods to date are based on recursive methods such as least squares, for most systems that are expressed as linear in the parameters (LIP). To overcome this LIP assumption, neural networks (NNs) are now employed for system identification since these networks learn complex mappings from a set of examples. As seen in the previous chapters, due to NN approximation properties (Cybenko 1989) as well as the inherent adaptation features of these networks, NN present a potentially appealing alternative to modeling of nonlinear systems. Moreover, from a practical perspective, the massive parallelism and fast adaptability of NN implementations provide additional incentives for further investigation.","url":"https://doi.org/10.1201/9781420015454-9","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-02T00:22:01Z","doi":"10.1201/9781420015454-9","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.31979/etd.wum7-btdc","name":"Nitrogenase Iron Protein Classification using CNN Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.31979/etd.wum7-btdc","authors":["Amer Rez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-01-11T00:31:47Z","doi":"10.31979/etd.wum7-btdc","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.36227/techrxiv.176826845.56179350/v1","name":"NEUROEVOLUTION: A NEURAL NETWORK-ORIENTED OPTIMIZATION APPROACH","source":"crossref","abstract":"NeuroEvolution refers to the use of evolutionary algorithms to optimize neural network parameters and, in some cases, network architectures. The provided document outlines the fundamental components of evolutionary computation when applied to neural networks, including chromosome representation, population initialization, fitness evaluation, selection, crossover, mutation, replacement, and termination criteria. These processes collectively enable a population of neural-network-based solutions to evolve over time toward better performance on a given task. Additionally, the document highlights the role of population diversity and discusses how mechanisms such as elitism and diversity monitoring help avoid premature convergence. This work summarizes these concepts and bases a methodological framework on the principles presented.","url":"https://doi.org/10.36227/techrxiv.176826845.56179350/v1","authors":["Kishu Gupta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-13T01:41:02Z","doi":"10.36227/techrxiv.176826845.56179350/v1","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1080/0954898x.2024.2448534","name":"New delay-dependent uniform stability criteria for fractional-order BAM neural networks with discrete and distributed delays","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2024.2448534","authors":["Shafiya Muthu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-26T10:27:47Z","doi":"10.1080/0954898x.2024.2448534","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/neurel.2010.5644086","name":"Improved neural network for checking the stability of multidimensional systems","source":"crossref","abstract":"In this paper, the author's previous work is extended and a new neural network is utilized to solve the stability problem of multidimensional systems. In the original authors work the problem is transformed into an optimization problem. Using the DeCarlo-Strintzis Theorem one has to check if |B(Z1,..., 1, Zm)| ≠ 0 for |Z1| = ... = |Zm| = 1 or equivalently if the min |B(Z1, ..., 1, Zm)| is 0 or not, where B(Z1, Z2, ..., Zm) is the denominator of the discrete transfer funcion. Then, the problem is reduced to a minimization problem and a neural network is proposed for solving it. To improve the chance of convergence towards the global minimum, an extension of this neural network based on random noise terms is proposed in this contribution. The numerical examples illustrate the validity and the efficiency of the new neural network.","url":"https://doi.org/10.1109/neurel.2010.5644086","authors":["Nikos E. Mastorakis","Valeri M. Mladenov","M. N. S. Swamy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-12-09T10:34:50Z","doi":"10.1109/neurel.2010.5644086","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1088/0954-898x_3_4_003","name":"In defence of single-electrode recordings","source":"crossref","abstract":"As a physicist observing the empirical struggle of neurophysiology to penetrate the computational secrets of neo-cortex, one is struck by the coexistence of two extreme positions. One has it that the computations performed in neo-cortex are too complex to be approachable by single-electrode recordings. The other is continuously discovering single neurons which can perform such complex tasks as to recognize the individual faces of the senior staff in the laboratory.Drawing on experience gained in the study of condensed matter, I would like to reopen the discussion, pointing out that some of the single-electrode recordings which are exposing such remarkable computational features could not possibly be of great relevance for the description of 'higher brain function'. On the other hand, some single-electrode experiments, which detect rather mundane features of performance, display remarkable dynamical features, which must surely underlie cortical function.All this leads us to the conclusion that, though simultaneous electrode recordings may be required for the exposure of some complex neuro-cognitive effects, the field of single-electrode investigation is only beginning to benefit from the treasures it has always been exposing, and which are still going undervalued.","url":"https://doi.org/10.1088/0954-898x_3_4_003","authors":["Daniel J Amit"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:12Z","doi":"10.1088/0954-898x_3_4_003","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.14311/nnw.2017.27.015","name":"PREDICTING THE DAILY TRAFFIC VOLUME FROM HOURLY TRAFFIC DATA USING ARTIFICIAL NEURAL NETWORK","source":"crossref","abstract":"","url":"https://doi.org/10.14311/nnw.2017.27.015","authors":["Mohammed Saiful Alam Siddique","Shamsul Hoque"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-07-13T08:13:38Z","doi":"10.14311/nnw.2017.27.015","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1080/713663221","name":"A simple white noise analysis of neuronal light responses","source":"crossref","abstract":"A white noise technique is presented for estimating the response properties of spiking visual system neurons. The technique is simple, robust, efficient and well suited to simultaneous recordings from multiple neurons. It provides a complete and easily interpretable model of light responses even for neurons that display a common form of response nonlinearity that precludes classical linear systems analysis. A theoretical justification of the technique is presented that relies only on elementary linear algebra and statistics. Implementation is described with examples. The technique and the underlying model of neural responses are validated using recordings from retinal ganglion cells, and in principle are applicable to other neurons. Advantages and disadvantages of the technique relative to classical approaches are discussed.","url":"https://doi.org/10.1080/713663221","authors":["E. J. Chichilnisky"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-07-08T00:00:06Z","doi":"10.1080/713663221","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.31673/2409-7292.2026.023501","name":"Diagnostics of printed circuit boards based on neural network models","source":"crossref","abstract":"","url":"https://doi.org/10.31673/2409-7292.2026.023501","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-02T08:21:08Z","doi":"10.31673/2409-7292.2026.023501","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/isic.1997.626446","name":"Neural network integration in control system structures: a case study towards intelligent control by neural network integration","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isic.1997.626446","authors":["J. Zaprianov","T. Atanasova"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-11-23T00:49:27Z","doi":"10.1109/isic.1997.626446","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1088/0954-898x/15/2/004","name":"Localized activity patterns in excitatory neuronal networks","source":"crossref","abstract":"The existence of localized activity patterns, or bumps, has been investigated in a variety of spatially distributed neuronal network models that contain both excitatory and inhibitory coupling between cells. Here we show that a neuronal network with purely excitatory synaptic coupling can exhibit localized activity. Bump formation ensues from an initial transient synchrony of a localized group of cells, followed by the emergence of desynchronized activity within the group. Transient synchrony is shown to promote recruitment of cells into the bump, while desynchrony is shown to be good for curtailing recruitment and sustaining oscillations of those cells already within the bump. These arguments are based on the geometric structure of the phase space in which solutions of the model equations evolve. We explain why bump formation and bump size are very sensitive to initial conditions and changes in parameters in this type of purely excitatory network, and we examine how short-term synaptic depression influences the characteristics of bump formation.","url":"https://doi.org/10.1088/0954-898x/15/2/004","authors":["Jonathan Rubin","Amitabha Bose"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2004-05-05T03:14:19Z","doi":"10.1088/0954-898x/15/2/004","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1088/0954-898x_14_3_302","name":"Statistics of natural image categories","source":"crossref","abstract":"In this paper we study the statistical properties of natural images belonging to different categories and their relevance for scene and object categorization tasks. We discuss how second-order statistics are correlated with image categories, scene scale and objects. We propose how scene categorization could be computed in a feedforward manner in order to provide top-down and contextual information very early in the visual processing chain. Results show how visual categorization based directly on low-level features, without grouping or segmentation stages, can benefit object localization and identification. We show how simple image statistics can be used to predict the presence and absence of objects in the scene before exploring the image.","url":"https://doi.org/10.1088/0954-898x_14_3_302","authors":["Antonio Torralba","Aude Oliva"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T16:03:53Z","doi":"10.1088/0954-898x_14_3_302","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.17816/rmmar632532-4222239","name":"Fig. 4. Cluster N 1 of the sensorimotor neural network","source":"crossref","abstract":"","url":"https://doi.org/10.17816/rmmar632532-4222239","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-08T05:20:05Z","doi":"10.17816/rmmar632532-4222239","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.21236/ada264802","name":"Evolving Neural Network Architecture","source":"crossref","abstract":"This work investigates the application of a stochastic search technique, evolutionary programming, for developing self-organizing neural networks. The chosen stochastic search method is capable of simultaneously evolving both network architecture and weights. The number of synapses and neurons are incorporated into an objective function so that network parameter optimization is done with respect to computational costs as well as mean pattern error. Experiments are conducted using feedforward networks for simple binary mapping problems.","url":"https://doi.org/10.21236/ada264802","authors":["John R. McDonnell","Don Waagen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-09-05T15:54:36Z","doi":"10.21236/ada264802","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.1992.226860","name":"Neural network channel equalization","source":"crossref","abstract":"The authors present computer simulation results of the performance of conventional and perceptron-based equalizers in the presence of intersymbol interference (ISI), additive noise and co-channel interference (CCI). They show that a three-layer perceptron equalizer which is trained and updated by a complex-valued backpropagation adaptive algorithm can achieve acceptable bit error rate performance and demonstrate the effect of the perceptron configuration, size, and adaptation parameters on the equalizer performance. It is shown that the perceptron equalizer can essentially match the performance of a conventional equalizer under all noise and interference conditions. It is observed that the convergence rate of the perceptron-based equalizer is much slower than that of the conventional equalizer. With a sufficiently small adaptation step size, both of these equalizers are robust to decision-directed error propagation during data transmission.>","url":"https://doi.org/10.1109/ijcnn.1992.226860","authors":["N.W.K. Lo","H.M. Hafez"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-01-02T11:19:33Z","doi":"10.1109/ijcnn.1992.226860","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/icnn.1993.298785","name":"Neural network techniques for multi-user demodulation","source":"crossref","abstract":"Adaptive methods for demodulating multi-user communication in a direct-sequence spread-spectrum multiple-access (DS/SSMA) environment are investigated. Adaptive radial basis function (RBF) networks that operate with knowledge of only a subset of the system parameters are studied. This approach is further bolstered by the fact that the optimal detector in the synchronous case can be implemented by an RBF network when all of the system parameters are known. The RBF network performance is compared with other multi-user detectors. The centers of the RBF neurons, when the system parameters are not fully known, are determined using clustering techniques. It is shown that the adaptive RBF network obtains near optimal performance and is robust in realistic communication environments.>","url":"https://doi.org/10.1109/icnn.1993.298785","authors":["U. Mitra","H.V. Poor"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-12-30T22:49:31Z","doi":"10.1109/icnn.1993.298785","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.7554/elife.106871","name":"Neural signatures of motor memories emerge in neural network models","source":"crossref","abstract":"Abstract Animals can learn and seamlessly perform a great number of behaviors. However, it is unclear how neural activity can accommodate new behaviors without interfering with those an animal has already acquired. Recent studies in monkeys performing motor and brain-computer interface (BCI) learning tasks have identified neural signatures—so-called “memory traces” and “uniform shifts”—that appear in the neural activity of a familiar task after learning a new task. Here we asked when these signatures arise and how they are related to continual learning. By modeling a BCI learning paradigm, we show that both signatures emerge naturally as a consequence of learning, without requiring a specific mechanism. In general, memory traces and uniform shifts reflected savings by capturing how information from different tasks coexisted in the same neural activity patterns. Yet, although the properties of these two different signatures were both indicative of savings, they were uncorrelated with each other. When we added contextual inputs that separated the activity for the different tasks, these signatures decreased even when savings were maintained, demonstrating the challenges of defining a clear relationship between neural activity changes and continual learning.","url":"https://doi.org/10.7554/elife.106871","authors":["Joanna C Chang","Claudia Clopath","Juan A Gallego"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-27T14:31:12Z","doi":"10.7554/elife.106871","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.1989.118638","name":"Theory of the backpropagation neural network","source":"crossref","abstract":"The author presents a survey of the basic theory of the backpropagation neural network architecture covering architectural design, performance measurement, function approximation capability, and learning. The survey includes previously known material, as well as some new results, namely, a formulation of the backpropagation neural network architecture to make it a valid neural network (past formulations violated the locality of processing restriction) and a proof that the backpropagation mean-squared-error function exists and is differentiable. Also included is a theorem showing that any L/sub 2/ function from (0, 1)/sup n/ to R/sup m/ can be implemented to any desired degree of accuracy with a three-layer backpropagation neural network. The author presents a speculative neurophysiological model illustrating how the backpropagation neural network architecture might plausibly be implemented in the mammalian brain for corticocortical learning between nearby regions of the cerebral cortex.>","url":"https://doi.org/10.1109/ijcnn.1989.118638","authors":["Hecht-Nielsen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-01-13T13:46:33Z","doi":"10.1109/ijcnn.1989.118638","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/icnn.1993.298591","name":"A neural network that embeds its own meta-levels","source":"crossref","abstract":"A recurrent neural network is presented which (in principle) can, besides learning to solve problems posed by the environment, also use its own weights as input data and learn new (arbitrarily complex) algorithms for modifying its own weights in response to the environmental input and evaluations. The network uses subsets of its input and output units for observing its own errors and for explicitly analysing and manipulating all of its own weights, including those weights responsible for analyzing and manipulating weights. This effectively embeds a chain of meta-networks and meta-meta-. . .-networks into the network itself.>","url":"https://doi.org/10.1109/icnn.1993.298591","authors":["J. Schmidhuber"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-12-30T17:49:31Z","doi":"10.1109/icnn.1993.298591","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1007/978-94-007-4491-2_12","name":"Memristor SPICE Modeling","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-94-007-4491-2_12","authors":["Chris Yakopcic","Tarek M. Taha","Guru Subramanyam","Robinson E. Pino"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-06-27T13:03:30Z","doi":"10.1007/978-94-007-4491-2_12","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.3109/0954898x.2011.637606","name":"On nonlinearity in neural encoding models applied to the primary visual cortex","source":"crossref","abstract":"Within the regression framework, we show how different levels of nonlinearity influence the instantaneous firing rate prediction of single neurons. Nonlinearity can be achieved in several ways. In particular, we can enrich the predictor set with basis expansions of the input variables (enlarging the number of inputs) or train a simple but different model for each area of the data domain. Spline-based models are popular within the first category. Kernel smoothing methods fall into the second category. Whereas the first choice is useful for globally characterizing complex functions, the second is very handy for temporal data and is able to include inner-state subject variations. Also, interactions among stimuli are considered. We compare state-of-the-art firing rate prediction methods with some more sophisticated spline-based nonlinear methods: multivariate adaptive regression splines and sparse additive models. We also study the impact of kernel smoothing. Finally, we explore the combination of various local models in an incremental learning procedure. Our goal is to demonstrate that appropriate nonlinearity treatment can greatly improve the results. We test our hypothesis on both synthetic data and real neuronal recordings in cat primary visual cortex, giving a plausible explanation of the results from a biological perspective.","url":"https://doi.org/10.3109/0954898x.2011.637606","authors":["Diego Vidaurre","Concha Bielza","Pedro Larrañaga"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-04-30T12:15:08Z","doi":"10.3109/0954898x.2011.637606","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1088/0954-898x_6_3_011","name":"Probable networks and plausible predictions — a review of practical Bayesian methods for supervised neural networks","source":"crossref","abstract":"Bayesian probability theory provides a unifying framework for data modelling. In this framework the overall aims are to find models that are well-matched to the data, and to use these models to make optimal predictions. Neural network learning is interpreted as an inference of the most probable parameters for the model, given the training data. The search in model space (i.e., the space of architectures, noise models, preprocessings, regularizers and weight decay constants) can then also be treated as an inference problem, in which we infer the relative probability of alternative models, given the data. This review describes practical techniques based on Gaussian approximations for implementation of these powerful methods for controlling, comparing and using adaptive networks.","url":"https://doi.org/10.1088/0954-898x_6_3_011","authors":["David J C Mackay"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T16:04:29Z","doi":"10.1088/0954-898x_6_3_011","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1007/978-94-009-0643-3_2","name":"A Hardware Emulator for Binary Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-94-009-0643-3_2","authors":["Marcin Skubiszewski"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-12-09T03:06:39Z","doi":"10.1007/978-94-009-0643-3_2","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1007/978-3-642-87596-0_2","name":"On Fields of Inhibitory Influence in a Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-87596-0_2","authors":["F. Ratliff"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-04-26T22:20:23Z","doi":"10.1007/978-3-642-87596-0_2","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1007/978-94-009-0643-3_38","name":"Neural Network Simulation on the MasPar MP-1 Massively Parallel Processor","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-94-009-0643-3_38","authors":["K. A. Grajski","G. Chinn","C. Chen","C. Kuszmaul","S. Tomboulian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-12-08T22:06:39Z","doi":"10.1007/978-94-009-0643-3_38","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1145/106965.105260","name":"Protein classification using a neural network database system","source":"crossref","abstract":"Neural networks are being applied to a widely expanding area of applications, including the biological applications of protein structure prediction and DNA sequence","url":"https://doi.org/10.1145/106965.105260","authors":["Cathy H. Wu","Adisorn Epidemiology","Tzx-Chung Chang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2004-02-05T16:00:56Z","doi":"10.1145/106965.105260","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.4018/978-1-6684-2408-7.ch064","name":"An Innovative Air Purification Method and Neural Network Algorithm Applied to Urban Streets","source":"crossref","abstract":"In the present work, multiphysics modeling was used to investigate the feasibility of a photocatalysis-based outdoor air purifying solution that could be used in high polluted streets, especially street canyons. The article focuses on the use of a semi-active photocatalysis in the surfaces of the street as a solution to remove anthropogenic pollutants from the air. The solution is based on lamellae arranged horizontally on the wall of the street, coated with a photocatalyst (TiO2), lightened with UV light, with a dimension of 8 cm × 48 cm × 1 m. Fans were used in the system to create airflow. A high purification percentage was obtained. An artificial neural network (ANN) was used to predict the optimal purification method based on previous simulations, to design purification strategies considering the energy cost. The ANN was used to forecast the amount of purified with a feed-forward neural network and a backpropagation algorithm to train the model.","url":"https://doi.org/10.4018/978-1-6684-2408-7.ch064","authors":["Meryeme Boumahdi","Chaker El Amrani","Siegfried Denys"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-17T11:47:50Z","doi":"10.4018/978-1-6684-2408-7.ch064","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.2006.1716490","name":"A Fuzzified Neural Fuzzy Inference Network that Learns from Linguistic Information","source":"crossref","abstract":"A Fuzzified Takagi-Sugeno-Kang (TSK)-type Neural Fuzzy Inference Network (FTNFIN) for handling linguistic information is proposed in this paper. The inputs and outputs of FTNFIN may be fuzzy numbers with any shapes. The α-cut technique is used in input fuzzification and consequent part computation, which enables the network to handle linguistic information. There are no rules in FTNFIN initially since they are constructed on-line by concurrent structure and parameter learning. The network has been applied to the learning of fuzzy input and output data, and good simulation results are achieved.","url":"https://doi.org/10.1109/ijcnn.2006.1716490","authors":["Chia-Feng Juang","C.-I. Lee","Tung-Jung Chan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-30T12:35:23Z","doi":"10.1109/ijcnn.2006.1716490","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.70729/ijser15140","name":"Image Compression Using Back Propagation Neural Network","source":"crossref","abstract":"Image compression technique is used to reduce the number of bits required in representing image, which helps to reduce the storage space and transmission cost. In the present research work back propagation neural network training algorithm has been used. Back propagation neural network algorithm helps to increase the performance of the system and to decrease the convergence time for the training of the neural network. The proposed scheme has been demonstrated through several experiments including cameraman and very promising results in compression as well as in reconstructed image over convectional neural network based technique.","url":"https://doi.org/10.70729/ijser15140","authors":["Neha Jaiswal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-07T07:36:09Z","doi":"10.70729/ijser15140","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1007/978-3-032-15046-2_7","name":"Multivariate Parametrized Logistic Neural Network Approximation over Infinite Domains","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-15046-2_7","authors":["George A. Anastassiou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-14T08:42:21Z","doi":"10.1007/978-3-032-15046-2_7","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.2006.1716761","name":"On derivation of stagewise second-order backpropagation by invariant imbedding for multi-stage neural-network learning","source":"crossref","abstract":"We present a simple, intuitive argument based on \"invariant imbedding\" in the spirit of dynamic programming to derive a stagewise second-order backpropagation (BP) algorithm. The method evaluates the Hessian matrix of a general objective function efficiently by exploiting the multistage structure embedded in a given neural-network model such as a multilayer perceptron (MLP). In consequence, for instance, our stagewise BP can compute the full Hessian matrix \"faster\" than the standard method that evaluates the Gauss-Newton Hessian matrix alone by rank updates in nonlinear least squares learning. Through our derivation, we also show how the procedure serves to develop advanced learning algorithms; in particular, we explain how the introduction of \"stage costs\" leads to alternative systematic implementations of multi-task learning and weight decay.","url":"https://doi.org/10.1109/ijcnn.2006.1716761","authors":["E. Mizutani","S. Dreyfus"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-30T17:35:23Z","doi":"10.1109/ijcnn.2006.1716761","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.18495/comengapp.v13i2.438","name":"An Improved Myocardial Infarction Detection using Convolutional Neural Network and Graph Neural Network Algorithm","source":"crossref","abstract":"Myocardial infarction (MI) is a crucial health problem and its mortality rate is higher than that of cancer. It is the damage and death of heart muscle from the sudden blockage of a coronary artery by a blood clot. Although lots of researches have been carried out with impressive performance record for detection of MI, however, existing approaches for MI detection can be improved upon for better performance. A vital piece of medical technology that aids in the diagnosis of a number of heart-related disorders in patients is an electrocardiogram (ECG). To find significant episodes in long-term ECG data, an automated diagnostic method is needed. Cardiologists face a very difficult problem when trying to quickly examine long-term ECG records. To pinpoint critical occurrences, a computer-based diagnosing tool is necessary. In this study we employ Convolutional Neural Network (CNN) algorithm with Graph Neural Network (GNN) to select best features and make appropriate classifications. The result of the study gave f1 score of 99.58%, precision of 99.5% and an accuracy of 99.72%. Our proposed model have shown a significant improvement in the detection of MI, this will aid in effectively addressing the challenge of performance drawback in this domain of research.","url":"https://doi.org/10.18495/comengapp.v13i2.438","authors":["Opeyemi Aderiike Abisoye"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-02T06:47:53Z","doi":"10.18495/comengapp.v13i2.438","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.2006.1716614","name":"Nonlinear System Identification Based on B-Spline Neural Network and Modified Particle Swarm Optimization","source":"crossref","abstract":"Artificial neural networks, in particular, feedforward multilayer networks and basis function networks, have gradually established themselves as a usual tool in approximating complex nonlinear systems. B-spline networks, a type of basis function neural network, are normally trained by gradient-based methods, which may fall into local minima during the learning phase. In order to overcome the drawbacks encountered by conventional learning methods, particle swarm optimization - a swarm intelligence methodology - can provide a stochastic global search of B-spline networks for nonlinear system identification. In this paper, a modified particle swarm optimization algorithm using Gaussian and Cauchy probability distributions are applied to adjust the control points of B-spline neural networks. Simulation results for the identification of Rössler systems are provided and demonstrate the effectiveness and robustness of the proposed identification scheme.","url":"https://doi.org/10.1109/ijcnn.2006.1716614","authors":["L. dos Santos Coelho","R.A. Krohling"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-30T17:35:23Z","doi":"10.1109/ijcnn.2006.1716614","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.2007.4371258","name":"Rotated General Regression Neural Network","source":"crossref","abstract":"A rotated general regression neural network is presented as an enhancement to the general regression neural network. A variable kernel estimate for multivariate densities is considered. A coordinate transformation is adopted which circumvent the difficulty of predicting multimodal distribution with large variance differences between modes which is associated with the general regression neural network. The proposed technique trains the network in a way that the variance differences between modes is kept small and in the same order. Further, the technique reduces the number of indispensable training parameters to two parameters and lowers the load of the computation as well as the time for conditions in which employing separate values of σ is unavoidable. The accuracy of the proposed technique is demonstrated by examining two different cases: the performance map of an axial compressor and the boundary layer profile over a flat plate. The results are compared with those by general regression neural network as well as the corresponding experimental data. Excellent improvement is obtained.","url":"https://doi.org/10.1109/ijcnn.2007.4371258","authors":["M. Gholamrezaei","K. Ghorbanian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-11-06T20:35:49Z","doi":"10.1109/ijcnn.2007.4371258","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1002/2050-7038.12538/v1/review1","name":"Review for \"The nonlinear autoregressive network with exogenous inputs (NARX) neural network to damp power system oscillations\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/2050-7038.12538/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-07-27T17:06:47Z","doi":"10.1002/2050-7038.12538/v1/review1","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/icnn.1995.487391","name":"Twofold type of backpropagation neural network","source":"crossref","abstract":"Various types of neural networks have been introduced and those have been used in various areas. In some areas, those operate in a very good manner, but in another they don't. For example, Boltzmann machine and Hopfield network have better estimation and analogy abilities compared with backpropagation neural networks, but they are not accurate and are not easily convergent. On the other hand, backpropagation neural networks are very good at learning various patterns, but are bad at estimation and analogy when they are are under a very noisy condition. This means that if backpropagation neural networks can overcome estimation and analogy limitations, this can cover most of the application areas. So in this paper, an analogy and estimation method has been studied by introducing a twofold type of backpropagation neural network. A very good result has been obtained. And also, a new application field of those theories has appeared.","url":"https://doi.org/10.1109/icnn.1995.487391","authors":["S. Sugiyama"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-11-19T13:30:57Z","doi":"10.1109/icnn.1995.487391","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1007/978-3-7908-1902-1_136","name":"Systolic Simulation of Hamming Neural Network","source":"crossref","abstract":"The paper describes the systolic simulation of Hamming net algorithm. Systolic arrays creation methodology is based on Data Dependence Graphs analysis. The proposed implementation is focused on completely digital circuits. Input data is passed through the neurons in a time share basis, weights are stored in digital shift registers and no separate thresholds are used. The architecture provides massive parallelism and reprogrammability. The efficiency of proposed simulation is discussed based on implementation quality criteria for array architecture.","url":"https://doi.org/10.1007/978-3-7908-1902-1_136","authors":["Jacek Mazurkiewicz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-03-11T00:11:40Z","doi":"10.1007/978-3-7908-1902-1_136","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.7551/mitpress/7011.003.0012","name":"Feature Extraction Using an Unsupervised Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.7551/mitpress/7011.003.0012","authors":["Nathan Intrator"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-12-26T09:22:20Z","doi":"10.7551/mitpress/7011.003.0012","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/icnn.1995.487331","name":"Parallel neural network architectures","source":"crossref","abstract":"Several parallel neural network (PNN) architectures are presented in this paper. PNNs can work parallelly and coordinately. The implementation of their training is much easier than that of a single NN. And there are many other attractive characteristics of PNNs such as a modular structure, easy implementation by hardware, high efficiency for their parallel structures (compared with sequential NN architectures), easy implementation of additional learning, etc. PNNs can be used to deal with such problems as data processing, pattern recognition, and classification. The learning and additional learning algorithms for PNNs are presented in this paper. Some simulation results are given to illustrate the advantages of all the PNNs considered.","url":"https://doi.org/10.1109/icnn.1995.487331","authors":["Wang Guoyin","Shi Hongbao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-11-19T13:30:57Z","doi":"10.1109/icnn.1995.487331","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.5772/intechopen.68530","name":"Review of Recently Progress on Neural Electronics and Memcomputing Applications in Intrinsic SiOx-Based Resistive Switching Memory","source":"crossref","abstract":"","url":"https://doi.org/10.5772/intechopen.68530","authors":["Cheng-Chih Hsieh","Yao-Feng Chang","Ying-Chen Chen","Xiaohan Wu","Meiqi Guo","Fei Zhou","Sungjun Kim","Burt Fowler","Chih-Yang Lin","Chih-Hung Pan","Ting-Chang Chang","Jack C. Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-04-05T06:33:36Z","doi":"10.5772/intechopen.68530","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.1992.226961","name":"The projection neural network","source":"crossref","abstract":"A novel neural network model, the projection neural network, is developed to overcome three key drawbacks of backpropagation-trained neural networks (BPNN), i.e., long training times, the large number of nodes required to form closed regions for classification of high-dimensional problems and the lack of modularity. This network combines advantages of hypersphere classifiers, such as the restricted Coulomb energy (RCE) network, radial basis function methods, and BPNN. It provides the ability to initialize nodes to serve either as hyperplane separators or as spherical prototypes (radial basis functions), followed by a modified gradient descent error minimization training of the network weights and thresholds, which adjusts the prototype positions and sizes and may convert closed prototype decision boundaries to open boundaries, and vice versa. The network can provide orders of magnitude decrease in the required training time over BPNN and a reduction in the number of required nodes. Theory and examples are given.>","url":"https://doi.org/10.1109/ijcnn.1992.226961","authors":["G.D. Wilensky","N. Manukian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-01-02T11:19:33Z","doi":"10.1109/ijcnn.1992.226961","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/icnn.1993.298590","name":"Inverse recall neural network model and feedback pattern recognition","source":"crossref","abstract":"An inverse recall neural network model and a feedback pattern recognition method based on the model are proposed. The inverse recall neural network model is trained by the same method as that used for a typical multilayer feedforward model. The model can produce an inverse mapping of the trained feedforward mappings to show the parts of an input pattern. The model is applied to the feedback recognition method which can extract features from input patterns and discriminates between them by the inverse recall neural network model. The feedback recognition method adjusts feature extraction parameters so as to detect the important parts shown by the neural network model in order to present them to the network, and to produce more certain recognition results. This method is examined on handwritten alpha-numerics. It is found that rejection ratio can be reduced by half at the same error ratio.>","url":"https://doi.org/10.1109/icnn.1993.298590","authors":["K. Yamada"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-12-30T22:49:31Z","doi":"10.1109/icnn.1993.298590","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1007/978-94-009-0643-3_175","name":"A Structure for Neural Network Pattern Classifiers","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-94-009-0643-3_175","authors":["Terrence L. Fine","Thomas W. Parks"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-12-09T03:06:39Z","doi":"10.1007/978-94-009-0643-3_175","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1088/0954-898x_14_2_302","name":"Sequence learning in differentially activated dendrites","source":"crossref","abstract":"Differentially activated areas of a dendrite permit the existence of zones with distinct rates of synaptic modification, and such areas can be individually accessed using a reference signal which localizes synaptic plasticity and memory trace retrieval to certain subregions of the dendrite. It is proposed that the neural machinery required in such a learning/retrieval mechanism could involve the NMDA receptor, in conjunction with the ability of dendrites to maintain differentially activated regions. In particular, it is suggested that such a parcellation of the dendrite allows the neuron to participate in multiple sequences, which can be learned without suffering from the 'wash-out' of synaptic efficacy associated with superimposition of training patterns. This is a biologically plausible solution to the stability-plasticity dilemma of learning in neural networks.","url":"https://doi.org/10.1088/0954-898x_14_2_302","authors":["Bjørn Gilbert Nielsen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:03:55Z","doi":"10.1088/0954-898x_14_2_302","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1017/9780511783692.007","name":"Neural Network Models","source":"crossref","abstract":"The most recent development in distributional semantics is represented by models based on artificial neural networks. In this chapter, we focus on the use of neural networks to build static embeddings. Like random encoding models, neural networks incrementally learn embeddings by reducing the high dimensionality of distributional data without building an explicit co-occurrence matrix. Differing from the first generation of distributional semantic models (DSMs), also termed count models, the distributional representations produced by neural DSMs are the by-product of training the network to predict neighboring words, hence the name of predict models. Since semantically similar words tend to co-occur with similar contexts, the network learns to encode similar lexemes with similar distributional vectors. After introducing the basic concepts of neural computation, we illustrate neural language models and their use to learn distributional representations. Then we pass to describe the most popular static neural DSMs, CBOW, and Skip-Gram. We conclude the chapter with a comparison between count and predict models.","url":"https://doi.org/10.1017/9780511783692.007","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-07T00:06:44Z","doi":"10.1017/9780511783692.007","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.7717/peerj.19672/table-3","name":"Table 3: The default neural network training parameters in AIMOS.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj.19672/table-3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-01T08:12:20Z","doi":"10.7717/peerj.19672/table-3","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.7717/peerj-cs.2802/fig-5","name":"Figure 5: A neural network that has a hidden layer.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.2802/fig-5","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-07T04:48:57Z","doi":"10.7717/peerj-cs.2802/fig-5","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.2006.247362","name":"Medical Image Segmentation using a Self-organizing Neural Network and Clifford Geometric Algebra","source":"crossref","abstract":"In this paper we present a method based on self-organizing neural networks to extract the shape of an object which is useful for segmentation tasks. For that, the method uses a set of transformations expressed as versors in the conformal geometric algebra framework. Such transformations, when applied to any geometric entity of this geometric algebra, define the shape of the object. The utility of this approach is showed with one synthetic and several medical images (computer tomography and magnetic resonance images), where the object of interest is well segmented even if there is no well defined contours in the original image. In fact, the segmentation results obtained are better than the results using the ggvf-snake, no matter if the initialization of the snake is given inside, outside or over the (blurred) contour of the object.","url":"https://doi.org/10.1109/ijcnn.2006.247362","authors":["J. Rivera-Rovelo","E. Bayro-Corrochano"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T15:34:22Z","doi":"10.1109/ijcnn.2006.247362","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.2006.1716794","name":"Designing a Muscle like System Based on PID Controller and Tuned by Neural Network","source":"crossref","abstract":"This paper presents a study on a muscle like system based on a PID controller tuned by a neural network. The approach is based on a non linear muscle model using system identification based on a NNARX (neural network autoregressive exogenous) structure. This model is used in a special configuration of an MLP in order to let the output of the closed loop formed by the motor and controller to follow that of this non linear muscle model. Two structures are compared and the robustness of the approach is tested with different models of DC motors.","url":"https://doi.org/10.1109/ijcnn.2006.1716794","authors":["H.J. Serhan","C.G. Nasr","P. Henaff"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-30T12:35:23Z","doi":"10.1109/ijcnn.2006.1716794","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn52387.2021.9533464","name":"CM-Net: a point cloud upsampling network based on adversarial neural network","source":"crossref","abstract":"In the real-life application scenarios, the collected point clouds are often sparse, noisy and non-uniform, especially if the application is unable to capture the local spatial layout due to the lack of points. Thus, point cloud upsampling aims to transform sparse point clouds into dense point clouds with uniform point distribution. This study proposes a generative adversarial network-based point cloud upsampling network called CM-Net (Circular Multi-Frequency Network). The model consists of two parts: a generator and a discriminator. The generator's purpose is to convert the input sparse point cloud into a dense upsampling point cloud with our specific parts, includes multi-frequency pooling module and positive polygon-based code. On the contrary, the discriminator incudes two parts; a feature extractor and a convolutional network module, which optimizes the generator's performance. Experimental results show that our network can learn the point cloud's underlying geometric information very well, and complete the even distribution points.","url":"https://doi.org/10.1109/ijcnn52387.2021.9533464","authors":["Xiaomeng Li","Chung-Ming Own","Kaizhen Wu","Qian Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-20T21:27:41Z","doi":"10.1109/ijcnn52387.2021.9533464","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.2006.246927","name":"Content-based Video Adaptation in Low/Variable Bandwidth Communication Networks Using Adaptable Neural Network Structures","source":"crossref","abstract":"In this paper, an adaptable neural network model is used for real time video delivery over communication networks of low and variable bandwidth, such as the wireless ones. The scheme performs video delivery in content domain in contrast to the previous approaches in which only temporal frame skipping is adopted. The proposed method requires no buffering of video frames and thus imposing no frame delay. In particular, in case of low bandwidth conditions, the proposed scheme estimates the number of frames that best represent the sequence within a time segment and transmit this number for delivery instead of a temporal frame skipping. Multiple key frames are considered by optimally approximating the real bandwidth availability with a rational fraction. Key frame estimation is accomplished using a neural network model capable of predicting the indices of the most appropriate key frames that are to be delivered without being available the video information. The model takes into account the previous information as it has been evaluated by the already delivered information. The proposed scheme is based on an efficient recursive estimation algorithm since the network weights cannot be considered constant throughout video transmission. This is due to the fact that content as well as bandwidth characteristics vary from time to time.","url":"https://doi.org/10.1109/ijcnn.2006.246927","authors":["A. Doulamis","G. Tziritas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T11:34:22Z","doi":"10.1109/ijcnn.2006.246927","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.4018/978-1-7998-0414-7.ch012","name":"Artificial Neural Network (ANN) in Network Reconfiguration for Improvement of Voltage Stability","source":"crossref","abstract":"Issues related to power system voltage levels have become increasingly important issue during last two and half decades. In power networks, low voltage situations may result in the loss of stability, voltage collapse and eventually to cascading power outages. Large number of incidents of voltage collapse has been reported in different countries across the globe. A simple indicator that has the potential in real time, i.e. L indicator has been used to find voltage profile at different switching condition and simulated using ANN in network reconfiguration for the improvement of voltage stability. A method for improving voltage stability in a power network comprising of multiple lines and switches has been suggested in this chapter based on system reconfiguration approach. ANN based fast and efficient methodology has been developed to obtain the optimum switching combination to achieve best voltage stability. The proposed scheme has been tested on an IEEE 14-bus system.","url":"https://doi.org/10.4018/978-1-7998-0414-7.ch012","authors":["Dipu Sarkar","Joyanta Kumar Roy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-09-18T13:52:17Z","doi":"10.4018/978-1-7998-0414-7.ch012","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.48185/jfcns.v7i1.1816","name":"Analysis of Stability in Rulkov Neural Networks with Fractional Orders and Asymmetric Memristor Synapses","source":"crossref","abstract":"Fractional-order models effectively capture memory and hereditary effects in neural and nonlinear dy namical systems. Memristors are ideal components for modeling synaptic connections due to their ability to emulate plasticity and memory effects. Discrete models of memristor-coupled neurons simplify computa tions and enable efficient analysis of large-scale networks. Despite their potential, discrete fractional-order memristor-coupled models have been less explored. To address this, we propose two novel discrete fractional order neural systems. The first system is a two-neuron motif coupled via dual memristors, while the second extends this configuration to a ring-shaped network of similar subnetworks. A new theorem on the stabil ity of discrete fractional-order systems is established, defining stability regions for both models. Numerical simulations illustrate the theoretical results and investigate how the fractional order, asymmetric memristive coupling, and other model and network parameters jointly influence the dynamics and stability of discrete time neurons.","url":"https://doi.org/10.48185/jfcns.v7i1.1816","authors":["Leila Eftekhari","Moein Khalighi","Saeid Abbasbandy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-04T01:08:59Z","doi":"10.48185/jfcns.v7i1.1816","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.7717/peerj-cs.3347/table-8","name":"Algorithm 2 : Multi-swarm PSO for neural network weight update.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.3347/table-8","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T08:33:07Z","doi":"10.7717/peerj-cs.3347/table-8","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1016/b978-0-12-228640-7.50021-0","name":"GLOSSARY","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-12-228640-7.50021-0","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-01T08:04:20Z","doi":"10.1016/b978-0-12-228640-7.50021-0","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.21236/ada273134","name":"Evolving Neural Network Connectivity","source":"crossref","abstract":"","url":"https://doi.org/10.21236/ada273134","authors":["J. R. McDonnell","D. Waagen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-08-31T18:15:42Z","doi":"10.21236/ada273134","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1201/b10515-11","name":"Intelligent Neural Network Systems and Evolutionary Learning","source":"crossref","abstract":"Although several conventional methods (e.g., pruning techniques) exist that may be used to automatically determine neural network con€guration and weights, they are often susceptible to trapping at local optima and characteristically dependent on the initial network structure (Gao et al., 1999). Overcoming these limitations would thus prove useful in the development of more intelligent neural network systems, those capable of demonstrating effective global search characteristics with fast convergence, and capable of providing alternative tools for modeling complex natural processes. The movement toward more intelligent network systems requires consideration of alternative strategies to help optimize neural network structure and aid in bringing multifaceted problems into focus. By converging on speci€c methodologies common to, for example, genetic algorithms, evolutionary programming, and fuzzy logic, we can begin to comprehend how when combined with neural networks, hybrid technology can impart the ef€ciency and accuracy needed in fundamental research, where multidisciplinary and multiobjective tasks are routinely performed. The objectives of this chapter are twofold: (1) to present theoretical concepts behind unconventional methodologies and (2) showcase a variety of example hybrid techniques, including neuro-fuzzy, neuro-genetic, and neuro-fuzzy-genetic systems.","url":"https://doi.org/10.1201/b10515-11","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-11T12:22:47Z","doi":"10.1201/b10515-11","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1887/0750303123/b365c122","name":"A neural network for the evaluation of hemodynamic variables","source":"crossref","abstract":"","url":"https://doi.org/10.1887/0750303123/b365c122","authors":["Tom Pike","Robert A Mustard"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2004-11-26T05:22:41Z","doi":"10.1887/0750303123/b365c122","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/icnn.1993.298777","name":"A neural network to diagnose liver cancer","source":"crossref","abstract":"A backpropagation neural network is designed to diagnose five classifications of hepatic masses: metastatic carcinoma, hepatoma (HCC), cavernous hemangioma, abscess, and cirrhosis. BrainMaker Professional version 2.5 software is used in this research. The input submitted to the network consists of 35 numbers per patient case, which represents ultrasonographic data and laboratory tests. The network architecture has 35 elements in the input layer, two hidden layers of 35 elements each, and five elements in the output layer. After being trained to a learning tolerance of 1%, the network classifies hepatic masses correctly in 51 of 72 cases. Continued research should provide a computerized second opinion that will be especially helpful to clinicians.>","url":"https://doi.org/10.1109/icnn.1993.298777","authors":["P.S. Maclin","J. Dempsey"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-12-30T22:49:31Z","doi":"10.1109/icnn.1993.298777","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1115/1.802566.paper51","name":"A Neural Network Based DTMF Decoder","source":"crossref","abstract":"Communications systems frequently use a technique known as dual-tone multifrequency dialing (DTMF). Many possible solutions have been proposed for the design of DTMF decoders. Hardware-based solutions use filter banks to separate signals into low-band and high-band channels and to detect specific frequencies. Outputs from the filters are used to reconstruct the depressed pushbutton. These designs often increase the parts count, which results in larger circuit board space and increased costs. Software-based approaches mainly use FFT algorithms or filter banks implemented on a DSP. These designs have complex algorithms with large computational requirements. This paper discusses an approach to develop an efficient neural network based implementation of a DTMF decoder.","url":"https://doi.org/10.1115/1.802566.paper51","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-06-25T16:01:43Z","doi":"10.1115/1.802566.paper51","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1007/978-94-009-0643-3_135","name":"Most Neural Networks Compute in Steps","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-94-009-0643-3_135","authors":["Armand de Callataÿ"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-12-09T03:06:39Z","doi":"10.1007/978-94-009-0643-3_135","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1201/b17332-9","name":"Forms of Neural Network Learning","source":"crossref","abstract":"We will explain linear networks and discuss the limitations imposed by their simple structures. For our purposes, linear networks are easier to teach, they perform certain tasks very well, and their results are easy to analyze. Chapter 6 will cover the more complex nonlinear networks.","url":"https://doi.org/10.1201/b17332-9","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-08-07T22:25:43Z","doi":"10.1201/b17332-9","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.1991.155664","name":"Analogical reasoning by neural network","source":"crossref","abstract":"Summary form only given, as follows. Analogical reasoning by neural network is discussed. The proposed method uses a template to create a network for analogical reasoning, and this can be done by an interactive activation and competition process. Computer simulation results indicate the effectiveness of the proposed analogical reasoning. >","url":"https://doi.org/10.1109/ijcnn.1991.155664","authors":["M. Hagiwara","Y. Anzai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-12-09T18:24:26Z","doi":"10.1109/ijcnn.1991.155664","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.17509/gea.v20i2.28163.s5108","name":"DEFUZZIFICATION OF ARTIFICIAL NEURAL NETWORK METHOD FOR LAND USE CLASSIFICATION","source":"crossref","abstract":"","url":"https://doi.org/10.17509/gea.v20i2.28163.s5108","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-08-30T04:22:07Z","doi":"10.17509/gea.v20i2.28163.s5108","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.22215/etd/1992-02058","name":"Neural network based detection of EEG abnormalities.","source":"crossref","abstract":"","url":"https://doi.org/10.22215/etd/1992-02058","authors":["Leon Lipoth"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-10-04T20:10:16Z","doi":"10.22215/etd/1992-02058","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.7717/peerj-cs.3527/fig-1","name":"Figure 1: The schematic diagram of fuzzy neural network structure.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.3527/fig-1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-04T08:10:26Z","doi":"10.7717/peerj-cs.3527/fig-1","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.17077/etd.r6q1np0x","name":"Artificial neural network for studying human performance","source":"crossref","abstract":"The vast majority of products and processes in industry and academia require human interaction. Thus, digital human models (DHMs) are becoming critical for improved designs, injury prevention, and a better understanding of human behavior. Although many capabilities in the DHM field continue to mature, there are still many opportunities for improvement, especially with respect to posture- and motion-prediction. Thus, this thesis investigates the use of artificial neural network (ANN) for improving predictive capabilities and for better understanding how and why human behave the way they do.\\nWith respect to motion prediction, one of the most challenging opportunities for improvement concerns computation speed. Especially, when considering dynamic motion prediction, the underlying optimization problems can be large and computationally complex. Even though the current optimization-based tools for predicting human posture are relatively fast and accurate and thus do not require as much improvement, posture prediction in general is a more tractable problem than motion prediction and can provide a test bead that can shed light on potential issues with motion prediction. Thus, we investigate the use of ANN with posture prediction in order to discover potential issues. In addition, directly using ANN with posture prediction provides a preliminary step towards using ANN to predict the most appropriate combination of performance measures (PMs) - what drives human behavior. The PMs, which are the cost functions that are minimized in the posture prediction problem, are typically selected manually depending on the task. This is perhaps the most significant impediment when using posture prediction. How does the user know which PMs should be used? Neural networks provide tools for solving this problem.\\nThis thesis hypothesizes that the ANN can be trained to predict human motion quickly and accurately, to predict human posture (while considering external forces), and to determine the most appropriate combination of PM(s) for posture prediction. Such capabilities will in turn provide a new tool for studying human behavior. Based on initial experimentation, the general regression neural network (GRNN) was found to be the most effective type of ANN for DHM applications. A semi-automated methodology was developed to ease network construction, training and testing processes, and network parameters. This in turn facilitates use with DHM applications.\\nWith regards to motion prediction, use of ANN was successful. The results showed that the calculation time was reduced from 1 to 40 minutes, to a fraction of a second without reducing accuracy. With regards to posture prediction, ANN was again found to be effective. However, potential issues with certain motion-prediction tasks were discovered and shed light on necessary future development with ANNs. Finally, a decision engine was developed using GRNN for automatically selecting four human PMs, and was shown to be very effective. In order to train this new approach, a novel optimization formulation was used to extract PM weights from pre-existing motion-capture data. Eventually, this work will lead to automatically and realistically driving predictive DHMs in a general virtual environment.","url":"https://doi.org/10.17077/etd.r6q1np0x","authors":["Mohammad Hindi Bataineh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-11-29T22:03:45Z","doi":"10.17077/etd.r6q1np0x","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.7717/peerj-cs.1977/table-4","name":"Table 4: Configuration of neural network structure for E-MFNN.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.1977/table-4","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-19T03:43:31Z","doi":"10.7717/peerj-cs.1977/table-4","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1016/j.cjph.2017.08.021","name":"Finite-time stability for memristor based uncertain neural networks with time-varying delays- via average dwell time approach","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.cjph.2017.08.021","authors":["M. Syed Ali","S. Saravanan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-08-24T09:21:39Z","doi":"10.1016/j.cjph.2017.08.021","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.2006.1716662","name":"Recurrent Neural Network Based Predictions of Elephant Migration in a South African Game Reserve","source":"crossref","abstract":"A large portion of South Africa's elephant population can be found on small wildlife reserves. When confined to enclosed reserves the elephant densities are much higher than observed in the wild. The large nutritional demands and destructive foraging behavior of elephants threaten rare species of vegetation. If conservation management is to protect threatened species of vegetation, knowing how long elephants will stay in one area of the reserve as well as which area they will move to next is essential. The goal of this study is to train a recurrent neural network (RNN) to continuously predict an elephant herd's next position in the Pongola Game Reserve. Accurate predictions would provide a useful tool in assessing future impact of elephant populations on different areas of the reserve. The particle swarm optimization (PSO) algorithm is used to adapt the weights of the neural network. Results are presented to show the effectiveness of RNN-PSO for elephant migration prediction.","url":"https://doi.org/10.1109/ijcnn.2006.1716662","authors":["P. Palangpour","G.K. Venayagamoorthy","K. Duffy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-30T17:35:23Z","doi":"10.1109/ijcnn.2006.1716662","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1088/0954-898x/5/2/008","name":"A shape-recognition model using dynamical links","source":"crossref","abstract":"A shape-recognition method is proposed, inspired from the dynamic-link theory of von der Malsburg (1981). The quality of a match between two images is assessed through an elastic cost functional; the minimal value reached by the cost over a suitably-defined space of maps is viewed as a distance between these two images. Experiments on nearest-neighbour classification of handwritten numerals are presented, using a computationally effective procedure for finding a reliable estimate of the matching distance.","url":"https://doi.org/10.1088/0954-898x/5/2/008","authors":["Elie Bienenstock","René Doursat"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-24T22:35:54Z","doi":"10.1088/0954-898x/5/2/008","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1088/0954-898x/11/4/305","name":"Randomly connected sigma–pi neurons can form associator networks","source":"crossref","abstract":"A set of sigma–pi units randomly connected to two input vectors forms a type of hetero-associator related to convolution- and matrix-based associative memories. Associations are represented as patterns of activity rather than connection strengths. Decoding the associations requires another network of sigma–pi units, with connectivity dependent on the encoding network. Learning the connectivity of the decoding network involves setting n3 parameters (where n is the size of the vectors), and can be accomplished in approximately 3e n log n presentations of random patterns. This type of network encodes information in activation values rather than in weight values, which makes the information about relationships accessible to further processing. This accessibility is essential for higher-level cognitive tasks such as analogy processing. The fact that random networks can perform useful operations makes it more plausible that these types of associative network could have arisen in the nervous systems of natural organisms during the course of evolution.","url":"https://doi.org/10.1088/0954-898x/11/4/305","authors":["Tony Plate"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:58:05Z","doi":"10.1088/0954-898x/11/4/305","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.2006.247390","name":"Recurrent Neural Network Based Gating for Natural Gas Load Prediction System","source":"crossref","abstract":"Prediction of natural gas consumption is an important element in gas load management aimed to better utilize the facilities of a gas distribution system. The major challenges faced by developers of prediction systems are the variety and volatility of consumer profiles, strong seasonal dependency and dependency on climatic conditions, and lack of extensive and reliable historical data. In this paper, the problem of seasonal dependency is tackled with a recurrent neural network used as a gate for a statistical mixture model. Historical consumption data along with climatic conditions and other auxiliary descriptors are combined with expert delineation of heating season boundaries to provide training data. The resulting gating system is capable of reliable identification of the start and end of the heating season and, combined with the statistical models, of accurate predictions of gas load.","url":"https://doi.org/10.1109/ijcnn.2006.247390","authors":["P. Musilek","E. Pelikan","T. Brabec","M. Simunek"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T11:34:22Z","doi":"10.1109/ijcnn.2006.247390","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.4018/978-1-6684-2408-7.ch015","name":"Artificial Neural Network Training Algorithms in Modeling of Radial Overcut in EDM","source":"crossref","abstract":"This chapter describes with the comparison of the most used back propagations training algorithms neural networks, mainly Levenberg-Marquardt, conjugate gradient and Resilient back propagation are discussed. In the present study, using radial overcut prediction as illustrations, comparisons are made based on the effectiveness and efficiency of three training algorithms on the networks. Electrical Discharge Machining (EDM), the most traditional non-traditional manufacturing procedures, is growing attraction, due to its not requiring cutting tools and permits machining of hard, brittle, thin and complex geometry. Hence it is very popular in the field of modern manufacturing industries such as aerospace, surgical components, nuclear industries. But, these industries surface finish has the almost importance. Based on the study and test results, although the Levenberg-Marquardt has been found to be faster and having improved performance than other algorithms in training, the Resilient back propagation algorithm has the best accuracy in testing period.","url":"https://doi.org/10.4018/978-1-6684-2408-7.ch015","authors":["Raja Das","Mohan Kumar Pradhan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-17T11:47:50Z","doi":"10.4018/978-1-6684-2408-7.ch015","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1016/j.nahs.2020.100861","name":"Mono/multi-periodicity generated by impulses control in time-delayed memristor-based neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.nahs.2020.100861","authors":["Zuowei Cai","Lihong Huang","Zengyun Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-01-16T05:29:34Z","doi":"10.1016/j.nahs.2020.100861","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1088/0954-898x_14_4_302","name":"Detecting dynamical changes within a simulated neural ensemble using a measure of representational quality","source":"crossref","abstract":"Technological advances allowing simultaneous recording of neuronal ensembles have led to many developments in our understanding of how the brain performs neural computations. One key technique for extracting information from neural populations has been population reconstruction. While reconstruction is a powerful tool, it only provides a value and gives no indication of the quality of the representation itself. In this paper, we present a mathematically and statistically justified measure for assessing the quality of a representation in a neuronal ensemble. Using a simulated neural network, we show that this measure can distinguish between system states and identify moments of dynamical change within the system. While the examples used in this paper all derive from a standard network model, the measure itself is very general. It requires only a representational space, measured tuning curves, and neural ensembles.","url":"https://doi.org/10.1088/0954-898x_14_4_302","authors":["Jadin C Jackson","A David Redish"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:06Z","doi":"10.1088/0954-898x_14_4_302","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1016/0893-6080(88)90307-3","name":"An external network model of the hippocampal formation","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90307-3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T01:05:53Z","doi":"10.1016/0893-6080(88)90307-3","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1201/9781439821992-8","name":"Recent Advances in Neural Network Applications in Process Control","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781439821992-8","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-11-19T00:12:42Z","doi":"10.1201/9781439821992-8","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.2005.1555795","name":"2005 International Neural Network Society Officers","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2005.1555795","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-06-07T18:33:07Z","doi":"10.1109/ijcnn.2005.1555795","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1017/cbo9780511624216.028","name":"Useful Results","source":"crossref","abstract":"","url":"https://doi.org/10.1017/cbo9780511624216.028","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2010-03-02T18:08:05Z","doi":"10.1017/cbo9780511624216.028","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.7717/peerj.15647/supp-1","name":"Supplemental Information 1: ROC, BP neural network and SVM data","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj.15647/supp-1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-30T04:01:33Z","doi":"10.7717/peerj.15647/supp-1","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.32920/25761549.v1","name":"Portfolio Selection with Convolutional Neural Network","source":"crossref","abstract":"&lt;p&gt;In this work, we applied Convolutional Neural network (CNN) models to select the portfolio weights that lead to the highest realized return in one time-step ahead. In fact, given four possible portfolio optimization methods, the CNN is used to forecast the one-step-ahead returns of the assets in the portfolio implicitly and selects the portfolio optimization approach leading to the highest portfolio return. We construct four different datasets based on the daily return time series of the 36 stocks in our portfolio. In each dataset, one instance is composed of the mean vector and the covariance matrix. The four datasets are obtained as a result of using four different methods to calculate mean vectors and covariance matrices. Six different CNN model architectures are constructed, and the models' performances are compared. The obtained results demonstrate the effectiveness of CNNs in portfolio selection.&lt;/p&gt;","url":"https://doi.org/10.32920/25761549.v1","authors":["Fahimeh Saei Manesh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-06T19:13:08Z","doi":"10.32920/25761549.v1","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.15368/theses.2020.21","name":"ELECTRICITY PRICE FORECASTING USING A CONVOLUTIONAL NEURAL NETWORK","source":"crossref","abstract":"Many methods have been used to forecast real-time electricity prices in various regions around the world. The problem is difficult because of market volatility affected by a wide range of exogenous variables from weather to natural gas prices, and accurate price forecasting could help both suppliers and consumers plan effective business strategies. Statistical analysis with autoregressive moving average methods and computational intelligence approaches using artificial neural networks dominate the landscape. With the rise in popularity of convolutional neural networks to handle problems with large numbers of inputs, and convolutional neural networks conspicuously lacking from current literature in this field, convolutional neural networks are used for this time series forecasting problem and show some promising results. This document fulfills both MSEE Master's Thesis and BSCPE Senior Project requirements.","url":"https://doi.org/10.15368/theses.2020.21","authors":["Elliott Winicki"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-01T18:14:06Z","doi":"10.15368/theses.2020.21","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1088/0954-898x_1_3_004","name":"On the dynamics of neural networks realizing associative memories of first and higher order","source":"crossref","abstract":"This paper presents a new study on the dynamics of neural networks realizing associative memories of first and higher order. This is accomplished by focusing on the dynamics of a system of coupled differential equations that is shown to be equivalent to the neural network which behaves as an associative memory. This equivalence allows the assignment of a Lyapunov function to neural networks realizing associative memories of any order. This analysis provides some new interpretations for the outer product rule, or correlational learning, and also a basis for the development of more sophisticated learning schemes. A fundamental difference in the behaviour of associative memories of even and odd order is also investigated.","url":"https://doi.org/10.1088/0954-898x_1_3_004","authors":["Nicolaos B Karayiannis","Anastasios N Venetsanopoulos"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:06Z","doi":"10.1088/0954-898x_1_3_004","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1088/0954-898x/14/1/309","name":"Analysis of neural coding through quantization with an information-based distortion measure","source":"crossref","abstract":"We discuss an analytical approach through which the neural symbols and corresponding stimulus space of a neuron or neural ensemble can be discovered simultaneously and quantitatively, making few assumptions about the nature of the code or relevant features. The basis for this approach is to conceptualize a neural coding scheme as a collection of stimulus-response classes akin to a dictionary or 'codebook', with each class corresponding to a spike pattern 'codeword' and its corresponding stimulus feature in the codebook. The neural codebook is derived by quantizing the neural responses into a small reproduction set, and optimizing the quantization to minimize an information-based distortion function. We apply this approach to the analysis of coding in sensory interneurons of a simple invertebrate sensory system. For a simple sensory characteristic (tuning curve), we demonstrate a case for which the classical definition of tuning does not describe adequately the performance of the cell studied. Considering a more involved sensory operation (sensory discrimination), we also show that, for some cells in this system, a significant amount of information is encoded in patterns of spikes that would not be discovered through analyses based on linear stimulus-response measures.","url":"https://doi.org/10.1088/0954-898x/14/1/309","authors":["A.G. Dimitrov","J.P. Miller","T. Gedeon","Z. Aldworth","A.E. Parker"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-01-22T23:14:48Z","doi":"10.1088/0954-898x/14/1/309","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1016/b978-0-12-228640-7.50001-5","name":"Front Matter","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-12-228640-7.50001-5","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-07-01T08:02:55Z","doi":"10.1016/b978-0-12-228640-7.50001-5","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.14711/thesis-991013098359403412","name":"Multilingual document embedding with sequential neural network models","source":"crossref","abstract":"One of the current state-of-the-art multilingual document embedding model LASER is based on the bidirectional LSTM (BiLSTM) neural machine translation (NMT) model. This paper presents a Transformer-based Multilingual sentence/Document Embedding model, T-MDE, which makes two significant improvements. Firstly, the BiLSTM encoder is replaced by the attention-based transformer structure with an novel information bottleneck design. The new model structure is more capable of learning sequential patterns in longer texts. Moreover, it is faster both in training and embedding generation. Secondly, we augment the NMT translation loss function with an carefully designed distance constraint loss term. It will further brings the embeddings of parallel sentences close together in the vector space. We call the T-MDE model trained with distance constraint, cT-MDE. Our T-MDE model significantly outperforms BiLSTM-based LASER in the cross-lingual document classification tasks.","url":"https://doi.org/10.14711/thesis-991013098359403412","authors":["Wei Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-05T04:27:30Z","doi":"10.14711/thesis-991013098359403412","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.7717/peerjcs.2008/fig-7","name":"Figure 7: Confusion matrix analysis of applied neural network approaches.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerjcs.2008/fig-7","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-17T03:36:29Z","doi":"10.7717/peerjcs.2008/fig-7","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.7717/peerj-cs.3201/table-6","name":"Table 6: Performance metrics for neural network based summarization methods.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.3201/table-6","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-27T08:00:24Z","doi":"10.7717/peerj-cs.3201/table-6","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1088/0954-898x_3_2_005","name":"Study of a learning algorithm for neural networks with discrete synaptic couplings","source":"crossref","abstract":"The authors present a new learning algorithm for neural networks with discrete synaptic couplings. The main difference with respect to other previous algorithms is that it is defined in the continuous space. Its performance and features are analysed in detail.","url":"https://doi.org/10.1088/0954-898x_3_2_005","authors":["C J Pérez Vicente","J Carrabina","E Valderrama"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T16:04:12Z","doi":"10.1088/0954-898x_3_2_005","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1088/0954-898x_15_4_004","name":"Multiplicative neural noise can favor an independent components representation of sensory input","source":"crossref","abstract":"Arguments have been advanced to support the role of principal components (e.g., Karhunen-Loéve, eigenvector) and independent components transformations in early sensory processing, particularly for color and spatial vision. Although the concept of redundancy reduction has been used to justify a principal components transformation, these transformations per se do not necessarily confer benefits with respect to information transmission in information channels with additive independent identically distributed Gaussian noise. Here, it is shown that when a more realistic source of multiplicative neural noise is present in the information channel, there are quantitative benefits to a principal components or independent components representation for Gaussian and non-Gaussian inputs, respectively. Such a representation can convey a larger quantity of information despite the use of fewer spikes. The nature and extent of this benefit depend primarily on the probability distribution of the inputs and the relative power of the inputs. In the case of Gaussian input, the greater the disparity in power between dimensions, the greater the advantage of a principal components representation. For non-Gaussian input distributions with a kurtosis that is super-Gaussian, an independent components representation is similarly advantageous. This advantage holds even for input distributions with equal power since the resulting density is still rotationally asymmetric. However, sub-Gaussian input distributions can lead to situations where maximally correlated inputs are the most advantageous with respect to transmitting the greatest quantity of information with the fewest number of spikes.","url":"https://doi.org/10.1088/0954-898x_15_4_004","authors":["Allan Gottschalk","Matthew G Sexton","Guilherme Roschke"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:00Z","doi":"10.1088/0954-898x_15_4_004","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1007/978-1-4615-3192-0_2","name":"Network Architecture","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4615-3192-0_2","authors":["Dean A. Pomerleau"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-06-15T05:55:34Z","doi":"10.1007/978-1-4615-3192-0_2","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.2006.246746","name":"A Fully CMOS Low-Cost Chaotic Neural Network","source":"crossref","abstract":"A chaotic IC is proposed and fabricated using a 0.35μm CMOS technology. The circuit iterates an N-shaped transfer function that can be modified using two external voltages, and is implemented using a three neurons network. The main advantages of the proposed circuit are based on its simplicity, small area (47 × 57μm2), and its MOS-only implementation requiring no more than 15 MOS transistors. Measurements show the suitability of the proposed system to reproduce a chaotic signal and to be used as a random number generator.","url":"https://doi.org/10.1109/ijcnn.2006.246746","authors":["J.L. Rossello","S. Bota","V. Canals","I. de Paul","J. Segura"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T11:27:21Z","doi":"10.1109/ijcnn.2006.246746","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1007/978-94-009-0643-3_139","name":"Neural Network Unit Density: A Critical Biological Parameter","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-94-009-0643-3_139","authors":["N. Azmy","J.-F. Vibert"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-12-09T03:06:39Z","doi":"10.1007/978-94-009-0643-3_139","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1088/0954-898x_6_3_009","name":"Unsupervised learning for Boltzman Machines","source":"crossref","abstract":"An unsupervised learning algorithm for a stochastic recurrent neural network based on the Boltzmann Machine architecture is formulated in this paper. The maximization of the mutual information between the stochastic output neurons and the clamped inputs is used as an unsupervised criterion for training the network. The resulting learning rule contains two terms corresponding to Hebbian and anti-Hebbian learning. It is interesting that these two terms are weighted by the amount of information transmitted in the learning synapse, giving an information-theoretic interpretation of the proportionality constant of Hebb's biological rule. The anti-Hebbian term, which can be interpreted as a forgetting function, supports the optimal coding. In this way, optimal nonlinear and recurrent implementations of data compression of Boolean patterns are obtained. As an example, the encoder problem is simulated and trained in an unsupervised way in a one layer network. Compression of non-uniform distributed binary data is included. Unsupervised classification, even for continuous inputs, is shown for the cases of four overlapping Gaussian spots and for a real-world example of thyroid diagnosis. In comparison with other techniques, the present model requires an exponentially smaller number of weights for the classification problem.","url":"https://doi.org/10.1088/0954-898x_6_3_009","authors":["Gustavo Deco","Lucas Parra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T16:04:47Z","doi":"10.1088/0954-898x_6_3_009","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1088/0954-898x/5/1/003","name":"Regulating the nonlinear dynamics of olfactory cortex","source":"crossref","abstract":"The dynamic behaviour of cortical structures can be changed significantly in character by different types of neuromodulators. We simulate such effects in a neural network model of the olfactory cortex and analyse the resulting nonlinear dynamics of this system, including during both learning and recall. The model has simple network units and realistic network connectivity. The input-output relation of populations of neurons is represented as a sigmoid function, with a single parameter determining threshold, slope and amplitude of the curve. This parameter can be thought of as corresponding to the concentration of a particular neuromodulator in the system. It can also be related to the level of arousal of an animal. By varying this ‘gain parameter’ we show that the model can give point attractor, limit cycle attractor and strange chaotic or non-chaotic attractor behaviour. We also display ‘transient chaos’ phenomena, which begin with chaos-like behaviour but eventually converge to a limit cycle. We demonstrate that the complex dynamics under neuromodulatory control can enhance weak signals and reduce recall time considerably, in particular when going from point attractor to limit cycle dynamics. Finally, we discuss the biological significance of these findings, recognizing the difficulties in characterizing the nonlinear dynamical states involved.","url":"https://doi.org/10.1088/0954-898x/5/1/003","authors":["Xiangbao Wu","Hans Liljenstrom"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/5/1/003","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1088/0954-898x_9_4_006","name":"Evolving neurocontrollers for balancing an inverted pendulum","source":"crossref","abstract":"This paper introduces an evolutionary algorithm that is tailored to generate recurrent neural networks functioning as nonlinear controllers. Network size and architecture, as well as network parameters like weights and bias terms, are developed simultaneously. There is no quantization of inputs, outputs or internal parameters. Different kinds of evolved networks are presented that solve the pole-balancing problem, i.e. balancing an inverted pendulum. In particular, controllers solving the problem for reduced phase space information (only angle and cart position) use a recurrent connectivity structure. Evolved controllers of 'minimal' size still have a very good benchmark performance.","url":"https://doi.org/10.1088/0954-898x_9_4_006","authors":["F Pasemann"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T16:04:53Z","doi":"10.1088/0954-898x_9_4_006","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.21275/sr21225214136","name":"Convolution Neural Network Based Image Recognition","source":"crossref","abstract":"The identification of an image is one thorny task in computer vision problems. Using the python programming language and a few other machine learning algorithms and python libraries, this image recognition and feature extraction can be achieved. In pattern- and image-recognition problems, convolutionary neural networks (CNNs) are commonly used as they have a range of benefits compared to other techniques. The basics of CNNs are covered in this document, including a description of the different layers used. In this paper, we presented a model for cat and dog image recognition from the Convolutionary Neural Network (CNN). Before feeding it to the CNN model, the cat and dog dataset is pre-processed.","url":"https://doi.org/10.21275/sr21225214136","authors":["Sofia Hamid","Mrigana Walia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-06T08:52:19Z","doi":"10.21275/sr21225214136","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.2006.247064","name":"An ETF Trading Decision Support System by Using Neural Network and Technical Indicators","source":"crossref","abstract":"This paper proposed a neural network based decision support system (DSS) to provide investors with suggestions on transaction timing and transaction strategies of Taiwan 50 index exchange traded funds (ETF). Various indicators were employed with corresponding application principles as the neural network underwent assigned training and learning procedures. It was revealed in the study results that the simulated transaction behavior following recommendations by the proposed system yielded better profits than solely applying Taiwan's weighted stock index.","url":"https://doi.org/10.1109/ijcnn.2006.247064","authors":["Chih-Lung Chen","Mu-Hsing Kuo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T15:34:22Z","doi":"10.1109/ijcnn.2006.247064","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.1992.226981","name":"Controlling chaos with a neural network","source":"crossref","abstract":"Chaotic situations may occur in complex systems as a normal operating mode or may accidentally be induced due to a change in some system parameter. The author reports one approach to the use of feedforward networks to dampen chaotic oscillations in Duffing's oscillator. A catastrophic failure of the neural network controller is also studied. For networks with a single hidden layer, a point of diminishing returns was encountered as the size of the hidden layer increased. Suppression improves slightly as the hidden layer size increases. The larger networks take longer to train and are less responsive to changes in oscillator dynamics; however the larger networks recover faster after a transient disturbance in the oscillator dynamics. The majority of the tests were conducted on a network with a single hidden layer of 50 elements. The addition of more hidden layers provided only marginal improvements in suppression at the expense of much longer training times.>","url":"https://doi.org/10.1109/ijcnn.1992.226981","authors":["T.W. Frison"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-01-02T11:19:33Z","doi":"10.1109/ijcnn.1992.226981","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.38007/nn.2020.010103","name":"Multilayer Performance Improvement of Feedforward Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2020.010103","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T03:35:42Z","doi":"10.38007/nn.2020.010103","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1016/0893-6080(88)90285-7","name":"An associative memory network for identifying mingling odors","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90285-7","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T01:05:53Z","doi":"10.1016/0893-6080(88)90285-7","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.21275/v5i6.nov163985","name":"Neural Network Based Detection of Melanoma Skin Cancer","source":"crossref","abstract":"The sensitivity and specificity for diagnosis of melanoma achieved by neural network analysis of Raman spectra were 85% and 99%, respectively. We propose that neural network analysis of near-infrared Fourier transform Raman spectra could provide a novel method for rapid, automated skin cancer diagnosis on unstained skin samples.","url":"https://doi.org/10.21275/v5i6.nov163985","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-06-15T18:01:00Z","doi":"10.21275/v5i6.nov163985","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.2006.246782","name":"A Neural Network based Technique for Automatic Classification of Road Cracks","source":"crossref","abstract":"This paper presents a neural network based technique for the classification of segments of road images into cracks and normal images. The density and histogram features are extracted. The features are passed to a neural network for the classification of images into images with and without cracks. Once images are classified into cracks and non-cracks, they are passed to another neural network for the classification of a crack type after segmentation. Some experiments were conducted and promising results were obtained. The selected results and a comparative analysis are included in this paper.","url":"https://doi.org/10.1109/ijcnn.2006.246782","authors":["J. Bray","B. Verma","Xue Li","W. He"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T11:34:22Z","doi":"10.1109/ijcnn.2006.246782","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.2006.247227","name":"The Modified Differential Evolution and the RBF (MDE-RBF) Neural Network for Time Series Prediction","source":"crossref","abstract":"We develop a modified differential evolution algorithm that produces radial basis function neural network controllers for chaotic systems. This method requires few controlling variables. We examine the result of applying the proposed algorithm to time series prediction, which illustrates the effectiveness of this technique. We apply this algorithm to several computational and real systems including Mackey-Glass time series, the Lorenz attractor, and experimental data obtained from the Henon map. Our experiments indicate that the structural differences between our approach and the other methods existing in the bibliography particularly are well suited to modeling chaotic time series data.","url":"https://doi.org/10.1109/ijcnn.2006.247227","authors":["H. Dhahri","Adel.M. Alimi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T15:34:22Z","doi":"10.1109/ijcnn.2006.247227","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/icit.2008.4608579","name":"Comparison on Zhang neural network and gradient neural network for time-varying linear matrix equation AXB = C solving","source":"crossref","abstract":"For solving online the linear matrix equation AXB = C with time-varying coefficients, this paper presents a special kind of recurrent neural networks by using a design method recently proposed by Zhang et al. Compared with gradient neural networks (abbreviated as GNN, or termed as gradient-based neural networks), the resultant Zhang neural network (termed as such and abbreviated as ZNN hereafter for presentation convenience) is designed based on a matrix-valued error function, instead of a scalar-valued error function. Zhang neural network is deliberately developed in the way that its trajectory could be guaranteed to globally exponentially converge to the time-varying theoretical solution of given linear matrix equation. In addition, Zhang neural network is described by an implicit dynamics, instead of an explicit dynamics usually describing recurrent neural networks. Convergence results of Zhang neural network are presented to show the neural-network performance. In comparison, we develop and simulate the gradient neural network as well, which is exploited to solve online the time-varying linear matrix equation. Computer-simulation results substantiate the theoretical efficacy and superior performance of Zhang neural network for the online solution of time-varying linear matrix equation, especially when using a power-sigmoid activation function.","url":"https://doi.org/10.1109/icit.2008.4608579","authors":["Yunong Zhang","Ke Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-08-28T05:34:49Z","doi":"10.1109/icit.2008.4608579","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.7717/peerj-cs.2976/fig-3","name":"Figure 3: Anomaly detection method based on multimodal neural network.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.2976/fig-3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-30T04:37:54Z","doi":"10.7717/peerj-cs.2976/fig-3","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.7717/peerjcs.1680/fig-9","name":"Figure 9: Results of neural network training, iterations 2,001–4,000.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerjcs.1680/fig-9","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-13T04:21:26Z","doi":"10.7717/peerjcs.1680/fig-9","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.7717/peerjcs.595/fig-7","name":"Figure 7: Competitive neural network architecture used for data classification.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerjcs.595/fig-7","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-08-02T03:14:48Z","doi":"10.7717/peerjcs.595/fig-7","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.14311/nnw.2015.25.020","name":"NEURAL-NETWORK-BASED GENETIC ALGORITHM FOR OPTIMAL KITCHEN FAUCET STYLES","source":"crossref","abstract":"Artificial neural networks (ANNs) are the models of choice in many data classification tasks.In this study, ANN classification models were used to explore user perceptions about kitchen faucet styles and investigate the relations between the overall preferences and kansei word scores of users.The scores given by consumers were obtained via a two-stage questionnaire mentioned in a previous study by the authors.Through the questionnaire, consumers were asked to give scores after examining three-dimensional (3-D) drawings of new product samples created with the help of industrial product designers.Because it was neither practical nor necessary to develop a prototype or a picture of each of the alternative designs, a fractional factorial experimental design similar to Taguchi's L-16 orthogonal array was used.After completing this preparatory work to develop ANNs and obtain the necessary related data, an analysis of variance (ANOVA) was performed to identify the critical factors that affect the accuracy of the ANN model to be used and determine the best factor levels for the ANN model.A genetic algorithm (GA) was then integrated with the ANN model found to be the best and implemented to determine the optimal levels of the design parameters related to product appearance.Lastly, the product categories were classified as unfavorable or favorable, and three products were derived for each category.In comparison with the previously published papers of the authors, the GA integrated with the ANN model was found to be an effective tool for revealing user perceptions in new product development.In regard to the findings of the present work, it can be said that, this technique can be used as an alternative of several complex analytical approaches, in order to explore users' perceptions.","url":"https://doi.org/10.14311/nnw.2015.25.020","authors":["Fehmi Burcin Ozsoydan","Celal Murat Kandemir","Ezgi Aktar Demirtas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-09-29T06:43:31Z","doi":"10.14311/nnw.2015.25.020","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/ijcnn.2006.247357","name":"Incremental Gain Analysis of Chaotic Recurrent Neural Network and Applications in Pattern Association","source":"crossref","abstract":"Chaotic neural networks have been successfully applied in pattern association problems in many research. However there are few in-depth theoretical analysis for such networks, such as stability issues. In this paper, we propose a new type of chaotic recurrent neural network (CRNN) which is more powerful in pattern association comparing to previous work. Furthermore robustness analysis is also presented based on circle theorem, which contributes to provide a theoretical guideline on how to choose the CRNN parameter in different cases. Simulations are also given to verify the results.","url":"https://doi.org/10.1109/ijcnn.2006.247357","authors":["Wu Yilei","Song Qing","Liu Sheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T11:34:22Z","doi":"10.1109/ijcnn.2006.247357","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.17950/ijer/v3s6/606","name":"Artificial Neural Network Model for Friction Stir Processing","source":"crossref","abstract":"Abstract — Friction stir processing (FSP) is an effective means of refining grain size of aluminum alloys. An artificial neural network model (ANN) is made for predicting the grain size of alloys which are processed by FSP. The simulated results from the model show how grain size varies with the process parameters. Keywords—Friction stir processing, ANN, grain size, grain refinement I.","url":"https://doi.org/10.17950/ijer/v3s6/606","authors":["Syed Muhammed Fahd"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-12-24T10:45:10Z","doi":"10.17950/ijer/v3s6/606","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.4018/978-1-6684-2408-7.ch033","name":"Gene Expression Dataset Classification Using Artificial Neural Network and Clustering-Based Feature Selection","source":"crossref","abstract":"With the progression of bioinformatics, applications of GE profiles on cancer diagnosis along with classification have become an intriguing subject in the bioinformatics field. It holds numerous genes with few samples that make it arduous to examine and process. A novel strategy aimed at the classification of GE dataset as well as clustering-centered feature selection is proposed in the paper. The proposed technique first preprocesses the dataset using normalization, and later, feature selection was accomplished with the assistance of feature clustering support vector machine (FCSVM). It has two phases, gene clustering and gene representation. To make the chose top-positioned features worthy for classification, feature reduction is performed by utilizing SVM-recursive feature elimination (SVM-RFE) algorithm. Finally, the feature-reduced data set was classified using artificial neural network (ANN) classifier. When compared with some recent swarm intelligence feature reduction approach, FCSVM-ANN showed an elegant performance.","url":"https://doi.org/10.4018/978-1-6684-2408-7.ch033","authors":["Audu Musa Mabu","Rajesh Prasad","Raghav Yadav"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-17T11:47:50Z","doi":"10.4018/978-1-6684-2408-7.ch033","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1007/3-540-29832-0_1086","name":"Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/3-540-29832-0_1086","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-07-10T11:34:18Z","doi":"10.1007/3-540-29832-0_1086","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.17760/d20385573","name":"DYAN-bicycleGAN","source":"crossref","abstract":"With the rapid development of neural networks and computer vision, video prediction has become a topic of interest. Inspired by the GAN related image-to-image translation network, this work addresses the challenge by modeling the dynamic information in a video sequence into the latent space and inferring the next frames with a domain-to-domain network. In this thesis, a novel video prediction network is presented. This DYAN-BicycleGAN hybrid model is able to predict the frames with the same length as input in one shot. The results show that the model can predict the dynamic information in videos and generate realistic frames.","url":"https://doi.org/10.17760/d20385573","authors":["Huaiyu Zheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-05-10T17:10:59Z","doi":"10.17760/d20385573","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.17760/d20409485","name":"Supervised classification on deep neural network attack toolchains","source":"crossref","abstract":"Deep learning, while an important machine learning technique, is susceptible to adversarial example attacks. Adversarial examples generated by adding perturbations on clean images/video frames can lead to mis-predictions of deep neural networks. Moreover, deep learning/machine learning can be used to deceive humans by generating adversarially falsified media e.g., deepfake attacks. The thesis work will study the above two attack scenarios, i.e., machine-centric adversary and human-centric adversary, with targets to fool ML decisions and human decisions, respectively.We aim to build a generalizable and scalable supervised learning system for classifying attack attributes behind the machine-centric attacks as well as the human-centric attacks. We start from building an integrated Attack Toolchain Library (ATL) with a broad coverage of both machine-centric and human-centric adversaries, as well as through an integrated user interface for greatflexibility and extensibility to serve our downstream tasks. Based on the developed ATL, we further design a meta-classifier pipeline architecture for predicting attack attributes. The proposed overall meta-classifier shows effectiveness in dealing with false alarms and data distribution shift, andgeneralization to both machine-centric and human-centric attacks.--Author's abstract","url":"https://doi.org/10.17760/d20409485","authors":["Yize Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-08-24T14:53:21Z","doi":"10.17760/d20409485","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.14341/dm13111-6994","name":"Figure 4. Architecture of the developed artificial neural network models.","source":"crossref","abstract":"","url":"https://doi.org/10.14341/dm13111-6994","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-11T04:27:42Z","doi":"10.14341/dm13111-6994","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.17816/rmmar632532-4222241","name":"Fig. 6. Cluster N 3 of the sensorimotor neural network","source":"crossref","abstract":"","url":"https://doi.org/10.17816/rmmar632532-4222241","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-08T05:20:05Z","doi":"10.17816/rmmar632532-4222241","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.7717/peerj-cs.3366/table-6","name":"Algorithm 1: Ant colony optimization with graph neural network embeddings.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.3366/table-6","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-09T08:00:28Z","doi":"10.7717/peerj-cs.3366/table-6","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1016/j.automatica.2024.111922","name":"Modelling of memristor networks and the effective memristor","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.automatica.2024.111922","authors":["Anne-Men Huijzer","Arjan van der Schaft","Bart Besselink"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-21T07:25:27Z","doi":"10.1016/j.automatica.2024.111922","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1002/2013rs005247","name":"Ionospheric single-station TEC short-term forecast using RBF neural network","source":"crossref","abstract":"In this article a radial basis function (RBF) neural network improved by Gaussian mixture model is developed to be used for forecasting ionospheric 30 min total electron content (TEC) data given the merits of its nonlinear modeling capacity. In order to understand more about the response of developed network model with respect to stations situated at different latitude, estimated TEC overhead of GPS ground stations BJFS (39.61°N, 115.89°E), WUHN (30.53°N, 114.36°E), and KUNM (25.03°N, 102.80°E) for 6 months in 2011 are used for training data set, validating data and test data set of RBF network model. The performance of the trained model is evaluated at a set of criteria. Our results show that the predicted TEC is in good agreement with observations with mean relative error of about 9% and root-mean-square error of less than 5 total electron content unit, 1 TECU = 1016 el m−2. Our comparison further indicates that RBF network offers a powerful and reliable tool for the design of ionospheric TEC forecast.","url":"https://doi.org/10.1002/2013rs005247","authors":["Z. Huang","H. Yuan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-03-21T22:24:52Z","doi":"10.1002/2013rs005247","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1007/978-3-642-34816-7_3","name":"RBF Neural Network Control Based on Gradient Descent Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-642-34816-7_3","authors":["Jinkun Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-01-24T23:15:56Z","doi":"10.1007/978-3-642-34816-7_3","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1007/978-3-030-90582-8_6","name":"In-Memory Computing with Non-volatile Memristor CAM Circuits","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-030-90582-8_6","authors":["Catherine E. Graves","Can Li","Giacomo Pedretti","John Paul Strachan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-23T13:07:05Z","doi":"10.1007/978-3-030-90582-8_6","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/icnn.1988.23890","name":"Relaxation neural network for nonorthogonal image transforms","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnn.1988.23890","authors":["Daugman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-01-06T16:42:02Z","doi":"10.1109/icnn.1988.23890","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1017/cbo9780511529771.015","name":"Neural Networks and Adaptive Control: Neural Network Models","source":"crossref","abstract":"","url":"https://doi.org/10.1017/cbo9780511529771.015","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-12-22T17:11:07Z","doi":"10.1017/cbo9780511529771.015","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1002/2050-7038.12538/v3/review1","name":"Review for \"The nonlinear autoregressive network with exogenous inputs (NARX) neural network to damp power system oscillations\"","source":"crossref","abstract":"Get your research seenMake an impact with these nine promotional tools. SEO• Use relevant keywords to make your title and abstract clear and easy to search for.• Off-page SEO strategies, like link building, can help get your paper seen. Conferences• Whether you're networking informally or presenting, think about some simple messages to promote your work.","url":"https://doi.org/10.1002/2050-7038.12538/v3/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-07-27T17:06:47Z","doi":"10.1002/2050-7038.12538/v3/review1","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1016/b978-0-12-815254-6.00013-7","name":"Neural Network Black Box Approach to the Modeling and Control of Dynamical Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-12-815254-6.00013-7","authors":["Yury V. Tiumentsev","Mikhail V. Egorchev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-06-21T15:36:10Z","doi":"10.1016/b978-0-12-815254-6.00013-7","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/icece.2008.4769258","name":"A comparative analysis of Feed-forward neural network &amp;#x00026; Recurrent Neural network to detect intrusion","source":"crossref","abstract":"As computer networks are grows exponentially security in computer system has become a foremost issue. Monitoring atypical activity can be one way to detect any violation that impedes computer systems security. Existing methods like statistical models [12] for intrusion detection not perform well whereas Neural network has been proved as an efficient method for intrusion detection [10]. In this paper Feed-forward and Recurrent Neural network is trained by Back propagation training algorithm and using normal data. Performances of these Neural Networks are compared against both normal data and intrusive data.","url":"https://doi.org/10.1109/icece.2008.4769258","authors":["Nipa Chowdhury","Mohammod Abul kashem"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-01-29T16:44:06Z","doi":"10.1109/icece.2008.4769258","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1088/0954-898x/5/2/003","name":"Efficient stereo coding in the multiscale representation*","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/5/2/003","authors":["Zhaoping Li","Joseph Atick"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/5/2/003","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.7717/peerj-cs.1903/fig-5","name":"Figure 5: The structure of the deep learning neural network.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.1903/fig-5","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-25T03:05:55Z","doi":"10.7717/peerj-cs.1903/fig-5","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.46569/20.500.12680/8s45qh205","name":"Neural Network Modeling of the Weather Prediction Task","source":"crossref","abstract":"","url":"https://doi.org/10.46569/20.500.12680/8s45qh205","authors":["Minjeong Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-07T22:15:25Z","doi":"10.46569/20.500.12680/8s45qh205","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.7717/peerjcs.2293/table-4","name":"Table 4: Comparison of human and neural network annotation performance.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerjcs.2293/table-4","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-22T05:11:48Z","doi":"10.7717/peerjcs.2293/table-4","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.70729/ijser18741","name":"Text Recognition using Multilayer Perceptron Neural Network","source":"crossref","abstract":"This work focuses on development of an Offline Hand Written English Character Recognition algorithm based on Artificial Neural Network (ANN). The ANN implemented in this work has single output neuron which shows whether the tested character belongs to a particular cluster or not. The implementation is carried out completely in 'Java' language. Offline handwritten English character recognition is difficult due to variation in shape, slope and size of individual characters. Such variations in handwriting can be handled by better pre-processing and feature extraction techniques.Handwritten character recognition is more difficult process as compared to typed or printed characters.In this paper, we present a handwritten character recognition system in which first of all original image is converted into greyscale image.After that pre-processing steps are applied on that greyscale image.Then individual characters split from word using segmentation.Features are extracted for those characters and multilayer perceptron classifier is used for classification.At last handwritten character is recognized and converted into machine printable form, which will be easier to store and use in future.However, the result showed that the algorithm recognized English alphabet patterns with maximum accuracy of more than 80.00%.","url":"https://doi.org/10.70729/ijser18741","authors":["Khushal Gupta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-07T08:13:46Z","doi":"10.70729/ijser18741","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.14711/thesis-991012994404403412","name":"All-optical neural network with nonlinear activation functions","source":"crossref","abstract":"991012994404403412 HKUST Electronic Theses All-optical neural network with nonlinear activation functions by Zuo Ying thesis 2021 1 online resource (xxiii, 130 pages) : illustrations (some color) Artificial neural networks (ANNs) have now been widely used for industrial applications and also…Read more ›","url":"https://doi.org/10.14711/thesis-991012994404403412","authors":["Ying Zuo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-16T21:38:45Z","doi":"10.14711/thesis-991012994404403412","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1007/978-1-84628-614-8","name":"Neural Network Models","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-84628-614-8","authors":["Philippe De Wilde"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-06-11T00:02:07Z","doi":"10.1007/978-1-84628-614-8","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.31390/gradschool_disstheses.348","name":"A Neural Network Approach to Dependent  *Reliability Estimation.","source":"crossref","abstract":"This research presents the creation of a new model for automating the generation of component and system reliability estimates from simulated field data for tightly coupled systems. The model utilizes the CMAC neural network architecture, which resembles the human cerebellum and is capable of approximating nonlinear functions. An analysis and testing of the network as a tool for reliability prediction of dependent components within an assembly has been performed. In order to evaluate the performance of the model, the network has been tested on simulated data and provided over 90% performance accuracy in learning non-linear functions that represent the dependency between components. This serves as a valuable tool for maintenance personnel faced with important and costly decisions regarding equipment maintenance policies.","url":"https://doi.org/10.31390/gradschool_disstheses.348","authors":["Roya Javadpour"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-13T21:35:52Z","doi":"10.31390/gradschool_disstheses.348","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.7717/peerj-cs.270/fig-1","name":"Figure 1: Artificial neural network architectures used for cancer classification.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.270/fig-1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-04-13T06:23:21Z","doi":"10.7717/peerj-cs.270/fig-1","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.1109/icnn.1996.549025","name":"Exploiting network redundancy for low-cost neural network realizations","source":"crossref","abstract":"A method is presented to optimize a trained neural network for physical realization styles. Target architectures are embedded microcontrollers or standard cell based ASIC designs. The approach exploits the redundancy in the network, required for successful training, to replace the synaptic weighting and the neuron transfer functions by ones that can be implemented with smaller cost. Redundancy indices are used to identify the network elements that are candidates for optimization to be performed by the judicious application of local, behaviour-invariant transformations. The usefulness of the presented approach is illustrated by a image processing application realized in our lab.","url":"https://doi.org/10.1109/icnn.1996.549025","authors":["H. Keegstra","W.J. Jansen","J.A.G. Nijhuis","L. Spaanenburg","H. Stevens","J.T. Udding"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-12-23T20:16:22Z","doi":"10.1109/icnn.1996.549025","addedAt":"2026-09-01T01:48:33.593Z","updatedAt":"2026-09-01T01:48:33.593Z"},{"id":"doi:10.2139/ssrn.5007895","name":"Rsea-Mvgnn: Multi-View Graph Neural Network with Reliable Structural Enhancement and Aggregation","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5007895","authors":["Junyu Chen","Long Shi","Badong Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-02T16:37:34Z","doi":"10.2139/ssrn.5007895","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.32388/tuz29y.3","name":"Flood Prediction by using Artificial Neural Network: A Case Study in Temerloh, Pahang","source":"crossref","abstract":"Floods are natural disasters that can cause significant property damage and sometimes result in loss of life. In Malaysia, floods occur every year, particularly on the East Coast of Peninsular Malaysia, due to the Northeast Monsoon and the impacts of climate change, which can lead to heavy rainfall at the end of the year. Temerloh, a district in Pahang, frequently experiences flooding events, especially between November and January. Despite various efforts in flood mitigation and preparation, the damage to both citizens and property each year results in costs amounting to thousands of Ringgits and the time needed to clean up the aftermath of floods. To address this issue, this research examined the hydrological and meteorological factors contributing to the floods in Temerloh and developed a machine-learning model capable of predicting future flood occurrences. The study utilized a dataset from the National Hydrological Network Management System (SPRHiN), which includes hydrological data and meteorological information for the specific location. The correlation analysis revealed a strong relationship between stream flow and water level to floods, with correlation coefficients (r values) of 0.83 and 0.76, respectively. In contrast, temperature exhibited an inverse relationship with floods, showing a correlation value of -0.28; this suggests that lower temperatures are associated with a higher likelihood of rain and subsequent flooding. The results indicated that the model, developed using an artificial neural network (ANN), achieved an impressive accuracy of 0.9909 and demonstrated strong performance, as evidenced by an area under the receiver operating characteristic (ROC) curve (AUC) value of 0.888. The model also exhibited low error rates, with a mean squared error (MSE) of 0.009 and a root mean squared error (RMSE) of 0.096. Additionally, the R² value of 0.768 and the F1 score of 0.875 indicate that the model possesses high precision and recall. Furthermore, a flood monitoring dashboard was created to provide interactive data visualization. This research is essential for understanding the factors contributing to flooding in Pahang and will offer valuable insights for future studies on floods.","url":"https://doi.org/10.32388/tuz29y.3","authors":["Ahmad Jazli Abdul Rahman","Nor Azuana Ramli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-17T22:17:44Z","doi":"10.32388/tuz29y.3","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1002/brb3.70085/v1/decision1","name":"Decision letter for \"Neural Determinants of Sedentary Lifestyle in Older Adults: A Brain Network Analysis\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/brb3.70085/v1/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-09T16:04:23Z","doi":"10.1002/brb3.70085/v1/decision1","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.21203/rs.3.rs-4273139/v1","name":"Prediction Model For Digital Image Tampering Using Customized Deep Neural Network Techniques","source":"crossref","abstract":"Abstract Image tampering detection is a critical area of research, given the widespread use of manipulated images for deceptive purposes. Convolutional Neural Networks (CNNs) have shown significant potential in automating the identification of tampered images. This paper presents customized deep learning model to detect tampering class with comparative analysis of CNN architectures - ResNet50V2, InceptionNetV3, MobileNetV2, and the proposed CNN, for image tampering detection. The proposed approach encompasses a dataset comprising four distinct classes: copy-move, inpaint, splicing, and normal images. This study sheds light on the comparative strengths and weaknesses of these CNN architectures. The dataset encompasses the key tampered classes, offering a holistic assessment of each model's ability to identify various tampering techniques. The custom CNN architecture is specifically tailored for this task, aiming to evaluate its efficiency compared to the established CNNs. Metrics for training and evaluation are standardized to generate equitable comparisons, encompassing performance indicators such as accuracy, precision, recall, and F1-score.This research contributes the knowledge in the field of image tampering detection, offering a comprehensive evaluation of multiple CNN architectures. Additionally, the effectiveness of separable convolutional layers is explored in deep neural networks, showcasing their potential to enhance scalability and effectiveness across various tasks in machine learning and computer vision. The proposed model, designed with separable convolution layers, exhibits superior validation accuracy and training accuracy compared to the other models under evaluation. Notably, The proposed customized model achieved an impressive F1 score of 96%, highlighting its proficiency in accurately detecting tampered regions within images while minimizing false positives.","url":"https://doi.org/10.21203/rs.3.rs-4273139/v1","authors":["Sachin Saxena","Archana Singh","Shailesh Tiwari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-13T19:32:25Z","doi":"10.21203/rs.3.rs-4273139/v1","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.2139/ssrn.4864049","name":"NERD: Neural Network for Edict of Risky Data Streams","source":"crossref","abstract":"Cyber incidents can have a wide range of cause from a simple connection loss to an insistent attack. Once a potential cyber security incidents and system failures have been identified, deciding how to proceed is often complex. Especially, if the real cause is not directly in detail determinable. Therefore, we developed the concept of a Cyber Incident Handling Support System. The developed system is enriched with information by multiple sources such as intrusion detection systems and monitoring tools. It uses over twenty key attributes like sync-package ratio to identify potential security incidents and to classify the data into different priority categories. Afterwards, the system uses artificial intelligence to support the further decision-making process and to generate corresponding reports to brief the Board of Directors. Originating from this information, appropriate and detailed suggestions are made regarding the causes and troubleshooting measures. Feedback from users regarding the problem solutions are included into future decision-making by using labelled flow data as input for the learning process. The prototype shows that the decision making can be sustainably improved and the Cyber Incident Handling process becomes much more effective.","url":"https://doi.org/10.2139/ssrn.4864049","authors":["Peter Hillmann","Sandro Passarelli","Cem Gündogan","Lars Stiemert","Matthias Schopp"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-21T09:30:04Z","doi":"10.2139/ssrn.4864049","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.2139/ssrn.4891803","name":"Neural Network Controller for Hybrid Energy Management System Applied to Electric Vehicles","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4891803","authors":["Alex  do Nascimento Ribeiro","Daniel  Mauricio Muñoz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-11T12:18:56Z","doi":"10.2139/ssrn.4891803","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1117/12.3073572","name":"Front Matter: Volume 13652","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3073572","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-11T23:42:46Z","doi":"10.1117/12.3073572","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1017/qpb.2024.2.pr9","name":"Recommendation: Quantitative analysis of lateral root development with time-lapse imaging and deep neural network — R1/PR9","source":"crossref","abstract":"","url":"https://doi.org/10.1017/qpb.2024.2.pr9","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-13T03:07:40Z","doi":"10.1017/qpb.2024.2.pr9","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.7554/elife.90597.2.sa0","name":"Reviewer #3 (Public Review): Hippocampome.org v2.0: a knowledge base enabling data-driven spiking neural network simulations of rodent hippocampal circuits","source":"crossref","abstract":"","url":"https://doi.org/10.7554/elife.90597.2.sa0","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-26T06:25:53Z","doi":"10.7554/elife.90597.2.sa0","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.21203/rs.3.rs-4210118/v1","name":"A novel approach for Plant disease Classification through Neural Network-Based Color Feature Analysis","source":"crossref","abstract":"Abstract plant disease identification using machine vision, which is a challenge in terms of maximizing both the quality and quantity of plant growth. The infection makes plants susceptible to disease. This needs continuous monitoring by experts, which is prohibitively expensive in large farms, but in some instances, erroneous observations by farmers culminate in poor diagnoses. Consequently, we need a fast and accurate plant disease diagnosis predicted to increase the area under cultivation, eliminate heavy losses, and ensure high accuracy. The focus must be on identifying early symptoms of plant disease using computer vision. In order to solve this problem, deep learning can combine machine learning and pattern recognition, two hottest topics in this field. We propose a novel method to identify different plant diseases using deep convolutional neural networks (CNNs). In this study, we propose an image-based classification approach for rice plant diseases, focusing solely on color features. We investigated 12 distinct color spaces and derived 4 features from each color channel, resulting in a total of 48 features. The accuracy of this model is much higher than that of traditional machine learning models. Using the best-performing model, we achieved a classification accuracy of 96.03%. The simulation results show that the proposed method for identifying plant diseases is effective and feasible.","url":"https://doi.org/10.21203/rs.3.rs-4210118/v1","authors":["Archana KS","Arun S"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-14T05:25:26Z","doi":"10.21203/rs.3.rs-4210118/v1","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1002/we.2976/v2/review1","name":"Review for \"Volt/VAr Regulation of the West Mediterranean Regional Electrical Grids Using SVC/STATCOM Devices With Neural Network Algorithms\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/we.2976/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-25T16:09:21Z","doi":"10.1002/we.2976/v2/review1","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1109/ijcnn60899.2024.10650675","name":"Real-Time spike sorting using an optimized STDP Spiking Neural Network on FPGA","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn60899.2024.10650675","authors":["Jérémy Cheslet","Marie Bernert","Romain Beaubois","Blaise Yvert","Timothée Lévi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-09T17:35:05Z","doi":"10.1109/ijcnn60899.2024.10650675","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1109/icccnt61001.2024.10724438","name":"Multimodal Fusion for Abusive Speech Detection Using Liquid Neural Networks and Convolution Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icccnt61001.2024.10724438","authors":["Ks Paval","Vishnu Radhakrishnan","Km Krishnan","G Jyothish Lal","B Premjith"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-04T23:06:46Z","doi":"10.1109/icccnt61001.2024.10724438","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.2139/ssrn.4994846","name":"Deep Neural Network-Aided Radio Frequency Fingerprinting for Identification of Near Field Communication Tags","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4994846","authors":["Woongsup Lee","Seon Yeob Baek"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-21T21:37:49Z","doi":"10.2139/ssrn.4994846","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.2139/ssrn.4722754","name":"Forecasting precious metals price based on artificial neural network trained by Lévy flight optimization algorithm","source":"crossref","abstract":"Artificial neural networks are popular data-driven models extensively used for predicting the prices of precious metals. This study suggests an optimized artificial neural network model specifically designed for monthly price of precious metals forecasting. For this purpose, the Lévy flight optimization algorithm is presented to adjust the weights and biases involved in the proposed artificial neural network. In a groundbreaking approach within the time series forecasting literature, we enhance the precision of short-term forecasts by organizing the features of the optimized neural network structure using diverse precious metals. To compare the efficiency of the presented forecasting model, we consider three models, autoregressive integrated moving average, support vector machine, and random forest. The collation results indicate that the artificial neural network optimized by Lévy flight algorithm outperforms the other prediction models in terms of accuracy. This model offers a unique approach to predicting the precious metals price and can be applied to&lt;br&gt;different time series beyond what has been studied in other research.","url":"https://doi.org/10.2139/ssrn.4722754","authors":["Farshid Mehrdoust","Maryam Noorani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-11T11:54:55Z","doi":"10.2139/ssrn.4722754","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1007/s00521-024-09721-y","name":"Reinforcement learning (RL)-based semantic segmentation and attention based backpropagation convolutional neural network (ABB-CNN) for breast cancer identification and classification using mammogram images","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-024-09721-y","authors":["Neha Thakur","Pardeep Kumar","Amit Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-11T13:01:47Z","doi":"10.1007/s00521-024-09721-y","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1145/3665138","name":"Efficient Automation of Neural Network Design: A Survey on Differentiable Neural Architecture Search","source":"crossref","abstract":"In the past few years, Differentiable Neural Architecture Search (DNAS) rapidly imposed itself as the trending approach to automate the discovery of deep neural network architectures. This rise is mainly due to the popularity of DARTS (Differentiable ARchitecTure Search), one of the first major DNAS methods. In contrast with previous works based on Reinforcement Learning or Evolutionary Algorithms, DNAS is faster by several orders of magnitude and uses fewer computational resources. In this comprehensive survey, we focused specifically on DNAS and reviewed recent approaches in this field. Furthermore, we proposed a novel challenge-based taxonomy to classify DNAS methods. We also discussed the contributions brought to DNAS in the past few years and its impact on the global NAS field. Finally, we concluded by giving some insights into future research directions for the DNAS field.","url":"https://doi.org/10.1145/3665138","authors":["Alexandre Heuillet","Ahmad Nasser","Hichem Arioui","Hedi Tabia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-15T11:33:30Z","doi":"10.1145/3665138","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1016/j.neunet.2023.11.051","name":"UTDNet: A unified triplet decoder network for multimodal salient object detection","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2023.11.051","authors":["Fushuo Huo","Ziming Liu","Jingcai Guo","Wenchao Xu","Song Guo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-24T11:44:51Z","doi":"10.1016/j.neunet.2023.11.051","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1109/inocon60754.2024.10511642","name":"Neural Touch for Enhanced Wearable Haptics with Recurrent Neural Network and IoT-Enabled Tactile Experiences","source":"crossref","abstract":"","url":"https://doi.org/10.1109/inocon60754.2024.10511642","authors":["K. Radhakrishna","D. Satyaraj","Hanumaji Kantari","V. Srividhya","R. Tharun","S. Srinivasan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-06T13:20:54Z","doi":"10.1109/inocon60754.2024.10511642","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.21203/rs.3.rs-3973244/v1","name":"A Prediction Model for Air Pollution using Artificial Neural Network and Multiple Linear Regression","source":"crossref","abstract":"Abstract O ver the past few decades, air pollution and preventive measures have proven scientifically challenging and the issue is still unending on a worldwide scale. The number of contaminants in the air is increasing daily as a result of the expanding population and the settling of more people in metropolitan regions. They have an impact on people's respiratory and cardiovascular systems, which raises the population's risk of disease and increases mortality. To better enhance public health, several attempts have been made by governmental organizations to comprehend and forecast the Air Quality Index. Without a doubt, the most crucial stage in prediction is the creation of a predictive model of the air quality, which will aid in environmental management and raise public awareness. The most important component of tracking air pollution is air quality prediction. Many methods will be useful in developing an effective model for pollution prediction. The best approach for prediction is to use an artificial neural network. Therefore, this study is conducted by gathering data on air pollutants for the U.P. state cities of Meerut and Ghaziabad and creating an optimum model for the air quality forecast.","url":"https://doi.org/10.21203/rs.3.rs-3973244/v1","authors":["Lokesh Kumar","Gaurav Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-22T10:22:49Z","doi":"10.21203/rs.3.rs-3973244/v1","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1007/978-3-031-39477-5_9","name":"Neural Network Architectures","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-39477-5_9","authors":["Gerald Friedland"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-12-01T06:04:04Z","doi":"10.1007/978-3-031-39477-5_9","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1109/tgrs.2024.3466952/v1/decision1","name":"Decision letter for \"Optimizing Satellite-Based Latent Heating Rate Profiling Using a Convolutional Neural Network Heating (CNNH) Algorithm\"","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tgrs.2024.3466952/v1/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-21T22:51:12Z","doi":"10.1109/tgrs.2024.3466952/v1/decision1","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.31237/osf.io/uynsj","name":"Investigating attention manipulation in behavioural data using Hierarchical Gaussian Filter and neural network models","source":"crossref","abstract":"Attention is a critical cognitive process that has been hypothesized to enable the brain to selectivelyfocus on relevant stimuli while filtering out distractions, thereby optimizing the allocation of limitedcomputational resources. Within the predictive coding framework, attention is conceptualized as amechanism that enhances the precision of sensory predictions, thereby reducing prediction errorsand improving cognitive efficiency. This thesis investigates attention manipulation in behavioral datathrough the application of the Hierarchical Gaussian Filter (HGF) and neural network models, with afocus on how diverted attention affects precision, and therefore surprise optimization, and difficultyin perceptual tasks. Using the HGF framework, we modeled hierarchical inference processes, exam-ining how tonic volatilities of the higher levels as well as expected precisions and expected meansof the models capture attentional differences under full and diverted attention conditions. The studyalso introduced contrast as a proxy for task difficulty, providing a quantifiable measure of the cognitive load associated with diverted attention. The neural network models were employed to explore weight distributions and saliency maps, offering a complementary perspective on how attention influences neural representations. While the neural network was able to identify substantial differences in the two attention conditions, albeit at the group level, the results from HGF models of indivindual participants revealed only a weak correlation between model parameters and actual attentional differences, suggesting that the models struggled to fully capture the complexity of attentional shifts between the two conditions. The findings underscore the challenges in using computational models to infer cognitive processes like attention, particularly when dealing with subtle variations in task difficulty and attention diversion.","url":"https://doi.org/10.31237/osf.io/uynsj","authors":["Abdullah Al Saqib Majumder"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-09T18:22:48Z","doi":"10.31237/osf.io/uynsj","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.52783/jes.7946","name":"Neural Network-Based Traffic Control System","source":"crossref","abstract":"Effective traffic management is essential for modern cities, as it helps to alleviate congestion and enhance mobility. This research proposes a novel approach to predicting traffic flow, utilizing a combination of advanced deep learning techniques. The model integrates spatial feature extraction, temporal dependency modeling, and attention mechanisms to provide accurate and interpretable predictions. By leveraging the strengths of different deep learning architectures, the proposed framework achieves significant improvements in prediction accuracy and efficiency compared to traditional models. The results of this study demonstrate the potential of hybrid deep learning models to address the complexities of modern traffic systems and highlight the importance of continued research in this area. Furthermore, the proposed framework's ability to provide real-time predictions makes it a valuable tool for intelligent traffic management systems, enabling cities to optimize their traffic flow and reduce congestion.","url":"https://doi.org/10.52783/jes.7946","authors":["Gauri V. Sonawane"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-21T10:17:48Z","doi":"10.52783/jes.7946","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.36227/techrxiv.171259831.10334526/v2","name":"A Convolutional Neural Network-Based Method for Accurate Computation of Scattered Fields From Reconfigurable Intelligent Surfaces","source":"crossref","abstract":"The cell-to-cell coupling in a reconfigurable intelligent surface (RIS) is very different from a periodic structure, where coupling effects can be precisely evaluated via full-wave analysis with periodic boundary conditions. We propose a novel method based on convolutional neural networks (CNNs), to predict the contribution of mutual coupling on the near-zone tangential electric field of every RIS unit cell that characterizes its scattering. Our CNN model incorporates an attention mechanism based on the squeeze-and-excitation block module, enhancing its capability to discern and quantify coupling effects, especially from neighboring cells surrounding the unit cell of interest. The predictions of the model enable the computation of RIS scattered fields, fully accounting for the aperiodic nature of an RIS. Comparisons to finite-element analysis confirm that our computed fields are accurate at any point and for any RIS configuration. Furthermore, our trained model can be retrained through transfer learning, to accurately and efficiently predict cell-to-cell coupling under different incident wave conditions, utilizing only a reduced number of training data. Therefore, the proposed method is a valuable tool for various practical applications, such as synthesizing RIS scattered field patterns and evaluating the performance of RIS-enabled channels.","url":"https://doi.org/10.36227/techrxiv.171259831.10334526/v2","authors":["Yuanzhi Liu","Costas Sarris"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-23T09:44:07Z","doi":"10.36227/techrxiv.171259831.10334526/v2","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1088/2632-2153/ad7e7a/v1/review1","name":"Review for \"A PNP ion channel deep learning solver with local neural network and finite element input data\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2632-2153/ad7e7a/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-24T17:15:02Z","doi":"10.1088/2632-2153/ad7e7a/v1/review1","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.21203/rs.3.rs-4949296/v1","name":"Broken Tooth Gear Fault Detection Using Vibration Signals Based on Convolutional Neural Network","source":"crossref","abstract":"Abstract Gear faults are a major concern in industrial settings, leading to performance degradation and potential system failures. This paper explores the use of Convolutional Neural Networks (CNNs) for broken tooth fault detection in gear systems. Traditional methods for fault detection rely on manual feature extraction from vibration signals, which can be time-consuming and may not capture all relevant information. CNNs, on the other hand, can automatically learn complex patterns from data, making them well-suited for this task. In this paper we develop a computationally tractable deep learning (DL) based CNN model that can be used for broken tooth fault diagnosis in various industrial settings, irrespective of the type of gearbox or gears being used. The authors further compare the performance of developed CNN model with traditional signal processing techniques and Support Vector Machine (SVM)-based classification. The CNN model achieved superior accuracy (98.6%) in distinguishing between broken and healthy teeth across various operating conditions for one experimental setup. For a second setup with a less severe broken tooth fault, the accuracy was 93%. In contrast, SVM models achieved a maximum accuracy of 90.7% using manually selected features. These findings underscore the superiority of the proposed deep learning (DL) based CNN model for broken teeth gear fault detection. Moreover, it exhibits greater resilience to fluctuations in operating conditions and fault types compared to conventional techniques. Comparisons with established deep learning models such as VGG16, AlexNet etc. demonstrate that the proposed model surpasses all others in terms of classification accuracy.","url":"https://doi.org/10.21203/rs.3.rs-4949296/v1","authors":["Priyom Goswami","Rajiv Nandan Rai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-24T14:01:44Z","doi":"10.21203/rs.3.rs-4949296/v1","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.2139/ssrn.4938900","name":"A Multiple Transferable Neural Network Method with Domain Decomposition for Elliptic Interface Problems","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4938900","authors":["Tianzheng Lu","Lili Ju","Liyong Zhu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-27T23:19:03Z","doi":"10.2139/ssrn.4938900","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.2139/ssrn.4939905","name":"Automatic Modulation Classification Using Convolutional Neural Network and Support Vector Machine","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4939905","authors":["Shanza Nasir","Shahzad Amin Sheikh","fahad mumtaz malik"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-28T22:17:42Z","doi":"10.2139/ssrn.4939905","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1117/12.3050128","name":"Research of improvement of multilingual scientific translation model based on neural network attention mechanism","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3050128","authors":["jing zhao","hongjing chang","Xuguang Zhang","chunmao li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-08T16:12:17Z","doi":"10.1117/12.3050128","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.2139/ssrn.4761198","name":"Enhancing Speaker Diarization with Deep Neural Network Embeddings and Spectral Clustering","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4761198","authors":["Yaqian Li","Xiaolong Zhang","Haibin Li","Wengming Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-20T18:58:51Z","doi":"10.2139/ssrn.4761198","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.21203/rs.3.rs-4613466/v1","name":"A Comparative Study of Machine Learning and Neural Network\nModels in Short-term Market Prediction","source":"crossref","abstract":"Abstract The prediction of the stock market and the prices of other commodities like crude oil, 1 constitutes a challenging task. Recently, the rapid progress in the field of Machine Leaning (ML), 2 led to an increased interest in applying ML techniques to market price predictions. In this study, 3 we conduct a comprehensive comparative analysis of the performance of 15 different ML models in 4 predicting the close prices of crude oil futures. These models include an Auto-Regressive Integrated 5 Moving Average (ARIMA) model, the Meta Prophet Library, a simple Recurrent Neural Network 6 (RNN), a Long-Short Term Memory (LSTM), a Gated Recurrent Unit (GRU), a Bi-directional LSTM 7 (BLSTM), a Bi-directional GRU (BGRU) and a number of hybrid models, including an LSTM-BGRU 8 and a BLSTM-BGRU. In addition, we evaluate the effectiveness of using Denoising Autoencoders 9 (DAE) in enhancing the performance of the networks by evaluating hybrid models with DAE layers, 10 including DAE-LSTM, DAE-BLSTM, DAE-GRU, DAE-BGRU, DAE-LSTM-GRU and DAE-BLSTM- 11 BGRU. In our analysis, we focus on short-term predictions dedicated for day trading. We compare 12 the performance of these models using the Root Mean Square Error (RMSE), Mean Absolute Error 13 (MAE), Mean Absolute Error Percentage (MAPE) and the R2. We find that the BGRU model yields the 14 best performance, with the GRU model not far behind. We also find that hybrid models containing 15 BGRUs or GRUs tend to perform better than other hybrid models. We find mixed evidence vis-a-vis 16 the effectiveness of DAEs in improving the performance of networks, where in some models the 17 performance improves, whereas for others the performance deteriorates. We find that the performance 18 of all models deteriorate when predicting sharp and sudden changes in prices. The key takeaway of 19 this study is that BGRUs, and to a lesser extent GRUs, seem to be the best route to follow in applying 20 AI/Ml to the task of market prediction.","url":"https://doi.org/10.21203/rs.3.rs-4613466/v1","authors":["Fayez Abu-Ajamieh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-21T18:06:58Z","doi":"10.21203/rs.3.rs-4613466/v1","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.2139/ssrn.5064645","name":"Automatic Grading of Barley Grain for Brewery Industries Using Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5064645","authors":["Debalke Embeyale","Yao-Tien Chen","Yaregal Assabie"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-19T18:38:06Z","doi":"10.2139/ssrn.5064645","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1038/s41598-024-59276-0","name":"Practical application of quantum neural network to materials informatics","source":"crossref","abstract":"Abstract Quantum neural network (QNN) models have received increasing attention owing to their strong expressibility and resistance to overfitting. It is particularly useful when the size of the training data is small, making it a good fit for materials informatics (MI) problems. However, there are only a few examples of the application of QNN to multivariate regression models, and little is known about how these models are constructed. This study aims to construct a QNN model to predict the melting points of metal oxides as an example of a multivariate regression task for the MI problem. Different architectures (encoding methods and entangler arrangements) are explored to create an effective QNN model. Shallow-depth ansatzs could achieve sufficient expressibility using sufficiently entangled circuits. The “linear” entangler was adequate for providing the necessary entanglement. The expressibility of the QNN model could be further improved by increasing the circuit width. The generalization performance could also be improved, outperforming the classical NN model. No overfitting was observed in the QNN models with a well-designed encoder. These findings suggest that QNN can be a useful tool for MI.","url":"https://doi.org/10.1038/s41598-024-59276-0","authors":["Hirotoshi Hirai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-13T02:01:55Z","doi":"10.1038/s41598-024-59276-0","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1016/j.neunet.2024.106339","name":"DCDLN: A densely connected convolutional dynamic learning network for malaria disease diagnosis","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106339","authors":["Zhijun Zhang","Cheng Ding","Mingyang Zhang","YaMei Luo","Jiajie Mai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-29T15:40:14Z","doi":"10.1016/j.neunet.2024.106339","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1080/0954898x.2024.2359609","name":"SJFO: Sail Jelly Fish Optimization enabled VM migration with DRNN-based prediction for load balancing in cloud computing","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2024.2359609","authors":["Rajesh Rathinam","Premkumar Sivakumar","Sivakumar Sigamani","Ishwarya Kothandaraman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-03T14:44:39Z","doi":"10.1080/0954898x.2024.2359609","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1007/s00521-024-10878-9","name":"Chicken moth flame optimization and region-based convolution neural network for water quality prediction","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-024-10878-9","authors":["D. Justin Jose","C. Helen Sulochana"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-19T08:37:22Z","doi":"10.1007/s00521-024-10878-9","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1145/3673277.3673314","name":"Research on the Application of Chemical Process Fault Diagnosis Methods Based on Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3673277.3673314","authors":["Kongpeng Wei","Hongbin Gu","Xiaolong Li","Bo Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-30T18:34:42Z","doi":"10.1145/3673277.3673314","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1145/3714334.3714338","name":"Research and Application of E-commerce Marketing Fraud Detection Method Based on Graph Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3714334.3714338","authors":["Hui Zhu","Weijie Zhong","Zihao Huang","Zhenyu Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-07T06:34:31Z","doi":"10.1145/3714334.3714338","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1088/1741-2552/ad5404","name":"Blindly separated spontaneous network-level oscillations predict corticospinal excitability","source":"crossref","abstract":"Abstract Objective. The corticospinal responses of the motor network to transcranial magnetic stimulation (TMS) are highly variable. While often regarded as noise, this variability provides a way of probing dynamic brain states related to excitability. We aimed to uncover spontaneously occurring cortical states that alter corticospinal excitability. Approach. Electroencephalography (EEG) recorded during TMS registers fast neural dynamics—unfortunately, at the cost of anatomical precision. We employed analytic Common Spatial Patterns technique to derive excitability-related cortical activity from pre-TMS EEG signals while overcoming spatial specificity issues. Main results. High corticospinal excitability was predicted by alpha-band activity, localized adjacent to the stimulated left motor cortex, and suggesting a travelling wave-like phenomenon towards frontal regions. Low excitability was predicted by alpha-band activity localized in the medial parietal–occipital and frontal cortical regions. Significance. We established a data-driven approach for uncovering network-level neural activity that modulates TMS effects. It requires no prior anatomical assumptions, while being physiologically interpretable, and can be employed in both exploratory investigation and brain state-dependent stimulation.","url":"https://doi.org/10.1088/1741-2552/ad5404","authors":["Maria Ermolova","Johanna Metsomaa","Paolo Belardinelli","Christoph Zrenner","Ulf Ziemann"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-04T22:28:25Z","doi":"10.1088/1741-2552/ad5404","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1101/2024.08.13.607720","name":"Deep graph convolutional neural network for one-dimensional hepatic vascular haemodynamic prediction","source":"crossref","abstract":"Abstract Hepatic vascular hemodynamics is an important reference indicator in the diagnosis and treatment of hepatic diseases. However, Method based on Computational Fluid Dynamics(CFD) are difficult to promote in clinical applications due to their computational complexity. To this end, this study proposed a deep graph neural network model to simulate the one-dimensional hemodynamic results of hepatic vessels. By connecting residuals between edges and nodes, this framework effectively enhances network prediction accuracy and efficiently avoids over-smoothing phenomena. The graph structure constructed from the centerline and boundary conditions of the hepatic vasculature can serve as the network input, yielding velocity and pressure information corresponding to the centerline. Experimental results indicate that our proposed method achieves higher accuracy on a hepatic vasculature dataset with significant individual variations and can be extended to applications involving other blood vessels. Following training, errors in both the velocity and pressure fields are maintained below 1.5%. The trained network model can be easily deployed on low-performance devices and, compared to CFD-based methods, can output velocity and pressure along the hepatic vessel centerline at a speed three orders of magnitude faster. Author summary When using deep learning methods for hemodynamic analysis, simple point cloud data cannot express the real geometric structure of the blood vessels, and it is necessary for the network to have additional geometric information extraction capability. In this paper, we use graph structure to express the structure of hepatic blood vessels, and deep graph neural network to predict the corresponding hemodynamic parameters. The graph structure can effectively express the geometric information of hepatic blood vessels and the topology of branch blood vessels, which can effectively improve the prediction accuracy with strong geometric generalisation ability. The results show that the method achieves the highest prediction accuracy in the one-dimensional hepatic vessel blood flow simulation dataset, and the experimental results on the human aorta also show that our method can be effectively applied to the blood flow simulation of other vascular organs.","url":"https://doi.org/10.1101/2024.08.13.607720","authors":["Weiqng Zhang","Shuaifeng Shi","Quan Qi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-16T21:35:14Z","doi":"10.1101/2024.08.13.607720","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.18699/bgrs2024-12.3-17","name":"Enhancing biomedical knowledge discovery through hybrid text-mining and graph neural network approaches in ANDSystem","source":"crossref","abstract":"","url":"https://doi.org/10.18699/bgrs2024-12.3-17","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-25T13:20:38Z","doi":"10.18699/bgrs2024-12.3-17","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.2139/ssrn.4703048","name":"Optimal Li-Ion Battery Charging with a Hybrid Model Based on Physical Modeling and a Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4703048","authors":["Milad Nouri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-22T23:07:46Z","doi":"10.2139/ssrn.4703048","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.21203/rs.3.rs-3942174/v1","name":"Copula Tubular Quantum Based Spearman Deep Neural for Influential Node Tracing in Social Network","source":"crossref","abstract":"Abstract Social networks are one the foremost origins of information transmission at present. Nevertheless, not all nodes in social networks are indistinguishable. As a matter of fact, certain nodes are said to be more influential than others, or to be more specific, their information gravitates to proliferate more. Identifying the most influential nodes in a social network called as the Influence Maximization problem remains one of the hot issue with the evolution of Internet and social media. Several methods have been proposed to identify influential nodes in composite networks, ranging from parallel algorithm to distribution difference and non-overlapping communities. However, most of the previous methods do not take into account error involved in overlapping communities in social network. To address this issue, in this work, a Copula Tubular Neighborhood and Quantum-based Spearman Deep Neural Network (CTNQ-SDNN) for influential node tracing in social network is proposed. The CTNQ-SDNN method is split into three sections. First, computationally efficient nodes are identified by employing Copula Probability Node Pre-processing model. Then, with the identification of effective nodes, accurate feature extraction is made by means of Tubular Neighborhood Intensity-based Feature extraction model. Finally, influential node selection and tracing in case of tie or overlapping communities with the purpose of reducing error rate is proposed by utilizing Spearman Deep Neural Influential Node Tracing model. Experimental results on telecom dataset social networks, comparing our proposed method against state-of-the-art methods in current literature, indicates our method to be efficient and robust in tackling the influence maximization issue even in case of tie or overlapping communications in social network via error rate.","url":"https://doi.org/10.21203/rs.3.rs-3942174/v1","authors":["Vimalkumar P","Balasubramanian C"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-19T18:21:10Z","doi":"10.21203/rs.3.rs-3942174/v1","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.22541/essoar.172202798.82044672/v1","name":"PEGSGraph: a Graph Neural Network for fast earthquake characterization based on Prompt ElastoGravity Signals","source":"crossref","abstract":"State-of-the-art earthquake early warning systems use the early records of seismic waves to estimate the magnitude and location of the seismic source before the shaking and the tsunami strike. Because of the inherent properties of early seismic records, those systems systematically underestimate the magnitude of large events, which results in catastrophic underestimation of the subsequent tsunamis. Prompt elastogravity signals (PEGS) are low-amplitude, light-speed signals emitted by earthquakes, which are highly sensitive to both their magnitude and focal mechanism. Detected before traditional seismic waves, PEGS have the potential to produce unsaturated magnitude estimates faster than state-of-the-art systems. Accurate instantaneous tracking of large earthquake magnitude using PEGS has been proven possible through the use of a Convolutional Neural Network (CNN). However, the CNN architecture is sub-optimal as it does not allow to capture the geometry of the problem. To address this limitation, we design PEGSGraph, a novel deep learning model relying on a Graph Neural Network (GNN) architecture. PEGSGraph accurately estimates the magnitude of synthetic earthquakes down to Mw 7.6-7.7 and determines their focal mechanisms (thrust, strike-slip or normal faulting) within 70 seconds of the event’s onset, offering crucial information for predicting potential tsunami wave amplitudes. Our comparative analysis on Alaska and Western Canada data shows that the GNN outperforms the CNN, especially on test samples with low signal-to-noise ratios, providing more reliable rapid magnitude estimates and enhancing tsunami warning reliability.","url":"https://doi.org/10.22541/essoar.172202798.82044672/v1","authors":["Céline Hourcade","Kévin Juhel","Quentin Bletery"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-26T17:06:40Z","doi":"10.22541/essoar.172202798.82044672/v1","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.26434/chemrxiv-2024-10h93","name":"Precise estimation of activation energies in gas-phase chemical reactions via artificial neural network","source":"crossref","abstract":"Various machine learning (ML) models are presented in this study, aiming to forecast the barrier heights (BHs) of gas-phase chemical reactions. The input features utilized in six distinct models were obtained from the structural and thermodynamic attributes of molecules, encompassing enthalpy, topological indices, and Morgan fingerprints derived from SMILES, using a dataset consisting of 5040 decomposition reaction records sourced from the Gas Phase Organic Chemistry database. Evaluating the effectiveness of the models included the application of essential metrics such as coefficient of determination, mean absolute error, and root mean square error. It is worth noting that artificial neural networks outperform the other models in this regard. Then we utilized Morgan fingerprints of different dimensions as inputs for the neural network models and conducted training with varying numbers of hidden layers. This endeavor led to slight improvements in the performance of gas-phase decomposition reactions, resulting in an average determination coefficient of 0.965 and a mean absolute error of 0.079 eV. Subsequently, the model was subjected to retraining using a comprehensive dataset comprising a wide range of chemical reactions. The results indicate that the artificial neural network approach has the capacity to generalize and adjust to a wider range of chemical reactions.","url":"https://doi.org/10.26434/chemrxiv-2024-10h93","authors":["Guo-Jin Cao","Sheng-Jie Lu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-30T00:54:01Z","doi":"10.26434/chemrxiv-2024-10h93","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.26434/chemrxiv-2024-jlwh5","name":"Graph neural network for 3-dimensional structures including dihedral angles for molecular property prediction","source":"crossref","abstract":"The prediction of molecular properties using graph neural network (GNN) based approaches has attracted great attention in recent years. Topological molecular graphs are commonly used for representing molecules in machine learning (ML). However, the challenge is to utilize the complete geometry information, like, bonds, angles and dihedral angles while processing a molecular graph. In this work we present predictive GNN accounting three-dimensional molecular structures including the dihedral angles (GNN3Dihed) in a systematic manner. Additionally, we demonstrate that the usage of autoencoders to generate latent space embeddings for usually sparse atomic and bond vectors reduces the number of parameters in the message passing stage while not reducing performance. We compare the performance of GNN3Dihed with state-of-the-art baselines on several tasks (regression and classification), e.g., solubility prediction, toxicity prediction, binding affinity, and quantum mechanical property prediction, and showed that the present architecture often outperforms other models–demonstrating the importance of 3D structural information for ML in chemistry.","url":"https://doi.org/10.26434/chemrxiv-2024-jlwh5","authors":["Sri Abhirath Reddy Sangala","Shampa Raghunathan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-13T07:34:42Z","doi":"10.26434/chemrxiv-2024-jlwh5","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1002/eng2.12866/v2/review1","name":"Review for \"Diagnosis of glaucoma using multi‐scale attention block in convolution neural network and data augmentation techniques\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/eng2.12866/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-13T17:19:47Z","doi":"10.1002/eng2.12866/v2/review1","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.2139/ssrn.4904035","name":"Multi-Patch Isogeometric Convolution Hierarchical Deep-Learning Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.4904035","authors":["Lei Zhang","Chanwook Park","Thomas J.R. Hughes","Wing Kam Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-24T08:51:34Z","doi":"10.2139/ssrn.4904035","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.26907/1562-5419-2024-27-4-598-655","name":"Neural Network Architecture of Embodied Intelligence","source":"crossref","abstract":"In recent years, advances in artificial intelligence (AI) and machine learning have been driven by advances in the development of large language models (LLMs) based on deep neural networks. At the same time, despite its substantial capabilities, LLMs have fundamental limitations such as spontaneous unreliability in facts and judgments; making simple errors that are dissonant with high competence in general; credulity, manifested by a willingness to accept a user's knowingly false claims as true; and lack of knowledge about events that have occurred after training has been completed. Probably the key reason is that bioinspired intelligence learning occurs through the assimilation of implicit knowledge by an embodied form of intelligence to solve interactive real-world physical problems. Bioinspired studies of the nervous systems of organisms suggest that the cerebellum, which coordinates movement and maintains balance, is a prime candidate for uncovering methods for realizing embodied physical intelligence. Its simple repetitive structure and ability to control complex movements offer hope for the possibility of creating an analog to adaptive neural networks. This paper explores the bioinspired architecture of the cerebellum as a form of analog computational networks capable of modeling complex real-world physical systems. As a simple example, a realization of embodied AI in the form of a multi-component model of an octopus tentacle is presented, demonstrating the potential in creating adaptive physical systems that learn and interact with the environment.","url":"https://doi.org/10.26907/1562-5419-2024-27-4-598-655","authors":["Ayrat Rafkatovich Nurutdinov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-05T10:16:56Z","doi":"10.26907/1562-5419-2024-27-4-598-655","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.20944/preprints202410.1287.v2","name":"Neural Network Model for Detecting Leaf Diseases and Assessing Invasive Species: Computational Approach","source":"crossref","abstract":"Invasive species and plant diseases are critical threats to ecosystems and agriculture worldwide. Effective early detection of these threats can significantly mitigate their impact on biodiversity and crop yields. This paper presents a neural network-based model for detecting leaf diseases and identifying invasive species using advanced image processing techniques. The model integrates edge detection, color analysis, and morphological feature extraction to assess leaf health and species type. By automating the identification process, this approach offers an efficient and scalable solution for real-time ecological monitoring, contributing to conservation and agricultural sustainability efforts.","url":"https://doi.org/10.20944/preprints202410.1287.v2","authors":["MD Nahidul Sabit"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-25T00:41:13Z","doi":"10.20944/preprints202410.1287.v2","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.20944/preprints202410.0956.v1","name":"Fuzzy-Based Convolutional Neural Network Model for Structural Response Prediction Under Seismic Excitation","source":"crossref","abstract":"This study addresses the challenge of predicting the dynamic behavior of the structures under seismic excitation. Accurate prediction of such systems&amp;#039; responses is critical for the design and evaluation of buildings and infrastructure. Traditional methods, including numerical models and differential equation solvers, often face significant computational burdens, especially with nonlinear hysteretic behaviors and large-scale problems. To overcome these limitations, a novel Fuzzy-based Convolutional Neural Network (FuzzyCNN) model is developed. This model integrates fuzzy logic principles with convolutional neural networks to effectively manage the uncertainties and complexities inherent in soil-structure interaction under seismic loads. The model&amp;#039;s performance is validated through both numerical simulations and experimental data from a mid-rise concrete building subjected to seismic events. Comparative analysis with a traditional Physics-informed CNN (PhyCNN) model demonstrates the superior accuracy and robustness of the FuzzyCNN in predicting seismic responses. Key results show that the FuzzyCNN model not only enhances prediction accuracy but also handles uncertainties more effectively than the PhyCNN model. The findings suggest that the FuzzyCNN model can significantly improve the efficiency and accuracy of dynamic response predictions. This advancement offers valuable implications for engineering design, seismic risk assessment, and the development of more resilient infrastructure.","url":"https://doi.org/10.20944/preprints202410.0956.v1","authors":["Mohammad Sadegh Barkhordari","Mohammad Mahdi Barkhordari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-15T01:23:56Z","doi":"10.20944/preprints202410.0956.v1","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1007/s00521-024-09668-0","name":"Reinforcement learning-based autonomous attacker to uncover computer network vulnerabilities","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-024-09668-0","authors":["Ahmed Mohamed Ahmed","Thanh Thi Nguyen","Mohamed Abdelrazek","Sunil Aryal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-07T05:02:31Z","doi":"10.1007/s00521-024-09668-0","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1109/jiot.2023.3331422","name":"Memristor-Based Conditioned Inhibition Neural Network Circuit With Blocking Generalization and Differentiation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/jiot.2023.3331422","authors":["Junwei Sun","Peilong Gao","Shiping Wen","Peng Liu","Yanfeng Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-11-09T19:03:51Z","doi":"10.1109/jiot.2023.3331422","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.20944/preprints202403.0109.v1","name":"Evolutionary Reinforcement Learning of Neural Network Controller for Acrobot Task — Part4: Particle Swarm Optimization","source":"crossref","abstract":"Evolutionary algorithms and swarm intelligence algorithms find applicability in reinforcement learning of neural networks due to their independence from gradient-based methods. To achieve successful training of neural networks using these algorithms, careful considerations must be made to select appropriate algorithms due to the availability of various algorithmic variations. In Part1, 2 and 3, the author previously reported experimental evaluations on Evolution Strategy, Genetic Algorithm, and Differential Evolution for reinforcement learning of neural networks, utilizing the Acrobot control task. This article constitutes Part4 of the series of comparative research. In this study, Particle Swarm Optimization is adopted as an instance of major swarm intelligence algorithms. The experimental result shows that PSO performed worse than all of DE, GA and ES. The difference between PSO and DE was statistically significant (p&amp;lt;.01). In addition, PSO exhibited lower capability in exploring solutions in high-dimensional search spaces than DE, GA, and ES did. A larger swarm size compensated for the weakness of PSO in global exploration, thus making itself more beneficial than a larger number of swarm search iterations.","url":"https://doi.org/10.20944/preprints202403.0109.v1","authors":["Hidehiko Okada"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-06T02:50:00Z","doi":"10.20944/preprints202403.0109.v1","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.52202/079017-0660","name":"Derivative-enhanced Deep Operator Network","source":"crossref","abstract":"","url":"https://doi.org/10.52202/079017-0660","authors":["Yuan Qiu","Nolan Bridges","Peng Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-03T11:20:56Z","doi":"10.52202/079017-0660","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.36227/techrxiv.171259831.10334526/v1","name":"A Convolutional Neural Network-Based Method for Accurate Computation of Scattered Fields From Reconfigurable Intelligent Surfaces","source":"crossref","abstract":"The cell-to-cell coupling in a reconfigurable intelligent surface (RIS) is very different from a periodic structure, where coupling effects can be precisely evaluated via full-wave analysis with periodic boundary conditions. We propose a novel method based on convolutional neural networks (CNNs), to predict the contribution of mutual coupling on the near-zone tangential electric field of every RIS unit cell that characterizes its scattering. Our CNN model incorporates an attention mechanism based on the squeeze-and-excitation block module, enhancing its capability to discern and quantify coupling effects, especially from neighboring cells surrounding the unit cell of interest. The predictions of the model enable the computation of RIS scattered fields, fully accounting for the aperiodic nature of an RIS. Comparisons to finite-element analysis confirm that our computed fields are accurate at any point and for any RIS configuration. Furthermore, our trained model can be retrained through transfer learning, to accurately and efficiently predict cell-to-cell coupling under different incident wave conditions, utilizing only a reduced number of training data. Therefore, the proposed method is a valuable tool for various practical applications, such as synthesizing RIS scattered field patterns and evaluating the performance of RIS-enabled channels.","url":"https://doi.org/10.36227/techrxiv.171259831.10334526/v1","authors":["Yuanzhi Liu","Costas Sarris"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-08T13:45:17Z","doi":"10.36227/techrxiv.171259831.10334526/v1","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1007/s00521-024-09873-x","name":"Retraction Note: Alcoholism identification via convolutional neural network based on parametric ReLU, dropout, and batch normalization","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-024-09873-x","authors":["Shui-Hua Wang","Khan Muhammad","Jin Hong","Arun Kumar Sangaiah","Yu-Dong Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-24T00:01:51Z","doi":"10.1007/s00521-024-09873-x","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1080/0954898x.2024.2435491","name":"ViTBayesianNet: An adaptive deep bayesian network-aided alzheimer disease detection framework with vision transformer-based residual densenet for feature extraction using MRI images","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2024.2435491","authors":["Revathi Mohan","Rajesh Arunachalam","Neha Verma","Shital Mali"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-12T00:14:36Z","doi":"10.1080/0954898x.2024.2435491","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1007/s00521-024-10031-6","name":"Retraction Note: Applications of artificial intelligence and hybrid neural network methods with new bonding method to prevent electroshock risk and insulation faults in high-voltage underground cable lines","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-024-10031-6","authors":["Bahadır Akbal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-21T00:01:28Z","doi":"10.1007/s00521-024-10031-6","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.64336/001c.94086","name":"Optimization of Convolutional Neural Network hyperparameters using Genetic Algorithms","source":"crossref","abstract":"The ever-increasing complexity of deep learning models leads to larger sizes and computational costs (greater execution time), making models extremely difficult to implement in resource constrained environments. Moreover, extensive hyperparameter tuning is necessary to create successful models. One approach to this problem is pruning, which removes redundant connections and neurons within the model. However, no approach fundamentally changes the structure of the model (layers, width, depth, filters, etc.). This would inherently bypass the necessity for tediously removing connections within the model and rather remove unnecessary layers and filters (kernels) which may not substantially contribute to performance. The proposed research introduces a approach to reduce inference times of Convolutional Neural Networks (CNNs) by dynamically changing the number of convolutional layers and the kernel parameters within those layers using Genetic Algorithms (GAs). By parameterizing architecture and layer configurations, this approach found the highest efficiency while maintaining a competitive accuracy. Increasing efficiency means decreasing the number of parameters within a model, thus reducing resource consumption during use and reducing inference time. In this paper, a dynamically trained model was tested on three datasets, MNIST, CIFAR-10, and CIFAR 100. Utilizing concepts from GA’s such as selection, crossover, and mutation, each model was iteratively trained and tested on each dataset. The resulting model maintained an accuracy at a given threshold while demonstrating an increase in efficiency by changing the number of convolutional layers and the corresponding filter parameters.","url":"https://doi.org/10.64336/001c.94086","authors":["Nirmit Shah"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-10T17:50:00Z","doi":"10.64336/001c.94086","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1002/cjce.25577/v2/review1","name":"Review for \"Fault estimation for multi-rate descriptor systems using bi-directional long short-term memory neural network\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/cjce.25577/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-22T01:09:11Z","doi":"10.1002/cjce.25577/v2/review1","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.2139/ssrn.4927691","name":"Neural Network Compression Using Binarization and Few Full-Precision Weights","source":"crossref","abstract":"Quantization and pruning are two effective Deep Neural Networks model compression methods.In this paper, we propose Automatic Prune Binarization (APB), a novel compression technique combining quantization with pruning. APB enhances the representational capability of binary networks using a few full-precision weights.Our technique jointly maximizes the accuracy of the network while minimizing its memory impact by deciding whether each weight should be binarized or kept in full precision.We show how to efficiently perform a forward pass through layers compressed using APB by decomposing it into a binary and a sparse-dense matrix multiplication. Moreover, we design two novel efficient algorithms for extremely quantized matrix multiplication on CPU, leveraging highly efficient bitwise operations. The proposed algorithms are 6.9x and 1.5x faster than available state-of-the-art solutions. We extensively evaluate APB on two widely adopted model compression datasets, namely Cifar-10 and ImageNet. APB shows to deliver better accuracy/memory trade-off compared to state-of-the-art methods based on i) quantization, ii) pruning, and iii) a combination of pruning and quantization.APB also outperforms quantization in the accuracy/efficiency trade-off, being up to 2x faster than the 2-bits quantized model with no loss in accuracy.","url":"https://doi.org/10.2139/ssrn.4927691","authors":["Cosimo Rulli","Franco  Maria Nardini","Salvatore Trani","Rossano Venturini"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-19T05:54:18Z","doi":"10.2139/ssrn.4927691","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.52843/cassyni.qksd21","name":"The Bézier curve and neural network model of the time-domain transient signals","source":"crossref","abstract":"The discussion is for the memory of Oleg Alexandrovich Tretyakov. In the discussion, one characteristic of the signal transfer of Professor Tretyakov's Evolutionary Approach to the Electromagnetics method is presented. Theoretically, the problem of the signal generated by a time-domain signal in a waveguide is addressed. The theoretic propagation is realized-exemplified through the actual TEC (TECU) map estimating by the Bézier curve and neural network. The striking aspect of the segmented prototype established with the Bézier approach is its adaptability. This mechanical curve, which does not need any preliminary preparation, is framed on differential geometric invariants. In the essay, a time-dependent complete set of magnetic waveguide modes is remembered. While the Dirichlet and Neumann eigenvalue problems determine the vector functions of the modes, the behavior of the time-evolving amplitudes is given by the Klein-Gordon equation. Examples of current data are discussed with the TEC map for the 2017 year. While the actual fluctuation of the interpolated CODE TEC atlas is illustrated, the mechanical Bézier curve family (untouched before) and the neural network introduce time-domain estimations to the reader. The parametric curve approach governs the Bézier model. The curve, which is C0 class segmented continuously, models on its way with new hourly components every twelve hours. The network model employs the solar wind parameters for the TEC atlas estimation. The reliability and consistency of the models are exhibited by the R correlation ratio, absolute error, and mean squared error. As a result, the R coefficient of the curve and network models vary around 91.2% and 98.8%, respectively. One can note the error of the network model falls to 1.1308 TECU. The outcomes are compatible with the former discussions.","url":"https://doi.org/10.52843/cassyni.qksd21","authors":["Emre Eroglu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-28T03:08:47Z","doi":"10.52843/cassyni.qksd21","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1109/tnnls.2023.3278938","name":"Few-Shot Relation Extraction With Dual Graph Neural Network Interaction","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnnls.2023.3278938","authors":["Jing Li","Shanshan Feng","Billy Chiu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-02T19:52:48Z","doi":"10.1109/tnnls.2023.3278938","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1007/s00521-023-09057-z","name":"Pathological brain classification using multiple kernel-based deep convolutional neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-023-09057-z","authors":["Lingraj Dora","Sanjay Agrawal","Rutuparna Panda","Ram Bilas Pachori"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-03T09:02:49Z","doi":"10.1007/s00521-023-09057-z","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1007/s11063-024-11668-z","name":"A Random Focusing Method with Jensen–Shannon Divergence for Improving Deep Neural Network Performance Ensuring Architecture Consistency","source":"crossref","abstract":"Abstract Multiple hidden layers in deep neural networks perform non-linear transformations, enabling the extraction of meaningful features and the identification of relationships between input and output data. However, the gap between the training and real-world data can result in network overfitting, prompting the exploration of various preventive methods. The regularization technique called ’dropout’ is widely used for deep learning models to improve the training of robust and generalized features. During the training phase with dropout, neurons in a particular layer are randomly selected to be ignored for each input. This random exclusion of neurons encourages the network to depend on different subsets of neurons at different times, fostering robustness and reducing sensitivity to specific neurons. This study introduces a novel approach called random focusing, departing from complete neuron exclusion in dropout. The proposed random focusing selectively highlights random neurons during training, aiming for a smoother transition between training and inference phases while keeping network architecture consistent. This study also incorporates Jensen–Shannon Divergence to enhance the stability and efficacy of the random focusing method. Experimental validation across tasks like image classification and semantic segmentation demonstrates the adaptability of the proposed methods across different network architectures, including convolutional neural networks and transformers.","url":"https://doi.org/10.1007/s11063-024-11668-z","authors":["Wonjik Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-17T19:02:15Z","doi":"10.1007/s11063-024-11668-z","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1002/cjce.25556/v2/review1","name":"Review for \"Development of a deep neural network and empirical model for predicting local gas holdup profiles in bubble columns\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/cjce.25556/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-22T01:07:19Z","doi":"10.1002/cjce.25556/v2/review1","addedAt":"2026-09-01T01:48:33.834Z","updatedAt":"2026-09-01T01:48:33.834Z"},{"id":"doi:10.1002/cjce.25556/v1/review1","name":"Review for \"Development of a deep neural network and empirical model for predicting local gas holdup profiles in bubble columns\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/cjce.25556/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-22T01:07:19Z","doi":"10.1002/cjce.25556/v1/review1","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.21203/rs.3.rs-4567953/v1","name":"Research on Text Sentiment Analysis of Dual-channel Hybrid Neural Network Based on LERT ","source":"crossref","abstract":"Abstract In current text sentiment analysis tasks, existing pre-trained language models are limited in fully grasping the intrinsic language features and deeply comprehending complex language structures. Classic neural network models struggle to adequately capture the semantic aspects of text. To address these challenges, this study introduces a novel dual-channel hybrid neural network approach for text sentiment analysis, leveraging the LERT model. This approach initially utilizes the advanced pre-trained language model LERT to generate dynamic word vectors from the text and subsequently captures both local and global semantic characteristics through a parallel dual-channel feature extraction layer. The features that have been extracted are merged and inputted into the fully connected layer, followed by the application of the softmax function to classify emotions. Results from experiments demonstrate that compared with other sentiment analysis models, the proposed model LDB-Net performs better in overall performance, validating the effectiveness of the proposed method.","url":"https://doi.org/10.21203/rs.3.rs-4567953/v1","authors":["Peng Ai","Qicheng Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-30T22:44:50Z","doi":"10.21203/rs.3.rs-4567953/v1","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1109/i4c62240.2024.10748465","name":"Inverter Fed Passive Memristor Emulator","source":"crossref","abstract":"","url":"https://doi.org/10.1109/i4c62240.2024.10748465","authors":["S Poornima","Kodeeswara Kumaran G"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-14T18:35:44Z","doi":"10.1109/i4c62240.2024.10748465","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1007/s00521-024-10230-1","name":"Smoke detection in foggy surveillance environment using parallel vision transformer network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-024-10230-1","authors":["Shubhangi Chaturvedi","Poornima Singh Thakur","Pritee Khanna","Aparajita Ojha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-06T11:02:56Z","doi":"10.1007/s00521-024-10230-1","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1109/jiot.2025.3574171","name":"Discrete Memristive Hopfield Neural Network and Application in Memristor-State-Based Encryption","source":"crossref","abstract":"","url":"https://doi.org/10.1109/jiot.2025.3574171","authors":["Han Bao","Jiahua Fan","Zhongyun Hua","Quan Xu","Bocheng Bao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-27T13:24:55Z","doi":"10.1109/jiot.2025.3574171","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1039/d5tc01371b/v2/review2","name":"Review for \"Amorphous Ta&lt;sub&gt;2&lt;/sub&gt;O&lt;sub&gt;5&lt;/sub&gt; memristor with excellent self-selective and artificial synaptic properties for artificial neural networks\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5tc01371b/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-16T17:06:47Z","doi":"10.1039/d5tc01371b/v2/review2","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1109/icdsns62112.2024.10691181","name":"Denial of Service (DoS) Attack Detection Using Feed Forward Neural Network in Cloud Environment","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icdsns62112.2024.10691181","authors":["Ponugoti Kalpana","P. Srilatha","Gudepu Sai Krishna","Ahmad Alkhayyat","Debarshi Mazumder"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-01T17:23:43Z","doi":"10.1109/icdsns62112.2024.10691181","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1007/978-3-031-73030-6_23","name":"Graph Neural Network Causal Explanation via Neural Causal Models","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-73030-6_23","authors":["Arman Behnam","Binghui Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-25T16:58:26Z","doi":"10.1007/978-3-031-73030-6_23","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1007/s00521-024-10476-9","name":"Potcapsnet: an explainable pyramid dilated capsule network for visualization of blight diseases","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-024-10476-9","authors":["Sachin Gupta","Ashish Kumar Tripathi","Avinash Chandra Pandey"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-10T05:02:19Z","doi":"10.1007/s00521-024-10476-9","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1016/j.neunet.2024.106110","name":"EMAT: Efficient feature fusion network for visual tracking via optimized multi-head attention","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.106110","authors":["Jun Wang","Changwang Lai","Yuanyun Wang","Wenshuang Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-06T11:34:43Z","doi":"10.1016/j.neunet.2024.106110","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.52202/079017-3896","name":"GLinSAT: The General Linear Satisfiability Neural Network Layer By Accelerated Gradient Descent","source":"crossref","abstract":"","url":"https://doi.org/10.52202/079017-3896","authors":["Hongtai Zeng","Chao Yang","Yanzhen Zhou","Cheng Yang","Qinglai Guo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-03T11:20:56Z","doi":"10.52202/079017-3896","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1109/npsc61626.2024.10987033","name":"Classification of Power Quality Disturbances Using Convolutional Neural Network and Temporal Convolutional Network Models","source":"crossref","abstract":"","url":"https://doi.org/10.1109/npsc61626.2024.10987033","authors":["Surendra Srinivas","Abhinav Jayaram","K Bhavadharani","K Somya Pant","Karthik Thirumala","T. Sunil Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-16T17:41:28Z","doi":"10.1109/npsc61626.2024.10987033","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1109/oncon62778.2024.10931637","name":"Prediction of Network Controllability Robustness Based on Graph Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/oncon62778.2024.10931637","authors":["Kunpeng Wang","Shaopeng Pang","Xinghui Wang","Cheng Liu","Yongguo Zhao","Hengqing Yang","Gengwei Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-26T06:47:05Z","doi":"10.1109/oncon62778.2024.10931637","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1088/1674-1056/adb8bb","name":"Resonant tunneling diode cellular neural network with memristor coupling and its application in police forensic digital image protection","source":"crossref","abstract":"Abstract Due to their biological interpretability, memristors are widely used to simulate synapses between artificial neural networks. As a type of neural network whose dynamic behavior can be explained, the coupling of resonant tunneling diode-based cellular neural networks (RTD-CNNs) with memristors has rarely been reported in the literature. Therefore, this paper designs a coupled RTD-CNN model with memristors (RTD-MCNN), investigating and analyzing the dynamic behavior of the RTD-MCNN. Based on this model, a simple encryption scheme for the protection of digital images in police forensic applications is proposed. The results show that the RTD-MCNN can have two positive Lyapunov exponents, and its output is influenced by the initial values, exhibiting multistability. Furthermore, a set of amplitudes in its output sequence is affected by the internal parameters of the memristor, leading to nonlinear variations. Undoubtedly, the rich dynamic behaviors described above make the RTD-MCNN highly suitable for the design of chaos-based encryption schemes in the field of privacy protection. Encryption tests and security analyses validate the effectiveness of this scheme.","url":"https://doi.org/10.1088/1674-1056/adb8bb","authors":["Fei 飞 Yu 余","Dan 丹 Su 苏","Shaoqi 邵祁 He 何","Yiya 亦雅 Wu 吴","Shankou 善扣 Zhang 张","Huige 挥戈 Yin 尹"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-21T03:48:13Z","doi":"10.1088/1674-1056/adb8bb","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.32604/cmc.2024.051996","name":"Network Security Enhanced with Deep Neural Network-Based Intrusion Detection System","source":"crossref","abstract":"","url":"https://doi.org/10.32604/cmc.2024.051996","authors":["Fatma S. Alrayes","Mohammed Zakariah","Syed Umar Amin","Zafar Iqbal Khan","Jehad Saad Alqurni"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-09T09:18:58Z","doi":"10.32604/cmc.2024.051996","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.52202/079017-0479","name":"BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network Inference","source":"crossref","abstract":"","url":"https://doi.org/10.52202/079017-0479","authors":["Changwoo Lee","Soo Min Kwon","Qing Qu","Hun-Seok Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-03T11:20:56Z","doi":"10.52202/079017-0479","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1109/ddcls66240.2025.11065528","name":"Sampled-data Stabilization of Delayed Memristor-based Neural Networks with Communication Delays via Continuous-time Model","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ddcls66240.2025.11065528","authors":["Huiping Lyu","Youming Xin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-11T17:42:05Z","doi":"10.1109/ddcls66240.2025.11065528","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1109/ic-sit63503.2024.10862075","name":"Modified Deep Neural Network Approach to Identify Heart Disease using IoMT: Artificial Neural Networks or Convolutional Neural Networks!","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ic-sit63503.2024.10862075","authors":["Debasish Swapnesh Kumar Nayak","Arpita Priyadarshini","Pabani Mahanta","Soumyarashmi Panigrahi","Sushanta Meher","Satyananda Swain"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-06T18:33:30Z","doi":"10.1109/ic-sit63503.2024.10862075","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1109/icdsns62112.2024.10691177","name":"Identify Dangerous Behaviors of Electric Power High Altitude Operators Using Convolutional Neural Network Based Multiple Parametric Exponential Linear Unit","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icdsns62112.2024.10691177","authors":["Xin Wan","Yubin He","Min Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-01T17:23:43Z","doi":"10.1109/icdsns62112.2024.10691177","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1080/0954898x.2025.2501418","name":"Correction","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2025.2501418","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-02T07:21:57Z","doi":"10.1080/0954898x.2025.2501418","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1109/ijcnn.2006.1716313","name":"System-Type Neural Network Architectures for Power Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.1716313","authors":["K.Y. Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-30T17:35:23Z","doi":"10.1109/ijcnn.2006.1716313","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1049/pbce053e_ch6","name":"Studies in artificial neural network based control","source":"crossref","abstract":"","url":"https://doi.org/10.1049/pbce053e_ch6","authors":["K. J. Hunt","D. Sbarbaro"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-10-06T14:14:16Z","doi":"10.1049/pbce053e_ch6","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.46916/11062026-1-978-5-00276-118-0","name":"THE ROLE OF NEURAL NETWORK TECHNOLOGIES IN INFORMATION SECURITY","source":"crossref","abstract":"","url":"https://doi.org/10.46916/11062026-1-978-5-00276-118-0","authors":["Alexander Sergeevich Bozhko"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-11T14:06:02Z","doi":"10.46916/11062026-1-978-5-00276-118-0","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1117/12.3052776","name":"Research on vehicle autonomous driving based on convolutional neural network and embedded system in computer vision","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3052776","authors":["David Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-19T16:04:45Z","doi":"10.1117/12.3052776","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1109/icesep62218.2024.10652066","name":"Fault Location of Active Distribution Network Cable Based on Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icesep62218.2024.10652066","authors":["Wei Li","Jisheng Lin","Xiangmao Cheng","Yao Li","Xuejun Qiu","Xin Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-06T17:38:15Z","doi":"10.1109/icesep62218.2024.10652066","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1109/icdsns62112.2024.10691197","name":"A Classification of Face Recognition System Using Faster Region-Based Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icdsns62112.2024.10691197","authors":["M. Maheswari","Haider Alabdeli","Aruna T M","R. Archana Reddy","Revathi. R"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-01T17:23:43Z","doi":"10.1109/icdsns62112.2024.10691197","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1088/0954-898x/5/3/003","name":"Kohonen neural networks for optimal colour quantization","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/5/3/003","authors":["Anthony Dekker"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/5/3/003","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/mwscas47672.2021.9531928","name":"A Dynamic System Approach to Spiking Memristor Network Investigation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mwscas47672.2021.9531928","authors":["Francesco Marrone","Gianluca Zoppo","Fernando Corinto","Marco Gilli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-13T22:17:52Z","doi":"10.1109/mwscas47672.2021.9531928","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1080/23080477.2024.2358672","name":"Islanded micro-grid under variable load conditions for local distribution network using artificial neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1080/23080477.2024.2358672","authors":["A. Venkat Rao","G. Suresh Babu","P. Satish Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-09T14:49:28Z","doi":"10.1080/23080477.2024.2358672","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1016/j.optlaseng.2024.108054","name":"Fourier-attention network: A deep neural network for lithographic misalignment sensing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.optlaseng.2024.108054","authors":["Nan Wang","Yi Li","Wei Jiang","Zhen'an Qin","Jun Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-01T01:39:05Z","doi":"10.1016/j.optlaseng.2024.108054","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1115/isfa2024-141304","name":"A Recurrent Neural Network Enhanced Unscented Kalman Filter for Human Motion Prediction","source":"crossref","abstract":"Abstract This paper presents a deep learning enhanced adaptive unscented Kalman filter (UKF) for predicting human arm motion in the context of manufacturing. Unlike previous network-based methods that solely rely on captured human motion data, which is represented as bone vectors in this paper, we incorporate a human arm dynamic model into the motion prediction algorithm and use the UKF to iteratively forecast human arm motions. Specifically, a Lagrangian-mechanics-based physical model is employed to correlate arm motions with associated muscle forces. Then a Recurrent Neural Network (RNN) is integrated into the framework to predict future muscle forces, which are transferred back to future arm motions based on the dynamic model. Given the absence of measurement data for future human motions that can be input into the UKF to update the state, we integrate another RNN to directly predict human future motions and treat the prediction as surrogate measurement data fed into the UKF. A noteworthy aspect of this study involves the quantification of uncertainties associated with both the data-driven and physical models in one unified framework. These quantified uncertainties are used to dynamically adapt the measurement and process noises of the UKF over time. This adaption, driven by the uncertainties of the RNN models, addresses inaccuracies stemming from the data-driven model and mitigates discrepancies between the assumed and true physical models, ultimately enhancing the accuracy and robustness of our predictions. One unique point of our method is that it integrates a dynamic model of human arms and two RNN models, and uses Monte Carlo dropout sampling to quantify the uncertainties inherent in our RNN prediction models and transforms them into the covariances of the UKF’s measurement and process noises respectively. Compared to the traditional RNN-based prediction, our method demonstrates improved accuracy and robustness in extensive experimental validations of various types of human motions.","url":"https://doi.org/10.1115/isfa2024-141304","authors":["Wansong Liu","Sibo Tian","Boyi Hu","Xiao Liang","Minghui Zheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-29T16:16:10Z","doi":"10.1115/isfa2024-141304","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1109/mc.2023.3342602","name":"Using Explainable AI for Neural Network-Based Network Attack Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mc.2023.3342602","authors":["Qingtian Zou","Lan Zhang","Xiaoyan Sun","Anoop Singhal","Peng Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-02T17:20:58Z","doi":"10.1109/mc.2023.3342602","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.7717/peerj-cs.2938/table-7","name":"Table 7: Application of capsule neural network in SI-BCI neural decoding.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.2938/table-7","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-23T04:13:43Z","doi":"10.7717/peerj-cs.2938/table-7","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/isocc.2018.8649932","name":"Memristor-based Neuromorphic Implementations for Artificial Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isocc.2018.8649932","authors":["Chun Zhao","Guang You Zhou","Ce Zhou Zhao","Li Yang","Ka Lok Man","Eng Gee Lim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-02-25T21:10:07Z","doi":"10.1109/isocc.2018.8649932","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1088/0954-898x_2_2_005","name":"‘Quantum’ neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_2_2_005","authors":["Maciej Lewenstein","Mariusz Olko"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:03Z","doi":"10.1088/0954-898x_2_2_005","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.52202/079017-2389","name":"Spiking Neural Network as Adaptive Event Stream Slicer","source":"crossref","abstract":"","url":"https://doi.org/10.52202/079017-2389","authors":["Jiahang Cao","Mingyuan Sun","Ziqing Wang","Hao Cheng","Qiang Zhang","Shibo Zhou","Renjing Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-03T11:20:56Z","doi":"10.52202/079017-2389","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1016/s0893-6080(97)00121-4","name":"The Neural Network Approach To A Parallel Decentralized Network Routing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/s0893-6080(97)00121-4","authors":["Hiroaki Kurokawa","Chun Ying Ho","Shinsaku Mori"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-25T22:54:47Z","doi":"10.1016/s0893-6080(97)00121-4","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.52202/079017-4081","name":"Regularized Adaptive Momentum Dual Averaging with an Efficient Inexact Subproblem Solver for Training Structured Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.52202/079017-4081","authors":["Zih-Syuan Huang","Ching-Pei Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-03T11:20:56Z","doi":"10.52202/079017-4081","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1109/iscs61804.2024.10581320","name":"Feature Extraction and Ranking using Fuzzy-Ksi for Network Intrusion Detection using a Krill Herd Optimized Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscs61804.2024.10581320","authors":["Ishan Bhateja","Palak Chaturvedi","Kanishka Thakran","Anshul Arora"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-12T17:34:35Z","doi":"10.1109/iscs61804.2024.10581320","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.5121/ijnsa.2024.16602","name":"Improving Intrusion Detection System using the Combination of Neural Network and Genetic Algorithm","source":"crossref","abstract":"One of the essential issues in network-based systems is a fault attack which is caused by intrusion. It is the responsibility of intrusion detection to provide capabilities such as adaptation, fault tolerance, high computational speed, and error resilience in the face of noisy information. Thus, the construction of an efficient intrusion detection model is highly appreciated to increase the detection rates as well as to decrease false detection. Currently, researchers are more focusing on abnormal behaviour of network as this system can easily recognize new attacks without updating the daily recognized databases. However, the capability of current developing machine learning algorithms suffers from inefficient use of intrusion detection particularly once it involved some huge datasets of irrelevant and redundant features. The main objective of this thesis is to achieve the higher detection rate with lower false detection for attack recognition in order to support efficient application of intrusion detection. To achieve this goal, a new machine learning model was designed and developed to provide intelligent recognition with new attack patterns. New proposed and improved algorithm GA-ANN is constructed to support the proof of concept. For evaluation, five datasets namely KDD CUP 99 from the online data repositories are used in the experiment. In the above scenarios, GA-ANN provides the highest detection rate for pattern recognition which was 98.98% based on 18 selected features. This means that the proposed IDS model is significant and increases the network security.","url":"https://doi.org/10.5121/ijnsa.2024.16602","authors":["Amin Dastanpour","Amirabbas Farizani","Raja Azlina Raja Mahmood"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-16T17:00:06Z","doi":"10.5121/ijnsa.2024.16602","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.7717/peerj-cs.3366/fig-3","name":"Figure 3: Graph neural network.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.3366/fig-3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-09T08:00:28Z","doi":"10.7717/peerj-cs.3366/fig-3","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2172/1995270","name":"Benchmarking Neural Network Architectures for Strong Gravitational Lens Classification","source":"crossref","abstract":"","url":"https://doi.org/10.2172/1995270","authors":["Eileen Nolan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-18T04:08:02Z","doi":"10.2172/1995270","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/icdsns62112.2024.10691031","name":"Deep Learning Model Based on Convolutional Neural Network for Automatic Intrusion Detection System","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icdsns62112.2024.10691031","authors":["Anuj Khanvilkar","Siddhi Gothivrekar","Mann Jain","Ujjawal Mishra","Anagha Perumal","Siddhi Kadu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-01T17:23:43Z","doi":"10.1109/icdsns62112.2024.10691031","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1051/matecconf/202439002003","name":"Forecasting network traffic in the information and telecommunication system of railway transport by means of a neural network","source":"crossref","abstract":"Network traffic is one of the most important actual indicators of the information and telecommunication system (ITS) of railway transport. Recent studies show that network traffic in the ITS of railway transport is self-similar (fractal), for the study of which the Hirst indicator can be used. One of the possible solutions is a method of network traffic forecasting using neural network technology, which will allow you to manage traffic in real time, avoid server overload and improve the quality of services, which confirms the relevance of this topic. The method of forecasting the parameters of network traffic in the ITS of railway transport using neural network technology is proposed: for long-term forecasting (day-ahead) of network traffic volume based on network traffic volumes for the previous three days using the created multilayer neuro-fuzzy network; for short-term prediction (one step forward, which takes five minutes) of network traffic intensity based on network traffic intensities for the previous fifteen minutes using the created multilayer neural network. The corresponding samples are formed on the basis of real values of network traffic parameters in the ITS of railway transport. Studies of optimal parameters of the created multilayer neural network, which can be integrated into specialized analytical servers of the ITS of railway transport, are carried out, which will provide a sufficiently high level of short-term forecasting of network traffic parameters (in particular intensity) in the ITS of railway transport at the stage of deepening the integration of the national transport network into the Trans-European Transport Network.","url":"https://doi.org/10.1051/matecconf/202439002003","authors":["Igor Zhukovytskyy","Victoria Pakhomova"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-24T09:07:23Z","doi":"10.1051/matecconf/202439002003","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1117/12.3049406","name":"Research on water supply network pressure prediction using PSO-BP neural network algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3049406","authors":["Chao-Ran Wang","Chang-Tao Wang","Dan Shan","Bao-Long Yuan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-12T18:17:00Z","doi":"10.1117/12.3049406","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1109/icdsns62112.2024.10690903","name":"Vision-Based Complete Scene Understanding Using Faster Region-Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icdsns62112.2024.10690903","authors":["Tejonidhi M R","Santosh Kumar Sahoo","Manjula B M","Thota Soujanya","Saravanan Kandaneri Ramamoorthy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-01T17:23:43Z","doi":"10.1109/icdsns62112.2024.10690903","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.52202/079017-4412","name":"The Importance of Being Scalable: Improving the Speed and Accuracy of Neural Network Interatomic Potentials Across Chemical Domains","source":"crossref","abstract":"","url":"https://doi.org/10.52202/079017-4412","authors":["Eric Qu","Aditi Krishnapriyan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-03T11:20:56Z","doi":"10.52202/079017-4412","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1109/tim.2026.3655905","name":"Exploring the Influence of Synaptic Parasitic Resistance on the Firing Dynamics of Memristor-Based HR-Tabu Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tim.2026.3655905","authors":["Chunlai Li","Shulun Tan","Xuanbing Yang","Zhijun Li","Shaobo He"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-20T20:39:50Z","doi":"10.1109/tim.2026.3655905","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1088/0954-898x/5/2/006","name":"Inductive inference and neural nets","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/5/2/006","authors":["Jakob Bernasconi","Karl Gustafson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-24T22:35:54Z","doi":"10.1088/0954-898x/5/2/006","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1007/s13278-024-01380-0","name":"HACNN: hierarchical attention convolutional neural network for fake review detection","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s13278-024-01380-0","authors":["Bhoompally Venkatesh","B. V. Ramnaresh Yadav"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-26T05:07:53Z","doi":"10.1007/s13278-024-01380-0","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1007/978-3-540-48125-6_7","name":"Design of Neural Network Optimal Models","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-540-48125-6_7","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-10-28T00:36:19Z","doi":"10.1007/978-3-540-48125-6_7","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1177/01423312231200514","name":"Delay-independent control for synchronization of memristor-based BAM neural networks with parameter perturbation and strong mismatch via finite-time technology","source":"crossref","abstract":"This paper mainly studies the synchronization problem of memristor-based bidirectional associative memory neural networks (MBAMNNs) via finite-time technology. Different from the existing neural network dynamic models, the given model in this paper is focused on the impact of parameter perturbation and strong mismatch, where strong mismatch includes parameter mismatch and time-varying delay mismatch. These characteristics can make the model be closer to the actual situation. A delay-independent feedback control scheme, which can stabilize the error system within finite-time regardless of whether the past state is known or not, is designed. It is worth noting that the constant is replaced by a function with the exponential term in the delay-independent controller, which can save the control cost to a certain extent. Based on the integral inequality technique, some sufficient conditions for MBAMNNs to converge to the equilibrium point within finite-time are provided. The validity and correctness of the theoretical results are finally confirmed by numerical simulation.","url":"https://doi.org/10.1177/01423312231200514","authors":["Lili Zhou","Huiying Zhang","Fei Tan","Kaiyue Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-06T07:51:52Z","doi":"10.1177/01423312231200514","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1109/ssaic61213.2024.00050","name":"Design of Music Art Teaching Quality Evaluation System Based on Deep Convolution Neural Network Algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ssaic61213.2024.00050","authors":["Fang Lin","Tiancheng Gu","Wen Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-22T17:33:12Z","doi":"10.1109/ssaic61213.2024.00050","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.1016/j.eswa.2024.124835","name":"Graph Neural Network Enhanced Dual-Branch Network for lesion segmentation in ultrasound images","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.eswa.2024.124835","authors":["Yaqi Wang","Cunang Jiang","Shixin Luo","Yu Dai","Jiangxun Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-03T12:57:10Z","doi":"10.1016/j.eswa.2024.124835","addedAt":"2026-09-01T01:48:33.835Z","updatedAt":"2026-09-01T01:48:33.835Z"},{"id":"doi:10.59879/huwf6","name":"Deep Neural Network Assisted Monte Carlo Tree Search Algorithm to Solve Bandwidth Slicing Placement Problem","source":"crossref","abstract":"To solve the network slicing placement problem, the methods based on CNN/RNN were inadequate in handling the randomness of fluctuating channel quality and bandwidth needs for each network slice. While the Monte Carlo Tree Search (MCTS) methodology effectively deals with the unpredictability of each slice’s channel quality and bandwidth request to optimize throughput, it remains time-consuming in finding an optimal solution. The cause is that MCTS relies on a uniform distribution to randomly sample one possible solution, which leads to subpar sampling efficiency. Our objective is to integrate a deep neural network (DNN) to assist MCTS. Specifically, the DNN first analyses the current allocation situation to predict probability distributions for achieving optimizing throughput. MCTS then leverages this DNN-produced probability distribution to pinpoint the best allocation scenario. Experimental results indicate that the performance of DNN-based MCTS with only 50 search iterations surpasses that of the original MCTS with 4,000 search iterations.","url":"https://doi.org/10.59879/huwf6","authors":["Liang-Chun Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-16T09:40:10Z","doi":"10.59879/huwf6","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1002/9781394343126.ch18","name":"Deploying a Deep Neural Network on\n            <scp>FPGA</scp>","source":"crossref","abstract":"","url":"https://doi.org/10.1002/9781394343126.ch18","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-14T17:48:35Z","doi":"10.1002/9781394343126.ch18","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1007/978-3-031-80056-6_8","name":"Parkinson’s Disease Prediction Using Artificial Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-031-80056-6_8","authors":["Nagarjuna Telagam","Nehru Kandasamy","D. Ajitha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-24T10:42:07Z","doi":"10.1007/978-3-031-80056-6_8","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1364/cleo_si.2025.ss118_7","name":"Single-Shot Wavefront Aberration Correction using a Hybrid Neural Network Approach","source":"crossref","abstract":"We present a machine learning-based approach for wavefront aberration correction using a single intensity image. Our approach utilizes a trained bias, implemented as a single optical element, to effectively resolve ambiguity issues.","url":"https://doi.org/10.1364/cleo_si.2025.ss118_7","authors":["Sina Moayed Baharlou","Muhammad Waleed Khalid","Alexander V. Sergienko","Abdoulaye Ndao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-18T17:02:18Z","doi":"10.1364/cleo_si.2025.ss118_7","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1039/d5ya00093a/v1/review1","name":"Review for \"A Sampling Fault Diagnosis Method for Power Battery Data in Cloud Platform Based on ResNet-BiLSTM Neural Network\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5ya00093a/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-25T21:09:14Z","doi":"10.1039/d5ya00093a/v1/review1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1038/s42256-025-01139-y","name":"Are neural network representations universal or idiosyncratic?","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s42256-025-01139-y","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-21T15:02:49Z","doi":"10.1038/s42256-025-01139-y","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.32743/unitech.2025.134.5.20124","name":"APPLICATION OF GRAPH NEURAL NETWORKS IN SOCIAL NETWORK RECOMMENDATION ANALYSIS","source":"crossref","abstract":"","url":"https://doi.org/10.32743/unitech.2025.134.5.20124","authors":["Alexander Yurievich Fonarev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-05T08:15:56Z","doi":"10.32743/unitech.2025.134.5.20124","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5263723","name":"Classification of Leathers Tanned with Different Vegetable Tannins by Convolution Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5263723","authors":["Sukru Omur","Nilay Ork Efendioglu","Mahmut Sinecen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-21T17:40:28Z","doi":"10.2139/ssrn.5263723","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1002/we.2976/v3/review2","name":"Review for \"Volt/VAr Regulation of the West Mediterranean Regional Electrical Grids Using SVC/STATCOM Devices With Neural Network Algorithms\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/we.2976/v3/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-25T16:09:21Z","doi":"10.1002/we.2976/v3/review2","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1039/d4sc07858f/v2/review2","name":"Review for \"IMPRESSION Generation 2 – Accurate, fast and generalised neural network model for predicting NMR parameters in place of DFT\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d4sc07858f/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-31T17:20:23Z","doi":"10.1039/d4sc07858f/v2/review2","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1016/j.placenta.2025.03.003","name":"Prediction of clinical risk factors in pregnancy using optimized neural network scheme","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.placenta.2025.03.003","authors":["G. Bhavani","C. Jeyalakshmi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-04T16:54:31Z","doi":"10.1016/j.placenta.2025.03.003","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/tiptekno68206.2025.11270119","name":"Interaction-Aware Interpersonal Graph Neural Network (IA-IGNN) for Stress Detection with Biosignals","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tiptekno68206.2025.11270119","authors":["İrem Aksoy","Fatma Patlar Akbulut"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-08T18:38:51Z","doi":"10.1109/tiptekno68206.2025.11270119","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/ibitec66306.2025.11472920","name":"Botnet Detection in IoT Devices Using Artificial Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ibitec66306.2025.11472920","authors":["Ahren Jun Sukirya","Gredion Prajena"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-13T19:35:30Z","doi":"10.1109/ibitec66306.2025.11472920","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5362904","name":"A Physics-Data Combined Neural Network Based Finite Volume Parametric Reduced Order Model","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5362904","authors":["Dunhui Xiao","Xinyu Pan","Lihua Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-23T06:08:31Z","doi":"10.2139/ssrn.5362904","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5224522","name":"Multi-Scale Attention-Based Spectral Neural Network For Underwater Reverberation Suppression","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5224522","authors":["Yuxin Fan","Zirui Wang","Qiao Hu","Zhiqiang Wei"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-21T13:52:26Z","doi":"10.2139/ssrn.5224522","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/ipc65510.2025.11282384","name":"Photonic Spiking Neural Network with Coupled Passive Silicon Microring Resonators","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ipc65510.2025.11282384","authors":["G. Donati","S. Biasi","L. Pavesi","A. Hurtado"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-22T18:39:16Z","doi":"10.1109/ipc65510.2025.11282384","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.47297/taposatwsp2633-456948.20250608","name":"Smart Contract Security Detection Based on Graph Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.47297/taposatwsp2633-456948.20250608","authors":["Su Ziteng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-04T07:16:37Z","doi":"10.47297/taposatwsp2633-456948.20250608","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/icicacs65178.2025.10968681","name":"Neural Network Deep Supervised Learning Algorithm Based on Multimodal Data","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icicacs65178.2025.10968681","authors":["Yunxia Fu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-24T17:02:57Z","doi":"10.1109/icicacs65178.2025.10968681","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.26855/jamc.2025.03.006","name":"A Neural Network-based Stock Timing Model","source":"crossref","abstract":"","url":"https://doi.org/10.26855/jamc.2025.03.006","authors":["Zhuoxin Lei"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-21T02:33:21Z","doi":"10.26855/jamc.2025.03.006","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1007/978-3-319-76375-0_4","name":"Aftermath of Finding the Memristor","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-76375-0_4","authors":["R. Stanley Williams"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-11-12T17:03:43Z","doi":"10.1007/978-3-319-76375-0_4","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1038/s41467-023-44620-1","name":"Purely self-rectifying memristor-based passive crossbar array for artificial neural network accelerators","source":"crossref","abstract":"Abstract Memristor-integrated passive crossbar arrays (CAs) could potentially accelerate neural network (NN) computations, but studies on these devices are limited to software-based simulations owing to their poor reliability. Herein, we propose a self-rectifying memristor-based 1 kb CA as a hardware accelerator for NN computations. We conducted fully hardware-based single-layer NN classification tasks involving the Modified National Institute of Standards and Technology database using the developed passive CA, and achieved 100% classification accuracy for 1500 test sets. We also investigated the influences of the defect-tolerance capability of the CA, impact of the conductance range of the integrated memristors, and presence or absence of selection functionality in the integrated memristors on the image classification tasks. We offer valuable insights into the behavior and performance of CA devices under various conditions and provide evidence of the practicality of memristor-integrated passive CAs as hardware accelerators for NN applications.","url":"https://doi.org/10.1038/s41467-023-44620-1","authors":["Kanghyeok Jeon","Jin Joo Ryu","Seongil Im","Hyun Kyu Seo","Taeyong Eom","Hyunsu Ju","Min Kyu Yang","Doo Seok Jeong","Gun Hwan Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-02T10:07:20Z","doi":"10.1038/s41467-023-44620-1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.26434/chemrxiv-2025-hpcws","name":"Architecture independent absolute solvation free energy calculations with neural network potentials","source":"crossref","abstract":"Allowing atoms or molecules to disappear is a critical step in alchemical free energy simulations (FES). The necessary tricks are well understood when using force fields. Over the past few years, neural network potentials (NNPs) have seen rapid development. Their potentially higher accuracy compared to force fields makes them attractive for use in FES. Here, we outline a method for gradually decoupling atoms and molecules in systems that are fully described by NNPs. Specifically, we show that manipulating the neighbor list is equivalent to using soft-core potentials in force-field-based FES. Since constructing the neighbor list is a central step, regardless of the NNP's inner workings, our approach is agnostic to NNP architecture. We validate the correctness of our methodology by demonstrating cycle closure for a model problem and report solvation free energies obtained with the MACE-OFF23(S/M) NNP.","url":"https://doi.org/10.26434/chemrxiv-2025-hpcws","authors":["Anna Katharina Picha","Sara Tkaczyk","Marcus Wieder","Stefan Boresch"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-05T04:15:41Z","doi":"10.26434/chemrxiv-2025-hpcws","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1101/2025.10.21.25338451","name":"ALTARN: A Tabular Residual Neural Network for Alzheimer’s Disease Classification and Prediction","source":"crossref","abstract":"Abstract Early and accurate prediction of Alzheimer’s disease (AD) from accessible clinical data remains a significant challenge in healthcare. This study proposes ALTARN, a tabular attention residual neural network architecture for robust classification of AD through heterogeneous patient data from a publicly available dataset of 2149 subjects, with medical, demographic, and lifestyle variables organized as structured tabular data. With sigmoid attention mechanisms for the dynamic reweighing of input variables for each patient, deep residual connections capturing complex, and non-linear relationships in tabular features, we propose ALTARN-an early Alzheimer prediction tool. ALTARN achieved an average cross-validated training accuracy of roughly 92.73%, alongside robust validation metrics, including an average accuracy of 85.06%, average precision of 80.73%, mean recall of 76.18%, and a mean validation F1-score of 78.32% when evaluated through five-fold stratified validation. When tested against other approaches, ALTARN meets and also exceeds the performance of supervised deep learning models for non-imaging AD classification. This further illustrates that deep neural network based approaches with tabular attention offer a promising direction for interpretable diagnosis of AD via non-imaging medical data.","url":"https://doi.org/10.1101/2025.10.21.25338451","authors":["Keshav Balakrishna","Alessandro Hammond","Abdeslem El Idrissi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-23T17:45:12Z","doi":"10.1101/2025.10.21.25338451","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.20944/preprints202506.2227.v1","name":"Neural Network-Informed Lotka-Volterra Dynamics for Cryptocurrency Market Analysis","source":"crossref","abstract":"Mathematical modeling plays a crucial role in supporting decision-making across a wide range of scientific disciplines. These models often involve multiple parameters, the estimation of which is critical to assessing their reliability and predictive power. Recent advancements in artificial intelligence have made it possible to efficiently estimate such parameters with high accuracy. In this study, we focus on modeling the dynamics of cryptocurrency market shares by employing a Lotka-Volterra system. We introduce a methodology based on a deep neural network (DNN) to estimate the parameters of the Lotka-Volterra model, which are subsequently used to numerically solve the system using a fourth-order Runge-Kutta method. The proposed approach, when applied to real-world market share data for Bitcoin, Ethereum, and alternative cryptocurrencies, demonstrates excellent alignment with empirical observations. Moreover, our method outperforms ARIMA models in terms of accuracy, showcasing its effectiveness for crypto market forecasting. The entire framework, including neural network training and Runge-Kutta integration, was implemented in MATLAB.","url":"https://doi.org/10.20944/preprints202506.2227.v1","authors":["Dimitris Kastoris","Dimitris Papadopoulos","Konstantinos Giotopoulos"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-29T21:04:00Z","doi":"10.20944/preprints202506.2227.v1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5243772","name":"Gated Recurrent Neural Network Enhanced Wind Power Prediction Accuracy Using Tpe Bayesian Optimization","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5243772","authors":["Mohsin  Ali Qazi","Dong  Hsiao Chiang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-06T21:43:49Z","doi":"10.2139/ssrn.5243772","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5232120","name":"Directed Hypergraph Neural Network: Building a Predictive Framework","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5232120","authors":["Yousra Moh Ousellam","Bikram Pratim BHUYAN","Rachida Fissoune","Amar  Ramdane Cherif"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-26T20:39:08Z","doi":"10.2139/ssrn.5232120","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.3390/sym17071129","name":"A Neural Network Training Method Based on Distributed PID Control","source":"crossref","abstract":"In the previous article, we introduced a neural network framework based on symmetric differential equations. This novel framework exhibits complete symmetry, endowing it with perfect mathematical properties. While we have examined some of the system’s mathematical characteristics, a detailed discussion of the network training methodology has not yet been presented. Drawing on the principles of the traditional backpropagation algorithm, this study proposes an alternative training approach that utilizes differential equation signal propagation instead of chain rule derivation. This approach not only preserves the effectiveness of training but also offers enhanced biological interpretability. The foundation of this methodology lies in the system’s reversibility, which stems from its inherent symmetry—a key aspect of our research. However, this method alone is insufficient for effective neural network training. To address this, we further introduce a distributed Proportional–Integral–Derivative (PID) control approach, emphasizing its implementation within a closed system. By incorporating this method, we achieved both faster training speeds and improved accuracy. This approach not only offers novel insights into neural network training but also extends the scope of research into control methodologies. To validate its effectiveness, we apply this method to the MNIST (Modified National Institute of Standards and Technology database) and Fashion-MNIST, demonstrating its practical utility.","url":"https://doi.org/10.3390/sym17071129","authors":["Kun Jiang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-15T08:04:41Z","doi":"10.3390/sym17071129","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5766403","name":"Image denoising with deep learning approach to obtain denoised clean image using convolution neural network(CNN) architecture","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5766403","authors":["Zeenal Patel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-18T18:36:58Z","doi":"10.2139/ssrn.5766403","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1002/eng2.70373/v5/review2","name":"Review for \"Enhancing Cardiovascular Disease Analysis in Healthcare Systems With Hybrid Random Forest and Neural Network Algorithm\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/eng2.70373/v5/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T23:21:22Z","doi":"10.1002/eng2.70373/v5/review2","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1016/j.chaos.2025.117426","name":"Dynamical analysis and hardware implementation of Hopfield Neural Networks based on fractional calculus and memristor coupling","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.chaos.2025.117426","authors":["Ningning Yang","Wenbo Jing","Chaojun Wu","XiaoMiao Guan","CanYong Weng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-20T17:29:31Z","doi":"10.1016/j.chaos.2025.117426","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.54216/jisiot.160119","name":"An Optimized Convolutional Neural Network for Alzheimer’s disease Detection","source":"crossref","abstract":"","url":"https://doi.org/10.54216/jisiot.160119","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-27T15:12:27Z","doi":"10.54216/jisiot.160119","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/icict64420.2025.11004915","name":"Detection of Artificially Generated Synthetic Images Using Parallel Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icict64420.2025.11004915","authors":["A Vishnupriya","Adarsh Tiwary"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-23T17:02:43Z","doi":"10.1109/icict64420.2025.11004915","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.17559/tv-20240501001513","name":"An ANP-Hopfield Neural Network Based Approach for Supply Chain Stress Testing","source":"crossref","abstract":"","url":"https://doi.org/10.17559/tv-20240501001513","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-28T14:45:41Z","doi":"10.17559/tv-20240501001513","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/sist61657.2025.11139350","name":"Depth-Guided Neural Network for Robust Face Anti-Spoofing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/sist61657.2025.11139350","authors":["Zhanseri Ikram"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-01T19:14:02Z","doi":"10.1109/sist61657.2025.11139350","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/icpics66386.2025.11347125","name":"Research on Deep Neural Network-Based Mood Prediction Model","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icpics66386.2025.11347125","authors":["Qin Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-28T20:54:45Z","doi":"10.1109/icpics66386.2025.11347125","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.23919/piers-fall62445.2025.11394658","name":"A Recurrent Neural Network Approach to Predicting Large Earthquakes","source":"crossref","abstract":"","url":"https://doi.org/10.23919/piers-fall62445.2025.11394658","authors":["Shuya Hara","Masao Masugi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-26T20:42:16Z","doi":"10.23919/piers-fall62445.2025.11394658","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5143186","name":"Graph Neural Network-Based Collaborative Filtering for Recommendation Systems","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5143186","authors":["Jun Yi","Xiaoqi Han","Wei Zhou","Shan Xiao","Chaoxu Mu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-18T14:43:34Z","doi":"10.2139/ssrn.5143186","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.20944/preprints202507.2651.v1","name":"Neural Network-Based Modeling for Precise Potato Yield Prediction Using Soil Parameters","source":"crossref","abstract":"This study analyses the potential of artificial neural networks (ANN) in accurately predicting potato yields based on 11 parameters characterising the soil environment. Accurate yield forecasting is crucial for optimising potato production, especially in the context of potato processing. Due to the significant impact of soil properties on yield, there is a need for comprehensive predictive models that take these factors into account. The field studies (2021-2024) included an analysis of soil parameters determining potato tuber yield. The developed ANN model was highly accurate, as evidenced by the following indicators: R² = 0.8227, RMSE = 4.19 t∙ha⁻¹, MAE = 3.35 t∙ha⁻¹, MAPE = 7.34%. Global sensitivity analysis showed that cation exchange capacity (CEC), base saturation percentage (V) and sum of exchangeable bases (S) are key parameters influencing tuber yield. The results indicate that neural networks are effective in modelling complex relationships between soil parameters and potato yield, and that soil properties play a fundamental role in increasing yields and improving potato quality. The approach used may contribute to optimising the nutrient content of potato tubers intended for French fry production. Future studies should include climate data and micronutrients to further improve predictive models.","url":"https://doi.org/10.20944/preprints202507.2651.v1","authors":["Magdalena Piekutowska","Gniewko Niedbała"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-01T00:47:06Z","doi":"10.20944/preprints202507.2651.v1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5380686","name":"Graph-Based Compactly Supported Radial Basis Function Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5380686","authors":["Hongjin Ren","Ruiping Niu","Dengao Li","Hongen Jia","Hongbin Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-05T20:37:01Z","doi":"10.2139/ssrn.5380686","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.21203/rs.3.rs-6478988/v1","name":"Enhanced Convolutional Neural Network for Robust Facial Expression Recognition on Fer2013 and Natural Image Datasets","source":"crossref","abstract":"Abstract This study presents an enhanced convolutional neural network (CNN) architecture tailored for accurate facial expression recognition. The model is trained on the FER2013 dataset and evaluated using both FER2013 and a custom dataset containing natural facial expressions. By incorporating multiple convolutional and pooling layers along with dropout regularization, the network effectively extracts and classifies emotion-related features. Experimental results demonstrate high recognition accuracy and strong generalization across controlled and real-world image scenarios. In order to study the application of convolutional neural networks in facial expression recognition, a 10-layer convolutional neural network model is designed to recognize facial expressions. The last layer uses the Softmax function to output the classification results of expressions. First, the convolution and pooling algorithms of convolutional neural networks were studied and the structure of the model was designed. Secondly, in order to more vividly display the features extracted by the convolutional layer, the extracted features are visualized and displayed in the form of feature maps. The convolutional neural network model in this work was tested on the Fer-2013 data set, and the experimental results demonstrated the superiority of the recognition rate. It is known that the Fer-2013 dataset contains data collected in an experimental environment, and in order to verify the generalization ability of model recognition, a self-made facial expression data set in natural state was created, and performed a series of preprocessing on the face images such as cropping, grayscale and pixel adjustment. The trained model, which was previously applied to the Fer-2013 dataset, was tested out on the new dataset. The experiment yielded promising results, one of which in the form of a recognition accuracy rate as high as 85.1%.","url":"https://doi.org/10.21203/rs.3.rs-6478988/v1","authors":["Prof. Prakash Sangle"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-22T18:28:44Z","doi":"10.21203/rs.3.rs-6478988/v1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2196/preprints.85127","name":"Clapping and Vibrating Caring  to Address Ineffective Airway Clearance Based on: Neural Network (Preprint)","source":"crossref","abstract":"BACKGROUND The accumulation of mucus in the airways is a serious health problem as it can obstruct airflow and impair lung function. This condition is typically managed by suctioning the mucus and performing manual chest clapping, which involves repeatedly patting the back. However, manual clapping is often ineffective and inefficient due to factors like operator fatigue and inconsistent application. This research introduces a portable clapping system called Clapping and Heater Integrated Caring device (CHIC) OBJECTIVE this research is to develop an automatic detection system that can reliably recognize human clapping and hand induced vibrations using wearable sensors. The study aims to design and implement pattern recognition algorithms, ranging from threshold based methods to lightweight machine learning models, that differentiate intentional clapping or vibrating gestures from environmental noise, and to evaluate the system’s real time performance in terms of accuracy, latency, and energy consumption across diverse usage scenarios. METHODS This research introduces an innovative medical device that integrates automatic clapping capabilities with a vibrating warm pillow. The goal of this innovation, named CHIC, is to overcome the limitations of manual methods and enhance the effectiveness of chest physiotherapy. A key feature that makes CHIC so relevant is the use of Neural Network (NN) technology to determine the number of claps based on the patient's condition RESULTS A Neural Network (NN) allows the system to adaptively generate the optimal clapping frequency based on the patient's physiological parameters, ensuring a more precise and personalized therapy compared to conventional approaches. Three different NN architectures were tested, and the one with three hidden layers and a neuron configuration of [20 30 40] proved to be the most effective. This configuration yielded a Mean Squared Error (MSE) of 0.00029279 for the training data and a Root Mean Squared Error (RMSE) of 0.02812 for the validation data. CONCLUSIONS The CHIC device demonstrated reliable performance for airway clearance therapy. Its ESP32 based control system, temperature monitoring, vibrating pillow, and rotary DC motor provided consistent and coordinated clapping actions. The integrated neural network algorithm dynamically adjusted the clapping frequency according to the patient’s physiological parameters, delivering a more precise and personalized treatment compared to manual chest percussion. The system operated without operator fatigue and maintained patient comfort, indicating that CHIC is an effective and practical solution for clinical and community based physiotherapy applications","url":"https://doi.org/10.2196/preprints.85127","authors":["Agus Khumaidi Khumaidi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-02T06:30:07Z","doi":"10.2196/preprints.85127","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/tgrs.2025.3602030/v1/decision1","name":"Decision letter for \"Physics-Inspired Neural Network for Joint Inversion of Multialtitude 3-D Gravity and Vertical Gradient\"","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tgrs.2025.3602030/v1/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-21T22:59:05Z","doi":"10.1109/tgrs.2025.3602030/v1/decision1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5211266","name":"Systematic Performance Analysis of Long Short-Term Memory Neural Network for Wind Speed Predictions","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5211266","authors":["Akram Miriyev","Wolf-Gerrit Fruh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-09T15:37:33Z","doi":"10.2139/ssrn.5211266","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.54985/peeref.2511a9775139","name":"Rhythmically Laminated Textures: Neural Network-Assisted Analysis Based on Discrete Angular Rotation Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.54985/peeref.2511a9775139","authors":["O.V. Gradov","A.B. Elfimov","N.A. Marnautov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-10T23:13:31Z","doi":"10.54985/peeref.2511a9775139","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.36227/techrxiv.176291893.35097559/v1","name":"Concurrent Generation of RSMTs for Multiple Nets using Graph Neural Network","source":"crossref","abstract":"A Rectilinear Steiner Minimum Tree (RSMT) is the shortest (in Manhattan distance) tree to interconnect a given set of 2D points called pins of a net, formed by joining only vertical and horizontal line (wire) segments through the pins and a few extra points called Steiner points. It is used as an initial skeleton route in many state-of-the-art global routers. However, finding an optimal RSMT is NP-hard. Existing techniques either generate optimal RSMTs in exponential/sub-exponential time or near-optimal RSMTs using heuristics or machine learning in polynomial time. However, each of these methods considers the construction of an RSMT of a single net at a time. The concurrent construction of RSMTs for multiple nets has the potential to reduce the overall construction time and edge-overlap mitigation of multiple nets. In this work, we propose a method for concurrent construction of RSMTs of multiple nets based on Graph Neural Network (GNN) with the aim of minimizing the overall construction time, group-wise edge-overlap and wirelength. Experimental results show that our model can generate RSMTs of K nets concurrently with significant reduction in construction time, group-wise edge-overlapping and wirelength as compared with multiple baseline methods.","url":"https://doi.org/10.36227/techrxiv.176291893.35097559/v1","authors":["Kritanta Saha","Mrinmoy Banik","Pritha Banerjee","Susmita Sur-Kolay"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-12T03:42:22Z","doi":"10.36227/techrxiv.176291893.35097559/v1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1039/d4sc07858f/v2/review1","name":"Review for \"IMPRESSION Generation 2 – Accurate, fast and generalised neural network model for predicting NMR parameters in place of DFT\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d4sc07858f/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-31T17:20:23Z","doi":"10.1039/d4sc07858f/v2/review1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.21203/rs.3.rs-7088954/v1","name":"A Novel RBF Neural Network-based Hybrid Technique and Its Applications","source":"crossref","abstract":"Abstract Recent studies have demonstrated that Radial Basis Function Neural Networks (RBFNNs), based on traditional methods like gradient descent, frequently produce local approximates after training. This motivation led us to propose an RBFNN-based novel hybrid algorithm that maintains the local and global approximation properties throughout the training process and maintains the balance between these approximation properties. This study introduces the RBFNN-based hybrid particle swarm optimization and cuckoo search with biogeography-based optimization (PSO-CS-BBO) algorithm for global exploration and optimal regions. Several experiments have taken place through six distinct methods for the initialization of RBFNN fitting to perceive the best alignment. Initially, the proposed hybrid was applied to a simple trigonometric function to find the ability of our approach to approximate the function, convergence graph, MSE, and stability analysis. In the final method, the Broyden-Fletcher-Goldfarb-Shanno (BFGS) method has been incorporated with our proposed technique to refine the outcome further and improve the convergence to the local optimum. This new hybrid scheme is capable of enhancing the training speed and convergence accuracy. Also, this hybrid-based network has been utilized in different real-world applications to evaluate its problem-solving capabilities, efficacy, and accuracy. The obtained results are rigorously compared with three existing RBFNN-based algorithms. The comparative analysis focused on approximate solutions, the algorithm's convergence, and mean square error (MSE). The proposed results reveal that the RBFNN-based hybrid technique is capable of solving complex, high-dimensional, stochastic, and nonlinear problems.","url":"https://doi.org/10.21203/rs.3.rs-7088954/v1","authors":["Sabir Ali","Jason A. Kurz","Sean oughton"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-24T03:01:06Z","doi":"10.21203/rs.3.rs-7088954/v1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5189246","name":"Optimizing Game Performance Through Ai-Driven Lod and Neural Network-Based Image Compression","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5189246","authors":["Mahyar Hassani-Vasmejani","Hosein Alavi-Rad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-22T13:37:09Z","doi":"10.2139/ssrn.5189246","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5203315","name":"Physics-Informed Modularized Neural Network for Advanced Building Control by Deep Reinforcement Learning","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5203315","authors":["zixin jiang","Xuezheng Wang","Bing Dong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-03T08:38:10Z","doi":"10.2139/ssrn.5203315","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.22541/essoar.175525655.54389731/v1","name":"Experimental Verification of a Two-Dimensional Inverse Method for Turbidity Currents Using a Deep Neural Network","source":"crossref","abstract":"Turbidites have been widely studied as indicators of the occurrences and magnitudes of paleo-tsunamis and paleo-earthquakes. Inversion to estimate the flow conditions from turbidites offers valuable insights into the magnitudes of paleo-seismic and tsunami events. However, conventional one-dimensional inverse models are insufficient for capturing the behavior of turbidity currents in tectonically active margins, where the seafloor topography is typically complex. Here, we developed a horizontal two-dimensional inverse model of turbidity currents based on a deep neural network (DNN) and evaluated its performance using both synthetic and flume experiment datasets. The model successfully estimated the model input parameters with a symmetric mean absolute percentage error (SMAPE) of less than 32.5%, except for the density-equivalent sediment concentration for saline water at the inlet. When applied to experimental data, the model reasonably reconstructed the flow conditions, yielding SMAPE values between 51.7 and 86.2%, despite the potential uncertainties introduced by sampling disturbances, data processing, and forward model limitations. The spatial distribution of bed thickness was also well predicted, except in cases where most of the suspension bypassed the depositional zone. Overall, the proposed inverse model demonstrated accuracy comparable to the previous one-dimensional model while offering greater applicability to complex seafloor geometries and maintaining low computational costs. These results suggest that the proposed method is well-suited for the field-scale inversion of turbidity currents in realistic geological settings.","url":"https://doi.org/10.22541/essoar.175525655.54389731/v1","authors":["Seiya Fujishima","Hajime Naruse"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-15T11:16:04Z","doi":"10.22541/essoar.175525655.54389731/v1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1007/s00521-025-11040-9","name":"Developing block-based physics-informed multi-layered neural network model for simulating the inelastic response of base-isolated structures","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-025-11040-9","authors":["Ahed Habib","Umut Yildirim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-13T02:18:13Z","doi":"10.1007/s00521-025-11040-9","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/ijcnn64981.2025.11227743","name":"DAGNet: A Dynamic Aggregation and Generation Network for Next POI Recommendation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn64981.2025.11227743","authors":["Yanli Zhang","Guochen Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T18:46:15Z","doi":"10.1109/ijcnn64981.2025.11227743","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/ijcnn64981.2025.11227187","name":"Deep Non-monotone Submodular Network: An Application to Conditional Video Summarization","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn64981.2025.11227187","authors":["Xiaowei Gu","Lu Lu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T18:46:15Z","doi":"10.1109/ijcnn64981.2025.11227187","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5088428","name":"Optimization and Range Expansion of Iris Reactor Accident Diagnosis Model Based on Lstm Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5088428","authors":["Tianze BAI","Changhong PENG"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-08T23:38:37Z","doi":"10.2139/ssrn.5088428","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1039/d5ya00093a/v2/review2","name":"Review for \"A Sampling Fault Diagnosis Method for Power Battery Data in Cloud Platform Based on ResNet-BiLSTM Neural Network\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5ya00093a/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-25T21:09:14Z","doi":"10.1039/d5ya00093a/v2/review2","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5426897","name":"What Hinders Electric Vehicle Diffusion? Insights from a Neural Network Approach","source":"crossref","abstract":"The transition to a zero-emission vehicle fleet represents a pivotal element of Europe's decarbonization strategy, with Italy's participation being particularly significant given the size of its automotive market. This study investigates the potential for battery electric cars (BEVs) to drive decarbonization of Italy's passenger vehicle fleet, focusing on the feasibility of targets set in the National Integrated Plan for Energy and Climate (PNIEC). Leveraging artificial neural networks, we integrate macroeconomic indicators, market-specific variables, and policy instruments to predict fleet dynamics and identify key factors influencing BEV adoption. We forecast that while BEV registrations will continue growing through 2030, the growth rate is projected to decelerate, presenting challenges for meeting ambitious policy targets. Our feature importance analysis demonstrates that BEV adoption is driven by an interconnected set of economic, infrastructural, and behavioral factors. Specifically, our model highlights that hybrid vehicle registrations and the vehicle purchase index exert the strongest influence on BEV registrations, suggesting that policy interventions should prioritize these areas to maximize impact. By offering data-driven insights and methodological innovations, our findings contribute to more effective policy design for accelerating sustainable mobility adoption while accounting for market realities and consumer behavior.","url":"https://doi.org/10.2139/ssrn.5426897","authors":["Monica Bonacina","Mert Demir","Antonio Sileo","Angela Zanoni"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-02T08:54:33Z","doi":"10.2139/ssrn.5426897","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1007/978-1-4471-2003-2_7","name":"Linear Quadtrees for Neural Network Based Position Invariant Pattern Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4471-2003-2_7","authors":["Emmanouel C. Mertzanis","James Austin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-12-02T14:54:17Z","doi":"10.1007/978-1-4471-2003-2_7","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/ccsb66722.2025.11154226","name":"A TOE-BP Neural Network Model for Pharmaceutical Digital Transformation Prediction","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ccsb66722.2025.11154226","authors":["Duoduo Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-17T17:29:13Z","doi":"10.1109/ccsb66722.2025.11154226","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/ijcnn64981.2025.11227630","name":"ASOD-Net: Arbitrary Sampling and Offset-based Detection Network for Remote Sensing Image","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn64981.2025.11227630","authors":["Xiwei Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T18:46:15Z","doi":"10.1109/ijcnn64981.2025.11227630","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/icetci64844.2025.11084122","name":"Key node identification method based on graph neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icetci64844.2025.11084122","authors":["Xian Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-24T17:50:58Z","doi":"10.1109/icetci64844.2025.11084122","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/ijcnn64981.2025.11227809","name":"MGFI-Net: A Multi-Grained Feature Integration Network for Enhanced Medical Image Segmentation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn64981.2025.11227809","authors":["Yucheng Zeng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T18:46:15Z","doi":"10.1109/ijcnn64981.2025.11227809","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1088/0954-898x/9/2/003","name":"Learning attractors in an asynchronous, stochastic electronic neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/9/2/003","authors":["P Del Giudice","S Fusi","D Badoni","V Dante","D Amit"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/9/2/003","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1088/0954-898x/9/1/007","name":"Slow stochastic Hebbian learning of classes of stimuli in a recurrent neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/9/1/007","authors":["Nicolas Brunel","Francesco Carusi","Stefano Fusi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/9/1/007","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1016/j.neunet.2025.107725","name":"Neural-network-based event-triggered adaptive secure fault-tolerant containment control for nonlinear multi-agent systems under denial-of-service attacks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107725","authors":["Xiangjun Wu","Shuo Ding","Ning Zhao","Huanqing Wang","Ben Niu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-18T13:53:02Z","doi":"10.1016/j.neunet.2025.107725","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1007/s00521-024-10963-z","name":"FLAME: fire detection in videos combining a deep neural network with a model-based motion analysis","source":"crossref","abstract":"Abstract Among the catastrophic natural events posing hazards to human lives and infrastructures, fire is the phenomenon causing more frequent damages. Thanks to the spread of smart cameras, video fire detection is gaining more attention as a solution to monitor wide outdoor areas where no specific sensors for smoke detection are available. However, state-of-the-art fire detectors assure a satisfactory Recall but exhibit a high false-positive rate that renders the application practically unusable. In this paper, we propose FLAME, an efficient and adaptive classification framework to address fire detection from videos. The framework integrates a state-of-the-art deep neural network for frame-wise object detection, in an automatic video analysis tool. The advantages of our approach are twofold. On the one side, we exploit advances in image detector technology to ensure a high Recall. On the other side, we design a model-based motion analysis that improves the system’s Precision by filtering out fire candidates occurring in the scene’s background or whose movements differ from those of the fire. The proposed technique, able to be executed in real-time on embedded systems, has proven to surpass the methods considered for comparison on a recent literature dataset representing several scenarios. The code and the dataset used for designing the system have been made publicly available by the authors at ( https://mivia.unisa.it/large-fire-dataset-with-negative-samples-lfdn/ ).","url":"https://doi.org/10.1007/s00521-024-10963-z","authors":["Diego Gragnaniello","Antonio Greco","Carlo Sansone","Bruno Vento"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-09T04:02:44Z","doi":"10.1007/s00521-024-10963-z","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5185708","name":"Revisiting Market Efficiency: An Application of Recurrent Neural Network GRU-D Model","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5185708","authors":["Abdelhamid Ben Jbara","Marjène Rabah","Mejda Dakhlaoui"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-15T17:39:19Z","doi":"10.2139/ssrn.5185708","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.21203/rs.3.rs-6479514/v1","name":"BP Neural Network Model for Late-Night Effects Prediction in Postgraduates' Hypertension","source":"crossref","abstract":"Abstract Graduate students exhibit a higher propensity for nocturnal hypertension episodes compared to the general working population. This study investigated the correlation between blood pressure and various physiological parameters, developing a continuous blood pressure prediction model based on highly correlated characteristics. Using a convenience sampling method involving physical examinations and structured questionnaires, 119 master's and doctoral students were selected. A BP neural network prediction model was constructed to analyze the impact of late-night academic work and dietary habits on blood pressure, identifying key influencing factors. Analysis demonstrated the model's high accuracy in blood pressure prediction, facilitating personalized health behavior recommendations. Evaluation metrics such as mean absolute error (MAE), standard deviation of error (SDE), root mean square error (RMSE), and R 2 were employed, achieving MAE = 3.56, SDE = 5.16, RMSE = 8.09, and R 2 = 0.99866 for systolic blood pressure (SBP), and MAE = 3.34, SDE = 4.46, RMSE = 7.26, and R 2 = 0.99284 for diastolic blood pressure (DBP) across test sets. These results met the standards set by the Association for the Advancement of Medical Instrumentation (AAMI). Factor weight analysis identified sleep duration (19.39%) and body weight as key hypertension drivers, followed by exercise duration, dietary habits, and emotional regulation. Prioritizing these factors is critical for developing targeted interventions. Systematic analysis of health data in research cohorts, particularly quantifying their pathogenic contributions to hypertension pathogenesis, advances predictive modeling and precision treatment frameworks.","url":"https://doi.org/10.21203/rs.3.rs-6479514/v1","authors":["Yanrui Che","Guangqing Li","Jingyao Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-15T11:02:27Z","doi":"10.21203/rs.3.rs-6479514/v1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1002/we.70052/v2/review1","name":"Review for \"Scaled Physical Modelling of Floating Offshore Wind Turbines Using a Neural Network‐Based Surrogate Model for Aerodynamic Emulation\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/we.70052/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-01T00:12:43Z","doi":"10.1002/we.70052/v2/review1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1002/eng2.70373/v3/review1","name":"Review for \"Enhancing Cardiovascular Disease Analysis in Healthcare Systems With Hybrid Random Forest and Neural Network Algorithm\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/eng2.70373/v3/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T23:21:22Z","doi":"10.1002/eng2.70373/v3/review1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.32388/1ozlen","name":"Review of: \"Synthetic Data Generation of Body Motion Data by Neural Gas Network for Emotion Recognition\"","source":"crossref","abstract":"","url":"https://doi.org/10.32388/1ozlen","authors":["Wellington P. dos Santos"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-22T09:41:21Z","doi":"10.32388/1ozlen","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.36227/techrxiv.176592058.84380101/v1","name":"An Energy-Efficient RFET-Based Stochastic Computing Neural Network Accelerator","source":"crossref","abstract":"Stochastic computing (SC) offers significant reductions in hardware complexity for traditional convolutional neural networks (CNNs). However, despite its advantages, stochastic computing neural networks (SCNNs) often suffer from high resource consumption due to components such as stochastic number generators (SNGs) and accumulative parallel counters (APCs), which limit overall performance. This paper proposes a novel SCNN architecture leveraging reconfigurable field-effect transistors (RFETs). The inherent reconfigurability at the device level enables the design of highly efficient and compact SNGs, APCs, and other essential components. Furthermore, a dedicated SCNN accelerator architecture is developed to facilitate system-level simulation. Based on accessible open-source standard cell libraries, experimental results demonstrate that the proposed RFET-based SCNN accelerator achieves significant reductions in area, latency, and energy consumption compared to its FinFET-based counterpart at the same technology node.","url":"https://doi.org/10.36227/techrxiv.176592058.84380101/v1","authors":["Sheng Lu","Qainhou Qu","Sungyong Jung","Qilian Liang","Chenyun Pan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-16T21:29:53Z","doi":"10.36227/techrxiv.176592058.84380101/v1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5143083","name":"Structural Damage Detection Using Graph Neural Network-Based Probabilistic Graphical Models","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5143083","authors":["Teng Li","Stephen Wu","Yong Huang","Hui Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-18T13:37:10Z","doi":"10.2139/ssrn.5143083","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5599420","name":"Graph Neural Network Enhanced Large Language Model for Commonsense Question Answering","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5599420","authors":["Shenggen Ju","Xingyue Li","Baoxing Jiang","Li Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-13T23:27:02Z","doi":"10.2139/ssrn.5599420","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1088/2634-4386/addee7/v1/review2","name":"Review for \"A spiking photonic neural network of 40,000 neurons, trained with latency and rank-order coding for leveraging sparsity\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2634-4386/addee7/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-31T17:07:02Z","doi":"10.1088/2634-4386/addee7/v1/review2","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5659495","name":"Emergent neural network-like mechanical response in interlocking materials","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5659495","authors":["Peng jiang","Jixiang Qi","Zengqin Shi","Heng Yang","Ying Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-25T16:39:01Z","doi":"10.2139/ssrn.5659495","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.33407/lib.naes.id/748283","name":"Chapter ХVІ. Neural network modeling and optimization of technological modes in polyvinyl chloride production","source":"crossref","abstract":"This study is dedicated to enhancing the efficiency of industrial polyvinyl chloride synthesis via the suspension polymerization of vinyl chloride. Research has been conducted on constructing the \"temperature trajectory\" of the suspension polymerization process based on the \"thermal shock\" strategy, according to which the final reaction temperature is increased to accelerate the reaction rate (reduce its duration). In accordance with the research objectives, a comprehensive analysis was carried out to assess the impact of technological parameters (the timing of additional vinyl chloride monomer introduction and the moment of thermal shock) on the quality of the obtained polyvinyl chloride. As a result of neural network approximation of active experimental data and multi-criteria optimization, the optimal values of technological factors were determined, ensuring the best quality indicators of polyvinyl chloride compared to operations conducted under the standard (isothermal) technological mode.","url":"https://doi.org/10.33407/lib.naes.id/748283","authors":["Arcady Shakhnovsky","Oleksandr Kvitka","Oleg Koliushko"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-03T12:32:17Z","doi":"10.33407/lib.naes.id/748283","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1002/eng2.70373/v2/review2","name":"Review for \"Enhancing Cardiovascular Disease Analysis in Healthcare Systems With Hybrid Random Forest and Neural Network Algorithm\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/eng2.70373/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T23:21:22Z","doi":"10.1002/eng2.70373/v2/review2","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1002/eng2.70373/v3/decision1","name":"Decision letter for \"Enhancing Cardiovascular Disease Analysis in Healthcare Systems With Hybrid Random Forest and Neural Network Algorithm\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/eng2.70373/v3/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T23:21:22Z","doi":"10.1002/eng2.70373/v3/decision1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1364/opticaopen.28902587.v1","name":"Q-factor Analysis in Free Space Optical Communication and Neural Network-Based Prediction","source":"crossref","abstract":"Free Space Optics (FSO) provides a promising alternative where fiber-optic deployment is impractical due to cost or fragility. However, FSO performance is highly vulnerable to atmospheric disturbances such as fog, rain, and dust, which can significantly degrade signal quality. To optimize system performance under varying conditions, it is crucial to understand how the Q-factor responds to changes in system parameters. This study investigates the effects of bit rate, filter type, transmitter and receiver aperture diameters, and transmission range on the Q-factor in FSO systems. We developed a detailed simulation model using OptiSystem to generate data, which was then used to train a feedforward neural network via MATLAB’s Neural Network Tool (NN-Tool) using the Levenberg–Marquardt algorithm. This model effectively captures complex, nonlinear relationships between input parameters and Q-factor outcomes, allowing accurate predictions without further simulations. The hybrid approach of combining simulation data with neural network-based modeling offers a practical and user-friendly tool for performance prediction and system planning. This research contributes to the design and optimization of high-data-rate FSO systems by addressing existing limitations in modeling and parameter tuning.","url":"https://doi.org/10.1364/opticaopen.28902587.v1","authors":["Mohammad Sikder","Fahim Sakib","Md Lokman Hossen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-06T10:25:22Z","doi":"10.1364/opticaopen.28902587.v1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.31224/4738","name":"Physics-informed neural network framework for solving forward and inverse flexoelectric problems","source":"crossref","abstract":"Flexoelectricity, the coupling between strain gradients and electric polarization, poses significant computational challenges due to its governing fourth-order partial differential equations that require C¹-continuous solutions. To address these issues, we propose a physics-informed neural network (PINN) framework grounded in an energy-based formulation that treats both forward and inverse problems within a unified architecture. The forward problem is recast as a saddle-point optimization of the total potential energy, solved via the deep energy method (DEM), which circumvents the direct computation of high-order derivatives. For the inverse problem of identifying unknown flexoelectric coefficients from sparse measurements, we introduce an additional variational loss that enforces stationarity with respect to the electric potential, ensuring robust and stable parameter inference. The framework integrates finite element-based numerical quadrature for stable energy evaluation and employs hard constraints to rigorously enforce boundary conditions. Numerical results for both direct and converse flexoelectric effects show excellent agreement with mixed-FEM solutions, and the inverse model accurately recovers material parameters from limited data. This study establishes a unified, mesh-compatible, and scalable PINN approach for high-order electromechanical problems, offering a promising alternative to traditional simulation techniques.","url":"https://doi.org/10.31224/4738","authors":["Hyeonbin Moon","Donggeun Park","Jinwook Yeo","Seunghwa Ryu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-26T16:30:36Z","doi":"10.31224/4738","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/spw67851.2025.00032","name":"Ignoring Directionality Leads to Compromised Graph Neural Network Explanations","source":"crossref","abstract":"","url":"https://doi.org/10.1109/spw67851.2025.00032","authors":["Changsheng Sun","Xinke Li","Jin Song Dong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-03T17:26:56Z","doi":"10.1109/spw67851.2025.00032","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.23919/ccc64809.2025.11179354","name":"A Gated Convolutional Neural Network-Based Method for Crop Phenotype Prediction","source":"crossref","abstract":"","url":"https://doi.org/10.23919/ccc64809.2025.11179354","authors":["Jing Xu","Yuxia Sheng","Wenyu Peng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-10T17:34:54Z","doi":"10.23919/ccc64809.2025.11179354","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.26855/acc.2025.07.001","name":"Research on Image Denoising Method Based on Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.26855/acc.2025.07.001","authors":["Shiqi Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-04T03:41:02Z","doi":"10.26855/acc.2025.07.001","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/smartindustrycon65166.2025.10986163","name":"Neural Network Despeckling for Ultrasound Phased Diagnostics of Metallic Details","source":"crossref","abstract":"","url":"https://doi.org/10.1109/smartindustrycon65166.2025.10986163","authors":["Yury S. Bekhtin","Konstantin M. Vorobiev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-09T17:56:01Z","doi":"10.1109/smartindustrycon65166.2025.10986163","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1016/j.energy.2025.137762","name":"Forecasting annual electricity consumption in Vietnam using radial basis function neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.energy.2025.137762","authors":["Thanh Hoa Bui","Keunjae Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-28T23:24:09Z","doi":"10.1016/j.energy.2025.137762","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/icpics66386.2025.11347379","name":"Pig Voice Classification Algorithm Based on Deep Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icpics66386.2025.11347379","authors":["Yanghong Qin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-28T20:54:45Z","doi":"10.1109/icpics66386.2025.11347379","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1016/j.neunet.2024.107015","name":"OperaGAN: A simultaneous transfer network for opera makeup and complex headwear","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2024.107015","authors":["Yue Ma","Chunjie Xu","Wei Song","Hanyu Liang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-09T17:08:46Z","doi":"10.1016/j.neunet.2024.107015","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.5194/egusphere-egu24-11928","name":"The dynamics of field soil water retention curves predicted by autoencoder neural network","source":"crossref","abstract":"The matric potential plays a pivotal role in understanding of water movement, plant water availability, and mechanical stability. In lack of direct measurements, the matric potential dynamics must be deduced from soil water content values, using the soil water retention curve. This approach is of particular importance at larger scales where only the water content (but not the potential) can be deduced from satellite data. However, because the relationship between water content and matric potential in natural field soils is highly ambiguous, not unique and dynamic, the prediction of matric potential from water content data is a big challenge. This ambiguity is related to different structures controlling drainage and wetting, dynamic effects, and seasonal changes of structures controlling the water distribution. In this study we present an autoencoder neural network as a new approach to analyze the soil moisture dynamics and to predict matric potential from water content data. The autoencoder compresses the water content time series into a site-specific feature (denoted as autoencoder value, AUV) that is representative of the underlying soil moisture dynamics. The AUV can then be used as predictor of the matric potential and the highly hysteretic soil water retention curve. The approach was tested successfully for nine soil profiles in the region of Solothurn (Switzerland). Three sites were chosen to establish the connection between AUV and the ambiguous soil water retention curve using a deep neural network, that was then applied to predict the matric potential dynamics of the other six sites. This method offers the potential to (i) deduce matric potential dynamics by relying solely on soil water content measurements (including satellite data), even when strong seasonal effects challenge standard methods, and (ii) serves as a warning system for changes in soil properties and in the intricate relationship between soil water content and matric potential dynamics.","url":"https://doi.org/10.5194/egusphere-egu24-11928","authors":["Nedal Aqel","Andrea Carminati","Peter Lehmann"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-08T22:29:45Z","doi":"10.5194/egusphere-egu24-11928","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1002/we.2976/v3/review1","name":"Review for \"Volt/VAr Regulation of the West Mediterranean Regional Electrical Grids Using SVC/STATCOM Devices With Neural Network Algorithms\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/we.2976/v3/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-25T16:09:21Z","doi":"10.1002/we.2976/v3/review1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5266015","name":"Anomaly Detection in Network Traffic Logs Using Image Transformation Techniques and Deep Convolutional Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5266015","authors":["Harry Wilson","James Wright"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-27T15:34:17Z","doi":"10.2139/ssrn.5266015","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/ic-nidc67200.2025.11390543","name":"Memristor-Based Circuit-Level Design of FFT Calculator for OFDM Systems in Internet of Things","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ic-nidc67200.2025.11390543","authors":["Luhan Wang","Haozhe Jin","Kehan Wang","Zhaoming Lu","Xiangming Wen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-24T20:54:40Z","doi":"10.1109/ic-nidc67200.2025.11390543","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1002/eng2.70019/v1/decision1","name":"Decision letter for \"Improved Conjugate Gradient Methods for Unconstrained Minimization Problems and Training Recurrent Neural Network\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/eng2.70019/v1/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-11T16:14:26Z","doi":"10.1002/eng2.70019/v1/decision1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/tgrs.2025.3602030/v3/decision1","name":"Decision letter for \"Physics-Inspired Neural Network for Joint Inversion of Multialtitude 3-D Gravity and Vertical Gradient\"","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tgrs.2025.3602030/v3/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-21T22:59:05Z","doi":"10.1109/tgrs.2025.3602030/v3/decision1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5312999","name":"Directed Hypergraph Neural Network: Building a Predictive Framework","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5312999","authors":["Yousra Moh Ousellam","Bikram Pratim BHUYAN","Rachida Fissoune","Amar  Ramdane Cherif"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T09:38:06Z","doi":"10.2139/ssrn.5312999","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5745985","name":"Invertible Coarse-to-Fine Neural Network for Defocus Deblurring with learned blur representation","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5745985","authors":["Yan Huang","Juan Chen","Hui Ji"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T03:39:17Z","doi":"10.2139/ssrn.5745985","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1007/s00521-025-11457-2","name":"Edge-supervised convolutional neural network for histopathological classification of oral cancer images","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-025-11457-2","authors":["Ahmed M. Gab Allah","Mohamed M. S. Gaballa","Nada M. Elshennawy","Amr Elkholy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-04T12:30:13Z","doi":"10.1007/s00521-025-11457-2","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.14341/dm13091-6933","name":"Figure 1. Neural network configuration.","source":"crossref","abstract":"","url":"https://doi.org/10.14341/dm13091-6933","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-20T07:35:41Z","doi":"10.14341/dm13091-6933","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1007/s00521-025-11653-0","name":"An efficient deep convolutional network model using mask images for multiclass classification of breast cancer ultrasound images","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-025-11653-0","authors":["Kadir Can Burçak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-16T12:29:21Z","doi":"10.1007/s00521-025-11653-0","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.53656/adpe-2025.09","name":"Surface shaping mechatronic neural network","source":"crossref","abstract":"Neural networks are fundamental concept in artificial intelligence and machine learning, inspired by the structure and function of the human brain. A neural network is a computational model composed of interconnected nodes (called neurons or units) organized in layers. These networks are designed to recognize patterns, learn from data, and make predictions or decisions. As a part of the neural networks, mechanical neural networks are physical systems designed to mimic the behavior of artificial neural networks using mechanical components. These systems leverage the properties of materials and structures to process information, adapt to external stimuli, or perform tasks such as pattern recognition, optimization, or control. The developed surface-shaping mechanical neural network is based on systems with parallel kinematics but in addition contains sensing elements part of the electronic system controlled by developed software. The system can adapt its surface geometry depend on the external stimuli, in this case the force applied on it.","url":"https://doi.org/10.53656/adpe-2025.09","authors":["Dobri Komarski","Velizar Vassilev","Hristiana Nikolova"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-04T17:16:16Z","doi":"10.53656/adpe-2025.09","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1049/icp.2025.2450","name":"Neural network based wireless charging output control strategy for UAVs","source":"crossref","abstract":"","url":"https://doi.org/10.1049/icp.2025.2450","authors":["Yixun Feng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-11T12:15:40Z","doi":"10.1049/icp.2025.2450","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/ijcnn64981.2025.11228142","name":"Contrastive Denoising Variational Recurrent Neural Network for Noise-Agnostic State Modeling of Soft Robotic Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn64981.2025.11228142","authors":["Shageenderan Sapai","Vishnu Monn Baskaran","Junn Yong Loo","Surya Nurzaman","Chee Pin Tan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T18:46:15Z","doi":"10.1109/ijcnn64981.2025.11228142","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5178853","name":"A Constraint-Preserving Neural Network Approach for Mean-Field Games Equilibria","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5178853","authors":["Jinwei Liu","Lu Ren","Wang Yao","Xiao Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-14T19:36:11Z","doi":"10.2139/ssrn.5178853","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5185403","name":"Aerodynamic Recovery in a Solar-Gas Turbine Power Plant, Performance Prediction Via Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5185403","authors":["mohamadreza sabzeali","Saeed Karimian Aliabadi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-19T15:48:22Z","doi":"10.2139/ssrn.5185403","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5599650","name":"Utilizing physics-informed neural network and geotechnical distance field for solving three-dimensional nonlinear consolidation","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5599650","authors":["Khiem Nguyen","Jongmuk Won"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-13T19:36:42Z","doi":"10.2139/ssrn.5599650","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5235863","name":"Yield Prediction of Prunus Humilis Fruits Based on Pso-Bp Artificial Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5235863","authors":["Jiahui Li","Linyou Lv","Yan Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-29T17:37:44Z","doi":"10.2139/ssrn.5235863","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.5194/egusphere-egu25-15255","name":"A Novel Global Gridded Ocean Oxygen Product Derived from Neural Network Emulators (1965&amp;#8211;2022)","source":"crossref","abstract":"Over the past decades, global ocean oxygen inventories have declined by 0.5&amp;#8211;3.3% relative to historical averages, with significant uncertainties in data-sparse regions such as the South Pacific and Indian Oceans. These gaps hinder accurate estimates of deoxygenation rates, potentially leading to underestimation of its magnitude. In this context, gridded oxygen products are essential for assessing global and regional trends and projecting the impacts of deoxygenation on marine ecosystems. However, traditional Optimal Interpolation (OI) methods are known to underestimate ocean oxygen loss, particularly in poorly observed areas.To address these limitations, we propose a novel approach to build a gridded oxygen concentration product. Specifically, we develop a neural network emulator of oxygen concentration based on temperature and salinity measurements. This neural network is then used to generate emulated oxygen concentration data, which are combined with dissolved oxygen measurements to produce a new global gridded oxygen concentration product spanning 1965 to 2022. We evaluate our product against climatological estimates from the World Ocean Atlas and other gridded oxygen products. Future work will leverage this gridded product to study the regional evolution of ocean deoxygenation, particularly in Oxygen Minimum Zone (OMZ) regions.","url":"https://doi.org/10.5194/egusphere-egu25-15255","authors":["Zouhair Lachkar","Said Ouala"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-15T03:19:02Z","doi":"10.5194/egusphere-egu25-15255","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5320214","name":"Quadrotor Attitude Control Under Perturbations with Neural Network and State Observer","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5320214","authors":["Ende Wang","Ziyao Chen","Jiageng Liu","Boxuan Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-25T16:44:34Z","doi":"10.2139/ssrn.5320214","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1002/eng2.70019/v2/decision1","name":"Decision letter for \"Improved Conjugate Gradient Methods for Unconstrained Minimization Problems and Training Recurrent Neural Network\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/eng2.70019/v2/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-11T16:14:26Z","doi":"10.1002/eng2.70019/v2/decision1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.36227/techrxiv.176617687.72969471/v1","name":"Neural Network Model Tree Prediction for Passive Microwave Sensor Quality Control","source":"crossref","abstract":"Earth remote sensing algorithms for spaceborne passive microwave sensors depend on high quality observations of top-of-atmosphere radiances. When these observations are adversely affected by non-geophysical processes, such as radio frequency interference (RFI), calibration drifts, or sensor anomalies, they can have detrimental impacts on retrievals or their assimilation into models. The rise of machine learning applications has exacerbated this problem because non-linear schemes can reveal even small issues with the data. A simple and computationally inexpensive method is presented for assessing the quality of observations both instantaneously and over time using a fully connected neural network model tree. The basic premise of this scheme involves using n-1 channels to predict the nth channel, and then identifying when the prediction error is larger than normal in order to identify potentially anomalous observations. Prediction error thresholds are chosen based on the application, and well-trained models with high correlations between channels can have prediction errors on the order of the noise-equivalent differential temperature (NEDT) of the sensor (less than 1 K in most cases). We find that this method is effective for identifying various types of observational problems and present case studies to this effect that demonstrate radio frequency interference, sensor electronic and physical anomalies, sun glint, and channel performance degradation. We also find that its sensitivity is ideal for quality control, even when the observational data has previously passed operational quality checks, and that this tool can be used to effectively prescreen problematic observations that may not be initially identifiable in the data application. This tool is readily available to the remote sensing community through freely distributed code with examples on training and application via a link provided in the Data Availability statement of this article.","url":"https://doi.org/10.36227/techrxiv.176617687.72969471/v1","authors":["Spencer R. Jones","Paula J. Brown","Christian D. Kummerow"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-19T20:41:15Z","doi":"10.36227/techrxiv.176617687.72969471/v1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1007/s00521-024-10940-6","name":"Radial basis function network-based optimization of the hard self-propelled rotary turning titanium","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-024-10940-6","authors":["Trung-Thanh Nguyen","Xuan-Ba Dang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-03T04:09:55Z","doi":"10.1007/s00521-024-10940-6","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1002/aisy.202100151","name":"Spike‐Enabled Audio Learning in Multilevel Synaptic Memristor Array‐Based Spiking Neural Network","source":"crossref","abstract":"Speech recognition involves the ability to learn the audios which are closely related to event sequence. Although speech recognition has been widely implemented in software neural networks, a hardware implementation based on energy efficient computing architecture is still missing. Herein, W/MgO/SiO 2 /Mo memristor arrays with multilevel resistance states are fabricated, where the weights of the artificial synapses in the memristor array can be tuned precisely by voltage pulses. Based on the array, speech recognition in memristive spiking neural networks (SNNs) with improved supervised tempotron algorithm on Texas Instruments digit sequences (TIDIGITS) dataset is conducted, demonstrating software‐comparable accuracy for speech recognition in the memristive SNN. It is envisioned that such memristive SNNs can pave the way to building a bioinspired spike‐based neuromorphic system for audio learning.","url":"https://doi.org/10.1002/aisy.202100151","authors":["Xulei Wu","Bingjie Dang","Hong Wang","Xiulong Wu","Yuchao Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-10-21T04:19:43Z","doi":"10.1002/aisy.202100151","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1007/s00521-025-11325-z","name":"Stock price forecasting through symbolic dynamics and state transition graphs with a convolutional recurrent neural network architecture","source":"crossref","abstract":"Abstract Accurate stock price forecasting remains a critical challenge in financial analytics due to volatile market conditions, non-stationary dynamics, and abrupt regime shifts that often defy traditional modeling techniques. This study proposes a comprehensive framework for stock price forecasting that integrates symbolic dynamics, graph-based state representations, and deep learning. By converting continuous-valued stock prices into discrete symbolic states representing amplitude and trend information, the method constructs transition matrices capturing probabilistic relationships within financial time series. These transition matrices are then processed by a convolutional recurrent neural network (CRNN), in which convolutional layers isolate local spatial dependencies in the symbolic-state domain, while recurrent LSTM layers capture multi-scale temporal dynamics extending across multiple time horizons. Experimental evaluations are conducted over prediction horizons of 1 day, 10 days, and 100 days, spanning pre-COVID, COVID, and post-COVID market regimes. The results indicate that while longer prediction horizons naturally incur greater forecasting uncertainty due to compounding variability, the integration of symbolic-state preprocessing with deep temporal modeling demonstrates significant robustness in handling non-stationary financial environments. During the stable pre-COVID period, the proposed methodology achieves reductions in mean squared error (MSE) of up to 98% relative to the volatile COVID phase, highlighting its capability to effectively leverage well-defined market patterns in stable economic conditions. Furthermore, the model consistently delivers competitive forecasting performance across all prediction horizons and market regimes. Collectively, these findings emphasize the potential of symbolic-state-based deep learning architectures as a viable pathway to address the complexity and volatility characteristic of modern financial markets.","url":"https://doi.org/10.1007/s00521-025-11325-z","authors":["Fuat Kaan Mirza","Önder Pekcan","Mustafa Hekimoğlu","Tunçer Baykaş"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-31T06:21:29Z","doi":"10.1007/s00521-025-11325-z","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1039/d5tc02764k/v2/decision1","name":"Decision letter for \"Tuneable Ionic Memristor Based on Bipolar Electrochemistry\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5tc02764k/v2/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-15T21:06:09Z","doi":"10.1039/d5tc02764k/v2/decision1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1088/0954-898x_6_4_007","name":"Neural modelling of psychiatric disorders","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_6_4_007","authors":["Eytan Ruppin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:29Z","doi":"10.1088/0954-898x_6_4_007","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1016/0893-6080(88)90492-3","name":"Loan underwriting by a neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90492-3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T05:05:53Z","doi":"10.1016/0893-6080(88)90492-3","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1016/j.est.2025.116907","name":"The integration of the convolutional neural network and fourier neural network methods for the battery pack capacity prediction","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.est.2025.116907","authors":["Xiang Chen","Zuhang Chen","Xingxing Wang","Yelin Deng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-08T16:02:41Z","doi":"10.1016/j.est.2025.116907","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.6113/tkpe.2025.30.5.450","name":"Time-Delay Neural Network based P&amp;O MPPT Control Method","source":"crossref","abstract":"","url":"https://doi.org/10.6113/tkpe.2025.30.5.450","authors":["Hak-Soo Kim","Yong-Kyo Seo","Sung-Kwan Kang","Dong-Hyun Lim","Eui-Cheol Nho"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-20T03:08:04Z","doi":"10.6113/tkpe.2025.30.5.450","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/noms57970.2025.11073582","name":"Granomaly: A Framework for Anomaly Detection in 5G Core Network Control Plane Traffic with Temporal Graph Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/noms57970.2025.11073582","authors":["Tobias Fritz","Alexander Schwankner","Jan-Hendrik Wissing","Robin Buchta","Gabi Dreo Rodosek"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-15T17:40:26Z","doi":"10.1109/noms57970.2025.11073582","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5404818","name":"A Transformer-Based Neural Network for Global Dust Nowcasting","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5404818","authors":["Shikang Du","Siyu Chen","Jiaqi He","Yu Fu","Lulu Lian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-25T17:38:51Z","doi":"10.2139/ssrn.5404818","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5388900","name":"Hybrid Physics-Informed Neural Network for Battery State of Health Prediction: A Data-Driven Digital Twin Approach","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5388900","authors":["Rohan Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-12T15:18:19Z","doi":"10.2139/ssrn.5388900","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5210864","name":"Physics-Informed Modularized Neural Network for Advanced Building Control by Deep Reinforcement Learning","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5210864","authors":["zixin jiang","Xuezheng Wang","Bing Dong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-09T10:36:33Z","doi":"10.2139/ssrn.5210864","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.31219/osf.io/gzjfy_v1","name":"Exploring Quantum Convolutional Neural Network for Fault Detection in Semiconductor Wafers","source":"crossref","abstract":"This research work on the well-known WM811K wafer map dataset intends to integrate the insights provided by wafer manufacturing techniques and the computing power of quantum convolutional neural networks (QCNN) approach. The work begins with demonstrating high accuracy (𝑹 𝟐 =99.32%) of the classical convolutional neural network (CCNN) consisting of three consecutive convolution layers on the WM-811K dataset. In later part of the paper, optimized for multi-class classification, the applied QCNN model consisting of four qubits used for convolutional and pooling layers exhibit 99.38% accuracy. The QCNN model establishes supremacy over CCNN model by reducing time requirement to train the model for classifying defects on the wafer images.","url":"https://doi.org/10.31219/osf.io/gzjfy_v1","authors":["Debajyoti Biswas","Shikha Marwaha","Sriya Atmakuru"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-12T18:28:14Z","doi":"10.31219/osf.io/gzjfy_v1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.17776/csj.1639638","name":"Artificial Neural Network Application on Strain Effect of WSe2","source":"crossref","abstract":"Ab initio density functional theory (DFT) calculations have been used to determine the band gap of the 2D layered material WSe2 under uniaxial strain. This involves finding optimised lattice parameters and calculating the electronic band structure. We also note that by applying strains ranging from -15% to 15%, a wide range of band gaps can be obtained to study the behaviours of the semimetal and metal. We found, WSe2 structure becomes semi-metal at +12% and -13% strains then or also becomes metal after +12% and -13% strains. The ensuing outcomes are then applied to the domain of machine learning. Initially, PR, which is polynomial regression, is a machine learning method that can be studied with numpy, sklearn and scipy modules, and ANN (artificial neural network) is the application with tensorflow module that is applied to the optimised semi-metallic and metallic structures. The application of the latter involves the Least Squares method. The implementation of Leaky Relu (LRelu) and Elu functions is instrumental in facilitating the deployment of ANN. The potential dataset is obtained by using Quantum Espresso, and the calculations are made by using the National Center for High Performance Computing of Turkey (UYBHM). The PR and ANN results are calculated using the existing data set. The primary objective of utilising PR and artificial neural networks is to facilitate the plotting of Valance Band Maximum (VBM) and Conduction Band Minimum (CBM) graphs in the vicinity of the Fermi level. This study based on data which are already available and could therefore be considered to be data mining. on the electronic band structure for WSe2.","url":"https://doi.org/10.17776/csj.1639638","authors":["Hamdi Dağıstanlı"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T08:32:15Z","doi":"10.17776/csj.1639638","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/devic63749.2025.11012482","name":"Memristor Synaptic Array with Spiking Neurons for Neuromorphic Audio Signal Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/devic63749.2025.11012482","authors":["Aarat Prasad","Gufran Ahmad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-29T17:06:14Z","doi":"10.1109/devic63749.2025.11012482","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5101183","name":"Bike-Sharing Ridership Prediction for Network Expansion Using Graph Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5101183","authors":["Ghazaleh Mohseni Hosseinabadi","Mehdi Nourinejad","Peter  Y. Park"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-17T17:41:27Z","doi":"10.2139/ssrn.5101183","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1002/eng2.70373/v4/decision1","name":"Decision letter for \"Enhancing Cardiovascular Disease Analysis in Healthcare Systems With Hybrid Random Forest and Neural Network Algorithm\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/eng2.70373/v4/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T23:21:22Z","doi":"10.1002/eng2.70373/v4/decision1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5253798","name":"Physics-Informed Modularized Neural Network for Advanced Building Control by Deep Reinforcement Learning","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5253798","authors":["zixin jiang","Xuezheng Wang","Bing Dong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-14T07:36:46Z","doi":"10.2139/ssrn.5253798","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.21203/rs.3.rs-7991330/v1","name":"A Quantum Neural Network for Fraud Detection Using a Data-Driven Priority Entanglement Scheme","source":"crossref","abstract":"Abstract This study investigates whether a variational quantum circuit can improve minority-class sensitivity when substituted for a single dense layer in a strong neural network baseline for credit-card fraud detection. Under matched parameter budgets and identical preprocessing, we evaluate a hybrid quantum–classical model against classical baselines on the Kaggle dataset, preserving all 492 fraud cases and downsampling legitimate transactions to 10,000. Our hybrid employs data re-uploading to expose all 30 features with 10–15 qubits. It introduces a data-driven priority-entanglement scheme that couples the most dependent feature pairs before a strongly entangling block. Across 100 (10-qubit) and 20 (15-qubit) randomized runs, the hybrid achieves meaningful and consistent gains in recall and PR-AUC over tuned classical models (e.g., PR-AUC 0.9229±0.006 at 15q/1-layer/10 priority pairs vs 0.9150±0.014 for logistic regression; recall +0.047 over the best classical result).Performance peaks at moderate entanglement budgets, beyond which deeper circuits only exacerbate a precision-recall trade-off, revealing an underlying trainability limit. Results indicate that correlation-guided entanglement provides a useful inductive bias that modestly improves fraud detection under strict capacity parity.","url":"https://doi.org/10.21203/rs.3.rs-7991330/v1","authors":["Yousaf Khaliq","Donglin Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-18T15:51:12Z","doi":"10.21203/rs.3.rs-7991330/v1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/icassp49660.2025.10889757","name":"SCNN: Spike Coupling Neural Network for Multimodal Brain Network Analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icassp49660.2025.10889757","authors":["Shaolong Wei","Jiashuang Huang","Mingliang Wang","Shu Jiang","Weiping Ding"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-12T13:52:43Z","doi":"10.1109/icassp49660.2025.10889757","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1088/0954-898x/4/1/005","name":"On learning simple neural concepts: from halfspace intersections to neural decision lists","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/4/1/005","authors":["Mario Marchand","Mostefa Golea"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/4/1/005","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1007/s00521-024-10832-9","name":"Develop a novel, faster mask region-based convolutional neural network model with leave-one-subject-out to predict freezing of gait abnormalities of Parkinson’s disease","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-024-10832-9","authors":["J. Ezhilarasi","T. Senthil Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-03T01:48:44Z","doi":"10.1007/s00521-024-10832-9","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5650693","name":"MMORR-PCNN: A Mode-Wavelength Multiplexed Photonic Neural Network for Edge AI Inference","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5650693","authors":["Thanh Do Tien","Thanh  Trung Le"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-24T01:49:53Z","doi":"10.2139/ssrn.5650693","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5292389","name":"Physics-Informed Modularized Neural Network for Advanced Building Control by Deep Reinforcement Learning","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5292389","authors":["zixin jiang","Xuezheng Wang","Bing Dong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-13T16:10:46Z","doi":"10.2139/ssrn.5292389","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.36227/techrxiv.174952940.04337137/v1","name":"Hardware-Based Spiking Neural Network for Real-Time Hand Gesture Recognition Using MYO Armband EMG sensor","source":"crossref","abstract":"Hand gesture recognition is a key technology for improving prosthetic control and enhancing human-robot interaction. Traditional machine learning approaches struggle with real-time, low-power constraints in embedded systems. This paper proposes a hardware-based Spiking Neural Network (SNN) for real-time hand gesture recognition from electromyography (EMG) signals using the MYO Armband. The SNN leverages energy-efficient, event-driven computation to classify dynamic gestures in real-time, demonstrating applicability in myoelectric prosthetics and robotics. Implemented on a low-cost FPGA, the proposed system achieves accurate and responsive gesture recognition under strict resource constraints.","url":"https://doi.org/10.36227/techrxiv.174952940.04337137/v1","authors":["Ali Mehrabi","Gaetano Gargiulo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-10T00:23:28Z","doi":"10.36227/techrxiv.174952940.04337137/v1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.64388/irev9i6-1712538","name":"An Enhanced Virtual Fitting Room Using Deep Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.64388/irev9i6-1712538","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-12T05:37:40Z","doi":"10.64388/irev9i6-1712538","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1016/0893-6080(88)90539-4","name":"Neural network that computes visual motion","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90539-4","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T05:05:53Z","doi":"10.1016/0893-6080(88)90539-4","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1016/j.neunet.2025.107140","name":"Context Sensitive Network for weakly-supervised fine-grained temporal action localization","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107140","authors":["Cerui Dong","Qinying Liu","Zilei Wang","Yixin Zhang","Feng Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-24T03:55:55Z","doi":"10.1016/j.neunet.2025.107140","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/tcsii.2022.3192616","name":"Gate-Controlled Memristor FPGA Model for Quantified Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tcsii.2022.3192616","authors":["Zhang Zhang","Ao Xu","Chao Li","Yadong Wei","Zhiheng Ge","Xin Cheng","Gang Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-07-20T19:32:56Z","doi":"10.1109/tcsii.2022.3192616","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/ijcnn.2006.1716481","name":"SIRENS: A Simple Reconfigurable Neural Hardware Structure for artificial neural network implementations","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.1716481","authors":["R. Eickhoff","T. Kaulmann","U. Ruckert"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-30T17:35:23Z","doi":"10.1109/ijcnn.2006.1716481","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5082556","name":"Advanced Product Recommender Systems Using Graph Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5082556","authors":["safae hmaidi","Mohamed Lazaar","Yasser El Madani El Alami","Yassine Afoudi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-01-04T17:37:42Z","doi":"10.2139/ssrn.5082556","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5579538","name":"Complex-valued Proximal Neural Network Methods for Solving  Complex-valued Mixed Variational Inequalities","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5579538","authors":["Yuanhua Wang","Siru Yin","Jun Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-08T18:42:01Z","doi":"10.2139/ssrn.5579538","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1016/0893-6080(88)90384-x","name":"Neural network learning controller for manipulators","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90384-x","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T01:05:53Z","doi":"10.1016/0893-6080(88)90384-x","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1002/aisy.202100111","name":"Neural Network Physically Unclonable Function: A Trainable Physically Unclonable Function System with Unassailability against Deep Learning Attacks Using Memristor Array","source":"crossref","abstract":"The dissemination of edge devices drives new requirements for security primitives for privacy protection and chip authentication. Memristors are promising entropy sources for realizing hardware‐based security primitives due to their intrinsic randomness and stochastic properties. With the adoption of memristors among several technologies that meet essential requirements, the neural network physically unclonable function (NNPUF) is proposed, a novel PUF design that takes advantage of deep learning algorithms. The proposed design integrated with the memristor array can be constructed easily because the system does not depend on write operation accuracy. To contemplate a nondifferentiable module during training, an original concept of loss called PUF loss is devised. Iterations of weight update with the loss function bring about optimal NNPUF performance. It is shown that the design achieves a near‐ideal 50% average value for security metrics, including uniformity, diffuseness, and uniqueness. This means that the NNPUF satisfies practical quality standards for security primitives by training with PUF loss. It is also demonstrated that the NNPUF response has an unassailable resistance against deep learning‐based modeling attacks, which is verified by the near‐50% prediction model accuracy.","url":"https://doi.org/10.1002/aisy.202100111","authors":["Junkyu Park","Yoonji Lee","Hakcheon Jeong","Shinhyun Choi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-10-09T05:57:44Z","doi":"10.1002/aisy.202100111","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5491209","name":"Neural Network Preconditioning of Linear Tabulation Methods for Fast Function Approximation","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5491209","authors":["Pavel  P. Popov","Jay  M. Arcities","Kaku Eduku"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-15T20:40:19Z","doi":"10.2139/ssrn.5491209","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.5194/egusphere-egu24-1665","name":"Optimisation of Regional Weather Forecasts for Northern Algeria Using a Convolutional Neural Network and AROME Model Analysis.","source":"crossref","abstract":"This study introduces an innovative approach aimed at enhancing the accuracy of regional weather forecasts from the AROME model, covering northern Algeria. By leveraging AROME analysis, a refined representation based on real observations and widely used for monitoring and validating our model, our primary objective was to precisely correct surface parameters, including temperature at 2 meters, humidity, wind force, and sea-level atmospheric pressure (MSLP). This correction was performed based on their forecast ensemble, all while preserving spatial resolution.This methodology has yielded promising results, demonstrating a significant improvement in the accuracy of regional weather forecasts. The presentation will delve into the detailed integration process of the Convolutional Neural Network (CNN) and AROME analysis, highlighting the successes achieved in correcting essential surface parameters. These advancements strengthen the reliability of regional meteorological models, with positive implications for resource planning and management in the northern region of Algeria.","url":"https://doi.org/10.5194/egusphere-egu24-1665","authors":["Islam Bousri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-08T10:59:06Z","doi":"10.5194/egusphere-egu24-1665","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5404825","name":"A Transformer-Based Neural Network for Global Dust Nowcasting","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5404825","authors":["Shikang Du","Siyu Chen","Jiaqi He","Yu Fu","Lulu Lian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-25T17:40:03Z","doi":"10.2139/ssrn.5404825","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.2139/ssrn.5334724","name":"Improved Post Training Quantization for Heavy Tailed Model Parameters in Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5334724","authors":["Jipeng Li","Xueqiong Yuan","Ercan  Engin Kuruoglu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-01T19:07:02Z","doi":"10.2139/ssrn.5334724","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1039/d5ya00093a/v2/review1","name":"Review for \"A Sampling Fault Diagnosis Method for Power Battery Data in Cloud Platform Based on ResNet-BiLSTM Neural Network\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5ya00093a/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-25T21:09:14Z","doi":"10.1039/d5ya00093a/v2/review1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1002/eng2.70373/v6/decision1","name":"Decision letter for \"Enhancing Cardiovascular Disease Analysis in Healthcare Systems With Hybrid Random Forest and Neural Network Algorithm\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/eng2.70373/v6/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-30T23:21:22Z","doi":"10.1002/eng2.70373/v6/decision1","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/pandafpe57779.2023.10141026","name":"The Synchronization Analysis of Stochastic Memristor-based Neural Networks with Inertial Terms","source":"crossref","abstract":"","url":"https://doi.org/10.1109/pandafpe57779.2023.10141026","authors":["Zhenkun Liu","Yang Jia","Ling Chen","Haihui Jiang","Shiqiang Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-09T17:21:38Z","doi":"10.1109/pandafpe57779.2023.10141026","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1007/s11063-025-11777-3","name":"Enhancing Deep Learning with Resilient Adversarial Network (RANet): An Advanced Adversarial Resilience Training Framework for Robust Image Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11063-025-11777-3","authors":["Saleh Alyahyan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-06-20T04:44:45Z","doi":"10.1007/s11063-025-11777-3","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1016/j.neunet.2025.107844","name":"A confidence-guided Unsupervised domain adaptation network with pseudo-labeling and deformable CNN-transformer for medical image segmentation","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107844","authors":["Jiwen Zhou","Yue Xu","Zinan Liu","Fabien Pfaender","Wanyu Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-08T11:14:21Z","doi":"10.1016/j.neunet.2025.107844","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/icsit65336.2025.11295472","name":"Fault Diagnosis Using Wavelet Based Denoising Integrated with Neural Networks: A Signal Processing Informed Neural Network Framework","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icsit65336.2025.11295472","authors":["Anisha Anil Jadhav","Jaydeep Kishore","B.P. Joshi","Shweta Goyal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-19T18:56:35Z","doi":"10.1109/icsit65336.2025.11295472","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/jiot.2023.3274116","name":"Memristor-Based Neural Network Circuit of Emotional Habituation With Contextual Dependency","source":"crossref","abstract":"","url":"https://doi.org/10.1109/jiot.2023.3274116","authors":["Junwei Sun","Linhao Zhao","Shiping Wen","Yanfeng Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-10T23:55:53Z","doi":"10.1109/jiot.2023.3274116","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1016/j.neunet.2025.107346","name":"Adaptive decoupling-fusion in Siamese network for image classification","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107346","authors":["Xi Yang","Pai Peng","Danyang Li","Yinghao Ye","Xiaohuan Lu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-13T04:10:11Z","doi":"10.1016/j.neunet.2025.107346","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/neuront66873.2025.11049978","name":"Critical Information Infrastructures Intelligent Protection: Digital Twins and Neural Network-Based Threat Detection Methods","source":"crossref","abstract":"","url":"https://doi.org/10.1109/neuront66873.2025.11049978","authors":["Evgenii S. Mityakov","Andrey I. Ladynin","Anna G. Shmeleva","Igor D. Kazakevich"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-07-03T17:27:00Z","doi":"10.1109/neuront66873.2025.11049978","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/tnnls.2024.3476439","name":"Hyperparameter Recommendation Integrated With Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnnls.2024.3476439","authors":["Liping Deng","Wen-Sheng Chen","Binbin Pan","MingQing Xiao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-18T17:31:51Z","doi":"10.1109/tnnls.2024.3476439","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1109/ijcnn64981.2025.11228372","name":"Enhancing Time Series Classification with Diversity-Driven Neural Network Ensembles","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn64981.2025.11228372","authors":["Javidan Abdullayev","Maxime Devanne","Cyril Meyer","Ali Ismail-Fawaz","Jonathan Weber","Germain Forestier"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T18:46:15Z","doi":"10.1109/ijcnn64981.2025.11228372","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1088/0954-898x_6_1_001","name":"Local dynamic interactions in the collicular motor map: a neural network model","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_6_1_001","authors":["Lina L E Massone","Tony Khoshaba"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T16:04:48Z","doi":"10.1088/0954-898x_6_1_001","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1080/0954898x.2019.1688878","name":"Fractional infinite-horizon optimal control problems with a feed forward neural network scheme","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2019.1688878","authors":["Mina Yavari","Alireza Nazemi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-11-15T06:50:47Z","doi":"10.1080/0954898x.2019.1688878","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1080/09548980601009650","name":"Coherent ongoing subthreshold state of a cortical neural network regulated by slow- and fast-spiking interneurons","source":"crossref","abstract":"","url":"https://doi.org/10.1080/09548980601009650","authors":["Osamu Hoshino"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-12-06T20:56:13Z","doi":"10.1080/09548980601009650","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1088/0954-898x_5_3_005","name":"Macroscopic properties of the cost function of a feed-forward neural network prior to training","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_5_3_005","authors":["M J Roberts"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T16:04:08Z","doi":"10.1088/0954-898x_5_3_005","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1016/j.neunet.2025.107313","name":"Heterogeneous Graph Neural Network with Adaptive Relation Reconstruction","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107313","authors":["Weihong Lin","Zhaoliang Chen","Yuhong Chen","Shiping Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-05T11:24:00Z","doi":"10.1016/j.neunet.2025.107313","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1080/0954898x.2022.2104463","name":"A smoothing gradient-based neural network strategy for solving semidefinite programming problems","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2022.2104463","authors":["Asiye Nikseresht","Alireza Nazemi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-08-04T12:37:41Z","doi":"10.1080/0954898x.2022.2104463","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1145/3769697.3771241","name":"Fuzz Testing for Polymorphic Network Firmware: A Collaborative Optimization Framework of LLMs and Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3769697.3771241","authors":["Ben Qian","Yunjie Gu","Changhe Wu","Yuan Mu","Xuan Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-08T17:13:50Z","doi":"10.1145/3769697.3771241","addedAt":"2026-09-01T01:48:34.125Z","updatedAt":"2026-09-01T01:48:34.125Z"},{"id":"doi:10.1007/978-1-4615-3642-0_1","name":"Neural Network Models and N-Queen Problems","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4615-3642-0_1","authors":["Yoshiyasu Takefuji"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-06-11T02:59:30Z","doi":"10.1007/978-1-4615-3642-0_1","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.2139/ssrn.6391418","name":"AI-based Computational Engineering using Hierarchical Deep Learning Neural Network","source":"crossref","abstract":"Computational engineering is undergoing a rapid transformation due to artificial intelligence (AI), which combines data-driven learning with physics-based modeling. An important advancement is the development of Hierarchical Deep Learning Neural Networks (HDLNNs), which employ layered architectures to capture multi-scale and multi-physics features. Operator learning models like DeepONet, Fourier Neural Operator (FNO), and Physics-Informed Neural Operator (PINO) built upon the ideas of early frameworks like Physics-Informed Neural Networks (PINNs), which incorporated governing equations into training, to enable resolution-invariant PDE surrogates. Hierarchical extensions like HiDeNN and Convolutional HiDeNN (C-HiDeNN) improve structural and material simulations, while Graph Neural Networks (GNNs) provide mesh-based multigrid-like learning. Despite the rapid progress, challenges remain in handling stiffness, generalization to complex geometries, and multi- fidelity integration. Through comparison with traditional solvers and a description of possible future directions for scalable, physics-consistent AI systems, this study investigates the role of HDLNNs in computational engineering.","url":"https://doi.org/10.2139/ssrn.6391418","authors":["Kanika Singhal","Harshita .","Inderpreet Kaur","Madhav Bansal","Kirti Kushwah"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-13T15:01:51Z","doi":"10.2139/ssrn.6391418","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.64898/2026.06.01.729343","name":"Predicting P-glycoprotein Substrate Status Using a Pretrained Graph Neural Network: A TDC Benchmark Study","source":"crossref","abstract":"Abstract P-glycoprotein (Pgp/ABCB1) is a critical efflux transporter that significantly impacts drug bioavailability and multidrug resistance. Accurate prediction of Pgp substrate status is essential for early-stage drug discovery. In this study, we evaluate a pretrained Graph Iso-morphism Network (GIN) with attribute masking on the Pgp_Broccatelli benchmark from the Therapeutics Data Commons (TDC). Our approach fine-tunes a GIN encoder pretrained on approximately 2 million molecules using a self-supervised attribute masking strategy, followed by a multilayer perceptron (MLP) classification head. On the TDC benchmark, our model achieves an AUROC of 0.937 ± 0.004 across five independent runs, ranking second on the leaderboard, as of May 2026. We further compare this approach against an XGBoost baseline using Morgan fingerprints (AUROC 0.912 ± 0.007), demonstrating the advantage of graph-based molecular representations with transfer learning for small-dataset ADMET prediction tasks.","url":"https://doi.org/10.64898/2026.06.01.729343","authors":["Jingjing Yan","Weicong Duan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-05T00:55:19Z","doi":"10.64898/2026.06.01.729343","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.21203/rs.3.rs-9897709/v1","name":"A Two-Dimensional Bayesian Continuous Attractor Neural Network for Robust Spatial State Estimation","source":"crossref","abstract":"Abstract Continuous Attractor Neural Networks (CANNs) have emerged as prominent bio-inspired models for spatial representation, with recent theoretical advances demonstrating their capacity for optimal Bayesian inference. However, the mathematical equivalence between attractor dynamics and optimal Bayesian inference has been largely confined to 1D circular variables. To bridge this gap, we propose a Bayesian CANN in a 2D Euclidean state space. The network conditions required for optimal inference are analytically derived by matching the network dynamics with the continuous-time Kalman-Bucy filter. Crucially, by introducing an advection-reaction operator splitting method, we resolve a velocity-dependent diffusion artifact, thereby preserving Bayesian consistency without artificially degrading the certainty of the internal representation. The proposed 2D Bayesian CANN achieves estimation accuracy comparable to Kalman and particle-based filters while retaining structural robustness to severe sensory conflict. This robustness arises from the linear superposition of conflicting sensory evidence followed by nonlinear attractor dynamics, which suppress dispersed low-confidence activity and realign the localized representation toward dominant sensory cues. These results bridge theoretical neuroscience and engineering state estimation, suggesting a bio-inspired framework for resilient autonomous navigation in unpredictable environments.","url":"https://doi.org/10.21203/rs.3.rs-9897709/v1","authors":["Hyo-Sang Shin","Sohyun Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-08T14:02:18Z","doi":"10.21203/rs.3.rs-9897709/v1","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.21203/rs.3.rs-8840997/v1","name":"Architecture and Scaling of the TSKI Model: A Phase–Temporal Neural Network Without a Loss Function","source":"crossref","abstract":"Abstract This paper presents a biologically inspired neural network model based on the theoretical framework of TSKI 4.2 [1] by Atorin A., and examines its potential for architectural scaling. The model is positioned as an alternative class of neural networks in which computation is not based on minimizing a loss function, but on the formation and stabilization of temporal information trajectories through phase–temporal synchronization of neurons and homeostatic regulation of their parameters. The paper is structured in two phases. The first phase describes the components of TSKI theory that have already been implemented in software. The main mathematical objects of the model and their implementation are discussed, including neurons and synaptic connections with a mirrored representation, where access to the connection vector is available to both presynaptic and postsynaptic neurons. The computational core of the model is described, implementing a single operational step based on a phase synchronization mechanism between presynaptic and postsynaptic neurons (k5 = 0, k5 = 1). This mechanism constitutes the necessary and sufficient condition for information computation and synaptic parameter updates, and represents a digital analogue of biological STDP (Spike-Timing-Dependent Plasticity). This fundamental computational algorithm of TSKI reduces computational costs by introducing a binary condition for synchronization within a synapse: when synchronization is present, computations and parameter updates are performed; when synchronization is absent, computational activity is blocked. The simulation also implements a computational algorithm analogous to biological homeostatic regulation, responsible for stabilizing neuronal parameters and influencing synchronization conditions across neural connections. Simulation results [2] obtained from four small-scale TSKI neural networks [3] are presented, on the basis of which the hypothesis is advanced that the TSKI model may reduce susceptibility to catastrophic forgetting after training. The main focus of the paper is its second part, which explores the scalability of TSKI and describes an architecture designed to enable such scaling. The architectural organization of the TSKI model is oriented toward reproducing principles of information processing characteristic of the biological nervous system: receptor zone → thalamic nuclei → cerebral cortex. Within this analogy, four functional zones are identified in the model, each performing a distinct role; their operating principles and architectural structures are described. The key objective of the TSKI architectural solution is to ensure alignment between the phase–temporal states of neurons and the temporal dynamics of changes in a physical (detectable) stimulus parameter. Such alignment is necessary for the TSKI model to form, associate, and reproduce adaptive responses to stimuli over time. The analysis of the proposed architectural solutions reveals local analogues of the backpropagation mechanism (error backpropagation in ANNs) and optimization algorithms used in classical neural network models, as applied to the TSKI architecture. The nature of the objective function in TSKI and methods for improving the efficiency of its realization through the model’s internal dynamics are also examined. The paper concludes by demonstrating a high degree of similarity between the information-processing principles of the TSKI architecture and those of the biological nervous system. It is shown that the TSKI algorithms developed and implemented in simulations of small-scale neural networks are fundamentally ready for architectural scaling, and that the architectural principles embedded in the functional zones are falsifiable. This creates the possibility for experimental verification of the theoretical assumptions formulated in this work.","url":"https://doi.org/10.21203/rs.3.rs-8840997/v1","authors":["Andrii Atorin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-18T08:26:50Z","doi":"10.21203/rs.3.rs-8840997/v1","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/icoecit68303.2026.11496720","name":"Deep Neural Network Approach for Efficient and Reliable Network Slicing in 5G Architecture","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icoecit68303.2026.11496720","authors":["Ambidi Naveena","Meghana Madipalli","Narayandas Shreya Vandana","Srivarsha Pochampally","Sneha Battula"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-05T20:00:29Z","doi":"10.1109/icoecit68303.2026.11496720","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.5220/0014917500005134","name":"Prediction of Electric Load Neural Network Prediction Model for Big Data","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0014917500005134","authors":["Yangfan Zhao","Zhiying Ren","Zhifeng Song"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-30T14:55:15Z","doi":"10.5220/0014917500005134","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1007/s00521-026-11903-9","name":"Enhancing prostate cancer diagnosis using 99mTc-PSMA SPECT: PCA-based feature extraction and neural network classification for Gleason score analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-026-11903-9","authors":["Masoumeh Dorri Giv","Samer Kais Jameel","Jafar Majidpour","Sayna Jamaati","Hossein Arabi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-03T00:53:22Z","doi":"10.1007/s00521-026-11903-9","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.38007/nn.2020.010101","name":"Invoice Recognition System based on Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2020.010101","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T03:35:42Z","doi":"10.38007/nn.2020.010101","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1109/tcds.2023.3321137","name":"Memristor-Based Neural Network Circuit of Associative Memory With Occasion Setting","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tcds.2023.3321137","authors":["Juntao Han","Xin Cheng","Guangjun Xie","Junwei Sun","Gang Liu","Zhang Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-10-02T18:07:46Z","doi":"10.1109/tcds.2023.3321137","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.52783/anuval.2045","name":"Hybrid Optimizer Switching for Deep Neural Network Training in Time Series Forecasting","source":"crossref","abstract":"Deep neural networks often encounter non-convex optimization challenges during training due to the presence of local minima, saddle points, and complex loss surfaces. Existing optimization algorithms such as Adam and Stochastic Gradient Descent (SGD) offer complementary advantages—Adam provides faster convergence, while SGD tends to achieve better generalization. However, neither optimizer alone effectively balances both properties in non-convex settings. To address this limitation, this paper proposes a phase-switch hybrid optimization strategy that combines the strengths of Adam and SGD. The proposed method employs Adam during the initial phase of training to enable rapid convergence and efficient exploration of the loss landscape, and then switches to momentum-based SGD in the later phase to improve generalization and ensure stable convergence. The effectiveness of the proposed approach is evaluated on three benchmark dataset the M4 time-series forecasting data set, under different learning rate settings. Experimental results demonstrate that the proposed method achieves performance that is superior or comparable to existing optimizers in terms of accuracy and loss minimization. These results indicate that the proposed hybrid optimization strategy provides a simple and effective solution for handling non-convex optimization problems","url":"https://doi.org/10.52783/anuval.2045","authors":["Harish Kunder"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-17T15:18:22Z","doi":"10.52783/anuval.2045","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.32388/i2cun7","name":"Review of: \"Synthetic Data Generation of Body Motion Data by Neural Gas Network for Emotion Recognition\"","source":"crossref","abstract":"","url":"https://doi.org/10.32388/i2cun7","authors":["Hany Akeel Al-hussaniy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-08T14:36:43Z","doi":"10.32388/i2cun7","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.2139/ssrn.6760256","name":"A Crack Growth-Guided Symbolic Regression-Neural Network Framework for Fatigue Life Prediction","source":"crossref","abstract":"To reduce the restrictions of empirical fatigue models and improve the physical consistency of purely data-driven approaches, this study proposes a fatigue life prediction framework integrating symbolic regression with physics-informed neural networks. In this framework, the local crack growth relation is connected with total fatigue life through two steps. Symbolic regression is first performed using fracture-mechanics variables, and explicit phenomenological expressions are obtained directly from crack growth rate data rather than from a prescribed empirical form. The equivalent initial flaw size is then used as the lower limit in the life integration. In this way, the identified crack growth law can be used as a constraint for total fatigue life prediction. A stress-ratio-dependent local correction is incorporated in the equivalent initial flaw size calculation to improve the physical consistency of life inference under different loading ratios. The identified crack-growth relationship, life inference constraint, and experimental fatigue life data are jointly embedded into the physics-informed neural network, enabling coordinated optimization between data supervision and physical constraints. Validation on public fatigue datasets of TC4, A36, and AA 2024-T3 shows that the proposed framework captures fatigue life evolution under different material conditions and provides better prediction accuracy, stability, and applicability than classical crack-growth-constrained models and purely data-driven models. Under limited target-material samples, the model also shows small-sample cross-material transfer potential. This study provides a physically interpretable and prediction-oriented modeling approach for fatigue life prediction under complex conditions.","url":"https://doi.org/10.2139/ssrn.6760256","authors":["Dongxu Zhang","Junjie Shi","Zhixun Wen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-13T19:39:29Z","doi":"10.2139/ssrn.6760256","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1201/9781003768654-30","name":"Convolutional Neural Network Approach for Grape Leaf Disease Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003768654-30","authors":["Prateek Mahapatra","Madhumita Panda"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-23T14:48:19Z","doi":"10.1201/9781003768654-30","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.2139/ssrn.6945159","name":"On-device Spiking Neural Network Locomotion Learning on a €100 Quadruped: Sim-to-Real with Brain Persistence","source":"crossref","abstract":"I present a complete Sim-to-Real pipeline for quadruped locomotion using biologically grounded spiking neural networks (SNNs) on a €100 Freenove Robot Dog Kit (FNK0050) with a Raspberry Pi 4. The system employs 232 Izhikevich neurons with reward-modulated spike-timing-dependent plasticity (R-STDP), a central pattern generator (CPG) for innate gait rhythm, and a cerebellar forward model for balance correction. Training occurs in MuJoCo simulation using a custom MJCF model of the Freenove hardware, achieving 8.22 m forward distance with zero falls in 50,000 steps (original training run; Table 3 compares CPG vs Full Stack configurations). The trained brain transfers to real hardware via a Bridge architecture mapping SNN motor outputs to servo commands with real-time IMU feedback (MPU6050). On-device learning enables the robot to reach actor competence 1.0 within 2,000 steps (40 seconds at 50 Hz). Brain persistence across sessions is demonstrated: a loaded brain achieves competence 1.0 from step 1, while a fresh brain requires 2,000 steps. A key finding: cerebellar correction magnitude is zero in simulation (where CPG produces clean movement) but non-zero on real hardware (where IMU noise and servo imprecision create real errors). This confirms the cerebellum's role as an error-driven adaptive system, not a pattern generator. The same architecture runs on the Unitree Go2 in simulation (45.15 ± 0.67 m, 10 seeds). All code is open source under Apache 2.0.","url":"https://doi.org/10.2139/ssrn.6945159","authors":["Marc Hesse"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-11T06:06:16Z","doi":"10.2139/ssrn.6945159","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.26434/chemrxiv.15003976/v2","name":"Beyond Multiscale: A Neural Network-Unified Molecular Model for Asymmetry-Free Dynamics Simulation","source":"crossref","abstract":"Adaptive multiscale simulations, such as adaptive QM/MM, are indispensable for investigating complex solution dynamics but historically suffer from a fundamental dilemma: the dynamic exchange of identical solvent molecules across different model resolutions introduces a physical asymmetry. This asymmetry forces a prohibitive trade-off between severe structural distortions and the violation of Hamiltonian conservation (continuous energy drift). To definitively resolve this issue, we propose the ”Integrated Molecular Model,” a paradigm-shifting framework that mathematically unifies multiple resolutions into a single, dynamically consistent potential. By employing a neural network that takes only the multiscale weight functions as input descriptors, our model learns to systematically cancel the non-physical transition forces originating from spatial discontinuities. As a proof-of-concept, we validated this unified framework on bulk water, aqueous ionic solutions, and reactive hydronium ions. Our approach not only faithfully restores artifact-free solvation structures but also strictly conserves the Hamiltonian, enabling unprecedentedly stable, long-term simulations under the microcanonical (NVE) ensemble. Consequently, the model successfully eliminates artificial thermostat-induced breathing modes, allowing for the rigorous evaluation of intrinsic dynamical properties such as diffusion coefficients. Furthermore, owing to its physically informed network design, the correction potential introduces less than 2\\% additional computational overhead and demonstrates remarkable zero-shot transferability across chemically similar ionic species. By fundamentally eradicating the inherent asymmetry of adaptive multiscale modeling, this highly scalable framework establishes a robust foundation for high-fidelity simulations of complex condensed-phase phenomena, including reactive dynamics at solid-liquid interfaces and ion transport in battery electrolytes.","url":"https://doi.org/10.26434/chemrxiv.15003976/v2","authors":["Takuma Ikeda","Hiroshi C. Watanabe","Haruyuki Nakano"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-23T14:28:27Z","doi":"10.26434/chemrxiv.15003976/v2","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.2139/ssrn.6988684","name":"CABORT: A deep neural network inference accelerator based on on-chip optical interconnect","source":"crossref","abstract":"Deep neural networks (DNNs) possess strong feature extraction abilities and have been widely used across various applications, serving as a core component of current artificial intelligence systems. However, the complex data communication within DNNs greatly limits model inference speed on local hardware devices. The development of silicon-based photonics has introduced on-chip optical interconnect technologies that offer fresh solutions for complex intra-chip communication. This study presents an innovative DNN accelerator architecture named CABORT, which employs optical interconnects organized in a ring topology. The CABORT framework incorporates wavelength division multiplexing (WDM) to enhance communication performance among convolutional layers. Its design includes an optical processing array composed of micro-ring resonators, power splitters, and photodetectors to facilitate efficient data transmission during convolutional computations. To further increase network throughput and alleviate the influence of optical signal crosstalk on the optical signal-to-noise ratio (OSNR), a neural task allocation algorithm based on the genetic algorithm is developed. Experimental findings reveal that CABORT, through its specialized task mapping strategy and distinctive network structure, achieves up to 68.0% lower latency and 55.9% less power consumption compared with existing DNN accelerators. These results verify the architecture’s effectiveness and highlight its potential as a highly promising direction for advanced deep neural network processing.","url":"https://doi.org/10.2139/ssrn.6988684","authors":["Zhenjiao Chen","Zehao Wang","Wentao Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-24T07:49:55Z","doi":"10.2139/ssrn.6988684","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1088/1361-6501/ae5dee/v1/decision1","name":"Decision letter for \"Neural Network-Based Inverse Design for Multi-Objective Performance Optimization of 70 kHz Ultrasonic Transducers\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1361-6501/ae5dee/v1/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-11T21:11:18Z","doi":"10.1088/1361-6501/ae5dee/v1/decision1","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1063/5.0320669","name":"A multigrid-based super-resolution convolutional neural network for multi-physical fields","source":"crossref","abstract":"A novel convolutional neural network-based super-resolution (SR) method was proposed to accurately predict high-resolution flow fields from coarse-grid computational fluid dynamics (CFD) results. To mitigate boundary artifacts caused by transposed convolution, a Boundary Compensated Module was developed, ensuring input conservation by balancing the “Upper Layer Contribution Number.” A Two-step Preprocessing Scheme combined with the nondimensionalized mean square error was introduced, which effectively tackled the issues associated with “multi-physical variables” and “wide operating conditions.” Furthermore, a multigrid-based super-resolution convolutional neural network was developed, incorporating a three-stage progressive upsampling process with hierarchical loss and regularization. The model enabled efficient reconstruction under conditions of “high SR factor” and “multi-physical variables.” The effectiveness of the proposed method was validated across four representative benchmark cases (Backward-Facing Step Flow, Lid-Driven Cavity Flow, Supersonic Flow, and Swirling Jet Flow), which demonstrated that the proposed method reduces L2 errors by approximately 50% compared with existing models. The method achieved roughly two orders of magnitude of computational speedup, demonstrating strong engineering viability as a surrogate for high-fidelity CFD simulations.","url":"https://doi.org/10.1063/5.0320669","authors":["Tieying Li","Changfu You"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-06T13:10:21Z","doi":"10.1063/5.0320669","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/iccmc69250.2026.11624789","name":"Watermarking in Deep Neural Network: A Comprehensive Survey","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccmc69250.2026.11624789","authors":["Ganesh Immanni","Rajeev Kumar","Anurag Goel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-29T19:13:09Z","doi":"10.1109/iccmc69250.2026.11624789","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.mtcomm.2026.115198","name":"Intelligent welding quality classification of dissimilar metal joints using neural network models","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.mtcomm.2026.115198","authors":["Ji Lyu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-16T07:12:56Z","doi":"10.1016/j.mtcomm.2026.115198","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.sasc.2026.200505","name":"Deep neural network-based music emotion recognition and generation system","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.sasc.2026.200505","authors":["Tao Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-26T23:51:17Z","doi":"10.1016/j.sasc.2026.200505","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1039/d6tc01104g/v1/review1","name":"Review for \"Volatile nanocomposite memristor with a phase stratification dielectric layer: a threshold switching with rich neuromorphic dynamics\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d6tc01104g/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-28T21:09:57Z","doi":"10.1039/d6tc01104g/v1/review1","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1093/ijlct/ctag019","name":"New energy power electronic DC motor control system based on a fuzzy neural network","source":"crossref","abstract":"Abstract Based on the uncertainty and control effect of electronic DC motors, a neural network algorithm, fuzzy control, and fuzzy neural network are designed. First, a small signal model controlled by a virtual direct filter motor is developed, and the stability and dynamic characteristics of the control strategy are analyzed. Next, the influence of the distribution map of the system based on the closed-loop transmission function, inertia coefficient, and step response curve is explored. Finally, the computer simulation analysis verifies the virtual inertial adaptive algorithm based on the fuzzy neural network.","url":"https://doi.org/10.1093/ijlct/ctag019","authors":["Hongmiao Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-24T12:40:49Z","doi":"10.1093/ijlct/ctag019","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.26434/chemrxiv.15004951/v1","name":"An efficient neural network architecture for molecular vibrational states: from rigid molecules to molecular complexes","source":"crossref","abstract":"Accurately solving the nuclear Schrödinger equation for molecular complexes exhibiting noncovalent interactions remains a challenge due to the exponential scaling of basis sets and the presence of strongly anharmonic, large-amplitude motions. Recently, we proposed a neural network (NN) method to tackle high-dimensional vibrational problems and successfully applied it to C 3 H 8 in full dimensionality; however, applying the method to molecular complexes has been hindered by difficulties in representing delocalized wave functions across multiple minima. In this work, we present a substantially improved NN-based methodology that overcomes these limitations through two key developments: (i) a novel NN architecture specifically designed to capture the asymptotic behavior and delocalization characteristics of weakly bound complexes, and (ii) an efficient training protocol that optimizes the variance of local energies. We demonstrate that this approach achieves sub‑cm -1 accuracy for the vibrational ground and excited states of CH 4 with substantially fewer parameters than the previous method requires. Crucially, for the prototypical water dimer (H 2 O) 2 , the new method successfully computes both ground state and intramolecular excited states with ~ 1 cm -1 accuracy using ~6,000 NN parameters. This work establishes a robust and scalable framework for performing full-dimensional, fully coupled vibrational calculations on molecular complexes, paving the way for accurate spectroscopic predictions of systems previously deemed intractable.","url":"https://doi.org/10.26434/chemrxiv.15004951/v1","authors":["Shuaishuai Zhao","Dong H. Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-19T08:48:28Z","doi":"10.26434/chemrxiv.15004951/v1","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.36341/rabit.v11i2.8061","name":"PENGEMBANGAN MODEL DEEP LEARNING UNTUK DETEKSI SUARA  MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK","source":"crossref","abstract":"Deteksi suara dan pengenalan kata kunci dalam sinyal audio telah menjadi bidang penelitian yang berkembang pesat karena aplikasinya yang luas, mulai dari pengawasan audio cerdas hingga sistem interaksi manusia-komputer. Penelitian ini bertujuan untuk mengembangkan model deep learning berbasis Convolutional Neural Network (CNN) untuk mendeteksi dan mengklasifikasikan kata-kata spesifik dalam rekaman suara secara otomatis. Fokus penelitian ini adalah pada pendeteksian kata kunci \"anjing\" dan \"anak-anak\" yang terdapat dalam data ucapan. Metodologi penelitian mencakup pra-pemrosesan data melalui pembersihan gangguan (noise) dan normalisasi, serta teknik augmentasi data seperti pitch shifting untuk meningkatkan performa model. Fitur suara diekstraksi menggunakan Short-Time Fourier Transform (STFT) untuk menghasilkan representasi visual berupa spektrogram sebagai input utama bagi arsitektur CNN. Hasil pengujian menunjukkan bahwa model yang dikembangkan berhasil mengklasifikasikan kata kunci tersebut dengan tingkat akurasi sebesar 90,00%. Model ini terbukti efektif dalam mengenali pola spektral dan temporal dari ucapan kata kunci dan dapat diimplementasikan untuk sistem deteksi suara waktu nyata","url":"https://doi.org/10.36341/rabit.v11i2.8061","authors":["NORITA SINAGA","Imam Riadi","Herman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-11T00:00:43Z","doi":"10.36341/rabit.v11i2.8061","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.2139/ssrn.7019278","name":"Virtual boundary integral neural network for three-dimensional exterior acoustic problems​","source":"crossref","abstract":"This paper presents a virtual boundary integral neural network (VBINN) for three-dimensional exterior acoustic problems. The method introduces a virtual boundary within the scatterer or vibrating body and represents the associated source density using a neural network. Based on the acoustic Green’s function, this representation satisfies the Sommerfeld radiation condition and enables direct evaluation of the acoustic pressure and its normal derivative at arbitrary field points. Because the integration surface is separated from the physical boundary, the formulation avoids the singular and near singular kernel evaluations in conventional boundary integral learning methods. To reduce sensitivity to boundary placement, the geometric parameters of the virtual boundary are optimized jointly with the source density during training. Numerical examples for acoustic scattering, multiple body interaction, and underwater acoustic propagation show close agreement with analytical solutions and COMSOL results, and the Burton-Miller extension further improves stability near characteristic frequencies. These results demonstrate the potential of VBINN for three-dimensional exterior acoustic analysis.","url":"https://doi.org/10.2139/ssrn.7019278","authors":["Jiahao Li","Qiang Xi","Ilia Marchevsky","Zhuojia Fu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-29T12:37:41Z","doi":"10.2139/ssrn.7019278","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.21203/rs.3.rs-9144582/v1","name":"Physics-Informed Neural Network for Inverse Design of Cylindrical Kresling Origami with Discrete Side Count Optimization","source":"crossref","abstract":"Abstract Origami mechanisms excel in space and material utilization, but their design variables involve the coupling of continuous and discrete variables, complicating reverse engineering—especially for polygons with dis crete side counts. Traditional numerical optimization methods struggle with discrete variables and lack automation. This paper proposes a Physics-Informed Neural Network (PINN) framework for the reverse engineering of Kresling origami. In this framework, the discrete side count *m* is first adjusted by a dis tance penalty to shorten the distance between the optimized and target values. This ensures contin uously differentiable gradients and smooth transitions, avoiding loss bounces. Then, a soft projection function (a softmax function with a learnable temperature) strictly constrains the output value to integers, ultimately achieving continuous differentiability. Physical constraints (potential energy difference and near zero torque, achieved through ∂U/∂β ≈ 0) are embedded in the loss function, enabling label-free training. Novel engineering constraints ensure manufacturability. Numerical examples show MSE of the energy curve &lt; 1e-5 in all tested cases and convergence to integer m in &gt;95% of runs.","url":"https://doi.org/10.21203/rs.3.rs-9144582/v1","authors":["Shijun Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-18T01:47:20Z","doi":"10.21203/rs.3.rs-9144582/v1","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1088/2631-8695/ae9677/v2/review1","name":"Review for \"Artificial Neural Network-Based Energy Management for Fuel Cell–Battery–Supercapacitor Hybrid Electric Vehicles\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2631-8695/ae9677/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-11T21:06:19Z","doi":"10.1088/2631-8695/ae9677/v2/review1","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.21203/rs.3.rs-8902258/v1","name":"Accelerated Circuit Simulations and Standard Cell Library Characterization through Neural Network-based Transistor Modeling","source":"crossref","abstract":"Abstract nn-based transistor models have proven to be a promising solution to accelerate device modeling. Although these models demonstrated remarkable speedup in circuit simulations, they were not rigorously tested in complex tasks within standard EDA tool flows for chip design, which require very high transistor model precision to provide accurate results and converge properly. To investigate their full potential and promise, we develop NN-based transistor models that accurately predict the drain current and various charges for a \\qty{3}{nm} nanosheet, and employ the models for a standard cell library characterization. This enables us to evaluate the accuracy and speedup under a very wide range of SPICE simulations, benchmarking our models against an industry-standard implementation. Since standard cell library characterization involves thousands of SPICE simulations, it serves as a great benchmark for transistor model quality and consistency. To further evaluate model accuracy, we also perform analog- and digital-level simulations for various complex circuits. Our experiments reveal that NN-based models are a valid alternative to existing transistor compact models, capable of producing accurate delay and power estimates with a much higher speed and convergence time compared to the conventional Verilog-A-based industry-standard (BSIM-CMG) transistor compact model. Our NNs achieve sub-\\((0.11%)\\) and \\((0.76%)\\) errors for delay and total power evaluation on a wide range of circuits, while taking up to 8 times less time during the standard cell library characterization. Additionally, we provide comprehensive information and guidance on NN accuracy, unveiling the relationship between NN size and its effect on circuit simulation precision.","url":"https://doi.org/10.21203/rs.3.rs-8902258/v1","authors":["Rodion Novkin","Hussam Amrouch"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-17T16:41:47Z","doi":"10.21203/rs.3.rs-8902258/v1","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.22541/essoar.175525655.54389731/v2","name":"Experimental Verification of a Two-Dimensional Inverse Method for Turbidity Currents Using a Deep Neural Network","source":"crossref","abstract":"Turbidites have been widely studied as indicators of the occurrences and magnitudes of paleo-tsunamis and paleo-earthquakes. Inversion to estimate flow conditions from turbidites offers valuable insights into the magnitudes of paleo-seismic and tsunami events. However, conventional one-dimensional inverse models are insufficient for capturing the behavior of turbidity currents in tectonically active margins, where the seafloor topography is typically complex. Here, we developed a horizontal two-dimensional inverse model of turbidity currents based on a deep neural network (DNN) and evaluated its performance using synthetic and flume experiment datasets. The model successfully estimated model input parameters with a symmetric mean absolute percentage error (SMAPE) of less than 29.7%, except for the density-equivalent sediment concentration for saline water at the inlet. When applied to experimental data, the model reasonably reconstructed flow conditions, yielding SMAPE values between 51.7 and 86.2%, despite potential uncertainties introduced by sampling disturbances, data processing, and forward model limitations. These values were reasonable even compared to the results of the previous one-dimensional inverse model (Cai and Naruse, 2021), which showed a SMAPE range of 24.2–113%. The spatial distribution of bed thickness was also well predicted, except when most of the suspension bypassed the depositional zone. Overall, the proposed inverse models demonstrated accuracy comparable to that of the previous one-dimensional model. They offer greater applicability to complex seafloor geometries and maintain low computational costs, providing a practical advantage over optimization-based methods. These results suggest that the proposed method is well-suited for the field-scale inversion of turbidity currents in realistic geological settings.","url":"https://doi.org/10.22541/essoar.175525655.54389731/v2","authors":["Seiya Fujishima","Hajime Naruse"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-03T15:35:27Z","doi":"10.22541/essoar.175525655.54389731/v2","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/gcon69192.2026.11648356","name":"A Physics-Informed Depth-Aware Morphological Neural Network for Pulmonary Disease Diagnosis","source":"crossref","abstract":"","url":"https://doi.org/10.1109/gcon69192.2026.11648356","authors":["Vishnudatta Indraganti","Anirban Dasgupta","Manish Bhatt"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-17T19:13:17Z","doi":"10.1109/gcon69192.2026.11648356","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.18469/ikt.2026.24.1.11","name":"USING NEURAL NETWORK TECHNOLOGIES TO OPTIMIZE MOBILE APP USER EXPERIENCE","source":"crossref","abstract":"This paper analyzes domestic and international sources confirming the potential of neural network technologies for solving user experience optimization problems in mobile applications. A comprehensive approach is proposed, including selecting the optimal combination of various neural network architectures, formulating the problem in terms of optimization, and selecting adequate loss functions to optimize various aspects of the user experience. As a result of the research, a mathematical model of a hybrid architecture (Transformer and LSTM) was developed, combining a recurrent part (LSTM) to account for the temporal structure and an attention mechanism (Transformer-encoder) for a detailed analysis of contextual features. To evaluate the effectiveness of the proposed hybrid model, the results of a comparison with alternative models are presented, which showed optimal values for the selected metrics. The implemented model has been integrated into the mobile application: the results of A/B testing confirmed significant optimization of the main user experience metrics.","url":"https://doi.org/10.18469/ikt.2026.24.1.11","authors":["Danil Nikolajevich Zinovjev","Mariya Anatoljevna Bogomolova"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-28T09:27:06Z","doi":"10.18469/ikt.2026.24.1.11","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.5772/intechopen.69024","name":"Nanoscale Switching and Degradation of Resistive Random Access Memory Studied by In Situ Electron Microscopy","source":"crossref","abstract":"","url":"https://doi.org/10.5772/intechopen.69024","authors":["Masashi Arita","Atsushi Tsurumaki-Fukuchi","Yasuo Takahashi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-04-05T06:33:36Z","doi":"10.5772/intechopen.69024","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1109/ijcnn.2015.7280819","name":"A CMOS spiking neuron for dense memristor-synapse connectivity for brain-inspired computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2015.7280819","authors":["Xinyu Wu","Vishal Saxena","Kehan Zhu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-10-01T21:48:02Z","doi":"10.1109/ijcnn.2015.7280819","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.51244/ijrsi.2025.12120138","name":"Convolutional Neural Network","source":"crossref","abstract":"Convolutional Neural Network forms the base of all computer vision applications. Uses like self-driving cars, object recognition, face recognition, etc. Simple neural networks struggle with images because they are slow at training and processing and have a large number of parameters. To overcome these issues, we use Convolutional Neural Networks.","url":"https://doi.org/10.51244/ijrsi.2025.12120138","authors":["Shrutika Adole","Prof. K. P. Barabde"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-20T11:28:06Z","doi":"10.51244/ijrsi.2025.12120138","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/melecon64486.2026.11418797","name":"Knowledge Guided Neural Network Task Planning for Generalization to Unseen Robotic Environments","source":"crossref","abstract":"","url":"https://doi.org/10.1109/melecon64486.2026.11418797","authors":["Farida Gamal","Ayman El-Badawy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-10T19:50:57Z","doi":"10.1109/melecon64486.2026.11418797","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/tpec67884.2026.11513212","name":"Preliminary Analysis of a Graph Neural Network Approach to Transmission Expansion Planning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tpec67884.2026.11513212","authors":["Joshua Xia","Adam Birchfield"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-15T19:51:24Z","doi":"10.1109/tpec67884.2026.11513212","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/cipher70417.2026.11523852","name":"Neural Network Techniques for RF Matching Circuits","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cipher70417.2026.11523852","authors":["Abhay Kumar Dubey","Sukwinder Singh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-21T19:40:52Z","doi":"10.1109/cipher70417.2026.11523852","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/icwr69602.2026.11513337","name":"Martingale and Graph Neural Network Edge Reweighting for Stable Community Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icwr69602.2026.11513337","authors":["Akram Karimi Zarandi","Ali Fahim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-15T03:06:29Z","doi":"10.1109/icwr69602.2026.11513337","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/vaict69205.2026.11519087","name":"Research on Student Learning State Diagnosis Algorithm Based on Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/vaict69205.2026.11519087","authors":["Song Kaiwen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-20T19:48:58Z","doi":"10.1109/vaict69205.2026.11519087","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/cieec69682.2026.11572508","name":"Adaptive Control Method of Grid-Forming Converters Based on Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cieec69682.2026.11572508","authors":["Xiaoran Wang","Yun Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-30T20:25:22Z","doi":"10.1109/cieec69682.2026.11572508","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.4018/ijec.420194","name":"Neural Network-Driven Optimization of Interdisciplinary Academic Leadership in Universities","source":"crossref","abstract":"The development of interdisciplinary academic leaders is crucial for universities aiming to enhance collaboration, innovation, and knowledge integration across disciplines. Research introduces a deep learning-based framework, Wingsuit Flying Search-driven Dynamic Recursive Neural Networks (WFS-DRNN), implemented using Python (3.11), to predict leadership potential and optimize development pathways. By modeling hierarchical and sequential relationships among faculty qualifications, research experience, collaborative networks, and mentorship records, the WFS-DRNN captures both explicit and latent patterns critical to leadership growth. The Wingsuit Flying Search Algorithm (WFSA) efficiently explores optimal development pathways, enabling tailored interventions, such as interdisciplinary project participation, mentorship opportunities, and skill enhancement programs. Experimental results indicate that WFS-DRNN surpasses traditional heuristic and statistical methods, achieving 95.8% accuracy, 95.2% precision, 92.75% recall, and a 95% F1-score.","url":"https://doi.org/10.4018/ijec.420194","authors":["Qiuyue Ling"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-28T22:26:46Z","doi":"10.4018/ijec.420194","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/b978-0-443-26747-5.00006-9","name":"Cancer prediction using random forest convolutional neural network machine learning approach","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-26747-5.00006-9","authors":["Sonam Gour"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-17T10:23:27Z","doi":"10.1016/b978-0-443-26747-5.00006-9","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.47297/taposatwsp2633-456914.20260705","name":"Neural-Network-Based Bandgap Prediction for Photonic Crystal Waveguide Design","source":"crossref","abstract":"","url":"https://doi.org/10.47297/taposatwsp2633-456914.20260705","authors":["Wang Hanyue"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-17T06:53:28Z","doi":"10.47297/taposatwsp2633-456914.20260705","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1177/15330338261451109","name":"Corrigendum to “A Novel Network-Level Fused Self-Attention Deep Neural Network for Cervical Cancer Classification from Cervicography Images”","source":"crossref","abstract":"","url":"https://doi.org/10.1177/15330338261451109","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-12T09:34:06Z","doi":"10.1177/15330338261451109","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.69979/3041-0843.26.01.045","name":"Research on Object Grasping Prediction Model of Flexible Robotic Arm Based on Feedforward Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.69979/3041-0843.26.01.045","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-19T02:04:26Z","doi":"10.69979/3041-0843.26.01.045","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/aero66936.2026.11520061","name":"Real-Time Stability Monitoring of Neural Network Based Missile Guidance","source":"crossref","abstract":"","url":"https://doi.org/10.1109/aero66936.2026.11520061","authors":["Kenneth McDonald","Edward Daughtery","Zhihua Qu","Trevor McCants","Jason Beck"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-22T19:33:47Z","doi":"10.1109/aero66936.2026.11520061","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.jhydrol.2025.134689","name":"Machine unlearning: bias correction in neural network downscaled storms","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.jhydrol.2025.134689","authors":["Simon Michael Papalexiou","Antonios Mamalakis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-28T07:43:22Z","doi":"10.1016/j.jhydrol.2025.134689","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.neucom.2026.133103","name":"DE-BNN: An evolutionary approach to Bayesian neural network posterior sampling","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2026.133103","authors":["Wesley Forbes","Min Long"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-20T16:30:03Z","doi":"10.1016/j.neucom.2026.133103","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/cai68641.2026.11536589","name":"Reject-Option Ensemble Learning for Neural Network-Based Channel Equalization","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cai68641.2026.11536589","authors":["Wellington D. Almeida","Ajalmar R. Rocha Neto"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-01T19:33:50Z","doi":"10.1109/cai68641.2026.11536589","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1051/bioconf/202623603001","name":"Colour classification of Bulgarian honey using spectroradiometry and neural network processing","source":"crossref","abstract":"This publication explores the possibility of implementing a colour classifier for various types of Bulgarian honey. For this purpose, spectroradiometric measurement is used based on a measuring device from JETI Technische Instrumente GmbH – Specbos1201 providing a measurement range in the visible spectrum – 380 ~ 820 nm, which is complemented by a reference light source BYK Byko-spectra – D65. The obtained data is used to implement two types of classification, between which a comparison was made in terms of a quality indicator - a KNN classifier and a classifier with a neural network with discrete outputs. In order to reduce the number of inputs, the spectral data was transformed into the standard CIE-Lab 1976 colour space. The obtained results show a very good possibility for implementing a classifier using a neural network, with an extremely low level of potential misclassification despite the usage of a relatively small amount of training data.","url":"https://doi.org/10.1051/bioconf/202623603001","authors":["Ventsislav Simonov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-25T07:47:37Z","doi":"10.1051/bioconf/202623603001","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.procs.2026.03.377","name":"Neural Network Model-Based Fault Diagnosis for Integrated Circuits","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.procs.2026.03.377","authors":["Lei Wu","Hongyuan Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-30T07:33:17Z","doi":"10.1016/j.procs.2026.03.377","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.17775/cseejpes.2022.01340","name":"Neural-Network Estimation Coordinated State Feedback Control for Parallel Inverters Considering Filter Parameter Variation","source":"crossref","abstract":"","url":"https://doi.org/10.17775/cseejpes.2022.01340","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-22T03:19:49Z","doi":"10.17775/cseejpes.2022.01340","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/isbdas69350.2026.11484250","name":"Projection Neural Network for Solving Interval Quadratic Programming Problems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isbdas69350.2026.11484250","authors":["Feng Zhou","Shenglan Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-24T19:44:36Z","doi":"10.1109/isbdas69350.2026.11484250","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.65599/iii9326","name":"APPLICATION OF NONLINEAR AUTOREGRESSIVE NEURAL NETWORK FOR PREDICTIVE ANALYSIS AND SIGNAL OPTIMIZATION IN 5G NETWORKS","source":"crossref","abstract":"This paper explores the possibility of improving the efficiency of fifth-generation communication networks through the use of intelligent forecasting methods. The aim of the study is to apply a nonlinear autoregressive neural network (NARNN) for the analysis and prediction of changes in radio signal parameters in 5G networks, followed by proactive radio resource management. Time series of RSRP and SINR indicators characterizing the state of the radio channel are used as input data. The modeling is carried out using a neural network architecture with time delays trained on experimental data. The forecasting accuracy is evaluated using standard error metrics. The results demonstrate that the application of NARNN makes it possible to detect signal quality degradation in advance and adapt network parameters, thereby ensuring more stable and reliable operation of fifth-generation networks. Keywords: fifth-generation networks, nonlinear autoregressive neural network, signal forecasting, time series, radio resource management, communication quality.","url":"https://doi.org/10.65599/iii9326","authors":["Behruz Saidov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-15T05:21:09Z","doi":"10.65599/iii9326","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.neucom.2026.134176","name":"Multi-time dynamics in neural network optimization: A unified framework bridging game theory and optimal control","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2026.134176","authors":["Massimiliano Ferrara"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-02T16:28:33Z","doi":"10.1016/j.neucom.2026.134176","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/ictp67998.2026.11485389","name":"Hybrid Graph-Neural Network and Transformer Models for Dynamic Social Network Analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ictp67998.2026.11485389","authors":["Shaziya Islam","Ansar Isak Sheikh","Jayapal Lande","Mayank Srivastava","Anandakumar Haldorai","Tarak Hussain","S Suresh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-23T19:57:35Z","doi":"10.1109/ictp67998.2026.11485389","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.7551/mitpress/3163.003.0005","name":"An Introduction to Neural Network Modeling","source":"crossref","abstract":"","url":"https://doi.org/10.7551/mitpress/3163.003.0005","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-12-14T02:49:52Z","doi":"10.7551/mitpress/3163.003.0005","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.3724/j.1006-8775.2026.019","name":"A neural network-based Forward Operator for Visible Satellite Images","source":"crossref","abstract":"","url":"https://doi.org/10.3724/j.1006-8775.2026.019","authors":["Yongbo Zhou","Sicheng Pan","Peilong Yu","Han Wei"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-04T01:58:50Z","doi":"10.3724/j.1006-8775.2026.019","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.63070/jesc.2026.032","name":"A Multi-Similarity Neural Network for Paraphrase Detection","source":"crossref","abstract":"This study introduces a multi-similarity neural network framework for paraphrase detection, an important task in natural language processing that identifies whether two sentences convey the same meaning using different expressions. The proposed method combines various similarity measures, such as string-based similarity, semantic similarity, and embedding-based similarity, with a deep learning classifier. The framework is structured as a three-phase pipeline: preprocessing, extraction of multiple similarity features, and classification through a neural network. It employs more than 168 string similarity algorithms, semantic measures derived from WordNet, and several pre-trained embedding models to compute similarity scores. These features are aggregated and supplied to a deep neural network to determine whether sentence pairs are paraphrases. The model was evaluated on the Microsoft Research Paraphrase Corpus (MSRP) using accuracy and F1-score as performance metrics. The experimental results indicate that the proposed framework achieves 81.74% accuracy and an F1 Score of 86.6%, surpassing several existing approaches. Overall, the results suggest that integrating diverse similarity measures with neural networks enhances the identification of both explicit and nuanced paraphrases, thereby supporting advancements in text analysis and plagiarism detection systems.","url":"https://doi.org/10.63070/jesc.2026.032","authors":["Emad Nabil"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-11T16:12:11Z","doi":"10.63070/jesc.2026.032","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.3724/2096-7004.di.2026.0104","name":"Telecom Fraud Detection via Dual Hypergraph Neural Network under Multi-Dimensional Sparsity","source":"crossref","abstract":"","url":"https://doi.org/10.3724/2096-7004.di.2026.0104","authors":["Jiyuan Li","Jianwu Dang","Na Jiang","Jingyu Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-16T09:18:32Z","doi":"10.3724/2096-7004.di.2026.0104","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/icasst68917.2026.11498667","name":"Facial Landmark Detection using Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icasst68917.2026.11498667","authors":["Jyoti Saini","Jyoti Rani","Nitasha Tayal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-01T19:51:19Z","doi":"10.1109/icasst68917.2026.11498667","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/isqed69900.2026.11534703","name":"A Low-Power Analog Spiking Neural Network with On-Chip Learning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isqed69900.2026.11534703","authors":["Kiruthikan Sithamparanathan","Jeff Dix"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-28T22:26:58Z","doi":"10.1109/isqed69900.2026.11534703","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.neucom.2025.132184","name":"Deep neural network fingerprinting by general examples","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2025.132184","authors":["Qingguang Li","Guangluan Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-24T07:35:20Z","doi":"10.1016/j.neucom.2025.132184","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.14722/ndss.2026.241870","name":"Memory Backdoor Attacks on Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.14722/ndss.2026.241870","authors":["Eden Luzon","Guy Amit","Roy Weiss","Torsten Krauß","Alexandra Dmitrienko","Yisroel Mirsky"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-13T16:20:44Z","doi":"10.14722/ndss.2026.241870","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.procs.2026.05.025","name":"Carbon Trading Prediction Using Attention Mechanism Deep Neural Network Fusion Model","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.procs.2026.05.025","authors":["Jing Jia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-02T12:09:11Z","doi":"10.1016/j.procs.2026.05.025","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.neucom.2026.133498","name":"Fundamental limits of neural network sparsification: Evidence from catastrophic interpretability collapse","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2026.133498","authors":["Dip Roy","Rajiv Misra","Sanjay Kumar Singh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-27T03:52:45Z","doi":"10.1016/j.neucom.2026.133498","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/ijcnn.2006.246761","name":"Hybrid Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.246761","authors":["S.W. Al-Sayegh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-07-18T11:27:21Z","doi":"10.1109/ijcnn.2006.246761","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.5220/0014312800004070","name":"Seismocardiography (SCG) Signal Classification of Valvular Heart Diseases with Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0014312800004070","authors":["Mahsa Banadkooki","Martin Bogdan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-27T11:13:44Z","doi":"10.5220/0014312800004070","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/ecai69016.2026.11613600","name":"Convexity Modulus in Incremental Neural Network Approximation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ecai69016.2026.11613600","authors":["Zahraa Haidar Sharba","Hawraa Abbas Almurieb"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-24T19:05:55Z","doi":"10.1109/ecai69016.2026.11613600","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.neucom.2026.134925","name":"Fixed point prediction using a hybrid neural network with chaotic oscillators","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2026.134925","authors":["Sasan Soltani","Farshid Khojasteh","Majid Alavi","Majid Haghverdi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-28T12:53:30Z","doi":"10.1016/j.neucom.2026.134925","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.neucom.2026.133914","name":"A hybrid quantum-classical neural network framework for genomic sequence classification","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2026.133914","authors":["Riya Bansal","Nikhil Kumar Rajput","Megha Khanna"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-09T23:09:45Z","doi":"10.1016/j.neucom.2026.133914","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1201/9780429265686-3","name":"Neural Network Structures","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9780429265686-3","authors":["Hasmik Osipyan","Bosede Iyiade Edwards","Adrian David Cheok"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-17T12:22:57Z","doi":"10.1201/9780429265686-3","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.5220/0014322300004052","name":"A Lightweight Spatial-Temporal Graph Neural Network for Long-Term Time Series Forecasting","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0014322300004052","authors":["Henok Moges","Deshendran Moodley"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-13T07:25:13Z","doi":"10.5220/0014322300004052","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/tnnls.2022.3176887","name":"Exponential Synchronization of Memristor-Based Competitive Neural Networks With Reaction- Diffusions and Infinite Distributed Delays","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnnls.2022.3176887","authors":["Leimin Wang","Chuan-Ke Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-05-27T16:57:57Z","doi":"10.1109/tnnls.2022.3176887","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.36341/rabit.v11i2.7934","name":"KLASIFIKASI TINGKAT KEMATANGAN BUAH PISANG TANDUK MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK","source":"crossref","abstract":"Penelitian ini bertujuan untuk membangun sistem klasifikasi tingkat kematangan buah pisang tanduk menggunakan metode Convolutional Neural Network (CNN) berbasis Transfer Learning dengan arsitektur MobileNetV2 dan EfficientNetB0. Dataset yang digunakan terdiri dari 1.142 citra buah pisang tanduk yang dibagi menjadi data training dan validation. Proses pelatihan model dilakukan menggunakan teknik augmentasi data dan regularisasi untuk meningkatkan kemampuan generalisasi model. Hasil penelitian menunjukkan bahwa model MobileNetV2 memperoleh performa terbaik dengan nilai accuracy sebesar 97,75%, precision sebesar 97,84%, recall sebesar 97,75%, dan F1-score sebesar 97,74%. Sementara itu, EfficientNetB0 memperoleh nilai accuracy sebesar 90,09%. Model terbaik kemudian diimplementasikan ke dalam sistem prediksi berbasis website untuk melakukan klasifikasi tingkat kematangan buah pisang tanduk secara otomatis dan real-time. Hasil penelitian menunjukkan bahwa metode CNN berbasis Transfer Learning mampu memberikan performa klasifikasi yang sangat baik dalam mengidentifikasi tingkat kematangan buah pisang tanduk.","url":"https://doi.org/10.36341/rabit.v11i2.7934","authors":["Dela_rizqi Fitriani","Dela Rizqi Fitriani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-11T00:03:24Z","doi":"10.36341/rabit.v11i2.7934","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.31645/jisrc.26.24.1.12","name":"An Enhanced Variant of Graph-Constrained Neural Multi-Objective Evolutionary Algorithm for Sparse Neural Network Training","source":"crossref","abstract":"Sparse neural networks are essential for deploying deep learning models on resource-limited and latency-sensitive platforms, where efficiency must be improved without compromising predictive performance. While the Graph-Constrained Neural Multi-Objective Evolutionary Algorithm (GCNMOEA) has demonstrated advantages in sparsity promotion, runtime efficiency, and population diversity, its performance is hindered by reduced accuracy, unstable early-stage convergence, and lower hypervolume under moderate sparsity. To address these limitations, this study proposes Enhanced GCNMOEA, an improved variant that integrates accuracy-aware graph mutation, a two- phase dominance–decomposition selection mechanism, multifidelity evaluation, and adaptive diversity scheduling. These enhancements collectively strengthen structural preservation, reduce fitness noise, and improve convergence behaviour. Experimental evaluations on MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100 across LeNet-5, ResNet-18, and MobileNetV2 architectures demonstrate that the proposed variant achieves consistently higher accuracy, improved hypervolume, and reduced IGD variance, while maintaining the sparsity and runtime benefits of the baseline algorithm. The results confirm that Enhanced GCNMOEA deliverreal-worldsuperior Pareto-front quality and improved robustness, making it a strong candidate for real world edge and embedded neural network applications.","url":"https://doi.org/10.31645/jisrc.26.24.1.12","authors":["Collen Channer","Syed Sajjad Hussain Rizvi","Peter Ndajah","Otis Osbourne"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-06T10:50:42Z","doi":"10.31645/jisrc.26.24.1.12","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1007/s00521-026-11898-3","name":"PolyNeXt: a novel semantic segmentation network for polyp detection in colonoscopy images","source":"crossref","abstract":"Abstract Colorectal polyps are precancerous lesions with a high risk of developing into cancer if left untreated. Colonoscopy is the gold standard for detecting and removing these polyps, but it has high miss rates, especially for small and flat polyps. Deep learning methods have been increasingly used to aid in polyp detection, but their performance remains limited when applied to samples captured under unconstrained conditions or when processing images of small and flat polyps. To address this challenge, we propose PolyNeXt, a novel polyp segmentation network that leverages ConvNeXtV2 and global response normalization (GRN) layers. We train PolyNeXt on a combined dataset of samples from Kvasir-SEG and CVC-ClinicDB and evaluate it on four public distinct datasets: ETIS-LaribPolypDB, CVC-ColonDB, CVC-300, and BKAI-IGH NeoPolyp-Small. PolyNeXt achieves state-of-the-art performance on polyps captured in suboptimal conditions, outperforming other methods in terms of Intersection over Union (IoU) and Dice coefficient. Our work demonstrates that PolyNeXt is an effective polyp segmentation network that can improve the accuracy and reliability of detecting polyps captured under challenging circumstances.","url":"https://doi.org/10.1007/s00521-026-11898-3","authors":["Khaled ELKarazle","Valliappan Raman","Caslon Chua","Patrick Then"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-17T03:28:27Z","doi":"10.1007/s00521-026-11898-3","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/icsigsys71160.2026.11613903","name":"Implementation of a Lightweight Convolutional Neural Network for the Detection of Gastrointestinal Disorders","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icsigsys71160.2026.11613903","authors":["Varun Sahni"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-22T19:15:10Z","doi":"10.1109/icsigsys71160.2026.11613903","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1093/jjfinec/nbag019","name":"Neural-Network Volatility Forecasting","source":"crossref","abstract":"Abstract We investigate how training regimes and sample size affect the performance of neural networks in financial forecasting. Using volatility forecasts for more than 10,000 stocks, we find that, within the specifications studied, performance gains from sample size scaling outweigh those from model size scaling or architectural choice. We further show that, when NNs are applied to financial data, global estimation is better aligned with their data-intensive nature and materially enhances their practical viability.","url":"https://doi.org/10.1093/jjfinec/nbag019","authors":["Chen Liu","Minh-Ngoc Tran","Chao Wang","Richard Gerlach","Robert Kohn"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-23T11:51:15Z","doi":"10.1093/jjfinec/nbag019","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.63367/199115992026063703017","name":"Biomedical Event Extraction via Multi-Grained Graph Neural Network","source":"crossref","abstract":"Biomedical event extraction (BEE) is a significant task which plays an important role for some downstream biomedical applications. The recent works have applied joint methods using Graph Convolutional Network (GCN) based on the dependency tree to capture non-local syntactic features for the BEE task. However, in the graph of GCN, some edges are redundant which need to be pruned, and some dependency type labels are neglected which only can make the model capture coarse-grained features. In this paper, we propose a novel BEE method based on a Multi-Grained Graph Neural Network (MGGNN) structure. Specifically, the coarse-grained module using a standard GCN in MGGNN can first capture coarse-grained features in the biological text. Then, based on the proposed relation-attention guided GCN (RAGGCN), the fine-grained module intro-duces dependency type labels to prune edges and generates full-connection weight adjacent matrices during the node aggregation, which can capture fine-grained features by refining the coarse-grained ones. The experiment results on the MLEE dataset show that the proposed model achieves state-of-the-art performance with 1.06% higher F1 score for the BEE task. The extended experiment on the ACE2005 dataset also confirms the great generalization in the general domain.","url":"https://doi.org/10.63367/199115992026063703017","authors":["Fangyong Tan","Jing Zhang","Ruifeng Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-29T11:25:30Z","doi":"10.63367/199115992026063703017","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1007/978-3-032-20855-2_6","name":"Deep Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-20855-2_6","authors":["Xiang-Sheng Wang","Chisheng Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-19T22:02:24Z","doi":"10.1007/978-3-032-20855-2_6","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.23919/eusipco47968.2020.9287574","name":"Offline Training for Memristor-based Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.23919/eusipco47968.2020.9287574","authors":["Guillem Boquet","Edwar Macias","Antoni Morell","Javier Serrano","Enrique Miranda","Jose Lopez Vicario"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-18T21:54:18Z","doi":"10.23919/eusipco47968.2020.9287574","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1088/2634-4386/acb2f0","name":"Text classification in memristor-based spiking neural networks","source":"crossref","abstract":"Abstract Memristors, emerging non-volatile memory devices, have shown promising potential in neuromorphic hardware designs, especially in spiking neural network (SNN) hardware implementation. Memristor-based SNNs have been successfully applied in a wide range of applications, including image classification and pattern recognition. However, implementing memristor-based SNNs in text classification is still under exploration. One of the main reasons is that training memristor-based SNNs for text classification is costly due to the lack of efficient learning rules and memristor non-idealities. To address these issues and accelerate the research of exploring memristor-based SNNs in text classification applications, we develop a simulation framework with a virtual memristor array using an empirical memristor model. We use this framework to demonstrate a sentiment analysis task in the IMDB movie reviews dataset. We take two approaches to obtain trained SNNs with memristor models: (1) by converting a pre-trained artificial neural network (ANN) to a memristor-based SNN, or (2) by training a memristor-based SNN directly. These two approaches can be applied in two scenarios: offline classification and online training. We achieve the classification accuracy of 85.88% by converting a pre-trained ANN to a memristor-based SNN and 84.86% by training the memristor-based SNN directly, given that the baseline training accuracy of the equivalent ANN is 86.02%. We conclude that it is possible to achieve similar classification accuracy in simulation from ANNs to SNNs and from non-memristive synapses to data-driven memristive synapses. We also investigate how global parameters such as spike train length, the read noise, and the weight updating stop conditions affect the neural networks in both approaches. This investigation further indicates that the simulation using statistic memristor models in the two approaches presented by this paper can assist the exploration of memristor-based SNNs in natural language processing tasks.","url":"https://doi.org/10.1088/2634-4386/acb2f0","authors":["Jinqi Huang","Alexantrou Serb","Spyros Stathopoulos","Themis Prodromakis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-13T22:28:01Z","doi":"10.1088/2634-4386/acb2f0","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1088/0954-898x_9_4_007","name":"Hypothetical neural mechanism that may play a role in mental rotation: an attractor neural network model","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_9_4_007","authors":["Ľubica Beňušková","Slavomír Eštok"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T16:05:01Z","doi":"10.1088/0954-898x_9_4_007","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.23919/date69613.2026.11539431","name":"Identifying Hardware Optimizations for Neural Network Inference using Virtual Prototypes","source":"crossref","abstract":"","url":"https://doi.org/10.23919/date69613.2026.11539431","authors":["Jan Zielasko","Rolf Drechsler"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-04T19:53:10Z","doi":"10.23919/date69613.2026.11539431","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/iwcmc69287.2026.11579829","name":"Neuromorphic Federated Continual Learning: A Spiking Neural Network Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iwcmc69287.2026.11579829","authors":["Manh V. Nguyen","Liang Zhao","Shaoen Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-03T19:49:45Z","doi":"10.1109/iwcmc69287.2026.11579829","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/melecon64486.2026.11418884","name":"Recognition and Localization of Breast Tumor Using a Neural Network Pipeline","source":"crossref","abstract":"","url":"https://doi.org/10.1109/melecon64486.2026.11418884","authors":["Florita Siritean","Loretta Ichim","Dan Popescu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-10T19:50:57Z","doi":"10.1109/melecon64486.2026.11418884","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/apscon68325.2026.11497496","name":"Lightweight Hybrid Neural Network for Enhanced ECG Signal Quality Assessment","source":"crossref","abstract":"","url":"https://doi.org/10.1109/apscon68325.2026.11497496","authors":["Evgenia Slivko","Kay Bierzynski","Lorenzo Servadei","Robert Wille"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-05T20:01:05Z","doi":"10.1109/apscon68325.2026.11497496","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1007/978-3-032-20855-2_5","name":"Shallow Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-20855-2_5","authors":["Xiang-Sheng Wang","Chisheng Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-19T22:02:38Z","doi":"10.1007/978-3-032-20855-2_5","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1201/9781420093339-7","name":"Neural Network Approaches for Defect Detection in Composite Materials","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781420093339-7","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-22T23:12:00Z","doi":"10.1201/9781420093339-7","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.1109/icosaas68663.2026.11649070","name":"HetGNN: Heterogeneous Graph Neural Network for English Learning Interest Assessment","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icosaas68663.2026.11649070","authors":["Lilan Chen","Yufeng Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-14T19:30:51Z","doi":"10.1109/icosaas68663.2026.11649070","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.23919/chicc.2019.8866412","name":"Multisynchronization of a class of delayed memristor-based neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.23919/chicc.2019.8866412","authors":["Ya-Qi Lin","Ming-Feng Ge","Teng-Fei Ding","Ziqi Zhu","Juanjuan He"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-10-17T23:19:42Z","doi":"10.23919/chicc.2019.8866412","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.31085/2310-8681-2026-1-228-133-142","name":"General social measures to prevent neural network crime: early prevention","source":"crossref","abstract":"","url":"https://doi.org/10.31085/2310-8681-2026-1-228-133-142","authors":["D. V. Budko"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-30T18:56:56Z","doi":"10.31085/2310-8681-2026-1-228-133-142","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.5220/0015078900004091","name":"Neural Network-Based Group Sparsity for Nonlinear Feature Selection in Multi-Output Problems","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0015078900004091","authors":["Mamadou Kanouté","Florence Forbes"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-20T01:35:31Z","doi":"10.5220/0015078900004091","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.neunet.2025.107959","name":"Concept-enhanced heterogeneous graph network for fact verification","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.107959","authors":["Zhendong Chen","Lejian Liao","Siu Cheung Hui","Heyan Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-08T02:16:09Z","doi":"10.1016/j.neunet.2025.107959","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/neuront71829.2026.11651370","name":"Compensation of Odometric Measurement Errors in a Mobile Robot based on a Nonlinear Motion Model using Neural Network Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1109/neuront71829.2026.11651370","authors":["Vasily D. Voroshchenko","Michael A. Gorkavyy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-18T19:03:54Z","doi":"10.1109/neuront71829.2026.11651370","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1007/s11063-011-9203-z","name":"Dynamics Analysis of a Class of Memristor-Based Recurrent Networks with Time-Varying Delays in the Presence of Strong External Stimuli","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11063-011-9203-z","authors":["Shiping Wen","Zhigang Zeng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-10-29T08:52:39Z","doi":"10.1007/s11063-011-9203-z","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.7717/peerjcs.1084/fig-1","name":"Figure 1: The network structure of convolutional neural network.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerjcs.1084/fig-1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-08-30T03:45:01Z","doi":"10.7717/peerjcs.1084/fig-1","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.38007/nn.2022.030407","name":"Image Features Fused with BP Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2022.030407","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T06:22:51Z","doi":"10.38007/nn.2022.030407","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1109/ijcnn.1989.118589","name":"ATM communications network control by neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.1989.118589","authors":["Hiramatsu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-01-13T18:46:33Z","doi":"10.1109/ijcnn.1989.118589","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.1109/syscon66367.2026.11503618","name":"Graph Neural Network-based Detection of Man-in-the-Middle Attacks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/syscon66367.2026.11503618","authors":["Awatef Khoury","Avi Mendelson","Ori Shacham-Barr"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-07T19:51:19Z","doi":"10.1109/syscon66367.2026.11503618","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.actaastro.2026.04.052","name":"Hybrid neural network adaptive relative navigation for orbital games","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.actaastro.2026.04.052","authors":["Shiyuan Zhang","Shan Lu","Qing Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-24T15:43:45Z","doi":"10.1016/j.actaastro.2026.04.052","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1088/2631-8695/ae8077","name":"A Multi-channel convolutional neural network for ECG signal classification","source":"crossref","abstract":"Abstract Electrocardiogram (ECG) signal classification plays significant role in early diagnosis, continuous monitoring cardiovascular diseases. The existing deep learning methods often rely on single-domain feature extraction methods, restricting capability of capturing their complex temporal, morphological, and spectral characteristics of non-stationary ECG signals. To overcome these limitations, proposes a novel multi-channel convolutional neural network (CNN) framework integrating Bernstein polynomial-based segmentation with Smoothed Pseudo Wigner–Ville Distribution-based time-frequency representation for robust ECG classification. The proposed framework combines a 1D CNN branch for temporal and morphological feature extraction with a 2D CNN branch for spectral feature learning. The proposed model was evaluated using MIT-BIH arrhythmia dataset and externally validated using PTB-XL ECG dataset. To improve evaluation reliability and minimize overfitting, patient-wise data splitting and 5-fold cross-validation were incorporated. The proposed framework achieves greater classification performance with an accuracy of 99.1%, sensitivity of 98.2%, specificity of 98.9%, precision of 98.0%, and F 1-score of 97.2% on the MIT-BIH dataset while maintaining strong generalization capability on PTB-XL. The proposed framework provides an effective and scalable solution for intelligent real-time ECG abnormality detection and future multi-class arrhythmia analysis.","url":"https://doi.org/10.1088/2631-8695/ae8077","authors":["Harshini Polavarapu","Rajesh Mitukula"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-22T22:53:15Z","doi":"10.1088/2631-8695/ae8077","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1007/978-1-4842-4421-0_6","name":"Neural Network Prediction Outside the Training Range","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4842-4421-0_6","authors":["Igor Livshin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-04-12T15:05:25Z","doi":"10.1007/978-1-4842-4421-0_6","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.geoai.2026.100080","name":"Ground motion modelling with bidirectional liquid neural network (BLiqNet)","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.geoai.2026.100080","authors":["Pavan Mohan Neelamraju","Raghukanth STG"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-22T15:56:46Z","doi":"10.1016/j.geoai.2026.100080","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.ins.2026.123418","name":"Cluster-guided adaptive multi-relational graph neural network for recommender systems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.ins.2026.123418","authors":["Jhansi Lakshmi Vigrahala","Abinash Pujahari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-25T00:18:19Z","doi":"10.1016/j.ins.2026.123418","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.3103/s1060992x25602234","name":"Radiography and Subject Data Integration for Osteoporosis Detection Using Dingo Optimization Based Deep Belief Network Model","source":"crossref","abstract":"","url":"https://doi.org/10.3103/s1060992x25602234","authors":["Dhanyavathi A","Veena M B"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-26T17:36:33Z","doi":"10.3103/s1060992x25602234","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.38007/nn.2021.020407","name":"Image Emotion Recognition Supporting Fuzzy Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2021.020407","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T18:12:48Z","doi":"10.38007/nn.2021.020407","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1007/978-981-97-4399-5_37","name":"New Results on Input-to-State Stability of Memristor-Based Inertial Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-4399-5_37","authors":["Yuxin Jiang","Song Zhu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-06T16:01:52Z","doi":"10.1007/978-981-97-4399-5_37","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1088/0954-898x_2_1_008","name":"The role of dimensionality in a threshold-controlled neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_2_1_008","authors":["A Hartstein"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:03:58Z","doi":"10.1088/0954-898x_2_1_008","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/cac.2017.8242954","name":"Adaptive synchronization of fractional-order memristor-based neural networks with multiple time-varying delays","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cac.2017.8242954","authors":["Jia Jia","Xia Huang","Yuxia Li","Zhen Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-01-05T17:56:39Z","doi":"10.1109/cac.2017.8242954","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1049/pbcs038e_ch7","name":"Memristor-based multiplier designs","source":"crossref","abstract":"","url":"https://doi.org/10.1049/pbcs038e_ch7","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-24T08:06:28Z","doi":"10.1049/pbcs038e_ch7","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.neurom.2026.06.479","name":"A Network-Informed Perspective on Targeting the Urge to Tic With CM-Pf Deep Brain Stimulation","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neurom.2026.06.479","authors":["John Wohlgemuth","Allison C. Waters","Joohi Jimenez-Shahed"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-08T16:46:01Z","doi":"10.1016/j.neurom.2026.06.479","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1007/s00521-026-11899-2","name":"ProAttNet: a novel network of prostate segmentation with multi-attention residual U-Net using magnetic resonance images","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-026-11899-2","authors":["R. Deiva Nayagam","D. Selvathi","S. Shalini"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-23T04:43:04Z","doi":"10.1007/s00521-026-11899-2","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.38007/nn.2021.020404","name":"Roughness Prediction Model Based on Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2021.020404","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T18:12:48Z","doi":"10.38007/nn.2021.020404","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.21203/rs.3.rs-2913556/v1","name":"A new deep neural network for forecasting: Deep dendritic artificial neural network","source":"crossref","abstract":"Abstract Deep artificial neural networks have become a good alternative to classical forecasting methods in solving forecasting problems. Popular deep neural networks classically use additive aggregation functions in their cell structures. It is available in the literature that the use of multiplicative aggregation functions in shallow artificial neural networks produces successful results for the forecasting problem. A type of high-order shallow artificial neural network that uses multiplicative aggregation functions is the dendritic neuron model artificial neural network, which has successful forecasting performance. The first contribution of this work is the transformation of the dendritic neuron model, which works with a single output in the literature, into a multi-output architecture. The second contribution is to propose a new dendritic cell based on the multi-output dendritic neuron model for use in deep artificial neural networks. The other most important contribution of the study is to propose a new deep artificial neural network, a deep dendritic artificial neural network, based on the dendritic cell. The training of the deep dendritic artificial neural network is carried out with the differential evolution algorithm. The forecasting performance of the deep dendritic artificial neural network is compared with basic classical forecasting methods and some recent shallow and deep artificial neural networks over stock market time series. As a result, it has been observed that deep dendritic artificial neural network produces very successful forecasting results for the forecasting problem.","url":"https://doi.org/10.21203/rs.3.rs-2913556/v1","authors":["Erol Egrioglu","Eren Bas"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-12T03:49:09Z","doi":"10.21203/rs.3.rs-2913556/v1","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1007/978-3-032-32918-9_3","name":"Software and Information System for Coordinate Measuring Arms with Neural Network Error Compensation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-32918-9_3","authors":["Denys Kataiev","Janusz Kacprzyk","Artur Zaporozhets"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-23T11:30:46Z","doi":"10.1007/978-3-032-32918-9_3","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/ijcnn.2011.6033530","name":"Memristor synaptic dynamics' influence on synchronous behavior of two Hindmarsh-Rose neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2011.6033530","authors":["Fernando Corinto","Alon Ascoli","Valentina Lanza","Marco Gilli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-10-06T17:24:17Z","doi":"10.1109/ijcnn.2011.6033530","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1007/s00521-026-12055-6","name":"NeuroXAI-Caps: an explainable CNN–capsule network for early Alzheimer’s diagnosis","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-026-12055-6","authors":["Muhammad Shahan Ibad","Omar Bin Samin","Adnan Amin","Feras Al-Obeidat","Fernando Moreira"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-10T15:19:58Z","doi":"10.1007/s00521-026-12055-6","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.neunet.2025.108221","name":"Multi-stage dual-domain progressive network with synergistic training for sparse-view CT reconstruction","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.108221","authors":["Jingyuan Shao","Huabao Chen","Qiankun Li","Xiang Huang","Jiong Shu","Lingling Liu","Shaobin Dou","Hongzhi Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-18T14:49:11Z","doi":"10.1016/j.neunet.2025.108221","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1007/978-3-032-32918-9_5","name":"Neural Network Calibration of Coordinate Measuring Systems: Architecture, Hyperparameter Study, and Experimental Validation","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-32918-9_5","authors":["Denys Kataiev","Janusz Kacprzyk","Artur Zaporozhets"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-23T11:30:36Z","doi":"10.1007/978-3-032-32918-9_5","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.neunet.2025.108502","name":"Color-resolved light field shaping via diffractive-electronic U-shape network with wavelength-aware virtual branching","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.108502","authors":["Yuheng Zong","Huaiping Jin","Hao Fang","Chai Hu","Jiashuo Shi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-22T16:57:00Z","doi":"10.1016/j.neunet.2025.108502","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1117/3.633187.apa","name":"The Feedforward Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1117/3.633187.apa","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2009-09-04T20:24:49Z","doi":"10.1117/3.633187.apa","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1007/s11432-018-9817-4","name":"Exponential stabilization of memristor-based neural networks with unbounded time-varying delays","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11432-018-9817-4","authors":["Jiemei Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-06-05T05:02:21Z","doi":"10.1007/s11432-018-9817-4","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1007/s00521-025-11833-y","name":"HASP-Net: hierarchical adaptive structural pooling network for ancient Chinese character recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-025-11833-y","authors":["Kunpeng Wang","Yuanping Zhu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-14T01:17:54Z","doi":"10.1007/s00521-025-11833-y","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.2514/6.2026-2194","name":"Deep Neural Network as 5-D Image for Threat Avoidance","source":"crossref","abstract":"","url":"https://doi.org/10.2514/6.2026-2194","authors":["Alexander W. Denton","Michael P. Riddick","Isaac E. Weintraub","Donald L. Kunz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-03T07:51:02Z","doi":"10.2514/6.2026-2194","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1145/3807246.3807298","name":"A Neural Network PID Control System Based on XGBoost Identifier","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3807246.3807298","authors":["Hongkai Zhang","Haoming Yuan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-09T10:50:37Z","doi":"10.1145/3807246.3807298","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1007/978-981-95-2964-3_3","name":"Neural Network-Based Event-Triggered Cooperative Adaptive Neural Control for Cyber-Physical Systems with Unknown State Time-Delays and Deception Attacks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-95-2964-3_3","authors":["Xin Wang","Huaqing Li","Tingwen Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-02T02:56:51Z","doi":"10.1007/978-981-95-2964-3_3","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.neunet.2026.109090","name":"MIRA: Multi-scale invertible dual-attention redundancy-aware network for high-capacity video steganography","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.109090","authors":["Qianhui XU","Ke NIU","Jun LI","Shunzhe Zhu","Yihang Lu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-11T06:31:01Z","doi":"10.1016/j.neunet.2026.109090","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1049/pbcs038e_ch6","name":"Memristor-based adder designs","source":"crossref","abstract":"","url":"https://doi.org/10.1049/pbcs038e_ch6","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-24T08:06:28Z","doi":"10.1049/pbcs038e_ch6","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1007/s00702-026-03128-w","name":"Language network disruption in patients with Lewy body diseases","source":"crossref","abstract":"Abstract Lewy body diseases, including Parkinson’s disease and dementia with Lewy bodies, are marked by neuronal α‑synuclein aggregation, motor parkinsonism, cognitive impairment and diverse non‑motor symptoms including communication impairments. Compared to other symptoms, non‑motor communication impairments remain under-explored, especially outside English‑speaking cohorts. The aim of this study was to elucidate the neural underpinnings of linguistic deficits as assessed by fMRI in Czech-speaking patients diagnosed with neuronal Lewy body disease and mild cognitive impairment (LBD-MCI). Scores from the Short Neuropsychological Battery and resting‑state functional MRI data were analyzed in 26 Czech‑speaking patients with LBD‑MCI and 24 healthy controls. Analyses targeted regions of interest within the dorsal and ventral language networks. We applied graph theory metrics, within‑network connectivity and seed‑based functional connectivity analysis. Graph analysis revealed dorsal‑stream disruption in LBD‑MCI: reduced clustering coefficient, increased path length, and diminished node strength, each correlating with language functions; ventral‑stream topology remained intact. Within‑network analyses showed impaired connectivity across both pathways, but weaker coupling between the opercular inferior frontal gyrus and posterior superior temporal gyrus predicted behavioral scores in language functioning, further highlighting dorsal vulnerability. Seed‑based analysis identified reduced frontotemporal connectivity in the dorsal stream and decreased fronto‑occipital and temporo-cerebellar connections in the ventral stream. LBD‑MCI is characterized particularly by network‑specific reductions in dorsal language stream efficiency and functional connectivity, underpinning syntactic and phonological processing deficits. These findings offer novel insights in the neural basis of language impairment in LBD-MCI.","url":"https://doi.org/10.1007/s00702-026-03128-w","authors":["Daniel Carbol","Lubomira Novakova","Patricia Klobusiakova","Irena Rektorova"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-07T08:02:53Z","doi":"10.1007/s00702-026-03128-w","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.neunet.2026.109016","name":"PDGCN: A progressive dual-branch graph convolution network for EEG emotion recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.109016","authors":["Lina Qiu","Minjin Wu","You Hu","Baiqiang Long","Tianjian Chen","Jiahui Pan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-17T15:45:28Z","doi":"10.1016/j.neunet.2026.109016","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.patcog.2026.113978","name":"Efficient Neural Architecture Search for brain-inspired spiking neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.patcog.2026.113978","authors":["Peilin Lai","Yang Zhang","Weizhao He","Yu Zeng","Hongsong Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-22T15:34:19Z","doi":"10.1016/j.patcog.2026.113978","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/ssiai68148.2026.11553767","name":"Inverting Neural Networks: New Methods to Generate Neural Network Inputs from Prescribed Outputs","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ssiai68148.2026.11553767","authors":["Rebecca Pattichis","Sebastian Janampa","Constantinos S. Pattichis","Marios S. Pattichis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-11T19:58:56Z","doi":"10.1109/ssiai68148.2026.11553767","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1007/978-3-540-48125-6_10","name":"Neural Network Adjustment Algorithms","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-540-48125-6_10","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-10-28T00:36:19Z","doi":"10.1007/978-3-540-48125-6_10","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1088/1674-1056/22/4/040502","name":"A memristor oscillator based on a twin-T network","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1674-1056/22/4/040502","authors":["Zhi-Jun Li","Yi-Cheng Zeng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-04-05T19:29:06Z","doi":"10.1088/1674-1056/22/4/040502","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/csnt69054.2026.11502506","name":"Optimized Convolutional Neural Network Architecture for Early and Accurate Heart Disease Diagnosis","source":"crossref","abstract":"","url":"https://doi.org/10.1109/csnt69054.2026.11502506","authors":["Karthikeyini S","Revathi. B.S","Ravikumar M","Abishek S","Athira S","Nithin G"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-08T19:37:43Z","doi":"10.1109/csnt69054.2026.11502506","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/icassp55912.2026.11462878","name":"VNODE: A Piecewise Continuous Volterra Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icassp55912.2026.11462878","authors":["Siddharth Roheda","Aniruddha Bala","Rohit Chowdhury","Rohan Jaiswal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-21T21:25:57Z","doi":"10.1109/icassp55912.2026.11462878","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/icassp55912.2026.11460488","name":"Multi-View Hierarchical Hypergraph Neural Network for Automatic Stuttering Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icassp55912.2026.11460488","authors":["Pragya Khanna","Anil Kumar Vuppala"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-21T21:25:28Z","doi":"10.1109/icassp55912.2026.11460488","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.2514/6.2026-2770","name":"Neural Network Aided Adaptive Tabulation with Dynamic Load Balancing for Vapor-Liquid Equilibrium Modeling of Transcritical Multiphase Flows","source":"crossref","abstract":"","url":"https://doi.org/10.2514/6.2026-2770","authors":["Navneeth Srinivasan","Suo Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-03T08:40:23Z","doi":"10.2514/6.2026-2770","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.neunet.2025.108466","name":"FFTNet: fNIRS-based frequency-enhanced patch network for driving fatigue detection","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.108466","authors":["Yu Li","Xudong Jia","Yu Sun","Yan Cui","Junhua Li","Zhen Yuan","Feng Wan","Hui Zheng","Hongtao Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-09T16:15:18Z","doi":"10.1016/j.neunet.2025.108466","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.55041/ijsrem65753","name":"Network Attacker Detection Using a Hybrid Graph Neural Network and Temporal Convolutional Network Framework","source":"crossref","abstract":"","url":"https://doi.org/10.55041/ijsrem65753","authors":["Titorea veera jothi Archunan Titorea veera jothi Archunan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-18T14:15:00Z","doi":"10.55041/ijsrem65753","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.2478/agriceng-2026-0004","name":"Application of Back-Propagation Artificial Neural Network and Particle Swarm Optimization Methods in Sprinkler Optimization","source":"crossref","abstract":"Abstract The aim of this paper was to analyze the primary and secondary order of influencing factors and to establish a BP neural network prediction model with different hydraulic performance indicators. Particle swarm optimization algorithm was used to test for the optimal hydraulic performance of the nozzle and validated by experiment. The orthogonal design covered the 200–300 kPa range, while the PSO algorithm selected 540 kPa based on the full dataset. The sprinkler was raised at a height of 1.4 m from the ground level in a square configuration. The optimal parameter combination for the square layout achieved higher uniformity and controlled maximum kinetic energy relative to the average sprinkling intensity. Results from the experiment gave 4.71 mm·h −1 , 83.28% and 0.0078 W·m −2 for average sprinkler intensity, CU and maximum kinetic energy, respectively. Compared with the rangeanalysis- based scheme, the optimized configuration reduced average irrigation intensity while improving uniformity and kinetic energy performance. The maximum error between experimental results and optimization results was 3.29%, indicating that the optimization model is feasible and reliable. This study proposes a practical optimization framework for the design and operation of sprinkler irrigation systems.","url":"https://doi.org/10.2478/agriceng-2026-0004","authors":["Zakaria Issaka"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-17T10:42:12Z","doi":"10.2478/agriceng-2026-0004","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1039/d6tc01104g/v2/review2","name":"Review for \"Volatile nanocomposite memristor with a phase stratification dielectric layer: a threshold switching with rich neuromorphic dynamics\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d6tc01104g/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-28T21:09:57Z","doi":"10.1039/d6tc01104g/v2/review2","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1039/d6tc01104g/v1/review3","name":"Review for \"Volatile nanocomposite memristor with a phase stratification dielectric layer: a threshold switching with rich neuromorphic dynamics\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d6tc01104g/v1/review3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-28T21:09:57Z","doi":"10.1039/d6tc01104g/v1/review3","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1145/3795101.3814677","name":"A Probabilistic L-System Inspired Designer for Neural Architecture Search: A Graph Neural Network Case Study on Node Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3795101.3814677","authors":["Maciej Krzywda","Szymon Łukasik","Amir Gandomi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-13T20:45:38Z","doi":"10.1145/3795101.3814677","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/newcas58973.2024.10666111","name":"PyT-NeuroPack: A Hybrid PyTorch/Memristor-Crossbar Simulation Tool for Convolutional Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/newcas58973.2024.10666111","authors":["Cristian Sestito","Weijie Huang","Shady Agwa","Themis Prodromakis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-17T18:47:00Z","doi":"10.1109/newcas58973.2024.10666111","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.2514/6.2026-0590","name":"Neural-Network-Based Computational Framework for the Variational Theory of Lift","source":"crossref","abstract":"","url":"https://doi.org/10.2514/6.2026-0590","authors":["Abdelrahman A. Elmaradny","Aras Vakilimafakheri","Abdelrahman A. Abdelrazek","Haithem E. Taha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-29T07:09:51Z","doi":"10.2514/6.2026-0590","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/ijcnn64981.2025.11228482","name":"A Novel Computing Paradigm for MobileNetV3 using Memristor","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn64981.2025.11228482","authors":["Jiale Li","Zhihang Liu","Sean Longyu Ma","Chiu-Wing Sham","Chong Fu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T18:46:15Z","doi":"10.1109/ijcnn64981.2025.11228482","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/icaci55529.2022.9837571","name":"Globally Exponential Stability of Uncertain Memristor-based Recurrent Neural Networks with Unbounded Time-varying Delays","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icaci55529.2022.9837571","authors":["Yijie Dong","Jianmin Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-07-29T19:38:39Z","doi":"10.1109/icaci55529.2022.9837571","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/icicip.2015.7388205","name":"Dissipativity results for memristor-based recurrent neural networks with mixed delays","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icicip.2015.7388205","authors":["Kai Zhong","Song Zhu","Qiqi Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-01-21T18:11:03Z","doi":"10.1109/icicip.2015.7388205","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.compbiolchem.2026.109248","name":"Reconstructing the intestinal microbiota ecological network based on graph neural network and contrastive learning: Predicting key microbiota regulatory targets in Crohn’s Disease","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.compbiolchem.2026.109248","authors":["Huiyi Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-09T20:25:48Z","doi":"10.1016/j.compbiolchem.2026.109248","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1007/978-3-319-02630-5_7","name":"Synapse as a Memristor","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-02630-5_7","authors":["Weiran Cai","Ronald Tetzlaff"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-12-18T10:27:01Z","doi":"10.1007/978-3-319-02630-5_7","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1007/s00500-026-11382-z","name":"Structure-enhanced embedding for attributed network with graph neural network in context of transfer learning","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00500-026-11382-z","authors":["Phu Pham"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-25T11:19:07Z","doi":"10.1007/s00500-026-11382-z","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/edm69524.2026.11632205","name":"Multi-Scale Temporal Graph Neural Network with Stochastic Dynamics for Cloud and Industrial Network Intrusion Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/edm69524.2026.11632205","authors":["Roger Nick Anaedevha","Alexander Gennadievich Trofimov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-12T19:19:27Z","doi":"10.1109/edm69524.2026.11632205","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1088/0954-898x/9/4/008","name":"A recurrent neural network for modelling dynamical systems","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/9/4/008","authors":["Coryn Bailer-Jones","David MacKay","Philip Withers"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-24T22:35:54Z","doi":"10.1088/0954-898x/9/4/008","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.5267/j.ijdns.2025.9.014","name":"Determinants of smart government continuous use: A two-staged structural equation modeling-artificial neural network approach","source":"crossref","abstract":"This study aimed to develop and empirically validate an integrated model for continuous smart government service usage. This model integrates constructs from the unified theory of acceptance and use of the technology framework with the expectation-confirmation model, along with an additional construct: trust. Structural equation modeling (SEM) was used to analyze data collected via online questionnaires from 369 people who utilized smart government services in the United Arab Emirates. Next, an artificial neural networks model was used to rank the relative influence of the significant predictors identified through SEM analysis. The findings reveal that, among the significant predictors affecting the continuous use of smart government services, facilitating conditions, satisfaction, and perceived usefulness had the most substantial impact. Furthermore, this study highlights the direct influence of perceived usefulness, confirmation, facilitating conditions, effort expectancy, social influence, and public trust on citizen satisfaction.","url":"https://doi.org/10.5267/j.ijdns.2025.9.014","authors":["Nuseiba Altarawneh","Omar Hujran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-06T13:50:46Z","doi":"10.5267/j.ijdns.2025.9.014","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.engappai.2026.114278","name":"A sustainable medical waste supply chain network design under uncertainty using internet of things and convolution neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.engappai.2026.114278","authors":["Fatemeh Sogandi","Mahdyeh Shiri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-10T20:15:46Z","doi":"10.1016/j.engappai.2026.114278","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.23919/date51398.2021.9473989","name":"Efficient Identification of Critical Faults in Memristor Crossbars for Deep Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.23919/date51398.2021.9473989","authors":["Ching-Yuan Chen","Krishnendu Chakrabarty"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-08-24T22:11:46Z","doi":"10.23919/date51398.2021.9473989","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/ccdc.2017.7979335","name":"On memristor-based impulsive neural networks with time-delay","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ccdc.2017.7979335","authors":["Bin Hu","Zhi-Hong Guan","Zhi-Wei Liu","Xiao-Wei Jiang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-07-25T16:10:21Z","doi":"10.1109/ccdc.2017.7979335","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/access.2026.3714448","name":"gQINN: Gradient-Enhanced Queue-Informed Neural Network for Estimating Queueing Delay in an Aggregation Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/access.2026.3714448","authors":["Kyota Hattori","Tomohiro Korikawa","Chikako Takasaki"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-17T19:45:58Z","doi":"10.1109/access.2026.3714448","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1007/978-1-4842-4421-0_5","name":"Neural Network Development Using the Java Encog Framework","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4842-4421-0_5","authors":["Igor Livshin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-04-12T15:05:25Z","doi":"10.1007/978-1-4842-4421-0_5","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1007/978-3-319-02630-5_5","name":"Memristor, Hodgkin-Huxley, and Edge of Chaos","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-02630-5_5","authors":["Leon Chua"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-12-18T10:27:01Z","doi":"10.1007/978-3-319-02630-5_5","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.38007/nn.2022.030404","name":"Network Public Opinion Prediction Based on Improved Particle Swarm Optimization and BP Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2022.030404","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T06:22:51Z","doi":"10.38007/nn.2022.030404","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1007/978-981-92-0549-3_57","name":"FOPF Neural Network: A Flexible Neural Network Framework Addressing Renewable Energy Uncertainty","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-92-0549-3_57","authors":["Jianbo Nie","Hao Feng","Zhou Lan","Kun Wang","Chenlin Gu","Hanze Zhou","Kan Yang","Youbing Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-17T07:16:28Z","doi":"10.1007/978-981-92-0549-3_57","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.3390/fintech5030070","name":"Network-Aware FinTech Intelligence for ESG Risk Forecasting: A Graph Neural Network and Transformer-Based NLP Approach","source":"crossref","abstract":"Environmental, Social, and Governance (ESG) risks increasingly propagate across interconnected supply chains, yet conventional ESG assessment methods remain largely reliant on firm-level disclosures and static ESG ratings that often overlook indirect risk transmission among trading partners. This study develops a network-aware artificial intelligence (AI) framework for forecasting ESG risk by integrating Graph Neural Networks (GNNs), transformer-based natural language processing (NLP), explainable AI, and conventional machine-learning techniques. The proposed framework combines supply-chain network structures, shipment-level trade information, ESG controversy records, governance indicators, and transformer-derived ESG sentiment extracted using FinBERT and RoBERTa. Using a dataset of 11,386 firms across 27 industries from 2015 to 2025, the proposed GNN achieved the highest predictive performance, outperforming conventional machine-learning models with an ROC-AUC of 0.913. The results further demonstrate that supply-chain network centrality and transformer-derived ESG sentiment substantially improve the early identification of firms exposed to future ESG controversies. By integrating network relationships with textual ESG intelligence, the proposed framework advances FinTech-enabled ESG analytics and provides a scalable approach for proactive risk monitoring, sustainable investment decision-making, and supply-chain risk management.","url":"https://doi.org/10.3390/fintech5030070","authors":["Michael A. Aruwaji","Ferina Marimuthu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-10T09:24:53Z","doi":"10.3390/fintech5030070","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.38007/nn.2022.030305","name":"Image Content Segmentation Based on Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2022.030305","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T18:14:38Z","doi":"10.38007/nn.2022.030305","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.38007/nn.2020.010104","name":"Weather Recognition Algorithm based on Convolution Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2020.010104","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T03:35:42Z","doi":"10.38007/nn.2020.010104","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.fuel.2025.137279","name":"Decoding the complex reaction network of nitromethane combustion via neural network potential molecular dynamics simulation","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.fuel.2025.137279","authors":["Wen-Ya Ma","Zheng-Hua He","Bo Wen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-23T16:56:46Z","doi":"10.1016/j.fuel.2025.137279","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.3389/fphar.2026.1686243","name":"Analysis of the interaction network relationship between drugs using a graph neural network","source":"crossref","abstract":"Introduction The ever-increasing complexity of biochemical systems, alongside the rapid growth of pharmaceutical and biomedical data, underscores the urgent need for intelligent, scalable, and interpretable computational models. These models must be capable of supporting next-generation decision-support systems and driving knowledge discovery in the realm of computational science. Traditional approaches to relational biomedical modeling, however, often struggle to accurately capture intricate multi-relational dependencies and typically lack robustness in sparse or incomplete interaction domains. To address these pressing limitations, we present a novel, biologically grounded graph-based learning framework designed to overcome such challenges. Methods Our approach comprises a two-tiered system: PHARMNet, a multi-relational graph neural network (GNN) equipped with memory-augmented attention mechanisms, and INTERACT-SCOPE, an advanced, context-aware optimization strategy that leverages structured biomedical ontologies and domain knowledge. PHARMNet employs relation-specific graph convolutions and semantic embedding alignment to effectively model latent relational dependencies in biochemical and pharmacological datasets. In parallel, INTERACT-SCOPE improves predictive generalization and stability by incorporating ontology-guided constraints, estimating epistemic uncertainty, and applying adaptive graph regularization techniques tailored to biomedical structures. Results and Discussion Through rigorous experimental evaluations across a variety of pharmacological interaction categories, our framework consistently achieves state-of-the-art (SOTA) predictive performance, enhanced model interpretability, and notable robustness—especially in low-data or high-noise scenarios. These outcomes strongly align with the journal’s mission to promote innovative and knowledge-driven advances in software engineering, artificial intelligence, and biomedical informatics. Ultimately, our article illustrates the synergistic integration of computational intelligence, domain-informed graph representation learning, and scalable modeling, contributing a powerful and interpretable solution to real-world challenges in healthcare informatics and biomedical discovery. Experimental results demonstrate that MGTNSyn outperforms existing methods, achieving an AUC of 0.873 and an F1-score of 0.831 on drug–drug interaction (DDI) benchmark datasets.","url":"https://doi.org/10.3389/fphar.2026.1686243","authors":["Zhongyi Chai","Jing Wang","Huili Du"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-11T22:10:25Z","doi":"10.3389/fphar.2026.1686243","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.56726/irjmets99277","name":"Real Time Language Translation App using Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.56726/irjmets99277","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-27T14:48:51Z","doi":"10.56726/irjmets99277","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.71052/srb2024/jsyp7766","name":"DCDTI: Dual-Channel Neural Network for Drug-Target Interaction Prediction","source":"crossref","abstract":"Background: The computational identification of drug-target interaction (DTI) is pivotal in drug discovery and chemical genomics. Current network-based approaches model DTI as a link prediction problem utilizing bipartite graphs. However, simplistic representations fail to encapsulate crucial biological semantic information, and how to effectively integrate molecular structure features with graph neural networks has emerged as a non-negligible challenge in the DTI domain. Results: To address these issues, we propose a Dual-Channel Neural Network for Drug-Target Interaction (DCDTI) prediction model based on GLTransformer, aiming to learn high-quality representations of the topological structures of drugs and targets with precision. Extensive experiments validate that DCDTI surpasses state-of-the-art methods. Case studies have further confirmed its generalization ability in actual DTI scenarios. Conclusion: DCDTI provides a powerful method for DTI prediction, which can also serve as a screening tool for studies of drug discovery.","url":"https://doi.org/10.71052/srb2024/jsyp7766","authors":["Ping Zhang","Yongbin Zeng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-01T07:14:56Z","doi":"10.71052/srb2024/jsyp7766","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/icscan66520.2026.11588442","name":"Oral Cancer Prediction Using Metaheuristic Optimized Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icscan66520.2026.11588442","authors":["R. Sathishkumar","Vijayalakshmi R","I. Govindharaj"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-07T19:42:48Z","doi":"10.1109/icscan66520.2026.11588442","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/tnnls.2020.2985860","name":"Bipartite Synchronization of Multiple Memristor-Based Neural Networks With Antagonistic Interactions","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnnls.2020.2985860","authors":["Ning Li","Wei Xing Zheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-04-23T19:54:14Z","doi":"10.1109/tnnls.2020.2985860","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/icist49303.2020.9202035","name":"Synchronization of Memristor-Based Coupled Neural Networks with Delay via Intermittent Coupling","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icist49303.2020.9202035","authors":["Jiejie Chen","Boshan Chen","Zhigang Zeng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-09-23T00:19:28Z","doi":"10.1109/icist49303.2020.9202035","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1088/1674-1056/ae1dec","name":"Dynamic analysis and DNA coding-based image encryption of memristor synapse-coupled hyperchaotic IN-HNN network","source":"crossref","abstract":"Abstract The rapid development of brain-like neural networks and secure data transmission technologies has placed greater demands on highly complex neural network systems and highly secure encryption methods. To this end, the paper proposes a novel high-dimensional memristor synapse-coupled hyperchaotic neural network by using the designed memristor as the synapse to connect an inertial neuron (IN) and a Hopfield neural network (HNN). By using numerical tools including bifurcation plots, phase plots, and basins of attraction, it is found that the dynamics of this system are closely related to the memristor coupling strength, self-connection synaptic weights, and inter-connection synaptic weights, and it can exhibit excellent hyperchaotic behaviors and coexisting multi-stable patterns. Through PSIM circuit simulations, the complex dynamics of the coupled IN-HNN system are verified. Furthermore, a DNA-encoded encryption algorithm is given, which utilizes generated hyperchaotic sequences to achieve encoding, operation, and decoding of DNA. The results show that this algorithm possesses strong robustness against statistical attacks, differential attacks, and noise interference, and can effectively resist known/selected plaintext attacks. This work will provide new ideas for the modeling of large-scale brain-like neural networks and high-security image encryption.","url":"https://doi.org/10.1088/1674-1056/ae1dec","authors":["Shuang 双 Zhao 赵","Yunzhen 云贞 Zhang 张","Xiangjun 湘军 Chen 陈","Bin 彬 Gao 高","Chengjie 成杰 Chen 陈"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-11T10:47:43Z","doi":"10.1088/1674-1056/ae1dec","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.5194/egusphere-egu26-20172","name":"Neural Network Modelling of Climate Change and Reservoir Impacts on Upper Miño River Flow","source":"crossref","abstract":"Climate change is altering the global hydrological cycle and, when combined with human interventions such as reservoir operations, the river flow regime is further modified. Given the strong spatial heterogeneity of these impacts and the basin-specific nature of hydrological responses, regional studies are essential to assess local vulnerabilities. This study investigates projected changes in streamflow in the upper Miño River basin (northwestern Iberian Peninsula), including the impact of the Belesar reservoir, by comparing historical conditions (1985–2014) with future projections (2070–2099) under the SSP5-8.5 and SSP2-4.5 scenarios. Artificial neural networks were employed to model basin hydrology by estimating streamflow from temperature and precipitation data, and to simulate reservoir operations, achieving satisfactory validation performance.Under the high-emission SSP5-8.5 scenario, results indicate a projected intensification of hydrological variability, with the 10th percentile, used to define low-flow conditions, decreasing by approximately 10%, whereas the percentile corresponding to a one-year return period (high-flow conditions) increases by about 5%, with the mean streamflow declining by more than 15%. Under the more moderate SSP2-4.5 scenario, changes are less pronounced, with a ~5% reduction in the low-flow percentile and a more moderate decrease in mean streamflow, while the high-flow percentile is expected to decrease by around 30 %, exhibiting an opposite trend to the extreme emission scenario. Reservoir operation was analysed under the SSP5-8.5 scenario to assess its regulatory capacity under future extreme conditions. Results show that reservoir management could mitigate projected impacts by redistributing water seasonally, more than doubling summer downstream flows compared to future natural conditions and reducing winter extremes, with peak flows lowered by approximately 15%. Overall, while future natural conditions are projected to become more critical, both moderate emission pathways and effective reservoir operation can substantially alleviate adverse hydrological impacts.","url":"https://doi.org/10.5194/egusphere-egu26-20172","authors":["Helena Barreiro-Fonta","Diego Fernández-Nóvoa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-14T04:55:57Z","doi":"10.5194/egusphere-egu26-20172","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/icassp55912.2026.11462755","name":"Graph Neural Network-Based Reinforcement Learning for Cooperative Network Localization","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icassp55912.2026.11462755","authors":["Jinze Wu","Zhi Li","Zhiyun Lin","Hui Cheng","Lorenzo Zino","Alessandro Rizzo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-21T21:24:02Z","doi":"10.1109/icassp55912.2026.11462755","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/iscas48785.2022.9937701","name":"Offset Rejection in a DC-Coupled Hybrid CMOS/Memristor Neural Front-End","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas48785.2022.9937701","authors":["Jiaqi Wang","Alexander Serb","Shiwei Wang","Themistoklis Prodromakis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-11T20:38:08Z","doi":"10.1109/iscas48785.2022.9937701","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/ijcnn.2014.6889506","name":"STDP learning rule based on memristor with STDP property","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2014.6889506","authors":["Ling Chen","Chuandong Li","Tingwen Huang","Xing He","Hai Li","Yiran Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-09-10T10:30:33Z","doi":"10.1109/ijcnn.2014.6889506","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.30919/faf2347","name":"Cuckoo Catfish Optimizer-Hybrid Convolutional Neural Network: A Hybrid Convolutional Neural Network with Cuckoo Catfish Optimizer for Non-Destructive Fruit Quality Grading in Precision Agriculture","source":"crossref","abstract":"","url":"https://doi.org/10.30919/faf2347","authors":["Govinda B. Sambare","Mahesh P. Wankhade","Geeta Navale","Snehlata Kapil Wankhade","Amar R. Buchade","Arati Deshpande","Dewanand Meshram","Baliram S. Gayal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-08T09:53:37Z","doi":"10.30919/faf2347","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/iciptm69057.2026.11465896","name":"AI-Powered Neural Network System for Real-Time Network Anomaly Detection in Cybersecurity","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iciptm69057.2026.11465896","authors":["Ashutosh Bhushan","Navleen Kaur","Monisha","Mini Srivastava","Smriti Sethi","Mehpreet Kaur"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-13T19:34:56Z","doi":"10.1109/iciptm69057.2026.11465896","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/icosaas68663.2026.11648733","name":"Graph Neural Network based Lateral Movement Detection in Enterprise Network Traffic","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icosaas68663.2026.11648733","authors":["Ouku Bhulakshmi","Nagari Kavya Sree","M. V. Subramanyam","Farooq Sunar Mahammad","Telagathoti Anusha","Kumar Devapogu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-14T19:36:42Z","doi":"10.1109/icosaas68663.2026.11648733","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.2139/ssrn.6642465","name":"Spectral Analysis Reveals Fundamental Differences between Human and Deep Neural Network Shape Representations","source":"crossref","abstract":"While the human visual system is known to be highly sensitive to global and configural shape information, deep neural networks models (DNNs) trained on ImageNet seem to favour local shape features.&amp;nbsp; However, a more exact understanding of these differences has remained elusive, in part due to a lack of systematic methods for exploring the nature of high-dimensional shape representations.&lt;br&gt;&lt;br&gt;Here we argue that a novel shape frequency analysis can provide important insights into these representations.&amp;nbsp; We explore this hypothesis through a series of experiments in which we measure human and DNN sensitivity across the shape frequency spectrum.&amp;nbsp; These experiments reveal systematic differences between human and DNN models in spectral tuning and sensitivity to the amplitude and phase of shape frequency components.&amp;nbsp; Using this frequency analysis approach, we also show that recent curriculum modifications claimed to create more human-like AI systems primarily act to attenuate sensitivity to higher shape frequencies rather than sharpening discriminative tuning to lower frequencies.&amp;nbsp;&amp;nbsp; Overall, we find that humans are tuned to much lower shape frequencies than DNN models, and as a consequence these models are unable to predict the majority of variance in human judgements of shape stimuli.","url":"https://doi.org/10.2139/ssrn.6642465","authors":["Nicholas Baker","John Wilder","James  H. Elder"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-27T23:50:08Z","doi":"10.2139/ssrn.6642465","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.2139/ssrn.6161526","name":"A Conformable Fractional Physics-Informed Neural Network for Real-Time 6G Signal Modeling in Dispersive Nanomaterials","source":"crossref","abstract":"The emergence of sixth-generation (6G) telecommunications at Terahertz (THz) frequencies necessitates advanced computational electromagnetic solvers capable of modeling anomalous dispersion in complex nanomaterials. Traditional grid-based methods, such as Finite-Difference Time-Domain (FDTD), are hindered by intensive mesh generation and stability constraints. This paper presents a novel meshfree soft computing framework: the Conformable Fractional Physics-Informed Neural Network (fPINN).&amp;nbsp; &lt;div&gt; By embedding Conformable Fractional Calculus (CFC) into the neural network's loss function, the fractional order α serves as a tunable dispersion index, enabling the capture of non-local memory effects and signal aging in graphene-based media without the computational overhead of traditional fractional operators. A dual-optimizer strategy (Adam and L-BFGS) achieves a high-precision convergence floor of O(10-6). The results demonstrate that the fPINN accurately simulates anomalous dispersion phenomena-including pulse broadening and peak attenuation-across fractional orders (α ∈ [0.1, 1.0]), effectively mitigating spectral bias in high-frequency regimes.&amp;nbsp; &lt;/div&gt; &lt;div&gt; Furthermore, the mesh-free, surrogate-model nature of the fPINN enables real-time field prediction with microsecond inference latency,&amp;nbsp;offering a transformative computational acceleration over classical numerical techniques. This synergy of physics-informed deep learning and localized fractional calculus provides a robust, scalable computational tool for real-time optimization in reconfigurable intelligent surfaces and digital twin implementations for next-generation wireless systems. &lt;/div&gt;","url":"https://doi.org/10.2139/ssrn.6161526","authors":["Basem Ajarmah","Iyad Odeh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-10T10:51:21Z","doi":"10.2139/ssrn.6161526","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.21203/rs.3.rs-10282772/v1","name":"A Physics-Informed Neural Network Frameworkfor Elastodynamic Wave Propagation inBimaterial Systems","source":"crossref","abstract":"Abstract Physics-informed neural networks (PINNs) provide a promising framework for solving partial differential equations while embedding the underlying physical laws directly into the learning process. This study presents a PINN-based framework for modeling transient elastodynamic wave propagation in bimaterial systems governed by the axisymmetric equations of linear elasticity. A steel-aluminum specimen representative of a Split Hopkinson Pressure Bar configuration is considered, and the governing elastodynamic equations, together with the corresponding initial, boundary, and interface conditions, are incorporated directly into the network through a physics-informed loss function. High-fidelity finite-element simulations performed using ANSYS Workbench Explicit Dynamics are used for validation and as supplementary data constraints during training. The proposed framework accurately predicts wave transmission and reflection across the bimaterial interface and reproduces axial and radial displacement histories, face-averaged responses, and the dominant stress and strain evolution with close agreement to the finite-element solutions. The trained network further demonstrates the ability to predict wave responses at previously unseen time instants and for modified material properties without requiring additional finite-element simulations, providing a continuous surrogate model for elastodynamic analysis. Mesh-sensitivity studies confirm numerical robustness, while additional material combinations demonstrate the generality of the proposed methodology. The results show that integrating physics-informed neural networks with explicit finite-element analysis provides an accurate and computationally efficient framework for elastodynamic wave propagation in heterogeneous solids, offering an effective surrogate modeling approach for high-rate solid mechanics and impact engineering applications.","url":"https://doi.org/10.21203/rs.3.rs-10282772/v1","authors":["Sonal Ankush Chibire","Jenn-Terng Gau","Bo Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-14T16:07:33Z","doi":"10.21203/rs.3.rs-10282772/v1","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/mpcon69668.2026.11508500","name":"Neural Network-Based Simulation Framework for Anthrax Disease Progression in Animal Populations","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mpcon69668.2026.11508500","authors":["Vikash Panthi","Nikita Kashyap","Manoj Gupta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-15T03:00:58Z","doi":"10.1109/mpcon69668.2026.11508500","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1109/codit70676.2026.11631093","name":"Evaluation of NAP-based approaches for monitoring Neural Network classifiers","source":"crossref","abstract":"","url":"https://doi.org/10.1109/codit70676.2026.11631093","authors":["Islem Touati","Abderraouf Boussif"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-07T19:16:20Z","doi":"10.1109/codit70676.2026.11631093","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1016/j.radmeas.2026.107759","name":"Radon concentration measurement method based on GRU neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.radmeas.2026.107759","authors":["Zhiqiang Ning","Jian Zhang","Qiguo Xiao","Zhiqiang Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-30T20:33:11Z","doi":"10.1016/j.radmeas.2026.107759","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1002/cem.70088","name":"In‐Situ Detection of Microplastic Particles on Food Using Hyperspectral Imaging With One‐Dimensional Convolutional Neural Network and Artificial Neural Network","source":"crossref","abstract":"ABSTRACT Hyperspectral imaging (HSI) has emerged as a promising technique for microplastic detection through analysis of reflectance variations across multiple wavelengths. Traditional approaches have focused primarily on isolated microplastic particles, requiring labor‐intensive separation procedures impractical for routine monitoring. The challenge of detecting microplastics directly on food surfaces stems from spectral similarities between microplastics and food matrices, making differentiation difficult using conventional methods. Leveraging recent advances in machine learning, this study explores how artificial neural networks (ANN) and one‐dimensional convolutional neural networks (1D‐CNN) can identify subtle spectral differences to detect microplastic particles on seafood without isolation. We systematically evaluated model architectures, preprocessing techniques, and hyperparameter configurations to optimize detection performance using hyperspectral data from tilapia samples contaminated with polyethylene microspheres. Our findings demonstrate that 1D‐CNN models trained on hyperspectral data without dimensionality reduction significantly outperform other approaches, achieving object‐level detection F1 scores of 0.963 for 600‐μm particles and 0.950 for 300‐μm particles. This detection strategy represents a substantial improvement over traditional methods and highlights the potential of deep learning–based approaches for non‐destructive, efficient microplastic detection in food safety applications.","url":"https://doi.org/10.1002/cem.70088","authors":["Nikhita Sai Nayani","Ran Yang","Yue Sun","Lihong Yang","Lifeng Zhou","Yiming Feng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-22T07:02:28Z","doi":"10.1002/cem.70088","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1088/0954-898x/2/1/004","name":"Recognition and categorization in a structured neural network with attractor dynamics","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/2/1/004","authors":["C Fassnacht","A Zippelius"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-24T22:35:54Z","doi":"10.1088/0954-898x/2/1/004","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:34.685Z"},{"id":"doi:10.1088/0954-898x/5/4/010","name":"Self-organization in complex pattern spaces using a logic neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/5/4/010","authors":["G Tambouratzis","D Tambouratzis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/5/4/010","addedAt":"2026-09-01T01:48:34.685Z","updatedAt":"2026-09-01T01:48:35.256Z"},{"id":"doi:10.1002/adma.202518105","name":"Humidity-Gated Memristive Dynamics Enabling Near-Sensor Spiking Computation for Wind Direction and Noise-Resilient Speech Recognition.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202518105","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202518105","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1038/s41598-026-36824-4","name":"A novel hybrid medical image encryption scheme based on memristive chaos and DNA-ARX-3DES with Real-Time implementation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-36824-4","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-36824-4","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1093/nsr/nwag317","name":"Self-powered intelligence for personalized healthcare.","source":"europepmc","abstract":"","url":"https://doi.org/10.1093/nsr/nwag317","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1093/nsr/nwag317","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/adma.202512238","name":"2D Vanadium Carbide/Oxide Heterostructure-Based Artificial Sensory Neuron for Multi-Color Near-Infrared Object Recognition.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202512238","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202512238","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1038/s41467-025-68227-w","name":"Compute-in-memory implementation of state space models for event sequence processing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-68227-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-025-68227-w","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/adma.202520288","name":"Room-Temperature Skyrmionic Synapse in 2D Ferromagnet Fe&lt;sub&gt;3&lt;/sub&gt;GaTe&lt;sub&gt;2&lt;/sub&gt; Operating via Collective Spin Texture Transformation.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202520288","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202520288","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/adma.202511352","name":"Zn&lt;sup&gt;2+&lt;/sup&gt; Engineered Low-Barrier LiNbO&lt;sub&gt;3&lt;/sub&gt; Enables Visible-Light Programmable Ferroelectric Memristors for Noise-Immune Neuromorphic Vision.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202511352","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202511352","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/adma.202514099","name":"Vertical Self-Rectifying Memristive Arrays for Page-Wise Parallel Logic and Arithmetic Processing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202514099","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/adma.202514099","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1038/s41598-026-50931-2","name":"Performance evaluation of green building in the process of rural revitalization driven by Artificial Intelligence and BP neural network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-50931-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-50931-2","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1038/s41467-026-71907-w","name":"Temporal-Spatial Fusion Vision Hardware Enables Streamlined In-Sensor Computing for Dynamic Scenes.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-71907-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-71907-w","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1038/s41598-026-35671-7","name":"Memristance and transmemristance in multiterminal memristive systems.","source":"europepmc","abstract":"Memristive devices represent promising building blocks for the development of next-generation memory technologies, computing architectures, and neuromorphic systems. In addition to conventional two-terminal memristive circuits and crossbar array structures, multiterminal memristive systems, where emergent behaviours arise from the mutual interaction of numerous memristive elements, have been explored for neuromorphic data processing and computing applications. In this work, we extend the concept of two-terminal memristive devices to generic multiterminal memristive systems. Beyond its ability to describe the specific case of crossbar arrays, the proposed theoretical framework is also applicable to more complex systems such as self-organizing memristive networks, whose internal state dynamics depend not only on time-varying input signals but also on the spatial distribution of the stimulated terminals. After discussing the notion of memristance in multiterminal devices as the evolution of the system “seen” from the stimulating terminals, we demonstrate that the two-terminal memristive framework can be generalized to the concept of transmemristance when additional, non-stimulating electrodes are used to monitor the system’s evolution. Providing a connection between circuit theory and network science, these concepts are investigated both analytically and experimentally using a theoretical memristive graph model and an experimental memristive system based on self-organizing nanowire networks.","url":"https://doi.org/10.1038/s41598-026-35671-7","authors":["Gianluca Milano","Davide Pilati","Fabio Michieletti","Alessandro Cultrera","Carlo Ricciardi","E. Miranda"],"tags":["Memristor","Neuromorphic engineering","Computer science","Crossbar switch","Electronic circuit"],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-35671-7","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"doi:10.1038/s41598-026-38265-5","name":"Leveraging haze-aware features for improved image clarity and detection accuracy with an optimized DCNN-YOLOv8 network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-38265-5","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-38265-5","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/advs.202523273","name":"Memristive Baffle Systems: Design, Simulation, and Applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202523273","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.202523273","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1038/s41467-025-67316-0","name":"Bioinspired flexible sensing-processing-visualizing integrated system towards tactile-visual signal recognition.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-67316-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-025-67316-0","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1038/s41598-026-49801-8","name":"Bearing fault diagnosis based on multi-branch enhanced GhostNet with adaptive focal loss.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-49801-8","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-49801-8","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.3390/e28030260","name":"Analysis and Application of a 3D Chaotic System with Flexible Offset and Frequency Control.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/e28030260","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3390/e28030260","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1038/s41598-026-44949-9","name":"Influence of programming-pulse properties on weight-update characteristics of charge-trapping IGZO synaptic transistors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-44949-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-44949-9","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1038/s41598-026-58982-1","name":"Hyperchaotic fractional-order image encryption with Knight's tour scrambling for satellite imagery.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-58982-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-58982-1","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/advs.202517077","name":"Giant Switchable Remanent Polarization and Photocurrent in Ferroelectric Thin Film Photomemristor for In Situ Training.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202517077","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.202517077","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1155/joph/8857887","name":"Diabetic Retinopathy Detection: AI Models and Approaches.","source":"europepmc","abstract":"","url":"https://doi.org/10.1155/joph/8857887","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1155/joph/8857887","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/advs.202515893","name":"Artificial Neuron Based on Electrical Anisotropy from WSe&lt;sub&gt;2&lt;/sub&gt; Field Effect Transistors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202515893","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.202515893","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.1038/s41598-026-40614-3","name":"AI-based intelligent sensing detection of cybersecurity threats using multimodal sensor data in smart devices.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-40614-3","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-40614-3","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.1021/acsaelm.5c02633","name":"Structure-Function Coupling in Pyridyl Triazole Copolymers for Neuromorphic Synaptic Transistors.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsaelm.5c02633","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acsaelm.5c02633","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.1038/s41378-026-01287-0","name":"Implementation of reservoir computing using coupled microelectromechanical drum resonators via sideband-pumped phonon-cavity dynamics.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41378-026-01287-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41378-026-01287-0","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.1002/advs.202524248","name":"Multi-Physical Field Modulated P-Bit Device Based on VO&lt;sub&gt;2&lt;/sub&gt; Thin Film.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202524248","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.202524248","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.1002/advs.202517994","name":"Tunneling-Controlled Fusion of Short- and Long-Term Memory in SiO&lt;sub&gt;2&lt;/sub&gt;/HfO&lt;sub&gt;2&lt;/sub&gt;-Based Neuromorphic Device for Time-Series Prediction.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202517994","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.202517994","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.1021/acs.nanolett.5c06450","name":"Atomistic Origin of RTN-like Centers Created and Annihilated by RRAM Write Processes.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acs.nanolett.5c06450","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1021/acs.nanolett.5c06450","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.1093/nar/gkag337","name":"On the molecular basis of enduring memory in neurons, and cell fate in fibroblasts.","source":"europepmc","abstract":"Memories can last a lifetime, and how this is achieved remains an unanswered challenge. Most current thinking sees molecular traces of memories (engrams) as sets of synaptic proteins facilitating neuronal co-firing and co-wiring. However, most proteins turn over in months or less. Another challenge is how fibroblasts remember their cell fate for decades, and an emerging model sees functionally related genes co-firing in clusters (called transcription factories and condensates) that make RNAs specifying cell fate. As clustering is driven by entropic forces acting throughout time, the first cells may have possessed this memory system, and Nature could have exploited it to store engrams when nervous systems evolved. Then, transcription creates the naïve neuronal substrate and defines which cells are included in co-wiring and co-firing circuits, before progressive cell differentiation consolidates long-term memories. I speculate that transcription plays another central role. For every nucleotide added to a nascent RNA, transcription generates a pyrophosphate-a chelating agent that sequesters the calcium ions that can modify action-potential spike-trains. In other words, the same nano-wired DNA computer that specifies cell fate could store and manipulate our memories.","url":"https://doi.org/10.1093/nar/gkag337","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1093/nar/gkag337","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.1002/advs.202520795","name":"Non-Volatile Phase Modulation with Ultralow Energy Consumption Enabled by 2D Ferroelectric/TMD Heterostructures.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/advs.202520795","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1002/advs.202520795","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.1038/s41598-026-49290-9","name":"LSTM-driven chaotic keystream generator for robust medical image encryption.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-026-49290-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41598-026-49290-9","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.1038/s41467-026-68452-x","name":"Single-shot matrix-matrix photonic processor based on spatial-spectral hypermultiplexed parallel diffraction.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-026-68452-x","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.1038/s41467-026-68452-x","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.3389/fnhum.2026.1783138","name":"Self-referential processing as the biological switch between classical and quantum functioning of the brain.","source":"europepmc","abstract":"","url":"https://doi.org/10.3389/fnhum.2026.1783138","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2026","doi":"10.3389/fnhum.2026.1783138","addedAt":"2026-09-01T01:48:34.686Z","updatedAt":"2026-09-01T01:48:35.258Z"},{"id":"doi:10.1088/0954-898x_1_1_003","name":"The effectiveness of analogue ‘neural network’ hardware","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_1_1_003","authors":["J J Hopfield"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T16:03:59Z","doi":"10.1088/0954-898x_1_1_003","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1088/1402-4896/adca65","name":"A four-dimensional memristor-coupled neural network chaotic dynamical system based on multi-level logic pulse stimulation","source":"crossref","abstract":"Abstract In this paper, we propose a chaotic dynamics system based on a three-neuron cosine magnetically controlled memristor synapse-coupled Hopfield neural network. The system consists of a line equilibrium set composed of an infinite number of points, these points in the equilibrium set are dictated by the coupling strength, and when the coupling strength reaches 3, the line equilibrium set is composed of an infinite number of stability points and the index-2 saddle-foci. Numerical analysis of the bifurcation diagram, Lyapunov exponents and phase plots, reveals that there are attractors with different orbits in the system with the change in coupling strength. Moreover, after multilevel-logic pulse is added, the neural network has the capability to generate and control intricate multi-scroll attractors according to different system parameter values. The analog circuit of the four-dimensional magnetically controlled memristor synapse-coupled Hopfield neural network was designed, and the correctness of the numerical simulation was verified via PSIM circuit simulation software.","url":"https://doi.org/10.1088/1402-4896/adca65","authors":["Manhong Fan","Shiqi Xu","Qingsong Liu","Qian Xiao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-04-08T22:51:21Z","doi":"10.1088/1402-4896/adca65","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1109/access.2021.3122973","name":"Memristor-Based Neural Network Circuit of Delay and Simultaneous Conditioning","source":"crossref","abstract":"","url":"https://doi.org/10.1109/access.2021.3122973","authors":["Xinyu Xu","Weilin Xu","Baolin Wei","Fangrong Hu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-10-27T19:43:32Z","doi":"10.1109/access.2021.3122973","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1016/j.vlsi.2024.102203","name":"A logic device based on memristor-diode crossbar and CMOS periphery as spike router for hardware neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.vlsi.2024.102203","authors":["A.N. Busygin","S. Yu Udovichenko","A.D. Pisarev","A.H.A. Ebrahim","A.A. Gubin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-08T03:26:27Z","doi":"10.1016/j.vlsi.2024.102203","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-408446/v1","name":"Automatic road sign detection and recognition based on neural network","source":"crossref","abstract":"Abstract Road sign detection and recognition is an integral part of intelligent transportation sys-tems (ITS). It increases protection by reminding the driver of the current condition of the route, such as notices, bans, limitations and other valuable driving information. This paper describes a novel system for automatic detection and recognition of road signs, which is achieved in two main steps. First, the initial image is pre-processed using DBSCAN clustering algorithm. The clustering is performed based on color information, and the generated clusters are segmented using Artificial neural networks (ANN) classifier. The resulting ROIs are then carried out based on their aspect ratio and size to retain only significant ones. Then, a shape-based classification is performed using ANN as classifier and HDSO as feature to detect the circular, rectangular and triangular shapes. Second, a hybrid feature is defined to recognize the ROIs detected from the first step. It involves a combination of the so-called GLBP-Color which is an extension of the classical gradient local binary patterns (GLPB) feature to the RGB color space and the local self-similarity (LSS) feature. ANN, Adaboost and support vector machine (SVM) have been tested with the introduced hybrid feature and the first one is selected as it outperforms the other two. The proposed method has been tested in outdoor scenes, using a collection of common databasets, well known in the traffic sign community (GTSRB, GTSDB and STS). The results demonstrate the effectiveness of our method when compared to recent state-of-the-art methods.","url":"https://doi.org/10.21203/rs.3.rs-408446/v1","authors":["Redouan Lahmyed","Mohamed El Ansari","Zakaria Kerkaou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-06-04T23:04:09Z","doi":"10.21203/rs.3.rs-408446/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.32388/zrlgu9","name":"Review of: \"Synthetic Data Generation of Body Motion Data by Neural Gas Network for Emotion Recognition\"","source":"crossref","abstract":"","url":"https://doi.org/10.32388/zrlgu9","authors":["Muhammad Naveed Riaz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-02T15:39:32Z","doi":"10.32388/zrlgu9","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1109/tgrs.2025.3567422/v2/review3","name":"Review for \"SVIFNN: Robust Inpainting Fourier Neural Network for SST Scientific Visualization Image Leveraging Significant Stability and Nonsignificant Anomalies\"","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tgrs.2025.3567422/v2/review3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-21T22:53:22Z","doi":"10.1109/tgrs.2025.3567422/v2/review3","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.7554/elife.89131.1.sa2","name":"Reviewer #1 (Public Review): When and why does motor preparation arise in recurrent neural network models of motor control?","source":"crossref","abstract":"","url":"https://doi.org/10.7554/elife.89131.1.sa2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-08-10T15:39:42Z","doi":"10.7554/elife.89131.1.sa2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.7554/elife.89131.2.sa1","name":"Reviewer #2 (Public Review): When and why does motor preparation arise in recurrent neural network models of motor control?","source":"crossref","abstract":"","url":"https://doi.org/10.7554/elife.89131.2.sa1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-20T13:26:22Z","doi":"10.7554/elife.89131.2.sa1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-10361693/v1","name":"A physics-guided graph neural network for interpretable multiscale modelling of concrete properties","source":"crossref","abstract":"Abstract Hierarchical materials derive macroscopic performance from interactions among phases and interfaces, yet most machine-learning models represent concrete as a flat mixture vector. Here we develop HiCon-GNN, a physics-guided graph neural network that mirrors the paste–mortar–interfacial transition zone (ITZ)–concrete hierarchy using coupled mortar- and concrete-scale proxy graphs. Mask-aware encoders retain incomplete literature records, while soft priors impose binder composition, weak-interface and cross-property consistency. Trained on 13,170 records, HiCon-GNN jointly predicts compressive, tensile and flexural strength with held-out R 2 values of 0.953, 0.887 and 0.926 and RMSEs of 10.69, 2.00 and 3.20 MPa, respectively. It reduces RMSE relative to a matched tabular neural network by 19%, 5% and 16%, while remaining close to the best target-specific ensemble models and stable across repeated random partitions. The learned latent states recover the expected paste–mortar–concrete strength hierarchy, matrix densification and porous, weak-ITZ behaviour. Capacity decomposition identifies mortar strength as the dominant reference scale and separates interface-controlled reduction from mesoscale matrix and topology effects. The latent quantities are physically regularised hypotheses, while they expose testable multiscale pathways unavailable to structure-blind models. HiCon-GNN therefore combines competitive multi-property prediction with a physically inspectable representation for data-driven concrete design.","url":"https://doi.org/10.21203/rs.3.rs-10361693/v1","authors":["Ye Li","Fangying Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-22T03:16:32Z","doi":"10.21203/rs.3.rs-10361693/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1007/978-981-16-1354-8_27","name":"Memristor-Based Neural Network Circuit of Associative Memory with Multimodal Synergy","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-16-1354-8_27","authors":["Juntao Han","Xiao Xiao","Xiangwei Chen","Junwei Sun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-31T08:02:49Z","doi":"10.1007/978-981-16-1354-8_27","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1016/j.vlsi.2026.102731","name":"A dual-neuron second-order memristor-based Hopfield neural network with controllable extreme multistability and its application in image encryption","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.vlsi.2026.102731","authors":["Yan Wang","Kangdi Yin","Jie Jin","Hongyan Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-27T08:08:24Z","doi":"10.1016/j.vlsi.2026.102731","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-9440511/v1","name":"Artificial Neural Network: A tool for Rapid Quantitative Elemental Analysis Using Neutron Activation Analysis","source":"crossref","abstract":"Abstract This paper presents a methodology for rapid quantitative elemental analysis using Neutron Activation Analysis (NAA) coupled with an Artificial Neural Network (ANN). A three-layer feed-forward ANN with back-propagation algorithm was developed to determine concentrations of long-lived activation products (Co, Cs, Eu, Fe, Hf, Sb, Sc, Ta, Tb, Ce) relevant to nuclear reactor shielding decommissioning. The methodology is demonstrated using simulated gamma-ray spectral data generated from the activation equation based on typical cement composition ranges reported in literature. The optimized ANN architecture (4 input neurons; 1 hidden layer with 4 neurons using tanh activation; 1 output neuron) achieved a correlation coefficient of 0.991 between input features and predicted concentrations. Mean relative errors ranged from 3.2% to 6.2% across all elements. The proposed method eliminates the need for matched elemental standards and reduces analysis time by approximately 80% compared to conventional relative NAA. This methodology provides a foundation for rapid, multi-element analysis in nuclear decommissioning applications, with experimental validation planned for future work.","url":"https://doi.org/10.21203/rs.3.rs-9440511/v1","authors":["M. E. Medhat"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-30T04:05:20Z","doi":"10.21203/rs.3.rs-9440511/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1039/d5dd00367a/v1/review1","name":"Review for \"&lt;b&gt;SynCat&lt;/b&gt; : Molecule-Level Attention Graph Neural Network for Precise Reaction Classification\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5dd00367a/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-06T21:07:36Z","doi":"10.1039/d5dd00367a/v1/review1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.7554/elife.89131.3.sa2","name":"Reviewer #2 (Public Review): When and why does motor preparation arise in recurrent neural network models of motor control?","source":"crossref","abstract":"","url":"https://doi.org/10.7554/elife.89131.3.sa2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-13T11:26:10Z","doi":"10.7554/elife.89131.3.sa2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1002/we.2763/v2/review2","name":"Review for \"Research on short‐term output power forecast model of wind farm based on neural network combination algorithm\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/we.2763/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-22T17:02:21Z","doi":"10.1002/we.2763/v2/review2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-780802/v1","name":"Atrial Fibrillation Detection Using Feedforward Neural Network","source":"crossref","abstract":"Abstract Atrial fibrillation is one of the most common arrhythmias in clinics, which has a great impact on people's physical and mental health. Electrocardiogram (ECG) based arrhythmia detection is widely used in early atrial fibrillation detection. However, ECG needs to be manually checked in clinical practice, which is time-consuming and labor-consuming. It is necessary to develop an automatic atrial fibrillation detection system. Recent research has demonstrated that deep learning technology can help to improve the performance of the automatic classification model of ECG signals. To this end, this work proposes effective deep learning based technology to automatically detect atrial fibrillation. First, novel preprocessing algorithms of wavelet transform and sliding window filtering (SWF) are introduced to reduce the noise of the ECG signal and to filter high-frequency components in the ECG signal, respectively. Then, a robust R-wave detection algorithm is developed, which achieves 99.22% detection sensitivity, 98.55% positive recognition rate, and 2.25% deviance on the MIT-BIH arrhythmia database. In addition, we propose a feedforward neural network (FNN) to detect atrial fibrillation based on ECG records. Experiments verified by a 10-fold cross-validation strategy show that the proposed model achieves competitive detection performance and can be applied to wearable detection devices. The proposed atrial fibrillation detection model achieves an accuracy of 84.00%, the detection sensitivity of 84.26%, the specificity of 93.23%, and the area under the receiver working curve of 89.40% on the mixed dataset composed of Challenge2017 database and MIT-BIH arrhythmia database.","url":"https://doi.org/10.21203/rs.3.rs-780802/v1","authors":["Yunfan Chen","Chong Zhang","Chengyu Liu","Yiming Wang","Xiangkui Wan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-15T21:43:30Z","doi":"10.21203/rs.3.rs-780802/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-6035148/v1","name":"Forecasting Gold Price using Hybrid Deep Neural Network LSTM-Autoencoder","source":"crossref","abstract":"Abstract Gold prices hold a significant place in the global economy as they reflect the economic health, which influences markets, investments, and currency values. Industries that rely on commodities, investors and decision-makers, need accurate forecasting gold prices. Existing models for gold price forecasting, struggle with overfitting, poor adaptability and difficulty in handling volatile or long term trend changes. For this research, various deep learning models were evaluated, which includes Long Short-Term Memory, Convolutional Neural Networks, hybrid LSTM-CNN. The proposed hybrid model of LSTM-Autoencoders, to predict the gold prices for the data taken from September 2000 to January 2024. We also examines the impact of external parameters such as US dollar price, silver price, and crude oil price on forecasting gold prices. Furthermore, a comparative analysis of these external parameters shows that, only gold prices as a prediction parameter yields the highest accuracy across various evaluation metrics. While the silver prices showed some association with the gold price prediction, crude oil had a comparatively low predictive value. Additionally the proposed LSTM-Autoencoders hybrid model has shown the highest accuracy outperforming the other models, while addressing the challenge of overfitting effectively. The results and findings from this study, aid in exploring the role of deep learning in financial time series domain, offering insights which contributes to financial analysts market strategist and economic forecasters.","url":"https://doi.org/10.21203/rs.3.rs-6035148/v1","authors":["Agampreet Saini","Rahul Kumar Singh","Puneet Sinha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-05-13T02:28:13Z","doi":"10.21203/rs.3.rs-6035148/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.7287/peerj-cs.895v0.1/reviews/2","name":"Peer Review #2 of \"A deep crowd density classification model for Hajj pilgrimage using fully convolutional neural network (v0.1)\"","source":"crossref","abstract":"","url":"https://doi.org/10.7287/peerj-cs.895v0.1/reviews/2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-30T02:30:37Z","doi":"10.7287/peerj-cs.895v0.1/reviews/2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-10274597/v1","name":"Repair Instead of Retraining: A Constraint-Guided Framework for Neural Network Repair","source":"crossref","abstract":"Abstract Deep neural networks remain vulnerable to adversarial perturbations and backdoor attacks, yet repairing a deployed model without full retraining must balance interpretability, behavioral fidelity, and computational cost. We present a constraint-guided---but not formally certified---framework that uses DeepSHAP to localize a sparse set of fault-relevant weights, collects symbolic path constraints from benign and adversarial executions through concolic testing, and searches for weight updates with Max-SMT. Candidate repairs are always evaluated on the original deployed model, so reported accuracy and attack success rate reflect actual runtime behavior rather than simplified analysis models. Rather than committing to a single fixed recipe, we characterize a configurable repair design space---including which weights to modify, how constraints are collected, and how candidates are ranked---and study it through more than 4{,}700 runs on six benchmarks. Repair success depends critically on jointly choosing the weight direction, the surrogate model used for constraint collection, and the simplification strength. For backdoor benchmarks, outgoing-weight repair with an activation-gated surrogate achieves near-complete backdoor removal on Fashion-MNIST and MNIST-BD (attack success rate from above 98\\% to below 8\\%). For adversarial benchmarks, bias-only repair substantially reduces misbehavior on MNIST-6 (100\\% to 5.81\\%) and ResNet18 (85.51\\% to 40.42\\%). CIFAR-10 and GTSRB remain challenging under single-layer repair, highlighting a tractability--fidelity trade-off. These results show that bias-direction repair is a critical and previously underexplored option for adversarial correction, discoverable only through systematic design-space exploration.","url":"https://doi.org/10.21203/rs.3.rs-10274597/v1","authors":["Ting Yu Liu","Fang Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-22T13:58:58Z","doi":"10.21203/rs.3.rs-10274597/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1007/springerreference_19704","name":"neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/springerreference_19704","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-08-01T14:24:22Z","doi":"10.1007/springerreference_19704","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1007/978-1-4842-7368-5_2","name":"Internal Mechanics of Neural Network Processing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4842-7368-5_2","authors":["Igor Livshin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-10-18T21:30:54Z","doi":"10.1007/978-1-4842-7368-5_2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1039/d6sc03899a/v2/review2","name":"Review for \"Incorporating Neural Network in the AMOEBA Polarizable Force Field for Ligand Field Effects of Cu 2+ Ion\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d6sc03899a/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-23T13:11:05Z","doi":"10.1039/d6sc03899a/v2/review2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-2767197/v1","name":"Effectiveness of Parallel Computer Data and Video English Course Based on Neural Network","source":"crossref","abstract":"Abstract With the expansion of the scale of deep learning network and the rapid increase of the number of network training parameters, the network training time is getting longer and longer. In deep learning, convolutional neural network reduces the number of some parameters through weight distribution, but the problems such as large number of parameters and long network training time still exist. This paper implements convolutional neural network in distributed environment, and proposes parallel computer data and time-based scheduling strategy to optimize distributed convolutional neural network. This paper also studies the effectiveness of video English curriculum. It is found that with the development of network technology, information technology is more and more widely used in the education industry, and students can realize distance autonomous learning. At present, the network teaching platform is diversified, with the functions of knowledge point learning, online examination and so on. Aiming at the problems existing in the video English course, the project response theory is introduced into the design and development of the platform system. Taking college users as the research object, this paper constructs a data model of College Students' learning behavior, provides all-round services for college students, and improves the effectiveness of video English teaching. At the same time, based on the project response theory, this paper analyzes the current situation of College Students' autonomous learning, so as to improve the efficiency of College Students' autonomous learning. Based on neural network, this paper makes an in-depth study on parallel computer data and video English course, hoping to bring some help to the improvement of College Students' English learning.","url":"https://doi.org/10.21203/rs.3.rs-2767197/v1","authors":["Min She","Fen Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-10T17:42:51Z","doi":"10.21203/rs.3.rs-2767197/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1002/brb3.2140/v1/review2","name":"Review for \"Temporal lobe epilepsy alters neural responses to human and avatar facial expressions in the face perception network\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/brb3.2140/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-05-07T17:23:49Z","doi":"10.1002/brb3.2140/v1/review2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1108/ilt-05-2024-0182/v2/review1","name":"Review for \"Instance segmentation of on-line wear debris using deep convolutional neural network with transfer learning\"","source":"crossref","abstract":"","url":"https://doi.org/10.1108/ilt-05-2024-0182/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-17T16:01:54Z","doi":"10.1108/ilt-05-2024-0182/v2/review1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.53555/m.v9i9.5842","name":"THE DEEP NEURAL NETWORK-A REVIEW","source":"crossref","abstract":"Deep neural networks are considered the backbone of artificial intelligence, we will present a review of an article about the importance of neural networks and their role in other sciences, their characteristic, networks architecture, types, mathematical definition of deep neural networks, as well as their applications.","url":"https://doi.org/10.53555/m.v9i9.5842","authors":["Eman Jawad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-23T07:45:52Z","doi":"10.53555/m.v9i9.5842","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.7554/elife.89131.2.sa2","name":"Reviewer #1 (Public Review): When and why does motor preparation arise in recurrent neural network models of motor control?","source":"crossref","abstract":"","url":"https://doi.org/10.7554/elife.89131.2.sa2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-05-20T13:26:22Z","doi":"10.7554/elife.89131.2.sa2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1098/rsos.230706/v1/review2","name":"Review for \"Fault diagnosis for wind turbines with graph neural network model based on one-shot learning\"","source":"crossref","abstract":"","url":"https://doi.org/10.1098/rsos.230706/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-06T17:06:12Z","doi":"10.1098/rsos.230706/v1/review2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-9872496/v2","name":"TrustFedKG-Health:  Explainability-Aware Personalized Federated Knowledge  Graph Neural Network  with Uncertainty-Guided Clinical Reasoning","source":"crossref","abstract":"Abstract During preliminary experiments with federated graph learning on MIMIC-IV, we observed a consistent failure mode: hospitals with large patient volumes systematically dominated model aggregation even when their EHR records contained substantially higher rates of missing lab values and inconsistent diagnostic coding. A hospital contributing 30% of training samples but with 18% missing lab values outweighed a smaller, well-curated site in every round of standard FedAvg training. This quality-blindness motivated the core design of TrustFedKG-Health. A second observation drove the knowledge graph component: patient similarity graphs constructed purely from feature statistics missed clinically established disease-drug-symptom co-occurrences-two patients sharing a metformin-T2DM-polyuria triple were treated as unrelated if their raw feature vectors differed. Addressing both problems simultaneously, without requiring hospitals to share patient data, defined the design space for this work. We present TrustFedKG-Health, a federated knowledge graph neural network for disease risk prediction. It addresses these failures through five components. First, XFedGAT, a quality-aware aggregation algorithm weighting hospitals by dataset quality, prediction confidence, and explanation stability. Second, a Medical Knowledge Graph (MKG) layer encoding UMLS disease-drug-symptom triples as additional graph edges. Third, Monte Carlo dropout for calibrated predictive uncertainty. Fourth, dual SHAP and GNNExplainer attribution. Fifth, Llama-2-7B clinical narrative generation. We evaluated on MIMIC-IV (52,723 ICU records, 4-hospital non-IID Dirichlet split) and UCI Heart Disease over 5 independent runs. On MIMIC-IV, TrustFedKG-Health achieves classification accuracy of 94.7 ± 0.6% and F1-score of 0.934 ± 0.008, outperforming all baselines including centralized GAT by 3.1% (p &lt; 0.01, paired t-test). LLM-generated explanations were evaluated with BLEU, ROUGE-L, and BERTScore against a set of 200 gold-standard narratives used as reference text during development (BLEU-4 = 0.421, BERTScore F1 = 0.847); these metrics serve as a proxy measure and a full clinical evaluation by independent physicians is planned as future work. Ablation studies confirm the independent contribution of each module, and a dedicated Threats to Validity section provides transparent assessment of generalizability. Statistical significance is confirmed for all key comparisons (p &lt; 0.05).","url":"https://doi.org/10.21203/rs.3.rs-9872496/v2","authors":["ARITRIK GHOSH"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-26T18:10:26Z","doi":"10.21203/rs.3.rs-9872496/v2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1088/1361-6528/ae645a/v1/review1","name":"Review for \"Understanding the volatile memristor via direct observation of surface diffusion-regulated Cu-based conductive filaments\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1361-6528/ae645a/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-25T21:02:46Z","doi":"10.1088/1361-6528/ae645a/v1/review1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1109/ickecs61492.2024.10617381","name":"Analysis of Memristor Neural Networks for fault Tolerant Computing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ickecs61492.2024.10617381","authors":["Bhagya","Sharana Basaveshweshwar G Hiremath","C N Vijayakumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-07T17:29:50Z","doi":"10.1109/ickecs61492.2024.10617381","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1016/j.neucom.2011.04.016","name":"Exponential synchronization of memristor-based recurrent neural networks with time delays","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2011.04.016","authors":["Ailong Wu","Zhigang Zeng","Xusheng Zhu","Jine Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-06-03T13:12:06Z","doi":"10.1016/j.neucom.2011.04.016","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1049/pbcs038e_ch2","name":"Memristor logic gates","source":"crossref","abstract":"","url":"https://doi.org/10.1049/pbcs038e_ch2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-24T08:06:28Z","doi":"10.1049/pbcs038e_ch2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.7287/peerj-cs.895v0.2/reviews/2","name":"Peer Review #2 of \"A deep crowd density classification model for Hajj pilgrimage using fully convolutional neural network (v0.2)\"","source":"crossref","abstract":"","url":"https://doi.org/10.7287/peerj-cs.895v0.2/reviews/2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-30T02:30:40Z","doi":"10.7287/peerj-cs.895v0.2/reviews/2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-2601995/v1","name":"Convolutional neural network classifier incorporating misclassification information","source":"crossref","abstract":"Abstract In this paper we introduce misclassification information for the improved training of convolutional neural network classifiers (CNNCs) for image recognition. We construct a additional autoencoder neural network, called tutor, that forces the CNNCs to learn the difference between the misclassified picture and the picture corresponding to the misclassified category. Making full use of the classification results to guide the CNNCs for purposeful learning is expected to improve the learning efficiency and classification performance. We integrate the proposed tutor into several state-of-the-art CNNCs architectures and demonstrate improvement in their recognition performance on CIFAR-10/100 and MNIST datasets. Our results suggest that making the most of misclassification information to guide the training of the model can lead to significant performance improvement.","url":"https://doi.org/10.21203/rs.3.rs-2601995/v1","authors":["Junying Hu","Rongrong Fei","Fang Du","Peiju Chang","Jiangshe Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-02T12:28:08Z","doi":"10.21203/rs.3.rs-2601995/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-2716283/v1","name":"Application of Interactive information system in College Personnel Management by using BP Neural Network Algorithm","source":"crossref","abstract":"Abstract The BP neural network algorithm has flexible modeling ability and data parallel processing ability. While processing data, it learns through self-learning and adaptive algorithms and associative functions. In the calculation mode of the bp neural network algorithm, the paper conducts forward conduction on the data signal, and conducts reverse conduction according to the obtained error value. The process of transferring the BP neural network algorithm content involved in the data from the input layer to the output layer under the data pattern formed by the forward guidance. And according to the analysis of BP neuron model data of three layers and above, the algorithm form of input layer and output layer is readjust, and the interval data is obtained and analyzed and summarized, so as to trigger the event research on the application of personnel management in colleges and universities. From the problem of university personnel management thoughts, to system flow numerical analysis as a starting point, starting from the present situation, the form of the personnel management of colleges and universities, this paper analyzed the characteristics of the personnel management at this stage, and the personnel management of colleges and universities ever form the difference, and according to the principle of summed up the characteristics of modern personnel management model, and analyzing the theory of knowledge, From the concept, logic and physical structure of data analysis and design, in the personnel management system of colleges and universities form an important direction of development.","url":"https://doi.org/10.21203/rs.3.rs-2716283/v1","authors":["Lou Minsheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-04-17T14:48:57Z","doi":"10.21203/rs.3.rs-2716283/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-7624030/v1","name":"Neural network smoothing of American options payoff with grid refinement strategies","source":"crossref","abstract":"Abstract For an American call or put option, at the expiry time, the value function is a ramp function, the Delta sensitivity is a Heaviside function and Gamma is a Dirac delta measure. In addition, the first derivative with respect to the early exercise boundary is singular and relates to Theta sensitivity at the free boundary. This research explores the possibility of whether deep learning can efficiently account for the payoff condition and learn these irregularities. To this end, we introduce a smoothed modular learning approximant (SMLA) that combines key expressions, and a regulator representing a smoothed terminal condition for the value function. The SMLA's derivatives at the terminal time correspond to smoothed Heaviside and Dirac delta functions. With appropriate grid refinement strategies, our neural network solver can predict the early exercise boundary and its derivative, value function, and Greeks. The predictive performance of SMLA is illustrated by examples, and accurate results are achieved even for extreme maturity time and volatility values","url":"https://doi.org/10.21203/rs.3.rs-7624030/v1","authors":["Chinonso Nwankwo","Tony Ware","Weizhong Dai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-17T03:17:57Z","doi":"10.21203/rs.3.rs-7624030/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-1340444/v1","name":"Artificial Neural Network Approach versus Analytical Solutions for Relativistic Polytropes","source":"crossref","abstract":"Abstract Over the last few decades, artificial neural networks (ANN) have played an important role in many areas of human activity and have found application in many branches of natural sciences. ANNs have been widely used to tackle problems related to linear and nonlinear differential equations, and numerous paradigms for ANN architecture have been employed. Based on ANN and the Taylor series, this research proposes a computational technique to solve difficulties connected to the Tolman-Oppenheimer-Volkoff equations (TOV) of the relativistic gas spheres. We used ANN to study two cases related to relativistic polytropes. The first is to simulate both the Emden and the relativistic functions, and the second is to predict the zeros of the Emden function and its corresponding relativistic functions. In its feed-forward back-propagation learning scheme, we used the ANN framework. The efficiency of the proposed algorithm is evaluated by running it through seven models concerning the polytropic indices-relativistic parameter pairs ( n = 0 , σ = 0.2), ( n = 0.5 , σ = 0.3), ( n = 1 , σ = 0.4), ( n = 1.5 , σ = 0.1), ( n = 2 , σ = 0.5), ( n = 2.5 , σ = 0.6), and ( n = 3 , σ = 0.7). The obtained solutions aided in the resolution improvement of relativistic polytropic gas sphere problems and the comparison between the analytical and the ANN solutions gives good agreement for the two cases under study.","url":"https://doi.org/10.21203/rs.3.rs-1340444/v1","authors":["Mohamed Nouh","Emad Abdel-Salam","Yosry Azzam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-06T15:09:50Z","doi":"10.21203/rs.3.rs-1340444/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1088/1361-6501/ae5dee/v1/review1","name":"Review for \"Neural Network-Based Inverse Design for Multi-Objective Performance Optimization of 70 kHz Ultrasonic Transducers\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1361-6501/ae5dee/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-11T21:11:18Z","doi":"10.1088/1361-6501/ae5dee/v1/review1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-7693532/v1","name":"Physics-informed Fourier Basis Neural Network for Fluid Mechanics","source":"crossref","abstract":"Abstract Conventional machine learning approaches struggle to capture periodic patterns and solve quasi-periodic boundary problems in fluid mechanics. This study proposes a physics-informed Fourier basis neural network (PIFBNN) that integrates adaptive Fourier series with physical constraints to address canonical partial differential equations. The architecture preserves Fourier series' natural mathematical compatibility with periodic phenomena while incorporating trainable parameters (angular frequencies and weight coefficients) that enhance basis function flexibility and nonlinear learning capacity. We evaluate the framework on six fundamental fluid dynamics benchmarks: two-dimensional cylinder wake flow, lid-driven cavity flow, Kovasznay flow, Helmholtz equation, Burgers equation, and Allen-Cahn equation. Results demonstrate PIFBNN's consistent superiority over standard physics-informed neural network (PINN) in accuracy. Through sparse data reconstruction experiments and adjusting the activation functions of neural networks and comparing , we further validate the dual advantages of Fourier basis neural network (FBNN) over conventional artificial neural network (ANN): inherent periodicity handling and reduced sensitivity to activation function selection. The FBNN architecture maintains robust performance across different activation functions, as verified through systematic comparisons with ANN and PINN baselines. These findings position PIFBNN as a promising computational framework for complex fluid dynamics problems.","url":"https://doi.org/10.21203/rs.3.rs-7693532/v1","authors":["Chao Wang","Shilong Li","Zelong Yuan","Chunyu Guo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-30T03:57:12Z","doi":"10.21203/rs.3.rs-7693532/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-3921220/v1","name":"Forecast of SO2 Air Contamination utilizing Artificial Neural Network: Sample of City Meerut","source":"crossref","abstract":"Abstract SO2 is among the air poisons that assume the best part in air contamination. In this study, using data from 2019 to 2023, estimates of how this contaminant was affecting human health and the environment were made using artificial neural networks, a well-liked learning method in use today. Information having a place with Meerut territory, where the center of industry is located, was acquired by the Air Observation Center of Uttar Pradesh Pollution Control Board (UPPCB), and modeling and optimization were completed in SPSS programming. The obtained SO2 estimation results were subjected to a multilayer perceptron analysis before being compared with the actual data. Furthermore, the SO2 value for the province of Meerut has been recorded to occasionally beyond the permissible level, particularly during periods of high production.","url":"https://doi.org/10.21203/rs.3.rs-3921220/v1","authors":["Lokesh kumar","Gaurav Kumar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-13T19:06:19Z","doi":"10.21203/rs.3.rs-3921220/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1109/tgrs.2025.3602030/v3/review1","name":"Review for \"Physics-Inspired Neural Network for Joint Inversion of Multialtitude 3-D Gravity and Vertical Gradient\"","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tgrs.2025.3602030/v3/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-21T22:59:05Z","doi":"10.1109/tgrs.2025.3602030/v3/review1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1098/rsos.230706/v1/review3","name":"Review for \"Fault diagnosis for wind turbines with graph neural network model based on one-shot learning\"","source":"crossref","abstract":"","url":"https://doi.org/10.1098/rsos.230706/v1/review3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-07-06T17:06:12Z","doi":"10.1098/rsos.230706/v1/review3","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.4018/978-1-6684-2408-7.ch077","name":"Convolutional Neural Network","source":"crossref","abstract":"Machine learning is the study of algorithms and models for computing systems to do tasks based on pattern identification and inference. When it is difficult or infeasible to develop an algorithm to do a particular task, machine learning algorithms can provide an output based on previous training data. A well-known machine learning model is deep learning. The most recent deep learning models are based on artificial neural networks (ANN). There exist several types of artificial neural networks including the feedforward neural network, the Kohonen self-organizing neural network, the recurrent neural network, the convolutional neural network, the modular neural network, among others. This article focuses on convolutional neural networks with a description of the model, the training and inference processes and its applicability. It will also give an overview of the most used CNN models and what to expect from the next generation of CNN models.","url":"https://doi.org/10.4018/978-1-6684-2408-7.ch077","authors":["Mário Pereira Véstias"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-17T11:47:50Z","doi":"10.4018/978-1-6684-2408-7.ch077","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-2220817/v1","name":"Automatic Detection of Pneumonia using Concatenated Convolutional Neural Network","source":"crossref","abstract":"Abstract Pneumonia is a life-threatening disease and early detection can save lives, many automated systems have contributed to the detection of this disease and currently deep learning models have become one of the most widely used models for building these systems. In this study, two deep learning models are combined: DenseNet169 and pre-activation ResNet models and used for automatic detection of pneumonia. DenseNet169 model is an extension of the ResNet model, while the second is a modified version the ResNet model, these models achieved good results in the field of medical imaging. Two methods are used to deal with the problem of unbalanced data: class weight, which enables to control the percentage of data to be used from the original data for each class of data, while the other method is resampling, in which modified images are produced with an equal distribution using data augmentation. The performance of the proposed model is evaluated using a balanced dataset consists of 5856 images. Achieved results were promising compared to several previous studies. The model achieved a precision value of 98%, an area under curve (AUC) based on ROC of 97%, and a loss value of 0.23.","url":"https://doi.org/10.21203/rs.3.rs-2220817/v1","authors":["Ahmad T. Al-Taani","Ishraq T. Al-Dagamseh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-07T19:28:31Z","doi":"10.21203/rs.3.rs-2220817/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1002/cjce.25416/v1/review1","name":"Review for \"Modelling a chemical plant using grey‐box models employing the support vector regression and artificial neural network\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/cjce.25416/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-24T17:09:51Z","doi":"10.1002/cjce.25416/v1/review1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-754775/v1","name":"An Optimal Approach for Heart Sound Classification Using Artificial Neural Network","source":"crossref","abstract":"Abstract Heart sound auscultation is one of the most widely used approaches for detecting cardiovascular disorders. Diagnosing abnormalities of heart sound using a stethoscope depends on the physician’s skill and judgement. Several studies have shown promising results in the automatic detection of cardiovascular disorders based on heart sound signals. However, the accuracy performance needs to be improved as automated heart sound classification aids in the early detection and prevention of the dangerous effects of cardiovascular problems. In this study, an optimal heart sound classification method based on machine learning technologies for cardiovascular disease prediction is performed. It consists of three steps: pre-processing that sets the 5 s duration of the Physionet Challenge 2016 datasets, feature extraction using mel-frequency cepstrum coefficients (MFCC), and classification using an artificial neural network (ANN) with one hidden layer that provides low parameter consumption. Ten-fold cross-validation was used to evaluate the performance of the proposed method. The best model obtained 94% accuracy and 93% AUC score, which were assessed using 1626 test datasets. Taken together, the results show that the proposed method obtained excellent classification results and provided low parameter consumption, thereby reducing computational time to facilitate a real-time implementation.","url":"https://doi.org/10.21203/rs.3.rs-754775/v1","authors":["Yunendah Nur Fu’adah","Ki Moo Lim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-07-30T15:48:14Z","doi":"10.21203/rs.3.rs-754775/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-852812/v1","name":"PIPxResNet: Penalty Induced Prototype-Based eXplainable Residual Neural Network for Heartbeat Classification","source":"crossref","abstract":"Abstract Early stage heartbeat classification using the electrocardiogram signals can prevent cardiovascular diseases that causes millions of deaths annually around the world. In the past, researchers have used deep neural networks to achieve significant performance for heartbeat classification but their black-box nature and prediction rationale limits real-world deployment. We propose a Penalty Induced Prototype based eXplainable Residual Neural Network (PIPxResNet) that addresses the black-box nature of deep neural networks. PIPxResNet encodes the temporal variations of heartbeats by employing pretrained residual neural network following the concept of task transfer learning. The algorithm further extracts prototypes that are most representative of the training dataset that explain model predictions to general physicians, making them clinically relevant. The prototypes of a particular class having close resemblance to other class prototypes are penalised and their contribution towards corresponding class is reduced. In addition, the classification performance is improved by synthesising regular and irregular heartbeats using a deep convolution conditional generative adversarial network. The proposed method can easily be adopted to other domains that requires explanations for the classification tasks. The PIPxResNet performs at par with existing state-of-the-art algorithms without compromising individual class performance when tested on four publicly available annotated datasets. The proposed model is capable to perform automated screening and provide medical attention by simulating a clinical decision support system for general physicians.","url":"https://doi.org/10.21203/rs.3.rs-852812/v1","authors":["Deepankar Nankani","Rashmi Dutta Baruah"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-08-30T16:59:49Z","doi":"10.21203/rs.3.rs-852812/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1002/eng2.12950/v2/review2","name":"Review for \"Fault detection and classification in overhead transmission lines through comprehensive feature extraction using temporal convolution neural network\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/eng2.12950/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-03T17:08:45Z","doi":"10.1002/eng2.12950/v2/review2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-772506/v1","name":"Graph Neural Network for Integrated Water Network Partitioning and Dynamic District Metered Areas","source":"crossref","abstract":"Abstract Water distribution systems (WDSs) are used to transmit and distribute water resources in cities. Water distribution networks (WDNs) are partitioned into district metered areas (DMAs) by water network partitioning (WNP), which can be used for leak control, pollution monitoring, and pressure optimization in WDS management. In order to overcome the limitations of optimal search range and the decrease of recovery ability caused by two-step WNP and fixed DMAs in previous studies, this study developed a new method combining a graph neural network to realize integrated WNP and dynamic DMAs to optimize WDS management and respond to emergencies. The proposed method was tested in a practical case study; the results showed that good hydraulic performance of the WDN was maintained and that dynamic DMAs demonstrated excellent stability in emergency situations, which proves the effectiveness of the method in WNP.","url":"https://doi.org/10.21203/rs.3.rs-772506/v1","authors":["KEZHEN RONG","Minglei Fu","JIAWEI CHEN","LEJIN ZHENG","JIANFENG ZHENG","ZAHER MUNDHER YASEEN"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-10-11T20:16:09Z","doi":"10.21203/rs.3.rs-772506/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-4171645/v1","name":"DCNN: A Novel Binary and Multi-Class Network Intrusion Detection Model via Deep Convolutional Neural Network","source":"crossref","abstract":"Abstract Network security has become imperative in the context of our interconnected networks and everyday communications. Recently, many deep learning models have been proposed to tackle the problem of predicting intrusions and malicious activities in interconnected systems. However, they solely focus on binary classification and lack reporting on individual class performance in case of multi-class classification. Therefore, the need for an efficient and accurate network intrusion detection system has reached a pivotal point. In this paper, we propose a novel intelligent detection system based on convolutional neural network, namely DCNN. The proposed model can be utilized to analyze and detect attacks and intrusions in intelligent network systems. The DCNN model is applied against two benchmark datasets and compared with state-of-the-art models. Experimental results show that the proposed model improved resilience to intrusions and malicious activities for binary as well as multi-class classification. Furthermore, our DCNN model outperforms similar intrusion detection systems in terms of positive predicted value, true positive rate, F1 measure, and accuracy. The scores obtained for binary and multi-class classifications on the CICIoT2023 dataset are 99.50% and 99.25%, respectively. Additionally, for the CICIDS-2017 dataset, DCNN attains a score of 99.96% for both binary and multi-class classifications.","url":"https://doi.org/10.21203/rs.3.rs-4171645/v1","authors":["Ahmed Shebl","Sayed Elsedimy","Amr Ismail","Ahmed Salama","Mostafa Herajy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-01T06:00:18Z","doi":"10.21203/rs.3.rs-4171645/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1036/1097-8542.449750","name":"Neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1036/1097-8542.449750","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-07-10T15:46:54Z","doi":"10.1036/1097-8542.449750","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-2508012/v1","name":"N-Net: A Convolutional Neural Network for Medical Image Segmentation","source":"crossref","abstract":"Abstract This paper presents a novel supervised convolutional neural network architecture, \"N-Net\", capable of effectively learning and generalizing from small amounts of medical images to perform accurate segmentation tasks. Our model utilizes an encoder-decoder structure with a residual downsampling mechanism and a custom convolutional block to capture and process image information at multiple resolutions in the encoder segment. We employ data augmentation techniques to enrich the training set, thus increasing our model's performance. While our architecture is versatile and applicable to various segmentation tasks, in this study, we demonstrate its capabilities specifically for polyp segmentation in colonoscopy images. We evaluate the performance of our method on several popular benchmark datasets for polyp segmentation, Kvasir-SEG, CVC-ClinicDB, CVC-ColonDB, and ETIS-LARIBPOLYPDB showing that it achieves state-of-the-art results in terms of mean Dice coefficient, Jaccard index, Precision, Recall, and Accuracy. Our approach demonstrates strong generalization capabilities, achieving excellent performance even with limited training data.","url":"https://doi.org/10.21203/rs.3.rs-2508012/v1","authors":["Razvan-Gabriel Dumitru","Darius Peteleaza","Catalin Craciun"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-30T17:03:30Z","doi":"10.21203/rs.3.rs-2508012/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-3397792/v1","name":"Developing the Optimal Hybrid Neural Network for Predicting the Factor of  Air Pollutants","source":"crossref","abstract":"Abstract Urban air pollution can be reduced via precise air pollutant forecasts.For that, the air quality index (AQI) quantifies air quality.In this manner, accurate and trustworthy air quality index (AQI) estimates are essential for preserving the natural environment and the general population's health. Using the backpropagation (BP) algorithm, this study describes a method for enhancing the performance of neural networks. Using a network optimized with natural swarm intelligence, a novel optimal-hybrid model approachto Nature Swarm Intelligence (NSI), predicting the Air Quality Index (AQI), is possible. This NSI comprises the optimization algorithms Dove Swarm optimization (DSA) and Bat Algorithm (BA), which aim to optimize the weight of the Backpropagation neural network (BPNN) to promote the air quality prediction. The constructed optimal-hybrid modelcaptured the characteristics of the AQI series and produced a more accurate AQI forecast according to exhaustive comparisons using a set of evaluation indicators. Experiments conducted verify the proposed modelis validfor application when attempting to forecast the AQI. This is because it receives a high RMSE, MAPE, Error Absolute total, and Accuracy value from the simulation. This is because the simulation results suggest that the network model could be a good option for actualization, which is why this is the case.","url":"https://doi.org/10.21203/rs.3.rs-3397792/v1","authors":["Neduncheliyan S","Priya Viswanathan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-02-12T05:56:12Z","doi":"10.21203/rs.3.rs-3397792/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-5290268/v1","name":"Segmenting ancient cemetery under forests using synthesized LiDAR-derived data and deep convolutional neural network","source":"crossref","abstract":"Abstract The investigation and identification of spatial distribution of archaeological remains is full of challenges in forested areas, deep learning (DL) methods and light-detection and ranging (LiDAR) make it possible to quickly and automatically identify remains under vegetation cover. This study applied a semantic segmentation model based on convolutional neural networks and LiDAR-derived data to segment an ancient cemetery in a forested area in Baling Mountain and Jishan Mountain in Jingzhou City, Hubei Province, China. We proposed to synthesize multiple LiDAR-derived data into three-channel and five-channel data and perform data augmentation. Moreover, the channel attention (CA) mechanism was used to improve the U-Net and TransUNet models. Finally, segmentation of cemeteries in two regions was implemented and model migration was applied to new geographic regions. The results indicated that it has higher precision using five-channel raster data synthesized with elevation (DEM), slope, hillshade, roughness, and curvature than one or three derived data synthesized raster data in the test dataset. For the U-Net model, the intersection over union (IoU), precision, and recall reached 0.885, 0.921, and 0.924, respectively, for the TransUNet model, the IoU, precision, and recall reached 0.901, 0.921, and 0.944, respectively, successfully segmenting the unknown region cemetery. In addition, the migration of the model also indicated that the model trained by synthesizing data has better portability. In conclusion, our results contribute to the current discussion on techniques for automatically extracting historical terrain features using the DL method and LiDAR-derived data, and can also provide useful guidance for identifying archaeological remains in vegetation covered areas.","url":"https://doi.org/10.21203/rs.3.rs-5290268/v1","authors":["Hong Yang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-11-06T18:05:20Z","doi":"10.21203/rs.3.rs-5290268/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1098/rsos.240042/v1/review2","name":"Review for \"Combining three-dimensional acoustic coring and a convolutional neural network to quantify species contributions to benthic ecosystems\"","source":"crossref","abstract":"","url":"https://doi.org/10.1098/rsos.240042/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-20T17:06:39Z","doi":"10.1098/rsos.240042/v1/review2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.32388/r2pjwz","name":"Review of: \"Automated detection of superficial fungal infections from microscopic images through a regional convolutional neural network\"","source":"crossref","abstract":"","url":"https://doi.org/10.32388/r2pjwz","authors":["Enes Ayan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-10-29T17:26:51Z","doi":"10.32388/r2pjwz","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.23919/chicc.2017.8027986","name":"Asymptotical synchronization of memristor-based neural networks with time-varying delays via adaptive control","source":"crossref","abstract":"","url":"https://doi.org/10.23919/chicc.2017.8027986","authors":["Yueheng Li","Zhanyu Yang","Zhe Dong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-09-29T19:54:00Z","doi":"10.23919/chicc.2017.8027986","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1039/d5dd00367a/v1/review2","name":"Review for \"&lt;b&gt;SynCat&lt;/b&gt; : Molecule-Level Attention Graph Neural Network for Precise Reaction Classification\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5dd00367a/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-06T21:07:36Z","doi":"10.1039/d5dd00367a/v1/review2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.7554/elife.89131.3.sa3","name":"Reviewer #1 (Public Review): When and why does motor preparation arise in recurrent neural network models of motor control?","source":"crossref","abstract":"","url":"https://doi.org/10.7554/elife.89131.3.sa3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-13T11:26:10Z","doi":"10.7554/elife.89131.3.sa3","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1111/ijfs.17298/v2/review2","name":"Review for \"Modelling thermal characteristics of cocoa butter using a feed‐forward artificial neural network based on multilayer perceptron\"","source":"crossref","abstract":"","url":"https://doi.org/10.1111/ijfs.17298/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-06-21T17:09:36Z","doi":"10.1111/ijfs.17298/v2/review2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-1064671/v1","name":"Convolutional Neural Network and Clustering-Based Codebook Design Method for Massive MIMO Systems","source":"crossref","abstract":"Abstract In this paper, we propose a convolutional neural network(CNN) and clustering based codebook design method. Specifically, we train two different CNN networks, i.e., CNN1 and CNN2, to compress the channel state information(CSI) matrices into the channel vectors and recover the channel vectors back into the CSI matrices, respectively. After that, the clustering algorithm clusters the output of CNN1, i.e., the channel vectors into several clusters and outputs a centroid for each cluster. The sum-distance between each centroid and the channel vectors in the corresponding cluster is the smallest, which can lead to the maximum sum-rate of massive MIMO codebook design. Then, the centroids are recovered into matrices by CNN2. The output of CNN2 is our proposed codebook for massive multiple-input multiple-output(MIMO) systems. In the simulation, we compare the performance of different clustering algorithms. We also compare the proposed codebook with the traditional Discrete Fourier Transform(DFT) codebook. Simulation results show the superiority of the proposed algorithm.","url":"https://doi.org/10.21203/rs.3.rs-1064671/v1","authors":["Jing Xing","Die Hu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-30T22:41:17Z","doi":"10.21203/rs.3.rs-1064671/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1140/epjs/s11734-022-00642-2","name":"ReLU-type memristor-based Hopfield neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1140/epjs/s11734-022-00642-2","authors":["Chengjie Chen","Fuhong Min"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-08-04T09:03:38Z","doi":"10.1140/epjs/s11734-022-00642-2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1109/ijcnn.2012.6252577","name":"Memristor-based synapse design and training scheme for neuromorphic computing architecture","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2012.6252577","authors":["Hui Wang","Hai Li","Robinson E. Pino"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-08-01T16:47:51Z","doi":"10.1109/ijcnn.2012.6252577","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1088/1361-6528/ae645a/v1/review2","name":"Review for \"Understanding the volatile memristor via direct observation of surface diffusion-regulated Cu-based conductive filaments\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1361-6528/ae645a/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-25T21:02:46Z","doi":"10.1088/1361-6528/ae645a/v1/review2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-3380046/v1","name":"Perception of Groundnuts Leaf Disease by Neural Network with Progressive Re-Sizing","source":"crossref","abstract":"Abstract India is the world's second-largest groundnut producer after Brazil. An major crop of oilseeds is groundnuts. Because of this, the crop's quality and yield have declined, which has had a detrimental effect on the agricultural economy. This is partly because the crop is more susceptible to various diseases. It is required to create more precise and reliable automated approaches to address this problem and improve the identification of groundnut leaf diseases. This article proposes a deep learning-driven approach based on a progressive scaling technique for the accurate classification and identification of groundnut leaf diseases. The five main groundnut leaf diseases that are the subject of this study are leaf spot, armyworm effect, wilts, yellow leaf, and healthy leaf. The proposed model is trained using both progressive resizing and conventional techniques, and its performance is assessed using cross-entropy loss. A fresh dataset is meticulously curated in Gujarat state, India's Saurashtra region, for training and validation. Due to the dataset's uneven sample distribution across disease categories, an extended focus loss function was used to correct this class imbalance. In order to evaluate the performance of the suggested model, a number of performance metrics are utilized, including accuracy, sensitivity, F1-score, precision, and sensitivity. Notably, the suggested model has a 96.12% success rate, which signifies a considerable increase in the disease identification accuracy. It's important to note that the model incorporating progressive resizing beats the basic neural network-based model based on cross-entropy loss, highlighting the potency of the recommended approach.","url":"https://doi.org/10.21203/rs.3.rs-3380046/v1","authors":["Usikela Naresh","T. Bhaskara Reddy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-09-29T22:11:15Z","doi":"10.21203/rs.3.rs-3380046/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1039/d6cp00670a/v1/review1","name":"Review for \"Spectral-Directed Electrostatics Strategy Integrated within a Graph Neural Network Approach for the Prediction of Nanocluster Structures\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d6cp00670a/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-03T11:54:42Z","doi":"10.1039/d6cp00670a/v1/review1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.7554/elife.89131.4.sa2","name":"Reviewer #2 (Public Review): When and why does motor preparation arise in recurrent neural network models of motor control?","source":"crossref","abstract":"","url":"https://doi.org/10.7554/elife.89131.4.sa2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-24T10:16:12Z","doi":"10.7554/elife.89131.4.sa2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1002/we.2451/v2/review2","name":"Review for \"Performance enhancement of the artificial neural network–based reinforcement learning for wind turbine yaw control\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/we.2451/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-11-26T06:09:51Z","doi":"10.1002/we.2451/v2/review2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1002/cjce.25416/v1/review2","name":"Review for \"Modelling a chemical plant using grey‐box models employing the support vector regression and artificial neural network\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/cjce.25416/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-24T17:09:51Z","doi":"10.1002/cjce.25416/v1/review2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1002/brb3.2763/v1/review1","name":"Review for \"A medium‐weight deep convolutional neural network‐based approach for onset epileptic seizures classification in EEG signals\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/brb3.2763/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-10-05T17:02:17Z","doi":"10.1002/brb3.2763/v1/review1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-952669/v1","name":"Breast cancer segmentation and classification in ultrasound images using convolutional neural network","source":"crossref","abstract":"Abstract Breast most cancers is one of the main reasons of mortality in ladies throughout the world. Early detection contributes to a discount withinside the quantity of untimely fatalities. Using ultrasound (US) pics, we gift deep studying (DL) strategies for breast most cancers segmentation and category into 3 classes: regular, benign, and malignant. The versions in most cancers length and traits are the mission of segmentation and category tasks. The proposed technique became evolved and evaluated the use of US pics amassed from 780 breast cancers. This has a look at tested using deep studying to scientific pics of breast most cancers acquired with the aid of using ultrasound scan. For evaluation, we used intersection over union (IoU), accuracy. When evaluated with IoU the nice proposed technique yielded 100%curacy on regular breast segmentation, 79.27% on benign, and 93.73% on malignant most cancers. Also, the accuracy of category three classes is 87.86%. Our have a look at indicates the usefulness of deep studying techniques for breast most cancers segmentation and category. You can locate the preskilled weights and elements of our Implementation and the prediction of our technique may be located at https://github.com/shb8086/Cancer.","url":"https://doi.org/10.21203/rs.3.rs-952669/v1","authors":["Shima Baniadam Dizaj","Pourya Valizadeh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-10-04T23:38:22Z","doi":"10.21203/rs.3.rs-952669/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1088/0954-898x/2/1/008","name":"The role of dimensionality in a threshold-controlled neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/2/1/008","authors":["A Hartstein"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/2/1/008","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.37550/tdmu.ejs/2026.02.734","name":"Sparsity-aware ternary neural networks for memristor crossbar computing","source":"crossref","abstract":"","url":"https://doi.org/10.37550/tdmu.ejs/2026.02.734","authors":["Tien Nguyen Van"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-15T10:31:03Z","doi":"10.37550/tdmu.ejs/2026.02.734","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-1490110/v1","name":"Heart Disease Prediction Using Scaled Conjugate Gradient Back Propagation of Artificial Neural Network","source":"crossref","abstract":"Abstract Heart disease is a deadly disease in human life. The mortality rate from any disease is the highest in the world. Therefore, before reaching the final stage of this heart disease, all precautionary measures must be taken. For this reason without the help of any kind of traditional methods, if we can scientifically diagnose heart disease at an early stage through various decision support systems, then surely death rate of this disease will decrease in the whole world. Many researchers investigate the diagnosis of heart disease by creating various intelligent medical decision support systems. Artificial neural network concepts represent the highest predictive accuracy over medical data compared to other decision support systems. In this paper we propose a better prediction method for the existence of heart disease through the scaled conjugate gradient back propagation of artificial neural networks using K-fold cross validation. For cardiac datasets, the University of California Irvine (UCI) Machine Learning Repository and IEEE data port have been used. For Cleveland processed heart dataset, the proposed system uses 13 input attributes and provides minimum 63.3803% &amp; maximum 100% accurate results similarly for Cleveland Hungarian Statlog heart dataset the proposed system uses 11 input attributes and provides minimum 88.4754% &amp; maximum 100% accurate results by estimating the presence and absence of heart disease during testing.","url":"https://doi.org/10.21203/rs.3.rs-1490110/v1","authors":["BANIBRATA PAUL","Bhaskar Karn"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-31T15:32:26Z","doi":"10.21203/rs.3.rs-1490110/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1108/ilt-05-2024-0182/v1/review1","name":"Review for \"Instance segmentation of on-line wear debris using deep convolutional neural network with transfer learning\"","source":"crossref","abstract":"","url":"https://doi.org/10.1108/ilt-05-2024-0182/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-12-17T16:01:54Z","doi":"10.1108/ilt-05-2024-0182/v1/review1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.7554/elife.89131.3.sa1","name":"Reviewer #3 (Public Review): When and why does motor preparation arise in recurrent neural network models of motor control?","source":"crossref","abstract":"","url":"https://doi.org/10.7554/elife.89131.3.sa1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-08-13T11:26:10Z","doi":"10.7554/elife.89131.3.sa1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1039/d4nj04953e/v1/review1","name":"Review for \"Cetyltrimethylammonium bromide Modified Magnetic Apricot Shells for Removing Congo Red Dye and its Artificial Neural Network Model\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d4nj04953e/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-21T16:14:11Z","doi":"10.1039/d4nj04953e/v1/review1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1002/eng2.12878/v1/review2","name":"Review for \"An improved custom convolutional neural network based hand sign recognition using machine learning algorithm\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/eng2.12878/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-20T17:19:55Z","doi":"10.1002/eng2.12878/v1/review2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1002/cjce.25273/v2/review1","name":"Review for \"An adding‐points strategy surrogate model for well control optimization based on radial basis function neural network\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/cjce.25273/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-04-25T17:08:23Z","doi":"10.1002/cjce.25273/v2/review1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1002/cjce.25416/v2/review2","name":"Review for \"Modelling a chemical plant using grey‐box models employing the support vector regression and artificial neural network\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/cjce.25416/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-24T17:09:51Z","doi":"10.1002/cjce.25416/v2/review2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.7287/peerj-cs.635v0.2/reviews/1","name":"Peer Review #1 of \"Ultrasonic based concrete defects identification via wavelet packet transform and GA-BP neural network (v0.2)\"","source":"crossref","abstract":"","url":"https://doi.org/10.7287/peerj-cs.635v0.2/reviews/1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-06T12:43:57Z","doi":"10.7287/peerj-cs.635v0.2/reviews/1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-8051099/v1","name":"Fully parallel programming on 1k graphene interfacial memristor crossbar array for edge computing","source":"crossref","abstract":"Abstract Fine-tuning pre-trained neural networks in resource-constrained environments demands ultra-low-power hardware capable of real-time response. Filamentary memristors show great promise in neural networks inference but suffer from stochastic switching, undesirable for fine-tuning. While non-filamentary memristors feature more deterministic switching, they are limited by slow writes (&gt; 100 µs), poor retention (&lt; 10 4 s), and low on/off ratios (&lt; 100). Through device-circuit-system co-design, we engineer a metal-insulator-graphene (MIG) non-filamentary memristor with graphene electrodes for hysteresis-enhanced switching, achieving 50-µs writes, &gt; 1-year retention, &gt; 5,000 on/off ratio, and linear, symmetric conductance tuning under identical pulses. We elucidate switching mechanisms and build a physics-based compact model for circuit design. A parallel outer-product programming scheme is proposed to enable stochastic gradient descent across the whole crossbar array simultaneously. This scheme is validated on isolated devices and a 6×6 subarray within a 32×32 array with 92% yield. Based on this scheme, a reconfigurable architecture is designed that enables fine-tuning of four convolutional neural networks (CNNs) on CIFAR-10 in under 6 s and 0.2 J, achieving near–floating-point accuracy on two of the networks. Our platform unlocks real-time edge intelligence, revolutionizing autonomous and pervasive computing with high energy efficiency.","url":"https://doi.org/10.21203/rs.3.rs-8051099/v1","authors":["Tania Roy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-08T17:43:27Z","doi":"10.21203/rs.3.rs-8051099/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-3935900/v1","name":"Step Network: A Neural Network that Takes Into Account Spatial Structure and Texture Features for Human Pose Transfer","source":"crossref","abstract":"Abstract Portrait synthesis guided by pose presents a challenging frontier in image generation. In our latest research, we have introduced an innovative network called the Step network, specifically designed to overcome the limitations identified in previous works. Our approach differs from traditional methods by honing in on the spatial structure of the pose, enabling a gradual migration of the pose while minimizing the loss of spatial structure information at each step. Taking inspiration from triplet loss, we have incorporated Style Discriminator to elevate texture generation. Moreover, in contrast to prior research, we have placed greater emphasis on refining the generation of facial areas. To achieve this, we employed a specialized loss function that combines triplet loss and L1 loss to optimize facial features, resulting in images that are more aligned with human perception. Additionally, we have also extended our method to include the ability to replace clothing on the body. To evaluate the quality of the images generated, we utilized evaluation metrics wihch are PSNR, SSIM, FID, and LPIPS. Through both qualitative and quantitative experiments comparing our approach with state-of-the-art models, we have demonstrated significant improvements across these metrics, confirming its superiority. Specifically, our method achieved a PSNR of 18.0376, SSIM of 0.7686, FID of 10.8102, and LPIPS of 0.1665. Our experimental results and open source code in the following url: https://github.com/FineURRight/Step-Network/tree/main.","url":"https://doi.org/10.21203/rs.3.rs-3935900/v1","authors":["Han Mo","Yang Xu","Caideng Zhang","Yongdan Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T20:24:36Z","doi":"10.21203/rs.3.rs-3935900/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1002/adma.202103376","name":"Wafer‐Scale 2D Hafnium Diselenide Based Memristor Crossbar Array for Energy‐Efficient Neural Network Hardware","source":"crossref","abstract":"Abstract Memristor crossbar with programmable conductance could overcome the energy consumption and speed limitations of neural networks when executing core computing tasks in image processing. However, the implementation of crossbar array (CBA) based on ultrathin 2D materials is hindered by challenges associated with large‐scale material synthesis and device integration. Here, a memristor CBA is demonstrated using wafer‐scale (2‐inch) polycrystalline hafnium diselenide (HfSe 2 ) grown by molecular beam epitaxy, and a metal‐assisted van der Waals transfer technique. The memristor exhibits small switching voltage (0.6 V), low switching energy (0.82 pJ), and simultaneously achieves emulation of synaptic weight plasticity. Furthermore, the CBA enables artificial neural network with a high recognition accuracy of 93.34%. Hardware multiply‐and‐accumulate (MAC) operation with a narrow error distribution of 0.29% is also demonstrated, and a high power efficiency of greater than 8‐trillion operations per second per Watt is achieved. Based on the MAC results, hardware convolution image processing can be performed using programmable kernels (i.e., soft, horizontal, and vertical edge enhancement), which constitutes a vital function for neural network hardware.","url":"https://doi.org/10.1002/adma.202103376","authors":["Sifan Li","Mei‐Er Pam","Yesheng Li","Li Chen","Yu‐Chieh Chien","Xuanyao Fong","Dongzhi Chi","Kah‐Wee Ang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-09-12T13:27:53Z","doi":"10.1002/adma.202103376","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1109/icst50505.2020.9732800","name":"Network Architecture Search Method on Hyperparameter Optimization of Convolutional Neural Network: Review","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icst50505.2020.9732800","authors":["Hudalizaman","Igi Ardiyanto","Sunu Wibirama"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-03-17T20:52:50Z","doi":"10.1109/icst50505.2020.9732800","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1007/978-94-009-0643-3_134","name":"Classifying Artificial Neural Network Architecture","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-94-009-0643-3_134","authors":["J. P. Evans"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-12-08T22:06:39Z","doi":"10.1007/978-94-009-0643-3_134","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1109/apccas51387.2021.9687674","name":"Efficient Techniques for Extending Service Time for Memristor-based Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/apccas51387.2021.9687674","authors":["Yu Ma","Chengrui Zhang","Pingqiang Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-02-02T22:03:05Z","doi":"10.1109/apccas51387.2021.9687674","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-9189154/v1","name":"Performance of Artificial Neural Network and Physics-Informed Neural Networks for Flexural Strength Using Sugarcane Bagasse Ash and Distilled Sewage Water ","source":"crossref","abstract":"Abstract An increasing number of eco-conscious construction projects are looking to agricultural waste products, such as sugarcane bagasse ash (SCBA) and Distilled Sewage Water, to partially replace cement and Pure Water in their mixes. This study evaluates the predictive power of Artificial Neural Networks (ANNs) and Physics-Informed Neural Networks (PINNs) by examining the increase in flexural strength of SCBA-based concrete at 7, 14, and 28 days. The results of the experiment showed a steady increase in flexural strength with curing age, indicating constant hydration and good matrix densification. The nonlinear correlation between mix design factors and strength was anticipated using ANN and PINN methods and tested and validated through training, cross-validation (OOF), testing and full-dataset appraisals. The ANN demonstrated relatively high training accuracy, but it showed evidence of overtraining and poor generalisation, as indicated by negative R2 values on the validation and test datasets. Conversely, the PINN, where constraints are included in the loss function based on the physics, demonstrated a relatively higher stability and reduced error values (MSE, MAE, RMSE) on every data split. Reduced variance dispersion in PINN was demonstrated using residual analysis, and SHAP-based interpretability showed that cement content, percentage of SCBA and ratio of water-binder were the strongest predictors of flexural strength. Despite the fact that both models still need additional improvement to be more generalisable, the findings indicate that physics-informed learning can improve the robustness and interpretability of strength prediction. The suggested integrated experimental-PINN system presents a potential solution to the sustainable concrete performance modelling and the intelligent mix design optimisation.","url":"https://doi.org/10.21203/rs.3.rs-9189154/v1","authors":["Mayuri Ahirrao","Rakesh Patel","Chaitanya Mishra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-26T04:51:15Z","doi":"10.21203/rs.3.rs-9189154/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1088/0954-898x/2/4/005","name":"Neural network models of list learning","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/2/4/005","authors":["Neil Burgess","J Shapiro","M Moore"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/2/4/005","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1007/978-3-540-48125-6_16","name":"Neural Network Reliability","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-540-48125-6_16","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-10-28T04:36:19Z","doi":"10.1007/978-3-540-48125-6_16","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.5220/0007831102100219","name":"Enhancing Neural Network Prediction against Unknown Disturbances with Neural Network Disturbance Observer","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0007831102100219","authors":["Maxime Pouilly-Cathelain","Philippe Feyel","Gilles Duc","Guillaume Sandou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-08-09T05:20:20Z","doi":"10.5220/0007831102100219","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.3109/0954898x.2012.739722","name":"Special issue on “Neural Network Simulation”","source":"crossref","abstract":"","url":"https://doi.org/10.3109/0954898x.2012.739722","authors":["Romain Brette","Christian Leibold"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-04-30T12:11:54Z","doi":"10.3109/0954898x.2012.739722","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1088/0954-898x/9/4/007","name":"Hypothetical neural mechanism that may play a role in mental rotation: an attractor neural network model","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/9/4/007","authors":["Ľubica Beňušková","Slavomír Eštok"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/9/4/007","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1007/978-981-97-9440-9_37","name":"Speech Encryption Scheme Based on Chaotic Memristor Neural Network and S-Box","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-97-9440-9_37","authors":["Dawei Zhao","Hui Yu","Chuan Chen","Lixiang Li","Ling Mi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-31T17:07:06Z","doi":"10.1007/978-981-97-9440-9_37","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1016/j.neucom.2025.132525","name":"Memristor-based neural network hardware with hybrid stochastic neuron for fully in-situ training","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2025.132525","authors":["Sang-Gyun Gi","Ankur Singh","Byung-Geun Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-25T22:55:13Z","doi":"10.1016/j.neucom.2025.132525","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.38007/nn.2022.030207","name":"Neural Network in Internet Financial Services","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2022.030207","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T18:14:06Z","doi":"10.38007/nn.2022.030207","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1007/s00521-016-2546-7","name":"Finite-time synchronization of stochastic memristor-based delayed neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-016-2546-7","authors":["Yanchao Shi","Peiyong Zhu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2016-08-22T06:17:41Z","doi":"10.1007/s00521-016-2546-7","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1016/j.ins.2011.07.044","name":"Synchronization control of a class of memristor-based recurrent neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.ins.2011.07.044","authors":["Ailong Wu","Shiping Wen","Zhigang Zeng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-08-09T13:47:33Z","doi":"10.1016/j.ins.2011.07.044","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1109/icent.2017.37","name":"Algorithm for Determining Optimum Operation Tolerances of Memristor-Based Artificial Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icent.2017.37","authors":["S.N. Danilin","S.A. Shchanikov","A.E. Sakulin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-12-28T21:30:30Z","doi":"10.1109/icent.2017.37","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1149/ma2020-02312039mtgabs","name":"Overcoming Limitations in Evaluation of Memristor Technologies for Neural Networks","source":"crossref","abstract":"Intrinsic switching characteristics of two resistive memory technologies, hafnia (RRAM)- and carbon nanotube (CNT)- based, are evaluated with respect to their implementation in deep neural networks (DNN) and possible mitigation approaches to performance degradation. Both RRAM (poly-crystalline metal oxide) and NRAM (fabric of interlocking matrix of CNTs) operations employ modulations of the conductive paths through a semi-isolating layer sandwiched between electrodes. RRAM and NRAM characteristics demonstrate similar features when evaluated employing commonly used switching times &gt; 100 ns: variability of the weights update values linked to stochasticity of the switching processes, asymmetric weight change, and memory update saturation. Though materials are different, the observed undesirable trends have a common cause that is excessive energy released within the duration of switching operations: it induces gradual changes in the material structure surrounding conductive paths. Such changes, in turn, affect temperature distribution and related structural rearrangements during the subsequent switching. In particular, memory update saturation reflects on exhaustion of the number of structural blocks (atoms, CNTs) available for expanding the conductive path under specific used operation conditions. As follows, by reducing energy released in each operation we may suppress excessive structural changes, hence related performance degradation features. Indeed, under sub-ns switching conditions relevant to high-frequency circuitry operations, both RRAM and NRAM demonstrate significant performance improvement making them promising for DNN implementations.","url":"https://doi.org/10.1149/ma2020-02312039mtgabs","authors":["William Whitehead","Dmitry Veksler","Gennadi Bersuker"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-22T18:59:27Z","doi":"10.1149/ma2020-02312039mtgabs","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1007/springerreference_67343","name":"Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/springerreference_67343","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-08-29T18:41:41Z","doi":"10.1007/springerreference_67343","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-282859/v1","name":"Adaptive TCS creation and assignment mechanism for cognitive radio network using Golden Eagle optimized Hybrid Multilayer Perceptron-Convolutional Neural Network","source":"crossref","abstract":"Abstract The authors have requested that this preprint be removed from Research Square.","url":"https://doi.org/10.21203/rs.3.rs-282859/v1","authors":["Anjana Devi Javar","V. Prasanna Sriniva"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-03-17T16:08:18Z","doi":"10.21203/rs.3.rs-282859/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.4135/9781526493514","name":"Deep Learning in Python: Fundamentals of Neural Network Theory","source":"crossref","abstract":"","url":"https://doi.org/10.4135/9781526493514","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-03-26T00:13:02Z","doi":"10.4135/9781526493514","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.38007/nn.2020.010106","name":"Neural Network Stability Fusing Robust Features","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2020.010106","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T03:35:42Z","doi":"10.38007/nn.2020.010106","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.38007/nn.2021.020205","name":"Convolutional Neural Network in Image Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2021.020205","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T05:28:48Z","doi":"10.38007/nn.2021.020205","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.2139/ssrn.5173475","name":"Prescribed Performance Synchronization of Memristor-Based Chaotic Systems with Uncertainties Via Neural Adaptive Learning Control Strategy","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.5173475","authors":["Cong Li","Shijia Zhu","Zhili Xiong","Xue Chen","Jing Luo","Shuyu Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-11T00:36:53Z","doi":"10.2139/ssrn.5173475","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.5302/j.icros.2015.14.8041","name":"Memristor Bridge Synapse-based Neural Network Circuit Design and Simulation of the Hardware-Implemented Artificial Neuron","source":"crossref","abstract":"","url":"https://doi.org/10.5302/j.icros.2015.14.8041","authors":["Chang-ju Yang","Hyongsuk Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-23T20:42:44Z","doi":"10.5302/j.icros.2015.14.8041","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1109/nanoarch.2011.5941495","name":"Robust neural logic block (NLB) based on memristor crossbar array","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nanoarch.2011.5941495","authors":["Djaafar Chabi","Weisheng Zhao","Damien Querlioz","Jacques-Olivier Klein"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-07-08T17:44:31Z","doi":"10.1109/nanoarch.2011.5941495","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1109/ijcnn.2006.1716172","name":"Hybrid Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2006.1716172","authors":["S.W. Al-Sayegh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2006-10-30T17:35:23Z","doi":"10.1109/ijcnn.2006.1716172","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1016/j.neunet.2020.04.025","name":"Training memristor-based multilayer neuromorphic networks with SGD, momentum and adaptive learning rates","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2020.04.025","authors":["Zheng Yan","Jiadong Chen","Rui Hu","Tingwen Huang","Yiran Chen","Shiping Wen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-05-07T11:51:54Z","doi":"10.1016/j.neunet.2020.04.025","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1016/j.neucom.2021.08.072","name":"Memristor-based neural network circuit with weighted sum simultaneous perturbation training and its applications","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neucom.2021.08.072","authors":["Cong Xu","Chunhua Wang","Yichuang Sun","Qinghui Hong","Quanli Deng","Haowen Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-08-20T00:15:55Z","doi":"10.1016/j.neucom.2021.08.072","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.7498/aps.71.20220098","name":"Memristor based spiking neural network accelerator architecture","source":"crossref","abstract":"Spiking neural network (SNN) as the third-generation artificial neural network, has higher computational efficiency, lower resource overhead and higher biological rationality. It shows greater potential applications in audio and image processing. With the traditional method, the adder is used to add the membrane potential, which has low efficiency, high resource overhead and low level of integration. In this work, we propose a spiking neural network inference accelerator with higher integration and computational efficiency. Resistive random access memory (RRAM or memristor) is an emerging storage technology, in which resistance varies with voltage. It can be used to build a crossbar architecture to simulate matrix computing, and it has been widely used in processing in memory (PIM), neural network computing, and other fields. In this work, we design a weight storage matrix and peripheral circuit to simulate the leaky integrate and fire (LIF) neuron based on the memristor array. And we propose an SNN hardware inference accelerator, which integrates 24k neurons and 192M synapses with 0.75k memristor. We deploy a three-layer fully connected network on the accelerator and use it to execute the inference task of the MNIST dataset. The result shows that the accelerator can achieve 148.2 frames/s and 96.4% accuracy at a frequency of 50 MHz.","url":"https://doi.org/10.7498/aps.71.20220098","authors":["Chang-Chun Wu","Pu-Jun Zhou","Jun-Jie Wang","Guo Li","Shao-Gang Hu","Qi Yu","Yang Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-17T11:05:35Z","doi":"10.7498/aps.71.20220098","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1007/978-1-4471-2003-2_10","name":"Neural Network Control of Robot Arm Tracking Movements","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4471-2003-2_10","authors":["Dean Shumsheruddin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-12-02T14:54:17Z","doi":"10.1007/978-1-4471-2003-2_10","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1088/0954-898x/10/1/002","name":"Sparsification from dilute connectivity in a neural network model of memory","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/10/1/002","authors":["Miguel Maravall"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/10/1/002","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1088/0954-898x/6/3/001","name":"Modelling transpositional invariancy of melody recognition with an attractor neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/6/3/001","authors":["Lubica Beňušková"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-24T22:35:54Z","doi":"10.1088/0954-898x/6/3/001","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1007/978-3-540-48125-6_17","name":"Neural Network Diagnostics","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-540-48125-6_17","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-10-28T04:36:19Z","doi":"10.1007/978-3-540-48125-6_17","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1007/978-1-4842-4421-0_2","name":"Internal Mechanics of Neural Network Processing","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4842-4421-0_2","authors":["Igor Livshin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-04-12T15:05:25Z","doi":"10.1007/978-1-4842-4421-0_2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1016/j.chaos.2024.115611","name":"Nonlinear dynamics and sliding mode control for global fixed-time synchronization of a novel 2 × 2 memristor-based cellular neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.chaos.2024.115611","authors":["Yuman Zhang","Yuxia Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-11T12:21:52Z","doi":"10.1016/j.chaos.2024.115611","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1007/s11063-019-09982-y","name":"Exponential Synchronization of Inertial Memristor-Based Neural Networks with Time Delay Using Average Impulsive Interval Approach","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11063-019-09982-y","authors":["R. Rakkiyappan","D. Gayathri","G. Velmurugan","Jinde Cao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-01-25T11:06:03Z","doi":"10.1007/s11063-019-09982-y","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1140/epjst/e2019-900005-8","name":"Dynamical analysis, sliding mode synchronization of a fractional-order memristor Hopfield neural network with parameter uncertainties and its non-fractional-order FPGA implementation","source":"crossref","abstract":"","url":"https://doi.org/10.1140/epjst/e2019-900005-8","authors":["Karthikeyan Rajagopal","Murat Tuna","Anitha Karthikeyan","İsmail Koyuncu","Prakash Duraisamy","Akif Akgul"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-10-30T18:53:15Z","doi":"10.1140/epjst/e2019-900005-8","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1140/epjp/s13360-022-02652-4","name":"Dynamic analysis and application in medical digital image watermarking of a new multi-scroll neural network with quartic nonlinear memristor","source":"crossref","abstract":"","url":"https://doi.org/10.1140/epjp/s13360-022-02652-4","authors":["Fei Yu","Huifeng Chen","Xinxin Kong","Qiulin Yu","Shuo Cai","Yuanyuan Huang","Sichun Du"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-07T12:05:16Z","doi":"10.1140/epjp/s13360-022-02652-4","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1109/mocast54814.2022.9837695","name":"Neuron Deactivation Scheme for Defect-Tolerant Memristor Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/mocast54814.2022.9837695","authors":["Seokjin Oh","Jiyong An","Kyeong-Sik Min"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-07-28T19:47:12Z","doi":"10.1109/mocast54814.2022.9837695","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1109/iscas.2013.6571870","name":"Features of memristor emulator-based artificial neural synapses","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iscas.2013.6571870","authors":["Maheshwar Pd. Sah","Changju Yang","Ram Kaji Budhathoki","Hyongsuk Kim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-08-14T11:40:23Z","doi":"10.1109/iscas.2013.6571870","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1049/pbcs038e_ch8","name":"Memristor-based divider designs","source":"crossref","abstract":"","url":"https://doi.org/10.1049/pbcs038e_ch8","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-03-24T08:06:28Z","doi":"10.1049/pbcs038e_ch8","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1007/978-3-319-76375-0_40","name":"Memristor Emulators","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-319-76375-0_40","authors":["Dalibor Biolek"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-11-12T22:03:43Z","doi":"10.1007/978-3-319-76375-0_40","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1088/0954-898x_4_1_006","name":"Generalization error for a bar-counting multilayer neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_4_1_006","authors":["August Romeo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:16Z","doi":"10.1088/0954-898x_4_1_006","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1088/0954-898x_2_3_006","name":"A high storage capacity neural network content-addressable memory","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_2_3_006","authors":["Eric Hartman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:03:59Z","doi":"10.1088/0954-898x_2_3_006","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1088/0954-898x/5/4/003","name":"Dynamics of an attractor neural network converting temporal into spatial correlations","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/5/4/003","authors":["Nicolas Brunel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/5/4/003","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1039/d6tc01104g/v2/review1","name":"Review for \"Volatile nanocomposite memristor with a phase stratification dielectric layer: a threshold switching with rich neuromorphic dynamics\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d6tc01104g/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-28T21:09:57Z","doi":"10.1039/d6tc01104g/v2/review1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1007/s10791-026-10084-2","name":"Research on network security situation awareness algorithm based on quantum neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s10791-026-10084-2","authors":["Nan Li","Yu Wang","Haibo Zhang","Zhiqiang Li","Weina Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-07T08:20:27Z","doi":"10.1007/s10791-026-10084-2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1088/1361-6528/ae645a/v2/review2","name":"Review for \"Understanding the volatile memristor via direct observation of surface diffusion-regulated Cu-based conductive filaments\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1361-6528/ae645a/v2/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-25T21:02:46Z","doi":"10.1088/1361-6528/ae645a/v2/review2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1080/09548980701840343","name":"Extrasynaptic-GABA-mediated neuromodulation in a sensory cortical neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1080/09548980701840343","authors":["Osamu Hoshino"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2008-05-12T13:05:12Z","doi":"10.1080/09548980701840343","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1088/0954-898x/1/3/003","name":"An attractor neural network model of semantic fact retrieval","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/1/3/003","authors":["E Ruppin","M Usher"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-07-26T19:51:19Z","doi":"10.1088/0954-898x/1/3/003","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-352817/v1","name":"Hate Speech Detection using Modified Principal Component Analysis and Enhanced Convolution Neural Network on Twitter Dataset","source":"crossref","abstract":"Abstract Online social media are increasingly catching people’s eye among users of the Internet. Services provided by social networking vendors like Twitter and Facebook are very attractive, with widespread proliferation among internet users. As a downside of their predominance in the domain of social networking, Twitter and Facebook are frequently pestered with the problem of handling offensive, threat, fake, hate words. One of the major problems, apparent in online social media, is the toxic online content. In the existing system, the methods are not dealt with large dataset. Also the feature extraction method is not efficient to extract important features in the given dataset. To overcome the above mentioned issues, in this work, Modified Principal Component Analysis (MPCA) and Enhanced Convolution Neural Network (ECNN) is proposed. Natural Language Processing (NLP) is implemented to build an automatic system through the inclusion of syntactic and semantic analysis. This work contains main phases are such as pre-processing, feature extraction and classification process. The pre-processing is done by using normalization method which is used to remove the white spaces, replace the consecutive exclamation and question marks, and eliminate stop words. These preprocessed features are taken into feature extraction process. MPCA algorithm is applied to perform feature extraction process. It uses set of correlated features and extracts more informative features for the given dataset. Then the classification algorithm is proposed to detect the hate speech or abusive languages. ECNN is proposed to classify hate and non-hate from the online content more accurately. It takes many inputs and generates output with minimum amount of time with higher accuracy for larger dataset. Thus, the result concludes that the proposed MPCA+ECNN algorithm provides higher accuracy, precision, recall and F-measure values rather than the existing methods.","url":"https://doi.org/10.21203/rs.3.rs-352817/v1","authors":["Majed Alowaidi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-05-17T14:54:50Z","doi":"10.21203/rs.3.rs-352817/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-3043490/v1","name":"Adaptive Coati Deep Convolutional Neural Network-based Oral Cancer Diagnosis in Histopathological Images for Clinical Applications","source":"crossref","abstract":"Abstract Oral cancer is common cancer that appears in the mouth, posing a significant threat to public health due to its high mortality rate. Oral Squamous Cell Carcinoma (OSCC) is the most prevalent type of oral cancer, accounting for most cases, and it holds the seventh position among all types of cancers worldwide. Detecting OSCC early on is crucial to increase the chances of successful treatment and improve patients' survival rates. However, traditional diagnosis methods such as biopsy, where small tissue samples are extracted from the affected area and tested under a microscope, are time-consuming and require expert analysis. Moreover, due to the heterogeneity of OSCC, accurate diagnosis is challenging, and there is a need for alternative approaches to enhance the detection result of OSCC images. Therefore, this work develops two new approaches for segmenting and identifying OSCC with deep learning techniques named Mask Mean Shift CNN, named MMShift-CNN. The proposed MMShift-CNN approach attained the highest results in segmenting the OSCC region from the input image by retrieving color, texture, and shape features. The novel proposed method attained better performance with accuracy, F-measure, MSE, precision, sensitivity, and specificity of 0.9883, 0.9883, 0.0117, 0.999, 0.9867, and 0.99, respectively. These results reveal the efficiency of the proposed approach in accurately detecting oral cancer and potentially improving the efficiency of oral cancer diagnosis.","url":"https://doi.org/10.21203/rs.3.rs-3043490/v1","authors":["Dharani R"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-29T05:24:18Z","doi":"10.21203/rs.3.rs-3043490/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.7287/peerj.8693v0.2/reviews/2","name":"Peer Review #2 of \"Detection and visualization of abnormality in chest radiographs using modality-specific convolutional neural network ensembles (v0.2)\"","source":"crossref","abstract":"","url":"https://doi.org/10.7287/peerj.8693v0.2/reviews/2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-03-22T02:30:27Z","doi":"10.7287/peerj.8693v0.2/reviews/2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1007/s11063-023-11326-w","name":"Echo State Network Optimization: A Systematic Literature Review","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11063-023-11326-w","authors":["Rebh Soltani","Emna Benmohamed","Hela Ltifi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-06-29T13:02:15Z","doi":"10.1007/s11063-023-11326-w","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1109/tnn.2011.2162110","name":"Comprehensive Review of Neural Network-Based Prediction Intervals and New Advances","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnn.2011.2162110","authors":["A. Khosravi","S. Nahavandi","D. Creighton","A. F. Atiya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-08-03T17:20:51Z","doi":"10.1109/tnn.2011.2162110","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1007/s00521-021-05948-1","name":"Fake review and reviewer detection through behavioral graph partitioning integrating deep neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-021-05948-1","authors":["Bundit Manaskasemsak","Jirateep Tantisuwankul","Arnon Rungsawang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-04-20T08:02:34Z","doi":"10.1007/s00521-021-05948-1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.2478/v10048-012-0026-5","name":"Performance Evaluation of Neural Network Based Pulse-Echo Weld Defect Classifiers","source":"crossref","abstract":"","url":"https://doi.org/10.2478/v10048-012-0026-5","authors":["S. Seyedtabaii"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-02-14T13:04:03Z","doi":"10.2478/v10048-012-0026-5","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-2365290/v1","name":"Diagnosing of Skin Lesions Using Deep Convolutional Neural Network and Support Vector Machines","source":"crossref","abstract":"Abstract The authors have requested that this preprint be removed from Research Square.","url":"https://doi.org/10.21203/rs.3.rs-2365290/v1","authors":["Seyede Tara Naghshbandi","Abdolhosein Fathi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-14T16:05:06Z","doi":"10.21203/rs.3.rs-2365290/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.21203/rs.3.rs-2257631/v1","name":"Modeling of consumption of Gasoline (MS) and Diesel (HSD) in India using SARIMA and Neural Network","source":"crossref","abstract":"Abstract Petroleum products fuel the economic engine of a country. It is vital that accurate demand forecasting is done for these products. Various forecasting methods from simple methods like moving average to complex fuzzy logic have been used to forecast the demand for Petroleum products with varying degree of accuracy. This study compares the forecasting accuracy of two machine learning forecasting models namely Seasonal Auto Regressive Integrated Moving Average (SARIMA) and Neural Network to forecast the consumption of Gasoline (MS) and Diesel (HSD) in India and conclude which model is able to better predict the demand. To compare the forecast accuracy of models, Mean Absolute Percentage Error (MAPE) is used. The model with the lowest Mean Absolute Percentage Error (MAPE) is considered as the better forecasting model. The study concludes SARIMA and Neural Network are able to predict the consumption of Gasoline (MS) with almost equal accuracy while SARIMA is able to predict the consumption of Diesel (HSD) significantly better then Neural Network.","url":"https://doi.org/10.21203/rs.3.rs-2257631/v1","authors":["Ramesh Murthy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-21T21:39:05Z","doi":"10.21203/rs.3.rs-2257631/v1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.1088/1741-2552/ac9257/v1/review2","name":"Review for \"Modelling mouse auditory response dynamics along a continuum of consciousness using a deep recurrent neural network\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1741-2552/ac9257/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-16T17:03:41Z","doi":"10.1088/1741-2552/ac9257/v1/review2","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.7287/peerj-cs.766v0.1/reviews/1","name":"Peer Review #1 of \"Effect on speech emotion classification of a feature selection approach using a convolutional neural network (v0.1)\"","source":"crossref","abstract":"","url":"https://doi.org/10.7287/peerj-cs.766v0.1/reviews/1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-11-08T01:33:11Z","doi":"10.7287/peerj-cs.766v0.1/reviews/1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.7287/peerj.8693v0.1/reviews/1","name":"Peer Review #1 of \"Detection and visualization of abnormality in chest radiographs using modality-specific convolutional neural network ensembles (v0.1)\"","source":"crossref","abstract":"","url":"https://doi.org/10.7287/peerj.8693v0.1/reviews/1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-03-22T02:30:26Z","doi":"10.7287/peerj.8693v0.1/reviews/1","addedAt":"2026-09-01T01:48:34.796Z","updatedAt":"2026-09-01T01:48:34.796Z"},{"id":"doi:10.23939/jcpee2026.01.007","name":"Intelligent digital stethoscope for neural network analysis of auscultatory signals: a review of sensors, architectures and algorithms","source":"crossref","abstract":"A auscultation into a measurement process: heart and/or lung sounds are captured by a sensor, amplified by a low-noise analogue front-end, digitized, processed using digital signal processing (DSP) techniques, and can be analyzed by neural networks. The paper summarizes key approaches to designing an intelligent digital stethoscope, including the selection of sensors and the auscultation head, requirements for the analogue front-end and ADC, the sequence of digital signal processing stages, modern neural network architectures for classification and pre-screening, as well as practices for evaluating model performance. Special attention is given to the impact of noise, contact artifacts, and data distribution shifts across different devices and recording conditions. The presented results can serve as a basis for planning experiments and future publications.","url":"https://doi.org/10.23939/jcpee2026.01.007","authors":["Taras Komaryshyn","Ihor Kogut"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-19T05:49:36Z","doi":"10.23939/jcpee2026.01.007","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.21203/rs.3.rs-2570982/v1","name":"Image recognition of sports dance teaching and auxiliary function data verification based on neural network algorithm","source":"crossref","abstract":"Abstract Nowadays, physical dance is widely spread in the society as an emerging sport. Dance movement is favored by people because of its unique social function and fitness effect. For dance teaching, dance movement analysis can help optimize and improve the existing dance movements and the understanding and inheritance of traditional dance movements. With the rise of online teaching, intelligent identification and analysis of dance movements can promote the better development of sports dance teaching. However, the relevant research in this area is still very scarce. As the basis of this kind of research, there is an urgent need for dance motion recognition technology. Based on this background, this paper by introducing neural network algorithm for dance teaching sports image special recognition design, the algorithm can combine feature extraction technology to process video, extract the dance movements in the target data set, then for the extraction of cumulative feature extraction operation, in order to accumulate all the collected target features, so as to further complete the gradient histogram acquisition. Through the design experimental test, the cumulative feature image extraction results obtained through the algorithm are obviously better than the traditional image recognition results, so the design rationality and effectiveness of the algorithm are proved, and the sports dance teaching can be specially assisted. This paper designs an effective auxiliary image recognition algorithm by introducing the neural network algorithm into the field of sports dance teaching.","url":"https://doi.org/10.21203/rs.3.rs-2570982/v1","authors":["Yuchuan Lin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-02-15T11:27:57Z","doi":"10.21203/rs.3.rs-2570982/v1","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.21203/rs.3.rs-19197/v1","name":"Research on Personnel Performance Evaluation Model Based on Neural Wireless Network Data Mining Algorithm","source":"crossref","abstract":"Abstract In order to effectively evaluate personnel performance, a distributed data mining algorithm for spatial networks based on BP neural wireless network is proposed. In the cloud computing environment, an excavator is used to construct multiple input multiple output spatial network data, analyze the data structure, and perform redundant data compression of massive data through time-frequency feature extraction. Combined with adaptive matching filtering method, the characteristics of the data are matched. The spatial frequency feature extraction method is used to locate the features of the multiple-input multiple-output spatial network data, and the fourth-order cumulant slice is used for reorganization. Data in time series. In order to improve the accuracy of data mining, the BP neural network is used to classify and identify the extracted data features to achieve the optimization of data mining. This algorithm improves the accuracy of personnel performance evaluation, and simultaneously establishes a hierarchical analysis and quantitative evaluation model for the performance of government managers, and adjusts the results of hierarchical statistical analysis on government administrators as needed. The performance evaluation and optimization of government administrators were introduced. The empirical analysis results show that the method has higher accuracy for government managers' performance evaluation, higher efficiency of big data processing and better integration.","url":"https://doi.org/10.21203/rs.3.rs-19197/v1","authors":["Wei Liang","Tingyi Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-03-27T20:56:03Z","doi":"10.21203/rs.3.rs-19197/v1","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.21203/rs.3.rs-1461025/v1","name":"Daily average relative humidity forecasting with LSTM neural network and ANFIS approaches","source":"crossref","abstract":"Abstract Because hurricanes, droughts, floods, and heat waves are all important factors in measuring environmental changes, they can all result from changes in atmospheric air temperature and relative humidity (RH). Besides, climate, weather, industry, human health, and plant growth are all affected by RH. Accurately and consistently forecasting RH is a challenge due to its non-linear nature. The present study tried to predict one day ahead of RH in determined provinces from different climatic regions of Turkey (Ankara, Erzurum, Samsun, Diyarbakır, Antalya, and Bilecik) using long short-term memory (LSTM) and adaptive neuro-fuzzy inference system (ANFIS) with fuzzy c-means (FCM) based machine learning models. As evaluation criteria, root mean square error (RMSE), mean absolute error (MAE), and correlation coefficient (R) were employed. The outcomes from the forecasting models were also validated using observed data. During the testing stage, the smallest MAE and RMSE values were discovered to be 5.76% and 7.51%, respectively, in Erzurum province, with an R-value of 0.892 when using the LSTM method. Moreover, the smallest MAE and RMSE values were obtained to be 5.95% and 7.67% respectively, in Erzurum province with an R-value of 0.887 using the ANFIS model according to the hourly RH prediction. The results indicate that both the LSTM and ANFIS approaches performed well in daily RH prediction, with the LSTM and ANFIS approaches producing nearly identical results.","url":"https://doi.org/10.21203/rs.3.rs-1461025/v1","authors":["Arif Ozbek","Şaban Ünal","Mehmet Bilgili"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-18T13:28:42Z","doi":"10.21203/rs.3.rs-1461025/v1","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.21203/rs.3.rs-27563/v1","name":"Chirp Signal Denoising Based on Convolution Neural Network","source":"crossref","abstract":"Abstract Many classical chirp signal processing algorithm may experience distinct performance decrease in noise circumstance. To address the problem, this paper proposes a deep learning based approach to filter noises in time domain. The proposed denoising convolutional neural network (DCNN) is trained to recover the original clean chirps from observation signals with noises. Following denosing, we employ two parameter estimation algorithm to DCNN output. Simulation result show that the proposed DCNN method improves the signal noise ratio (SNR) and parameter estimation accuracy to a great extent compared to the signals without denoising. And DCNN have a strong adaptability of low SNR input scenarios that never trained.","url":"https://doi.org/10.21203/rs.3.rs-27563/v1","authors":["Ben Guangli","Xifeng Zheng","Yongcheng Wang","Xin Zhang","Ning Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-05-13T20:46:00Z","doi":"10.21203/rs.3.rs-27563/v1","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.7287/peerj.8693v0.3/reviews/2","name":"Peer Review #2 of \"Detection and visualization of abnormality in chest radiographs using modality-specific convolutional neural network ensembles (v0.3)\"","source":"crossref","abstract":"","url":"https://doi.org/10.7287/peerj.8693v0.3/reviews/2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-03-22T02:30:32Z","doi":"10.7287/peerj.8693v0.3/reviews/2","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.21203/rs.3.rs-1996632/v1","name":"Adaptive Convolutional Neural Network-based Speckle Removal From Undersampled K-space Data","source":"crossref","abstract":"Abstract This paper presents the framework for accelerating MR Imaging (MRI) by adopting Compressive Sampling/Sensing (CS) strategy. The major drawback is the extensive time involved in recovering MR Images from the limited k -space data which is often affected by various noises. Specifically speckle noise is seen to affect medical imaging modalities like ultrasound and MR scanning. This work presents the mathematical analysis for the distribution that arises due to the Speckle scattering. Further, a method has been devised to eliminate the Speckle noise to reconstruct MR images from the sub-sampled k -space (spatial frequency) data, while preserving the visual quality. The proposed sparse reconstruction method constructs on a Deep Convolutional Neural Network (DCNN) to reduce the reconstruction time. The CNN training involves the pairs of images which are generated from sub-sampled noisy spatial frequency points and the corresponding fully sampled k -space data. The performance of the proposed method has been evaluated with various sub-sampling schemes. The results show a remarkable reduction in the computation time along with high image quality for various undersampling strategies.","url":"https://doi.org/10.21203/rs.3.rs-1996632/v1","authors":["MALLAVELLI V.R. Manimala","C Dhanunjaya Naidu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-08-31T17:43:47Z","doi":"10.21203/rs.3.rs-1996632/v1","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.1002/2050-7038.12391/v1/review2","name":"Review for \"A self-constructing Lyapunov neural network controller to track global maximum power point in PV systems\"","source":"crossref","abstract":"","url":"https://doi.org/10.1002/2050-7038.12391/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-03-26T17:06:14Z","doi":"10.1002/2050-7038.12391/v1/review2","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.7287/peerj.14335v0.4/reviews/3","name":"Peer Review #3 of \"Predicting RNA secondary structure by a neural network: what features may be learned? (v0.4)\"","source":"crossref","abstract":"","url":"https://doi.org/10.7287/peerj.14335v0.4/reviews/3","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-18T01:31:15Z","doi":"10.7287/peerj.14335v0.4/reviews/3","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.21203/rs.3.rs-8576637/v1","name":"NB-Net: A Biologically-Inspired Framework for Neural Network Width Expansion","source":"crossref","abstract":"Abstract Deep learning has achieved remarkable success across various fields, however, most research in this area has primarily focused on increasing network depth, leading to a relative lack of systematic exploration of network width. Inspired by the structure of biological neural systems, widening a neural network can enhance the resolution of the feature space, enabling the capture of richer and more fine-grained visual features. To this end, we propose a novel architecture called Neuron Bundle Network (NB-Net), featuring a groundbreaking dual 1×1 convolution fusion mechanism that revolutionizes multi-branch feature integration. NB-Net is inspired by the morphological structure of dendrites and axons in biological neurons. It aggregates multiple parallel processing paths using diverse convolutional layers and attention modules through our innovative dual 1×1 convolution design. Our dual 1×1 convolution fusion mechanism serves as the core innovation, providing superior feature integration compared to traditional single-stage merge operations by enabling gradual dimensionality reduction and enhanced gradient stability. The framework introduces several key innovations, including the dual 1×1 convolution two-stage merge mechanism for stable gradient flow, adaptive learning rate scaling for attention integration, and a systematic approach to kernel diversity orchestrated through our fusion strategy. Ablation studies demonstrate that the dual 1×1 convolution mechanism drives performance gains, enabling competitive results with efficient structured sparsity and feature fusion.","url":"https://doi.org/10.21203/rs.3.rs-8576637/v1","authors":["Longfei Tan","Zhaohui Huang","Wei-Liang Meng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-22T19:22:27Z","doi":"10.21203/rs.3.rs-8576637/v1","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.21203/rs.3.rs-2906389/v1","name":"Design of Accurate Multi-class Optimized Lightweight Convolution Neural Network for Rice Varieties Classification","source":"crossref","abstract":"Abstract Worldwide, more than 40k rice varieties are existing, each with different nutritional content and quality. Identifying these has to be consistent, automated, and accurate. Considering the feature extraction process, convolution Neural Networks (CNN) are preferred over machine learning (ML) for this classification. Transfer learning approaches help to optimize the CNN model; therefore, it fits in an FPGA. Seven different CNN models were proposed to classify five rice varieties, each model differs based on the: kernel depth; the number of convolution layers (CL); the number of fully connected layers (FCL); and the number of neurons per FCL. These were analyzed considering 70% and 30% for training and testing respectively. A dataset of 15,000 images/variety with each image of resolution. This results in an O ptimized L ight w eight C onvolutional N eural Network (OpLW-CNN) model, having a CL, followed by two FCLs. This model is further analyzed using a random set of images: 500, 5000, and 75000 to fit the model optimally. This model achieves 99%, 98.13%, and 98.14% of specificity, F1-score, and accuracy for a set of 5000 images. These metrics are approximately 1% to 2% lesser than the performance of the benchmark model, and 81.5% fewer computations. Also, this model requires less than a second to classify an image.","url":"https://doi.org/10.21203/rs.3.rs-2906389/v1","authors":["Deepika Selvaraj","Arunachalam Venkatesan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-05-11T13:42:30Z","doi":"10.21203/rs.3.rs-2906389/v1","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.21203/rs.3.rs-831690/v1","name":"A Hybrid Encoded and Adapted-tuned Neural Network for Asset Medical Image Watermarking Technique","source":"crossref","abstract":"Abstract Digital image watermarking techniques are used to authenticate identity of owners and copyright protection of asset images. Asset medical images (AMI) specially require extreme care when embed a watermark message because additional information should affect the AMI quality and the changes in AMI gray levels may interfere with its interpretation. This paper introduces a hybrid encoded and adapted-tuned neural network (TNN) for AMI watermarking technique to cover almost essential watermarking requirements. To attain robustness, security and invisibility, uses human visual system (HVS) and TNN to tune the AMI and to find the maximum amount of adaptive watermark message before the watermark message becomes visible. To achieve transparency, enhance AMI using histogram equalization. Embedding is performed into the middle frequency coefficients of discrete cosine transform of the AMI, to avoid visual parts in the low frequency coefficient and the noise and attacks in high frequency to improve image robustness and increase capacity comparing to spatial domain.","url":"https://doi.org/10.21203/rs.3.rs-831690/v1","authors":["mina hanna","Mazhar Tayel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-01-17T21:56:42Z","doi":"10.21203/rs.3.rs-831690/v1","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.21203/rs.3.rs-2157214/v1","name":"Automatic Diagnosis of Cardiovascular Diseases from ECG Signals using Convolutional Neural Network and Soft Computing Methods","source":"crossref","abstract":"Abstract Since the last decade, the Electrocardiogram (ECG) tool has received medical experts and researchers' attention for accurate and fast diagnosis of cardiovascular diseases (CVD). The automatic detection and classification of 1D ECG-based heart disease have become more realistic and efficient solutions using the deep learning technique such as Convolutional Neural Network (CNN). As CNN is designed mainly for 2D or 3D applications therefore, designing CNN to process 1D ECG becomes challenging. We proposed a novel framework for automatic CVD detection and classification from the raw ECG signals using 1D-CNN deep learning technique. The framework consists of pre-processing, automatic feature extraction, feature optimization, and classification. In pre-processing, raw ECG signals are filtered to remove the baseline drift and power line interference using median and notch filters respectively. The pre-processed ECG signals are then used to extract the QRS and ST waves using the dynamic thresholding in the wavelet transfer domain. The fusion of QRS and ST waves have fed to automatic 1D-CNN that consists of layers i.e,1D convolutional layer, ReLU layer, and max-pooling layers. The 1D-CNN is proposed in this paper to extract features automatically with little computing complexity. The high-dimensional raw CNN features are optimized by applying a feature selection and scaling approach. For classification, different soft computing techniques such as Long- Short Term Memory (LSTM), Support Vector Machine (SVM), Naïve Bays (NB), Artificial Neural Network (ANN), and k-nearest neighbor (KNN) are applied. The experimental performances of the proposed model have been investigated on a publicly available research dataset and outperformed recent CNN-based techniques.","url":"https://doi.org/10.21203/rs.3.rs-2157214/v1","authors":["Shimpy Goyal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-11-17T14:43:52Z","doi":"10.21203/rs.3.rs-2157214/v1","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.21203/rs.3.rs-1574912/v1","name":"Determination and Evapotranspiration of different Agro-climatic regions of India by Artificial Neural Network","source":"crossref","abstract":"Abstract Climate change has a tremendous effect on the evapotranspiration (ET) process worldwide and the computation of ET for various climatic regions is essential for efficient water management. ET was estimated using Artificial Neural Network models for 10 stations falling under different agro-climatic regions of India. Although the Penman–Monteith ET model has superior predictive ability than the other methods, owing to the need for a large number of climatic variables, it is difficult to use in data-short conditions and it is necessary to determine the most important climatic variables for the agro-climatic regions. Most sensitive climatic variables were identified from the Principal Component Analysis (PCA) for all the stations. Sensitivity analysis showed that the overall average change in ET 0 values for 25% change in the climatic variables were 18%, 16%, 14%, 7%, 5%, 4% respectively for T max , RH mean, R n, Wind speed, T min and sunshine hours. New ET models were developed for each station, both with all climatic variables and with the important climatic variables identified by PCA, using the ANN model and compared the performance with Penman–Monteith ET estimates. Net radiation, high and low temperatures, usual relative humidity, wind velocity, and the ratio of daily sunshine hours are all input variables to the model, with ET0 values as an output. Several neurons in the hidden layer for each station for the best model performance were found. PCA variables guaranteed the most reliable estimation of potential evapotranspiration (PET) accounting for 98% of the variability. The average values of coefficient of determination (R 2 ), standard error of estimate (SEE), and percentage efficiency (%) were observed as 0.96, 0.24, 94% respectively. There was no significant difference between the ANN model with all climatic variables and with the PCA variables identified indicating that the ANN model with variables resulting from PCA can be preferred for practical applications.","url":"https://doi.org/10.21203/rs.3.rs-1574912/v1","authors":["Markutty Abraham","Sankaralingam Mohan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-06-07T17:09:42Z","doi":"10.21203/rs.3.rs-1574912/v1","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.2478/v10048-012-0007-8","name":"Hardware Prototyping of Neural Network based Fetal Electrocardiogram Extraction","source":"crossref","abstract":"","url":"https://doi.org/10.2478/v10048-012-0007-8","authors":["M. Hasan","M. Reaz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-04-20T01:07:08Z","doi":"10.2478/v10048-012-0007-8","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.21203/rs.3.rs-10278153/v1","name":" Principal Component Analysis Searched Binary Neural Network for Carcinoma Detection using Multi-Modal Data","source":"crossref","abstract":"Abstract Early detection of carcinoma is vital as its absence often leads to late-stage diagnosis, limited treatment options and significantly reduced survival rates. However, existing diagnostic methods often exhibit low sensitivity in early stages. Additionally, these methods can be invasive, costly, and reliant on specialized equipment. To address these challenges, a model called Principal Component Analysis Searched Binary Neural Network (PCA-SBNN) is proposed for carcinoma detection. At first, input CT image is taken and is subjected to an image pre-processing stage, which is carried out using the Contra-Harmonic Mean filter. Next, liver area segmentation is performed using TBConvL-Net, which is followed by feature extraction, where features extracted through this process are taken as output-1. On the other hand, clinical data is taken as input and passed through a data normalization phase that is accomplished by Peldschus normalization. The normalized clinical data obtained from this step is considered as output-2. At last, output-1 and output-2 are taken together to detect carcinoma using the proposed PCA-SBNN model, which is the integration of Principal Component Analysis Network (PCANet) with Searched Binary Neural Network (SBNN). The efficacy of PCA-SBNN is evaluated by assuming metrics, such as accuracy, sensitivity, specificity, False Omission Rate (FOR), Matthews Correlation Coefficient (MCC) with superior values of 96.78%, 95.92%, 96.97%, 0.036 and 0.958.","url":"https://doi.org/10.21203/rs.3.rs-10278153/v1","authors":["T Thangam","A.Kaleel Rahuman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-05T12:05:36Z","doi":"10.21203/rs.3.rs-10278153/v1","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:34.797Z"},{"id":"doi:10.3390/ma18163820","name":"Filamentary Resistive Switching Mechanism in CuO Thin Film-Based Memristor.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/ma18163820","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.3390/ma18163820","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1038/s41467-025-60085-w","name":"Memristive Bellman solver for decision-making.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-60085-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-60085-w","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1038/s41467-025-57543-w","name":"Electrochemical ohmic memristors for continual learning.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-025-57543-w","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41467-025-57543-w","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1021/acsnano.5c02480","name":"Silk Fibroin-Based Biomemristors for Bionic Artificial Intelligence Robot Applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1021/acsnano.5c02480","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1021/acsnano.5c02480","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1126/sciadv.adr5262","name":"Harnessing spatiotemporal transformation in magnetic domains for nonvolatile physical reservoir computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.adr5262","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1126/sciadv.adr5262","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1038/s41598-025-96462-0","name":"The use of artificial intelligence-based Siamese neural network in personalized guidance for sports dance teaching.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41598-025-96462-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1038/s41598-025-96462-0","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1016/j.mtbio.2025.101934","name":"Rapid detection of brain tumor cells using memristors for biomedical applications.","source":"europepmc","abstract":"","url":"https://doi.org/10.1016/j.mtbio.2025.101934","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1016/j.mtbio.2025.101934","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1038/s41467-024-45312-0","name":"Memristor-based storage system with convolutional autoencoder-based image compression network.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-024-45312-0","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41467-024-45312-0","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1126/sciadv.adt3584","name":"Double-opponent spiking neuron array with orientation selectivity for encoding and spatial-chromatic processing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.adt3584","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1126/sciadv.adt3584","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1038/s41467-024-44773-7","name":"High-speed and energy-efficient non-volatile silicon photonic memory based on heterogeneously integrated memresonator.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-024-44773-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41467-024-44773-7","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1126/sciadv.adu2663","name":"Nanoelectronics-enabled reservoir computing hardware for real-time robotic controls.","source":"europepmc","abstract":"","url":"https://doi.org/10.1126/sciadv.adu2663","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1126/sciadv.adu2663","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1007/s40820-024-01335-2","name":"Recent Advances in In-Memory Computing: Exploring Memristor and Memtransistor Arrays with 2D Materials.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s40820-024-01335-2","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1007/s40820-024-01335-2","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.3390/mi14122233","name":"Coexisting Firing Patterns in an Improved Memristive Hindmarsh-Rose Neuron Model with Multi-Frequency Alternating Current Injection.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/mi14122233","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.3390/mi14122233","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1002/adma.202310704","name":"Memristor-Based Neuromorphic Chips.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202310704","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1002/adma.202310704","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.3390/mi15010051","name":"Behavioral Modeling of Memristors under Harmonic Excitation.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/mi15010051","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.3390/mi15010051","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1038/s41467-023-43317-9","name":"Bringing uncertainty quantification to the extreme-edge with memristor-based Bayesian neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-023-43317-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.1038/s41467-023-43317-9","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1002/adma.202419678","name":"Challenges and Opportunities of Upconversion Nanoparticles for Emerging NIR Optoelectronic Devices.","source":"europepmc","abstract":"","url":"https://doi.org/10.1002/adma.202419678","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2025","doi":"10.1002/adma.202419678","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1038/s41467-024-45670-9","name":"Hardware implementation of memristor-based artificial neural networks.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-024-45670-9","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41467-024-45670-9","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1186/s40580-024-00432-7","name":"Two-dimensional material-based memristive devices for alternative computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1186/s40580-024-00432-7","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1186/s40580-024-00432-7","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.3390/mi14101840","name":"A Design Methodology for Fault-Tolerant Neuromorphic Computing Using Bayesian Neural Network.","source":"europepmc","abstract":"","url":"https://doi.org/10.3390/mi14101840","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2023","doi":"10.3390/mi14101840","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1007/s11571-023-10029-1","name":"Memristive patch attention neural network for facial expression recognition and edge computing.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s11571-023-10029-1","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1007/s11571-023-10029-1","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1038/s41467-024-52488-y","name":"Computing high-degree polynomial gradients in memory.","source":"europepmc","abstract":"","url":"https://doi.org/10.1038/s41467-024-52488-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1038/s41467-024-52488-y","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1007/s40820-024-01525-y","name":"Ultra-Transparent and Multifunctional IZVO Mesh Electrodes for Next-Generation Flexible Optoelectronics.","source":"europepmc","abstract":"","url":"https://doi.org/10.1007/s40820-024-01525-y","authors":[],"tags":[],"confidence":0.8,"sites":["neuromorphic"],"publishedDate":"2024","doi":"10.1007/s40820-024-01525-y","addedAt":"2026-09-01T01:48:34.797Z","updatedAt":"2026-09-01T01:48:35.021Z"},{"id":"doi:10.1109/icici68867.2026.11564880","name":"Multi-Headed Attention-based Parallel Convolution Neural Network for Deepfake Image Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icici68867.2026.11564880","authors":["Harsh Shukla","Dharmesh Rathod"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-18T20:07:15Z","doi":"10.1109/icici68867.2026.11564880","addedAt":"2026-09-01T01:48:35.256Z","updatedAt":"2026-09-01T01:48:35.256Z"},{"id":"doi:10.1117/12.3116034","name":"RINKA: efficient artificial neural network model for drone-based object detection","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3116034","authors":["Paweł Tomiło"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-06T20:58:04Z","doi":"10.1117/12.3116034","addedAt":"2026-09-01T01:48:35.256Z","updatedAt":"2026-09-01T01:48:35.256Z"},{"id":"doi:10.1109/icc59461.2026.11588083","name":"Benchmarking Spatio-Temporal Graph Neural Networks for Airborne Network Performance Prediction","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icc59461.2026.11588083","authors":["Ali Yilmaz Yildirim","Fabien Geyer","Georg Carle"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-14T19:38:09Z","doi":"10.1109/icc59461.2026.11588083","addedAt":"2026-09-01T01:48:35.256Z","updatedAt":"2026-09-01T01:48:35.256Z"},{"id":"doi:10.18127/j19998554-202602-04","name":"Comparison of performance of neural network models of computer vision applied to tensor processors","source":"crossref","abstract":"Specialized hardware accelerators like Tensor Processing Units (TPUs) are promising for deploying real-time computer vision models, but their efficiency heavily depends on compatibility with a specific neural network architecture. YOLO family object detection models (v5, v8, v11), being the de facto standard, are initially optimized for GPUs. Practical questions arise: which of the modern YOLO versions adapts most efficiently to TPUs in terms of the balance between speed, accuracy, and porting complexity, and how does their performance differ from the reference GPU implementation? The objective of the article is to conduct a comparative performance analysis of modern YOLO models (v5, v8, v11 by Ultralytics) after their adaptation for execution on TPUs, aiming to identify the most suitable model for practical application on this hardware platform. Using a porting methodology based on TensorFlow and optimizations (quantization), YOLOv5, YOLOv8, and YOLOv11 models have been adapted and tested. A comparative analysis of key metrics (inference speed, mAP accuracy, TPU resource utilization efficiency) allowed for ranking the models and identifying the leader, which demonstrates the optimal compromise between minimal accuracy degradation and maximum speedup on TPUs compared to GPUs. The results provide engineers and developers with evidence-based recommendations for selecting a specific YOLO model version for deployment on TPUs. This helps to reduce the time and resources required to find an optimal solution when creating resource-efficient computer vision systems for autonomous driving, video surveillance, and robotics tasks.","url":"https://doi.org/10.18127/j19998554-202602-04","authors":["M.A. Kukushkin","P.A. Ukhov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-22T12:37:40Z","doi":"10.18127/j19998554-202602-04","addedAt":"2026-09-01T01:48:35.256Z","updatedAt":"2026-09-01T01:48:35.256Z"},{"id":"doi:10.1109/icbase70763.2026.11619400","name":"Neural Network Channel Modeling Based on Self-Attention Mechanism","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icbase70763.2026.11619400","authors":["Qiyao Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-29T19:09:09Z","doi":"10.1109/icbase70763.2026.11619400","addedAt":"2026-09-01T01:48:35.256Z","updatedAt":"2026-09-01T01:48:35.256Z"},{"id":"doi:10.26226/m.6657251f918878861e1bd8c3","name":"Captioning Knee MRI Sequences: Metadata-Independent Classification with a 3D Convolutional Neural Network-Recurrent Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.26226/m.6657251f918878861e1bd8c3","authors":["Yu-Cherng Chang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-09-04T03:58:58Z","doi":"10.26226/m.6657251f918878861e1bd8c3","addedAt":"2026-09-01T01:48:35.256Z","updatedAt":"2026-09-01T01:48:35.256Z"},{"id":"doi:10.2139/ssrn.6802602","name":"Predictive Accuracy of Neural Network Model with Multiple Train Functions for Stochastic Stock Indices","source":"crossref","abstract":"Two popular stock indices, i.e., BSE and NSE, are modeled through Artificial Neural Network (ANN) to identify superior combinations for predictive accuracy. Ten-year daily data of closing index along with open, high and low indices are modeled through NARX modeling. The statistical tools AAE, RMSE, MAPE and MSPE are used to find out the predictive accuracy of ANN model. The results indicate ANN (4-10-1) with trainfunction GDX as the best predictor within the final outcome. The high predictive accuracy of the model to predict stock indices suggests a relook at the EMH for long-term data series.","url":"https://doi.org/10.2139/ssrn.6802602","authors":["Vijay Shankar Pandey","Jitendra Kumar Sharma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-29T13:33:48Z","doi":"10.2139/ssrn.6802602","addedAt":"2026-09-01T01:48:35.256Z","updatedAt":"2026-09-01T01:48:35.256Z"},{"id":"doi:10.2139/ssrn.6292455","name":"Neural Network–Based ERP Detection from BCI-Oriented EEG Signals Using Time–Frequency Features and Image Representation","source":"crossref","abstract":"Abstract—The domain of Brain–Computer Interface (BCI)explores how humans can interact with computers without directphysical input. Electroencephalography (EEG) signals containrich information about the bioelectrical activity of the brain, butthey are noisy, high-dimensional, and often subject-dependent.Traditional EEG-based BCI approaches rely on handcraftedfeature extraction and often fail to capture subtle spatial–temporal patterns. In this work, we propose an image-based EEGrepresentation and a neural network architecture with optimalfeature selection in the frequency and time–frequency domainsto detect event-related potentials (ERPs). The proposed methodachieves classification accuracy ranging from 74% to 92%.Additionally, a CNN-based ERP detection approach achieves an accuracy of 82% to 92%.","url":"https://doi.org/10.2139/ssrn.6292455","authors":["MD  NAZRUL ISLAM"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-23T14:38:56Z","doi":"10.2139/ssrn.6292455","addedAt":"2026-09-01T01:48:35.256Z","updatedAt":"2026-09-01T01:48:35.256Z"},{"id":"doi:10.2196/preprints.98668","name":"Retraction: Artificial Intelligence–Based Neural Network for the Diagnosis of Diabetes: Model Development (Preprint)","source":"crossref","abstract":"UNSTRUCTURED","url":"https://doi.org/10.2196/preprints.98668","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-28T19:45:36Z","doi":"10.2196/preprints.98668","addedAt":"2026-09-01T01:48:35.256Z","updatedAt":"2026-09-01T01:48:35.256Z"},{"id":"doi:10.38007/nn.2021.020203","name":"Intelligent Vehicle Lane Recognition Based on Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2021.020203","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T05:28:48Z","doi":"10.38007/nn.2021.020203","addedAt":"2026-09-01T01:48:35.256Z","updatedAt":"2026-09-01T01:48:35.256Z"},{"id":"doi:10.1021/acs.jpclett.2c00654.s003","name":"BuRNN: Buffer Region Neural Network Approach for Polarizable-Embedding Neural Network/Molecular Mechanics Simulations","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acs.jpclett.2c00654.s003","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-25T13:21:46Z","doi":"10.1021/acs.jpclett.2c00654.s003","addedAt":"2026-09-01T01:48:35.256Z","updatedAt":"2026-09-01T01:48:35.256Z"},{"id":"doi:10.38007/nn.2021.020105","name":"Improved Text Classification Algorithm Based on Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2021.020105","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T18:10:50Z","doi":"10.38007/nn.2021.020105","addedAt":"2026-09-01T01:48:35.256Z","updatedAt":"2026-09-01T01:48:35.256Z"},{"id":"doi:10.21660/2026.143.5405","name":"CONVOLUTIONAL NEURAL NETWORK-BASED SPACE DETECTION MODEL FOR STIRRUPS AND TIES","source":"crossref","abstract":"","url":"https://doi.org/10.21660/2026.143.5405","authors":["Samuel John Pajarillaga Abella"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-08T07:47:26Z","doi":"10.21660/2026.143.5405","addedAt":"2026-09-01T01:48:35.256Z","updatedAt":"2026-09-01T01:48:35.256Z"},{"id":"doi:10.2139/ssrn.6294733","name":"Remaining useful life prediction of bearings using an enhanced neural network with a novel activation function","source":"crossref","abstract":"Rotating components are commonly used in several industries such as transportation, manufacturing and power plants. Bearings are considered as critical components in rotating machinery. Thus, the remaining useful life (RUL) prediction of bearings is regarded as an important process in bearing prognostics and health management (PHM). This study presents a new framework for predicting the RUL of bearings based on signal decomposition and a modified neural network that employs a novel Sine–Sigmoid activation function, referred to as Sinmoid. The proposed model consists of three main parts. Initially, the original vibration signal is segmented, and salient statistical metrics of the segmented data are calculated to construct a statistical feature dataset. Subsequently, the statistical metrics are decomposed using Empirical Mode Decomposition (EMD) to reveal the underlying degradation behavior of the bearing. Finally, the neural network equipped with Sinmoid activation function is employed to predict the RUL of the bearing. The model was implemented on a rolling bearing dataset prepared from the PRONOSTIA platform, and the results revealed the superiority of the proposed model in comparison with other approaches.","url":"https://doi.org/10.2139/ssrn.6294733","authors":["Ali Najmi","Rasoul Shafaei"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-27T15:31:11Z","doi":"10.2139/ssrn.6294733","addedAt":"2026-09-01T01:48:35.256Z","updatedAt":"2026-09-01T01:48:35.256Z"},{"id":"doi:10.1088/0954-898x/7/2/022","name":"A fast, three-layer neural network for path finding","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/7/2/022","authors":["Th Kindermann","H Cruse","K Dautenhahn"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/7/2/022","addedAt":"2026-09-01T01:48:35.256Z","updatedAt":"2026-09-01T01:48:35.256Z"},{"id":"doi:10.1039/d6tc00569a/v1/review1","name":"Review for \"Integrated Digital and Analog Resistive Switching in a Bis-Indolyl Derivative-Based Memristor for Artificial Synaptic Applications\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d6tc00569a/v1/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-16T21:36:14Z","doi":"10.1039/d6tc00569a/v1/review1","addedAt":"2026-09-01T01:48:35.256Z","updatedAt":"2026-09-01T01:48:35.256Z"},{"id":"doi:10.20517/iontronics.2026.02","name":"Ion-shuttling memristor: towards ionic computing and neuromorphic sensing","source":"crossref","abstract":"The iontronic memristor has attracted growing attention as a promising candidate for neuromorphic computing and sensing. Recently, a novel iontronic memristor, termed the ion-shuttling memristor (ISM), has been proposed. Benefiting from its bio-mimicking structure, ISM can emulate ion-selective neuron functions alongside basic functions. ISM has several potential advantages, including interfacial receptors and the incorporation of multiple ionophores. On this basis, ISM may pave the way for future applications, such as sophisticated multi-carrier neuromorphic computing and neuromorphic sensing.","url":"https://doi.org/10.20517/iontronics.2026.02","authors":["Boyang Xie","Ping Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-30T07:18:29Z","doi":"10.20517/iontronics.2026.02","addedAt":"2026-09-01T01:48:35.256Z","updatedAt":"2026-09-01T01:48:35.256Z"},{"id":"doi:10.1007/978-1-4842-7368-5_6","name":"Neural Network Prediction Outside of the Training Range","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-1-4842-7368-5_6","authors":["Igor Livshin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2021-10-18T21:30:54Z","doi":"10.1007/978-1-4842-7368-5_6","addedAt":"2026-09-01T01:48:35.256Z","updatedAt":"2026-09-01T01:48:35.256Z"},{"id":"doi:10.1109/coconet.2018.8476878","name":"Notice of Retraction: Variability Analysis of Memristor-based Sigmoid Function","source":"crossref","abstract":"","url":"https://doi.org/10.1109/coconet.2018.8476878","authors":["Nursultan Kaiyrbekov","Olga Krestinskaya","Alex Pappachen James"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-10-22T21:04:09Z","doi":"10.1109/coconet.2018.8476878","addedAt":"2026-09-01T01:48:35.256Z","updatedAt":"2026-09-01T01:48:35.256Z"},{"id":"doi:10.1109/icnc59488.2023.10462797","name":"Robust ψ-Type Stability of Memristor-Based Neural Networks with Unbounded Time-Varying Delay Under Input Perturbation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc59488.2023.10462797","authors":["Jiarui Wang","Song Zhu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-03-19T18:09:52Z","doi":"10.1109/icnc59488.2023.10462797","addedAt":"2026-09-01T01:48:35.256Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.neunet.2007.04.008","name":"Reducing uncertainties in neural network Jacobians and improving accuracy of neural network emulations with NN ensemble approaches","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2007.04.008","authors":["Vladimir M. Krasnopolsky"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2007-05-02T14:37:24Z","doi":"10.1016/j.neunet.2007.04.008","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1088/0954-898x_5_4_003","name":"Dynamics of an attractor neural network converting temporal into spatial correlations","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_5_4_003","authors":["Nicolas Brunel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:09Z","doi":"10.1088/0954-898x_5_4_003","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1007/springerreference_81546","name":"Artificial Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/springerreference_81546","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-01-20T08:29:16Z","doi":"10.1007/springerreference_81546","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.21203/rs.3.rs-8842235/v1","name":"Stable Control of Wireless Charging under Coil Vibration Situation by A Transfer Learning-based Fuzzy Neural Network","source":"crossref","abstract":"Abstract In recent years, wireless power transfer (WPT) systems have gained significant attention for their convenience,safety, and environmental advantages over traditional charging methods. However, the instability in received voltage due to coil vibration during wireless charging has posed a substantial challenge to the advancement of this technology. To address this issue, this paper proposes optimizing the controller using transfer learning. The optimized controller is designed to ensure stable charging voltage. Specifically, this paper applies transfer learning to enhance a fuzzy neural network (FNN) controller by transferring knowledge from a source domain to a target domain, thereby significantly improving controller performance. Moreover, to mitigate the challenge of insufficient target domain data in transfer learning, a self-correction method is introduced to augment the target domain dataset. To validate the effectiveness of the transfer learning-optimized controller, both simulation and hardware experiments are conducted and compared with four other mainstream controllers. The efficiency of the FNN controller optimized by transfer learning reach 68%, 64%, and 58% under three different disturbance levels, respectively, outperforming the other controllers. Additionally, the maximum voltage deviation is ±2%, and the voltage amplitude is 2.55V, both of which are superior to those of the comparative controllers.","url":"https://doi.org/10.21203/rs.3.rs-8842235/v1","authors":["Yunduo Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-19T12:45:44Z","doi":"10.21203/rs.3.rs-8842235/v1","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.7112170","name":"Engineering structural synthetic reliability estimation using enhanced moving neural network-based dimensional modeling method","source":"crossref","abstract":"To perform synthetic reliability estimation of engineering structures, an enhanced moving neural network-based dimensional modeling (DMEMNN) method is proposed based on artificial neural network (ANN) model, heuristic algorithm, moving regression (MR) method and dimensional modeling concept, in which the ANN model is used to reflect relationships between each response and these related input parameters, the heuristic algorithm is applied to improve the ability of searching compact support region (CSR) radius and determining effective modeling samples, the MR technique is adopted to find these unknown coefficients with the determined effective modeling samples, and the dimensional modeling concept is employed to derive synchronous modeling of multiple responses. In this case, four models are developed by introducing four chaotic mapping (CM) strategies and sled dog optimizer (SDO). For illustrating the applicability of the proposed DMEMNN method and the effectiveness of four developed models, a multi-objective nonlinear function (MONF) fitting and probabilistic analyses, an aircraft hydraulic system (HS) pressure and temperature prediction and reliability evaluation and an aeroengine high-pressure turbine blisk (HPTB) multi-failure response and reliability analyses are implemented, the analytical results show that the proposed framework holds excellent advantages in modeling and simulation capabilities.","url":"https://doi.org/10.2139/ssrn.7112170","authors":["Junyao Wang","Cheng Lu","Da Teng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-13T15:40:17Z","doi":"10.2139/ssrn.7112170","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.38007/nn.2020.010201","name":"License Plate Recognition Technology Based on Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2020.010201","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T18:08:52Z","doi":"10.38007/nn.2020.010201","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1007/springerreference_8264","name":"artificial neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/springerreference_8264","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-08-01T13:54:05Z","doi":"10.1007/springerreference_8264","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.6190079","name":"An Attention-Based Graph Neural Network with Adaptive Gated Fusion for Predicting Molecular Solubility","source":"crossref","abstract":"Aqueous solubility is an important property in drug discovery, as it strongly influences drug absorption, bioavailability, and therapeutic effectiveness. Chemists often seek to optimize molecular structures to improve solubility; however, experimental measurement is time-consuming and costly. Therefore, developing a trustworthy machine learning model for solubility prediction can significantly reduce costs in early-stage drug development. Traditional computational approaches typically rely on local molecular features, such as atomic and bond properties, or tabular molecular descriptors, which may fail to capture complex structure–property relationships. In this study, we present a novel hybrid GNN architecture that integrates both local structural information and global molecular descriptors through an edge attention mechanism with gated fusion. Our approach combines atom-level graph representations with molecular-level features to capture comprehensive structure-solubility relationships. The model employs attention-based message passing to dynamically weight atomic contributions and a learnable gating mechanism to adaptively balance local and global information based on molecular complexity. Evaluated on the benchmark ESOL dataset, our model achieves superior performance with R2 = 0.936, RMSE = 0.51, and MAE = 0.38 on the test set. To verify the generalizability of our approach, we tested the model on the AqSolDB dataset, confirming its ability to predict solubility for new molecules. By providing accurate predictions with transparent explanations, this model helps researchers identify promising drug candidates earlier, reducing development time and costs.","url":"https://doi.org/10.2139/ssrn.6190079","authors":["Md. Shamim Parvej","Md. Anisur Rahman"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-13T03:08:57Z","doi":"10.2139/ssrn.6190079","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.6644522","name":"GAF-SCNN: Ghost-Attention Fusion Semantic Convolutional Neural Network for Real-Time Urban Scene Understanding","source":"crossref","abstract":"Real-time semantic segmentation is a key capability for autonomous driving, robotic navigation, and intelligent surveillance systems. To enable the use of dense predictors on resource-constrained edge devices, we seek to develop a model that jointly minimizes parameters, FLOPs, and latency, maintaining competitive segmentation accuracy. We introduce a novel compact architecture, GAF-SCNN (Ghost Attention Fusion Semantic Convolutional Neural Network), which integrates the three efficient architecture designs into a unified framework of a shared dual-branch architecture: (i) Ghost modules [1] for parameter-efficient feature generation, (ii) Squeeze-and-Excitation (SE) Channel Attention [2] for adaptive feature recalibration, and (iii) a novel Mini Context Pooling (MCP) module for efficient multi-scale context aggregation [3]. The main innovation of the GAF-SCNN is the integration of all three strategies into one common Fast-SCNN-like encoder framework. This approach is novel in the sense that it has not been attempted before within the 400 K parameter scope. The proposed GAF-SCNN architecture adopts the shared encoder framework of Fast SCNN [4], where a LiteDown_Block (Conv2D + 2*DSConv) downscales the input to a size of H/8 × W/8 × 64, and the encoder shares the same architecture for the Global Feature Extractor and the Fusion branch. Four stacked GhostBottleneck blocks with SE Channel Attention form the Global Feature Extractor, followed by a novel Mini Context Pooling (MCP) module for contextaggregation. Finally, the Adaptive Fusion Block with SE Gating integrates the features, and the Compact Classifier Head with two stages of DSConv produces the final segmentation results at the full resolution using 8 times bilinear interpolation. GAF-SCNN, when trained end-to-end for 1000 epochs using the Cityscapes benchmark [5] at 1024x2048 resolution, achieves a competitive 57.4% mIoU and 81.07% mean Pixel Accuracy (mPA) on the validation set, using a minimal 384.87 K parameters, establishing an excellent accuracy-efficiency trade-off for edge-deployable segmentation.","url":"https://doi.org/10.2139/ssrn.6644522","authors":["Ahsan Ul Haq","Veningston K"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-25T02:41:52Z","doi":"10.2139/ssrn.6644522","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.62329/jgwp4527","name":"Comparative Evaluation of Neural Network Compression Techniques Across Cloud GPU, NPU, and CPU Platforms","source":"crossref","abstract":"Pruning, INT8 quantization and knowledge distillation were compared across a cloud GPU, a laptop NPU and a 2017 desktop CPU over 46 configurations on MNIST and CIFAR-10. The NPU ran baseline inference three times faster than the cloud GPU, and the legacy CPU reached a tenfold speedup on distilled models, challenging the assumption that inference belongs in the cloud.","url":"https://doi.org/10.62329/jgwp4527","authors":["Harri Sn"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-20T17:55:52Z","doi":"10.62329/jgwp4527","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.26434/chemrxiv.10001743/v2","name":"A Multitask Graph Neural Network Framework for AMES Mutagenicity Prediction","source":"crossref","abstract":"The process of drug screening and development is long, complex, and costly, making early and reliable assessment of toxicity a central challenge in pharmaceutical research. In this context, the ability to accurately predict drug-induced toxicity in general, and mutagenicity in particular, is crucial for guiding decision-making and reducing late-stage attrition. In particular, deep learning approaches can be utilized to predict the results of the Ames mutagenicity test, which is commonly employed for toxicity screening in drug development. Recent work has shown that deep learning multitask approaches that account for the contributions of individual bacterial strains improve mutagenicity prediction. However, most existing models rely on molecular descriptors, which are limited in their representation of molecular structure and properties and often lack interpretability. Graph neural networks are chemically intuitive and overcome many of these limitations. Here, we present a deep learning, multitask graph neural network model for predicting Ames mutagenicity. The proposed approach outperforms existing models, including those from the Ames/QSAR International Challenge, and demonstrates high sensitivity for identifying mutagenic compounds. In addition, our model is highly interpretable. GNNExplainer analysis of atom-level contributions revealed that the model learned known structural alerts associated with mutagenicity, as well as additional molecular patterns and contextual features, including three-dimensional structural properties. Importantly, these insights were captured in a strain-specific manner, highlighting the value of a multitask approach for modeling mutagenic mechanisms. Finally, the model identified previously unreported molecular substructures potentially associated with mutagenicity, supporting its utility in drug design and development.","url":"https://doi.org/10.26434/chemrxiv.10001743/v2","authors":["Abigail E Teitgen","Eugenia Ulzurrun","Nuria E Campillo","Eduardo R Hernández"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-30T19:07:16Z","doi":"10.26434/chemrxiv.10001743/v2","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.6136422","name":"A PVT-Aware Offset Calibration of Dynamic Comparator Using Neural Network Assisted Capacitive Tuning","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.6136422","authors":["Angel Garg","Abhishek Sheoran","Anil Singh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-26T18:46:19Z","doi":"10.2139/ssrn.6136422","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.5194/egusphere-egu26-9179","name":"Detecting hail-prone environments using a W-Net convolutional neural network","source":"crossref","abstract":"Hailstorms are known to cause great damage to agriculture and infrastructure. However, understanding and identifying the conditions favorable to hail remains a major challenge due to the complex, multi-scale nature of deep convective processes. In this study, we investigate the use of a W-Net convolutional neural network (CNN), which proved successful in image segmentation tasks, to identify atmospheric environments susceptible to hail from high-resolution numerical weather prediction data. The NOAA High-resolution Rapid Refresh (HRRR) model explicitly resolves convective processes owing to its fine spatial (3 km) and temporal (hourly) resolution. We consider meteorological variables from HRRR outputs relevant to deep convection and hail as input features for the W-Net model. Together with hail reports across the United States for the past ten years, we construct a deep learning framework. The trained network learns spatial patterns associated with hail-prone environments and produces gridded probability maps of hail occurrence. This data-driven approach shows the potential of deep learning methods for identification of hazardous convective weather. Once trained, the model can be applied to other regions, provided that the sub-daily, high-resolution meteorological fields are available.","url":"https://doi.org/10.5194/egusphere-egu26-9179","authors":["Lana Hercigonja","Zeeshan Aslam","Moetasim Ashfaq","Maja Telišman Prtenjak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-13T23:35:41Z","doi":"10.5194/egusphere-egu26-9179","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.3390/s26031078","name":"Feature Augmentation-Based Adaptive Neural Network Control for Quadrotors","source":"crossref","abstract":"In this article, an adaptive neural network (ANN) controller based on feature augmentation (FA) is designed for quadrotors. The proposed controller consists of two components: a position sub-controller and an attitude sub-controller. We use the ANN to estimate unknown internal and external disturbance terms within quadrotors. To improve the learning accuracy of the ANN, we design an FA structure, which enables networks to more effectively learn the characteristics in the data. To increase the learning rate of the ANN, a state predictor (SP) is proposed to anticipate the state errors, which subsequently updates the learning rate of the ANN. Based on stability analysis, we prove that the closed-loop system is input-to-state stable (ISS). Finally, the effectiveness of our proposed control algorithm is demonstrated by comparing it with related control algorithms on both the MATLAB R2020a/Simulink simulation platform and a quadrotor experimental platform.","url":"https://doi.org/10.3390/s26031078","authors":["Bang Song","Mengxing Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-06T16:32:59Z","doi":"10.3390/s26031078","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.26434/chemrxiv.15006282/v1","name":"ChemGNN: Graph Neural Network Surrogate Guided Design of Carbon Nanotube Membranes for High-Efficiency Desalination","source":"crossref","abstract":"ChemGNN, a deep-learning-accelerated framework that learns a graph-based surrogate of membrane transport and actively proposes high-performance designs. Each CNT configuration is encoded as a heterogeneous graph in which tube nodes carry geometry and functionalization features, edges encode inter-tube spacing, and global features describe operating conditions such as pressure, temperature gradient, and salinity. A contextual message-passing encoder produces node embeddings that a transformer-style readout fuses into a representation predicting water permeance and salt rejection. An expected-improvement acquisition function then selects the most informative candidates for molecular-dynamics validation, closing an active-design loop that concentrates expensive simulations on promising regions of the design space. We evaluate ChemGNN on a dataset of 12,480 configurations with 86 experimental hold-out measurements, comparing against an MD-only random search, a Gaussian-process surrogate, and a topologyagnostic multilayer perceptron surrogate. ChemGNN achieves the highest water permeance of 63.5 LMH/bar and salt rejection of 99.2 percent while requiring roughly an order of magnitude fewer molecular-dynamics evaluations than all baselines. Extensive analyses further reveal the non-linear sensitivity of performance to tube diameter, array pitch, temperature gradient, and feed salinity, and a human evaluation by domain experts confirms the novelty and practical relevance of the proposed designs. These results demonstrate that graph-aware deep learning effectively captures the coupled geometry-transport relationship underlying CNT membrane desalination.","url":"https://doi.org/10.26434/chemrxiv.15006282/v1","authors":["Linyu Meng","Shuo Tang","Yaqing Luo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-20T08:24:47Z","doi":"10.26434/chemrxiv.15006282/v1","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.5194/egusphere-egu26-12550","name":"Identifying zircon provenances using domain-adversarial neural network","source":"crossref","abstract":"Zircon trace element geochemistry is a pivotal tool for unraveling petrogenesis and the evolutionary history of the Earth’s crust. While two-dimensional (2D) discriminant diagrams are conventionally used to identify parent rock types, the emergence of machine learning (ML) has introduced a transformative research paradigm. ML not only enhances classification accuracy but also resolves the inherent ambiguities found in traditional geochemical diagrams. However, the reliability of current ML models typically depends on the vast archives of labeled samples from the Phanerozoic. When extending research to “deep-time” samples, such as Hadean zircons, the scarcity of labeled data often forces researchers to rely on models trained exclusively on Phanerozoic datasets. This approach is prone to misclassification due to “domain shift,” caused by systematic variations in zircon trace element distributions across different geological eons. To address this challenge, we propose a Domain Adversarial Neural Network (DANN) framework tailored for zircon trace element analysis. By aligning the feature distributions of the source domain (Phanerozoic) and the target domain (Precambrian), the DANN extracts “domain-invariant yet geologically significant” high-dimensional feature representations, effectively mitigating the effects of temporal data bias. Our results demonstrate that DANN significantly outperforms traditional machine learning methods across multiple performance metrics. Furthermore, t-SNE visualization confirms that the source and target domains are effectively aligned within the feature space. When applied to ~4.3 Ga zircon samples from the Jack Hills, the model achieved a classification accuracy of 0.923. This high level of performance underscores the framework’s exceptional generalization capability for identifying unlabeled deep-time samples and its potential for broader applications in Precambrian geology. This study develops a transferable, data‑driven framework for inferring deep‑time geological processes, providing a novel methodology to address the limitations inherent in the traditional principle of uniformitarianism. Furthermore, the framework is extensible to other mineral systems (e.g., apatite, monazite), thereby opening new avenues for quantitatively reconstructing the dynamic evolution of the early Earth.","url":"https://doi.org/10.5194/egusphere-egu26-12550","authors":["Mengwei Zhang","Guoxiong Chen","Timothy Kusky","Mark Harrison","Qiuming Cheng","Lu Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-14T01:11:56Z","doi":"10.5194/egusphere-egu26-12550","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1038/s41598-026-65766-0","name":"Neural network-driven adaptive PD controller for hexacopter UAV path tracking","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s41598-026-65766-0","authors":["Nigatu Wanore Madebo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-11T08:03:28Z","doi":"10.1038/s41598-026-65766-0","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.21203/rs.3.rs-10396887/v1","name":"An Innovative Perspective to Profound Functions of the Brain: Hypothesis of Resonance of Closed Neural Network Geometries","source":"crossref","abstract":"Abstract Perception and consciousness can be reformulated as intrinsic properties of resonant dynamics in recurrent neural circuits. Despite extensive empirical characterization of cortical activity, existing models lack a principled mechanism explaining how temporally structured sensory inputs give rise to stable and reproducible perceptual states. Here, I introduce Resonance of Closed Neural Network Geometries (RCNNG), a theoretical framework in which the physical properties of sensory inputs induce the formation of physically instantiated closed neural geometries whose resonance profiles reflect the temporal–spectral structure of the input. These closed geometries arise from resonant patterns of the frequency spectrum in the repeating network, but the perceptual similarity does not depend on the geometric or topological similarity of the physical structures themselves. Instead, perceptual equivalence emerges when distinct physical geometries map to identical resonant identities in a higher-dimensional resonance state space constituting an intrinsic property of the resonant closed graph and its mapping into a perceptual state space. Dynamical systems analysis and simulations of adaptive recurrent networks show that repeated or coherent stimuli drive the system toward stable resonant attractors characterized by closed cycle dynamics encoding perceptual invariants such as color, shape, and multimodal conjunctions. Within this framework, perception corresponds to the resonance of the closed geometry generated by the input, whereas consciousness arises from the simultaneous or sequential resonance of multiple linked or unlinked closed geometries across the network as a whole. This global resonance process gives rise to an intrinsic phenomenological property termed innergence, which characterizes the first-person experiential aspect of resonant state space identities. RCNNG thus distinguishes between the physical formation of closed neural geometries and their resonant identities, providing a unified account of perceptual stability, memory recall, reactivation of sensory experiences, and the emergence of conscious experience.","url":"https://doi.org/10.21203/rs.3.rs-10396887/v1","authors":["Hasan Niazi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-21T07:31:31Z","doi":"10.21203/rs.3.rs-10396887/v1","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.7344543","name":"Soliton Profiles in 1D: Enhanced Neural-Network Solvers and Constrained Deep Ritz Methods","source":"crossref","abstract":"We develop and compare {\\it enhanced} neural-network solvers for one-dimensional ground-state profiles, which are solutions of $$Q^{\\prime\\prime}=bQ-\\gamma Q^{p},\\quad Q&gt;0,\\quad p&gt;1, \\quad b&gt;0,$$the stationary profile equation for the nonlinear Schr\\\"odinger, generalized Korteweg--de Vries, and nonlinear Klein--Gordon equations. Its explicit $\\sech$-type solutions serve as exact reference for error computation. We improve on the standard Adam-trained physics-informed neural network (PINN) baseline by introducing higher-order optimization via Gauss-Newton / Levenberg-Marquardt and L-BFGS refinements, as well as Fourier-feature PINNs, and constrained Deep Ritz (DR) formulations. In DR approaches we introduce two new neural-network formulations: a {\\it Nehari-constrained} Deep Ritz method, in which the height is learned by projecting onto the Nehari/Pokhozhaev manifold, and a {\\it Weinstein} Deep Ritz method, in which the profile shape minimizes the Weinstein quotient. The Deep Ritz formulations perform best overall, in particular, the Weinstein variant gives the best error-runtime balance. The neural network based solvers remain less accurate and efficient than classical Petviashvili iteration in 1D, but their mesh-free formulation and independence from exact profiles make them promising in higher dimensions and for more complicated nonlinearities and dispersive operators.","url":"https://doi.org/10.2139/ssrn.7344543","authors":["CHANDLER HAIGHT","Alex  D. Rodriguez","Svetlana Roudenko"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-24T12:00:02Z","doi":"10.2139/ssrn.7344543","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/tnse.2019.2934357","name":"Memristor-Based Design of Sparse Compact Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tnse.2019.2934357","authors":["Shiping Wen","Huaqiang Wei","Zheng Yan","Zhenyuan Guo","Yin Yang","Tingwen Huang","Yiran Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-08-14T20:17:46Z","doi":"10.1109/tnse.2019.2934357","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1201/9781420015454-8","name":"Neural Network Control of Nonstrict Feedback Nonlinear Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781420015454-8","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-12-02T00:22:01Z","doi":"10.1201/9781420015454-8","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.21203/rs.3.rs-8389167/v1","name":"Efficient Nudged Elastic Band Method using Neural Network Bayesian Algorithm Execution","source":"crossref","abstract":"Abstract The discovery of a minimum energy pathway (MEP) between metastable states is crucial for scientific tasks including catalyst and biomolecular design. However, the standard nudged elastic band (NEB) algorithm requires hundreds to tens of thousands of compute-intensive simulations, making applications to complex systems prohibitively expensive. We introduce Neural Network Bayesian Algorithm Execution (NN-BAX), a framework that jointly learns the energy landscape and the MEP. NN-BAX sequentially fine-tunes a foundation model by actively selecting samples targeted at improving the MEP. Tested on Lennard-Jones and Embedded Atom Method systems, our approach achieves a one to two order of magnitude reduction in energy and force evaluations with negligible loss in MEP accuracy and demonstrates scalability to &gt;100-dimensional systems. This work is therefore a promising step towards removing the computational barrier for MEP discovery in scientifically relevant systems, suggesting that weeks-long calculations may be achieved in hours or days with minimal loss in accuracy.","url":"https://doi.org/10.21203/rs.3.rs-8389167/v1","authors":["Pranav Kakhandiki","Sathya Chitturi","Daniel Ratner","Sean Gasiorowski"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-04T07:27:21Z","doi":"10.21203/rs.3.rs-8389167/v1","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.6913173","name":"Intrinsic variability and benchmarking of Long Short-Term Memory neural network for wind speed prediction","source":"crossref","abstract":"In recent years, complex Artificial Intelligence (AI) models have emerged as a key approach for renewable energy forecasting. However, studies often fail to adequately benchmark foundational models, like pure Long-Short Term Memory (LSTM) networks, against external benchmarks. To address this, the current study attempts to evaluate the performance of LSTM models in wind speed prediction. LSTM models are benchmarked against the universally available baseline, persistence. Intrinsic variability is measured by repeating the experiments with random initialization, sensitivity to typical configuration characteristics is assessed and input data selection’s impacts are evaluated for two complementary data sources, global atmospheric reanalysis and high-frequency anemometer measurements. Across all tests, minimal LSTM architectures with short input windows performed best, while increasing model depth and width or input complexity did not improve predictive skill. When using the hourly data from a global data base, LSTM setups generally perform close to persistence and tend to display much higher bias, whereas LSTM models could reliably outperform persistence for ultra-short prediction from anemometer data. One important observation across all experiments is significant intrinsic variability of error metrics arising from stochastic elements in the training. The findings illustrate the importance of reporting uncertainty and repetitions in wind forecasting studies using AI tools as a standard practice.","url":"https://doi.org/10.2139/ssrn.6913173","authors":["Akram Miriyev","Wolf-Gerrit Fruh"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-10T14:48:56Z","doi":"10.2139/ssrn.6913173","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.22541/authorea.15007191/v1","name":"A 500KV Transmission Line Fault Detection, Classification and Location Using Artificial Neural Network","source":"crossref","abstract":"A large amount of electrical power is intended to be transported from generation point to consumption point via overhead lines. These transmission lines are often subjected to a wide range of conditions that can result in electrical faults. This paper focuses on the applications of artificial neural networks (ANN) to detect, classify, and locate faults in overhead power transmission lines. A 500KV, 300km transmission line system was designed in MATLAB-SIMULINK. A three-phase fault block was used to create four types of faults: single line-to-ground, line-to-line, double line-to-ground, and three-phase fault. The faulty current and voltage data were used as inputs to train, validate and test the ANN. The intelligent locator procedures were trained, tested, and evaluated using a multilayer neutral network with pattern recognition, employing Scale Conjugate Gradient method. The system performance was evaluated using the confusion matrix, training state plots, receiver operating curve, and Mean Square Error (MSE). The validation performance measured by MSE was 9.5885*10^-9, while the confusion matrix demonstrated 99% effectiveness. The system detected, classified, and pinpointed fault locations within 1km. The system proved to be a highly accurate method for overhead transmission line’s fault analysis. Keywords: Transmission Lines, Faults, Artificial Neural Network, Mean Square Error","url":"https://doi.org/10.22541/authorea.15007191/v1","authors":["Yusufu Meshit Ndonkeh","Thomas Mih","Edickson Bobo Yungho"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-08T01:37:15Z","doi":"10.22541/authorea.15007191/v1","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.3390/electronics15102086","name":"Time-Series Modeling Based on a Modified Volterra Neural Network","source":"crossref","abstract":"This paper proposes a novel neural network model that integrates a modified Volterra digital filter with a feedforward neural network for time-series modeling. In the proposed architecture, all input signals in the conventional Volterra filter are replaced by corresponding output signals, since time-series problems typically consist of observable output sequences over time without explicit external inputs. These output signals, together with their cross-product terms, are constructed as input vectors for the feedforward neural network. To optimize the network parameters, including weights and thresholds, the well-known particle swarm optimization (PSO) algorithm is employed. Based on the proposed PSO-trained neural network model, two types of time series are investigated: chaotic time series and financial time series involving exchange rates. For each case, multiple independent runs with different initial conditions are conducted to ensure the robustness of the proposed method. Furthermore, the effects of varying filter orders and population sizes on modeling performance are also examined.","url":"https://doi.org/10.3390/electronics15102086","authors":["Wei-Der Chang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-13T16:26:37Z","doi":"10.3390/electronics15102086","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.6403970","name":"Enhancing Minimization Methods for Electrical Impedance Tomography Inverse Problem Using Convolutional Neural Network Architectures","source":"crossref","abstract":"This paper investigates the improvement of accuracy and efficiency in the Alternating Direction Method of Multipliers for recovering a non-smooth diffusion parameter in ill-posed elliptic boundary value problems, particularly in Electrical Impedance Tomography. The primary challenge is accurately identifying the diffusion parameter from noisy boundary data. This work provides a historical perspective, addresses identifiability issues, and proposes techniques to solve the problem. Specifically, it introduces an approach based on Alternating Direction Method of Multipliers, integrating Convolutional Neural Network architectures to enhance the identification process and mitigate the impact of noise. The contributions extend to multiple measurements, demonstrating the effectiveness of the proposed methodology in solving complex inverse problems in biomedical imaging, as shown in the numerical experiment section.","url":"https://doi.org/10.2139/ssrn.6403970","authors":["Oumaima Anzal","Najib Guessous","Youssef Ouakrim"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-12T22:38:54Z","doi":"10.2139/ssrn.6403970","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/neurel.2012.6419968","name":"Regular session 2: Neural network algorithms and realizations","source":"crossref","abstract":"","url":"https://doi.org/10.1109/neurel.2012.6419968","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2013-01-31T12:22:27Z","doi":"10.1109/neurel.2012.6419968","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acs.jpclett.2c00654.s002","name":"BuRNN: Buffer Region Neural Network Approach for Polarizable-Embedding Neural Network/Molecular Mechanics Simulations","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acs.jpclett.2c00654.s002","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-25T13:21:46Z","doi":"10.1021/acs.jpclett.2c00654.s002","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/icsc67292.2026.00076","name":"Dominance Scoring Method Using Multi-layer Graph Convolutional Neural Network and Geometric Formation Features","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icsc67292.2026.00076","authors":["Shunsuke Takagi","Yohei Nakada"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-24T19:44:40Z","doi":"10.1109/icsc67292.2026.00076","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.26434/chemrxiv.15003886/v1","name":"An analytically differentiable submatrix-descriptor neural-network potential for molecular simulations of liquid water","source":"crossref","abstract":"Machine-learning potentials can accelerate atomistic simulations, but their use in molecular dynamics requires descriptors that are symmetry preserving, differentiable and straightforward to evaluate. We present a compact neural-network potential based on local submatrix descriptors and apply it to liquid water. A sparsified Coulomb or sine matrix is reduced to atom-centred submatrices, which are converted into fixedlength descriptors by deterministic neighbour ranking. A single shared network maps all atomic descriptors to energy contributions, avoiding element-specific subnetworks while retaining chemical identity through the matrix elements. Because the descriptor is differentiable, conservative forces are obtained analytically by the chain rule. For periodic liquid water, five-fold cross-validation gives a lowest mean absolute energy error of 0.0609 eV atom−1 with the sine-matrix descriptor. Analytical forces agree with finite-difference derivatives of the trained model, and conservative-force dynamics preserves the qualitative oxygen–oxygen radial distribution function.","url":"https://doi.org/10.26434/chemrxiv.15003886/v1","authors":["Varadarajan Rengaraj","Thomas D. Kühne","Thomas Kühne"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-26T06:03:36Z","doi":"10.26434/chemrxiv.15003886/v1","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.20944/preprints202601.2421.v1","name":"Enhanced Motion Prediction of Semi-Submersible Platform Using Bayesian Neural Network and Field Monitoring Data","source":"crossref","abstract":"The motion prediction of semi-submersible platforms is of significant importance for improving operational efficiency, ensuring platform safety, and providing early warning information for potential risks. Traditional prediction methods, such as those based on hydrodynamic simulations combined with Kalman filters, often face limitations due to their reliance on precise hydrodynamic parameters, which are difficult to obtain in practice. More recently, data-driven approaches, particularly deep learning models like Long Short-Term Memory (LSTM) networks, have shown promise in predicting complex motions. However, these methods often treat the prediction process as a “black box,” leading to issues such as lack of generalization ability, overfitting, and an inability to quantify the uncertainty of prediction results. To address these challenges, this paper proposes a novel motion prediction method for semi-submersible platforms based on a Bayesian neural network (BNN). The BNN incorporates Bayesian inference to effectively integrate prior knowledge and measured data, thereby quantifying uncertainties and improving prediction accuracy. The method is validated using field-measured motion data from a semi-submersible platform in the South China Sea. Compared with LSTM networks, the BNN demonstrates superior anti-noise performance and prediction accuracy, achieving an accuracy rate of up to 91.5%. Moreover, over 92% of the true values are captured within the 95% confidence interval of the prediction results. This study highlights the potential of BNNs for real-time motion prediction of offshore platforms, providing valuable support for early warning systems and operational decision-making.","url":"https://doi.org/10.20944/preprints202601.2421.v1","authors":["Song Li","Jia-wang Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-02T05:09:43Z","doi":"10.20944/preprints202601.2421.v1","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/siu71813.2026.11636657","name":"ADS-B Signal Separation with a Dual-Path Convolutional-Recurrent Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/siu71813.2026.11636657","authors":["Burcu Türk","Işın Erer"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-11T19:20:04Z","doi":"10.1109/siu71813.2026.11636657","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2118/231836-pa","name":"Accelerated Permeability Upscaling: A Convolutional Neural Network Approach","source":"crossref","abstract":"Summary Efficiently determining effective permeability involves substantial computational efforts, even when employing local upscaling techniques. This research utilizes a convolutional neural network (CNN) architecture for the rapid estimation of effective permeability. The CNN takes as input the permeability maps of specific layers from the fine-scale model earmarked for upscaling into layer(s) featuring coarser cells. Treating fine-scale permeability maps as 3D high-resolution images, the CNN produces a three- to six-channel lower-resolution image. Each channel represents the upscaled permeability map in a major direction, along with nondiagonal permeabilities of a symmetric permeability tensor. The simplicity and robustness of the proposed architecture stem from its two 3D convolutional hidden layers, characterized by varying filter numbers and kernel sizes. The effectiveness of the network was evaluated using two distinct data sets: (1) a continuous Gaussian model and (2) the Egg model with 100 permeability realizations. In the first data set, 500 geological realizations were generated and upscaled using a pressure solver with periodic boundary conditions (BCs), employing both local and extended local methods. The same upscaling procedure was applied to 100 realizations of the Egg model. A portion of the realizations was allocated for training, and the remainder was allocated for testing. The CNN exhibited a highly promising capture of nonlinear behavior, displaying no signs of overfitting. The results, visually and quantitatively assessed through an exceptionally high mean R2 score, were further validated through the computation of the pressure fields, affirming the accuracy of the estimated permeabilities. Notably, the training runtime proved significantly shorter than the computation time required for upscaling using the pressure-solver method. This proposed method holds the potential to substantially reduce upscaling computations, marking a stride toward more computationally efficient quasiglobal upscaling methods.","url":"https://doi.org/10.2118/231836-pa","authors":["Mohammad Sayyafzadeh","Saeid Telvari","Dominique Guérillot","Mohammad Sharifi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-27T15:23:17Z","doi":"10.2118/231836-pa","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1117/12.3120322","name":"Chip dynamic power prediction method based on improved graph neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1117/12.3120322","authors":["Sihan Du"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-12T17:59:03Z","doi":"10.1117/12.3120322","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.6079187","name":"Communications in Mathematical Physics Neural Network Formation via Navier-Stokes Dynamics and Spectral Encoding by Riemann Zeta Zeros","source":"crossref","abstract":"We propose a theoretical framework in which neural network formation is modeled as an emergent process governed by Navier-Stokes-type dynamics on a highdimensional functional manifold. In this framework, neural connectivity patterns arise from the evolution of a continuous flow field representing synaptic density and signal propagation. We further hypothesize that the long-term stable modes of this flow admit a spectral decomposition whose critical frequencies correspond to the non-trivial zeros of the Riemann zeta function. Under this conjecture, neural computation can be interpreted as the selection and interaction of zeta-zero-indexed eigenmodes, providing a novel bridge between fluid dynamics, number theory, and learning systems.","url":"https://doi.org/10.2139/ssrn.6079187","authors":["Chur Chin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-10T11:14:14Z","doi":"10.2139/ssrn.6079187","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.56726/irjmets88183","name":"Deep Convolutional Neural Network Driven 3D Facial Geometry","source":"crossref","abstract":"","url":"https://doi.org/10.56726/irjmets88183","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-10T06:21:22Z","doi":"10.56726/irjmets88183","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/ijcnn.2012.6252563","name":"Memristor crossbar based hardware realization of BSB recall function","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2012.6252563","authors":["Miao Hu","Hai Li","Qing Wu","Garrett S. Rose","Yiran Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2012-08-01T16:47:51Z","doi":"10.1109/ijcnn.2012.6252563","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.neunet.2026.108624","name":"Adversarially robust neural network decision boundaries via tropical geometry","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.108624","authors":["Kurt Pasque","Christopher Teska","Ruriko Yoshida","Keiji Miura","Jefferson Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-21T00:30:55Z","doi":"10.1016/j.neunet.2026.108624","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.6082127","name":"Accelerating stochastic simulation of post-failure landslide runout using a random graph neural network-based simulator","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.6082127","authors":["Yongjin Choi","Seungjun Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-26T16:08:09Z","doi":"10.2139/ssrn.6082127","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.6756746","name":"GAF-SCNN: Ghost-Attention Fusion Semantic Convolutional Neural Network for Real-Time Urban Scene Understanding","source":"crossref","abstract":"We present GAF-SCNN (Ghost Attention Fusion Semantic CNN), a compact architecture for real-time semantic segmentation targeting edge deployment in autonomous driving, robotics, and surveillance. GAF-SCNN integrates three efficient design strategies within a Fast-SCNN-like shared dual-branch encoder: (i) Ghost modules for parameter-efficient feature generation, (ii) Squeeze-and-Excitation channel attention for adaptive feature recalibration, and (iii) a novel Mini Context Pooling (MCP) module for multi-scale context aggregation. A LiteDown_Block downscales input to H/8×W/8×64, feeding four stacked GhostBottleneck blocks with SE attention as the Global Feature Extractor, followed by MCP and an Adaptive Fusion Block with SE gating. A two-stage DSConv Classifier Head produces full-resolution outputs via 8× bilinear interpolation. This unified integration within a sub-400K parameter budget is novel. Trained end-to-end for 1000 epochs on Cityscapes (1024×2048), GAF-SCNN achieves 57.4% mIoU and 81.07% mPA with only 384.87K parameters, offering a strong accuracy-efficiency trade-off.","url":"https://doi.org/10.2139/ssrn.6756746","authors":["Ahsan Ul Haq","Veningston K"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-13T06:42:52Z","doi":"10.2139/ssrn.6756746","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1039/d5ta09133k/v2/review1","name":"Review for \"Graph Neural Network-Based Multi-Objective Bayesian Optimization for Enhanced Screening of Metal–Organic Frameworks with Optimal Separation Performance\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5ta09133k/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-10T21:10:43Z","doi":"10.1039/d5ta09133k/v2/review1","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1039/d5ra05957g/v4/decision1","name":"Decision letter for \"Controllable Synthesis and Enhanced Photochromic Performance of Er-Doped WO3 Nano Neural Network-like Structures\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d5ra05957g/v4/decision1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-14T21:08:35Z","doi":"10.1039/d5ra05957g/v4/decision1","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1103/4zzl-qbsf","name":"Neural-network-based design and implementation of fast and robust quantum gates","source":"crossref","abstract":"","url":"https://doi.org/10.1103/4zzl-qbsf","authors":["Anonymous"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-31T18:45:26Z","doi":"10.1103/4zzl-qbsf","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.19101/ijacr.2025.1570016","name":"Context-aware misinformation detection using BERT-based neural network with TF-IDF integration","source":"crossref","abstract":"","url":"https://doi.org/10.19101/ijacr.2025.1570016","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-17T10:56:44Z","doi":"10.19101/ijacr.2025.1570016","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/apec51134.2026.11517036","name":"Data-Driven Capacity Estimation of Lithium-ion Batteries via Temperature-Coupled Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/apec51134.2026.11517036","authors":["Ala A. Hussein"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-20T19:48:55Z","doi":"10.1109/apec51134.2026.11517036","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.59462/3068-174x.4.2.142","name":"Artificial Neural Network Modeling of Surplus Value Extraction and Criminality: A Computational Approach from Political Economy","source":"crossref","abstract":"","url":"https://doi.org/10.59462/3068-174x.4.2.142","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-26T09:11:09Z","doi":"10.59462/3068-174x.4.2.142","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1364/cleo_si.2026.sm1e.7","name":"A Few-shot Physics-inspired Diffractive Neural Network for Zooming Image Edge Detection","source":"crossref","abstract":"We propose physics-inspired diffractive neural networks for zooming image edge detection. By embedding DNN-layers into the physical model of traditional lens imaging, our method requires fewer training-data, less diffractive layers, while achieving better generalization performance.","url":"https://doi.org/10.1364/cleo_si.2026.sm1e.7","authors":["Shengyao Xu","Pengsheng Zhou","Weijie Chang","Guofeng Zhu","Feng Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-15T11:08:03Z","doi":"10.1364/cleo_si.2026.sm1e.7","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.6551274","name":"Multi-graph Decoupled Heterogeneous Graph Neural Network with Reinforcement Learning and Decoupled Contrastive Loss","source":"crossref","abstract":"Emotion Recognition in Conversation (ERC) is a key task in human-computer interaction and affective computing. Currently, leveraging graph neural networks to model the complex interactions among speakers has become mainstream. However, existing methods still face three major challenges: first, it is difficult to effectively filter out emotion-irrelevant noise during feature extraction; second, the intra-modal and inter-modal dependencies are coupled within a single graph structure, limiting the model&amp;apos;s fine-grained modeling capability; third, static graph construction often introduces a large number of noisy connections, which interfere with information propagation between nodes. To address these issues, we propose a multi-graph heterogeneous graph neural network based on reinforcement learning and a decoupled contrastive loss function (RL-DCLHGNN). First, a decoupled contrastive loss function is designed in the upstream task, which separates task-relevant features from irrelevant ones by pulling positive sample pairs closer in the task-relevant feature space while pushing them away from negative samples. Second, a heterogeneous graph structure that separates intra-modal and inter-modal relationships is constructed to capture different levels of interactions respectively. Finally, reinforcement learning technology is introduced into the node connection strategy, and a dynamic sliding window mechanism is designed, enabling the model to adaptively adjust the number of connected nodes based on the current dialogue context. Extensive experiments on the IEMOCAP and MELD datasets demonstrate that RL-DCLHGNN achieves superior performance.","url":"https://doi.org/10.2139/ssrn.6551274","authors":["Yunfeng Xu","Hao Chen","Haipeng Tan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-09T17:39:54Z","doi":"10.2139/ssrn.6551274","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.6259403","name":"An energy-efficient attention-based spiking neural network for medical image classification","source":"crossref","abstract":"Modern medical imaging demands models capable of processing high-resolution images while maintaining computational and energy efficiency compatible with clinical deployment. Current dominant approaches based on Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) face critical limitations: CNNs lack global context modeling, while ViTs incur prohibitive computational costs for high-resolution medical images. Spiking Neural Networks (SNNs) represent a promising energy-efficient alternative, yet their adoption in medical imaging remains limited due to performance degradation from spike discretization and challenges in processing fine-grained spatial details at high resolution. To date: no hybrid architecture effectively combining SNNs with attention mechanisms has been validated on high-resolution medical data. This work addresses this gap by introducing ViA-RCSNN (Vision Attention Recurrent Convolutional Spiking Neural Network), a hybrid SNN-attention architecture that integrates convolutional feature extraction, cross-attention with patch-based positional encoding for global context, and spiking neurons for sparse temporal processing. Validated across four MedMNIST datasets covering different medical imaging domains (organ, pneumonia, breast, blood), ViA-RCSNN achieves 6x faster inference and ∼5x lower inference energy compared to ResNet-18, a widely studied CNN baseline on these benchmarks, while delivering competitive accuracy, resulting in up to 76x improvement in test-accuracy-per-training-energy. These results demonstrate that hybrid SNN architectures can effectively handle 224x224 multi-modal medical imaging, establishing them as viable energy-efficient alternatives for clinical applications.","url":"https://doi.org/10.2139/ssrn.6259403","authors":["Garreau Kenza","Brad Niepceron","Emmanuel Bellenger","Filippo Grassia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-22T14:39:02Z","doi":"10.2139/ssrn.6259403","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.21203/rs.3.rs-9519230/v1","name":"L-System Genetic Encoding for Scalable Neural Network Evolution: A Comparison with Direct Matrix Encoding","source":"crossref","abstract":"Abstract An artificial world of barriers and plains scattered with food is used to test the feasibility of using genetic algorithms to optimize hebbian neural networks to perform on problems without apriori knowledge of the problem domain. A formal L-System based genetic alphabet for neural networks, titled Lsys, and a neural network genetic modeling tool titled Wp1hgn are introduced. Lsys and Matrix neural network topology genetic encoding methods are compared across 24 experimental runs. Lsys encoding achieved a mean maximum food count of 3802 ± 197 at generation 1000 across 8 runs with varied parameters, compared to 1388 ± 610 for Matrix encoding, a 2.74x performance advantage with an 8.5-fold improvement in consistency as measured by coefficient of variation (5.2% vs 44.0%). All 8 Lsys populations successfully learned to navigate the environment, while 4 of 8 Matrix populations failed to achieve competitive performance at any point during 1000 generations. When transferred to a novel maze environment, Lsys populations demonstrated immediate robust generalization, achieving a mean maximum food count of 2455 ± 176 compared to 422 ± 212 for Matrix populations, a 5.82x advantage that exceeded the training world performance gap. A MatrixLSG control condition, in which initial populations were generated using Lsys genotypes and then evolved using Matrix operators, demonstrated that the performance advantage of Lsys encoding derives primarily from the genetic algorithm operating on the compressed symbolic Lsys alphabet throughout evolution rather than from initial population structure. Lsys encoding is shown to provide faster convergence, higher peak performance, dramatically greater reliability, and superior generalization to novel environments compared to Matrix encoding across all experimental conditions tested.","url":"https://doi.org/10.21203/rs.3.rs-9519230/v1","authors":["Alexander Stuy","Nodin Weddington"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-27T01:38:46Z","doi":"10.21203/rs.3.rs-9519230/v1","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.56726/irjmets92085","name":"Skin Disease Diagnosis Using Convolutional Neural Network Techniques","source":"crossref","abstract":"","url":"https://doi.org/10.56726/irjmets92085","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-27T10:36:14Z","doi":"10.56726/irjmets92085","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.6545175","name":"Discovering Human Behavioral Transmission Laws in Epidemics via a Physics-Constrained Neural Network","source":"crossref","abstract":"Epidemic transmission is shaped not only by pathogen biology but by adaptive human behavioral responses, yet existing frameworks lack a mathematically explicit, data-derived formulation of this coupling. We introduce a physics-constrained neural network and symbolic regression (PCNN-SR) framework treating epidemic modeling as an inverse problem: recovering the time-varying transmission rate [[EQUATION]] from multimodal surveillance records while enforcing epidemiological consistency. Applied to Swedish COVID-19 data, the framework distills a three-component behavioral law encoding two previously informalized mechanisms: a risk compensation effect, in which rising vaccination coverage proxies pandemic fatigue and NPI relaxation; and a surveillance bias effect, in which testing policy stringency inflates observed transmission estimates independently of viral spread. Digital twin simulations confirm that mobility-only models fail to reproduce the late-stage transmission resurgence occurring when mobility had returned to baseline, while the hybrid law reconstructs multi-wave patterns with high fidelity. This disease-agnostic methodology offers an interpretable and scalable pathway for extracting behavioral transmission laws from heterogeneous public health data.","url":"https://doi.org/10.2139/ssrn.6545175","authors":["Yang Xu","Qing Han","Jude Dzevela Kong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-13T15:43:28Z","doi":"10.2139/ssrn.6545175","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1088/2631-8695/ae5ec7/v2/response1","name":"Author response for \"A Hardware-Efficient Multi-Exit Bayesian Neural Network Accelerator for Speech Classification on FPGA\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/2631-8695/ae5ec7/v2/response1","authors":["haoheng huang","Zilong Liang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-14T21:11:02Z","doi":"10.1088/2631-8695/ae5ec7/v2/response1","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.6635176","name":"A Graph Neural Network Surrogate for Traffic Simulation in Probabilistic Wildfire Evacuation Planning","source":"crossref","abstract":"Agent-based traffic simulation is one of the computational bottleneck in probabilistic wildfire evacuation frameworks that rely on Monte Carlo analysis to populate Bayesian network models. To address this challenge, this paper presents a graph neural network (GNN) based traffic simulator that replaces agent-based counterparts within wildfire egress frameworks such as WiSE (Wildfire Safe Egress). The surrogate operates on a graph representation of the evacuation danger zone, constructed automatically from openly available road network and population data. A two-branch architecture processes static spatial features (distances to destinations and fire) through graph convolutional layers and dynamic vehicle occupancy through a graph convolutional LSTM, predicting next-step node occupancy across the network. The model is trained on a single agent-based simulation scenario from the 2018 Camp Fire in the Paradise-Magalia area of California and validated on a second scenario with a different destination configuration. Results show that the surrogate predicts occupancy dynamics, generates plausible evacuation routes, and produces departure-travel time distributions suitable for Bayesian network calibration. When integrated with WiSE, the surrogate yields a safe evacuation estimate of 15.9%, consistent with the 16% obtained from the agent-based reference, confirming that the surrogate preserves the decision-relevant outputs of the wildfire evacuation framework.","url":"https://doi.org/10.2139/ssrn.6635176","authors":["Mohammad Pishahang","Eduardo Rodriguez","Enrique  Lopez Droguett"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-23T14:52:56Z","doi":"10.2139/ssrn.6635176","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.jhydrol.2026.135403","name":"A physically based neural network for flood routing: The Muskingum-Recurrent neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.jhydrol.2026.135403","authors":["Zhaoxi Li","Tiejian Li","Jian Sun","Jiaye Li","Weidong Li","Jie Zhao","Jiahua Wei"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-03T01:44:16Z","doi":"10.1016/j.jhydrol.2026.135403","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.6985309","name":"NODE LEVEL CAPSULE GRAPH NEURAL NETWORK WITH ARTIFICIAL PROTOZOA OPTIMIZATION APPROACH","source":"crossref","abstract":"Hybrid renewable energy systems (HRES) are frequently employed to combine several energy sources, like the sun, wind, and hydroelectric, to provide reliable power. These systems are essential for optimizing energy distribution and enhancing stability, especially in decentralized grids. However, challenges like handling rapid load changes and maintaining consistent voltage levels remain, requiring further improvements in control strategies. In this, Droop Control-Based Optimization of Hybrid Renewable Energy Systems: Combining Node-Level Capsule Graph Neural Network with Artificial Protozoa Optimizer (DCHRES-NLCGNN-APO) is proposed in this chapter. First, the input information is gathered from the ’Dataset for renewable energy systems’ dataset. After that, a pre-processing section receives the gathered data. The data from the gathered dataset is cleaned and normalized during pre-processing using Data-Adaptive Gaussian Average Filtering (DAGAF). The feature extraction phase receives the pre-processed output for extracting relevant features like time of day, weather conditions, and historical load patterns with the help of Three-Dimensional Quantum Wavelet Transforms (3D-QWT). Finally, for effective energy management, future energy production and consumption are predicted using a Node-Level Capsule Graph Neural Network (NLCGNN). Node-Level Capsule Graph Neural Networks typically don&amp;apos;t use optimization techniques to choose the best parameters to ensure accurate prediction of feature demand. Hence, the Artificial Protozoa Optimizer (APO) is suggested in order to optimize the NLCGNN&amp;apos;s weight parameters, which accurately forecast the future energy need. The suggested DCHRES-NLCGNN-APO Python is used to implement the strategy. Using performance criteria like accuracy, error rate, precision, recall, specificity, and F1-score, the suggested method&amp;apos;s performance is evaluated in comparison to other current approaches such Artificial Neural Network-based Dual Droop Control for Virtual Synchronous Generators in Microgrid Systems (SGDC-ANN), Artificial Rabbits optimized Neural Network-based Energy Management System for Isolated DC Microgrids with PV, Batteries, and Supercapacitors (EMS-ARONN), and Deep Reinforcement Learning-Based Dynamic Droop Control Strategy for Optimal Operation and Frequency Regulation (DDCOFR-DRL).","url":"https://doi.org/10.2139/ssrn.6985309","authors":["Hemalatha G","Nithyashree R","Thirumoorthi P","Harikumar M E"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-23T19:44:22Z","doi":"10.2139/ssrn.6985309","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.31224/5974","name":"Hardware-Efficient Neural Network Implementation: A Power-Accuracy Trade-off Analysis for Quantized Classification Neural Network","source":"crossref","abstract":"This paper presents a comprehensive analysis of power-accuracy trade-offs in quantized neural network implementations for Application-Specific Integrated Circuit (ASIC) design. A three-layer feedforward neural network trained on the Wisconsin Breast Cancer dataset is implemented using a complete design flow from PyTorch model training to ASIC synthesis. The study evaluates 14-bit, 16-bit, and 18-bit uniform post-training quantization schemes and their impact on classification accuracy, power consumption, and area utilization. A lookup table (LUT) based sigmoid activation function is employed to reduce computational complexity in hardware implementation. The design is synthesized using Cadence Stratus High-Level Synthesis (HLS) tool targeting 500 MHz operation frequency on GPDK 45nm technology. Results demonstrate that 18-bit quantization achieves 95.6% accuracy with 2.44 mW power consumption and 183,963 GE (Gate Equivalent) area, representing an optimal balance between computational precision and hardware efficiency. The 16-bit implementation provides a reasonable compromise with 89.4% accuracy, 1.819 mW power, and 162,379 GE area, while the 14-bit version shows significant accuracy degradation to 64.9% despite lower power consumption of 1.924 mW.","url":"https://doi.org/10.31224/5974","authors":["Amogh Anshu N"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-11T17:58:20Z","doi":"10.31224/5974","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.17485/ijst/v19i23.374","name":"AGNN-LB: Adaptive Graph Neural Network Based Load Balancing for Energy Efficient and Congestion Aware Wireless Sensor Networks","source":"crossref","abstract":"Objectives: To propose a novel neural network-based load balancing approach for energy-efficient and congestion-aware routing in large-scale wireless sensor network (WSN) environments. The key objective is to develop intelligent routing that is capable of learning node-level interactions and predicting network load conditions to enhance routing efficiency, traffic fairness, and network lifetime. Methods: The Adaptive Graph Neural Network-Based Load Balancing (AGNN-LB) method treats wireless sensor networks as graphs comprised of sensor nodes and links as vertices (V) and edges (E), respectively. Node attributes such as residual energy, queue length, traffic rate, node degree, transmission delay, congestion level, and link quality are extracted by a graph feature extraction layer. The adaptive graph convolution layers learn the latent spatial correlations among neighboring nodes and encode spatial node embeddings. Subsequently, the dynamic load balancing engine predicts the node loads and re-routes network traffic based on the learned graph embedding. The AGNN-WSN2026 dataset containing 1,000 samples of graph-enabled sensor nodes is utilized for training and evaluating the performance. The proposed AGNN-LB is compared against baseline models such as GW-LBC and DBlock-RLB. The implementation is done using PyTorch for GNN development, NS-3 for network simulation, and Python for performance evaluation and statistical analysis. Findings: The simulation results reveal that AGNN-LB shows an outstanding performance, outperforming baseline models in energy efficiency with 96.8%, 97.4% network lifetime and a load balancing index of 96.5%, whereas it achieves a lower congestion level of 4.2% and end-to-end delay of 18.6 ms under different network environments. Novelty: The model stands as a unique design that combines AGNN with load balancing decision-making for wireless sensor networks (WSNs). Unlike typical clustering and routing schemes, the new design learns the spatial dependency among nodes as well as congestion propagation behavior to facilitate topology-aware, energy-aware, and intelligent traffic distribution for future autonomous WSNs. Keywords: Wireless Sensor Networks, Graph Neural Networks, Load-Balancing Model, Energy Efficiency, Congestion-Aware WSNs","url":"https://doi.org/10.17485/ijst/v19i23.374","authors":["D Maheshwaran","V Saravanan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-08T07:20:02Z","doi":"10.17485/ijst/v19i23.374","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1007/s11227-025-08200-y","name":"Dynamic shortcut connections of deep residual neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11227-025-08200-y","authors":["H. Moayed"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-11T05:26:35Z","doi":"10.1007/s11227-025-08200-y","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.30546/209501.101.2026.3.01.306","name":"Physics-informed neural network modelling of the Schrödinger equation for the Van Der Waals potential","source":"crossref","abstract":"","url":"https://doi.org/10.30546/209501.101.2026.3.01.306","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-04T08:24:16Z","doi":"10.30546/209501.101.2026.3.01.306","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.21203/rs.3.rs-10207639/v1","name":"Error Analysis of Higher Order Integration Schemes in the Context of Neural Network based Modelling","source":"crossref","abstract":"Abstract This work shows that numerical integration schemes, such as the trapezoidal sum, the randomized trapezoidal sum, the composite Simpson's rule and the composite Gaussian quadrature, might not achieve their asymptotic order for practical step widths when applied to neural network functions. A theoretical error analysis is displayed and experiments in the context of learning Euler's elastica as well as approaches to alleviate the phenomena are discussed.","url":"https://doi.org/10.21203/rs.3.rs-10207639/v1","authors":["Felix Mest","Martin Arnold"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-03T09:36:19Z","doi":"10.21203/rs.3.rs-10207639/v1","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.65695/igvfds2924vbyg","name":"IGVFDS2924VBYG","source":"crossref","abstract":"","url":"https://doi.org/10.65695/igvfds2924vbyg","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-07T05:55:36Z","doi":"10.65695/igvfds2924vbyg","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/icrc60800.2023.10386352","name":"Performance comparison of memristor crossbar-based analog and FPGA-based digital weight-memory-less neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icrc60800.2023.10386352","authors":["Chinamu Kawano","Masanori Hashimoto"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-01-15T15:56:12Z","doi":"10.1109/icrc60800.2023.10386352","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.procs.2026.03.376","name":"Design and Implementation of Intelligent Information System Based on Hybrid Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.procs.2026.03.376","authors":["Junhao Su"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-30T07:33:17Z","doi":"10.1016/j.procs.2026.03.376","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.15199/48.2026.07.3","name":"Forest fire detection system using Convolutional Neural Network and MODIS satellite data in Indonesia","source":"crossref","abstract":"","url":"https://doi.org/10.15199/48.2026.07.3","authors":["Sri ROSA"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-31T10:56:11Z","doi":"10.15199/48.2026.07.3","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/cvidl70130.2026.11637676","name":"A Convolutional Neural Network-Based Garbage Classification Method with Overfitting Prevention","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cvidl70130.2026.11637676","authors":["Ruixiang Guan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-17T19:18:35Z","doi":"10.1109/cvidl70130.2026.11637676","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1121/10.0044372","name":"A multi-task neural network for source localization in shallow-water environment with depth classification","source":"crossref","abstract":"Limited high-quality training data can cause overfitting and weak generalization in deep-learning-based source localization, leading to degraded performance in realistic environments. In this study, a multi-task neural network with a depth-classification branch is developed, motivated by the depth resolution of a vertical line array and the depth-dependent structure of the localization ambiguity surface. The depth-classification branch regularizes depth estimation and reduces model complexity, thereby mitigating overfitting in the range-regression branch. Transfer learning from simulations to experiments further improves performance with limited measurements. The developed network yields improved localization performance, as demonstrated using both simulated and experimental data.","url":"https://doi.org/10.1121/10.0044372","authors":["Jing Guo","Juan Zeng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-15T15:43:36Z","doi":"10.1121/10.0044372","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.istruc.2026.112701","name":"Direct fatality-based seismic design of steel moment-resisting frames using artificial neural network models","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.istruc.2026.112701","authors":["Hamed Dadkhah","Mahsa Noruzvand"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-24T16:26:44Z","doi":"10.1016/j.istruc.2026.112701","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1111/coin.70189","name":"<scp>RETRACTION</scp>\n                    : Research on Group Behavior Model Based on Neural Network Computing","source":"crossref","abstract":"RETRACTION : J. Wei , Y. Tian , and J. Geng , “,” Computational Intelligence 38 no. ( 2022 ): 731 – 746 , https://doi.org/10.1111/coin.12403 . The above article, published online on 29 September 2020 in Wiley Online Library ( wileyonlinelibrary.com ) has been retracted by agreement between the journal Editor‐in‐Chief, Diana Inkpen; and Wiley Periodicals LLC. The article was published as part of a guest‐edited issue. Following an investigation by the publisher, all parties have concluded that this article was accepted solely on the basis of a compromised peer review process. The editors have therefore decided to retract the article. The authors have been informed of the retraction.","url":"https://doi.org/10.1111/coin.70189","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-23T11:18:37Z","doi":"10.1111/coin.70189","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1088/2631-8695/ae94fe","name":"Fault diagnosis algorithm for building electrical engineering systems based on BP neural network","source":"crossref","abstract":"Abstract In view of the fact that the traditional diagnosis technology cannot meet the increasingly complex reliability requirements of modern building electrical systems, a fault diagnosis method of building electrical systems based on hyperparameter back propagation neural network (BPNN) is proposed in this study. By constructing a three-layer BPNN model and comparing various parameter configurations in the experiment, the optimal number of hidden layer nodes, learning rate and momentum factor are determined. The results show that the diagnostic accuracy of the optimized model is 90% and 85% on the training set and the test set respectively, and its performance is significantly better than that of the traditional rule diagnosis and expert system in short circuit, open circuit, overload and grounding fault identification. The diagnosis framework constructed in this study effectively reduces the dependence on manual experience and provides technical support for improving the safety and operation level of building electrical systems. The follow-up work will focus on introducing advanced feature extraction technology and online learning mechanism to further improve the comprehensiveness of system diagnosis.","url":"https://doi.org/10.1088/2631-8695/ae94fe","authors":["Hua Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-04T22:58:07Z","doi":"10.1088/2631-8695/ae94fe","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.67535/tsp.000002.003","name":"Graph Neural Network for Context-Aware Cyber Threat Intelligence: A Hybrid Approach","source":"crossref","abstract":"The rapid expansion of Internet of Things (IoT) devices and advanced high-speed data transmission networks has complicated modern cyber attacks to the point that it is now relatively simple for attackers to evade the traditional security controls in place. The current generation of standard Intrusion Detection Systems (IDS) has a significant limitation in that they are based on signatures, which are merely an inventory of all of the previously identified threats to computer systems. Therefore, if there is a new type of attack that has not been previously identified or is a slightly altered version of an existing attack, then the IDS will not detect it, and therefore will provide no alerts to the security personnel. Although it is not a perfect solution, one potential solution that addresses the shortcomings of IDS is Deep Learning. Deep Learning could be considered useful in identifying known attack types using Supervised Learning. However, it is significantly less effective in identifying any kind of a Zero-Day attack. In order to address this limitation, Unsupervised Learning could be applied to identify any distinct activity or pattern within a user’s behavior. However, many Unsupervised Learning techniques are unable to provide sufficient accuracy to accurately distinguish the actual type of attack being detected. Although some Unsupervised Learning techniques may be used to discover statistical anomalies, they typically do not provide specific details regarding the attack. Attention Network (GAT) and an unsupervised Graph AutoEncoder (GAE) into a single architecture, allowing us to benefit from both high-accuracy feature extraction capabilities of the supervised GAT, and the flexibility of the unsupervised GAE. Rather than treating each packet in a network as an independent and unconnected static unit of data, we define the traffic (or stream) across the entire network through temporal connection windows. The GAT serves as the primary means to detect known threats, with an accuracy of 91.24%. The GAE is used to verify the classification of ’normal’ traffic by checking for possible Zero-Day anomalies via reconstruction errors with a threshold set at 0.6. Evaluation results using the UNSW-NB15 dataset demonstrate that this multi-layered framework is more stable and has a higher ability to detect threats than traditional CNN and GCN methods.","url":"https://doi.org/10.67535/tsp.000002.003","authors":["Rubina Khadim","Asma Razaq","Aoun Muhammad","Umar Fayyaz","Sehrish Raza"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-12T17:59:42Z","doi":"10.67535/tsp.000002.003","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1007/978-981-95-8220-4","name":"Intelligent Adaptive Control with System Constraints","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-95-8220-4","authors":["Kapil Sachan","Ahmad Jobran Al-Mahasneh","Sreenatha Anavatti","Radhakant Padhi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-23T11:09:07Z","doi":"10.1007/978-981-95-8220-4","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2523/iptc-25234-ms","name":"Physics-Informed Neural Network for Robust Petrophysical Interpretation with Learnable Physical Parameters","source":"crossref","abstract":"Abstract Accurate estimation of porosity (ϕ), water saturation (SW), and shale volume (VSH) is crucial for quantitative reservoir characterization. Traditional deterministic models, such as Archie's equation and shaly-sand formulations (e.g., Simandoux, Waxman-Smits, and Dual Water models), rely on fixed parameters that are often uncertain, while purely data-driven machine learning models can act as black boxes and lack physical consistency. To address these issues, we introduce a physics-informed neural network (PINN) framework that combines petrophysical constraints with data-driven learning. The model uses a deep feedforward neural network as its core, with physics-based losses derived from Archie's resistivity law and gamma-ray shale volume relationships incorporated into the training process. Formation water resistivity (RW) and the cementation exponent (m) are treated as learnable parameters, allowing for automatic calibration to reservoir-specific conditions. The model is trained on 46,034 standardized well log data points from nine wells, utilizing seven input logs: compressional slowness (DTC), shear slowness (DTS), bulk density (DEN), gamma ray (GR), neutron porosity (NEU), photoelectric factor (PEF), and deep resistivity (RDEP). An independent test set of 11,275 depth samples from four additional wells is used for evaluation. To assess the contribution of the physics-informed formulation, a baseline multilayer perceptron (MLP) with the same architecture but without physics-based constraints was trained for comparison. The baseline MLP achieved R2 values of 0.9702 for ϕ, 0.9863 for Sw, and 0.9802 for VSH. In contrast, the proposed PINN achieved higher R2 values of 0.9825, 0.9911, and 0.9885, respectively, along with consistently lower mean squared errors (MSE) and mean absolute errors (MAE). These results demonstrate that incorporating physics-based constraints improves both predictive accuracy and physical consistency. The model also learns formation-specific parameters, converging to RW = 0.0541 Ω · m and m = 1.2851, enhancing interpretability and adaptability to field-specific conditions. Overall, the findings highlight that physics-informed machine learning effectively bridges the gap between deterministic petrophysical models and black-box neural networks, providing a robust and interpretable framework for reducing uncertainty in reservoir evaluation and supporting more reliable subsurface decision-making.","url":"https://doi.org/10.2523/iptc-25234-ms","authors":["S. Acharya","K. Fabian","K. Westeng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-13T00:04:58Z","doi":"10.2523/iptc-25234-ms","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/tpec67884.2026.11513102","name":"Physics-Informed Neural Network Enhanced SRF-PLL for Grid-Connected Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/tpec67884.2026.11513102","authors":["Varsha Sunkara","Kartik Kashyap","Prabhakaran KK"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-15T19:51:24Z","doi":"10.1109/tpec67884.2026.11513102","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/smartindustrycon68821.2026.11492841","name":"Neural Network Techniques for Radio Signal Prediction in 5G Intelligent Communication Systems","source":"crossref","abstract":"","url":"https://doi.org/10.1109/smartindustrycon68821.2026.11492841","authors":["Behruz Saidov","Daler Anvarzoda","Azamjon Davlatov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-27T19:47:39Z","doi":"10.1109/smartindustrycon68821.2026.11492841","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.inffus.2025.103789","name":"Survey of Neural Network Approaches to Target Tracking with an Emphasis on Interpretability","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.inffus.2025.103789","authors":["Marco Mari","Lauro Snidaro"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-10-01T06:49:19Z","doi":"10.1016/j.inffus.2025.103789","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.mejo.2025.107011","name":"A neural network-optimized broadband RF rectifier with wide dynamic range","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.mejo.2025.107011","authors":["Jialu Wang","Fabin Fan","Xiaofang Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-08T16:19:36Z","doi":"10.1016/j.mejo.2025.107011","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1190/geo-2024-0889","name":"Simultaneous imaging of basement relief and varying susceptibility using trained deep neural network","source":"crossref","abstract":"ABSTRACT Imaging basement relief is challenging, given the unclear distribution of physical properties in the subsurface and the decreasing sensitivity of geophysical data to geometry with the increasing burial depth. Most previous studies using the traditional Tikhonov-regularized inversion approach generally followed the path of inverting only for the geometry model with a known and uniform physical property model, and recent studies have started to invert for basement relief and varying physical property models to improve the accuracy of imaging the basement relief. In this work, a supervised deep-learning-based simultaneous inversion method was proposed to image the basement relief and the magnetic susceptibility variation in the basement rock while using the conceptual prior information, such as the presence of geologic faults, to guide the recoveries. Particularly, the U-net architecture, followed by a fully connected layer, was adopted to map the information of multiscale features from the data and prior-information domains into the inverted-model domains. Because there was no coupling between the basement relief and susceptibility, the network was replicated and trained separately with different emphases to invert for two models separately. The synthetic tests showed that, although the trained network inverting for the susceptibility model was hindered by the low data sensitivity to susceptibility changes, it delineated the trend of the true susceptibility model and sharp boundaries between different sections, whereas the network inverting for the basement depth showed that its inversion result has higher fidelity compared to those from traditional methods. The field-data test over the Illinois Basin showed promising results on the inverted basement depth, whereas the inverted susceptibility models successfully revealed the mafic intrusion that was recorded in previous studies. Our field-data test also found that the assumption of a nonmagnetic sediment rock might be inappropriate when using the deep neural network to recover basement depth.","url":"https://doi.org/10.1190/geo-2024-0889","authors":["Zhuo Liu","Yaoguo Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-25T08:51:06Z","doi":"10.1190/geo-2024-0889","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.37399/2686-9241.2026.1.167-180","name":"Theoretical and Methodological Aspects of Integrating Neural Network Technologies into Forensic Science","source":"crossref","abstract":"Introduction. The issues of using neural network technologies in forensic science are very relevant and discussed. Currently, various scientific projects are being implemented to create neural networks for solving problems of certain types of expertise. However, the availability of a theoretical framework and methodological support are important conditions for the implementation of these developments in practical expert activities. At the same time, there is currently no unambiguous approach to determining the status of an artificial neural network in the methodology of forensic examination, as well as a theoretical justification of the main aspects related to the use of neural network technologies in the production of expertise. Theoretical Basis. Methods. The theoretical basis of the research was the works of leading scientists in the field of forensic science, as well as works reflecting the results of experiments on the use of neural networks in solving expert problems. In the course of the research, general scientific methods of cognition (analysis, synthesis, inductive and deductive method, logical method), and private scientific methods (formal-logical, system-structural, logical-legal) were used. Results. The necessity of developing theoretical framework for the use of artificial neural networks in forensic examination is substantiated. The general theoretical provisions will apply to all types of forensic examinations and serve as the basis for specific methodological provisions. Based on information about the functioning features of neural network technologies, the concept of an artificial neural network is formulated in relation to forensic science. Discussion and Conclusion. The use of neural network technologies in the production of forensic examination should be based on the method of expert research. In the classification of methods according to the degree of generality and subordination, the neural network-based method will refer to special methods of expert research. According to the degree of impact on the object under study, the method under consideration will be non-destructive. Along with the development of new research methods, the use of neural networks for the digitalization and automation of expert techniques can yield positive results.","url":"https://doi.org/10.37399/2686-9241.2026.1.167-180","authors":["Nataliya M. Turkova"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-24T13:18:18Z","doi":"10.37399/2686-9241.2026.1.167-180","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.6731645","name":"Graph Neural Network using Temporal and Spectral Correlations for Underwater Acoustic Event Detection","source":"crossref","abstract":"Acoustic signals measured in underwater environments exhibit complicated and diverse temporal and spectral characteristics and often involve overlapping multiple sources, making accurate acoustic event detection challenging. Most of existing approaches only use temporal information so that they have limitations in effectively capturing both temporal and spectral information of overlapping events. To overcome this limitation, we propose a graph neural network with temporal and spectral correlations (GTSC) for underwater acoustic event detection. The proposed GTSC is composed of a temporal graph and a spectral graph obtained from convolutional features, which are processed by separate tensor-weighted graph convolution. Temporal and spectral adjacency tensors for learning are generated by multiplying class-wise annotation with convolutional features, and an event-based loss function is employed for enhancing class discriminability. To improve detection performance, the GTSC aggregates class-specific features using learnable weight matrices. Experimental results using underwater acoustic datasets demonstrate that the GTSC achieves superior detection performance compared to existing algorithms under various signal-to-interference ratio (SIR) and signal-to-noise ratio (SNR) conditions.","url":"https://doi.org/10.2139/ssrn.6731645","authors":["Kibae Lee","Yoonsang Jeong","Chong Hyun Lee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-07T21:37:25Z","doi":"10.2139/ssrn.6731645","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.21203/rs.3.rs-9384240/v1","name":"Accuracy-Latency Trade-offs Under Neural Network Compression in Safety-Critical Edge AI Applications: A Controlled Simulation Study","source":"crossref","abstract":"Abstract Neural network compression is indispensable for deploying AI on resource-constrained edge hardware across safety-critical domains including healthcare monitoring, prosthetic limb control, educational robotics, and autonomous navigation. Standard compression evaluation relies on overall accuracy on balanced benchmark datasets, which cannot capture the failure modes that determine safety in deployment: sensitivity-specificity divergence in imbalanced clinical classifiers, hard latency deadlines on embedded processors, and cross-seed instability in multi-class controllers. The present study characterises these domain-specific failure modes empirically and introduces evaluation tools and a pre-deployment procedure to address them. We conducted a controlled simulation study on four synthetic domain-representative datasets: clinical fall event detection via 3-axis accelerometry (binary classification, 18% fall prevalence), prosthetic gesture decoding via 4-channel surface electromyography (5 classes), intelligent tutoring system problem-type classification (30 features, 4 classes), and multi-class terrain state classification for legged robotics (200 features, 6 classes including deliberately confusable pairs). Post-training magnitude pruning and structured pruning were applied at six sparsity levels yielding parameter compression ratios (PCR) of 1.4x–9.5x, each condition replicated across five random seeds. Statistical analysis used paired t-tests (df = 4), one-way ANOVA, and 95% confidence intervals. We introduce two evaluation contributions: Youden's J (binary and macro-averaged one-vs-rest) as the primary metric in place of accuracy, and the Hardware-Task Feasibility Analysis (HTFA), a pre-deployment latency screening procedure. A pruning criterion ablation, comparing global magnitude, layer-wise magnitude, and random weight removal, isolates the mechanism underlying magnitude pruning's accuracy preservation. Four findings are reported. First, in clinical fall event detection, magnitude and structured pruning both preserved accuracy to 4.9x PCR with no statistically significant degradation (all p &gt; 0.05 through 4.9x); degradation emerged only at extreme compression (9.5x: 98.7 ± 1.2%, p = 0.098). A class-imbalance ablation confirmed that sensitivity collapse at 9.5x is a sparsity threshold effect, Youden's J drops to 83.5–95.1% at 9.5x regardless of fall prevalence (10% or 18%), not a consequence of class imbalance. Second, in assistive prosthetic control, HTFA identified that Arduino Nano 33 BLE cannot meet the 10ms perceptibility deadline at any compression level because fixed processor overhead (11.0ms) exceeds the deadline independent of model size; projected latency ranges from 26.6ms (uncompressed) to 12.6ms (9.5x PCR), making hardware selection the required intervention. Third, the intelligent tutoring classification task proved highly compressible: magnitude pruning at 4.9x PCR produced non-significant accuracy degradation (1.7pp, p = 0.058), while terrain state classification for legged robotics degraded significantly at the same ratio (3.2pp, 95% CI [0.5, 5.9], p = 0.041). Structured pruning was markedly inferior to magnitude pruning in three of four domains. Fourth, the pruning criterion ablation demonstrated that random weight removal at 4.9x PCR reduces accuracy to 45.0 ± 13.5% versus 94.7 ± 2.3% for magnitude pruning, a 52.9 percentage point gap confirming that weight magnitude ordering, rather than parameter count reduction per se, is the active mechanism of accuracy preservation. Compression behaviour is domain-specific: the same PCR that is safe for intelligent tutoring classification (4.9x, non-significant degradation) is significantly harmful for terrain state classification in legged robotics, and no level of compression is sufficient for assistive prosthetic control on microcontroller hardware without a platform upgrade. Youden's J and HTFA provide practical, implementable alternatives to accurac","url":"https://doi.org/10.21203/rs.3.rs-9384240/v1","authors":["Nikitha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-14T10:29:21Z","doi":"10.21203/rs.3.rs-9384240/v1","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.21203/rs.3.rs-10646614/v1","name":"Factorial Benchmarking of Exact and Finite-Shot Gradient Resolvability in a Four-Qubit Hybrid Quantum Neural Network","source":"crossref","abstract":"Abstract Gradient resolvability in quantum neural networks can depend simultaneously on circuit structure, objective construction, and finite-shot measurement, yet these interventions are usually benchmarked separately. We use a complete 2³ factorial design to test interactions among a pair-restricted controlled-NOT (CNOT) schedule (E), normalized transverse-field Ising model (TFIM) energy objective (L), and fixed residual shortcut (R) in a four-qubit measure–re-encode–reset hybrid quantum neural network. Across 50 matched initialization clusters and 30 finite-shot replicates per scientific cell, configurations were matched by block count, parameter identity, and total implemented simulator-shot budget. The centered E × L interaction in exact-gradient magnitude was positive and was supported by both mixed-model inference and an initialization-cluster bootstrap; the positive direction was retained in an independent-seed dataset, although its magnitude and depth profile remained uncertain. Finite-shot E × L and E × R interactions met the protocol-derived Wald/Holm rule, but their 1,000-fit nested-bootstrap intervals included zero, and the residual result was estimator-mode sensitive and inactive at D = 1, 2. The L × R-by-depth interaction remained unresolved. These results show that factorial benchmarking can expose composition effects that marginal comparisons miss while separating exact-gradient signal from finite-shot estimator behavior. They do not establish optimization success, hardware advantage, shot savings, or matched physical-resource cost.","url":"https://doi.org/10.21203/rs.3.rs-10646614/v1","authors":["Brandon Shen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-11T11:31:02Z","doi":"10.21203/rs.3.rs-10646614/v1","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.7250399","name":"Learning the Propagation of Policy Shocks in Global Food Trade: A Graph Neural Network Disciplined by Spatial Equilibrium","source":"crossref","abstract":"Export restrictions in staple food markets raise prices far beyond the countries that impose them, yet the incidence of that transmission across the trade network, and the welfare it shifts between developing and developed economies, is hard to measure. This study couples a structural spatial-equilibrium model of the food-trade network with a graph neural network trained to emulate its shock-propagation operator. The panel spans eighteen agricultural commodities from 2008 to 2022; the structural core, an Anderson and van Wincoop multilateral-resistance system calibrated to six core staples, maps a restriction at any origin to the price response at every destination. A graph attention network reproduces this operator out of sample, with a mean coefficient of determination of 0.6496. From it the study derives Systemic Food-Trade Transmission Centrality, ranking origins by the welfare-weighted price pressure of their restrictions. Without being given trade volumes, it identifies Russia for wheat, India for rice, Ukraine for maize, Brazil for soybean and sugar, and Indonesia for palm oil. Welfare losses fall more heavily on developing importers, which bear 1.9456 times the incidence of developed importers, rising to 3.1265 times in rice. A 2022 validation confirms that the model predicts supply reallocation away from the restricting bloc.","url":"https://doi.org/10.2139/ssrn.7250399","authors":["Ayodele Idowu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-13T10:45:26Z","doi":"10.2139/ssrn.7250399","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1007/s11432-016-0555-2","name":"Fixed-time synchronization of delayed memristor-based recurrent neural networks","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11432-016-0555-2","authors":["Jinde Cao","Ruoxia Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2017-01-26T01:43:46Z","doi":"10.1007/s11432-016-0555-2","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1088/0954-898x_6_3_001","name":"Modelling transpositional invariancy of melody recognition with an attractor neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_6_3_001","authors":["Lubica Beňušková"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:31Z","doi":"10.1088/0954-898x_6_3_001","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/inforino68543.2026.11556871","name":"Neural Network-Based Multitarget Radar Data Association Model for Education","source":"crossref","abstract":"","url":"https://doi.org/10.1109/inforino68543.2026.11556871","authors":["O.N. Marchuk","V.A. Loginov"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-12T19:41:19Z","doi":"10.1109/inforino68543.2026.11556871","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/asens69964.2026.11605262","name":"Research on Big Data Mining Methods Based on Graph Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/asens69964.2026.11605262","authors":["Qianhui Shen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-21T19:08:30Z","doi":"10.1109/asens69964.2026.11605262","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.procs.2026.07.316","name":"Deformation prediction of deep foundation pit support based on BP neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.procs.2026.07.316","authors":["Jianming Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-20T11:23:50Z","doi":"10.1016/j.procs.2026.07.316","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1039/d6tc00569a/v1/review2","name":"Review for \"Integrated Digital and Analog Resistive Switching in a Bis-Indolyl Derivative-Based Memristor for Artificial Synaptic Applications\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d6tc00569a/v1/review2","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-16T21:36:14Z","doi":"10.1039/d6tc00569a/v1/review2","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/wccst67302.2026.11496262","name":"Image-Based Obfuscated Malware Detection Using Lightweight Binarized Neural Network Architecture","source":"crossref","abstract":"","url":"https://doi.org/10.1109/wccst67302.2026.11496262","authors":["Khushboo Das","Dhruba Kumar Bhattacharyya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-05T19:59:50Z","doi":"10.1109/wccst67302.2026.11496262","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.13164/re.2026.0105","name":"A Neural Network-Enabled OTFS-PAPR Reduction with Low Computational Complexity","source":"crossref","abstract":"","url":"https://doi.org/10.13164/re.2026.0105","authors":["M. I. Al-Rayif","E. E. Eldukhri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-28T06:37:35Z","doi":"10.13164/re.2026.0105","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1504/ijbm.2026.10073155","name":"Rapid recognition of multimodal emotion based on graph convolutional neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1504/ijbm.2026.10073155","authors":["Tan Liu","Qiqun Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-29T13:02:14Z","doi":"10.1504/ijbm.2026.10073155","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1088/0954-898x_10_1_002","name":"Sparsification from dilute connectivity in a neural network model of memory","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_10_1_002","authors":["Miguel Maravall"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T16:03:49Z","doi":"10.1088/0954-898x_10_1_002","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.neunet.2025.108269","name":"A systematic literature review of spatio-temporal graph neural network models for time series forecasting and classification","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2025.108269","authors":["Flavio Corradini","Flavio Gerosa","Marco Gori","Carlo Lucheroni","Marco Piangerelli","Martina Zannotti"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-03T20:27:38Z","doi":"10.1016/j.neunet.2025.108269","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.7717/peerj-cs.2232/fig-10","name":"Figure 10: Distribution of neural network architectures based on the pathology analyzed by the different types of neural network architectures.","source":"crossref","abstract":"","url":"https://doi.org/10.7717/peerj-cs.2232/fig-10","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-10-21T04:07:31Z","doi":"10.7717/peerj-cs.2232/fig-10","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.59324/ejsmt.2026.2(3).08","name":"Neural Network-Based Classification of Skin Diseases  with Deep Learning","source":"crossref","abstract":"Millions of individuals all over the world have skin diseases and their adequate and timely diagnosis is inescapable in the treatment process. The paper explains a revolutionary approach to automated classification of skin diseases that uses the deep learning and the neural networks as instruments to enhance the accuracy of the classification. The shortcomings of the traditional approaches to the diagnosis are overcome by the suggested system which makes use of the opportunities of the neural networks to determine the complicated patterns of the dermatological images. The implication of our methodology is to acquire a great amount of information regarding the photo images of the various skin conditions on the reliable sources. These pictures are efficiently processed in order to normalize the format and eliminate noises and advanced feature extraction algorithms are deployed in order to obtain relevant data. The system is comprised of the core of the properly designed deep neural network, a deep neural network architecture, specifically formulated to operate on skin diseases. The model is trained using the preprocessed data and this will optimally maximize the model performance in terms of the accuracy of classification of skin conditions of different types. It functions on the basis of the advanced deep learning and the work of the system is evaluated critically with the aid of the test dataset. These are the measures of the efficacy of the model, they are accuracy, precision, recall, and F1-score. The research may be applied in the design of the automated dermatological diagnosis since it can demonstrate that deep learning may revolutionize the field of skin diseases classification. The conclusion also underlines the significance of the presented system and the research directions in the future which would assist in improving the system and enhancing its functionality.","url":"https://doi.org/10.59324/ejsmt.2026.2(3).08","authors":["Ahmed Qusay Jawad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-02T06:59:12Z","doi":"10.59324/ejsmt.2026.2(3).08","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1201/9781003761969-14","name":"Joint stiffness estimation of body structure using neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003761969-14","authors":["A. Okabe","N. Tomioka"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-27T09:05:51Z","doi":"10.1201/9781003761969-14","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/nnice68970.2026.11465287","name":"Multi-Channel Dynamic Convolutional Network for Knowledge Graph Completion","source":"crossref","abstract":"","url":"https://doi.org/10.1109/nnice68970.2026.11465287","authors":["Yanni Feng","Haitao Yu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-07T19:54:56Z","doi":"10.1109/nnice68970.2026.11465287","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.26434/chemrxiv.15001313/v1","name":"Benchmarking Ice-Water Equilibria Exhibited by Foundation Neural Network Potentials","source":"crossref","abstract":"Herein we report the melting points of ice exhibited by some recently published foundation Neural Network Potentials (NNPs) using the direct coexistence method: SO3LR, Orb v3, MACE-MP and Fennix-Bio1, as well as the first generation model ANI-2x. Using our previously published LICH-TEST algorithm, we classify the structural motifs adopted by individual molecules over time, finding that most models correctly exhibit ice growth and shrinkage via interfacial hexagonal structures. However, the observed melting temperatures vary from the experimental value significantly, with the lowest and highest nearly 130 K apart. The growth rates of ice below the melting points were also found to vary significantly, in some cases exceeding classical water models by one decade. SO3LR was the only NNP exhibiting an accurate value, and represents the best trade-off of speed and accuracy for the simulation of ice nucleation in (bio)organic systems. Disconcertingly the MACE, Orb and ANI models overestimate the melting point to such a degree that liquid water is effectively under deep supercooling when simulated at standard conditions. By comparing variants of the latter two potentials, we infer that an accurate description of dispersion interactions during training and/or evaluation improves the water density isobar and leads to slightly better melting temperatures, albeit with a substantial speed penalty when added during inference. We conclude with some general recommendations for training the next generation of foundation models, in order to improve their description of ice-water interactions.","url":"https://doi.org/10.26434/chemrxiv.15001313/v1","authors":["Rasmus Nilsson","Golnaz Roudsari","Mária Lbadaoui-Darvas","Bernhard Reischl","Stephen Ingram"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-27T05:53:51Z","doi":"10.26434/chemrxiv.15001313/v1","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.20944/preprints202601.2166.v1","name":"Exploration of Asymmetric Relationships in Graph Neural Network Topology","source":"crossref","abstract":"As an information extraction framework, graph neural network has been widely used in many fields, but there is a serious problem of over-smoothing in graph neural network, that is, with the increase of the number of iterations, the nodes gradually tending toward similarity, resulting in reduced feature distinguishability and deteriorated model performance. In order to solve this problem, this paper proposes a novel solution, that is, to alleviate the over-smoothing problem in graph neural networks from the perspective of changing the topological information dimension. This article uses graph regularization to solve this problem, by fine-tuning the topology structure, the research objectives can be achieved, and demonstrated through extensive ablation experiments, a large number of experiments verify the effectiveness and feasibility of the proposed method. Physically speaking, this method limits the connection strength of the adjacency matrix to a finite number of steps; The higher the order, the more obvious the restriction effect, therefore, it can alleviate the problem of over smoothing in graph neural networks to a certain extent.","url":"https://doi.org/10.20944/preprints202601.2166.v1","authors":["Lin Ma","Wenjun Wang","Jun Wang","Zhitao Ma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-29T02:47:09Z","doi":"10.20944/preprints202601.2166.v1","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.6926201","name":"Horizontal Gasliquid Swirling Flow Regime Identification Based on Attention Mechanism and Multi-scale Convolutional Neural Network","source":"crossref","abstract":"Real-time identification of gasliquid two-phase flow regimes is essential for maintaining the safety and stability of industrial processes, including chemical production, petroleum transportation, and energy systems. However, swirling flow regimes characterized by complex structures and strong dynamic behavior, present significant challenges for flow regime identification and intelligent control. Most existing methods rely on handcrafted feature extraction, which introduces subjectivity and limits real-time performance, rendering them unsuitable for deployment in resource-constrained industrial environments. To overcome these limitations, this paper proposes a lightweight convolutional neural network that combines a multi-scale convolutional architecture with an attention mechanism to enhance hierarchical feature extraction. The proposed model achieves a recognition accuracy of 99.26% on a self-constructed swirling flow image dataset, with an average inference time of 1.37 milliseconds and only 0.84 million parameters—significantly fewer than those of mainstream deep learning models. It achieves a favorable balance between recognition accuracy and deployment efficiency. Unlike previous studies that focused solely on identification performance, this work extends the evaluation framework to include key deployment metrics such as floating-point operations, parameter size, and inference latency. This systematic evaluation demonstrates the feasibility of achieving performance gains through structural optimization under lightweight constraints. This study offers new insights into the efficient identification of complex gasliquid swirling flow regimes and exhibits promising potential for intelligent monitoring and edge deployment in industrial applications.","url":"https://doi.org/10.2139/ssrn.6926201","authors":["wen liu","jiayu li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-12T14:46:09Z","doi":"10.2139/ssrn.6926201","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1088/0954-898x/6/3/004","name":"Learning internal representations in an attractor neural network with analogue neurons","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x/6/3/004","authors":["Daniel Amit†","Nicolas Brunel"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2002-08-25T02:35:54Z","doi":"10.1088/0954-898x/6/3/004","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.6177789","name":"GraphMux: A Graph Neural Network Framework for Encrypted Traffic Classification","source":"crossref","abstract":"The growing dominance of encrypted network traffic and new encrypted algorithms (TLS 1.3, QUIC, DoH) poses significant challenges for reliable network classification, particularly as many existing approaches rely on text or image-based representations, which struggle to capture the inherent structural relationships present in network communication—relationships that can naturally be modeled as graphs. In this work, we introduce GraphMux, a GNN-based framework that leverages line graph transformations to fuse multiple graph views into a unified representation. We also present three graph-based flow representations (TIG+Chain, StarBurst, and 2Chain) designed to capture temporal burst dynamics and client–server interaction patterns using only packet time, direction, and length information, without incorporating any unencrypted statistical features.We evaluate our approach on several datasets: two academic datasets (UTMobileNetTraffic2021 and QUIC PCAP) and a commercial dataset (Flash), using four Graph Neural Network architectures. Across all datasets, GraphMux consistently achieves the strongest performance, and the proposed graph constructions frequently produce the leading results. Additional experiments examining attribute-selection strategies reveal a clear positive correlation between well-aligned feature assignments and classification accuracy, underscoring the importance of principled attribute design when constructing graph representations for encrypted traffic.","url":"https://doi.org/10.2139/ssrn.6177789","authors":["Matan Klein","Revital Marbel","Chen Hajaj","Ran Dubin","Amit Dvir"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-04T16:38:42Z","doi":"10.2139/ssrn.6177789","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.20944/preprints202603.1920.v1","name":"Water and Gas Flooding Oil Monitored by a Realtime Unet-Neural-Network-Based Method","source":"crossref","abstract":"To achieve real-time and accurate detections of residual oil distribution during water or CO₂ flooding, this study utilizes the high-frequency Ground Penetrating Radar (GPR) for monitoring of the flooding process in real time. The U-Net neural networks are trained to invert for the subsurface dielectric constants and conductivity distributions. The study first utilizes the gprMax forward tool to simulate the dynamic response changes of rock electrical parameters during flooding and constructs a high-resolution training dataset of 100,000 samples. Each sample contains the relationships between a subsurface electrical parameter model and its corresponding multi-transmitter, multi-receiver GPR responses. A deep learning inversion network based on the U-Net architecture is trained to extract multi-scale features through an encoder-decoder structure, achieving an end-to-end mapping from GPR echo signals to subsurface electrical parameters. Numerical and physical core experimental results show that the method accurately inverts the electrical parameter distributions of the oil, water, and gas in the sandstone model, successfully capturing the position and morphology changes of the displacement front. The average relative error of dielectric constant inversion is controlled within 5%, with the error mainly concentrated in high-conductivity water regions for conductivity inversion results. Compared to traditional full waveform inversion methods, the proposed approach offers a fast inversion solution and is less affected by the initial model and noise. The results reveal the feasibility and superiority of the neural network based deep learning method in GPR electromagnetic inversion, providing a new method for real-time flooding monitoring and intelligent reservoir development during oil and gas flooding.","url":"https://doi.org/10.20944/preprints202603.1920.v1","authors":["Jie Zhang","Maolei Cui","Rui Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-25T06:03:14Z","doi":"10.20944/preprints202603.1920.v1","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1007/s00521-026-12388-2","name":"Deep neural network for glaucoma detection using contact lens sensor data","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-026-12388-2","authors":["Paweł Pietrzak","Hubert Świerczyński","Szymon Szczęsny","Cezary Mazurek","Juliusz Pukacki","Robert Wasilewicz"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-06T09:42:54Z","doi":"10.1007/s00521-026-12388-2","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.26434/chemrxiv.15005553/v1","name":"Quantitative Pathway-Resolved Kinetics from Neural Network-Guided Weighted Ensemble Simulations","source":"crossref","abstract":"Many crucial biomolecular processes, such as ligand dissociation and conformational switching, occur via multiple competing transition pathways. While standard rare-event sampling methodologies provide rigorous estimates of the global transition rate, they typically collapse the underlying mechanistic heterogeneity into a single global constant, obscuring the relative kinetic contributions of distinct channels. Here, we introduce a path-resolved weighted ensemble (WE) framework that quantitatively assigns steady- state flux to competing transition channels without modifying the underlying unbiased dynamics. In our approach, initial reactive trajectories generated via direction-guided adaptive sampling are clustered by dynamic time warping (DTW) and smoothed into neural-network-refined representative paths. These refined routes are formulated as path collective variables (PathCVs) to pre-seed and guide channel-specific WE simulations. We demonstrate the robustness of this framework across systems of increasing complexity. On a model three-hole potential, the method accurately captures a temperature-dependent pathway crossover. In the benzamidine-trypsin complex, it isolates the dominant unbinding route while quantifying the fluxes of subdominant channels. Finally, for imatinib dissociation from Abl kinase, the method reveals that the clinically relevant N368S resistance mutation drastically redistributes reactive flux from the P-loop/hinge channel toward the αC-helix channel, accelerating escape. This framework successfully translates qualitative pathway classification into rigorous, pathway-specific kinetic observables, offering a powerful tool for understanding mutation-induced mechanistic","url":"https://doi.org/10.26434/chemrxiv.15005553/v1","authors":["Dibyendu Maity","Shaheerah Shahid","Sayari Bhattacharya","Rupak Majumdar","Suman Chakrabarty"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-02T10:45:57Z","doi":"10.26434/chemrxiv.15005553/v1","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.7100538","name":"Physics Informed Neural Network Model for Flow around Encapsulated Phase Change Materials","source":"crossref","abstract":"In this work, we present a simple physics informed neural network framework for coupled flow and heat transfer around encapsulated phase change materials. The heat transfer fluid region is solved by using the continuity, momentum, and energy equations as constraints in the neural network loss function. The phase change process is represented in a simplified way by keeping the capsule surface at the melting temperature and estimating the melting time from a lumped latent heat balance. No computational fluid dynamics or experimental field data are used during training. The model is tested for single and paired circular capsules in a two-dimensional channel. The predicted fields show the expected wake region behind the capsules, symmetry of the flow, cooling of the fluid near the capsule surface, and changes in flow passage caused by capsule spacing. The wall temperature gradients obtained from the model are used to estimate melting time and volume based energy storage rate. The study shows that the method can be used as an exploratory tool for preliminary analysis of phase change material systems.","url":"https://doi.org/10.2139/ssrn.7100538","authors":["Subhasish Das","Manish Agrawal","Prasenjit Rath","Anirban Bhattacharya"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-11T15:41:32Z","doi":"10.2139/ssrn.7100538","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.64898/2026.04.07.717084","name":"A Hierarchical Spatial Graph Neural Network Resolves Immunogenic and Tolerogenic Tertiary Lymphoid Structures in Renal Cell Carcinoma","source":"crossref","abstract":"Abstract Tertiary lymphoid structures (TLS) in the tumour microenvironment span a functional spectrum from immunogenic — driving germinal centre reactions and anti-tumour immunity — to tolerogenic, harbouring regulatory T cells and suppressive myeloid populations. Distinguishing these states is clinically critical: immunogenic TLS predict ICI response whereas tolerogenic TLS may promote immune evasion. Bulk transcriptomics conflates productive TLS with exhausted immune infiltrates, masking this distinction. We present a hierarchical graph neural network (GNN) that operates directly on 10x Visium spatial transcriptomics graphs to classify TLS functional state at the cluster level. Using a three-scale architecture combining graph attention (GAT) and differentiable pooling (DiffPool), the model hierarchically aggregates spot-level signals into niche- and region-level representations before predicting immunogenic versus tolerogenic state. Trained on 915 TLS clusters from 24 renal cell carcinoma (RCC) Visium samples (GSE175540), the model achieves a validation AUC-ROC of 0.718 and a clinical AUC of 0.908 on IgG-validated samples from the BIONIKK cohort. Zero-shot transfer to an independent multi-cancer Visium cohort (GSE203612; breast, liver, ovarian, pancreatic, uterine) correctly identifies hepatocellular carcinoma as harbouring the most tolerogenic TLS, consistent with the known immunosuppressive liver tumour microenvironment. Spatial decomposition of CXCL13 across TLS and non-TLS compartments reveals that 85% of tissue CXCL13 signal originates from non-TLS parenchyma, where it co-expresses primarily with exhaustion markers (mean Spearman rho = 0.233) rather than Tfh markers (CXCR5 rho = 0.039) — a pattern consistent with the paradoxical association of bulk CXCL13 with worse overall survival in TCGA-KIRC (HR = 1.38, p &lt; 0.001). Code and processed data are deposited at GitHub and Zenodo.","url":"https://doi.org/10.64898/2026.04.07.717084","authors":["Gavin Peng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-09T07:55:17Z","doi":"10.64898/2026.04.07.717084","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.6830313","name":"A Double-Head Physics-Informed Neural Network with RGB Consistency for Stable Training","source":"crossref","abstract":"Physics-Informed Neural Networks (PINNs) offer a framework for solving partial differential equations without labeled datasets by embedding governing equations into the loss function. However, their performance deteriorates as problem complexity and spatiotemporal dimensionality increases because of training instability, spectral bias, and optimization difficulty. To address this, we propose an RGB-Consistency PINN framework that learns a physical scalar field together with its RGB representation as an auxiliary output. The model employs a double-head architecture with a physics head and a visual head and combines a differentiable lookup-table (LUT)-based mapping with a stop-gradient strategy to preserve physics-constrained learning while introducing structural regularization. We evaluated the method on four benchmark problems: 2D lid-driven cavity flow, 2D Burgers’ equation, 2D heat transfer, and 3D heat transfer. For relatively simple two-dimensional problems, improvements in global mean error metrics are limited, but the method consistently improves the reconstruction of characteristic local structures such as centerline profiles, recirculation regions, and localized bumps. Its advantages become more pronounced in diffusion-dominated problems, where it yields more stable temperature-field evolution, gradient-energy decay, and root-mean-square-error (RMSE) behavior. In the 3D heat-transfer case, the method more accurately reproduces the initial Gaussian thermal structure and more faithfully captures the diffusive behavior of the reference solution in terms of variance and standard deviation; in particular, variance-trajectory tracking accuracy improves from 65.21% to 92.24% in the early-time interval. These results indicate that RGB-based auxiliary learning acts as an effective regularization strategy for improving training stability and global physical-behavior reconstruction in complex and high-dimensional PDE problems.","url":"https://doi.org/10.2139/ssrn.6830313","authors":["Byeonggyu Jeon","Shin Hyuk Kim","Yongha Park"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-26T05:39:37Z","doi":"10.2139/ssrn.6830313","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.7199665","name":"EGNN‑DEM: an approach combining equivariant graph neural network (EGNN) with DEM for particle breakage simulation","source":"crossref","abstract":"Particle breakage is widespread in nature and engineering settings. Accurately simulating particle breakage behavior is therefore of great importance. Existing discrete element method (DEM) breakage models, such as particle replacement and bonded particle clusters, often struggle to balance computational efficiency and realistic fragmentation. This study proposes a particle breakage model, termed EGNN‑DEM, that combines an equivariant graph neural network (EGNN) with DEM. The model takes the geometry, external force distribution, and topological relationships of a particle at the peak stress moment as input. It predicts edge fracture probabilities and performs post-processing to obtain breakage fragments. Training data are generated from DEM simulations of single particle breakage. The model adopts a scalar-vector dual-channel equivariant message passing architecture. It retains external force directions as three-dimensional vectors, ensuring rotational equivariance. Meanwhile, physically inspired features such as force flow potential and betweenness are introduced to compensate for the information loss caused by missing contact forces. Triaxial compression test simulations of sandy gravel verify that the model can reproduce the macroscopic mechanical response and breakage characteristics. The prediction time for a single particle is within seconds, striking a balance between accuracy and efficiency. This study provides a new data‑driven paradigm for particle breakage simulation in DEM.Particle breakage is widespread in nature and engineering settings. Accurately simulating particle breakage behavior is therefore of great importance. Existing discrete element method (DEM) breakage models, such as particle replacement and bonded particle clusters, often struggle to balance computational efficiency and realistic fragmentation. This study proposes a particle breakage model, termed EGNN‑DEM, that combines an equivariant graph neural network (EGNN) with DEM. The model takes the geometry, external force distribution, and topological relationships of a particle at the peak stress moment as input. It predicts edge fracture probabilities and performs post-processing to obtain breakage fragments. Training data are generated from DEM simulations of single particle breakage. The model adopts a scalar-vector dual-channel equivariant message passing architecture. It retains external force directions as three-dimensional vectors, ensuring rotational equivariance. Meanwhile, physically inspired features such as force flow potential and betweenness are introduced to compensate for the information loss caused by missing contact forces. Triaxial compression test simulations of sandy gravel verify that the model can reproduce the macroscopic mechanical response and breakage characteristics. The prediction time for a single particle is within seconds, striking a balance between accuracy and efficiency. This study provides a new data‑driven paradigm for particle breakage simulation in DEM.","url":"https://doi.org/10.2139/ssrn.7199665","authors":["Deze Yang","Xihua Chu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-29T03:37:56Z","doi":"10.2139/ssrn.7199665","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.7243278","name":"Neural Network-Based Generation of Three-Dimensional Structured Elliptic Grids","source":"crossref","abstract":"To address the limitations of traditional elliptic grid generation methods, a neural network-based framework for elliptic grid generation has been proposed. However, its applicability to three-dimensional problems remains unexplored. In this work, the framework is extended to three-dimensional surface and volumetric grid generation. The governing equations are reformulated in a form directly defined on the physical domain, where the domain corresponds to the solid region for volumetric grids and to the associated parametric domain for surface grids. A neural network is employed to solve the resulting elliptic equations subject to prescribed boundary conditions, thereby enabling the generation of structured grids for both surface and volumetric geometries. Numerical results demonstrate that the proposed method is feasible and robust in three-dimensional models and is capable of generating high-quality structured grids.","url":"https://doi.org/10.2139/ssrn.7243278","authors":["Huaijun Yue","Zaiyou Yang","Q Song","Ning Wei","Qiang Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-06T15:41:49Z","doi":"10.2139/ssrn.7243278","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.7716/aem.v15i3.3519","name":"Music Learning Path Optimization System Integrating Graph Neural Network","source":"crossref","abstract":"Traditional music learning path recommendation systems often fail to model multidimensional correlations within knowledge structures, resulting in incomplete path coverage and limited adaptability. This study proposes a learning path optimization system integrating GraphSAGE and Dueling DQN. A heterogeneous music knowledge graph is first constructed to represent knowledge points, skills, styles, and their prerequisite or coupling relationships. GraphSAGE with an LSTM aggregator is then used to dynamically fuse multimodal features into unified node embeddings. On this basis, the Dueling DQN algorithm uses cognitive state vectors, including mastery level and cognitive load, to optimize path strategies under coverage-gain and load-penalty constraints. Experiments show that the recommended paths achieve 89.6% knowledge coverage with an average length of 12.4 steps for beginners. Compared with standard DQN, Dueling DQN improves coverage by 3.3%. The system increases the path completion rate of beginners to 94.2%, outperforming traditional models such as DySAT, and achieves an average ABRSM score of 128.3. By combining heterogeneous graph modeling with reinforcement learning, the proposed framework improves path coverage, reduces route redundancy, and may provide methodological reference for graph-based optimization in electromagnetic-system training and wireless network planning.","url":"https://doi.org/10.7716/aem.v15i3.3519","authors":["D. N. Zhao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-14T08:42:51Z","doi":"10.7716/aem.v15i3.3519","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.26434/chemrxiv.10001947/v2","name":"More accurate and reproducible glass transition temperature calculation with unsupervised machine learning and neural network charges","source":"crossref","abstract":"Accurate computational modeling of the glass transition is a longstanding challenge in polymer chemistry. Atomistic molecular dynamics simulations offer a powerful approach to observe the changes in viscoelasticity, density and chain mobility associated with the glass transition, yet they often overestimate the glass transition temperature (T g ) and have limited sensitivity to number average molecular weight and dispersity. These deficiencies are largely attributed to high levels of noise in simulation data masking the T g , inaccurate polymer representations, and limited force field transferability. In this study, we build a robust and automated workflow to calculate T g using unsupervised machine learning, and apply it to a range of polymer models and dispersities. We show that our workflow provides improved T g estimates when compared to other established, 'bulk' measurements (e.g., monitoring changes in RMSD or density). We also benchmark different neural network charge models, which streamline polymer force field parameterization, and assess their influence on the T g .","url":"https://doi.org/10.26434/chemrxiv.10001947/v2","authors":["Hannah N Turney","Micaela Matta"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-17T06:22:21Z","doi":"10.26434/chemrxiv.10001947/v2","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.6651938","name":"Integrating RBF Neural Network Forecasts into Hamilton-Jacobi-Bellman Portfolio Optimization: A Comparative Study with Monte Carlo Simulations","source":"crossref","abstract":"This study examines how alternative scenario-generated methods affect Hamilton-Jacobi-Bellman portfolio optimization using real return data from publicly listed shipping companies. We compare two input-generation approaches: Radial Basis Function Neural Network forecasts and Monte Carlo simulations calibrated on the same historical return series. Both are embedded in an identical HJB framework to derive optimal dynamic portfolio weights. The resulting strategies are evaluated out of sample using forecast accuracy, Sharpe ratio, terminal wealth, realized utility, and maximum drawdown. By linking machine-learning forecasts and simulation-based scenarios to dynamic portfolio choice, the paper provides an empirical framework for assessing data-driven asset allocation in shipping equity markets.","url":"https://doi.org/10.2139/ssrn.6651938","authors":["Alexander Vassilev"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-26T10:44:02Z","doi":"10.2139/ssrn.6651938","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.6537487","name":"Dynamic Routing in Ring-Circulant NoCs Using a Modified Hopfield Neural Network","source":"crossref","abstract":"Efficient and reliable routing remains a fundamental challenge in Networks‐on‐Chip (NoCs), especially under dynamic traffic patterns and time‐varying link conditions that degrade performance and scalability. Although ring‐circulant topologies offer desirable structural regularity and short average path lengths, existing routing schemes often fail to fully exploit their potential due to limited adaptability and insufficient optimization capabilities. To address these limitations, this paper proposes a dynamic routing algorithm for ring‐circulant NoCs based on a modified Hopfield neural network. The method formulates path selection as an energy‐minimization problem, enabling the network to converge toward low‐cost routes while incorporating real‐time link variations. The algorithm is implemented and evaluated through simulation using multiple workloads and traffic scenarios to ensure generality. The results demonstrate that the proposed neural optimization‐based routing significantly improves throughput and reduces latency compared with conventional clockwise and adaptive routing schemes, particularly under congested or irregular traffic conditions. These findings highlight the suitability of Hopfield‐based optimization as an effective and lightweight mechanism for real‐time routing in ring‐circulant NoCs and indicate its potential for deployment in future scalable on‐chip interconnect architectures.","url":"https://doi.org/10.2139/ssrn.6537487","authors":["Ali Rezaipour","Mona Moradi","Razieh Farazkish","Nasrin Amiri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-07T17:42:41Z","doi":"10.2139/ssrn.6537487","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.7177748","name":"Automated AFGL Quantum Number Assignment for CO2 Isotopologues using a Graph Neural Network","source":"crossref","abstract":"Accurate quantum number assignment for calculated molecular energy levels is a critical bottleneck in generating line broadening parameters for comprehensive line lists for radiative transfer applications. We present an automated pipeline for assigning Air Force Geophysics Laboratory (AFGL) quantum numbers to CO$_2$ calculated rovibrational states lying below 15000 \\cm\\ across all 12 stable isotopologues. A GraphSAGE graph neural network is trained transductively on empirical (\\textsc{MARVEL}) energy levels, exploiting inter-isotopologue perturbation chains and intra-isotopologue rotational ladder edges to propagate assignment information to unlabelled calculated states. Physical uniqueness is enforced locally by a Hungarian algorithm solver operating within groups of states sharing the same polyad, rotational quantum number, and parity. A five-generation bootstrap loop iteratively promotes high-confidence predictions into the training set, expanding coverage without additional labelling effort. The pipeline assigns 244~001 previously unlabelled states over 12 isotopologues, accounting for 11.44~\\% of all available states, with coverage now increased to 97.4~\\% below 5~000~cm$^{-1}$. The pipeline includes a novel decision tree method for converting AFGL to Herzberg notation in asymmetric isotopologues, while the architecture and Hungarian uniqueness enforcement are applicable beyond CO$_2$: any molecular system with a conserved polyad-like quantum number and a large body of unlabelled computed states is a natural target for this approach, suggesting a pathway toward automated quantum number annotation for the next generation of large-scale computed line lists.","url":"https://doi.org/10.2139/ssrn.7177748","authors":["Marco Barnfield","Sergei  N. Yurchenko","Jonathan Tennyson"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-25T02:38:16Z","doi":"10.2139/ssrn.7177748","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.6638119","name":"Dual-Parameter Distribution Correction for Neural-Network Calibration: A Shrinkage-and-Scaling Framework With Multi-Seed Empirical Validation","source":"crossref","abstract":"Neural-network classifiers trained with cross-entropy loss are frequently mis-calibrated: their output probabilities do not match empirical accuracy rates. Standard training-time remedies such as label smoothing and focal loss, while widely used, can worsen calibration in compact-model / short-training regimes. We present a dual-parameter distribution correction framework in which (i) a shrinkage operator K reweights the empirical probability distribution toward its mean and (ii) a scaling constant R, derived from the Average Shrinking Constant (ASC) between discrete and continuous representations, modulates the training loss. The two operators are combined in a hybrid objective J = R•L + α•D_KL(p_emp^K ‖ p_model) that simultaneously smooths the empirical distribution and regularises optimisation dynamics. We provide a theoretical interpretation of the framework, connecting K to James-Stein-style shrinkage estimators and to a training-time analogue of temperature scaling, and R to Dirichlet-style smoothing of class priors. We validate the framework on CIFAR-10, CIFAR-100 and SVHN using a compact convolutional network across three random seeds (42, 123, 456) and six training regimes. Paired t-tests on per-seed values show that the combined method significantly reduces Expected Calibration Error (ECE) over the baseline on CIFAR-100 (p = 0.015, Cohen's d = 4.72) and produces large-magnitude improvements on CIFAR-10 and SVHN that, within the n = 3 seed budget, do not all reach the 0.05 significance threshold (p = 0.19 and p = 0.23 respectively). The framework outperforms label smoothing and focal loss by a large margin on every dataset (p &amp;lt; 0.001, d &amp;gt; 22). We report all per-seed values, all raw p-values, and explicitly flag the limited seed count, the compact-model regime, and the missing comparison to Temperature Scaling and Mixup as honest limitations. Full reference code and per-seed JSON data are released with the paper.","url":"https://doi.org/10.2139/ssrn.6638119","authors":["RamaKrishna Pasupuleti"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-29T13:24:17Z","doi":"10.2139/ssrn.6638119","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1007/springerreference_60433","name":"Granular Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/springerreference_60433","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-08-29T12:20:21Z","doi":"10.1007/springerreference_60433","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.38007/nn.2026.050102","name":"Research on Big Data Security Governance and Privacy Protection Strategies for Cross-Domain Data Circulation Scenarios","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2026.050102","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-22T03:20:40Z","doi":"10.38007/nn.2026.050102","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.54216/jisiot.180225","name":"Deep Neural Network Graph with Reinforcement Learning for Test Case Prioritization","source":"crossref","abstract":"","url":"https://doi.org/10.54216/jisiot.180225","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-09-07T15:33:59Z","doi":"10.54216/jisiot.180225","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.14744/thermal.0001070","name":"Evaluation of infrared radiations from top of the atmosphere through artificial neural network modeling","source":"crossref","abstract":"","url":"https://doi.org/10.14744/thermal.0001070","authors":["Usama Ayub YOUSUFZAI"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-02T09:53:24Z","doi":"10.14744/thermal.0001070","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/icndsa68777.2026.11652072","name":"An Accelerated Neural Network Framework for Facial Emotion Recognition","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icndsa68777.2026.11652072","authors":["Neha Mathur","Paresh Jain","Pankaj Dadheech"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-19T19:07:35Z","doi":"10.1109/icndsa68777.2026.11652072","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.38007/nn.2022.030308","name":"Product Information Classification based on Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2022.030308","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T18:14:38Z","doi":"10.38007/nn.2022.030308","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.3788/col202624.041103","name":"Optical diffraction neural network assisted computational ghost imaging through dynamic scattering media","source":"crossref","abstract":"","url":"https://doi.org/10.3788/col202624.041103","authors":["Yuegang Li","Ze Zheng","Junjie Wang","Ming He","Jianping Fan","Tailong Xiao","Guihua Zeng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-20T07:33:17Z","doi":"10.3788/col202624.041103","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/wispnet69615.2026.11489406","name":"Graph Neural Network Based Skin Lesion Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/wispnet69615.2026.11489406","authors":["Moorthi S","Senthil Kumar Thangavel","K Somasundaram"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-29T19:46:17Z","doi":"10.1109/wispnet69615.2026.11489406","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/icnc68183.2026.11416920","name":"Hybrid Quantum–Classical Convolutional Neural Network for Robust RF Sensing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icnc68183.2026.11416920","authors":["Yujie Sun","Xuyu Wang","Shiwen Mao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-09T19:55:54Z","doi":"10.1109/icnc68183.2026.11416920","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/b978-0-443-29981-0.00011-2","name":"Achieving energy efficiency in FPGA-based neural network inference accelerators through approximate computing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-29981-0.00011-2","authors":["Burhan Khurshid"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-14T15:03:10Z","doi":"10.1016/b978-0-443-29981-0.00011-2","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1364/cleo_si.2026.stu1e.2","name":"A Hybrid Photonic Integrated Engine for Convolution and Full Connection in a Convolutional Neural Network","source":"crossref","abstract":"We present a hybrid photonic integrated engine for convolutional neural networks. Four consecutive convolutional layers and a deep fully connected neural network with five hidden layers are experimentally implemented for the task of digit recognition.","url":"https://doi.org/10.1364/cleo_si.2026.stu1e.2","authors":["Yiran Guan","Shanshan Cheng","Mahdi Chegini","Jianping Yao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-28T21:01:23Z","doi":"10.1364/cleo_si.2026.stu1e.2","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/iccad69956.2026.11643153","name":"Road Traffic Data Classification Using Deep Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccad69956.2026.11643153","authors":["Yosr Ranim Slim","Joaquim Ferreira","Chokri Souani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-17T19:19:14Z","doi":"10.1109/iccad69956.2026.11643153","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1007/s00521-026-11865-y","name":"Dual-stage deep neural network for tooth localization and caries segmentation in panoramic dental imaging","source":"crossref","abstract":"Abstract This study develops and evaluates an automatic AI-based system for dental caries segmentation in panoramic radiographs, contributing to the expanding research on AI applications in dental imaging. Our approach implements a two-stage process: first using the object detection model for precise tooth extraction, followed by specialized segmentation techniques for caries identification. System performance evaluation yielded exceptional results, with a Dice score of 0.926, precision of 0.921, recall of 0.931, and IoU of 0.862. These metrics demonstrate the system’s high effectiveness in accurately detecting dental caries from panoramic radiographs, indicating strong potential for clinical dental diagnostics. The proposed method offers a practical approach to panoramic caries segmentation, with results highlighting both the feasibility and efficiency of AI integration in comprehensive dental diagnostics. This work demonstrates a practical implementation of a two-stage segmentation system optimized for clinical relevance.","url":"https://doi.org/10.1007/s00521-026-11865-y","authors":["Sirawich Vachmanus","Suchaya Pornprasertsuk-Damrongsri","Pattanasak Mongkolwat","Noppanan Phinklao","Dhanaporn Papasratorn","Jira Kitisubkanchana","Sarunya Chaikantha","Raweewan Arayasantiparb"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-13T04:44:18Z","doi":"10.1007/s00521-026-11865-y","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1007/978-981-95-8110-8_6","name":"Scaling Laws of Deep Learning Neural Networks: Information Loss","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-95-8110-8_6","authors":["Cheng Wang","Yuhang Lin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-11T22:10:29Z","doi":"10.1007/978-981-95-8110-8_6","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/elnano63396.2026.11601312","name":"Neural Network–Based Solution of the Inverse Radar Cross Section Problem","source":"crossref","abstract":"","url":"https://doi.org/10.1109/elnano63396.2026.11601312","authors":["Maksym Buhai","Maxim Legenkiy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-17T19:43:07Z","doi":"10.1109/elnano63396.2026.11601312","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/wccst67302.2026.11496084","name":"Embedding-Enhanced Deep Neural Network for Hypertension Risk Prediction Using Mixed-Type Clinical Data","source":"crossref","abstract":"","url":"https://doi.org/10.1109/wccst67302.2026.11496084","authors":["Jeena Joseph"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-05T19:59:50Z","doi":"10.1109/wccst67302.2026.11496084","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.23919/aciecps00006.2026.00007","name":"Enhanced LSTM Neural Network for Integrating Multi-Source Factors in Carbon Price Prediction","source":"crossref","abstract":"","url":"https://doi.org/10.23919/aciecps00006.2026.00007","authors":["Bundit Rotyoon","Tanasanee Phienthrakul"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-27T19:47:32Z","doi":"10.23919/aciecps00006.2026.00007","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.25206/2311-4908-2026-13-1-38-43","name":"COMPARATIVE ANALYSIS OF NEURAL NETWORK ARCHITECTURES FOR FAKE NEWS DETECTION","source":"crossref","abstract":"The paper presents a comparative analysis of CNN, LSTM and BERT neural network architectures used for binary classification of news texts into fake and reliable ones. The aim of the study is to identify the most effective model for automatic detection of fakes, taking into account classification accuracy and computational complexity. The structural features of the models and their training are considered, and the results of testing on a public dataset are analyzed. In conclusion, an effective model has been identified effective model.","url":"https://doi.org/10.25206/2311-4908-2026-13-1-38-43","authors":["A.D. SOTNIKOV","N.A. MOISEEVA"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-02T09:16:28Z","doi":"10.25206/2311-4908-2026-13-1-38-43","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/eng2.70802","name":"Research on Engineering Cost Estimation Based on Enhanced Neural Network Optimization Method","source":"crossref","abstract":"ABSTRACT Considering the fundamental challenge of accurately and reliably predicting the final cost of engineering projects, due to the multiple factors and the complexity of the relationships between them, the present study presents an innovative framework. This framework, with the aim of improving the accuracy of the predictions, is based on hybrid feature selection and advanced neural network optimization using genetic algorithms guided by reinforcement learning. The proposed method consists of three main phases: In the first phase, preprocessing of raw records is performed to obtain a set of suitable features for processing. In the second step, a hybrid feature selection algorithm based on information gain and Boruta is used. These techniques simultaneously rank the features, and after normalizing the weights and determining the final ranking, the Recursive Feature Elimination with Cross‐Validation (RFE‐CV) is used to select the most relevant features. In the third phase, to perform the prediction operation, a multilayer perceptron (MLP) neural network is optimized using a new optimization algorithm called Q‐Learning‐assisted Genetic Algorithm (QLGA). By adjusting the structure and weight vector, an efficient model is created according to the training data, which is able to improve the prediction performance compared to conventional training algorithms. In this optimization algorithm, the Q‐Learning strategy is used to guide the population towards the global optimum. After determining the optimal MLP model, it is used to predict new samples. The root mean squared error and mean absolute percentage error values of 8.2 and 4.5, respectively, show that the proposed method is very effective at predicting the final costs of engineering projects compared to other methods that are already out there.","url":"https://doi.org/10.1002/eng2.70802","authors":["Jiaqi Xu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-09T04:18:43Z","doi":"10.1002/eng2.70802","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.datak.2026.102599","name":"A graph neural network approach to automated resume classification","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.datak.2026.102599","authors":["Asmae Melliani","Mohammed Rziza"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-24T23:47:50Z","doi":"10.1016/j.datak.2026.102599","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.nexres.2026.102263","name":"Hybrid residual neural network modeling for robust end-effector prediction in planar robotic manipulators","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.nexres.2026.102263","authors":["Sathees Kumar Nataraj"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-02T19:56:31Z","doi":"10.1016/j.nexres.2026.102263","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/isqed69900.2026.11534720","name":"Carbon Emission-Based Sustainability Model For Photonic Neural Network Accelerators","source":"crossref","abstract":"","url":"https://doi.org/10.1109/isqed69900.2026.11534720","authors":["Siqin Liu","Avinash Karanth","Ahmed Louri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-28T22:26:58Z","doi":"10.1109/isqed69900.2026.11534720","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.18494/sam5753","name":"Wind Turbine Gearbox Fault Detection Method Based on One-dimensional Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.18494/sam5753","authors":["Hong-Wei Sian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-22T22:09:24Z","doi":"10.18494/sam5753","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1088/0954-898x_1_3_003","name":"An attractor neural network model of semantic fact retrieval","source":"crossref","abstract":"","url":"https://doi.org/10.1088/0954-898x_1_3_003","authors":["E Ruppin","M Usher"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2015-08-18T20:04:04Z","doi":"10.1088/0954-898x_1_3_003","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.38007/nn.2020.010403","name":"Lung Cancer Detection Considering Convolutional Autoencoder Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.38007/nn.2020.010403","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-01T03:55:33Z","doi":"10.38007/nn.2020.010403","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.26434/chemrxiv.10001743/v3","name":"A Multitask Graph Neural Network Framework for AMES Mutagenicity Prediction","source":"crossref","abstract":"The long, complex, and costly process of drug development makes early, reliable toxicity assessment a central challenge in pharmaceutical research. Accurately predicting drug-induced toxicity and mutagenicity is crucial for guiding decision-making and reducing late-stage attrition. Deep learning approaches can predict the results of the Ames mutagenicity test, a standard screening method; however, most existing models rely on molecular descriptors that limit structural representation, lack interpretability, and do not account for Ames results of individual bacterial strains. Graph neural networks (GNNs) are chemically intuitive and overcome these limitations. This work presents a deep learning, multitask GNN model for predicting Ames mutagenicity. The proposed approach outperforms existing models, including those from the Ames/QSAR International Challenge. Furthermore, the model is highly interpretable. Explainability analysis of atom-level contributions reveal that the model is capable of learning known structural alerts associated with mutagenicity, along with additional molecular patterns and three-dimensional structural properties. Importantly, these insights are captured in a strain-specific manner, highlighting the value of a multitask approach. Finally, the model is able to identify previously unreported molecular substructures potentially associated with mutagenicity, supporting its utility in drug design and development.","url":"https://doi.org/10.26434/chemrxiv.10001743/v3","authors":["Abigail E Teitgen","Eugenia Ulzurrun","Nuria E Campillo","Eduardo R Hernández"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-09T06:35:22Z","doi":"10.26434/chemrxiv.10001743/v3","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.36227/techrxiv.177208051.12907488/v1","name":"IoT-edge Computing enabled Secure and Intelligent Fertilizer Management Framework using Blockchain and Transformer Neural Network","source":"crossref","abstract":"Modern precision agriculture depends on safe and effective fertilizer management. However, existing systems lack real-time decision-making capabilities, rarely incorporate secure traceability methods, and mainly concentrate on nutrient prediction without determining the type of soil fertilizer utilized for a specific crop. To classify fertilizer types (organic vs. inorganic) in real-time based on soil nutrient parameters (temperature, pH, EC, N, P, and K), this investigation suggests an innovative, lightweight self-attention transformer neural network (TNN) based Fertilizer class contract network (FCCN) model. The proposed research is one of the first to combine secure blockchain recording, fertigation, and fertilizer-type detection into a single edge-based pipeline that operates in real time. The process integrates blockchain-based transaction logging and IoT-edge computing for recording transparent and secure agricultural activity. Whenever deficits emerge, the suggested method uses Venturi irrigation to automatically activate fertigation after processing real-time sensor data at the edge to determine the types of fertilizer utilized and the nutritional status. This work uses a decentralized and scalable architecture compared to cloud-dependent or AI-based-only models. Fertilizer classification and fertigation actions based on the real-time nutrient level recommendation are recorded as immutable transactions on an Ethereum blockchain using a Proof-of-Stake (PoS) consensus. Before the final on-chain recording, validator logic confirms the accuracy of field data, fertigation events, and real-time soil nutrient levels. Real-time blockchain measurements reveal transaction completion speeds of less than 0.03 seconds, gas consumption of less than 62,000 units, and throughput of 15-35. Experimental findings show that FCCN categorization accuracy surpasses 98.85%.","url":"https://doi.org/10.36227/techrxiv.177208051.12907488/v1","authors":["Rohit Kumar Kasera","Tapodhir Acharjee"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-26T04:35:21Z","doi":"10.36227/techrxiv.177208051.12907488/v1","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.26434/chemrxiv.15001313/v2","name":"Benchmarking Ice-Water Equilibria Exhibited by Foundation Neural Network Potentials","source":"crossref","abstract":"Herein we report the melting points of ice exhibited by some recently published foundation Neural Network Potentials (NNPs) using the direct coexistence method: SO3LR, Orb v3, MACE-MP, FENNIX-Bio1, NEP89 and PET-MAD as well as the first generation model ANI-2x. Using our previously published LICH-TEST algorithm, we classify the structural motifs adopted by individual molecules over time, finding that most models correctly exhibit ice growth and shrinkage via interfacial hexagonal structures. However, the observed melting temperatures vary from the experimental value significantly, with the lowest and highest nearly 150 K apart. The growth rates of ice below the melting points were also found to vary significantly, in some cases exceeding classical water models by one decade. SO3LR was the only NNP exhibiting an accurate value, and represents the best trade-off of speed and accuracy for the simulation of ice nucleation in (bio)organic systems. Disconcertingly the MACE, Orb and ANI models overestimate the melting point to such a degree that liquid water is effectively under deep supercooling when simulated at standard conditions. By comparing variants of the latter two potentials, we infer that an accurate description of dispersion interactions during training and/or evaluation improves the water density isobar and leads to slightly better melting temperatures, albeit with a substantial speed penalty if added during inference. We conclude with some general recommendations for training the next generation of foundation models, in order to improve their description of ice-water interactions.","url":"https://doi.org/10.26434/chemrxiv.15001313/v2","authors":["Rasmus Nilsson","Golnaz Roudsari","Mária Lbadaoui-Darvas","Bernhard Reischl","Stephen Ingram"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-06T05:35:12Z","doi":"10.26434/chemrxiv.15001313/v2","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.46855/energy-proceedings-12208","name":"Graph Neural Network-Based Security Assessment for Power Grids with Interpretable Feature Attribution","source":"crossref","abstract":"","url":"https://doi.org/10.46855/energy-proceedings-12208","authors":["Yuanhao Dai","Yunchao Sun","Wei Hu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-29T11:18:46Z","doi":"10.46855/energy-proceedings-12208","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.7229385","name":"Reduced-chemistry LES of hydrogen combustion using neural-network-based NO source-term prediction","source":"crossref","abstract":"The defossilization of energy-intensive industries, particularly mining and steelmaking, is essential for achieving the deep emission reductions required by global climate targets. Replacing fossil fuels with hydrogen offers a promising route for high-temperature industrial processes, but this transition requires fast and accurate predictive tools capable of resolving turbulent combustion and NOx formation under high-temperature conditions. In this study, a hybrid reduced-chemistry/artificial-neural-network (ANN) framework is developed for large-eddy simulation (LES) of a pilot-scale hydrogen-fired furnace supplied with highly preheated air. Unlike ANN approaches that replace the full chemistry integrator, the present method retains finite-rate chemistry for the main hydrogen oxidation process and uses the ANN only to reconstruct the NO production rate from the resolved thermochemical state. Three chemistry treatments are compared: a detailed mechanism with direct NO source-term evaluation (M1), a reduced mechanism derived from the detailed chemistry and coupled with ANN-predicted NO production rate (M2), and the Curran hydrogen mechanism coupled with the same ANN model (M3). Zero-dimensional PSR tests show that the chemistry-integration times of M2 and M3 are approximately 17% of that of M1, while LES timing tests demonstrate an approximately sevenfold overall speedup. M2 reproduces the detailed-mechanism temperature, heat release, and major-species evolution more accurately than M3. In the furnace LES, M2 predicts outlet quantities and domain-integrated heat release close to M1 and in reasonable agreement with measurements. M1 gives the closest agreement with the measured NO emission range, followed by M2, whereas M3 shows the largest overprediction. The higher NO level in M2 is traced mainly to excessive contributions from regions above 2100 K and near-stoichiometric mixtures (0.6 &lt; Φ &lt; 1.0). The proposed framework therefore provides an efficient route for NO prediction in highly preheated industrial hydrogen furnaces, although its accuracy remains sensitive to errors in the thermochemical fields supplied by the simplified mechanism.","url":"https://doi.org/10.2139/ssrn.7229385","authors":["Pikai Zhang","Sony Chindada","Christophe Duwig"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-04T06:52:11Z","doi":"10.2139/ssrn.7229385","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/icsedis68157.2026.11517988","name":"Enhanced AI-based Biometric Authentication using Recurrent Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icsedis68157.2026.11517988","authors":["Gopinath P","Gopi Krishnan P"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-18T19:44:46Z","doi":"10.1109/icsedis68157.2026.11517988","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.bpj.2025.11.2101","name":"BPS2026 – Geometry-aware RNA-small molecule binding site prediction with equivariant graph neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.bpj.2025.11.2101","authors":["JinHyeok Yoo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-19T16:32:02Z","doi":"10.1016/j.bpj.2025.11.2101","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.51903/elkom.v18i2.3238","name":"Klasifikasi Jenis Bunga Menggunakan Algoritma Convolutional Neural Network (CNN)","source":"crossref","abstract":"This research aims to develop a multiclass flower image classification system using the Convolutional Neural Network (CNN) algorithm with the EfficientNet architecture. The main problem addressed is the difficulty of manual identification of flower species that share high visual similarity. The research stages include collecting 17,299 flower images across 19 classes, performing data preprocessing such as image resizing, pixel normalization, and augmentation, followed by model training using the EfficientNet transfer learning approach. The model was trained for 10 epochs with an 80:20 training-validation data split. The evaluation results show that the model achieved a validation accuracy of 98.05% with a loss value of 0.0968, and an average precision, recall, and F1-score of 0.98. The trained model was then implemented into a web-based application built using the Next.js framework, enabling users to upload flower images and obtain real-time classification results via the Hugging Face API. The system successfully identified flower species with a confidence level of 99.87%. These findings demonstrate that combining a modern CNN architecture with transfer learning provides efficient and highly accurate flower classification performance, which can be effectively implemented for educational and digital conservation purposes.","url":"https://doi.org/10.51903/elkom.v18i2.3238","authors":["Ade Irgi Firdaus","Dwi Okta Djoas","Riefaldi Diofano Saputra","Indry Anggraeny","Hilda Apriliya Ningsih"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-20T08:15:31Z","doi":"10.51903/elkom.v18i2.3238","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/ijcnn55064.2022.9892808","name":"Memristor Based Circuit Design for Liquid State Machine Verified with Temporal Classification","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn55064.2022.9892808","authors":["Alex Henderson","Chris Yakopcic","Steven Harbour","Tarek M. Taha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-09-30T19:56:04Z","doi":"10.1109/ijcnn55064.2022.9892808","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/access.2018.2885221","name":"Lag Exponential Synchronization of Delayed Memristor-Based Neural Networks via Robust Analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1109/access.2018.2885221","authors":["Hong Cheng","Shouming Zhong","Qishui Zhong","Kaibo Shi","Xin Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-12-05T20:03:13Z","doi":"10.1109/access.2018.2885221","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/cnna.2014.6888625","name":"Shared memristance restoring circuit for memristor-based Cellular Neural Networks","source":"crossref","abstract":"","url":"https://doi.org/10.1109/cnna.2014.6888625","authors":["YoungSu Kim","SangHak Shin","Kyeong-Sik Min"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2014-09-03T18:38:31Z","doi":"10.1109/cnna.2014.6888625","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.7218445","name":"Constrained Neural Network Based Fallback Control for PV–heat-pump Systems Under ICT Failure","source":"crossref","abstract":"In the transition to a CO2-free energy system, ensuring resilience in energy management during ICT failures is crucial. This research investigates whether an AI based heat-pump controller can maintain operational continuity and reduce operational deterioration under such conditions. Three AI models focusing on the power grid, heat-pump operations, and an integrated system were developed using neural networks optimized with genetic algorithms and compared to a conventional server based controller.For operational assessment, the integrated model was merged with a deterministic physical feasibility layer and compared to emergency electric heater and local rule based fallbacks. Results demonstrate that task-specific models deliver marginally higher prediction accuracy, whereas the integrated model generates all four necessary outputs with only a small compromise in grid related precision.During the temporary December 2013 ICT outage, the constrained AI met 99.974% of the modelled heat demand and lowered grid-import energy by 50.4% and electric-heater electricity by 97.2% compared to the emergency fallback, but it did not cut peak grid import. Across five household profiles in Winter and Transition, all 40 scenario trajectories achieved complete modelled heat-service coverage. In the 2045-informed low-voltage-grid case study, the constrained AI avoided 91.6%–92.4% of the emergency-fallback importenergy penalty and decreased the majority of the associated peak-import and transformer-loading deterioration, while all instances stayed within network constraints. The findings suggest constrained AI as a potential local backup alternative, while it is not universally superior to a well-designed rule based controller.","url":"https://doi.org/10.2139/ssrn.7218445","authors":["Sadia Ferdous Snigdha","Tanja Manuela Kneiske"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-02T19:04:35Z","doi":"10.2139/ssrn.7218445","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.5772/intechopen.115629","name":"Fast Marching Method-Inspired Inversion Neural Network for Permeability Prediction","source":"crossref","abstract":"Characterizing permeability heterogeneity is crucial for accurate reservoir modeling, as it dominates fluid flow in subsurface reservoirs. Traditional methods for permeability estimation typically couple reservoir simulators with iterative inversion methods. In addition, the estimation of heterogeneous permeability fields can be challenging because of the high dimensionality of the geological models, monitoring data paucity, and high computational costs of simulations. All these factors may lead to high uncertainty for fluid flow behavior predictions. This chapter introduces recent deep learning models for permeability estimation inspired by the fast marching method (FMM). These models can predict permeability fields from pressure derivative data. Such “data” are obtained using a semi-analytic asymptotic solution to the diffusivity equation that uses the diffusive time of flight (DTOF), which itself can be efficiently calculated by using the FMM. Due to the spatial nature of the permeability estimation, deep neural networks (DNNs) are adopted to perform the inversion. The first inversion neural network (INN) model takes the pressure derivative collected at sparse observational locations as input variables and inversely estimates the permeability field. Further, an ensemble INN (EINN) is introduced to directly learn the nonlinear mapping between the innovation vector and the update vector in the history-matching problem. With the ensemble feature, the EINN can effectively quantify the uncertainty in the heterogeneous permeability fields. The applicability of the INN and EINN in permeability estimation is demonstrated with reasonable accuracy and high efficiency, which represents a significant leap forward in the inversion methods for reservoir engineering, geoscience, and hydrogeology.","url":"https://doi.org/10.5772/intechopen.115629","authors":["Bicheng Yan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-08-25T11:31:36Z","doi":"10.5772/intechopen.115629","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.47176/pd.2026.1559","name":"Acoustic Shield: Lightweight Neural Network for Audio-Based Drone Detection and Classification","source":"crossref","abstract":"","url":"https://doi.org/10.47176/pd.2026.1559","authors":["Fatemeh Alimadadi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-25T07:17:37Z","doi":"10.47176/pd.2026.1559","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.21203/rs.3.rs-9375800/v1","name":"A Dynamical Systems Approach to Alzheimer's Disease: A Neural Network Model with Positive Feedback Mechanisms","source":"crossref","abstract":"Abstract Alzheimer's disease is a progressive neurodegenerative disorder characterized by a continuous decline in cognitive function. Based on the theory of artificial neural networks, this paper proposes a dynamic model with a positive feedback mechanism to explain the onset and progression of Alzheimer's disease. The model takes the number of neurons, levels of neuroinflammation, and pathological protein load as core state variables and introduces the coupling relationships among them, revealing critical behaviors and self-accelerating mechanisms in disease progression. Through numerical simulations implemented in Python, we analyze the effects of different intervention strategies (anti-inflammatory drugs, anti-Aβ drugs, neuroprotective agents, and combination therapies) on disease trajectories and identify the critical window for treatment. The results indicate that combination therapy is the most effective in delaying the crossing of cognitive thresholds, and the timing of intervention has a decisive impact on efficacy. This study provides a unified theoretical framework for understanding the pathological mechanisms of Alzheimer's disease, guiding early interventions, and developing multi-target treatment strategies.","url":"https://doi.org/10.21203/rs.3.rs-9375800/v1","authors":["Yixin Cheng","Zhi Cheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-14T14:20:15Z","doi":"10.21203/rs.3.rs-9375800/v1","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.6865301","name":"Melting Behavior and Phase Stability of CaO from Neural Network Potentials: a Molecular Dynamics Study","source":"crossref","abstract":"We investigate the melting behavior of calcium oxide (CaO) under extreme conditions, a problem that remains poorly constrained due to experimental limitations despite its relevance for geophysical and technological applications. We develop a Machine Learning Interatomic Potential (MLIP) for CaO with PANNA 2.0 and the LATTE descriptor, training it on a dataset of ∼12,000 configurations including solid, liquid, interfacial, and void-containing structures, extracted from ab−initio molecular dynamics data employing PBEsol exchange-correlation functional. We perform large-scale molecular dynamics simulations to compute the melting temperature at ambient pressure using both the void-nucleated melting (VNM) and two-phase coexistence (TPC) methods, obtaining Tm=3055±11 K and Tm=2847±15 K, respectively. We calculate an enthalpy of fusion of ∆Hf ∼ 73 kJ/mol, in agreement with thermodynamic assessments and ab initio calculations. We also reproduce the thermal expansion and obtain a volume increase of ∼29% at Tm, consistent with the corresponding decrease in density extracted from spatially resolved number density profiles. Finally, we calculate the high-pressure melting curve of CaO up to 20 GPa, providing one of the very few computational determinations of this quantity to date. The results confirm that the overheating ratio η is not constant under pressure, increasing from 17% at ambient pressure to 24% at 20 GPa, confirming previous findings and ruling out the assumption of a fixed overheating ratio. Our results establish MLIP-based simulations as a robust and efficient framework for investigating phase stability in ionic oxides and provide new insight into the melting behavior of CaO under extreme conditions.","url":"https://doi.org/10.2139/ssrn.6865301","authors":["Francesca Menescardi","Stefano de Gironcoli"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-03T13:02:45Z","doi":"10.2139/ssrn.6865301","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.36227/techrxiv.176945884.42345088/v1","name":"DISTIL: A Distributed Spiking Neural Network Accelerator on 2.5D Chiplet Systems","source":"crossref","abstract":"Spiking Neural Networks (SNNs) implemented on in-memory computing (IMC) based architectures offer a promising solution for energy-efficient inference. However, the area and memory required to store temporal neuronal state membrane potentials updated by leaky-integrate fire (LIF) activation functions increase with the growing complexity of SNN models. Chiplet based 2.5D architectures provide scalability, but deploying SNNs on such systems introduces a critical design trade-off: a single global LIF module minimizes area but increases inter-chiplet communication latency, while dedicating an LIF module per layer reduces latency at the cost of excessive memory overhead. Existing approaches do not adequately address this trade-off or the placement of LIF modules on the interposer, leading to either large area overhead or communication bottlenecks on the Network-on-Interposer (NoI). This paper proposes DISTIL, a design and optimization framework for high-performance, areaefficient multi-chiplet architecture for SNN inference. DISTIL performs a design-space exploration (DSE) to jointly optimize the grouping of neural layers into shared sets of LIF tiles and their physical placement on the interposer to lower inter-chiplet traffic. Our experimental results show that DISTIL achieves up to 4.3× higher throughput per unit area (TOPS/mm 2) compared to state-of-the-art SNN accelerators while reducing LIF memory overhead by (60-90%).","url":"https://doi.org/10.36227/techrxiv.176945884.42345088/v1","authors":["Pramit Kumar Pal","Harsh Sharma","Abhishek Moitra","Partha Pratim Pande"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-26T20:20:47Z","doi":"10.36227/techrxiv.176945884.42345088/v1","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1007/s00521-020-04752-7","name":"Designing pulse-coupled neural networks with spike-synchronization-dependent plasticity rule: image segmentation and memristor circuit application","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00521-020-04752-7","authors":["Xudong Xie","Shiping Wen","Zheng Yan","Tingwen Huang","Yiran Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2020-02-03T14:03:47Z","doi":"10.1007/s00521-020-04752-7","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.7075195","name":"Neural Network Solution Based on Peridynamic Differential Operator for the Population Balance Equations in Crystallization Process","source":"crossref","abstract":"The population balance equation (PBE), the primary governing equation for modeling dynamic crystallization behavior, is addressed in this paper through a proposed physics-informed neural network (PINN) framework based on the peridynamic differential operator (PDDO). By introducing the non-local integral form of PDDO into the loss function, the framework can inherently handle discontinuities and derivative singularities, thereby reducing its reliance on dense spatial and temporal discretization. Besides, we analyze the coupling mechanism between the truncation error of PDDO and the approximation error of neural networks, and estimate the total error for the proposed PDDO‑PINN algorithm. Numerical experiments are conducted to validate our error estimates and the efficiency of the proposed algorithm. Numerical results confirm that the proposed PDDO-PINN method can effectively suppress numerical oscillation/substantial diffusion and improve the prediction accuracy of crystal size distribution, and exhibit prominent advantages particularly when handling discontinuous or sharp-gradient crystal size distribution.","url":"https://doi.org/10.2139/ssrn.7075195","authors":["Cengceng Dong","Hongjiong Tian"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-07T20:41:24Z","doi":"10.2139/ssrn.7075195","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.6621458","name":"AdapTGN: An Adaptive Temporal-Relational Graph Neural Network for Social Media Bot Detection","source":"crossref","abstract":"Automated social media bots represent a persistent and increasingly sophisticated threat to the integrity of online information ecosystems, influencing democratic discourse, financial markets, and public health communication. Coordinated bot activity can distort electoral narratives, manipulate financial sentiment, and spread health misinformation at scale, highlighting the urgent need for robust and adaptive detection systems. However, despite extensive research, existing bot detection approaches share a key limitation: they fail to model social interactions as both temporally dynamic and relationally diverse. Traditional feature-based methods treat accounts independently, ignoring network structure. Sequential models capture temporal behavior but isolate users, overlooking coordinated patterns. Static Graph Neural Networks (GNNs) incorporate structural relationships but collapse temporal information into fixed snapshots. Temporal Graph Neural Networks (TGNNs) improve upon this by modeling evolving graphs, yet they remain limited by two critical issues: (i) reliance on a single, relationagnostic temporal decay function that cannot distinguish between fast-evolving interactions (e.g., retweets) and long-lasting associations (e.g., hashtag co-occurrence), and (ii) simplistic memory initialization that ignores valuable community-level structural priors. To address these limitations, this paper proposes AdapTGN, an Adaptive Temporal-Relational Graph Neural Network. The model introduces a relation-specific temporal decay mechanism, where distinct learnable decay parameters are assigned to different interaction types-co-hashtag (HT), retweet (RT), and mention (MN). This enables the model to capture heterogeneous temporal dynamics more accurately. Additionally, AdapTGN incorporates relation-aware temporal encodings, community-informed memory initialization using Louvain clustering, and a cross-relation gating mechanism that dynamically weights interaction types based on contextual relevance. Experimental evaluation on TwiBot-22 and Cresci-RTBust-2019 datasets demonstrates the effectiveness of the proposed approach. AdapTGN achieves an F1-score of 0.8892 and AUC-ROC of 0.9418 on TwiBot-22, outperforming the baseline TGN by 2.47 percentage points in F1 with statistically significant improvement (p = 0.031). Furthermore, the model exhibits strong temporal generalization, with only a 5.8 percentage point drop in F1 under distribution shift, compared to over 11 pp in competing methods. Ablation studies confirm the importance of each component, particularly persistent memory, temporal encoding, and multi-relational modeling. The learned decay parameters also align with real-world interaction dynamics, enhancing interpretability and practical reliability.","url":"https://doi.org/10.2139/ssrn.6621458","authors":["Mukeswar Shah Teli","Saurav Neupane","Pratik Lohani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-29T13:23:10Z","doi":"10.2139/ssrn.6621458","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1088/1757-899x/466/1/012049","name":"Synchronization of Memristor-Based Delayed Neural Networks via Aperiodically Intermittent Control","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1757-899x/466/1/012049","authors":["Mengzhuo Luo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2018-12-28T11:14:08Z","doi":"10.1088/1757-899x/466/1/012049","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.47297/taposatwsp2633-456917.20260706","name":"Facial Expression Recognition and Analysis Based on Neural Network Acceleration System","source":"crossref","abstract":"","url":"https://doi.org/10.47297/taposatwsp2633-456917.20260706","authors":["Li Jixuan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-19T08:08:40Z","doi":"10.47297/taposatwsp2633-456917.20260706","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/eng2.70804","name":"Mobile Base Station User Scheduling Optimization Algorithm Based on Graph Neural Network","source":"crossref","abstract":"ABSTRACT With the upgrading of mobile communication technology and the rise of the mobile communications industry, the mobile Internet is booming. However, mobile Internet networks are facing the next technological revolution due to the explosive growth of mobile devices, the expanding scale of networks, and the increasing demand of users for quality of service. To overcome the problems of high computational overhead and ineffective use of network history data information in traditional optimization algorithms, a graph neural network‐based joint user scheduling and power allocation model is proposed, combined with an analytical formulation of beam vectors, to achieve joint user scheduling and beamforming optimization. Simulation analysis shows that the proposed algorithm improves the convergence speed by nearly 20% compared with the traditional scheduling algorithm and saves 4.8% energy consumption compared with the widely used base station always‐on strategy.","url":"https://doi.org/10.1002/eng2.70804","authors":["Jingya Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-15T07:18:26Z","doi":"10.1002/eng2.70804","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.54216/mor.060108","name":"Deep Learning-Based Classification of Brain Tumors from Magnetic Resonance Imaging Scans Using a Convolutional Neural Network Model","source":"crossref","abstract":"","url":"https://doi.org/10.54216/mor.060108","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-26T00:04:11Z","doi":"10.54216/mor.060108","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/b978-0-443-30285-5.00013-8","name":"Neural network observer-based adaptive finite-time frequency control of cyber-physical power systems","source":"crossref","abstract":"","url":"https://doi.org/10.1016/b978-0-443-30285-5.00013-8","authors":["Dipayan Guha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-05T12:31:04Z","doi":"10.1016/b978-0-443-30285-5.00013-8","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/iciics67880.2026.11483363","name":"Dynamic Temporal Adaptive Multi-Objective Neural Network for Smart Laboratory Management System","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iciics67880.2026.11483363","authors":["Qinghua Jiang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-11T19:57:57Z","doi":"10.1109/iciics67880.2026.11483363","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1364/cleo_at.2026.am2b.3","name":"Nano-patterns inspection using plasmonic structured illumination and deep neural network","source":"crossref","abstract":"We propose a Moiré inspection technique. A plasmonic source generates near-field Sz patterns that multiply a passive photomask; a physics-aware deep neural network fuses far-field frames with the reference layout, yielding pixel-level defect prediction.","url":"https://doi.org/10.1364/cleo_at.2026.am2b.3","authors":["Lingxiao Zhou","Shuwei Guo","Jiechen Wang","Yue Cao","Masood Mortazavi","Pingfan Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-15T11:02:23Z","doi":"10.1364/cleo_at.2026.am2b.3","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.15302/frontphys.2026.083201","name":"Using a single circuit to compute the gradients with respect to all parameters of a quantum neural network","source":"crossref","abstract":"","url":"https://doi.org/10.15302/frontphys.2026.083201","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-06T05:34:57Z","doi":"10.15302/frontphys.2026.083201","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1364/cleo_at.2026.jtu.86","name":"Photonic Logic Adder Based on Integrated Diffractive Neural Network","source":"crossref","abstract":"We propose a novel end-to-end architecture for photonic full adder and other logic operations based on on-chip diffractive neural network, achieving 100% accuracy for 4-bit full adder. Our results hold significance for general-purpose photonic computing.","url":"https://doi.org/10.1364/cleo_at.2026.jtu.86","authors":["Guangpu Li","Chao Wang","Ziyu Ying","Xiuzhi Chen","Jiyuan Zheng","Qionghai Dai","Chenchen Deng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-15T11:04:39Z","doi":"10.1364/cleo_at.2026.jtu.86","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1108/f-06-2025-0101","name":"A multiclassifier convolutional neural network to identify defect type and severity in roofing elements","source":"crossref","abstract":"Purpose Roofing is highly susceptible to environmental damage from elements like wind, snow and rain. Regular inspection and maintenance are essential to extend a roof’s lifespan. This study aims to develop an automated system that detects and classifies roofing damage types and their severity using image-based analysis, helping asset managers prioritize repairs and allocate maintenance resources more effectively. Design/methodology/approach This study uses Convolutional Neural Networks (CNNs) for image-based damage detection and classification. Over 3,000 images of roofing segments (1.5 × 1.12 m) from institutional buildings were used for training and testing. The model first identifies damage type – no damage, vegetation or ponding – then classifies vegetation damage severity into low, moderate or severe. Findings The developed CNN model achieved over 94% accuracy in both damage type and severity classification. The results demonstrate the model’s effectiveness in analyzing roofing defects. Research limitations/implications Future enhancements include expanding the system to detect additional defect types like cracks and flashing defects, offering a scalable solution for systematic roof condition assessment and maintenance planning. Originality/value Unlike traditional manual inspections, this approach uses computer vision techniques to offer a scalable, data-driven framework that identifies damage types and quantifies severity levels. This makes roofing inspections more efficient, consistent and safer.","url":"https://doi.org/10.1108/f-06-2025-0101","authors":["Kareem Mostafa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-31T05:51:03Z","doi":"10.1108/f-06-2025-0101","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1016/j.apm.2026.116994","name":"An optimized neural network for fractional PDEs in option pricing","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.apm.2026.116994","authors":["Indu Rani","Chandan Kumar Verma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-23T06:52:24Z","doi":"10.1016/j.apm.2026.116994","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.18280/ts.430304","name":"Prediction and Classifications of Breast Cancer Using Enhanced Convolutional Neural Network Approaches","source":"crossref","abstract":"","url":"https://doi.org/10.18280/ts.430304","authors":["Sathishkumar Jaganathan","Venkatasalam Kandasamy"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-30T09:03:23Z","doi":"10.18280/ts.430304","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1002/eng2.70987","name":"Physics Constraint‐Guided Neural Network for Solving Partial Differential Equations","source":"crossref","abstract":"ABSTRACT Partial differential equations (PDEs) are key tools for modeling continuous physical processes, but traditional solvers are costly for high‐dimensional problems with complex boundaries. Existing neural network solvers usually add physical constraints only as loss terms, which limits physical constraint embedding learning and can cause local violations. To address this issue, this paper proposes a Physics Constraint‐Guided Network (PCGN) for deep PDE solving. Its main novelty is to introduce physical information at three levels: feature representation, optimization, and output correction. First, governing equations, boundary conditions, and initial conditions are encoded into propagatable constraint features, and neighborhood propagation improves local consistency. Second, adaptive residual balancing adjusts different constraint terms, reducing instability from uneven residual scales. Third, a differentiable constraint projection layer corrects predictions toward feasible solutions. Experiments on Burgers' equation and Darcy flow show that PCGN achieves lower absolute and relative errors than existing deep learning solvers, while improving training stability and physical consistency.","url":"https://doi.org/10.1002/eng2.70987","authors":["Zhihui Hou","Yaxu Peng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-03T04:23:11Z","doi":"10.1002/eng2.70987","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1007/springerreference_61728","name":"Artificial Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/springerreference_61728","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2011-08-29T16:36:33Z","doi":"10.1007/springerreference_61728","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1109/icassp55912.2026.11463675","name":"Lightweight Implicit Neural Network for Binaural Audio Synthesis","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icassp55912.2026.11463675","authors":["Xikun Lu","Fang Liu","Weizhi Shi","Jinqiu Sang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-21T21:23:31Z","doi":"10.1109/icassp55912.2026.11463675","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.1021/acs.jpclett.2c00654.s001","name":"BuRNN: Buffer Region Neural Network Approach for Polarizable-Embedding Neural Network/Molecular Mechanics Simulations","source":"crossref","abstract":"","url":"https://doi.org/10.1021/acs.jpclett.2c00654.s001","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-04-25T13:21:46Z","doi":"10.1021/acs.jpclett.2c00654.s001","addedAt":"2026-09-01T01:48:35.257Z","updatedAt":"2026-09-01T01:48:35.257Z"},{"id":"doi:10.2139/ssrn.6349378","name":"Quantile-based Interpretable Neural Network Models: Mortality Forecasting and Actuarial Simulations","source":"crossref","abstract":"This paper introduces a class of quantile-based, interpretable neural network (NN) models for mortality prediction: the Lee-Carter neural network (LCNN) model, the Renshaw-Haberman neural network (RHNN) model, and the simple neural network (simpleNN) model that balances simplicity with predictive performance. These models preserve the linear interpretability of classic stochastic mortality models while harnessing the flexibility of NNs to capture complex nonlinear patterns in mortality data, thereby achieving enhanced predictive performance. Leveraging a composite loss function that integrates pinball, median anchoring, and quantile-crossing penalty terms, we estimate mortality quantiles and develop an efficient simulation scheme based on interpolation. This framework provides distributional insights essential for pricing, reserving and risk management. Extensive empirical analyses across multiple populations demonstrate that the proposed models consistently outperform traditional approaches in predictive accuracy. We further illustrate their practical utility through an application to longevity swap pricing.","url":"https://doi.org/10.2139/ssrn.6349378","authors":["Yang Qiao","Jinggong Zhang","Wenjun Zhu","Chou‐Wen Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-26T04:24:29Z","doi":"10.2139/ssrn.6349378","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1201/9781003732273-6","name":"Autonomous Cognitive Agents in a Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1201/9781003732273-6","authors":["Subhash Kak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-13T10:27:07Z","doi":"10.1201/9781003732273-6","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.20944/preprints202605.1369.v1","name":"Asymptotic Expansions for Quantum Neural Network Operators: A Non-Commutative Voronovskaya Theorem","source":"crossref","abstract":"We establish a complete asymptotic expansion for Quantum Neural Network Operators (QNNOs) approximating arbitrary quantum channels, providing a non-commutative analogue of the classical Voronovskaya theorem. Within a rigorous functional analytic framework, we introduce quantum Sobolev and Hölder spaces Cm,γ(H) based on Fréchet differentiability in the Liouville representation, and we measure approximation errors using the diamond norm. Our main result, the Quantum Voronovskaya–Damasclin Theorem, reveals a multiscale decomposition of the error into three distinct contributions: integer-order terms involving Fréchet derivatives and even kernel moments, fractional corrections governed by Marchaud fractional derivatives that capture Hölder regularity of order γ, and intrinsically non-commutative commutator terms that vanish in classical settings. The remainder is sharply bounded by O(n−(m+γ)(log n)3m/2) with an explicit constant depending on m, γ, and the Hilbert space dimension d. As applications, we derive a quantum central limit theorem for QNNO fluctuations, construct optimal interpolation geodesics between quantum channels using Kubo–Ando means, and develop a quantum Richardson extrapolation method that reveals fundamental acceleration limits imposed by fractional smoothness. Our results establish a rigorous bridge between classical approximation theory, fractional calculus, and quantum machine learning, providing a powerful tool for the design and analysis of quantum neural networks in finite-dimensional settings.","url":"https://doi.org/10.20944/preprints202605.1369.v1","authors":["Rômulo Damasclin Chaves dos Santos"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-21T02:03:38Z","doi":"10.20944/preprints202605.1369.v1","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.31234/osf.io/z6m2k_v1","name":"A Neural Network Model of Retrieval Difficulty in Chinese Handwriting","source":"crossref","abstract":"Chinese speakers frequently experience failures in retrieving the orthographic form of characters during handwriting, a phenomenon known as the tip-of-the-pen (TOP) state, in which the writer knows the word but cannot produce its complete written form. Empirical research has identified character-level lexical variables that predict retrieval difficulty, but there have been no computational models of orthographic retrieval in Chinese. Here we present OrthoNet, a feed-forward neural network that takes pre-trained meaning and sound embeddings as input and learns to map them onto Chinese characters through frequency-weighted, error-driven training on a large-scale lexical corpus. Using Shannon entropy over the model’s output distribution as a graded measure of retrieval uncertainty, we evaluated OrthoNet against human behavioral data from previous dictation studies of Chinese handwriting. Entropy significantly predicted both TOP rate and writing latency beyond the variance accounted for by established lexical predictors. This result suggests that orthographic retrieval difficulty can be understood as a natural consequence of the statistical structure of the learned mapping from meaning and sound to orthographic form.","url":"https://doi.org/10.31234/osf.io/z6m2k_v1","authors":["Weihao Lin","Yongqi Su","Yueran Yang","Ruiming Wang","Charles Kemp"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-10T18:36:41Z","doi":"10.31234/osf.io/z6m2k_v1","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.66967/jsc.2026.v2i103","name":"Fractional Convergence of Symmetrized Neural Network Operators: A Generalized Voronovskaya-Damasclin Approach","source":"crossref","abstract":"This paper explores the asymptotic behavior of univariate neural network operators, with an emphasis on both classical and fractional differentiation over infinite domains. The analysis leverages symmetrized and perturbed hyperbolic tangent activation functions to investigate basic, Kantorovich, and quadrature-type operators. Voronovskaya-type expansions, along with the novel Voronovskaya-Damasclin theorem, are derived to obtain precise error estimates and establish convergence rates, thereby extending classical results to fractional calculus via Caputo derivatives. The study delves into the intricate interplay between operator parameters and approximation accuracy, providing a comprehensive framework for future research in multidimensional and stochastic settings. This work lays the groundwork for a deeper understanding of neural network operators in complex mathematical.","url":"https://doi.org/10.66967/jsc.2026.v2i103","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-08T07:51:54Z","doi":"10.66967/jsc.2026.v2i103","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.26434/chemrxiv.15004189/v1","name":"Are Atoms Enough? An Explainable Graph Neural Network for Carbon Capture and Gas Separation in Metal-Organic Frameworks","source":"crossref","abstract":"Are atoms enough to represent metal-organic frameworks (MOFs) in a graph neural network? Dominant crystal graph neural networks assume so, encoding each MOF entirely through its atoms and leaving pore space to emerge on its own. We introduce PoreGCN, a heterogeneous graph neural network in which Voronoi-derived pore vertices sit alongside atoms via dedicated atom-to-pore edges, giving the model a direct view of the cavities that govern adsorption and separation. Adding pore vertices produces large gains on the properties that matter most for screening. On the 2,737 real CoRE MOFs, the largest cavity diameter R2 rises from 0.07 under an atom-only baseline to 0.95 under PoreGCN. On the 51,163 hypothetical hMOF structures, PoreGCN reaches R2 between 0.91 and 0.99 across five geometric properties and R2 = 0.86 on log10(CO2/N2) selectivity. Retaining atoms alongside pores also unlocks two complementary attribution channels, the pore branch identifies which cavities drive a prediction, and the atom branch traces those cavities back to the metal nodes and linker chemistry responsible for them, something a pore-only model cannot do. Agreement between these two channels, combined with ensemble consensus, defines a four-scenario trust framework that separates individual predictions worth acting on from those requiring further validation, regardless of the model's population-level accuracy. Trustworthy selectivity predictions are 83.8% accurate at the 20% relative-error threshold against 8.3% for the untrustworthy subset, a roughly tenfold precision lift on the same model and test partition. The signal survives distribution shift, the condition that matters most in practice, maintaining a 1.3 to 2.0-fold enrichment on real CoRE MOFs as an independent external dataset, even where population-level calibration has been lost entirely. PoreGCN also recovers established chemistry independently, ranking fluorinated linkers and Zr-cluster secondary building units highest for CO 2 /N 2 selectivity. Predictions, trust labels, and per-atom attributions are available through a public web tool. https://huggingface.co/spaces/catenate/PoreGCN","url":"https://doi.org/10.26434/chemrxiv.15004189/v1","authors":["Abdulmujeeb T. Onawole"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-02T08:57:17Z","doi":"10.26434/chemrxiv.15004189/v1","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.26434/chemrxiv.10001743/v1","name":"A Multitask Graph Neural Network Framework for AMES Mutagenicity Prediction","source":"crossref","abstract":"The process of drug screening and development is long, complex, and costly, making early and reliable assessment of toxicity a central challenge in pharmaceutical research. In this context, the ability to accurately predict drug-induced toxicity in general, and mutagenicity in particular, is crucial for guiding decision-making and reducing late-stage attrition. In particular, deep learning approaches can be utilized to predict the results of the Ames mutagenicity test, which is commonly employed for toxicity screening in drug development. Recent work has shown that deep learning multitask approaches that account for the contributions of individual bacterial strains improve mutagenicity prediction. However, most existing models rely on molecular descriptors, which are limited in their representation of molecular structure and properties and often lack interpretability. Graph neural networks are chemically intuitive and overcome many of these limitations. Here, we present a deep learning, multitask graph neural network model for predicting Ames mutagenicity. The proposed approach outperforms existing models, including those from the Ames/QSAR International Challenge, and demonstrates high sensitivity for identifying mutagenic compounds. In addition, our model is highly interpretable. GNNExplainer analysis of atom-level contributions revealed that the model learned known structural alerts associated with mutagenicity, as well as additional molecular patterns and contextual features, including three-dimensional structural properties. Importantly, these insights were captured in a strain-specific manner, highlighting the value of a multitask approach for modeling mutagenic mechanisms. Finally, the model identified previously unreported molecular substructures potentially associated with mutagenicity, supporting its utility in drug design and development.","url":"https://doi.org/10.26434/chemrxiv.10001743/v1","authors":["Abigail E Teitgen","Eugenia Ulzurrun","Nuria E Campillo","Eduardo R Hernández"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-30T07:31:21Z","doi":"10.26434/chemrxiv.10001743/v1","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.17794/rgn.2026.4.4","name":"SHEAR WAVE MODELLING FROM CONVENTIONAL WELL LOGS USING INTEGRATED DEEP LEARNING INTEGRATED CONVOLUTIONAL NEURAL NETWORK (I-CNN)","source":"crossref","abstract":"Shear-wave velocity (Vs), together with compressional wave velocity, provides a crucial source of information for both geomechanical and geophysical studies. Vs data are often unavailable. Moreover, direct measurement of Vs remains relatively costly. Four machine learning algorithms were created to predict Vs from traditional well logs in order to get around these restrictions: Probability Neural Network (PNN), Multilayer Feed-Forward Neural Network (MLFFNN), Deep Feed-Forward Neural Network (DFFNN), one-dimensional Convolutional Neural Network (1D-CNN), and an Integrated Convolutional Neural Network (I-CNN). The dataset consists of two wells (19,121 data points were gathered) of authentic industrial wireline logs from two anonymized wells, provided with formal authorization from the data owner exclusively for academic research purposes, including model training, testing, and validation. There were three primary parts in the methodology: (1) pre-processing the data to get rid of noise and change it into the right format; (2) using domain knowledge to drive feature engineering and selection; and (3) training, testing, and optimizing the model. The results demonstrated that the I-CNN model in RCW-1 well achieved the best performance, with an R2 value of 0.971. When applied to the blind well (RCW-2), the I-CNN model maintained strong generalization capability, achieving an average R2 value of 0.956. These findings indicate that the I-CNN outperforms other methods in handling complex, nonlinear relationships in Vs prediction. Overall, this study contributes to the growing body of literature on machine learning applications in petrophysical analysis by introducing an integrated deep learning framework that surpasses traditional approaches.","url":"https://doi.org/10.17794/rgn.2026.4.4","authors":["Rahmat Catur Wibowo","Ida Bagus Suananda Yogi","Indra Arifianto","Muh Sarkowi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-29T20:46:00Z","doi":"10.17794/rgn.2026.4.4","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.3390/sym18040649","name":"A Neural Network-Assisted Variable Step-Size NLMS Algorithm","source":"crossref","abstract":"The traditional normalized least-mean-square (NLMS) algorithm faces an inherent trade-off between convergence rate and steady-state error, and its adaptability is limited in non-stationary environments. This paper proposes a neural network-assisted variable step-size NLMS algorithm (NN-VSS-NLMS). An analytically motivated reference step size is first derived under a zero-mean statistically symmetric signal assumption to characterize the desired step-size trend. Based on this reference, an eight-dimensional feature vector composed of input signal power, error energy, and related statistical descriptors is constructed to describe the instantaneous signal state, and a two-layer fully connected neural network (NN) is introduced as an auxiliary tool to provide data-driven correction to the reference step size. In addition, dynamic modulation, step-size constraints, and smoothing operations are incorporated to regulate the predicted step size and enhance its controllability under time-varying conditions. Through simulations with stationary and non-stationary inputs as well as time-invariant and time-varying systems, the proposed algorithm achieves up to a fourfold improvement in convergence rate and more than 8 dB reduction in steady-state error compared with the classical NLMS algorithm, while maintaining improved tracking ability.","url":"https://doi.org/10.3390/sym18040649","authors":["Zhipeng Li","Yalan Guo"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-13T11:38:26Z","doi":"10.3390/sym18040649","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1016/j.neunet.2026.109115","name":"Randomized neural network with adaptive forward regularization for online task-free class incremental learning","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.neunet.2026.109115","authors":["Junda Wang","Minghui Hu","Ning Li","Abdulaziz Al-Ali","Ponnuthurai Nagaratnam Suganthan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-16T06:10:57Z","doi":"10.1016/j.neunet.2026.109115","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.2139/ssrn.6837691","name":"Predicting Kresling Origami Mechanics under Compression Using Simplicial Neural Network","source":"crossref","abstract":"Kresling origami structures exhibit strongly nonlinear mechanical behaviour that is difficult to predict using reduced-order models or graph neural networks (GNNs), which are limited to pairwise interactions. This work presents the first simplicial neural network (SNN) framework for predicting the nonlinear mechanical response of Kresling origami. By incorporating the Hodge Laplacian, the model explicitly captures higher-order node–edge–face interactions and panel-level constraints absent in GNNs. The deformation is parametrised by twist angle and radial scaling, enabling simultaneous prediction of force–displacement response and deformation evolution. The SNN achieves high accuracy against numerical simulations and enables efficient large-scale inference. Two distinct compression-induced deformation modes and a previously unreported geometric scaling law linking twist–strain coupling to aspect ratio and staggered angle are revealed through analysis of 30,000 designs.","url":"https://doi.org/10.2139/ssrn.6837691","authors":["Fukun Xia","Shanqing Xu","Guangsi Shi","zhipeng gao","Wei Qiang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-27T13:40:08Z","doi":"10.2139/ssrn.6837691","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1038/s41928-025-01536-6","name":"A photonically linked memristive neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s41928-025-01536-6","authors":["Ilia Valov","Xin Zheng"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-14T10:01:52Z","doi":"10.1038/s41928-025-01536-6","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.2139/ssrn.6106971","name":"Enhancement of AV1 Compressed Images Using Image Blind Denoising Feature of Dual Convolutional Neural Network (DCBDNet)","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.6106971","authors":["Atiq urRehman","Waqar Ahmad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-21T07:42:02Z","doi":"10.2139/ssrn.6106971","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.2139/ssrn.6117386","name":"Delta Observer: Learning Continuous Semantic Manifolds between Neural Network Representations - From Geometric Divergence to Linear Semantic Accessibility","source":"crossref","abstract":"Neural networks solving the same computational task can learn fundamentally different internal representations depending on their architectural inductive biases. Understanding and comparing these representations remains a central challenge in interpretability research. We introduce the Delta Observer, a dual-encoder architecture that learns to map between the activation spaces of different neural network architectures by discovering shared semantic primitives. Through experiments on 4-bit binary addition, we train two architectures-a monolithic multi-layer perceptron and a compositional modular network-that both achieve perfect task performance while learning geometrically distinct representations. We then train the Delta Observer to map between these two representation spaces. Remarkably, we find that semantic information can be linearly accessible (𝑅 2 = 0.9505 for carry count prediction) without exhibiting strong geometric clustering (Silhouette coefficient = 0.0320), challenging the prevailing assumption that interpretability requires discrete, spatially separated feature clusters. Our results suggest semantic primitives are better characterized as continuous gradients in latent space than as discrete categorical labels-challenging prevailing assumptions in mechanistic interpretability. By training the Delta Observer on transparent \"glass box\" models to supervise opaque \"black box\" ones, we open a scalable path toward cross-architectural interpretability and inherently understandable systems.","url":"https://doi.org/10.2139/ssrn.6117386","authors":["Aaron Josserand-Austin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-10T10:32:47Z","doi":"10.2139/ssrn.6117386","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.18260/1-2--60451","name":"SHARE: A Neural Network Learning Module Bridges Biology, Computation, and Aritifical Intelligence Literacy","source":"crossref","abstract":"","url":"https://doi.org/10.18260/1-2--60451","authors":["Jennifer Hatch"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-21T14:49:31Z","doi":"10.18260/1-2--60451","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1109/iccsc67078.2026.11468514","name":"Optimized Adaptive Multiobjective Evolutionary Algorithm for Cognitive Radio Resource Scheduling Using Deep Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccsc67078.2026.11468514","authors":["Rushikesh Pawar"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-15T19:22:02Z","doi":"10.1109/iccsc67078.2026.11468514","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1007/s11432-025-4734-4","name":"Semi-tensor product-based convolutional neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11432-025-4734-4","authors":["Daizhan Cheng","Xiao Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-16T11:15:59Z","doi":"10.1007/s11432-025-4734-4","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1109/ccdc69976.2026.11560148","name":"OptiSVDD: An Optical Neural Network Framework for One-Class Anomaly Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ccdc69976.2026.11560148","authors":["Zongtao Chen","Na Wang","Xinyu Zhang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-24T19:47:19Z","doi":"10.1109/ccdc69976.2026.11560148","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1093/bib/bbag443","name":"A comprehensive survey on graph neural networks for gene regulatory network inference","source":"crossref","abstract":"Abstract The gene regulatory network (GRN) represents a complex web of genetic interactions that governs cellular functions and responses to environmental stimuli. Understanding these intricate relationships is crucial for advancing developmental biology, disease modeling, and therapeutic discovery. With the growing interest in graph-based approaches, graph neural networks (GNNs) have emerged as a powerful tool for GRN inference, offering the ability to capture high-dimensional dependencies and topological structures within gene networks. This survey presents the first comprehensive review of GNN-based methods for GRN inference, analyzing 16 state-of-the-art approaches. We categorize these methods based on their underlying architectures, inference strategies, and computational frameworks. Additionally, we provide a critical evaluation of their strengths, limitations, and real-world applicability. Unlike prior surveys that focus on either scRNA-seq or deep learning broadly, this work systematically unifies graph architectures, learning paradigms, and data regimes under a common benchmarking framework. By identifying key challenges—such as scalability, interpretability, and dataset limitations—this survey aims to guide both life scientists in selecting appropriate computational models and researchers in developing next-generation GRN inference techniques using graph-based learning.","url":"https://doi.org/10.1093/bib/bbag443","authors":["Noor Jamal Alkhateeb","Mamoun Awad"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-29T11:11:09Z","doi":"10.1093/bib/bbag443","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1007/s00500-025-11157-y","name":"Retraction Note: Analysis of industry convergence based on improved neural network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s00500-025-11157-y","authors":["Nan Ma"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-06T07:56:23Z","doi":"10.1007/s00500-025-11157-y","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1109/icssas68835.2026.11559517","name":"Optimization Enabled Neural Network for Early Prediction of ICU Admission","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icssas68835.2026.11559517","authors":["Abhishek Patil","Yuvraj Patil"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-22T19:52:40Z","doi":"10.1109/icssas68835.2026.11559517","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1007/978-981-95-8110-8_5","name":"Scaling Laws of Deep-Learning Neural Networks: Expressive Power","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-981-95-8110-8_5","authors":["Cheng Wang","Yuhang Lin"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-11T22:17:50Z","doi":"10.1007/978-981-95-8110-8_5","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1504/ijict.2026.10080617","name":"Multimodal deep neural network inference for design colour emotion quantification","source":"crossref","abstract":"","url":"https://doi.org/10.1504/ijict.2026.10080617","authors":["Wenjie Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-15T13:00:35Z","doi":"10.1504/ijict.2026.10080617","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.17775/cseejpes.2023.05580","name":"Neural Network Model with Cascaded Structure for State-of-Charge Estimation in Lithium-Ion Batteries","source":"crossref","abstract":"","url":"https://doi.org/10.17775/cseejpes.2023.05580","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-18T01:42:21Z","doi":"10.17775/cseejpes.2023.05580","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1109/iciscn67954.2026.11566513","name":"Nursing Risk Assessment of Child Using Temporal Spatial Weighted Probabilistic Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iciscn67954.2026.11566513","authors":["Lili Chai"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-23T19:43:02Z","doi":"10.1109/iciscn67954.2026.11566513","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1088/1742-6596/3206/1/012126","name":"Integrations with a neural network","source":"crossref","abstract":"Abstract In this contribution we describe a strategy to automatically perform parametric integrations through a specialized fitting of a neural network. The training is performed only once and the result can be used to obtain the value of the integral for any values of the unintegrated parameters. We show example applications and demonstrate that a usable accuracy can be obtained for integrations in 3 and 6 integrated dimensions with three unintegrated parameters.","url":"https://doi.org/10.1088/1742-6596/3206/1/012126","authors":["Daniel Maître","R. Santos-Mateos"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-14T10:32:37Z","doi":"10.1088/1742-6596/3206/1/012126","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.2351/7.0002049","name":"Physics-guided neural network framework for surface roughness prediction in additively manufactured metallic alloys","source":"crossref","abstract":"Surface roughness (Ra) significantly influences fatigue performance, corrosion behavior, and postprocessing requirements in additively manufactured metallic components. In practice, Ra optimization remains dependent on alloy-specific experimental campaigns, limiting scalability and slowing process qualification. To address this challenge, this study develops a physics-guided neural modeling framework for trend-level Ra prediction using physically motivated energy descriptors and data-efficient learning strategies. The approach integrates heat input, energy density, and normalized energy as physics-derived features, together with surrogate-assisted training designed to interpolate experimentally and literature-supported behavior within validated process windows. Separate neural networks were trained for 316L stainless steel, Ti-6Al-4V, and AlSi10Mg using an identical architecture, feature set, and hybrid data–physics loss formulation. The contribution lies in the engineering integration of physics-guided feature construction, controlled surrogate interpolation, and alloy-specific model training within a unified methodological workflow, rather than in proposing a new neural architecture or enforcing governing equations. Despite limited experimental datasets (75 samples for 316L and approximately 20 literature-derived samples per alloy), the framework demonstrates strong cross-validated trend consistency (R2 ≈ 0.98–0.995) under fivefold evaluation. Residual analysis and response-surface visualizations confirm stable and physically plausible behavior. The reported R2 values reflect agreement in dominant process–roughness trends rather than deterministic predictive certainty. Overall, the results indicate that a consistent physics-guided modeling strategy can support interpretable and data-efficient surface roughness prediction within experimentally qualified domains. The framework provides a foundation for extending physics-guided learning to related additive manufacturing quality metrics while remaining confined to validated operating windows.","url":"https://doi.org/10.2351/7.0002049","authors":["Aswin Karkadakattil"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-05T13:55:49Z","doi":"10.2351/7.0002049","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1115/1.4070470","name":"Physics-Informed Neural Network Engines to Predict Viscoelastic Behavior of Elastomers/Hydrogels","source":"crossref","abstract":"Abstract This study presents a physics-informed neural network (PINN) framework to model the nonlinear viscoelastic behavior of polymers and soft materials. By integrating principles from polymer science, statistical physics, and continuum mechanics, the model captures key inelastic features such as permanent set, strain rate dependence, and multirelaxation behavior. The formulation is based on an eight-chain network representation, with a rheological model composed of a rate-independent hyperelastic spring and a rate-dependent Maxwell element. To improve generalizability and reduce computational cost, the model employs machine-learned (ML) surrogate free energy functions trained with minimal experimental data. These surrogate models embed physical constraints, such as thermodynamic consistency and polyconvexity, directly into the learning architecture. As a result, the proposed framework outperforms conventional constitutive models in predictive accuracy and training efficiency. The approach is validated against experimental data for elastomers, hydrogels, and biological tissues across varying strain rates. Despite its complex formulation, the numerical implementation remains accessible and efficient, making it suitable for a wide range of soft material applications. The model can be easily integrated in elastomer aging-prediction software such as K-Load 2. The viscoelastic model developed here is intended for open-source incorporation into broader digital-twin frameworks for simulating the nonlinear viscoelastic response of soft materials, see Github for source codes. This ensures future reproducibility and facilitates industrial deployment while maintaining full scientific independence of the present study.","url":"https://doi.org/10.1115/1.4070470","authors":["Hossein Naderi","Roozbeh Dargazany"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-11-24T15:07:46Z","doi":"10.1115/1.4070470","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1109/ijcnn.2019.8852005","name":"Design Space Evaluation of a Memristor Crossbar Based Multilayer Perceptron for Image Processing","source":"crossref","abstract":"","url":"https://doi.org/10.1109/ijcnn.2019.8852005","authors":["Chris Yakopcic","B. Rasitha Fernando","Tarek M. Taha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2019-10-01T03:44:32Z","doi":"10.1109/ijcnn.2019.8852005","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.2139/ssrn.7258600","name":"Neural Network-Based Energy Management for a Grid-Connected Solar PV-Battery EV Charging Station with ANFIS MPPT","source":"crossref","abstract":"This paper presents an integrated artificial-neural-network (ANN) energy management system (EMS) for a single-phase grid-connected solar photovoltaic (PV) powered electric-vehicle (EV) charging station supported by stationary battery energy storage. An adaptive neuro-fuzzy inference system (ANFIS) generates the array-level maximum-power-point voltage reference from irradiance and temperature, while the ANN maps PV power and stationary-battery state of charge (SOC) to a supervisory grid-current reference. The common 500-V DC link couples the 2-kW PV source, bidirectional stationary-battery converter, bidirectional EVbattery converter, and grid inverter with an LCL filter. The MATLAB/Simulink results evaluate both learning models and the closedloop power stage. The ANFIS regression exhibits R = 1.0000 for the MPP-voltage target. The ANN achieves a best validation meansquared error of 5.9092×10^-3 at epoch 266 and an overall regression coefficient of R = 0.99996; target and predicted current references remain nearly coincident over 1000 samples. Under a stepped irradiance profile of 1000, 500, 300, 200, and 100 W/m^2, PV power follows approximately 2.0, 1.0, 0.6, 0.4, and 0.2 kW, respectively. The EV battery is continuously charged from an initial SOC near 9%, while the stationary battery, initialized near 70% SOC, supports the DC bus and the grid transitions from export at high irradiance to import as PV generation decreases. After start-up, the DC-link voltage is regulated close to 500 V. The combined results demonstrate accurate AI reference generation and coordinated PV-battery-grid power sharing for uninterrupted EV charging.","url":"https://doi.org/10.2139/ssrn.7258600","authors":["Premkumar K"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-14T06:55:16Z","doi":"10.2139/ssrn.7258600","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1038/s41598-025-34115-y","name":"Deep neural network-based biostatistical analysis for disease marker screening","source":"crossref","abstract":"","url":"https://doi.org/10.1038/s41598-025-34115-y","authors":["Xinyi Wang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-29T09:56:15Z","doi":"10.1038/s41598-025-34115-y","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.2139/ssrn.6127028","name":"Interpolation Approximation of Fractional Order Differential Equations and Its Physical Information Neural Network Solution","source":"crossref","abstract":"","url":"https://doi.org/10.2139/ssrn.6127028","authors":["Liu Xuan","Hengfei Ding","Haidong Qu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-24T14:13:16Z","doi":"10.2139/ssrn.6127028","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.3390/engproc2026127001","name":"Contactless Respiratory Monitoring Using Acoustic Convolutional Neural Network Classification","source":"crossref","abstract":"","url":"https://doi.org/10.3390/engproc2026127001","authors":["Kirill Kurskiy","Yuanying Qu","Minzhang Liu","Jiafeng Zhou"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-24T09:12:56Z","doi":"10.3390/engproc2026127001","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1002/dac.70360","name":"Network Traffic Detection in Software‐Defined Network Using Optimized Rotation‐Invariant Coordinate Convolutional Neural Network","source":"crossref","abstract":"ABSTRACT software‐defined networking (SDN) offers flexible traffic management but remains vulnerable to sophisticated cyberattacks, necessitating accurate and efficient network traffic detection. Existing SDN‐based intrusion detection systems often suffer from high computational cost, poor scalability, and reduced accuracy in high‐throughput or encrypted environments. To address these limitations, the NTD‐SDN‐RICCNN framework is proposed, which integrates fast robust iterative filtering (FRIF) for noise removal with spectral graph fast Fourier transform (SGFFT) for discriminative feature extraction. Rotation‐invariant coordinate convolutional neural network (RICCNN) optimized with weighted velocity‐guided gray wolf optimizer (WVGWO) for parameter tuning. The proposed method reduces redundant feature processing while improving detection accuracy and inference speed. Experiments on the SDN intrusion detection dataset show that NTD‐SDN‐RICCNN attains 99.7% accuracy, 99.6% precision, 99.5% recall, and reduces computational time by up to 32.5% compared to the state‐of‐the‐art baselines. These results demonstrate the method's effectiveness and scalability for real‐time SDN intrusion detection in diverse network conditions.","url":"https://doi.org/10.1002/dac.70360","authors":["V. Sujatha","S. Prabakeran"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-12-16T00:25:41Z","doi":"10.1002/dac.70360","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1080/0954898x.2025.2452274","name":"A novel skin cancer detection architecture using tangent rat swarm optimization algorithm enabled DenseNet","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2025.2452274","authors":["Balashanmuga Vadivu P","Om Prakash PG","Aravind Karrothu","Sriramakrishnan GV"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-02-28T06:58:31Z","doi":"10.1080/0954898x.2025.2452274","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.2514/6.2026-0847","name":"Contrail Persistence Prediction Using a Probabilistic Deep Neural Network Based Hybrid Modeling Framework","source":"crossref","abstract":"","url":"https://doi.org/10.2514/6.2026-0847","authors":["R Murali Krishnan","Anindya Bhaduri","Brett Matthews","Saikat Ray Majumder"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-29T07:09:51Z","doi":"10.2514/6.2026-0847","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1364/cleo_at.2026.jtu.87","name":"Robust Retrieval in a Photonic Hopfield Neural Network","source":"crossref","abstract":"We demonstrate a 100-neuron photonic Hopfield neural network using a spatial light modulator that stores and retrieves 13 noisy patterns near the critical capacity α c = 0 . 138, with further capacity gains achievable through added nonlinearity.","url":"https://doi.org/10.1364/cleo_at.2026.jtu.87","authors":["Michael Katidis","Khalid Musa","Santosh Kumar","Zhaotong Li","Frederick Long","Chunlei Qu","Yu-Ping Huang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-15T11:04:35Z","doi":"10.1364/cleo_at.2026.jtu.87","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1049/ntw2.12073","name":"WITHDRAWAL: Big Data Technology Fusion Back Propagation Neural Network in Product Innovation Design Method","source":"crossref","abstract":"WITHDRAWAL: R. Li, Q. Zeng, “Big Data Technology Fusion Back Propagation Neural Network in Product Innovation Design Method”, IET Networks (2022): e12073. https://ietresearch.onlinelibrary.wiley.com/doi/10.1049/ntw2.12073 The above article, published online on 05 December 2022, on Wiley Online Library ( wileyonlinelibrary.com ), has been withdrawn by agreement between the Institution of Engineering and Technology and John Wiley &amp; Sons Ltd. UK. The withdrawal has been agreed as this manuscript was under consideration, but the journal decided not to proceed with publication. However, the article was accidentally published due to a technical error on the part of Wiley, the publisher, as an unedited accepted article prior to the version of record.","url":"https://doi.org/10.1049/ntw2.12073","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2022-12-05T03:14:45Z","doi":"10.1049/ntw2.12073","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1016/j.jnca.2026.104455","name":"Alert prediction in computer networks using transformer-based temporal graph neural networks: Identifying the next victim","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.jnca.2026.104455","authors":["Zahra Makki Nayeri","Mohsen Rezvani"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-27T15:58:22Z","doi":"10.1016/j.jnca.2026.104455","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1109/comsnets67989.2026.11418221","name":"Unsupervised Neural Network for Joint Optimization of RIS Phase Shift and Resource Allocation in mmWave Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/comsnets67989.2026.11418221","authors":["Pujitha Mamillapalli","Yoghitha Ramamoorthi","Abhinav Kumar","Tomoki Murakami","Tomoaki Ogawa","Yasushi Takatori"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-10T19:50:41Z","doi":"10.1109/comsnets67989.2026.11418221","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1109/iciics67880.2026.11483601","name":"Role-Aware Contrastive Graph Neural Network for Social Network Analysis in Twitter Bot Detection","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iciics67880.2026.11483601","authors":["Ashish Anand","Lakshmi. S R","Kruthi. P","Senthil Kumar. P","Parkipandla Charith"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-11T19:57:57Z","doi":"10.1109/iciics67880.2026.11483601","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1016/j.egyai.2026.100876","name":"Accelerating gas-network feasibility screening with a physics-informed graph neural network surrogate","source":"crossref","abstract":"","url":"https://doi.org/10.1016/j.egyai.2026.100876","authors":["Dongrui Jiang","Jochen Garcke","Okan Akca","Jeremias Hollnagel","Bernhard Klaassen","Mehrnaz Anvari","Joachim Müller-Kirchenbauer"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-28T15:47:57Z","doi":"10.1016/j.egyai.2026.100876","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.26634/jpr.13.1.11292","name":"ICARECS-2026 - EEG -DRIVEN MOTOR IMAGERY CLASSIFICATION USING DEEP NEURAL NETWORK FOR NEUROREHABILITATION APPLICATIONS","source":"crossref","abstract":"The recognition of motor imagery (MI) event-related potential EEG in brain–computer interface (BCI) is still a difficulty problem owing to the low signal-to-noise ratio and strong non-stationary characteristic of EEG signal which varied with time, environment and individual. In this paper, a motor imagery classification framework based on a modified Improved Feature Network (IFNet) is proposed. The raw EEG signal passed through band-pass filtering and structured trial segmentation for extracting the motor imagery epochs. The EEG epochs were put into the enhanced IFNet for extracting the characteristic features. The convolutional layers in the network can deeply mine the features of different EEG epochs in spatial–temporal domain. The batch normalization and dropout could help to alleviate the deviation of network and enhance the robustness of the network. Unlike the general approach of manually selecting the appropriate features for the BCI tasks, the proposed network can automatically learn the relevant features for BCI performance. The experimental results show that the proposed framework can achieve the better BCI performance, and faster and more stable convergence of the network, and also with a larger inter-class separability.","url":"https://doi.org/10.26634/jpr.13.1.11292","authors":["Sathiyanathan N"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-03T09:41:37Z","doi":"10.26634/jpr.13.1.11292","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.29363/nanoge.matsusspring.2026.879","name":"Experimental Demonstration of Memristor Stateful Logics for In-Memory Sorting","source":"crossref","abstract":"","url":"https://doi.org/10.29363/nanoge.matsusspring.2026.879","authors":["Hongrong Hu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-16T08:04:37Z","doi":"10.29363/nanoge.matsusspring.2026.879","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1088/1361-6528/ae645a/v2/review1","name":"Review for \"Understanding the volatile memristor via direct observation of surface diffusion-regulated Cu-based conductive filaments\"","source":"crossref","abstract":"","url":"https://doi.org/10.1088/1361-6528/ae645a/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-25T21:02:46Z","doi":"10.1088/1361-6528/ae645a/v2/review1","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1109/icetis61828.2024.10593680","name":"Research on Fault-Tolerant Algorithm for Memristor Neural Networks Based on On-Chip Training","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icetis61828.2024.10593680","authors":["Lei Wang","Youyu Wu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2024-07-24T17:48:49Z","doi":"10.1109/icetis61828.2024.10593680","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1109/access.2023.3236424","name":"New Zero Power Memristor Emulator Model and Its Application in Memristive Neural Computation","source":"crossref","abstract":"","url":"https://doi.org/10.1109/access.2023.3236424","authors":["Prashant Kumar","Pushkar Srivastava","Rajeev Kumar Ranjan","Montree Kumngern"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2023-01-12T21:23:28Z","doi":"10.1109/access.2023.3236424","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1016/0893-6080(88)90437-6","name":"Analog “neural” network integration","source":"crossref","abstract":"","url":"https://doi.org/10.1016/0893-6080(88)90437-6","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2003-04-25T01:05:53Z","doi":"10.1016/0893-6080(88)90437-6","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1061/9780784486931.060","name":"An Uncertainty-Aware Leakage Detection Framework Based on Monte Carlo Dropout Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1061/9780784486931.060","authors":["Oluwabunmi Iwakin","Nazia Raza","Faegheh Moazeni"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-23T10:00:56Z","doi":"10.1061/9780784486931.060","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1007/s11277-026-12103-3","name":"Retraction Note: Detection of Assaults in Network Intrusion System using Rough Set and Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1007/s11277-026-12103-3","authors":["N. Syed Siraj Ahmed","A. B. Feroz Khan"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-01T10:59:05Z","doi":"10.1007/s11277-026-12103-3","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1007/s42452-026-08478-4","name":"Effect of the memristor on Hopfield artificial neural networks and their application in encryption","source":"crossref","abstract":"Abstract One way to strengthen encryption algorithms against attacks is to increase of encryption keys and the level of disorder in the encryption system. This paper investigates a cosine-based memristive model W(φ) = cos(φ) by analyzing the effects of signal amplitude, frequency, and boundary conditions. The proposed memristive element exhibits strong nonlinearity and memory properties, making it suitable for chaotic applications. The memristor is incorporated into a three-cell Hopfield neural network, where it operates as a synaptic coupling element, an external radiation sensor, and a dynamic weight controller. These mechanisms generate rich chaotic dynamics, which are verified using bifurcation diagrams, Lyapunov exponents, and phase space analysis. Numerical simulations in MATLAB are experimentally validated using an ESP32 microcontroller, with chaotic signals observed on an oscilloscope. Based on the proposed Hopfield, an image encryption scheme is developed and evaluated. The encryption results demonstrate high security performance, with entropy of 7.9977, near-zero pixel correlation, NPCR of 99.64%, and PSNR of 6.77. The complete system is practically implemented using an ESP32, a Raspberry Pi, and a computer, confirming its feasibility for real-time secure communication.","url":"https://doi.org/10.1007/s42452-026-08478-4","authors":["Abu-Talib Y. Abbas","Mayada Marid Abdul Hussain","Ghida Yousif Abbass","Kaushik Dehingia","Santosh Kumar Choudhary","Suresh Babu Baluguri"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-21T14:15:48Z","doi":"10.1007/s42452-026-08478-4","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1063/5.0298269","name":"Smart online payment system using convolutional neural network algorithm compared with artificial neural network algorithm","source":"crossref","abstract":"","url":"https://doi.org/10.1063/5.0298269","authors":["T. P. Anithaashri","N. Velmurugan","T. M. Nithya","K. S. Guruprakash"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-08T13:35:19Z","doi":"10.1063/5.0298269","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.37385/3n6z5n26","name":"Early Detection of Foetal Pathological Conditions with Neural Network Method: Implementation of Backpropagation Neural Network and SMOTE on Cardiotocography Data","source":"crossref","abstract":"This research focuses on the development of an effective classification model for early detection of foetal pathological conditions using Cardiotocography (CTG) data by utilising the Backpropagation Neural Network (BPNN) method. The high maternal mortality rate (MMR) and infant mortality rate (IMR) in Indonesia, including Riau Province, emphasise the importance of accurate prenatal diagnosis. The main challenge of this research is to address the class imbalance issue in the CTG dataset, which is biased towards the Normal class (77.9%) compared to the Suspect (13.9%) and Pathological (8.2%) classes. This problem was addressed by applying the Synthetic Minority Oversampling Technique (SMOTE). The model's performance was evaluated using K-Fold Cross Validation (5-Fold and 10-Fold). The test results showed that the combination of BPNN and SMOTE significantly improved performance, achieving a highest average accuracy of 92.66% and a maximum accuracy of 94.84% in the 10-Fold Cross Validation scheme. The resulting model is stable, has a high generalisation capability, and has great potential to be integrated into an Artificial Intelligence (AI)-based Clinical Decision Support System (CDSS) to support evidence-based health policies in reducing Maternal Mortality Rate (MMR) and Infant Mortality Rate (IMR).","url":"https://doi.org/10.37385/3n6z5n26","authors":["Elin Haerani","Fadhilah Syafria","Novriyanto Novriyanto","Ismail Marzuki"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-16T15:14:48Z","doi":"10.37385/3n6z5n26","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.5220/0014297000004052","name":"Weighted Spatio-Temporal Graph Neural Network: A Novel Approach for Video Anomaly Detection","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0014297000004052","authors":["Linda Zitouni","Nahla Bhiri","Anouar Ben Khalifa"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-14T15:02:05Z","doi":"10.5220/0014297000004052","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1039/d6tc00569a/v2/review1","name":"Review for \"Integrated Digital and Analog Resistive Switching in a Bis-Indolyl Derivative-Based Memristor for Artificial Synaptic Applications\"","source":"crossref","abstract":"","url":"https://doi.org/10.1039/d6tc00569a/v2/review1","authors":[],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-16T21:36:14Z","doi":"10.1039/d6tc00569a/v2/review1","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1109/iccworkshops63917.2026.11586695","name":"Multi-Hop IoT Network Fault Detection Using Spatio-Temporal Graph Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iccworkshops63917.2026.11586695","authors":["Bishal Lakha","Jianlin Guo","Kieran Parsons","Takenori Sumi","Yukimasa Nagai","Edoardo Serra"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-15T20:00:48Z","doi":"10.1109/iccworkshops63917.2026.11586695","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.54914/jit.v12i1.2783","name":"Deteksi Perokok Menggunakan Algoritma You Only Look Once (YOLO) dan Convolutional Neural Network (CNN)","source":"crossref","abstract":"Teknologi pengolahan citra terus berkembang dan dimanfaatkan untuk identifikasi aktivitas manusia secara visual, termasuk pemantauan aktivitas merokok di kawasan tanpa rokok. Penelitian ini mengembangkan deteksi dan pengenalan aktivitas merokok dengan menggabungkan YOLO (You Only Look Once) untuk pendeteksian objek dan CNN (Convolutional Neural Network) sebagai pengklasifikasi citra. YOLO melakukan deteksi dan cropping objek manusia, sedangkan CNN mengklasifikasikan aktivitas merokok dan tidak merokok berdasarkan ciri visual. Dataset berjumlah 3.254 yang telah diproses menghasilkan masing-masing 560 citra valid untuk kelas smoking dan not smoking. Hasil pelatihan menunjukkan akurasi 96,09% pada data latih dan 94,44% pada data validasi, dengan loss yang stabil, serta evaluasi model menghasilkan accuracy 94,44%, precision 92,55%, recall 96,67%, F1-score 94,57%, dan Average Precision (AP) 98,72%, menunjukkan performa klasifikasi yang sangat baik. Model juga mampu mendeteksi aktivitas merokok secara responsif pada citra dan kamera real-time, membuktikan efektivitas kombinasi YOLO dan CNN dalam membangun deteksi otomatis dan berpotensi diterapkan di kawasan tanpa rokok.","url":"https://doi.org/10.54914/jit.v12i1.2783","authors":["Aprilian Gevindo","Syafri Arlis"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-30T09:20:21Z","doi":"10.54914/jit.v12i1.2783","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.5220/0015032100005056","name":"Mathematical Analysis of Attention Mechanisms and Research on the Linear Structure of Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0015032100005056","authors":["Keyu Chen"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-27T11:47:11Z","doi":"10.5220/0015032100005056","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.2514/6.2026-1117","name":"A Novel Parameterization Framework and Neural Network-Based Surrogate Modeling for Rotorcraft Fuselage Aerodynamic Prediction.","source":"crossref","abstract":"","url":"https://doi.org/10.2514/6.2026-1117","authors":["Manmohan Thakur","Apurva Anand","Koushik Marepally","James Baeder"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-29T07:39:48Z","doi":"10.2514/6.2026-1117","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1109/netps70564.2026.11650319","name":"Automatic Construction and Key Process Identification of Power Grid Construction Project Schedule Network Based on Graph Neural Network and Critical Path Method","source":"crossref","abstract":"","url":"https://doi.org/10.1109/netps70564.2026.11650319","authors":["Pengfei Wang","Lexuan Cao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-24T19:11:21Z","doi":"10.1109/netps70564.2026.11650319","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1109/iciscn67954.2026.11566462","name":"Spatio-Temporal Graph Neural Network with Global Spatio-Temporal Network for the Traffic Flow Prediction","source":"crossref","abstract":"","url":"https://doi.org/10.1109/iciscn67954.2026.11566462","authors":["K. Jyoshna","Ranjith Kumar Peddi","Pooja Nayak. S","Dhanamalar. M","S. Punitha"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-23T19:43:02Z","doi":"10.1109/iciscn67954.2026.11566462","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1080/03772063.2025.2567598","name":"Advanced Detection of VPN Network Traffic Utilizing an Optimized Curvature Graph Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1080/03772063.2025.2567598","authors":["Anitha Duraisamy","Nithya Arunagiri","Sharmila Vadivel","Velmurugan Ayyamperumal"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-24T03:28:34Z","doi":"10.1080/03772063.2025.2567598","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1109/csnt69054.2026.11502286","name":"Real-Time 3D Point Cloud Segmentation for Volumetric Weight Estimation using a Neural Network in a Mixed Reality Environment","source":"crossref","abstract":"","url":"https://doi.org/10.1109/csnt69054.2026.11502286","authors":["Shane Robertson","Muhammad Diyan","Hiba Alsmadi"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-08T19:37:43Z","doi":"10.1109/csnt69054.2026.11502286","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.2478/qic-2026-0026","name":"Neural Network-Based Active Vibration Suppression and Accurate Trajectory Tracking for Flexible Robotic Arms","source":"crossref","abstract":"Abstract Due to the expansion of the operating space of the mobile robotic arm and the improvement of the mobile platform’s ability to interact with the environment, it is widely used in the fields of transportation, search and rescue, security and surveillance. The study firstly designs the vibration suppression scheme of the robotic arm, uses the observer for observing the modal variables of the system, and observes the external perturbations as the state variables of the system, and then proposes the residual vibration suppression strategy based on the input shaping and the adaptive robust control method based on neural network, which utilizes the neural network to approximate the unknown nonlinearities in the controller and the observer, and designs the speed based on the adaptive neural network observer and controller, eliminating the influence of external factors on the control system and improving the control accuracy. Finally, a robotic arm experimental platform is built, and the control algorithm is verified through a large number of simulation experiments, and the research results show that the speed has a significant effect on the dynamic characteristics of the flexible arm, and the vibration curve range is smaller in the case of increasing the controller, and compared with the other four control methods, the tracking performance of the control method in this paper is improved by 15.8% to 65.4%, and it is able to better inhibit the elastic vibration of the flexible arm The tracking performance is improved by 15% to 65.4% compared with the other four control methods, which can better suppress the elastic vibration of flexible arm.","url":"https://doi.org/10.2478/qic-2026-0026","authors":["Yanshu Li"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-03T13:11:37Z","doi":"10.2478/qic-2026-0026","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1080/0954898x.2025.2457955","name":"Hybrid ladybug Hawk optimization-enabled deep learning for multimodal Parkinson’s disease classification using voice signals and hand-drawn images","source":"crossref","abstract":"","url":"https://doi.org/10.1080/0954898x.2025.2457955","authors":["Shanthini Shanmugam","Chandrasekar Arumugam"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2025-03-04T08:53:51Z","doi":"10.1080/0954898x.2025.2457955","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.51353/hf480q42","name":"Prediksi Prognosis Kanker Payudara Menggunakan Hybrid Artificial Neural Network Dan Gaussian Naïve Bayes","source":"crossref","abstract":"Breast cancer is one of the types of cancer that causes the most deaths in women in the world. Breast cancer prognosis is important to assist medical personnel in predicting the possibility of recurrence so that treatment can be provided more effectively. This study aims to implement a hybrid Artificial Neural Network (ANN) and Gaussian Naïve Bayes method for breast cancer prognosis prediction using the Breast Cancer Wisconsin Prognostic (WPBC) dataset. The dataset consisted of 198 patient records with 35 numerical features. The research stages included data preprocessing, normalization, splitting the dataset into training and testing data using an 80:20 ratio, feature extraction using ANN, and classification using Gaussian Naïve Bayes. Unlike previous studies that generally used single methods, this study utilizes ANN as a feature extractor before the classification process using Gaussian Naïve Bayes. ANN was used with one hidden layer containing 16 neurons to learn non-linear relationships among features before the classification process. Model evaluation was conducted using a confusion matrix with accuracy, precision, recall, and F1-score metrics. The experimental results showed that the hybrid ANN-Gaussian Naïve Bayes method achieved an accuracy of 90%, precision of 72.73%, recall of 88.89%, and an F1-score of 80%. These results indicate that the hybrid method provides better classification performance compared to single methods in breast cancer prognosis prediction.","url":"https://doi.org/10.51353/hf480q42","authors":["Jesika Octavia Hutagaol","Margaretha Yohanna","Harlen Gilbert Simanullang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-27T08:01:28Z","doi":"10.51353/hf480q42","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1145/3807246.3807259","name":"Research on Tea Polyphenol Detection Model Based on Residual Attention Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3807246.3807259","authors":["Shixian Hu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-09T10:50:37Z","doi":"10.1145/3807246.3807259","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1088/1742-5468/ae195e","name":"Gaussian universality in neural network dynamics with generalized structured input distributions","source":"crossref","abstract":"Abstract Analyzing neural network dynamics via stochastic gradient descent is crucial to building theoretical foundations for deep learning. Previous work has analyzed structured inputs within the hidden manifold model , often under the simplifying assumption of a Gaussian distribution. We extend this framework by modeling inputs as Gaussian mixtures to better represent complex, real-world data. Through empirical and theoretical investigation, we demonstrate that with proper standardization, the learning dynamics converges to the behavior seen in the simple Gaussian case. This finding exhibits a form of universality, where diverse structured distributions yield results consistent with Gaussian assumptions, thereby strengthening the theoretical understanding of deep learning models.","url":"https://doi.org/10.1088/1742-5468/ae195e","authors":["Jaeyong Bae","Hawoong Jeong"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-01-23T10:42:54Z","doi":"10.1088/1742-5468/ae195e","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.2514/6.2026-2664","name":"Adaptive Aerospace Intrusion Detection Using HyperNEAT-Driven Neural Network Evolution","source":"crossref","abstract":"","url":"https://doi.org/10.2514/6.2026-2664","authors":["Mustafa I. Akbas","Regan B. Bossie","Tyler Donay","Richard Pepe","Megan de Jonge"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-03T08:40:23Z","doi":"10.2514/6.2026-2664","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.5220/0014468700004052","name":"SpiTranNet-LIF: A Spiking Neural Network–Transformer Framework for Efficient Motor Imagery Decoding","source":"crossref","abstract":"","url":"https://doi.org/10.5220/0014468700004052","authors":["Maryam Titkanlou","Alireza Hashemi","Roman Mouček"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-03-15T06:35:40Z","doi":"10.5220/0014468700004052","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1088/1674-1056/ae68f9","name":"Symmetrical Turing instability in Chua corsage memristor siblings-based two-cell network","source":"crossref","abstract":"Abstract The Turing instability, a counterintuitive phenomenon in which two quiescent cells lose stability when coupled through a dissipative environment, has been explained via the edge of chaos theory. While the classical Turing instability and its local form have been recently elucidated, its symmetrical form — a distinct class of symmetry-breaking phenomena wherein two identical cells, each poised at a mirror-symmetrical stable operating point, undergo destabilization and bifurcate into two distinct mirror-symmetrical stable states under opposite bias voltages — has not been reported yet. This paper introduces a current-controlled odd-symmetrical Chua corsage memristor (OS-CCM) and employs it to investigate the symmetrical Turing instability in a resistively coupled two-cell network. Coupling two identical bistable OS-CCM-based cells, each originally poised at identical mirror-symmetrical stable states, via a passive resistor destabilizes their original stability, giving rise to two distinct stable states and ultimately leading to quadristability, referring to a dynamical phenomenon with four coexisting stable states, which demonstrates the emergence of symmetrical Turing instability. The quantitative condition for the emergence of this phenomenon is analytically derived and precisely determined through eigenvalue analysis. Both numerical simulations and hardware experiments confirm the correctness of the theoretical analysis.","url":"https://doi.org/10.1088/1674-1056/ae68f9","authors":["Zhicheng 桎成 Tian 田","Peipei 培培 Jin 靳","Shutong 姝彤 Liu 刘","Meiyuan 梅园 Gu 顾","Long 龙 Chen 陈","Guangyi 光义 Wang 王"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-06T09:47:15Z","doi":"10.1088/1674-1056/ae68f9","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.7148/2026-0540","name":"2d smoke pressure solving using custom transformer-based deep neural network","source":"crossref","abstract":"High-resolution simulation of incompressible smoke is computationally expensive because it requires repeatedly enforcing incompressibility through large Poisson solves while advecting fields that contain fine-scale structure. Although classical Eulerian projection-based solvers are robust and widely used, their cost grows rapidly with grid resolution, making high-fidelity results difficult to achieve in interactive settings. Recent progress in deep learning suggests that expensive numerical operators can be approximated by compact neural surrogates. In this work, we accelerate the pressure projection step in a two-dimensional smoke solver by replacing the iterative Poisson solver with a lightweight neural model. Instead of learning the entire simulation pipeline, we target the dominant linear solve and learn a direct mapping from the divergence of the intermediate velocity field to the corresponding pressure field used for projection. Training data is generated directly from the baseline simulator using its existing discretization and boundary handling, ensuring consistency between supervision and deployment. The proposed network is a multi-scale transformer-based encoder-decoder designed for efficient inference. To preserve physical correctness, training uses a composite objective that combines pressure reconstruction with an operator-level constraint that penalizes violations of the Poisson equation. The learned solver is integrated as a drop-in module within the simulator and supports varying runtime resolutions through interpolation before and after inference. The resulting system provides substantial speed-ups of the projection stage while maintaining visually plausible behavior over the evaluated sequences, enabling faster high-resolution smoke generation without modifying the remaining components of the solver.","url":"https://doi.org/10.7148/2026-0540","authors":["Michal Wieczorek","Marcin Wozniak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-06-30T16:55:14Z","doi":"10.7148/2026-0540","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.2139/ssrn.6793368","name":"Physics-Informed Graph Neural Network Surrogate for Steady-State Gas Network Simulation and Feasibility Analysis","source":"crossref","abstract":"Large-scale gas-network scenario evaluation is essential for integrated multi-carrier energy-system planning, particularly as gas infrastructure becomes increasingly coupled with power, heat, and hydrogen pathways. Conventional nonlinear hydraulic solvers provide high-fidelity feasibility assessment but are computationally expensive for stochastic screening and large scenario ensembles. Conversely, unconstrained learning-based surrogates can generate hydraulically infeasible states by violating mass balance or pressure consistency. This study develops a physics-informed graph neural network (PI-GNN) surrogate for steady-state gas-network simulation and feasibility assessment. The proposed model uses an edge-centric architecture to predict pipe-level squared-pressure differences and flows. A differentiable projection layer enforces nodal mass conservation on predicted flows, while Laplacian-based reconstruction maps edge pressure differences to topologically consistent nodal pressures.The framework is evaluated on GasLib-134, GasLib-135, and GasLib-582 using stochastically generated operating scenarios. On the meshed 582-node network trained with 5000 scenarios, the PI-GNN achieves a pressure mean absolute error of 1.05 bar, corresponding to 1.3% of the realized pressure range, with (R2 = 0.981). Projected-flow predictions achieve (R2 = 0.972), while mass-balance residuals are reduced to numerical precision, on the order of 10-5–10-4 Nm3/s. Compared with the MYNTS reference solver, the surrogate reduces per-scenario runtime from seconds to milliseconds, evaluating the largest benchmark in less than 40 ms. A multi-regional loadability study further shows that the PI-GNN reproduces feasibility boundaries and identifies dominant bottleneck structures consistent with reference hydraulic simulations. The proposed framework provides a constraint-aware planning accelerator for high-volume scenario screening, sensitivity analysis, and prioritization of cases requiring detailed hydraulic verification.","url":"https://doi.org/10.2139/ssrn.6793368","authors":["Dongrui Jiang","Jochen Garcke","Okan Akca","Jeremias Hollnagel","Bernhard Klaassen","Mehrnaz Anvari","Joachim Müller-Kirchenbauer"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-19T07:38:15Z","doi":"10.2139/ssrn.6793368","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1109/csnt69054.2026.11502173","name":"Graph Neural Network Framework for Interpretable EEG-Based Emotion Recognition Using Frequency-Band and Connectivity Analysis","source":"crossref","abstract":"","url":"https://doi.org/10.1109/csnt69054.2026.11502173","authors":["Ch Anwar Ul Hassan","Azhar Imran","Khursheed Aurangzeb","Hashim Elshafie"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-08T19:37:43Z","doi":"10.1109/csnt69054.2026.11502173","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1109/icaace69793.2026.11508645","name":"Consumer Purchase Intent Prediction in Cross-Border E-Commerce Based on a Fusion Model of Long Short-Term Memory Network and Convolutional Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1109/icaace69793.2026.11508645","authors":["Yuchen Man"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-15T02:40:33Z","doi":"10.1109/icaace69793.2026.11508645","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1007/978-3-032-08514-6_1","name":"Convolutional Neural Networks: Operation Principles and Applications","source":"crossref","abstract":"","url":"https://doi.org/10.1007/978-3-032-08514-6_1","authors":["Haosen Yu","Peiyao Sun","Bingkai Ding","Basel Halak"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-05T23:10:00Z","doi":"10.1007/978-3-032-08514-6_1","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.52972/hoaq.vol17no1.p76-84","name":"PENERAPAN ALGORITMA ARTIFICIAL NEURAL NETWORK UNTUK KLASIFIKASI KUALITAS BUAH APEL","source":"crossref","abstract":"Penelitian ini bertujuan untuk mengklasifikasikan kualitas buah apel menggunakan algoritma Artificial Neural Network (ANN) sebagai solusi terhadap keterbatasan metode seleksi manual yang cenderung subjektif, memakan waktu, dan kurang efisien pada skala industri. Dataset yang digunakan diperoleh dari situs Kaggle dan terdiri dari 4.000 data sampel apel dengan tujuh atribut fisik: ukuran, berat, kemanisan, kerenyahan, kejuicy-an, kematangan, dan keasaman. Data dibagi menjadi tiga bagian menggunakan metode stratified hold-out sampling, yaitu 70% untuk pelatihan, 15% untuk validasi, dan 15% untuk pengujian. Model ANN yang diterapkan menggunakan arsitektur Multilayer Perceptron (MLP) dengan dua hidden layer berisi 20 dan 10 neuron serta dilatih menggunakan algoritma Scaled Conjugate Gradient. Evaluasi dilakukan menggunakan confusion matrix dan metrik seperti akurasi, presisi, recall, dan F1-score. Hasil menunjukkan bahwa model ANN mencapai akurasi 92% pada data pengujian dengan performa optimal pada epoch ke-106. Perbandingan dengan algoritma lain seperti Random Forest (88,3%) dan Support Vector Machine (74,7%) menunjukkan keunggulan ANN dalam klasifikasi kualitas apel. Kurva ROC dan histogram error memperkuat bukti bahwa model memiliki generalisasi yang baik tanpa overfitting. Penelitian ini membuktikan bahwa ANN dapat menjadi solusi efektif dan efisien dalam otomasi penilaian mutu buah apel serta berpotensi diterapkan lebih luas pada produk hortikultura lainnya. This study aims to classify apple fruit quality using the Artificial Neural Network (ANN) algorithm as a solution to the limitations of manual selection methods, which tend to be subjective, time-consuming, and inefficient on an industrial scale. The dataset used was obtained from Kaggle and consists of 4,000 apple samples with seven physical attributes: size, weight, sweetness, crunchiness, juiciness, ripeness, and acidity. The data was divided into three parts using the stratified hold-out sampling method: 70% for training, 15% for validation, and 15% for testing. The ANN model implemented uses a Multilayer Perceptron (MLP) architecture with two hidden layers containing 20 and 10 neurons, and it is trained using the Scaled Conjugate Gradient algorithm. Evaluation was performed using a confusion matrix and metrics such as accuracy, precision, recall, and F1-score. The results show that the ANN model achieved 92% accuracy on the test data, with optimal performance reached at epoch 106. Comparisons with other algorithms such as Random Forest (88.3%) and Support Vector Machine (74.7%) demonstrate the superiority of ANN in classifying apple quality. The ROC curve and error histogram further confirm that the model has good generalization capabilities without overfitting. This study demonstrates that ANN is an effective and efficient solution for automating the assessment of apple fruit quality and has the potential to be more broadly applied to other horticultural products.","url":"https://doi.org/10.52972/hoaq.vol17no1.p76-84","authors":["Mega","Nia Marselina","Olivia Brilliant Chang"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-05-07T10:19:56Z","doi":"10.52972/hoaq.vol17no1.p76-84","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.54914/jtt.v12i1.2597","name":"Klasifikasi Buah Kelapa Sawit dengan Convolutional Neural Network Arsitektur Inception-v4","source":"crossref","abstract":"Industri kelapa sawit memegang peranan penting dalam perekonomian Indonesia, sehingga proses klasifikasi buah berdasarkan tingkat kematangan menjadi krusial untuk menjamin kualitas produksi minyak sawit. Penelitian ini bertujuan mengembangkan sistem klasifikasi buah kelapa sawit menjadi kategori matang dan mentah dengan menggunakan algoritma Convolutional Neural Network berbasis arsitektur Inception-v4. Dataset penelitian terdiri dari 2.900 gambar, yang terbagi menjadi data pelatihan (2.000), validasi (500), dan pengujian (400). Tahapan penelitian meliputi pengumpulan data, pre-processing (deteksi duplikat, augmentasi, dan normalisasi), pemodelan menggunakan Inception-v4, pelatihan model, evaluasi, dan interpretasi hasil. Evaluasi dilakukan menggunakan metrik accuracy, precision, recall, f1-score, dan confusion matrix. Hasil menunjukkan bahwa model Inception-v4 mampu mengklasifikasikan buah kelapa sawit dengan akurasi validasi tertinggi sebesar 95%. Eksperimen dengan berbagai optimizer (SGD, Adam, RMSprop, Adagrad, Adadelta) dilakukan untuk meningkatkan performa. Penelitian ini menunjukkan bahwa Inception-v4 efektif dalam klasifikasi buah kelapa sawit dan dapat diterapkan pada industri perkebunan untuk meningkatkan efisiensi panen dan produksi.","url":"https://doi.org/10.54914/jtt.v12i1.2597","authors":["Theresia Kurniati Seran","Septyan Eka Prastya","Muhammad Zulfadhilah","Rudy Ansari"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-07-15T07:45:04Z","doi":"10.54914/jtt.v12i1.2597","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1145/3810280.3810321","name":"Flow‑Based Confidence Evaluation Method for Equivariant Neural Network","source":"crossref","abstract":"","url":"https://doi.org/10.1145/3810280.3810321","authors":["Zhuoyu Li","Dingkang Hu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-08-19T07:50:42Z","doi":"10.1145/3810280.3810321","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.23969/infomatek.v28i1.36796","name":"Sistem Klasifikasi Citra Daun Obat Tradisional Dayak Kenyah Menggunakan Metode Convolutional Neural Network Dengan Arsitektur MobileNetV2","source":"crossref","abstract":"Masyarakat Suku Dayak Kenyah mewarisi pengetahuan tradisional dalam pemanfaatan tumbuhan sebagai obat. Namun, kemiripan morfologi antarspesies, terutama pada bagian daun, sering menjadi hambatan dalam proses identifikasi yang akurat. Penelitian ini bertujuan untuk mengembangkan sistem klasifikasi citra daun obat tradisional Suku Dayak Kenyah menggunakan Convolutional Neural Network (CNN) dengan arsitektur MobileNetV2. Tiga jenis daun yang menjadi fokus penelitian adalah daun senggani (Melastoma malabathricum L.), daun jarak (Jatropha curcas), dan daun sengkubak (Pycnarrhena cauliflora). Dataset penelitian terdiri dari 900 citra utama yang telah melalui tahap preprocessing dan augmentation, menghasilkan total 2.340 citra yang dibagi menjadi 80% data latih, 10% data validasi, dan 10% data uji. Pelatihan model dilakukan hingga 50 epoch, menghasilkan akurasi pelatihan dan validasi sebesar 100%, serta validation loss sebesar 0,0565. Evaluasi menggunakan data uji menunjukkan nilai precision, recall, dan F1-score rata-rata sebesar 100%. Namun, pengujian dengan 90 data uji eksternal (di luar dataset) menunjukkan penurunan performa dengan nilai precision 88%, recall 84%, dan F1-score 83% yang mengindikasikan adanya keterbatasan dalam generalisasi model terhadap data di luar distribusi pelatihan. Meskipun begitu, model MobileNetV2 mampu memberikan performa tinggi dalam klasifikasi citra daun pada dataset terkontrol serta mengidentifikasi tantangan generalisasi pada data eksternal. Oleh karena itu, model ini berpotensi dikembangkan lebih lanjut sebagai dasar sistem identifikasi tanaman obat berbasis citra daun yang adaptif dan aplikatif di lapangan.","url":"https://doi.org/10.23969/infomatek.v28i1.36796","authors":["Arif Fadllullah","Tia Natalia"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-17T09:50:43Z","doi":"10.23969/infomatek.v28i1.36796","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1002/eng2.70678","name":"Adaptive Calculation Method of Line Loss of Distribution Network Based on Genetic Algorithm and Artificial Neural Network","source":"crossref","abstract":"ABSTRACT Traditional methods for calculating distribution line losses often rely on complex mathematical models and extensive operational data, leading to cumbersome processes that struggle to ensure accuracy and timeliness in practical applications. To address these limitations, this paper proposes an adaptive calculation method for distribution line losses based on a genetic algorithm (GA) and an artificial neural network (ANN). The approach integrates automated data preprocessing using MATLAB's mapminmax function for feature normalization, an improved k ‐means clustering algorithm for data grouping, and a genetic algorithm to optimize the initial weights and thresholds of a backpropagation (BP) neural network. A 16‐4‐1 network structure is constructed, and a time‐division calculation model is introduced to enable simultaneous computation across multiple lines. Experimental results demonstrate that the proposed method significantly reduces the mean squared error and enhances the accuracy and efficiency of line loss calculation. The hybrid GA‐BP model combines global search capability with nonlinear fitting, enhances data preprocessing and clustering techniques, and improves data quality and model generalization ability.","url":"https://doi.org/10.1002/eng2.70678","authors":["Tianjun Chen","Tao Deng","Junyang Wu","Ming Wen","Chengming Liu"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-04-02T02:39:23Z","doi":"10.1002/eng2.70678","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"doi:10.1140/epjp/s13360-026-07322-3","name":"Hyperbolic recurrent neural network as the first type of non-Euclidean neural quantum state ansatz","source":"crossref","abstract":"","url":"https://doi.org/10.1140/epjp/s13360-026-07322-3","authors":["Harriet L. Dao"],"tags":[],"confidence":0.7,"sites":["neuromorphic"],"publishedDate":"2026-02-24T18:56:28Z","doi":"10.1140/epjp/s13360-026-07322-3","addedAt":"2026-09-01T01:48:35.581Z","updatedAt":"2026-09-01T01:48:35.581Z"},{"id":"oa:W7125261655","name":"Bayesian Inference via GeTe x ‐OTS Based Stochastic Synapse for Uncertainty‐Aware Medical Diagnostics","source":"openalex","abstract":"ABSTRACT Neuromorphic architectures leveraging stochastic device physics present a transformative approach for implementing probabilistic computing paradigms capable of intrinsic uncertainty quantification. In this work, we present a germanium‐telluride‐based ovonic threshold switch (GeTe x ‐OTS) exhibiting inherent stochastic dynamics, integrated into a compact 1‐selector‐1‐transistor‐1‐resistor (1S1T1R) synaptic unit. The OTS devices are demonstrated within an 8K‐array, confirming the future scalability for neuromorphic systems. Experimental validation on the GeTe x devices shows stable Gaussian‐distributed threshold voltage fluctuations ( σ = 100 mV), enabling precise control of synaptic activation probability through input pulse modulation. Utilizing this intrinsic stochasticity, we implement mini hardware realization of a Monte Carlo Dropconnect (MC‐Dropconnect) neural network, directly demonstrating the feasibility of the system. Applied to COVID‐19 diagnosis using chest X‐ray images, our system achieves robust uncertainty quantification through predictive entropy, improving classification accuracy to 98.1%, compared to 96.0% with a deterministic baseline. This uncertainty‐aware hardware design strategy provides a scalable pathway for implementing energy‐efficient neuromorphic systems with native uncertainty estimation capabilities.","url":"https://doi.org/10.1002/smm2.70062","authors":["Xinyu Wen","Lun Wang","K. L. Wang","Vivian Zhao","Zixuan Liu","Kexun He","J. Joshua Yang","Hao Tong","Xiangshui Miao","Yuhui He"],"tags":["Neuromorphic engineering","Computer science","Scalability","Probabilistic logic","Stochastic computing"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2026-01-21","doi":"https://doi.org/10.1002/smm2.70062","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4393148535","name":"Emerging ferroelectric materials ScAlN: applications and prospects in memristors","source":"openalex","abstract":"The research found that after doping with rare earth elements, a large number of electrons and holes will be produced on the surface of AlN, which makes the material have the characteristics of spontaneous polarization. A new type of ferroelectric material has made a new breakthrough in the application of nitride-materials in the field of integrated devices. In this paper, the application prospects and development trends of ferroelectric material ScAlN in memristors are reviewed. Firstly, various fabrication processes and structures of the current ScAlN thin films are described in detail to explore the implementation of their applications in synaptic devices. Secondly, a series of electrical properties of ScAlN films, such as the current switching ratio and long-term cycle durability, were tested to explore whether their electrical properties could meet the basic needs of memristor device materials. Finally, a series of summaries on the current research studies of ScAlN thin films in the synaptic simulation are made, and the working state of ScAlN thin films as a synaptic device is observed. The results show that the ScAlN ferroelectric material has high residual polarization, no wake-up function, excellent stability and obvious STDP behavior, which indicates that the modified material has wide application prospects in the research and development of memristors.","url":"https://doi.org/10.1039/d3mh01942j","authors":["Dong-Ping Yang","Xin‐Gui Tang","Qijun Sun","Jiaying Chen","Yanping Jiang","Dan Zhang","Huafeng Dong"],"tags":["Materials science","Ferroelectricity","Memristor","Doping","Electron"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-01-01","doi":"https://doi.org/10.1039/d3mh01942j","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4392745672","name":"Research Progress in Dielectric-Layer Material Systems of Memristors","source":"openalex","abstract":"With the rapid growth of data storage, traditional von Neumann architectures and silicon-based storage computing technologies will reach their limits and fail to meet the storage requirements of ultra-small size, ultra-high density, and memory computing. Memristors have become a strong competitor in next generation memory technology because of their advantages such as simple device structure, fast erase speed, low power consumption, compatibility with CMOS technology, and easy 3D integration. The resistive medium layer is the key to achieving resistive performance; hence, research on memristors mainly focuses on the resistive medium layer. This paper begins by elucidating the fundamental concepts, structures, and resistive-switching mechanisms of memristors, followed by a comprehensive review of how different resistive storage materials impact memristor performance. The categories of memristors, the effects of different resistive materials on memristors, and the issues are described in detail. Finally, a summary of this article is provided, along with future prospects for memristors and the remaining issues in the large-scale industrialization of memristors.","url":"https://doi.org/10.3390/inorganics12030087","authors":["Chunxia Wang","Xuemei Li","Zhendong Sun","Yang Liu","Ying Yang","Lijia Chen"],"tags":["Memristor","Resistive random-access memory","Resistive touchscreen","Von Neumann architecture","Computer science"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-03-13","doi":"https://doi.org/10.3390/inorganics12030087","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4412166147","name":"Transparent conductive oxides as a material platform for a realization of all-optical photonic neural networks","source":"openalex","abstract":"Photonics integrated circuits have an enormous potential to serve as a framework for a new class of information processing machines and can enable ultrafast artificial neural networks. They can overcome the existing speed and power limits of the electronic processing elements and provide additional benefits of photonics such as high-bandwidth, sub-nanosecond latencies and low-energy interconnect credentials leading to a new paradigm called neuromorphic photonics. The main obstacle to realizing such a task is a lack of proper material platform that imposes serious requirements on the architecture of the network. Here we suggest and justify that transparent conductive oxides can be an excellent candidate for such a task as they provide nonlinearity and bistability under both optical and electrical inputs.","url":"https://doi.org/10.1038/s41598-025-96226-w","authors":["Jacek Gosciniak","Jacob B. Khurgin"],"tags":["Realization (probability)","Photonics","Computer science","Artificial neural network","Electrical conductor"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-07-10","doi":"https://doi.org/10.1038/s41598-025-96226-w","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4406187914","name":"Process-dependent ferroelectric and memristive properties in polycrystalline Ca:HfO2-based devices","source":"openalex","abstract":"Memristors are considered key building blocks for developing neuromorphic or in-memory computing hardware. Here, we study the ferroelectric and memristive response of Pt/Ca:HfO2/Pt devices fabricated on silicon by spin-coating from chemical solution deposition followed by a pyrolysis step and a final thermal treatment for crystallization at 800°C for 90 s. For pyrolysis temperature of 300°C, the annealed samples are ferroelectric while for 400°C a dielectric behavior is observed. For each case, we found a distinct, forming-free, memristive response. Ferroelectric devices can sustain polarization switching and memristive behavior simultaneously. Aided by numerical simulations, we describe the memristive behavior of ferroelectric devices arising from oxide-metal Schottky barriers modulation by both the direction of the electrical polarization and oxygen vacancy electromigration. For non-ferroelectric samples, only the latter effect controls the memristive behavior.","url":"https://doi.org/10.3389/fmats.2024.1501000","authors":["C. Ferreyra","Miguel Badillo","M. J. Sánchez","Mónica Acuautla","Beatriz Noheda","D. Rubi"],"tags":["Ferroelectricity","Materials science","Crystallite","Process (computing)","Nanotechnology"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-01-08","doi":"https://doi.org/10.3389/fmats.2024.1501000","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4390880708","name":"Artificial Intelligence-Based Aquaculture System for Optimizing the Quality of Water: A Systematic Analysis","source":"openalex","abstract":"The world population is expected to grow to around 9 billion by 2050. The growing need for foods with high protein levels makes aquaculture one of the fastest-growing food industries in the world. Some challenges of fishing production are related to obsolete aquaculture techniques, overexploitation of marine species, and lack of water quality control. This research systematically analyzes aquaculture technologies, such as sensors, artificial intelligence (AI), and image processing. Through the systematic PRISMA process, 753 investigations published from 2012 to 2023 were analyzed based on a search in Scopus and Web of Science. It revealed a significant 70.5% increase in the number of articles published compared to the previous year, indicating a growing interest in this field. The results indicate that current aquaculture technologies are water monitoring sensors, AI methodologies such as K-means, and contour segmentation for computer vision. Also, it is reported that K means technologies offer an efficiency from 95% to 98%. These methods allow decisions based on data patterns and aquaculture insights. Improving aquaculture methodologies will allow adequate management of economic and environmental resources to promote fishing and satisfy nutritional needs.","url":"https://doi.org/10.3390/jmse12010161","authors":["Omar Capetillo-Contreras","Francisco David Pérez-Reynoso","Marco Antonio Zamora-Antuñano","José M. Álvarez-Alvarado","Juvenal Rodríguez‐Reséndiz"],"tags":["Aquaculture","Overexploitation","Fishing","Population","Business"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-01-13","doi":"https://doi.org/10.3390/jmse12010161","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4392558171","name":"Personalized strategies of neurostimulation: from static biomarkers to dynamic closed-loop assessment of neural function","source":"openalex","abstract":"Despite considerable advancement of first choice treatment (pharmacological, physical therapy, etc.) over many decades, neurological disorders still represent a major portion of the worldwide disease burden. Particularly concerning, the trend is that this scenario will worsen given an ever expanding and aging population. The many different methods of brain stimulation (electrical, magnetic, etc.) are, on the other hand, one of the most promising alternatives to mitigate the suffering of patients and families when conventional treatment fall short of delivering efficacious treatment. With applications in virtually all neurological conditions, neurostimulation has seen considerable success in providing relief of symptoms. On the other hand, a large variability of therapeutic outcomes has also been observed, particularly in the usage of non-invasive brain stimulation (NIBS) modalities. Borrowing inspiration and concepts from its pharmacological counterpart and empowered by unprecedented neurotechnological advancement, the neurostimulation field has seen in recent years a widespread of methods aimed at the personalization of its parameters, based on biomarkers of the individuals being treated. The rationale is that, by taking into account important factors influencing the outcome, personalized stimulation can yield a much-improved therapy. Here, we review the literature to delineate the state-of-the-art of personalized stimulation, while also considering the important aspects of the type of informing parameter (anatomy, function, hybrid), invasiveness, and level of development (pre-clinical experimentation versus clinical trials). Moreover, by reviewing relevant literature on closed loop neuroengineering solutions in general and on activity dependent stimulation method in particular, we put forward the idea that improved personalization may be achieved when the method is able to track in real time brain dynamics and adjust its stimulation parameters accordingly. We conclude that such approaches have great potential of promoting the recovery of lost functions and enhance the quality of life for patients.","url":"https://doi.org/10.3389/fnins.2024.1363128","authors":["Marta Carè","Michela Chiappalone","Vinícius Rosa Cota"],"tags":["Neurostimulation","Personalization","Deep brain stimulation","Modalities","Medicine"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-03-07","doi":"https://doi.org/10.3389/fnins.2024.1363128","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4400985292","name":"Experimental demonstration of magnetic tunnel junction-based computational random-access memory","source":"openalex","abstract":"The conventional computing paradigm struggles to fulfill the rapidly growing demands from emerging applications, especially those for machine intelligence because much of the power and energy is consumed by constant data transfers between logic and memory modules. A new paradigm, called \"computational random-access memory (CRAM),\" has emerged to address this fundamental limitation. CRAM performs logic operations directly using the memory cells themselves, without having the data ever leave the memory. The energy and performance benefits of CRAM for both conventional and emerging applications have been well established by prior numerical studies. However, there is a lack of experimental demonstration and study of CRAM to evaluate its computational accuracy, which is a realistic and application-critical metric for its technological feasibility and competitiveness. In this work, a CRAM array based on magnetic tunnel junctions (MTJs) is experimentally demonstrated. First, basic memory operations, as well as 2-, 3-, and 5-input logic operations, are studied. Then, a 1-bit full adder with two different designs is demonstrated. Based on the experimental results, a suite of models has been developed to characterize the accuracy of CRAM computation. Scalar addition, multiplication, and matrix multiplication, which are essential building blocks for many conventional and machine intelligence applications, are evaluated and show promising accuracy performance. With the confirmation of MTJ-based CRAM's accuracy, there is a strong case that this technology will have a significant impact on power- and energy-demanding applications of machine intelligence.","url":"https://doi.org/10.1038/s44335-024-00003-3","authors":["Yang Lv","Brandon R. Zink","Robert P. Bloom","Hüsrev Cılasun","Pravin Khanal","Salonik Resch","Zamshed I. Chowdhury","Ali Habiboglu","Weigang Wang","Sachin S. Sapatnekar","Ulya R. Karpuzcu","Jian‐Ping Wang"],"tags":["Tunnel magnetoresistance","Computer science","Random access","Random access memory","Materials science"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-07-25","doi":"https://doi.org/10.1038/s44335-024-00003-3","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4415104965","name":"From pulses to plasticity: Analytical tools for memristive synapse design","source":"openalex","abstract":"Neuromorphic device design demands a clear understanding of the dynamics governing conductance modulation under external stimuli. Many synaptic memristors can be described by a quasi-linear model, where a memory variable relaxes between two limiting states. Here, we derive analytical expressions for the response of such systems to trains of voltage pulses, providing closed formulations for paired-pulse facilitation (PPF), convergent potentiation, and frequency-dependent gain. This approach predicts how the memory variable evolves toward stationary values determined by device and stimulation parameters, offering a compact alternative to numerical simulations. We experimentally validate the model using a nanofluidic memristor based on a nanoporous membrane, showing that the predicted convergence closely matches measured potentiation and that the analytical PPF trends reproduce experimental data. These results establish a unified framework for describing spike-driven plasticity and enable reliable cross-comparison of synaptic behavior across memristive systems, facilitating their integration into neuromorphic circuits.","url":"https://doi.org/10.1063/5.0289570","authors":["Gonzalo Rivera‐Sierra","Juan Bisquert"],"tags":["Neuromorphic engineering","Memristor","Computer science","Electronic engineering","Variable (mathematics)"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-10-13","doi":"https://doi.org/10.1063/5.0289570","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4394747486","name":"Fast learning without synaptic plasticity in spiking neural networks","source":"openalex","abstract":"Spiking neural networks are of high current interest, both from the perspective of modelling neural networks of the brain and for porting their fast learning capability and energy efficiency into neuromorphic hardware. But so far we have not been able to reproduce fast learning capabilities of the brain in spiking neural networks. Biological data suggest that a synergy of synaptic plasticity on a slow time scale with network dynamics on a faster time scale is responsible for fast learning capabilities of the brain. We show here that a suitable orchestration of this synergy between synaptic plasticity and network dynamics does in fact reproduce fast learning capabilities of generic recurrent networks of spiking neurons. This points to the important role of recurrent connections in spiking networks, since these are necessary for enabling salient network dynamics. We show more specifically that the proposed synergy enables synaptic weights to encode more general information such as priors and task structures, since moment-to-moment processing of new information can be delegated to the network dynamics.","url":"https://doi.org/10.1038/s41598-024-55769-0","authors":["Anand Subramoney","Guillaume Bellec","Franz Scherr","Robert Legenstein","Wolfgang Maass"],"tags":["Synaptic plasticity","Neuroscience","Computer science","Spiking neural network","Synaptic scaling"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-04-12","doi":"https://doi.org/10.1038/s41598-024-55769-0","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4414260754","name":"Programmable Functional Connectivity and Synchronous Activity in Resistive Switching Self‐Assembled Nanostructured Networks","source":"openalex","abstract":"The efficiency of biological data processing systems is based on their adaptive connectivity and on the mutual interactions of their elements at different scales. These features are not substantially present in the design of electronic architectures based on conventional integrated circuits. The exploitation of self‐assembled systems characterized by nonlinear dynamics is actively investigated as a viable alternative strategy to develop energy‐efficient data processing devices. However, the encoding of external stimuli and the decoding of information from the analog response of such systems is still a challenge. Here we characterize the functional connectivity and the synchronicity between active sites in cluster‐assembled nanostructured Au films showing resistive switching behavior by a combined approach based on micro‐thermography and electrical measurements. We investigate the complex mechanisms involved in the network reorganization leading to its resistive switching activity and we identify the interplay between network dimensions and its emerging electrical behavior. We investigate the control on the synchronous activity and on the connectivity of the micrometric active sites which rule the emerging network dynamics and determe the performance of data processing devices. This activity is described using data analysis techniques commonly used in neuroscience, which are proposed for the first time to characterize neuromorphic systems.","url":"https://doi.org/10.1002/sstr.202500330","authors":["Davide Decastri","Thierry Nieus","Cristina Zuccali","Flavio Giacomozzi","Leandro Lorenzelli","Francesca Borghi","Paolo Milani"],"tags":["Neuromorphic engineering","Computer science","Encoding (memory)","Resistive touchscreen","Information processing"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-09-12","doi":"https://doi.org/10.1002/sstr.202500330","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4402715302","name":"Estimating optical flow: A comprehensive review of the state of the art","source":"openalex","abstract":"Optical flow estimation is a crucial task in computer vision that provides low-level motion information. Despite recent advances, real-world applications still present significant challenges. This survey provides an overview of optical flow techniques and their application. For a comprehensive review, this survey covers both classical frameworks and the latest AI-based techniques. In doing so, we highlight the limitations of current benchmarks and metrics, underscoring the need for more representative datasets and comprehensive evaluation methods. The survey also highlights the importance of integrating industry knowledge and adopting training practices optimized for deep learning-based models. By addressing these issues, future research can aid the development of robust and efficient optical flow methods that can effectively address real-world scenarios. • Investigating integration of traditional techniques in modern models. • Surveying key challenges of optical flow in real-world applications. • Offering the most comprehensive survey of datasets for optical flow. • Presenting a complete overview of Classical and Modern Optical Flow methods. • Highlighting crucial open questions, paving way for future research.","url":"https://doi.org/10.1016/j.cviu.2024.104160","authors":["Andrea Alfarano","Luca Maiano","Lorenzo Papa","Irene Amerini"],"tags":["Optical flow","Computer science","Flow (mathematics)","State (computer science)","Artificial intelligence"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-09-16","doi":"https://doi.org/10.1016/j.cviu.2024.104160","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4407223688","name":"Recent Progress in Flexible Piezoelectric Tactile Sensors: Materials, Structures, Fabrication, and Application","source":"openalex","abstract":"Flexible tactile sensors are widely used in aerospace, medical and health monitoring, electronic skin, human-computer interaction, and other fields due to their unique advantages, thus becoming a research hotspot. The goal is to develop a flexible tactile sensor characterized by outstanding sensitivity, extensive detection range and linearity, elevated spatial resolution, and commendable adaptability. Among several strategies like capacitive, piezoresistive, and triboelectric tactile sensors, etc., we focus on piezoelectric tactile sensors because of their self-powered nature, high sensitivity, and quick response time. These sensors can respond to a wide range of dynamic mechanical stimuli and turn them into measurable electrical signals. This makes it possible to accurately detect objects, including their shapes and textures, and for them to sense touch in real time. This work encapsulates current advancements in flexible piezoelectric tactile sensors, focusing on enhanced material properties, optimized structural design, improved fabrication techniques, and broadened application domains. We outline the challenges facing piezoelectric tactile sensors to provide inspiration and guidance for their future development.","url":"https://doi.org/10.3390/s25030964","authors":["Jingyao Tang","Yiheng Li","Yirong Yu","Qing‐Miao Hu","Wenya Du","Dabin Lin"],"tags":["Tactile sensor","Piezoresistive effect","Capacitive sensing","Piezoelectricity","Electronic skin"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-02-05","doi":"https://doi.org/10.3390/s25030964","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4413048995","name":"Spike-Count Reduction Techniques for Low Power Spiking Neural Networks","source":"openalex","abstract":"Spiking neural network (SNN) has demonstrated its great potential in low-power neuromorphic applications. In SNN, computation activities are associated with the arrival and firing of spikes, its power consumption is directly correlated with the number of spikes propagated in the network. In this paper, we explore two methods to reduce the spike-count in the network, aiming to reduce the power consumption of SNN. We use Poisson distribution function in the input layer and through adjusting the correlation (called the gain in the paper) between the probability of spike generation and input values, the number of spikes in the input layer can be reduced to only 20% of the baseline model with the accuracy degradation of less than 1%. We also exploit the leaky-integrate-and-fire (LIF) mechanism and use the refractory period to reduce the generation of spikes from the neurons in the hidden layers. Through this method, the spike-count is reduced by 20% $$\\sim $$ 50% while the performance degradation is still less than 1%. These two spike-count reduction techniques are implemented in Verilog RTL; the power simulation results demonstrate significant power reduction in performing SNN computations. We further discovered that for different network architectures, these two techniques have different trade-offs to achieve optimal spike-count reduction while maintaining satisfactory results. Compared with other spike-count reduction techniques, the proposed scheme is efficient and straightforward for hardware implementation, making it well-suited for edge computing scenarios.","url":"https://doi.org/10.1007/s11063-025-11786-2","authors":["Xinyu Kang","Zhitao Yang","Yuan Ren","Terry Tao Ye"],"tags":["Spike (software development)","Reduction (mathematics)","Computational intelligence","Spiking neural network","Artificial neural network"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-08-07","doi":"https://doi.org/10.1007/s11063-025-11786-2","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4400065203","name":"2D Graphene Oxide: A Versatile Thermo‐Optic Material","source":"openalex","abstract":"Abstract Efficient heat management and control in optical devices, facilitated by advanced thermo‐optic materials, are critical for many applications such as photovoltaics, thermal emitters, mode‐locked lasers, and optical switches. Here, a range of thermo‐optic properties of 2D graphene oxide (GO) films are investigated by precisely integrating them onto microring resonators (MRRs) with control over the film thicknesses and lengths. The refractive index, extinction coefficient, thermo‐optic coefficient, and thermal conductivity for the GO films with different layer numbers and degrees of reduction, as well as reversible reduction and enhanced optical bistability induced by the photo‐thermal effects, are comprehensively characterized. Experimental results show that the thermo‐optic properties of 2D GO films vary widely with the degree of reduction. In addition, significant anisotropy is observed for the thermo‐optic response, enabling efficient polarization‐sensitive devices. The versatile thermo‐optic response of 2D GO substantially expands the scope of functionalities and devices that can be engineered, making it promising for a diverse range of thermo‐optic applications.","url":"https://doi.org/10.1002/adfm.202406799","authors":["Junkai Hu","Jiayang Wu","Wenbo Liu","Di Jin","Houssein El Dirani","S. Kerdilès","Corrado Sciancalepore","Pierre Demongodin","Christian Grillet","Christelle Monat","Duan Huang","Baohua Jia","David Moss"],"tags":["Materials science","Optoelectronics","Graphene","Refractive index","Polarization (electrochemistry)"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-06-28","doi":"https://doi.org/10.1002/adfm.202406799","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4410779414","name":"Alcohol‐sensitive MoS 2 optoelectronic synapses for mimicking human‐like visual adaptation","source":"openalex","abstract":"Abstract The rapid advancements in humanoid robotics and autonomous driving demand smart artificial optoelectronic vision systems that can emulate human‐like perception. Although many studies have reported multi‐functional visual chips based on artificial optoelectronic synaptic devices, few can simulate complex behavioral characteristics of humans, like specific living habits and physiological adaptations. In this study, we demonstrated MoS 2 optoelectronic synapses capable of exhibiting tunable human‐like visual adaptation abilities under various alcohol concentrations, featuring remarkable photo‐induced conductance plasticity for emulating alcohol‐sensitive human visual recognition. Two working mechanisms involving hydrogen‐atom and oxygen‐atom doping were unveiled during the concentration‐dependent doping process. The visual adaptation abilities were systematically explored by controlling the doping concentration of alcohol molecules, and were further enhanced by electric and optoelectronic stimuli to emulate human‐like behaviors, such as slight drunkenness, heavy drunkenness, and sobering up. Under the influence of alcohol molecules and the modulation of device operating voltage, the accuracy of handwritten digit recognition for this device has greatly increased from 78.9% to 94.7%. image","url":"https://doi.org/10.1002/inf2.70019","authors":["Xiao Liu","Ming Huang","Xiongfeng Zou","Wajid Ali","Sajid Ur Rehman","Juan Li","Ziwei Li","Xiang Li","Anlian Pan"],"tags":["Adaptation (eye)","Optoelectronics","Neuroscience","Materials science","Computer science"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-04-15","doi":"https://doi.org/10.1002/inf2.70019","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4399118682","name":"Toward Practical Single‐Molecule/Atom Switches","source":"openalex","abstract":"Electronic switches have been considered to be one of the most important components of contemporary electronic circuits for processing and storing digital information. Fabricating functional devices with building blocks of atomic/molecular switches can greatly promote the minimization of the devices and meet the requirement of high integration. This review highlights key developments in the fabrication and application of molecular switching devices. This overview offers valuable insights into the switching mechanisms under various stimuli, emphasizing structural and energy state changes in the core molecules. Beyond the molecular switches, typical individual metal atomic switches are further introduced. A critical discussion of the main challenges for realizing and developing practical molecular/atomic switches is provided. These analyses and summaries will contribute to a comprehensive understanding of the switch mechanisms, providing guidance for the rational design of functional nanoswitch devices toward practical applications.","url":"https://doi.org/10.1002/advs.202400877","authors":["Xiaona Xu","Chunyan Gao","E. Ramya","Chuancheng Jia","Dong Xiang"],"tags":["Molecular switch","Computer science","Nanotechnology","Key (lock)","Electronic circuit"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-05-29","doi":"https://doi.org/10.1002/advs.202400877","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4410431401","name":"Bioinspired learning and memory in ionogels through fast response and slow relaxation dynamics of ions","source":"openalex","abstract":"Mimicking biological systems’ sensing, learning, and memory capabilities in synthetic soft materials remains challenging. While significant progress has been made in sensory functions in ionogels, their learning and memory capabilities still lag behind biological systems. Here, we introduce cation-π interactions and a self-adaptable ionic-double-layer interface in bilayer ionogels to control ion transport. Fast ion response enables sensing and learning, while slow ion relaxation supports long-term memory. The ionogels achieve bioinspired functions, including sensitization, habituation, classical conditioning, and multimodal memory, with low energy consumption (0.06 pJ per spike). Additionally, the ionogels exhibit mechanical adaptability, such as stretchability, self-healing, and reconfigurability, making them ideal for soft robotics. Notably, the ionogels enable a robotic arm to mimic the selective capture behavior of a Venus flytrap. This work bridges the gap between biological intelligence and artificial systems, offering promising applications in bioinspired, energy-efficient sensing, learning, and memory. Ionogels have been integrated into soft robotics, though it is challenging to design gels with learning and memory capabilities. Here the authors introduce ionic-double-layer ionogel using cation-π interactions to program the ionogel.","url":"https://doi.org/10.1038/s41467-025-59944-3","authors":["Ning Zhou","Ting Cui","Zhouyue Lei","Peiyi Wu"],"tags":["Ion","Relaxation (psychology)","Materials science","Chemical physics","Nanotechnology"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-05-16","doi":"https://doi.org/10.1038/s41467-025-59944-3","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4406787430","name":"All-silicon non-volatile optical memory based on photon avalanche-induced trapping","source":"openalex","abstract":"Abstract Implementing on-chip non-volatile optical memories has long been an actively pursued goal, promising significant enhancements in the capability and energy efficiency of photonic integrated circuits. Here, we demonstrate an non-volatile optical memory exclusively using the most common semiconductor material, silicon. By manipulating the photon avalanche effect, we introduce a trapping effect at the silicon-silicon oxide interface, which in turn demonstrates a non-volatile reprogrammable optical memory cell with a record-high 4-bit encoding, robust retention and endurance. This silicon avalanche-induced trapping memory provides a distinctively cost-efficient and high-reliability route to realize optical data storage in standard silicon foundry processes. We demonstrate its applications in trimming in optical interconnects and in-memory computing. Our in-memory computing test case reduces energy consumption by approximately 83% compared to conventional optical approaches.","url":"https://doi.org/10.1038/s42005-025-01934-4","authors":["Yuan Yuan","Yiwei Peng","Stanley Cheung","Wayne V. Sorin","Sean Hooten","Zhihong Huang","Di Liang","Jiuyi Zhang","Marco Fiorentino","Raymond G. Beausoleil"],"tags":["Trapping","Silicon","Optoelectronics","Materials science","Non-volatile memory"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-01-24","doi":"https://doi.org/10.1038/s42005-025-01934-4","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4405566600","name":"The ab initio non-crystalline structure database: empowering machine learning to decode diffusivity","source":"openalex","abstract":"Abstract Non-crystalline materials exhibit unique properties that make them suitable for various applications in science and technology, ranging from optical and electronic devices and solid-state batteries to protective coatings. However, data-driven exploration and design of non-crystalline materials is hampered by the absence of a comprehensive database covering a broad chemical space. In this work, we present the largest computed non-crystalline structure database to date, generated from systematic and accurate ab initio molecular dynamics (AIMD) calculations. We also show how the database can be used in simple machine-learning models to connect properties to composition and structure, here specifically targeting ionic conductivity. These models predict the Li-ion diffusivity with speed and accuracy, offering a cost-effective alternative to expensive density functional theory (DFT) calculations. Furthermore, the process of computational quenching non-crystalline structures provides a unique sampling of out-of-equilibrium structures, energies, and force landscape, and we anticipate that the corresponding trajectories will inform future work in universal machine learning potentials, impacting design beyond that of non-crystalline materials. In addition, combining diffusion trajectories from our dataset with models that predict liquidus viscosity and melting temperature could be utilized to develop models for predicting glass-forming ability.","url":"https://doi.org/10.1038/s41524-024-01469-2","authors":["Hui Zheng","Eric Sivonxay","Rasmus Christensen","Max C. Gallant","Ziyao Luo","Matthew J. McDermott","Patrick Huck","Morten M. Smedskjær","Kristin A. Persson"],"tags":["Ab initio","Thermal diffusivity","Materials science","Computer science","Database"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-12-19","doi":"https://doi.org/10.1038/s41524-024-01469-2","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4409810769","name":"Tunable Bipolar Photothermoelectric Response from Mott Activation for In‐Sensor Image Preprocessing","source":"openalex","abstract":"In-sensor image preprocessing, a subset of edge computing, offers a solution to mitigate frequent analog-digital conversions and the von Neumann bottleneck in conventional digital hardware. However, an efficient in-sensor device array with large-scale integration capability for high-density and low-power sensory processing is still lacking and highly desirable. This work introduces an adjustable broadband photothermoelectric detector based on a phase-change vanadium dioxide thin-film transistor. This transistor employs a vanadium dioxide/gallium nitride three-terminal structure with a gate-tunable phase transition at the gate-source junctions. This design allows for modulable photothermoelectric responsivities and alteration of the short-circuit photocurrent's polarities. The devices exhibit linear gate dependence for the broadband photoresponse and linear light-intensity dependence for both positive and negative photoresponsivities. The device's energy consumption is as low as 8 pJ per spike, which is one order of magnitude lower than that of previous Mott materials-based in-sensor preprocessing devices. A wafer-scale bipolar phototransistor array has also been fabricated by standard micro-/nano-fabrication techniques, exhibiting excellent stability and endurance (over 5000 cycles). More importantly, an integrated in-sensor convolutional network is successfully designed for simultaneous broadband image classification, medical image denoising, and retinal vessel segmentation, delivering exceptional performance and paving the way for future smart edge sensors.","url":"https://doi.org/10.1002/adma.202502915","authors":["Bowen Li","Ning Lin","Zhaowu Wang","Zhaowu Wang","Baojie Chen","Changyong Lan","Xiaocui Li","You Meng","Weijun Wang","Mingqi Ding","Pengshan Xie","Yuxuan Zhang","Zenghui Wu","Dengji Li","Fu‐Rong Chen","Chi Hou Chan","Zhongrui Wang","Zhongrui Wang","Johnny C. Ho"],"tags":["Materials science","Responsivity","Optoelectronics","Photodiode","Image sensor"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-04-25","doi":"https://doi.org/10.1002/adma.202502915","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4387459225","name":"Memory Technology: Development, Fundamentals, and Future Trends","source":"openalex","abstract":"The unprecedented development in the fields of artificial intelligence (AI), big data, and the internet of things (IoT) has been booming the expansion of the digital universe where data are growing at astronomical rates. The ever-increasing performance of computing systems is aspiring advanced memory technologies for both storage and computing applications. As the current mainstream non-volatile memory (NVM) technology, flash memory will be extended and continue to dominate for several years. Alternative memory technologies exploiting new materials and concepts to go beyond flash memory for standalone as well as embedded applications are consistently pursued to either replace the classical memory solutions or to fill the gap in conventional memory hierarchies. This chapter reviews the development and fundamentals of solid-state NVM technologies including the mainstream flash memory and the most promising alternative memory technologies. Finally, the future landscape and applications of NVM technologies are discussed.","url":"https://doi.org/10.1039/bk9781839169946-00001","authors":["Zongwei Wang","Yimao Cai"],"tags":["Computer science","Flash memory","Semiconductor memory","Computer memory","Non-volatile memory"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2023-10-09","doi":"https://doi.org/10.1039/bk9781839169946-00001","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4405828408","name":"Soft Artificial Synapse Electronics","source":"openalex","abstract":"Soft electronics, known for their bendable, stretchable, and flexible properties, are revolutionizing fields such as biomedical sensing, consumer electronics, and robotics. A primary challenge in this domain is achieving low power consumption, often hampered by the limitations of the conventional von Neumann architecture. In response, the development of soft artificial synapses (SASs) has gained substantial attention. These synapses seek to replicate the signal transmission properties of biological synapses, offering an innovative solution to this challenge. This review explores the materials and device architectures integral to SAS fabrication, emphasizing flexibility and stability under mechanical deformation. Various architectures, including floating-gate dielectric, ferroelectric-gate dielectric, and electrolyte-gate dielectric, are analyzed for effective weight control in SASs. The utilization of organic and low-dimensional materials is highlighted, showcasing their plasticity and energy-efficient operation. Furthermore, the paper investigates the integration of functionality into SASs, particularly focusing on devices that autonomously sense external stimuli. Functionalized SASs, capable of recognizing optical, mechanical, chemical, olfactory, and auditory cues, demonstrate promising applications in computing and sensing. A detailed examination of photo-functionalized, tactile-functionalized, and chemoreception-functionalized SASs reveals their potential in image recognition, tactile sensing, and chemosensory applications, respectively. This study highlights that SASs and functionalized SAS devices hold transformative potential for bioelectronics and sensing for soft-robotics applications; however, further research is necessary to address scalability, long-time stability, and utilizing functionalized SASs for prosthetics and in vivo applications through clinical adoption. By providing a comprehensive overview, this paper contributes to the understanding of SASs, bridging research gaps and paving the way toward transformative developments in soft electronics, biomimicking and biointegrated synapse devices, and integrated systems.","url":"https://doi.org/10.34133/research.0582","authors":["Md. Rayid Hasan Mojumder","Seongchan Kim","Cunjiang Yu"],"tags":["Electronics","Synapse","Nanotechnology","Computer science","Neuroscience"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-12-27","doi":"https://doi.org/10.34133/research.0582","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4405180690","name":"Spiking Variational Policy Gradient for Brain Inspired Reinforcement Learning","source":"openalex","abstract":"Recent studies in reinforcement learning have explored brain-inspired function approximators and learning algorithms to simulate brain intelligence and adapt to neuromorphic hardware. Among these approaches, reward-modulated spike-timing-dependent plasticity (R-STDP) is biologically plausible and energy-efficient, but suffers from a gap between its local learning rules and the global learning objectives, which limits its performance and applicability. In this paper, we design a recurrent winner-take-all network and propose the spiking variational policy gradient (SVPG), a new R-STDP learning method derived theoretically from the global policy gradient. Specifically, the policy inference is derived from an energy-based policy function using mean-field inference, and the policy optimization is based on a last-step approximation of the global policy gradient. These fill the gap between the local learning rules and the global target. In experiments including a challenging ViZDoom vision-based navigation task and two realistic robot control tasks, SVPG successfully solves all the tasks. In addition, SVPG exhibits better inherent robustness to various kinds of input, network parameters, and environmental perturbations than compared methods.","url":"https://doi.org/10.1109/tpami.2024.3511936","authors":["Zhile Yang","Shangqi Guo","Ying Fang","Zhaofei Yu","Jian K. Liu"],"tags":["Reinforcement learning","Artificial intelligence","Computer science","Machine learning","Pattern recognition (psychology)"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-12-09","doi":"https://doi.org/10.1109/tpami.2024.3511936","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4391879679","name":"Deep photonic network platform enabling arbitrary and broadband optical functionality","source":"openalex","abstract":"Expanding applications in optical communications, computing, and sensing continue to drive the need for high-performance integrated photonic components. Designing these on-chip systems with arbitrary functionality requires beyond what is possible with physical intuition, for which machine learning-based methods have recently become popular. However, computational demands for physically accurate device simulations present critical challenges, significantly limiting scalability and design flexibility of these methods. Here, we present a highly-scalable, physics-informed design platform for on-chip optical systems with arbitrary functionality, based on deep photonic networks of custom-designed Mach-Zehnder interferometers. Leveraging this platform, we demonstrate ultra-broadband power splitters and a spectral duplexer, each designed within two minutes. The devices exhibit state-of-the-art experimental performance with insertion losses below 0.66 dB, and 1-dB bandwidths exceeding 120 nm. This platform provides a tractable path towards systematic, large-scale photonic system design, enabling custom power, phase, and dispersion profiles for high-throughput communications, quantum information processing, and medical/biological sensing applications.","url":"https://doi.org/10.1038/s41467-024-45846-3","authors":["Ali Najjar Amiri","Aycan Deniz Vit","Kazim Görgülü","Emir Salih Magden"],"tags":["Computer science","Photonics","Scalability","Broadband","Electronic engineering"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-02-16","doi":"https://doi.org/10.1038/s41467-024-45846-3","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4396510838","name":"An organic brain-inspired platform with neurotransmitter closed-loop control, actuation and reinforcement learning","source":"openalex","abstract":"adaptive synaptic potentiation and depression, in a closed-loop fashion. The microfabricated platform could be interfaced and control a robotic hand which ultimately was able to learn the grasping of differently sized objects, autonomously.","url":"https://doi.org/10.1039/d3mh02202a","authors":["Ugo Bruno","Daniela Rana","Chiara Ausilio","Anna Mariano","Ottavia Bettucci","Simon Musall","Claudia Lubrano","Francesca Santoro"],"tags":["Neuromorphic engineering","Reinforcement learning","Bridge (graph theory)","Closed loop","Brain tissue"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-01-01","doi":"https://doi.org/10.1039/d3mh02202a","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4410855184","name":"Vector Ising spin annealer for minimizing Ising Hamiltonians","source":"openalex","abstract":"Abstract Complex optimization problems can be solved via dedicated machines which encode the problem in the couplings of spin Hamiltonians. However, traditional physical minimizers often select excited states due to limitations in spin dynamics. We introduce the Vector Ising Spin Annealer (VISA), a framework in gain-based computing that leverages light-matter interactions. We show that VISA overcomes the limitations by enabling spins to operate within a three-dimensional space, thereby providing a robust solution for effectively minimizing Ising Hamiltonians. Our comparative analysis demonstrates VISA’s superior performance relative to conventional single-dimension spin optimizers, highlighting its capacity to surmount significant energy barriers in intricate landscapes. Detailed studies on cyclic and random graphs reveal VISA’s proficiency in dynamically evolving the energy landscape through time-dependent gain and penalty annealing, underscoring its potential in advancing the field of complex problem-solving in physics-inspired and physics-based computing.","url":"https://doi.org/10.1038/s42005-025-02145-7","authors":["James Cummins","Natalia G. Berloff"],"tags":["Ising model","Ising spin","Square-lattice Ising model","Statistical physics","Physics"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-05-29","doi":"https://doi.org/10.1038/s42005-025-02145-7","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4400015167","name":"Spiking neural networks for physiological and speech signals: a review","source":"openalex","abstract":"","url":"https://doi.org/10.1007/s13534-024-00404-0","authors":["Sung Soo Park","Young-Seok Choi"],"tags":["Computer science","Spiking neural network","Wearable computer","Field (mathematics)","Temporal resolution"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-06-25","doi":"https://doi.org/10.1007/s13534-024-00404-0","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4406852025","name":"Post-processing methods for delay embedding and feature scaling of reservoir computers","source":"openalex","abstract":"Reservoir computing is a machine learning method that is well-suited for complex time series prediction tasks. Both delay embedding and the projection of input data into a higher-dimensional space play important roles in enabling accurate predictions. We establish simple post-processing methods that train on past node states at uniformly or randomly-delayed timeshifts. These methods improve reservoir computer prediction performance through increased feature dimension and/or better delay embedding. Here we introduce the multi-random-timeshifting method that randomly recalls previous states of reservoir nodes. The use of multi-random-timeshifting allows for smaller reservoirs while maintaining large feature dimensions, is computationally cheap to optimise, and is our preferred post-processing method. For experimentalists, all our post-processing methods can be translated to readout data sampled from physical reservoirs, which we demonstrate using readout data from an experimentally-realised laser reservoir system.","url":"https://doi.org/10.1038/s44172-024-00330-0","authors":["Jonnel Anthony Jaurigue","Joshua Robertson","Antonio Hurtado","Lina Jaurigue","Kathy Lüdge"],"tags":["Reservoir computing","Embedding","Computer science","Feature (linguistics)","Dimension (graph theory)"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-01-27","doi":"https://doi.org/10.1038/s44172-024-00330-0","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4411620613","name":"NSIP: Neural Network SPICE Integration Platform for Ferroelectric Field‐Effect Transistor‐Based Crossbar Arrays","source":"openalex","abstract":"This article presents the world's first demonstration of a neural network SPICE integration platform (NSIP) for simulating synaptic weights in HfZrO (HZO)‐based ferroelectric field‐effect transistor (FeFET) crossbar arrays tailored for neuromorphic computing. The FeFET compact model integrated in NSIP accurately reflects the hysteretic switching behavior observed in metal‐ferroelectric‐metal capacitors fabricated by incorporating the Preisach theory. Using databases, such as MNIST, the performance of NSIP is evaluated through voltage optimization, taking into account the effects of ferroelectric process parameters on cell conductivity, parasitic components, and nonideal characteristics in FeFET device arrays, with the goal of on‐device training for handwritten digit classification. This includes the inference accuracy and power efficiency characteristics of the FeFET‐based neural network (NN) array, along with the execution time of the customized simulation engine. The developed NSIP is then utilized to investigate the impact of the dynamic range of FeFET conductance, ferroelectric thickness, and line resistance on the performance of the NN. Power consumption and inference accuracy is measured at the same voltage bias over a range of ferroelectric thicknesses and the tradeoffs is analyzed in detail. The impact of line resistance on accuracy during the inference stage is studied, providing essential design guidance for the early stages of fabric.","url":"https://doi.org/10.1002/aisy.202500305","authors":["Juhwan Park","H. J. Kim","Hyunbo Cho","Jongwook Jeon"],"tags":["Crossbar switch","Spice","Computer science","Electronic engineering","Optoelectronics"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-06-25","doi":"https://doi.org/10.1002/aisy.202500305","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4283332145","name":"Heusler alloys for metal spintronics","source":"openalex","abstract":"Abstract Heusler alloys have been theoretically predicted and experimentally demonstrated to be an ideal spin source due to their half-metallicity at room temperature. The half-metallicity also offers low Gilbert damping constants for fast magnetization reversal with low switching current density. These intrinsic properties can offer better operationability in spin-transfer-torque-based devices. In addition spin–orbit torque can be exerted using Heusler alloys for spin Hall and caloritronic effects. These properties can be precisely controlled by substituting the constituent elements in a Heusler alloy. We review the recent development on these spintronic devices and summarize their future perspectives. Graphical abstract","url":"https://doi.org/10.1557/s43577-022-00350-1","authors":["Atsufumi Hirohata","David C. Lloyd"],"tags":["Spintronics","Condensed matter physics","Materials science","Alloy","Spin (aerodynamics)"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2022-06-01","doi":"https://doi.org/10.1557/s43577-022-00350-1","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4398765486","name":"An inorganic-blended p-type semiconductor with robust electrical and mechanical properties","source":"openalex","abstract":"Abstract Inorganic semiconductors typically have limited p-type behavior due to the scarcity of holes and the localized valence band maximum, hindering the progress of complementary devices and circuits. In this work, we propose an inorganic blending strategy to activate the hole-transporting character in an inorganic semiconductor compound, namely tellurium-selenium-oxygen (TeSeO). By rationally combining intrinsic p-type semimetal, semiconductor, and wide-bandgap semiconductor into a single compound, the TeSeO system displays tunable bandgaps ranging from 0.7 to 2.2 eV. Wafer-scale ultrathin TeSeO films, which can be deposited at room temperature, display high hole field-effect mobility of 48.5 cm2/(Vs) and robust hole transport properties, facilitated by Te-Te (Se) portions and O-Te-O portions, respectively. The nanosphere lithography process is employed to create nanopatterned honeycomb TeSeO broadband photodetectors, demonstrating a high responsibility of 603 A/W, an ultrafast response of 5 μs, and superior mechanical flexibility. The p-type TeSeO system is highly adaptable, scalable, and reliable, which can address emerging technological needs that current semiconductor solutions may not fulfill.","url":"https://doi.org/10.1038/s41467-024-48628-z","authors":["You Meng","Weijun Wang","Rong Fan","Zhengxun Lai","Wei Wang","Dengji Li","Xiaocui Li","Quan Quan","Pengshan Xie","Dong Chen","He Shao","Bowen Li","Zenghui Wu","Zhe Yang","SenPo Yip","Chun‐Yuen Wong","Yang Lü","Johnny C. Ho"],"tags":["Semiconductor","Materials science","Optoelectronics","Nanotechnology","Nanosphere lithography"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-05-24","doi":"https://doi.org/10.1038/s41467-024-48628-z","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4411004417","name":"Unveiling the switching mechanism of robust tetrazine-based memristive nociceptors via a spectroelectrochemical approach","source":"openalex","abstract":") and nanosecond level switching time (60 ns), can be successfully optimized. Moreover, a spectroelectrochemical strategy was employed for the first time to investigate the RS mechanism at the molecular level, elucidating the critical role of molecular design in modulating the device's working principles and electrical characteristics. The optimized memristor is capable of accurately emulating the four key behaviors of nociceptors. This achievement not only advances the application of organic materials in neuromorphic devices but also opens up new possibilities for the specialized customization of nociceptors.","url":"https://doi.org/10.1039/d5sc02710a","authors":["JiYu Zhao","Kun Liu","Wei Zeng","Zhuo Chen","Yifan Zheng","Zherui Zhao","Wen‐Min Zhong","Su‐Ting Han","Guanglong Ding","Ye Zhou","Xiaojun Peng"],"tags":["Mechanism (biology)","Tetrazine","Nociceptor","Chemistry","Computer science"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-01-01","doi":"https://doi.org/10.1039/d5sc02710a","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4413118591","name":"Roadmap on Optics and Photonics for Security and Encryption","source":"openalex","abstract":"In 1994, Javidi and Horner published a paper in Optical Engineering that highlighted the ability of free space optical systems to manipulate sensitive data for authentication purposes. The underlying idea was effective yet surprisingly simple: an optical nonlinear joint transform using a random phase mask in both the input and the reference could produce a correlation peak to indicate whether the input object is authentic or not. This seminal paper fueled the development of this new discipline. After three decades, optical encryption and security have matured into a field that plays a central role in the development of photonics techniques. While the pioneering work was mainly focused on the field of optical information processing, nowadays, a broad spectrum of disciplines are contributing to developing security solutions, including nanotechnology, materials science, quantum information, and deep learning, just to cite a few. The present roadmap paper gathers 28 leading authors in the field from 21 academic institutions across nine different countries. It is organized into 17 sections which discuss the present and future challenges, state-of-the-art technology, and real-world solutions to address the security challenges facing our society.","url":"https://doi.org/10.1109/access.2025.3597226","authors":["Bahram Javidi","Artur Carnicer","Kavan Ahmadi","Yasuhiro Awatsuji","Wen Chen","Thierry Fournel","Patrice Genevet","Jingying Guo","Wenqi He","Mathieu Hébert","Aloke Jana","Edmund Y. Lam","Gui‐Lu Long","Osamu Matoba","Zhenyu Mi","Inkyu Moon","Naveen K. Nishchal","Dong Pan","Xiang Peng","Pepijn W. H. Pinkse","Yishi Shi","Guohai Situ","Adrian Stern","Xiaogang Wang","Tian Xia","Yin Xiao","Zhenwei Xie","Shuo Zhu"],"tags":["Encryption","Photonics","Computer science","Ultrafast optics","Optics"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-01-01","doi":"https://doi.org/10.1109/access.2025.3597226","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4400229075","name":"Smaller and Faster Robotic Grasp Detection Model via Knowledge Distillation and Unequal Feature Encoding","source":"openalex","abstract":"In order to achieve higher accuracy, the complexity of grasp detection network increases accordingly with complicated model structures and tremendous parameters. Although various light-weight strategies are adopted, directly designing the compact network can be sub-optimal and difficult to strike the balance between accuracy and model size. To solve this problem, we explore a more efficient grasp detection model from two aspects: elaborately designing a light-weight network and performing knowledge distillation on the designed network. Specifically, based on the designed light-weight backbone, the features from RGB and D images with unequal effective grasping information rates are fully utilized and the information compensation strategies are adopted to make the model small enough while maintaining its accuracy. Then, the grasping features contained in the large teacher model are adaptively and effectively learned by our proposed method via knowledge distillation. Experimental results indicate that the proposed method is able to achieve comparable performance (98.9%, 93.1%, 82.3%, and 90.0% on Cornell, Jacquard, GraspNet, and MultiObj datasets, respectively) with more complicate models while reducing the parameters from MBs to KBs. Real-world robotic grasping experiment in an embedded AI computing device also prove the effectiveness of this approach.","url":"https://doi.org/10.1109/lra.2024.3421790","authors":["Hong Nie","Zhou Zhao","Lu Chen","Zhenyu Lu","Zhuomao Li","Jing Yang"],"tags":["GRASP","Encoding (memory)","Distillation","Computer science","Feature (linguistics)"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-07-02","doi":"https://doi.org/10.1109/lra.2024.3421790","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4406478661","name":"Challenges and opportunities for validation of AI-based new approach methods","source":"openalex","abstract":"The integration of artificial intelligence (AI) into new approach methods (NAMs) for toxicology rep­resents a paradigm shift in chemical safety assessment. Harnessing AI appropriately has enormous potential to streamline validation efforts. This review explores the challenges, opportunities, and future directions for validating AI-based NAMs, highlighting their transformative potential while acknowledging the complexities involved in their implementation and acceptance. We discuss key hurdles such as data quality, model interpretability, and regulatory acceptance, alongside opportunities including enhanced predictive power and efficient data integration. The concept of e-validation, an AI-powered framework for streamlining NAM validation, is presented as a comprehensive strategy to overcome limitations of traditional validation approaches, leveraging AI-powered modules for reference chemical selection, study simulation, mechanistic validation, and model training and evaluation. We propose robust validation strategies, including tiered approaches, performance benchmarking, uncertainty quantification, and cross-validation across diverse datasets. The importance of ongoing monitoring and refinement post-implementation is emphasized, addressing the dynamic nature of AI models. We consider ethical implications and the need for human oversight in AI-driven toxicology and outline the impact of trends in AI devel­opment, research priorities, and a vision for the integration of AI-based NAMs in toxicological practice, calling for collaboration among researchers, regulators, and industry stakeholders. We describe the vision of companion AI post-validation agents to keep methods and their validity status current. By addressing these challenges and opportunities, the scientific community can harness the potential of AI to enhance predictive toxicology while reducing reliance on traditional animal testing and increasing human relevance and translational capabilities. Plain language summaryScientists are using artificial intelligence (AI) to develop new ways of assessing chemical safety that do not rely on animal experiments. These methods can be faster, more accurate, more human-relevant, and more ethical than traditional approaches. However, before these new methods can be widely used, we need to make sure they are reliable and trustworthy. This article discusses the challenges in validating AI-based safety testing methods, such as ensuring data quality and making AI decisions transparent and understandable, and proposes strategies for thorough validation and ongoing monitoring of these AI methods. It also explores opportunities to use AI to simulate experi­ments, analyze complex biological information, and support validation of diverse NAMs. We emphasize the importance of collaboration among researchers, regulators, and industry to develop responsible AI use in toxicology. By addressing these challenges, we can harness AI’s power to improve chemical safety testing while reducing animal use.","url":"https://doi.org/10.14573/altex.2412291","authors":["Thomas Härtung","Nicole Kleinstreuer"],"tags":["Computer science","Data science","Management science","Artificial intelligence","Engineering"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-01-01","doi":"https://doi.org/10.14573/altex.2412291","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4405137460","name":"Tactile Feedback in Robot‐Assisted Minimally Invasive Surgery: A Systematic Review","source":"openalex","abstract":"BACKGROUND: Robot-assisted systems have predominantly relied on teleoperation, where visual feedback is the primary source of information. However, advances in tactile sensing and displays offer new opportunities to enhance surgical transparency, efficiency, and safety. METHODS: A PRISMA-guided search was conducted across PubMed, IEEE Xplore, Scopus, and Web of Science databases to identify relevant studies. RESULTS: Out of 645 screened articles, 98 met the inclusion criteria, and 33 were included in the final review. The review discusses various tactile feedback stimulus types, applications, and challenges in the context of robot-assisted minimally invasive surgery. CONCLUSION: While kinaesthetic feedback has been extensively explored to restore the natural interaction between the surgeon and the surgical environment, tactile feedback remains largely confined to research settings. This is due to significant challenges in integrating tactile feedback into robotic systems and current limitations of sensing technologies.","url":"https://doi.org/10.1002/rcs.70019","authors":["Jacinto Colan","Ana Davila","Yasuhisa Hasegawa"],"tags":["Teleoperation","Computer science","Robot","Human–computer interaction","Surgical robot"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-12-01","doi":"https://doi.org/10.1002/rcs.70019","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4399463559","name":"Emergent digital bio-computation through spatial diffusion and engineered bacteria","source":"openalex","abstract":"Biological computing is a promising field with potential applications in biosafety, environmental monitoring, and personalized medicine. Here we present work on the design of bacterial computers using spatial patterning to process information in the form of diffusible morphogen-like signals. We demonstrate, mathematically and experimentally, that single, modular, colonies can perform simple digital logic, and that complex functions can be built by combining multiple colonies, removing the need for further genetic engineering. We extend our experimental system to incorporate sender colonies as morphogen sources, demonstrating how one might integrate different biochemical inputs. Our approach will open up ways to perform biological computation, with applications in bioengineering, biomaterials and biosensing. Ultimately, these computational bacterial communities will help us explore information processing in natural biological systems.","url":"https://doi.org/10.1038/s41467-024-49264-3","authors":["Alex J. H. Fedorec","Neythen J. Treloar","Ke Yan Wen","Linda Dekker","Qing Hsuan Ong","Gabija Jurkeviciute","Enbo Lyu","Jack W. Rutter","K. Zhang","Luca Rosa","Alexey Zaikin","C. Barnes"],"tags":["Bacteria","Diffusion","Computation","Computer science","Computational biology"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-06-08","doi":"https://doi.org/10.1038/s41467-024-49264-3","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4407184482","name":"Bioelectronics with Topological Crosslinked Networks for Tactile Perception","source":"openalex","abstract":"Abstract Bioelectronics, which integrate biological systems with electronic components, have attracted significant attention in developing biomimetic materials and advanced hardware architectures to enable novel information‐processing systems, sensors, and actuators. However, the rigidity of conjugated molecular systems and the lack of reconfigurability in static crosslinked structures pose significant challenges for flexible sensing applications. Topological crosslinked networks (TCNs) featuring dynamic molecular interactions offer enhanced molecular flexibility and environmentally induced reconfigurability, decoupling the competition between performances. Here, recent advances are summarized in assembly methods of bioelectronics with different TCNs and elaborate ion/electron‐transport mechanisms from the perspective of molecular interactions. Decoupling effects can be achieved by comparing distinct TCNs and their respective properties, and an outlook is provided on a new range of neuromorphic hardware with biocompatibility, self‐healing, self‐powered, and multimodal‐sensing capabilities. The development of TCN‐based bioelectronics can significantly impact the fields of artificial neuromorphic perception devices, networks, and systems.","url":"https://doi.org/10.1002/apxr.202400165","authors":["Mingqi Ding","Pengshan Xie","Johnny C. Ho"],"tags":["Bioelectronics","Perception","Tactile perception","Cognitive science","Materials science"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-02-04","doi":"https://doi.org/10.1002/apxr.202400165","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4403299429","name":"A Three‐Terminal Memristive Artificial Neuron with Tunable Firing Probability","source":"openalex","abstract":"Abstract The human brain facilitates information processing via generating and receiving temporal patterns of short voltage pulses, a.k.a. neural spikes. This approach simultaneously grants low‐power operation as well as a high degree of noise immunity and fault tolerance at a small footprint and simplistic structure of the neurons. To date, the latter two key features are critically missing from the toolbox of artificial spiking neural network hardware, hindering the development of scalable and sustainable artificial intelligence (AI) platforms. Here, a compact, gate‐tunable neuron circuit is demonstrated, and its potential as a functional leaky integrate‐and‐fire (LIF) neuron is explored. It relies on a single nanoscale three‐terminal (3T) memristor device, which has been downscaled by 30% compared to previous work, where the set voltage and, thereby, the spiking probability of the neuron circuit can be widely tuned by the low‐voltage operation of the gate electrode. The influence of the gate voltage on the two‐terminal (2T) current–voltage characteristics is measured, statistically analyzed, and further utilized in a custom‐built LTspice model. The circuit simulations account for the experimentally observed, adjustable set voltage. The presented results demonstrate the merits of 3T memristors as compact, tunable, and versatile artificial neurons for neuromorphic computing applications.","url":"https://doi.org/10.1002/aelm.202400432","authors":["Mila Lewerenz","Elias Passerini","Luca Weber","Markus Fischer","Nadia Jimenez Olalla","Raphael Gisler","Alexandros Emboras","Mathieu Luisier","Miklós Csontos","Ueli Koch","Juerg Leuthold"],"tags":["Materials science","Terminal (telecommunication)","Memristor","Neuron","Nanotechnology"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-10-10","doi":"https://doi.org/10.1002/aelm.202400432","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4406703029","name":"Engineering Nonvolatile Polarization in 2D α-In2Se3/α-Ga2Se3 Ferroelectric Junctions","source":"openalex","abstract":"The advent of two-dimensional (2D) ferroelectrics offers a new paradigm for device miniaturization and multifunctionality. Recently, 2D α-In2Se3 and related III–VI compound ferroelectrics manifest room-temperature ferroelectricity and exhibit reversible spontaneous polarization even at the monolayer limit. Here, we employ first-principles calculations to investigate group-III selenide van der Waals (vdW) heterojunctions built up by 2D α-In2Se3 and α-Ga2Se3 ferroelectric (FE) semiconductors, including structural stability, electrostatic potential, interfacial charge transfer, and electronic band structures. When the FE polarization directions of α-In2Se3 and α-Ga2Se3 are parallel, both the α-In2Se3/α-Ga2Se3 P↑↑ (UU) and α-In2Se3/α-Ga2Se3 P↓↓ (NN) configurations possess strong built-in electric fields and hence induce electron–hole separation, resulting in carrier depletion at the α-In2Se3/α-Ga2Se3 heterointerfaces. Conversely, when they are antiparallel, the α-In2Se3/α-Ga2Se3 P↓↑ (NU) and α-In2Se3/α-Ga2Se3 P↑↓ (UN) configurations demonstrate the switchable electron and hole accumulation at the 2D ferroelectric interfaces, respectively. The nonvolatile characteristic of ferroelectric polarization presents an innovative approach to achieving tunable n-type and p-type conductive channels for ferroelectric field-effect transistors (FeFETs). In addition, in-plane biaxial strain modulation has successfully modulated the band alignments of the α-In2Se3/α-Ga2Se3 ferroelectric heterostructures, inducing a type III–II–III transition in UU and NN, and a type I–II–I transition in UN and NU, respectively. Our findings highlight the great potential of 2D group-III selenides and ferroelectric vdW heterostructures to harness nonvolatile spontaneous polarization for next-generation electronics, nonvolatile optoelectronic memories, sensors, and neuromorphic computing.","url":"https://doi.org/10.3390/nano15030163","authors":["Peipei Li","Delin Kong","Jin Yang","Shuyu Cui","Qi Chen","Yue Liu","Zhike He","Feng Liu","Yingying Xu","Huiyun Wei","Xinhe Zheng","Mingzeng Peng"],"tags":["Ferroelectricity","Heterojunction","Materials science","Optoelectronics","Semiconductor"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-01-22","doi":"https://doi.org/10.3390/nano15030163","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4405914892","name":"Recent Progress in Tactile Sensing and Machine Learning for Texture Perception in Humanoid Robotics","source":"openalex","abstract":"ABSTRACT Humanoid robots have garnered substantial attention recently in both academia and industry. These robots are becoming increasingly sophisticated and intelligent, as seen in health care, education, customer service, logistics, security, space exploration, and so forth. Central to these technological advancements is tactile perception, a crucial modality through which humanoid robots exchange information with their external environment, thereby facilitating human‐like behaviors such as object recognition and dexterous manipulation. Texture perception is particularly vital for these tasks, as the surface morphology of objects significantly influences recognition and manipulation abilities. This review addresses the recent progress in tactile sensing and machine learning for texture perception in humanoid robots. We first examine the design and working principles of tactile sensors employed in texture perception, differentiating between touch‐based and sliding‐based approaches. Subsequently, we delve into the machine learning algorithms implemented for texture perception using these tactile sensors. Finally, we discuss the challenges and future opportunities in this evolving field. This review aims to provide insights into the state‐of‐the‐art developments and foster advancements in tactile sensing and machine learning for texture perception in humanoid robotics.","url":"https://doi.org/10.1002/idm2.12233","authors":["Longteng Yu","Dabiao Liu"],"tags":["Humanoid robot","Tactile perception","Artificial intelligence","Perception","Human–computer interaction"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-12-30","doi":"https://doi.org/10.1002/idm2.12233","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4408047540","name":"LAST-PAIN: Learning Adaptive Spike Thresholds for Low Back Pain Biosignals Classification","source":"openalex","abstract":"Spiking neural networks (SNNs) present the potential for ultra-low-power computation, especially when implemented on dedicated neuromorphic hardware. However, a significant challenge is the efficient conversion of continuous real-world data into the discrete spike trains required by SNNs. In this paper, we introduce Learning Adaptive Spike Thresholds (LAST), a novel, trainable encoding strategy designed to address this challenge. The LAST encoder learns adaptive thresholds to transform continuous signals of varying dimensionality-ranging from time series data to high dimensional tensors-into sparse spike trains. Our proposed encoder effectively preserves temporal dynamics and adapts to the characteristics of the input. We validate the LAST approach in a demanding healthcare application using the EmoPain dataset. This dataset contains multimodal biosignal analysis for assessing chronic lower back pain (CLBP). Despite the dataset's small sample size and class imbalance, our LAST-driven SNN framework achieves a competitive Matthews Correlation Coefficient of 0.44 and an accuracy of 80.43% in CLBP classification. The experimental results also indicate that the same framework can achieve an F1-score of 0.65 in detecting protective behaviour. Furthermore, the LAST encoder outperforms conventional rate and latency-based encodings while maintaining sparse spike representations. This achievement shows promises for energy-efficient and real-time biosignal processing in resource-limited environments.","url":"https://doi.org/10.1109/tnsre.2025.3546682","authors":["Freek Hens","Mohammad Mahdi Dehshibi","Leila Bagheriye","Ana Tajadura‐Jiménez","Mahyar Shahsavari"],"tags":["Spike (software development)","Psychology","Artificial intelligence","Computer science","Physical medicine and rehabilitation"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-01-01","doi":"https://doi.org/10.1109/tnsre.2025.3546682","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4408819106","name":"Stochastic compact model for memory and threshold switching memristors","source":"openalex","abstract":"Memristors are electron devices whose resistance changes according to the history of electrical signals applied to their two terminals. These resistance changes can remain for very long times or relax after a short time. Thus, memristors can be used as electronic synapses and neurons in artificial neural networks implemented in hardware. These fully memristive neuromorphic circuits are mainly intended for artificial intelligence applications. In this work, we explore the properties of a stochastic compact model for the electrical behavior of memristors in the two regimes of long-time (non-volatile) and short-time (volatile) memory for synapse and neuron functions, respectively. In the case of non-volatile memristors, we focus on potentiation/depression transients, programming energy, programming time, and power requirements for writing conductance weights in artificial network crossbars. As for volatile memristors, we consider the modeling of their behavior in the context of a leaky-integrate-and-fire neuron, demonstrating how the model captures the threshold activation function and the input signal frequency dependence.","url":"https://doi.org/10.1063/5.0255043","authors":["J. Suñé","E. Miranda"],"tags":["Memristor","Computer science","Electronic engineering","Engineering"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-03-01","doi":"https://doi.org/10.1063/5.0255043","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4412379260","name":"Quantized Conductance and Multilevel Memory Operation in Mn 3 O 4 Nanowire Network Devices Combined with Low Voltage Operation and Oxygen Vacancy Induced Resistive Switching","source":"openalex","abstract":"Abstract Quantum effects in nanowires and nanodevices can potentially revolutionize the device concepts with multi‐functionalities for future technologies. Memristive devices which undergo transition from high resistance state to low resistance state involve nanoscale conduction paths can show quantum effects at room temperature. Here, Mn 3 O 4 nanowires based memristor showing very reliable resistive switching at very low voltages and with ON/OFF States ratio ∼ 10 3 is reported. The switching device can also be programmed to multiple memory states (up to 16 states ∼ 2 4 ). Since the conduction paths are geometrically constrained along the nanowires, quantized conductance steps are observed. Step‐wise conductance jumps are observed during the SET and RESET process with better control along RESET process. Conductance jumps range between 1 and 9 G 0 . The nanowire devices show very consistent resistive switching up to 100 °C. These measurements confirm extremely stable nanowire based resistive switching devices which can be used for next‐generation memories showing quantum effects in neuromorphic computing architectures.","url":"https://doi.org/10.1002/aelm.202500159","authors":["Keval Hadiyal","Ramakrishnan Ganesan","R. Thamankar"],"tags":["Materials science","Nanowire","Conductance","Resistive random-access memory","Voltage"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-07-13","doi":"https://doi.org/10.1002/aelm.202500159","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4406428599","name":"Advanced Materials Research at CUHK: From Biomedicine to Electronics and Beyond","source":"openalex","abstract":"This special issue spans a diverse array of topics, including nanomedicine, tissue engineering, regenerative medicine, organs-on-chips, biosensing, soft robotics, smart devices, nanofabrication, energy saving and storage, catalysis, spintronics, soft electronics, and neuromorphic computing. It showcases the breadth and depth of advanced materials research at the Chinese University of Hong Kong (CUHK), highlighting the innovation, collaboration, and excellence of CUHK's materials scientists.","url":"https://doi.org/10.1002/adma.202418618","authors":["Chuanbin Mao"],"tags":["Materials science","Biomedicine","Nanotechnology","Electronics","Engineering physics"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-01-01","doi":"https://doi.org/10.1002/adma.202418618","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4405455971","name":"Photoinduced Melting of V4O7 Correlated State","source":"openalex","abstract":"Abstract The compound V4O7 is one of the Magnéli phase (VnO2n − 1, n = 3, 4, …, 9) correlated vanadium oxides with distinct intriguing electronic and structural properties. The possibility to manipulate the phase state of V4O7 on an ultrafast time scale by light makes this material promising for potential applications in photonics, optoelectronics, quantum, and neuromorphic circuit design. In this work, the ultrafast spectroscopy of V4O7 reveals the second‐order nature of the photoinduced insulator‐to‐metal transition, emphasizing electronic and lattice contributions. The findings reveal the influence of the laser excitation level and temperature on these dynamics, providing a comprehensive understanding of V4O7 structural changes and response to external stimuli. The phenomenological model based on the Landau–Ginzburg formalism provides a robust framework for explaining the photoinduced transition dynamics, showing a detailed picture of the light interaction with the electronic and lattice subsystems. This integrated approach significantly enhances the understanding of V4O7 complex behavior upon photoexcitation, opening new possibilities for developing new optoelectronic devices and noninvasive optical control of the phase transition pathways in vanadates.","url":"https://doi.org/10.1002/aelm.202400539","authors":["Alexander Bartenev","Camilo Verbel","Qin Wu","Fernando Camino","Armando Rúa","Sergiy Lysenko"],"tags":["Photoexcitation","Materials science","Ultrashort pulse","Photonics","Neuromorphic engineering"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-12-15","doi":"https://doi.org/10.1002/aelm.202400539","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4410424827","name":"Quantum simulations of complex systems","source":"openalex","abstract":"Abstract In this review, we give a brief overview of quantum simulation as applied to the study of complex systems. In particular, we cover the basic ideas of quantum simulation, neuromorphic computation, the Sachdev–Ye–Kitaev model, as well as applications to quantum batteries.","url":"https://doi.org/10.1007/s40766-025-00069-0","authors":["O. Morsch","G. Massimo Palma","Davide Rossini"],"tags":["Computer science","Quantum","Statistical physics","Physics","Quantum mechanics"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-05-01","doi":"https://doi.org/10.1007/s40766-025-00069-0","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4410113721","name":"Strategic & Large-Scale Considerations of Neuromorphic Computing","source":"openalex","abstract":"Hardware Lottery• \"History tells us that scientific progress is imperfect.Intellectual traditions and available tooling can prejudice scientists away from some ideas and towards others.\"• \"…to describe when a research idea wins because it is compatible with available software and hardware, not because the idea is superior to alternative research directions\"• \"Hardware design has prioritized delivering on commercial use cases, while built-in flexibility to accommodate the next generation of ideas remains a secondary consideration.\"","url":"https://doi.org/10.2172/2563860","authors":["Craig M. Vineyard"],"tags":["Neuromorphic engineering","Scale (ratio)","Computer science","Computer architecture","Artificial intelligence"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-04-01","doi":"https://doi.org/10.2172/2563860","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4401307486","name":"Using CSNNs to Perform Event-based Data Processing & Classification on ASL-DVS","source":"openalex","abstract":"Recent advancements in bio-inspired visual sensing and neuromorphic computing have led to the development of various highly efficient bio-inspired solutions with real-world applications. One notable application integrates event-based cameras with spiking neural networks (SNNs) to process event-based sequences that are asynchronous and sparse, making them difficult to handle. In this project, we develop a convolutional spiking neural network (CSNN) architecture that leverages convolutional operations and recurrent properties of a spiking neuron to learn the spatial and temporal relations in the ASL-DVS gesture dataset. The ASL-DVS gesture dataset is a neuromorphic dataset containing hand gestures when displaying 24 letters (A to Y, excluding J and Z due to the nature of their symbols) from the American Sign Language (ASL). We performed classification on a pre-processed subset of the full ASL-DVS dataset to identify letter signs and achieved 100\\% training accuracy. Specifically, this was achieved by training in the Google Cloud compute platform while using a learning rate of 0.0005, batch size of 25 (total of 20 batches), 200 iterations, and 10 epochs.","url":"https://doi.org/10.48550/arxiv.2408.00611","authors":["Ria Patel","Sujit Tripathy","Zachary Sublett","Seoyoung An","Riya Patel"],"tags":["Computer science","Event (particle physics)","Event data","Artificial intelligence","Physics"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-08-01","doi":"https://doi.org/10.48550/arxiv.2408.00611","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4405292220","name":"A Comparative Analysis of Anomaly Detection Methods in IoT Networks: An Experimental Study","source":"openalex","abstract":"The growth of the Internet of Things (IoT) and its integration with Industry 4.0 and 5.0 are generating new security challenges. One of the key elements of IoT systems is effective anomaly detection, which identifies abnormal behavior in devices or entire systems. This paper presents a comprehensive overview of existing methods for anomaly detection in IoT networks using machine learning (ML). A detailed analysis of various ML algorithms, both supervised (e.g., Random Forest, Gradient Boosting, SVM) and unsupervised (e.g., Isolation Forest, Autoencoder), was conducted. The results of tests conducted on popular datasets (IoT-23 and CICIoT-2023) were collected and analyzed in detail. The performance of the selected algorithms was evaluated using commonly used metrics (Accuracy, Precision, Recall, F1-score). The experimental results showed that the Random Forest and Autoencoder methods are highly effective in detecting anomalies. The article highlights the importance of appropriate data preprocessing to improve detection accuracy. Furthermore, the limitations of a centralized machine learning approach in the context of distributed IoT networks are discussed. The article also presents potential directions for future research in the field of anomaly detection in the IoT.","url":"https://doi.org/10.3390/app142411545","authors":["Emanuel Krzysztoń","Izabela Rojek","Dariusz Mikołajewski"],"tags":["Anomaly detection","Anomaly (physics)","Computer science","Data mining","Physics"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-12-11","doi":"https://doi.org/10.3390/app142411545","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4386942778","name":"SpikingNeRF: Making Bio-inspired Neural Networks See through the Real World","source":"openalex","abstract":"In this paper, we propose SpikingNeRF, which aligns the temporal dimension of spiking neural networks (SNNs) with the radiance rays, to seamlessly accommodate SNNs to the reconstruction of neural radiance fields (NeRF). Thus, the computation turns into a spike-based, multiplication-free manner, reducing energy consumption and making high-quality 3D rendering, for the first time, accessible to neuromorphic hardware. In SpikingNeRF, each sampled point on the ray is matched to a particular time step and represented in a hybrid manner where the voxel grids are maintained as well. Based on the voxel grids, sampled points are determined whether to be masked out for faster training and inference. However, this masking operation also incurs irregular temporal length, making it intractable for hardware processors, e.g., GPUs, to conduct parallel training. To address this problem, we develop the temporal padding strategy to tackle the masked samples to maintain regular temporal length, i.e., regular tensors, and further propose the temporal condensing strategy to form a denser data structure for hardware-friendly computation. Experiments on various datasets demonstrate that our method can reduce energy consumption by an average of 70.79\\% and obtain comparable synthesis quality with the ANN baseline. Verification on the neuromorphic hardware accelerator also shows that SpikingNeRF can further benefit from neuromorphic computing over the ANN baselines on energy efficiency. Codes and the appendix are in \\url{https://github.com/Ikarosy/SpikingNeRF-of-CASIA}.","url":"https://doi.org/10.48550/arxiv.2309.10987","authors":["Xingting Yao","Qinghao Hu","Zhou, Fei","Tielong Liu","Zitao Mo","Zeyu Zhu","Zhengyang Zhuge","Jian Cheng"],"tags":["Computer science","Global illumination","Computation","Artificial neural network","Energy consumption"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2023-09-20","doi":"https://doi.org/10.48550/arxiv.2309.10987","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4393866074","name":"Ultrathin All‐Solid‐State MoS 2 ‐Based Electrolyte Gated Synaptic Transistor with Tunable Organic–Inorganic Hybrid Film","source":"openalex","abstract":"Abstract Electrolyte‐gated synaptic transistors (EGSTs) have attracted considerable attention as synaptic devices owing to their adjustable conductance, low power consumption, and multi‐state storage capabilities. To demonstrate high‐density EGST arrays, 2D materials are recommended owing to their excellent electrical properties and ultrathin profile. However, widespread implementation of 2D‐based EGSTs has challenges in achieving large‐area channel growth and finding compatible nanoscale solid electrolytes. This study demonstrates large‐scale process‐compatible, all‐solid‐state EGSTs utilizing molybdenum disulfide (MoS 2 ) channels grown through chemical vapor deposition (CVD) and sub‐30 nm organic‐inorganic hybrid electrolyte polymers synthesized via initiated chemical vapor deposition (iCVD). The iCVD technique enables precise modulation of the hydroxyl group density in the hybrid matrix, allowing the modulation of proton conduction, resulting in adjustable synaptic performance. By leveraging the tunable iCVD‐based hybrid electrolyte, the fabricated EGSTs achieve remarkable attributes: a wide on/off ratio of 10 9 , state retention exceeding 10 3 , and linear conductance updates. Additionally, the device exhibits endurance surpassing 5 × 10 4 cycles, while maintaining a low energy consumption of 200 fJ/spike. To evaluate the practicality of these EGSTs, a subset of devices is employed in system‐level simulations of MNIST handwritten digit recognition, yielding a recognition rate of 93.2%.","url":"https://doi.org/10.1002/advs.202308847","authors":["Jungyeop Oh","Seohak Park","Sang Hun Lee","Sung-Kyu Kim","Hyeonji Lee","Changhyeon Lee","Woonggi Hong","Jun‐Hwe Cha","Mingu Kang","Jun Hyup Jin","Sung Gap Im","Min Ju Kim","Sung‐Yool Choi"],"tags":["Materials science","Electrolyte","Molybdenum disulfide","Chemical vapor deposition","Transistor"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-04-02","doi":"https://doi.org/10.1002/advs.202308847","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4414285733","name":"Biomimetic Janus MXene membrane with bidirectional ion permselectivity for enhanced osmotic effects and iontronic logic control","source":"openalex","abstract":"Osmotic efficiency is fundamentally governed by the balance between membrane ion selectivity and permeability, a challenge central to both biological signal transmission and sustainable energy conversion. Conventional membranes are constrained to unidirectional transport of either cations or anions, severely limiting their versatility and performance. Inspired by the chloride voltage-gated channel 5 (ClC-5), we engineered a biomimetic Janus NP-MXene membrane featuring subnanochannels (~6.0 angstrom) and exceptional structural integrity, enabling controlled, simultaneous Na + /Cl − transport with unprecedented permselectivity. Under a 50-fold salinity gradient, the NP-MXene membrane achieved a record power density of 85.1 watts per square meter and an osmotic potential of 181.5 millivolts, the highest reported for a single device. Harnessing ion-specific signals from multi-ion transport, we further demonstrated an iontronic transistor capable of modulating ion flow by salinity gradients, eliminating the need for external gate voltage. This advance enables encoded signals and robotic control for advanced human-machine interfaces. The scalable fabrication of nanofluidic channels facilitates high-performance iontronics for efficient energy-information flow.","url":"https://doi.org/10.1126/sciadv.adx1184","authors":["Qian Han","Hongzhao Fan","Puguang Peng","Yan Du","Xiang Li","Yanhui Liu","Feiyao Yang","Yanguang Zhou","Zhong Lin Wang","Di Wei"],"tags":["Membrane","Janus","Nanotechnology","Ion channel","Ion transporter"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-09-17","doi":"https://doi.org/10.1126/sciadv.adx1184","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4387952752","name":"Smart Textile Optoelectronics for Human‐Interfaced Logic Systems","source":"openalex","abstract":"Abstract Textiles with a freedom of form factor, unlimited scalability, and high programmability provide an ideal platform for constructing wearable optoelectronic systems. The emerging wearable technologies, like artificial intelligence and Internet of Things, have driven the development of textile optoelectronics from simple functional blocks to sophisticated logic systems, offering a seamless, breathable, and programmable on‐body platform to synergistically sense, analyze, store, and feedback information in response to complex commands. In the past few years, the creation of such smart textile optoelectronics‐based logic systems is boosted by nanomaterial science and manufacturing integration technologies and has revolutionized human–machine interaction paradigms in numerous emerging fields. Herein, in this review, the recent progress of smart textile optoelectronics for human‐interfaced logic systems is timely summarized. This review begins with a concise discussion about the wearability evaluation and integration consideration of textile optoelectronic devices. Then, important breakthroughs in human‐interfaced logic systems based on smart textile optoelectronics are demonstrated by highlighting their representative device, working principle, and application scenarios. Finally, the existing challenges and potential directions in the field of textile optoelectronics‐integrated logic systems are analyzed.","url":"https://doi.org/10.1002/adfm.202308136","authors":["Hongyun Peng","Huiqiao Li","Guangming Tao","Liangjun Xia","Weilin Xu","Tianyou Zhai"],"tags":["Textile","Scalability","Computer science","Wearable computer","Nanotechnology"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2023-10-26","doi":"https://doi.org/10.1002/adfm.202308136","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4403887065","name":"Towards transformative innovation ecosystems: a systemic approach to responsible innovation","source":"openalex","abstract":"To address societal challenges, innovators committed to responsibility need to find ways to break away from unsustainable, or otherwise undesirable, path-dependencies in sociotechnical regimes. Such path-breaking innovation should not come at the expense of socioethical desirability. The emerging literature on responsible innovation ecosystems has focused on socioethical desirability but has neglected sociotechnical viability beyond a protected niche. Drawing on theoretical insights and concepts from the literature on Responsible Innovation, innovation ecosystems, and transition studies, we distinguish four types of ecosystems along the axes of desirability and viability and discuss examples of these types. We introduce the concept of transformative innovation ecosystems to refer to a type of ecosystem that combines desirability with viability. The concept is developed by bringing theoretical perspectives into conversation with empirical insights from the high-tech research and innovation cluster NeuroSys, which aims to create an ecosystem around brain-inspired computing.","url":"https://doi.org/10.1080/23299460.2024.2414482","authors":["Philipp Neudert","Mareike Smolka","Stefan Böschen"],"tags":["Transformative learning","Responsible Research and Innovation","Business","Knowledge management","Sociology"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-10-30","doi":"https://doi.org/10.1080/23299460.2024.2414482","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4296780357","name":"Statics and dynamics of skyrmions interacting with disorder and nanostructures","source":"openalex","abstract":"The study of skyrmions has grown as they have been realized in topologically stable spin-textured magnetic excitations. This overview treats magnetic skyrmions and skyrmion assemblies using a particle-based approach to describe a system in which the energy scales of the skyrmion-skyrmion interactions, sample disorder, temperature, and drive magnitude compete. Pinning and dynamic effects of skyrmions interacting with disordered or ordered substrates are of technological importance for skyrmion applications. Analogs to vortices in type-II superconductors, charge density waves, and colloidal particles are presented.","url":"https://doi.org/10.1103/revmodphys.94.035005","authors":["C. J. O. Reichhardt","C. J. O. Reichhardt","M. V. Miloševıć"],"tags":["Skyrmion","Physics","Condensed matter physics"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2022-09-20","doi":"https://doi.org/10.1103/revmodphys.94.035005","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4405539908","name":"Interfacial Electronic Charge Trapping and Photonic Carrier Excitation Coupling in Solution-Processed Zinc–Tin Oxide Thin-Film Transistors Applied for Logic Gate Design and Quantized Neural Network","source":"openalex","abstract":"High Resolution Image Download MS PowerPoint Slide Components needed in Artificial Intelligence with a higher information capacity are critically needed and have garnered significant attention at the forefront of information technology. This study utilizes solution-processed zinc–tin oxide (ZTO) thin-film phototransistors and modulates the values of V G, which allows for the regulation of electron trapping/detrapping at the ZTO/SiO 2 interface. By coupling the excited photonic carrier and electronic trapping, logic gates such as “AND,” “OR,” “NAND,” and “NOR” can be achieved. With the exponential growth in data generation, efficient processing and storage solutions are imperative. However, extensive data transfer between computing units and storage limits the level of artificial neural networks (ANNs). Consequently, quantized neural networks (QNNs) have gained interest for their reduced computational resource requirements and lower consumption. In this context, we introduce an optimized ternary logic circuit based on ZTO devices. By utilizing optical modulation to adjust the turn-on voltage of the single device, we demonstrate the achievement of ternary current states, thereby providing three distinct discrete states. This configuration can be extended to QNN computing, demonstrating multilevel quantized current values for in-memory computation. We achieved a handwriting digit recognition rate of 91.6%, thereby demonstrating reliable QNN hardware performance. This robust QNN performance indicates that the metal oxide phototransistor shows significant potential for future ternary computing systems.","url":"https://doi.org/10.1021/acsami.4c15102","authors":["Pei-Hsuan Chang","Wun-Yun Lin","Ya‐Chi Huang","Yu-Chieh Chen","Li‐Chung Shih","Jen‐Sue Chen"],"tags":["Materials science","Trapping","Optoelectronics","Excitation","Tin"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-12-18","doi":"https://doi.org/10.1021/acsami.4c15102","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W7106521575","name":"Ferroelectric Field-Effects for Neuromorphic Hardware","source":"openalex","abstract":"On conventional computers, the performance of AI models is limited by the data transfer between the memory and the processor. Compute-in-Memory architectures offer a new paradigm: Vector-Matrix Multiplications may be performed by a voltage drop through a matrix of programmable resistances, the “synaptic weights”. Ferroelectric materials are excellent candidates for their realization:[1] in a two- or three-terminals geometry and in combination with a semiconducting oxide,[2], [3], [4] the conductance is programmed by controlling the configuration of the ferroelectric domains. The unique fluorite unit cell of HfZrO4 allows for the stabilization of ferroelectricity below 3 nm,[5] facilitating the scaling of synaptic weights. The mechanisms governing the resistive switching in WOx / HZO-SL (5 nm) bilayers are discussed. The effect of the programming pulse duration and amplitude on the polarization switching are investigated, from milliseconds to nanoseconds timescales. Devices of different sizes and shapes are measured down to 500 nm in dimension. For an device size of 1 micrometer square, an On/Off ratio as high as 8 is obtained for 20 ns pulses, a 4-fold improvement compared to 40 um devices. The relatively low crystallization temperature of polycrystalline hafnium oxide / zirconium oxide superlattices (HZO-SL) is compatible with the Back-End-Of-Line (BEOL) of CMOS transistors.[6], [7] These results not only demonstrate the functionalization of the BEOL with synaptic weights, but also pave the way for the integration of ferroelectric field-effect transistors with Beyond CMOS semiconductors. [1] T. Mikolajick, et al., “From Ferroelectric Material Optimization to Neuromorphic Devices,” Advanced Materials, 2023, doi: 10.1002/adma.202206042. [2] L. Bégon-Lours et al., “Scaled, Ferroelectric Memristive Synapse for Back-End-of-Line Integration with Neuromorphic Hardware,” Advanced Electronic Materials, 2022, doi: 10.1002/aelm.202101395. [3] M. Halter et al., “Back-End, CMOS-Compatible Ferroelectric Field-Effect Transistor for Synaptic Weights,” ACS Appl. Mater. Interfaces, 2020, doi: 10.1021/acsami.0c00877. [4] M. Halter, et al., “A multi-timescale synaptic weight based on ferroelectric hafnium zirconium oxide,” COMMUNICATIONS MATERIALS, 2023, doi: 10.1038/s43246-023-00342-x. [5] L. Bégon-Lours et al., “Effect of cycling on ultra-thin HfZrO4, ferroelectric synaptic weights,” Neuromorph. Comput. Eng., 2022, doi: 10.1088/2634-4386/ac5b2d. [6] L. Bégon-Lours et al., “Back-End-of-Line Integration of Synaptic Weights using HfO2/ZrO2 Nanolaminates,” Advanced Electronic Materials, 2024, doi: 10.1002/aelm.202300649. [7] R. Hamming-Green, et al., “Multi-Level, Low-Voltage Programming of Ferroelectric HfO 2 /ZrO 2 Nanolaminates Integrated in the Back-End-Of-Line,” in 2024 8th IEEE EDTM, Bangalore, India, 2024, doi: 10.1109/EDTM58488.2024.10511719.","url":"https://doi.org/10.3929/ethz-c-000787924","authors":["Begon-Lours, Laura"],"tags":["Ferroelectricity","Neuromorphic engineering","Materials science","Optoelectronics","CMOS"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-10-20","doi":"https://doi.org/10.3929/ethz-c-000787924","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W7155223424","name":"Neuromorphic computing for radar and radio systems: a survey","source":"openalex","abstract":"Abstract Taking inspiration from the brain on how to create energy efficient and low latency neuromorphic systems has the potential to create new opportunities with AI across many domains. Firstly, it creates a possibility to mitigate problems with too large digital signal processing costs in various technologies. Secondly, it also enables the use of AI and machine learning algorithms where it is currently impossible due to energy constraints. Recently, neuromorphic technology has been introduced to radio communication and radar applications. In this work, we highlight advantages of applying energy efficient, low latency and often lightweight neuromorphic computing for radar and radio signal processing. We perform a comprehensive review of the main current works on neuromorphic technology for radar applications, focusing on frequency-modulated continuous-wave and synthetic aperture radar. Additionally, we cover radio frequency signal classification for both radar and radio signals. Our ambition is to facilitate research on neuromorphic computing for radar and radio systems, as well as help bringing researchers from these fields together.","url":"https://doi.org/10.1088/2634-4386/ae6369","authors":["Hanna Hamrell","Thomas K. Sjögren","Hannes Ovrén"],"tags":["Neuromorphic engineering","Radar","Computer science","Energy (signal processing)","Software-defined radio"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2026-04-22","doi":"https://doi.org/10.1088/2634-4386/ae6369","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4398243919","name":"Physics to system-level modeling of silicon-organic-hybrid nanophotonic devices","source":"openalex","abstract":"The continuous growth in data volume has sparked interest in silicon-organic-hybrid (SOH) nanophotonic devices integrated into silicon photonic integrated circuits (PICs). SOH devices offer improved speed and energy efficiency compared to silicon photonics devices. However, a comprehensive and accurate modeling methodology of SOH devices, such as modulators corroborating experimental results, is lacking. While some preliminary modeling approaches for SOH devices exist, their reliance on theoretical and numerical methodologies, along with a lack of compatibility with electronic design automation (EDA), hinders their seamless and rapid integration with silicon PICs. Here, we develop a phenomenological, building-block-based SOH PICs simulation methodology that spans from the physics to the system level, offering high accuracy, comprehensiveness, and EDA-style compatibility. Our model is also readily integrable and scalable, lending itself to the design of large-scale silicon PICs. Our proposed modeling methodology is agnostic and compatible with any photonics-electronics co-simulation software. We validate this methodology by comparing the characteristics of experimentally demonstrated SOH microring modulators (MRMs) and Mach Zehnder modulators with those obtained through simulation, demonstrating its ability to model various modulator topologies. We also show our methodology's ease and speed in modeling large-scale systems. As an illustrative example, we use our methodology to design and study a 3-channel SOH MRM-based wavelength-division (de)multiplexer, a widely used component in various applications, including neuromorphic computing, data center interconnects, communications, sensing, and switching networks. Our modeling approach is also compatible with other materials exhibiting the Pockels and Kerr effects. To our knowledge, this represents the first comprehensive physics-to-system-level EDA-compatible simulation methodology for SOH modulators.","url":"https://doi.org/10.1038/s41598-024-61618-x","authors":["Maryam Moridsadat","Marcus Tamura","Lukas Chrostowski","Sudip Shekhar","Bhavin J. Shastri"],"tags":["Computer science","Silicon photonics","Nanophotonics","Photonics","Neuromorphic engineering"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-05-23","doi":"https://doi.org/10.1038/s41598-024-61618-x","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4411727697","name":"Real-time human-robot interaction and service provision using hybrid intelligent computing framework","source":"openalex","abstract":"Human-robot interaction has gained significant attention in various domains, including healthcare, customer service, and industrial automation. High computational cost, inefficient service matching, and elevated failure rates in dynamic service contexts are some primary disadvantages of existing query-processing systems. This research introduces a Hybrid Intelligent Computing Model (HICM) to improve robots' ability to process inquiries autonomously. The goal is to make robots better at responding to human questions in real time with efficient, personalized, and context-specific solutions. Using self-organized computing approaches, robotic agents can reliably provide end-users with services suited to their demands. Due to their autonomous nature, robots must be able to calculate quickly and accurately to provide timely services. To meet these needs, the proposed HICM incorporates a sophisticated decision-support system to handle human questions and find the appropriate services. Within this decision-making framework, the model evaluates the characteristics and relevance of questions about accessible services by combining annealing and Tabu Search approaches. To avoid addressing queries incompatibly, the Tabu Search technique approaches query resolution as a non-convergent optimization issue. Comparing HICM's performance to other models reveals significant improvements over CDS, DGTA, and CCS. In particular, HICM reduced calculation time by 8.67%, service time by 15.09%, and failure rates by 7.87%. In terms of important metrics, HICM fared better than the competing models. Its success factor was 11.8% higher, its matching ratio was 14.88% higher, and its failure rates were 6.22% lower. These findings demonstrate the model's efficiency and reliability in terms of robotic query processing and real-time service delivery.","url":"https://doi.org/10.1371/journal.pone.0324986","authors":["Mohammed Albekairi","Meshari D. Alanazi","Turki M. Alanazi","Mohamed Vall Ould Mohamed","Khaled Kaâniche","Anis Sahbani","Ali Elrashidi"],"tags":["Computer science","Automation","Robot","Matching (statistics)","Simulated annealing"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-06-27","doi":"https://doi.org/10.1371/journal.pone.0324986","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4409282579","name":"A materials- and devices-centric approach to neuromorphic computing","source":"openalex","abstract":"The fundamental physics of spintronic devices makes them an excellent technology for realizing neuromorphic computing hardware. At the heart of all spintronic devices is a magnetic material that can be driven out of equilibrium with spin torques and host dynamics, such as phase transitions and criticality, self-oscillations, synchronization, stochastic resonance, and chaos, which form the basis of many brain algorithms. This paper highlights the potential of magnetic tunnel junctions for realizing the key building blocks, including on-chip non-volatile memory, probabilistic bits, stochastic oscillators, coherent oscillators, of echo-state networks, spiking neural networks, and population coding neural systems for edge AI applications. Antiferromagnetic spintronics offers a new paradigm to exploit a plethora of antiferromagnetic materials for energy-efficient computing applications. We present calculations of device performance, energy dissipation, and offer insights into technology-device co-optimization. System-level calculations of the performance of a spintronics-based spiking neural network for practical workloads that uses spiking antiferromagnetic neurons with auto-reset functionality, ferromagnetic synapses, and electrical interconnects are discussed. Our calculations reveal that the energy consumption of the network is limited by the ferromagnetic synapses and electrical interconnects, while the latency is dominated by neurons. Yet, spintronics spiking networks perform at a fraction of energy and latency cost compared to CMOS-only solutions, while spintronics systems are also much more area efficient. The paper concludes by summarizing the limits, challenges, and opportunities of spintronics for edge AI applications.","url":"https://doi.org/10.1145/3676536.3697133","authors":["Shaloo Rakheja"],"tags":["Neuromorphic engineering","Computer science","Computer architecture","Computational science","Artificial neural network"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-10-27","doi":"https://doi.org/10.1145/3676536.3697133","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4399132882","name":"Electroactive composite biofilms integrating Kombucha, Chlorella and synthetic proteinoid Proto–Brains","source":"openalex","abstract":"In this study, we present electroactive biofilms made from a combination of Kombucha zoogleal mats and thermal proteinoids. These biofilms have potential applications in unconventional computing and robotic skin. Proteinoids are synthesized by thermally polymerizing amino acids, resulting in the formation of synthetic protocells that display electrical signalling similar to neurons. By incorporating proteinoids into Kombucha zoogleal cellulose mats, hydrogel biofilms can be created that have the ability to efficiently transfer charges, perform sensory transduction and undergo processing. We conducted a study on the memfractance and memristance behaviours of composite biofilms, showcasing their capacity to carry out unconventional computing operations. The porous nanostructure and electroactivity of the biofilm create a biocompatible interface that can be used to record and stimulate neuronal networks. In addition to in vitro neuronal interfaces, these soft electroactive biofilms show potential as components for bioinspired robotics, smart wearables, unconventional computing devices and adaptive biorobotic systems. Kombucha-proteinoids composite films are a highly customizable material that can be synthesized to suit specific needs. These films belong to a unique category of ‘living’ materials, as they have the ability to support cellular systems and improve bioelectronic functionality. This makes them an exciting prospect in various applications. Ongoing efforts are currently being directed towards enhancing the compositional tuning of conductivity, signal processing and integration within hybrid bioelectronic circuits.","url":"https://doi.org/10.1098/rsos.240238","authors":["Anna Nikolaidou","Panagiotis Mougkogiannis","Andrew Adamatzky"],"tags":["Biofilm","Chlorella","Chemistry","Composite number","Biochemistry"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-05-01","doi":"https://doi.org/10.1098/rsos.240238","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4414069761","name":"Neural Synaptic Simulation Based on ZnAlSnO Thin-Film Transistors","source":"openalex","abstract":"In the era of artificial intelligence, neuromorphic devices that simulate brain functions have received increasingly widespread attention. In this paper, an artificial neural synapse device based on ZnAlSnO thin-film transistors was fabricated, and its electrical properties were tested: the current-switching ratio was 1.18 × 107, the subthreshold oscillation was 1.48 V/decade, the mobility was 2.51 cm2V−1s−1, and the threshold voltage was −9.40 V. Stimulating artificial synaptic devices with optical signals has the advantages of fast response speed and good anti-interference ability. The basic biological synaptic characteristics of the devices were tested under 365 nm light stimulation, including excitatory postsynaptic current (EPSC), paired-pulse facilitation (PPF), short-term plasticity (STP), and long-term plasticity (LTP). This device shows good synaptic plasticity. In addition, by changing the gate voltage, the excitatory postsynaptic current of the device at different gate voltages was tested, two different logical operations of “AND” and “OR” were achieved, and the influence of different synaptic states on memory was simulated. This work verifies the application potential of the device in the integrated memory and computing architecture, which is of great significance for promoting the high-quality development of neuromorphic computing hardware.","url":"https://doi.org/10.3390/mi16091025","authors":["Yang Zhao","Chao Wang","Laizhe Ku","Liang Guo","Xuefeng Chu","Fan Yang","Jieyang Wang","Chunlei Zhao","Yaodan Chi","Xiaotian Yang"],"tags":["Neuromorphic engineering","Excitatory postsynaptic potential","Postsynaptic potential","Transistor","Synapse"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-09-07","doi":"https://doi.org/10.3390/mi16091025","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W7131910141","name":"Photonic Neuromorphic Computing enabled by a BIC Metasurface","source":"openalex","abstract":"Photonic neuromorphic computing promises revolutionary advances in parallel and high-speed processing, yet a key challenge persists: co-integrating nonlinearity, dense connectivity, and intrinsic memory monolithically to enable brain-inspired, spatiotemporal information processing. Here, we overcome this challenge by introducing a monolithic photonic recurrent network based on an active metasurface operating at bound state in the continuum (BIC). The BIC mode mediates strong,long-range coupling across the lattice, creating a reconfigurable recurrent network topology in hardware. Concurrently, the gain medium provides both optical nonlinearity for neuronal activation and a finite carrier lifetime that serves as a built in, analog temporal memory. This synergy enables computation to emerge directly from the collective spatiotemporal dynamics of the driven-dissipative photonic system, effectively realizing a physical reservoir computer on a chip. We experimentally validate a minimal yet physically complete system on benchmark tasks: brain MRI image classification and human action recognition, achieving 92.16% and 85.36% accuracies, respectively. This work establishes a scalable pathway toward ultrafast, energy-efficient neuromorphic intelligence where processing is an inherent property of tailored light matter interaction.","url":"https://openalex.org/W7131910141","authors":["Jingsong Fu","Ruiheng Jin","Zhaohui Xie","Haijun Tang","Xiong Jiang","Yue Cui","Xiangtong Kong","Wentao Hao","Geyang Qu","Can Huang","Qingha Song"],"tags":["Neuromorphic engineering","Reservoir computing","Computer science","Scalability","Photonics"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2026-02-26","doi":"","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4410446803","name":"Forecasting the future: From quantum chips to neuromorphic engineering and bio-integrated processors","source":"openalex","abstract":"Computing is at the forefront of advances in human civilization and technology. Alongside communication, it is a critical technology that often drives improvements in many other scientific fields. Over the last 60 years, computing has achieved unprecedented advances attributed to scaling laws predicted by Moore’s law, whereby the number of components on a chip doubles every two years, and Dennard’s voltage scaling, whereby the voltage of components is also halved. However, continuous similar advances are no longer necessarily guaranteed, leading to the potential emergence of the so-called ‘Beyond Moore’s Law’ era. Even while traditional transistor scaling is ending, the demand for computing continues to grow in all sectors of the economy by almost orders of magnitude. The end of traditional scaling is expected to result in a computing crunch due to an energy crisis, necessitating the exploration of renewable sources of energy and computers that consume far less energy. Among many possible alternative computing architectures, neuromorphic computing based on brain-inspired computing is one of the most promising (Feng et al., 2018; Himelstein, 2022; Schell, 2024).","url":"https://doi.org/10.70593/978-93-49910-47-8_12","authors":["Botlagunta Preethish Nandan"],"tags":["Neuromorphic engineering","Computer architecture","Quantum","Computer science","Systems engineering"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-05-07","doi":"https://doi.org/10.70593/978-93-49910-47-8_12","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W7141935789","name":"A neuroscience perspective on dendrites for neuromorphic computing","source":"openalex","abstract":"","url":"https://doi.org/10.2172/3024806","authors":["Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)","Frances Chance"],"tags":["Neuromorphic engineering","Perspective (graphical)","Computer science","Neuroscience","Cognitive science"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-03-01","doi":"https://doi.org/10.2172/3024806","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4406829651","name":"Reliable, efficient, and scalable photonic inverse design empowered by physics‐inspired deep learning","source":"openalex","abstract":"On-chip computing metasystems composed of multilayer metamaterials have the potential to become the next-generation computing hardware endowed with light-speed processing ability and low power consumption but are hindered by current design paradigms. To date, neither numerical nor analytical methods can balance efficiency and accuracy of the design process. To address the issue, a physics-inspired deep learning architecture termed electromagnetic neural network (EMNN) is proposed to enable an efficient, reliable, and flexible paradigm of inverse design. EMNN consists of two parts: EMNN Netlet serves as a local electromagnetic field solver; Huygens-Fresnel Stitch is used for concatenating local predictions. It can make direct, rapid, and accurate predictions of full-wave field based on input fields of arbitrary variations and structures of nonfixed size. With the aid of EMNN, we design computing metasystems that can perform handwritten digit recognition and speech command recognition. EMNN increases the design speed by 17,000 times than that of the analytical model and reduces the modeling error by two orders of magnitude compared to the numerical model. By integrating deep learning techniques with fundamental physical principle, EMNN manifests great interpretability and generalization ability beyond conventional networks. Additionally, it innovates a design paradigm that guarantees both high efficiency and high fidelity. Furthermore, the flexible paradigm can be applicable to the unprecedentedly challenging design of large-scale, high-degree-of-freedom, and functionally complex devices embodied by on-chip optical diffractive networks, so as to further promote the development of computing metasystems.","url":"https://doi.org/10.1515/nanoph-2024-0504","authors":["Guocheng Shao","Tiankuang Zhou","Tao Yan","Yanchen Guo","Zhao Yun","Ruqi Huang","Lu Fang"],"tags":["Computer science","Deep learning","Scalability","Computer engineering","Metamaterial"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-01-26","doi":"https://doi.org/10.1515/nanoph-2024-0504","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W7115181294","name":"Potentialities of electrochemical devices for memory and neuromorphic computing","source":"openalex","abstract":"This chapter explores the transformative role of electrochemical devices in next-generation memory and neuromorphic computing systems. Bridging the gap between traditional energy applications and intelligent electronics, electrochemical platforms leverage ionic–electronic coupling to mimic synaptic behaviors found in biological systems. This chapter presents the working principles and architectures of key electrochemical memory technologies such as electrochemical random-access memory (ECRAM), organic electrochemical transistors (OECTs), and electrochemical synaptic transistors (ESTs), emphasizing their analog programmability, low-power operation, and integration potential. These devices offer a viable solution to the limitations of conventional von Neumann computing by co-locating memory and processing units, fostering energy-efficient, adaptive, and brain-inspired computing. The chapter also addresses critical material and architectural challenges, such as ion transport control, state retention, and scalability. With growing interest in neuromorphic engineering, electrochemical systems present an adaptable and interdisciplinary platform poised to drive innovation in edge computing, artificial intelligence, and bio-integrated electronics.","url":"https://doi.org/10.1039/9781837070244-00001","authors":["Harshita Rai","Kshitij RB Singh","Arunadevi Natarajan","Shyam S. Pandey"],"tags":["Neuromorphic engineering","Von Neumann architecture","Computer science","Leverage (statistics)","Bridging (networking)"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-12-15","doi":"https://doi.org/10.1039/9781837070244-00001","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4404016562","name":"Variable‐Range Hopping Conduction in Amorphous, Non‐Stoichiometric Gallium Oxide","source":"openalex","abstract":"Abstract Amorphous, non‐stoichiometric gallium oxide (a‐GaO x , x < 1.5) is a promising material for many electronic devices, such as resistive switching memories, neuromorphic circuits and photodetectors. So far, all respective measurements are interpreted with the explicit or implicit assumption of n‐type band transport above the conduction band mobility edge. In this study, the experimental and theoretical results consistently show for the first time that for an O/Ga ratio x of 0.8 to 1.0 the dominating electron transport mechanism is, however, variable‐range hopping (VRH) between localized states, even at room temperature and above. The measured conductivity exhibits the characteristic exponential temperature dependence on T −1/4 , in remarkable agreement with Mott's iconic law for VRH. Localized states near the Fermi level are confirmed by photoelectron spectroscopy and density of states (DOS) calculations. The experimental conductivity data is reproduced quantitatively by kinetic Monte Carlo (KMC) simulations of the VRH mechanism, based on the ab‐initio DOS. High electric field strengths F cause elevated electron temperatures and an exponential increase of the conductivity with F 1/2 . Novel results concerning surface oxidation, magnetoresistance, Hall effect, thermopower and electron diffusion are also reported. The findings lead to a new understanding of a‐GaO x devices, also with regard to metal|a‐GaO x Schottky barriers.","url":"https://doi.org/10.1002/aelm.202400407","authors":["Philipp Hein","Tobias Romstadt","Fabian M. Draber","Jinseok Ryu","Thorben Böger","Andreas Falkenstein","Miyoung Kim","Manfred Martin"],"tags":["Variable-range hopping","Materials science","Amorphous solid","Stoichiometry","Range (aeronautics)"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-11-03","doi":"https://doi.org/10.1002/aelm.202400407","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W7150754891","name":"Controlled oxygen vacancy electrode reservoir for robust WO3-based memory devices","source":"openalex","abstract":"Abstract Oxide-based memristors are promising candidates as neuromorphic hardware in energy-efficient edge computing applications for the Internet of Things (IoT). However, achieving simultaneously optimized memristive and synaptic performance with low-temperature fabrication, compatible with complementary metal-oxide-semiconductor (CMOS) processes, remains a challenge. Here, we demonstrate a dual-function electrode selection strategy—controlled oxygen vacancy electrode reservoir—implemented in a simple, low-temperature-fabricated indium tin oxide (ITO)/WO 3 /TiN thin film system. We systematically vary the oxygen stoichiometry in the ITO top electrode, which serves not only as an electrical contact, but also as a dynamic oxygen reservoir. A high oxygen-vacancy concentration in the ITO enables optimized memristive performance of low electroforming and operation voltages, and robust memristive and synaptic endurance. This electrode-focused defect engineering approach offers a versatile route to advanced memristor design, enabling many applications in IoT and neuromorphic systems.","url":"https://doi.org/10.1038/s43246-026-01143-8","authors":["Ziyi Yuan","Babak Bakhit","Jiahao Lu","Yi-Xuan Liu","Atif Jan","Xinjuan Li","Abin Varghese","Bipin Rajendran","Caterina Ducati","Giuliana Di Martino","Markus Hellenbrand","Judith Louise MacManus-Driscoll"],"tags":["Neuromorphic engineering","Memristor","Materials science","Electroforming","Electrode"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2026-04-06","doi":"https://doi.org/10.1038/s43246-026-01143-8","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4415543396","name":"Ultra‐Sensitive Negative Photoconductivity Transistors via Long‐Afterglow Doping for All‐Optical Encryption","source":"openalex","abstract":"Abstract Negative photoconductivity (NPC)‐based devices, characterised by the light‐induced suppression of electrical conduction, have garnered significant interest for their multifunctional optoelectronic applications, fast light response and broadband spectral adaptability. However, conventional planar heterostructured NPC‐based devices exhibit poor device performance owing to interfacial defects that disrupt carrier transport and recombination dynamics. In this study, an innovative bulk doping strategy is presented that incorporates organic long‐afterglow materials into polymer semiconductors to achieve high‐performance negative photoconductivity transistors (NPTs). The long‐afterglow dopants generate long‐lived charge separation states that effectively trap gate‐modulated majority carriers of polymer semiconductors, enabling persistent NPC with photosensitivity (5.29 × 10⁶) and detectivity (3.40 × 10 13 Jones). In addition, this bulk doping strategy creates abundant trapping sites, which enable intralayer carrier recombination within the doped semiconductor film while maintaining an ultrahigh photosensitivity. Notably, this strategy can be generalised across diverse dopant‐semiconductor systems. Furthermore, leveraging these exceptional NPTs, the negative synaptic functionalities are successfully emulated. To highlight its practical potential, system‐level applicability is demonstrated by integrating NPTs into a recurrent neural network (RNN) for all‐optical encryption/decryption, achieving up to 91% accuracy. This study establishes a general paradigm for high‐performance NPC‐based devices, unlocking their potential for next‐generation optoelectronics and secure neuromorphic systems.","url":"https://doi.org/10.1002/adma.202514723","authors":["Jiangli Han","Ding Ma","Lixian Jiang","Yu Zhang","Meiqiu Dong","Yunfeng Deng","Yanhou Geng","Rui Huang","Cheng Xu","Xin Zheng","Guifang Dong","Lian Duan"],"tags":["Materials science","Optoelectronics","Photoconductivity","Doping","Transistor"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-10-25","doi":"https://doi.org/10.1002/adma.202514723","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W7140112752","name":"Symmetric pulse-enabled highly linear analog switching in ALD-grown HfO2/Ta2O5-based memristor for multi-level storage and synaptic applications","source":"openalex","abstract":"Analog memristors with multilevel cells are suitable for analog in-memory and neuromorphic applications. Herein, we report a 2-bit/cell complementary-metal-oxide-semiconductor (CMOS)-compatible HfO 2 /Ta 2 O 5 bilayer memristor with both TiN electrodes fabricated via single thermal atomic layer deposition at 300 °C. The fabricated devices exhibit stable bipolar switching characteristics distinguished between both low resistance state and the high resistance state with a P/E endurance of 10 5 WRITE cycles, as well as show better retention property beyond 10 4 s. The devices exhibited excellent uniformity in terms of low device-to-device (D2D) and low cycle-to-cycle (C2C) variation. Furthermore, analog switching responses are implemented with the pulse width from 2 ms to 500 µs, and the corresponding percentage change in the device resistance was measured. The results exhibit a significant change in the device resistance even at 500 µs, with an overall change in the device resistance in the range of 10%–17%. In addition, the performance of the devices has been verified for neuromorphic applications using the experimentally extracted data. The non-linearity of 0.07, including highly stable synaptic plasticity, has been achieved using symmetric pulses, making the devices compatible for designing an analog memristor-based neuromorphic computing system hardware.","url":"https://doi.org/10.3389/fnano.2026.1788527","authors":["Parthasarathi Pal","Sanjay Kumar","Themis Prodromakis"],"tags":["Neuromorphic engineering","Memristor","Materials science","Synaptic weight","Optoelectronics"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2026-03-23","doi":"https://doi.org/10.3389/fnano.2026.1788527","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4416251859","name":"Dynamic Reservoir Computing with Physical Neuromorphic Networks","source":"openalex","abstract":"Reservoir Computing (RC) with physical systems requires an understanding of the underlying structure and internal dynamics of the specific physical reservoir. In this study, physical nano–electronic networks with neuromorphic dynamics are investigated for their use as physical reservoirs in an RC framework. These neuromorphic networks operate as dynamic reservoirs, with node activities in general coupled to the edge dynamics through nonlinear nano–electronic circuit elements, and the reservoir outputs influenced by the underlying network connectivity structure. This study finds that networks with varying degrees of sparsity generate more useful nonlinear temporal outputs for dynamic RC compared to dense networks. Dynamic RC is also tested on an autonomous multivariate chaotic time series prediction task with networks of varying densities, which revealed the importance of network sparsity in maintaining network activity and overall dynamics, that in turn enabled the learning of the chaotic Lorenz63 system’s attractor behavior.","url":"https://doi.org/10.1109/ijcnn64981.2025.11229247","authors":["Yinhao Xu","Georg A. Gottwald","Zdenka Kuncic"],"tags":["Neuromorphic engineering","Reservoir computing","Computer science","Attractor","Chaotic"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-06-30","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229247","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4385670534","name":"Key Concepts, Technologies, Current Challenges and Research Areas of Telecommunication Engineering and Neural Communication","source":"openalex","abstract":"The field of telecommunication engineering has undergone remarkable progress, focusing on enhancing data transfer speed and reliability. Despite these advancements, challenges remain, particularly concerning the growing demand for bandwidth and the need for more efficient communication systems. In contrast, neural communication, a burgeoning field, seeks to leverage neural networks' principles in communication systems. The convergence of telecommunication engineering and neural communication holds promise for revolutionary advancements in communication methods. This research paper presents an overview of telecommunication engineering, encompassing key concepts, technologies, current challenges, and research areas. It also addresses neural communication, covering its key concepts, technologies, current challenges, and research areas. Furthermore, the paper explores the intersection of telecommunication engineering and neural communication, highlighting ongoing research and development, potential future developments, and potential applications. The paper concludes by summarizing key findings and recommending directions for future research in this exciting area.","url":"https://doi.org/10.53759/0088/jbsha202303004","authors":["Anandakumar Haldorai"],"tags":["Telecommunications","Key (lock)","Leverage (statistics)","Computer science","Communications system"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2023-01-05","doi":"https://doi.org/10.53759/0088/jbsha202303004","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4416738940","name":"Low-Power Ionically Tunable Bilayer MoS 2 Synaptic Transistors","source":"openalex","abstract":"High Resolution Image Download MS PowerPoint Slide Electrochemical random-access memory (ECRAM) devices offer the possibility of highly linear, energy-efficient conductance modulation via electrochemical doping. This makes them attractive as synaptic weights for neuromorphic applications. Herein, we demonstrate inorganic ECRAM transistors with two-dimensional (2D) bilayer MoS 2 channels exhibiting both ionic and electrostatic gating. Our devices show electrochemical modulation of the channel conductance and electrostatic gating to achieve idle-state leakage currents of I D < 100 fA (measurement limit). These unique capabilities are enabled by the 2D semiconductor channel, which supports both electrostatic (conventional field effect) and electrochemical, non-volatile gating. Unlike oxide-based ECRAMs, which typically operate in a degenerately doped regime, the crystalline 2D channel has a low baseline carrier density, which can be modulated electrostatically. Our devices demonstrate highly linear and symmetric training characteristics, evaluated using synaptic metrics commonly applied to memristive devices. These findings highlight the potential of 2D-based ECRAM devices for power-efficient synaptic electronics.","url":"https://doi.org/10.1021/acs.nanolett.5c02372","authors":["Or Levit","Emanuel Ber","Yair Keller","Boris Minkovich","Eilam Yalon"],"tags":["Materials science","Neuromorphic engineering","Conductance","Transistor","Gating"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-11-17","doi":"https://doi.org/10.1021/acs.nanolett.5c02372","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4407838685","name":"Reconfigurable logic circuits and rectifier based on two-terminal ionic homojunctions","source":"openalex","abstract":"Reconfigurable logic devices that can perform multiple functions with fewer components offer a solution for increasing data processing demands. Achieving reconfigurability without complex designs, however, remains challenging. In this study, we present a two-terminal reconfigurable homojunction device based on ionic-conducting CuInP 2 S 6 (CIPS). The device achieves tunable and reversible rectification by controlling Cu migration under an electric field. The homojunction is formed by modulating the contact potential of the CIPS channel, resulting in an asymmetric contact barrier. The resulting device has a rectification ratio of up to 4 × 10⁴, an ultra-low leakage current (∼100 fA), and a high breakdown voltage of 170 V, maintaining read stability over 3,000 cycles. It operates at frequencies up to 10 kHz and can be reconfigured as OR and AND logic states depending on the Cu migration direction of the CIPS homojunction.","url":"https://doi.org/10.1016/j.device.2025.100712","authors":["Zhipeng Zhong","Xing Cheng","Wenqing Song","Qianyi Yang","Xiang Li","Yuyang Wang","Wan Wang","Yezhao Zhuang","Yan Chen","Wu Shi","Tie Lin","Xiangjian Meng","Hai Huang","Jianlu Wang","Junhao Chu"],"tags":["Terminal (telecommunication)","Electronic circuit","Rectifier (neural networks)","Computer science","Materials science"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-02-21","doi":"https://doi.org/10.1016/j.device.2025.100712","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W7161758747","name":"Introducing sustainable neuromorphic computing in Engineering Mechanics","source":"openalex","abstract":"Abstract We introduce a sustainable neuromorphic approach for numerical simulations in Engineering Mechanics. The finite element method (FEM) is widely used in engineering design; however, worldwide, there is no neuromorphic technology available in mechanics, even though the need for computational capacity with complex mechanical models is increasing 1 . AI-enhanced engineering approaches, such as agent-based models 2 , intensify the high energy demand coupled to CO 2 emissions 3,4 . However, the solution of mechanical boundary value problems in numerical simulations on neuromorphic chips accounting for physical and geometrical nonlinearities has not been researched. Here we show that complex mechanical phenomena can be approximated by spiking neural networks (SNN), thereby creating a new sparse signal transmission of mechanical state variables. We found that hybrid neural networks, composed of sparse and non-sparse neuronal activity, result in the best trade-off between accuracy and energy savings. The required energy is reduced by several orders of magnitude compared to classical numerical simulations, which can significantly lower CO 2 emissions in time-consuming computations. Due to their inherent path dependency, spike activation models are well-suited for nonlinear regression and physics-based approaches in nonlinear mechanics. Our results demonstrate how neuromorphic computing can be applied to a wide range of structural forming processes in engineering, since it differs fundamentally from neuromorphic classification studies in the literature and provides the basis for function approximation. Moreover, it is investigated how neural networks and non-machine learning operations can be deployed on Field-Programmable Gate Arrays (FPGAs). We anticipate our study to be a starting point for more sustainable AI models in engineering science and related disciplines.","url":"https://doi.org/10.1038/s44387-026-00118-x","authors":["Marcus Stoffel","Rutwik Gulakala","Vasileios Polydoras","Saurabh Balkrishna Tandale"],"tags":["Neuromorphic engineering","Nonlinear system","Artificial neural network","Computer science","Energy (signal processing)"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2026-05-21","doi":"https://doi.org/10.1038/s44387-026-00118-x","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4401100137","name":"Highly stable two-dimensional Ruddlesden–Popper perovskite-based resistive switching memory devices","source":"openalex","abstract":"s, and good endurance characteristics of 200 cycles. This study investigates temperature-dependent RS behaviors, elucidating the creation and annihilation of a conducting pathway in the presence of an external electric field. Additionally, the RS property of 2D RP perovskite-based memory devices is found to be retained over 45 days at ambient conditions under a relative humidity of 47% ± 4%. Our findings may accelerate the technological deployment of stable 2D perovskite-based RS memory devices for successful logic application.","url":"https://doi.org/10.1039/d4nr01395f","authors":["Milon Kundar","Koushik Gayen","Rajeev Ray","Dushyant Kushavah","Suman Kalyan Pal"],"tags":["Perovskite (structure)","Resistive random-access memory","Resistive touchscreen","Materials science","Data retention"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-01-01","doi":"https://doi.org/10.1039/d4nr01395f","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4410436654","name":"Enhancing reservoir predictions of chaotic time series by incorporating delayed values of input and reservoir variables","source":"openalex","abstract":"Time series generated by chaotic dynamical systems can be effectively predicted using readouts from driven reservoir dynamics. In practical scenarios, however, only time series measurements with partial knowledge of the chaotic system's state are usually available. To address this aspect, we evaluate and compare the performance of reservoir computing in predicting time series under both conditions of complete and partial knowledge of the state. Our results show that memory improves the prediction accuracy only when the system state is partially known. For cases with partial state knowledge, we extend the mean prediction horizon by including delayed values of both the input and reservoir variables. To ensure the robustness of this result, we test it in systems with varying degrees of complexity. Finally, we show that the inclusion of delayed values can also facilitate the optimization of hyperparameters for predictions based on full knowledge of the system state.","url":"https://doi.org/10.1063/5.0258250","authors":["Luk Fleddermann","Sebastian Herzog","Ulrich Parlitz"],"tags":["Reservoir computing","Chaotic","Series (stratigraphy)","Computer science","Robustness (evolution)"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-05-01","doi":"https://doi.org/10.1063/5.0258250","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4327603999","name":"Review of visual reconstruction methods of retina-like vision sensors","source":"openalex","abstract":"Retina-like vision sensors have been a new development in recent years. They output an asynchronous spike or event signal by continuously sampling the scene light intensity information. This research summarizes the sampling principle of existing retina-like vision sensors (including spatial contrast, temporal contrast, and temporal integration vision sensors) and retina-like cameras with additional circuits. Compared to traditional cameras, retina-like vision sensors have high dynamic ranges and high temporal domain resolution; however, as the spike signal is stored as 1 and 0 (or $-1$), compatibility with traditional vision is difficult to obtain. If neuromorphic vision sampling can be considered as the encoding process of the scene light intensity, then the visual information reconstruction is the decoding process. Thus, visual information reconstruction can bridge the gap between neuromorphic vision and traditional frame-based vision. Recently, many image reconstruction algorithms have used asynchronous spikes or event signals. By processing such spikes or event signals, an image of high temporal domain resolution can be reconstructed. In this research, according to the sampling characteristics of different retina-like vision sensors, we summarize the existing image reconstruction methods based on event and spike cameras. Moreover, the opportunities and challenges of retina-like visual sampling and visual information reconstruction, as well as their possible development directions, are discussed and prospected.","url":"https://doi.org/10.1360/ssi-2021-0397","authors":["林 朱","永鸿 田"],"tags":["Retina","Computer vision","Optometry","Artificial intelligence","Computer science"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2023-03-01","doi":"https://doi.org/10.1360/ssi-2021-0397","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4392597219","name":"Native point defects in 2D transition metal dichalcogenides: A perspective bridging intrinsic physical properties and device applications","source":"openalex","abstract":"Two-dimensional (2D) transition metal dichalcogenides (TMDs) hold immense promise as ultrathin-body semiconductors for cutting-edge electronics and optoelectronics. In particular, their sustained charge mobility even at atomic-level thickness as well as their absence of surface dangling bonds, versatile band structures, and silicon-compatibility integration make them a prime candidate for device applications in both academic and industrial domains. Despite such high expectations, group-VI TMDs reportedly exhibit a range of enigmatic properties, such as substantial contact resistance, Fermi level pinning, and limited unipolar charge transport, which are all rooted in their inherent defects. In other words, intrinsic physical properties resulting from their native defects extend their influence beyond the material level. Bridging point-defect-induced material properties and their behavior at the device level, this Perspective sheds light on the significance of crystalline defects beyond a rather simple defect–property relationship. As a distinctive approach, we briefly review the well-established defect model of conventional III–V semiconductors and further apply it to the emergent defect behaviors of 2D TMDs such as their defect-induced gap states. Within the main discussion, we survey a range of behaviors caused by the most prevalent intrinsic defect, namely, vacancies, within 2D TMDs, and their implications for electronic and optoelectronic properties when employed at the device level. This review presents an in-depth summary of complexities in material properties as well as device characteristics arising from intrinsic point defects and provides a solid foundation for the cross-links among native defects and material/device properties.","url":"https://doi.org/10.1063/5.0185604","authors":["Kyungmin Ko","Mingyu Jang","Jaeeun Kwon","Joonki Suh"],"tags":["Bridging (networking)","Transition metal","Materials science","Nanotechnology","Perspective (graphical)"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-03-08","doi":"https://doi.org/10.1063/5.0185604","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4410620374","name":"Advances in AI-powered energy management systems for renewable-integrated smart grids","source":"openalex","abstract":"The accelerating global shift toward renewable energy integration presents both a technical imperative and a systemic challenge to traditional power grid architectures. Variability, decentralization, and real-time balancing requirements have exposed the limitations of conventional control and forecasting strategies. This review critically examines how artificial intelligence (AI) is redefining energy management systems to meet the operational and strategic needs of renewable-integrated smart grids. It explores the state-of-the-art in AI-based load and generation forecasting, real-time grid state estimation, anomaly detection, and predictive maintenance, highlighting how machine learning and deep learning techniques enhance grid observability and fault resilience. Particular attention is given to AI-driven optimization of energy storage dispatch, multi-agent coordination in microgrids, and the deployment of edge intelligence for decentralized control. Furthermore, the review evaluates current barriers—ranging from data sparsity and model interpretability to lack of standardization—and proposes targeted research directions, including explainable AI, quantum-enhanced computing, and AI-powered coordination of distributed storage and vehicle-to-grid (V2G) networks. The convergence of AI, digital infrastructure, and policy innovation emerges as critical to unlocking the full potential of next-generation grids. This article provides researchers, engineers, and policymakers with a rigorous synthesis of current advancements and a forward-looking agenda for achieving intelligent, resilient, and decarbonized energy systems.","url":"https://doi.org/10.30574/wjaets.2025.15.2.0685","authors":["Ifeanyi Kingsley Egbuna","Faisal Benna Salihu","Chinemeremma Collins Okara","Damilola Emmanuel Olayiwola","E. Smart","Olabode Anifowose","Paul Oluchukwu Mbamalu"],"tags":["Renewable energy","Smart grid","Systems engineering","Energy management","Computer science"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-05-23","doi":"https://doi.org/10.30574/wjaets.2025.15.2.0685","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4412929968","name":"Large-scale photonic processors and their applications","source":"openalex","abstract":"Digital electronics have been essential in all technological breakthroughs over the past decades, from the advent of the internet to the miniaturization of portable devices with ever-increasing capabilities. While they continue to drive technological innovation, certain applications demanding extraordinary bandwidth and performance reveal the need for complementary emerging technologies. Photonics is particularly well-suited for this purpose, leveraging light to process large volumes of information with minimal latency. The scalability of photonic integrated circuits (PICs) is advancing rapidly, with increasing numbers of actuators improving performance and extending applicability across different domains. Analyzing two decades of development, this study extracts the scalability laws guiding photonics evolution, doubling every two years and predicting a transition from hundreds to 10 5 actuators in PICs within six years. We also tackle key challenges and emphasize the crucial synergy between electronics, software, and photonics, which will determine the market penetration and industry impact of large-scale photonic processors.","url":"https://doi.org/10.1038/s44310-025-00075-4","authors":["Daniel Pérez","Luis Torrijos‐Morán"],"tags":["Scale (ratio)","Photonics","Computer science","Parallel computing","Optoelectronics"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-08-04","doi":"https://doi.org/10.1038/s44310-025-00075-4","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4414701265","name":"MCU Intelligent Upgrades: An Overview of AI-Enabled Low-Power Technologies","source":"openalex","abstract":"Microcontroller units (MCUs) serve as the core components of embedded systems. In the era of smart IoT, embedded devices are increasingly deployed on mobile platforms, leading to a growing demand for low-power consumption. As a result, low-power technology for MCUs has become increasingly critical. This paper systematically reviews the development history and current technical challenges of MCU low-power technology. It then focuses on analyzing system-level low-power optimization pathways for integrating MCUs with artificial intelligence (AI) technology, including lightweight AI algorithm design, model pruning, AI acceleration hardware (NPU, GPU), and heterogeneous computing architectures. It further elaborates on how AI technology empowers MCUs to achieve comprehensive low power consumption from four dimensions: task scheduling, power management, inference engine optimization, and communication and data processing. Through practical application cases in multiple fields such as smart home, healthcare, industrial automation, and smart agriculture, it verifies the significant advantages of MCUs combined with AI in performance improvement and power consumption optimization. Finally, this paper focuses on the key challenges that still need to be addressed in the intelligent upgrade of future MCU low power consumption and proposes in-depth research directions in areas such as the balance between lightweight model accuracy and robustness, the consistency and stability of edge-side collaborative computing, and the reliability and power consumption control of the sensor-storage-computing integrated architecture, providing clear guidance and prospects for future research.","url":"https://doi.org/10.3390/jlpea15040060","authors":["Tong Zhang","Ben Huang","Xiewen Liu","Jiaqi Fan","Junbo Li","Yue Zhao","Yanfang Wang"],"tags":["Microcontroller","Embedded system","Key (lock)","Upgrade","Computer science"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2025-10-01","doi":"https://doi.org/10.3390/jlpea15040060","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W7126270210","name":"Bioinspired Crossmodal Tactile Sensory Nerve for High‐Accurate Object Recognition","source":"openalex","abstract":"Crossmodal perception enabled by the human somatosensory system can be followed to effectively perceive and analyze multiple sensory signals. Here, we construct an artificial crossmodal sensory neuron system by integrating pressure–temperature bimodal sensors with a Hf 0.5 Zr 0.5 O 2 ‐based complementary memristor, which emulates the tactile perception, neural coding, and synaptic processing functions of humans. With the developed bimodal sensor, the pressure and temperature information can be collected and further converted to electrical signals with excellent sensitivities of 26 407 kPa −1 and −3.34%°C −1 , respectively. The complementary memristor can enable information storage and simulate biological synaptic functions, achieving bioinspired neuromorphic processing of sensory signals. Combined with machine learning, this artificial crossmodal sensory neuron system presents an improved accuracy of 96.67% in recognizing temperatures and shapes of distinct objects. This work demonstrates potential applications of the integrated system in advanced neuromorphic hardware for wearable human‐machine interfaces and biomimetic robotics.","url":"https://doi.org/10.1002/eem2.70279","authors":["Delu Chen","Yuetong Han","Xiaodong Wang","Wanli Cheng","Jianjie He","Xing Li","Yoshifumi Oshima","Chongxin Shan","Shaobo Cheng"],"tags":["Crossmodal","Neuromorphic engineering","Sensory system","Somatosensory system","Computer science"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2026-01-29","doi":"https://doi.org/10.1002/eem2.70279","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"},{"id":"oa:W4402605216","name":"Increased Static Charge‐Induced Threshold Voltage Shifts and Memristor Activity in Pentacene OFETs Comprising Polystyrene‐Based Gate Dielectrics Containing Electroactive Small Molecule Crystallites","source":"openalex","abstract":"Abstract Top‐contact bottom‐gate pentacene OFETs are fabricated with single layer dielectrics comprised of either polystyrene (PS), poly(4‐methylstyrene) (P4MS), or poly(4‐tert‐butylstyrene) (P4TBS). The polystyrenes are blended with varying concentrations of two different small molecules, dibenzotetrathiafulvalene (DBTTF) and 2,8‐difluoro‐5,11‐bis(triethylsilylethynyl)anthradithiophene (diF‐TES‐ADT), to form small, separated crystallites contained throughout the polymer dielectric layer. The OFET characteristics of these devices are investigated and their threshold voltage shifts are measured after −70 V static charging for 5 min. Two‐terminal measurements are conducted using multiple different gate biases in the range of −50 to +50 V to investigate memristor behavior in the devices. OFETs containing DBTTF exhibited ΔVth increases as large as 330% relative to control OFETs containing no DBTTF, while OFETs containing at least 7.5 wt.% DBTTF exhibited memristor activity, with currents ranging from 20 nA to 44 µA depending on the applied bias. This work demonstrates that including small, separated crystallites in polymer dielectrics enhances their charge storage ability and can be promising for creating nonbinary memory devices for data processing. Additionally, the observed memristor activity indicates the OFETs in this work can be used in development of neuromorphic systems that aim to mimic the synaptic behavior of the human nervous system.","url":"https://doi.org/10.1002/adfm.202410763","authors":["Christopher R. Bond","Daniel H. Reich","Howard E. Katz"],"tags":["Materials science","Pentacene","Organic field-effect transistor","Polystyrene","Dielectric"],"confidence":0.72,"sites":["neuromorphic"],"publishedDate":"2024-09-18","doi":"https://doi.org/10.1002/adfm.202410763","addedAt":"2026-09-01T06:01:44.307Z","updatedAt":"2026-09-01T06:01:44.307Z"}]