AI 安全与对齐 · 全部实体（第 15 / 100 页）

本页收录第 1401–1500 条，共 10000 条 · 返回 AI 安全与对齐 首页

• Neural Architecture Search for Spiking Neural Networks
  Spiking Neural Networks (SNNs) have gained huge attention as a potential energy-efficient alternative to conventional Artificial Neural Networks (ANNs) due to their inherent high-sparsity activation. However, most prior SNN methods use ANN-like architectures (…
  arxiv Youngeun Kim, Yuhang Li, Hyoungseob Park, Yeshwanth Venkatesha 等 2022-01-23T16:34:27Z 置信度 0.78 cs.NEcs.AIcs.LGeess.SP
• A constraints-based approach to fully interpretable neural networks for detecting learner behaviors
  The increasing use of complex machine learning models in education has led to concerns about their interpretability, which in turn has spurred interest in developing explainability techniques that are both faithful to the model's inner workings and intelligibl…
  arxiv Juan D. Pinto, Luc Paquette 2025-04-10T16:58:11Z 置信度 0.78 cs.LGcs.AI
• Cartesian Genetic Programming Approach for Designing Convolutional Neural Networks
  The present study covers an approach to neural architecture search (NAS) using Cartesian genetic programming (CGP) for the design and optimization of Convolutional Neural Networks (CNNs). In designing artificial neural networks, one crucial aspect of the innov…
  arxiv Maciej Krzywda, Szymon Łukasik, Amir Gandomi H 2024-09-30T18:10:06Z 置信度 0.78 cs.NEcs.AIcs.LG
• A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation
  Recent instruction fine-tuned models can solve multiple NLP tasks when prompted to do so, with machine translation (MT) being a prominent use case. However, current research often focuses on standard performance benchmarks, leaving compelling fairness and ethi…
  arxiv Giuseppe Attanasio, Flor Miriam Plaza-del-Arco, Debora Nozza, Anne Lauscher 2023-10-18T17:36:55Z 置信度 0.78 cs.CLcs.LG
• Encoding Optimization for Low-Complexity Spiking Neural Network Equalizers in IM/DD Systems
  Neural encoding parameters for spiking neural networks (SNNs) are typically set heuristically. We propose a reinforcement learning-based algorithm to optimize them. Applied to an SNN-based equalizer and demapper in an IM/DD system, the method improves performa…
  arxiv Eike-Manuel Edelmann, Alexander von Bank, Laurent Schmalen 2025-08-19T12:32:13Z 置信度 0.78 cs.NEeess.SP
• Missing Data Prediction and Classification: The Use of Auto-Associative Neural Networks and Optimization Algorithms
  This paper presents methods which are aimed at finding approximations to missing data in a dataset by using optimization algorithms to optimize the network parameters after which prediction and classification tasks can be performed. The optimization methods th…
  arxiv Collins Leke, Bhekisipho Twala, T. Marwala 2014-03-21T15:11:52Z 置信度 0.78 cs.NEcs.LG
• Generating Segment Durations in a Text-To-Speech System: A Hybrid Rule-Based/Neural Network Approach
  A combination of a neural network with rule firing information from a rule-based system is used to generate segment durations for a text-to-speech system. The system shows a slight improvement in performance over a neural network system without the rule firing…
  arxiv Gerald Corrigan, Noel Massey, Orhan Karaali 1998-11-24T22:51:20Z 置信度 0.78 cs.NEcs.HC
• Game-Theoretic Gradient Control for Robust Neural Network Training
  Feed-forward neural networks (FFNNs) are vulnerable to input noise, reducing prediction performance. Existing regularization methods like dropout often alter network architecture or overlook neuron interactions. This study aims to enhance FFNN noise robustness…
  arxiv Maria Zaitseva, Ivan Tomilov, Natalia Gusarova 2025-07-25T10:26:25Z 置信度 0.78 cs.NEcs.LG
• Computer modeling of feelings and emotions: a quantitative neural network model of the feeling-of-knowing
  The first quantitative neural network model of feelings and emotions is proposed on the base of available data on their neuroscience and evolutionary biology nature, and on a neural network human memory model which admits distinct description of conscious and …
  arxiv Petro M. Gopych 2002-06-03T22:31:45Z 置信度 0.78 cs.AIcs.NEq-bio.NCq-bio.QM
• A Spiking Neural Network Learning Markov Chain
  In this paper, the question how spiking neural network (SNN) learns and fixes in its internal structures a model of external world dynamics is explored. This question is important for implementation of the model-based reinforcement learning (RL), the realistic…
  arxiv Mikhail Kiselev 2022-09-20T09:31:01Z 置信度 0.78 cs.NE
• Motif-topology improved Spiking Neural Network for the Cocktail Party Effect and McGurk Effect
  Network architectures and learning principles are playing key in forming complex functions in artificial neural networks (ANNs) and spiking neural networks (SNNs). SNNs are considered the new-generation artificial networks by incorporating more biological feat…
  arxiv Shuncheng Jia, Tielin Zhang, Ruichen Zuo, Bo Xu 2022-11-12T08:23:55Z 置信度 0.78 cs.NEcs.LGeess.SP
• Interpretable Neural PDE Solvers using Symbolic Frameworks
  Partial differential equations (PDEs) are ubiquitous in the world around us, modelling phenomena from heat and sound to quantum systems. Recent advances in deep learning have resulted in the development of powerful neural solvers; however, while these methods …
  arxiv Yolanne Yi Ran Lee 2023-10-31T13:56:25Z 置信度 0.78 cs.AI
• Multi-Objective Optimization for Size and Resilience of Spiking Neural Networks
  Inspired by the connectivity mechanisms in the brain, neuromorphic computing architectures model Spiking Neural Networks (SNNs) in silicon. As such, neuromorphic architectures are designed and developed with the goal of having small, low power chips that can p…
  arxiv Mihaela Dimovska, Travis Johnston, Catherine D. Schuman, J. Parker Mitchell 等 2020-02-04T16:58:25Z 置信度 0.78 cs.NEcs.ETcs.LG
• Recurrent Neural Network Grammars
  We introduce recurrent neural network grammars, probabilistic models of sentences with explicit phrase structure. We explain efficient inference procedures that allow application to both parsing and language modeling. Experiments show that they provide better …
  arxiv Chris Dyer, Adhiguna Kuncoro, Miguel Ballesteros, Noah A. Smith 2016-02-25T02:42:58Z 置信度 0.78 cs.CLcs.NE
• Quantum Neural Machine Learning - Backpropagation and Dynamics
  The current work addresses quantum machine learning in the context of Quantum Artificial Neural Networks such that the networks' processing is divided in two stages: the learning stage, where the network converges to a specific quantum circuit, and the backpro…
  arxiv Carlos Pedro Gonçalves 2016-09-22T12:12:05Z 置信度 0.78 cs.NEcond-mat.dis-nnnlin.AOquant-ph
• Photonic Neural Networks: A Compact Review
  It has long been known that photonic science and especially photonic communications can raise the speed of technologies and producing manufacturing. More recently, photonic science has also been interested in its capabilities to implement low-precision linear …
  arxiv Mohammad Ahmadi, Hamidreza Bolhasani 2023-02-16T16:10:02Z 置信度 0.78 cs.NE
• Comparison of Neural Network based Soft Computing Techniques for Electromagnetic Modeling of a Microstrip Patch Antenna
  This paper presents the comparison of various neural networks and algorithms based on accuracy, quickness, and consistency for antenna modelling. Using MATLAB Nntool, 22 different combinations of networks and training algorithms are used to predict the dimensi…
  arxiv Yuvraj Singh Malhi, Navneet Gupta 2021-09-21T10:08:22Z 置信度 0.78 cs.NEcs.AI
• Leveraging Deep Neural Network Activation Entropy to cope with Unseen Data in Speech Recognition
  Unseen data conditions can inflict serious performance degradation on systems relying on supervised machine learning algorithms. Because data can often be unseen, and because traditional machine learning algorithms are trained in a supervised manner, unsupervi…
  arxiv Vikramjit Mitra, Horacio Franco 2017-08-31T01:00:19Z 置信度 0.78 cs.LGcs.CLstat.ML
• Deep Neural Networks - A Brief History
  Introduction to deep neural networks and their history.
  arxiv Krzysztof J. Cios 2017-01-19T18:43:56Z 置信度 0.78 cs.NEcs.CVcs.LG
• Local and global gestalt laws: A neurally based spectral approach
  A mathematical model of figure-ground articulation is presented, taking into account both local and global gestalt laws. The model is compatible with the functional architecture of the primary visual cortex (V1). Particularly the local gestalt law of good cont…
  arxiv Marta Favali, Giovanna Citti, Alessandro Sarti 2015-12-21T10:27:58Z 置信度 0.78 cs.CV
• Event-based Neural Spike Detection Using Spiking Neural Networks for Neuromorphic iBMI Systems
  Implantable brain-machine interfaces (iBMIs) are evolving to record from thousands of neurons wirelessly but face challenges in data bandwidth, power consumption, and implant size. We propose a novel Spiking Neural Network Spike Detector (SNN-SPD) that process…
  arxiv Chanwook Hwang, Biyan Zhou, Ye Ke, Vivek Mohan 等 2025-05-10T07:07:00Z 置信度 0.78 eess.SPcs.NE
• The Physics of Living Neural Networks
  Improvements in technique in conjunction with an evolution of the theoretical and conceptual approach to neuronal networks provide a new perspective on living neurons in culture. Organization and connectivity are being measured quantitatively along with other …
  arxiv Jean-Pierre Eckmann, Ofer Feinerman, Leor Gruendlinger, Elisha Moses 等 2010-07-30T14:48:05Z 置信度 0.78 cond-mat.dis-nnphysics.bio-phq-bio.NC
• GACNN: Training Deep Convolutional Neural Networks with Genetic Algorithm
  Convolutional Neural Networks (CNNs) have gained a significant attraction in the recent years due to their increasing real-world applications. Their performance is highly dependent to the network structure and the selected optimization method for tuning the ne…
  arxiv Parsa Esfahanian, Mohammad Akhavan 2019-09-29T19:55:10Z 置信度 0.78 cs.NE
• Physics-Informed Tensor Basis Neural Network for Turbulence Closure Modeling
  Despite the increasing availability of high-performance computational resources, Reynolds-Averaged Navier-Stokes (RANS) simulations remain the workhorse for the analysis of turbulent flows in real-world applications. Linear eddy viscosity models (LEVM), the mo…
  arxiv Leon Riccius, Atul Agrawal, Phaedon-Stelios Koutsourelakis 2023-11-24T16:07:35Z 置信度 0.78 physics.flu-dynphysics.comp-ph
• Investigating Network Parameters in Neural-Network Quantum States
  Recently, quantum-state representation using artificial neural networks has started to be recognized as a powerful tool. However, due to the black-box nature of machine learning, it is difficult to analyze what machine learns or why it is powerful. Here, by ap…
  arxiv Yusuke Nomura 2022-02-03T17:13:21Z 置信度 0.78 quant-phcond-mat.dis-nncond-mat.str-elphysics.comp-phphysics.data-an
• Neuroevolution of Neural Network Architectures Using CoDeepNEAT and Keras
  Machine learning is a huge field of study in computer science and statistics dedicated to the execution of computational tasks through algorithms that do not require explicit instructions but instead rely on learning patterns from data samples to automate infe…
  arxiv Jonas da Silveira Bohrer, Bruno Iochins Grisci, Marcio Dorn 2020-02-11T19:03:34Z 置信度 0.78 cs.NEcs.CVcs.LG
• Application of artificial neural networks and genetic algorithms for crude fractional distillation process modeling
  This work presents the application of the artificial neural networks, trained and structurally optimized by genetic algorithms, for modeling of crude distillation process at PKN ORLEN S.A. refinery. Models for the main fractionator distillation column products…
  arxiv Lukasz Pater 2016-04-30T11:46:58Z 置信度 0.78 cs.NE
• Truly Sparse Neural Networks at Scale
  Recently, sparse training methods have started to be established as a de facto approach for training and inference efficiency in artificial neural networks. Yet, this efficiency is just in theory. In practice, everyone uses a binary mask to simulate sparsity s…
  arxiv Selima Curci, Decebal Constantin Mocanu, Mykola Pechenizkiyi 2021-02-02T20:06:47Z 置信度 0.78 cs.LGcs.NE
• ReLU Neural Networks of Polynomial Size for Exact Maximum Flow Computation
  This paper studies the expressive power of artificial neural networks with rectified linear units. In order to study them as a model of real-valued computation, we introduce the concept of Max-Affine Arithmetic Programs and show equivalence between them and ne…
  arxiv Christoph Hertrich, Leon Sering 2021-02-12T17:23:34Z 置信度 0.78 cs.LGcs.CCcs.DScs.NEstat.ML
• Investigating Emotion-Color Association in Deep Neural Networks
  It has been found that representations learned by Deep Neural Networks (DNNs) correlate very well to neural responses measured in primates' brains and psychological representations exhibited by human similarity judgment. On another hand, past studies have show…
  arxiv Shivi Gupta, Shashi Kant Gupta 2020-11-22T16:48:02Z 置信度 0.78 cs.NEcs.AIcs.CV
• On the Importance of Consistency in Training Deep Neural Networks
  We explain that the difficulties of training deep neural networks come from a syndrome of three consistency issues. This paper describes our efforts in their analysis and treatment. The first issue is the training speed inconsistency in different layers. We pr…
  arxiv Chengxi Ye, Yezhou Yang, Cornelia Fermuller, Yiannis Aloimonos 2017-08-02T08:05:09Z 置信度 0.78 cs.LGcs.AIcs.CVcs.NE
• CRISP-NAM: Competing Risks Interpretable Survival Prediction with Neural Additive Models
  Competing risks are crucial considerations in survival modelling, particularly in healthcare domains where patients may experience multiple distinct event types. We propose CRISP-NAM (Competing Risks Interpretable Survival Prediction with Neural Additive Model…
  arxiv Dhanesh Ramachandram, Ananya Raval 2025-05-27T15:52:15Z 置信度 0.78 cs.LG
• Unreduced Dynamic Complexity: Towards the Unified Science of Intelligent Communication Networks and Software
  Operation of autonomic communication networks with complicated user-oriented functions should be described as unreduced many-body interaction process. The latter gives rise to complex-dynamic behaviour including fractally structured hierarchy of chaotically ch…
  arxiv Andrei P. Kirilyuk 2006-03-16T11:23:23Z 置信度 0.78 physics.gen-ph
• A Hybrid Training Algorithm for Continuum Deep Learning Neuro-Skin Neural Network
  In this brief paper, a learning algorithm is developed for Deep Learning NeuroSkin Neural Network to improve their learning properties. Neuroskin is a new type of neural network presented recently by the authors. It is comprised of a cellular membrane which ha…
  arxiv Mehrdad Shafiei Dizaji 2023-02-03T15:54:06Z 置信度 0.78 cs.NE
• Parallel Hyperparameter Optimization Of Spiking Neural Network
  Spiking Neural Networks (SNN). SNNs are based on a more biologically inspired approach than usual artificial neural networks. Such models are characterized by complex dynamics between neurons and spikes. These are very sensitive to the hyperparameters, making …
  arxiv Thomas Firmin, Pierre Boulet, El-Ghazali Talbi 2024-03-01T11:11:59Z 置信度 0.78 cs.NEcs.AI
• BitSplit-Net: Multi-bit Deep Neural Network with Bitwise Activation Function
  Significant computational cost and memory requirements for deep neural networks (DNNs) make it difficult to utilize DNNs in resource-constrained environments. Binary neural network (BNN), which uses binary weights and binary activations, has been gaining inter…
  arxiv Hyungjun Kim, Yulhwa Kim, Sungju Ryu, Jae-Joon Kim 2019-03-23T11:52:23Z 置信度 0.78 cs.NEcs.CVcs.LG
• Extensional Properties of Recurrent Neural Networks
  A property of a recurrent neural network (RNN) is called \emph{extensional} if, loosely speaking, it is a property of the function computed by the RNN rather than a property of the RNN algorithm. Many properties of interest in RNNs are extensional, for example…
  arxiv Evgeny Dantsin, Alexander Wolpert 2024-10-30T06:29:02Z 置信度 0.78 cs.NEcs.LG
• Predicting the generalization gap in neural networks using topological data analysis
  Understanding how neural networks generalize on unseen data is crucial for designing more robust and reliable models. In this paper, we study the generalization gap of neural networks using methods from topological data analysis. For this purpose, we compute h…
  arxiv Rubén Ballester, Xavier Arnal Clemente, Carles Casacuberta, Meysam Madadi 等 2022-03-23T11:15:36Z 置信度 0.78 cs.LGmath.AT
• Individualized Risk Assessment of Preoperative Opioid Use by Interpretable Neural Network Regression
  Preoperative opioid use has been reported to be associated with higher preoperative opioid demand, worse postoperative outcomes, and increased postoperative healthcare utilization and expenditures. Understanding the risk of preoperative opioid use helps establ…
  arxiv Yuming Sun, Jian Kang, Chad Brummett, Yi Li 2022-05-07T02:35:04Z 置信度 0.78 cs.LGstat.AP
• Neural Network Approximations of Compositional Functions With Applications to Dynamical Systems
  As demonstrated in many areas of real-life applications, neural networks have the capability of dealing with high dimensional data. In the fields of optimal control and dynamical systems, the same capability was studied and verified in many published results i…
  arxiv Wei Kang, Qi Gong 2020-12-03T04:40:25Z 置信度 0.78 cs.LGcs.NEmath.NA
• From Nodes to Networks: Evolving Recurrent Neural Networks
  Gated recurrent networks such as those composed of Long Short-Term Memory (LSTM) nodes have recently been used to improve state of the art in many sequential processing tasks such as speech recognition and machine translation. However, the basic structure of t…
  arxiv Aditya Rawal, Risto Miikkulainen 2018-03-12T18:24:07Z 置信度 0.78 cs.NEcs.LG
• Focal Modulation Networks for Interpretable Sound Classification
  The increasing success of deep neural networks has raised concerns about their inherent black-box nature, posing challenges related to interpretability and trust. While there has been extensive exploration of interpretation techniques in vision and language, i…
  arxiv Luca Della Libera, Cem Subakan, Mirco Ravanelli 2024-02-05T06:20:52Z 置信度 0.78 cs.SDcs.LGeess.AS
• Sparsity-depth Tradeoff in Infinitely Wide Deep Neural Networks
  We investigate how sparse neural activity affects the generalization performance of a deep Bayesian neural network at the large width limit. To this end, we derive a neural network Gaussian Process (NNGP) kernel with rectified linear unit (ReLU) activation and…
  arxiv Chanwoo Chun, Daniel D. Lee 2023-05-17T20:09:35Z 置信度 0.78 cs.LGcond-mat.dis-nnq-bio.NC
• Evolutionary algorithms as an alternative to backpropagation for supervised training of Biophysical Neural Networks and Neural ODEs
  Training networks consisting of biophysically accurate neuron models could allow for new insights into how brain circuits can organize and solve tasks. We begin by analyzing the extent to which the central algorithm for neural network learning -- stochastic gr…
  arxiv James Hazelden, Yuhan Helena Liu, Eli Shlizerman, Eric Shea-Brown 2023-11-17T20:59:57Z 置信度 0.78 q-bio.NCcs.NE
• Understanding the Initial Condensation of Convolutional Neural Networks
  Previous research has shown that fully-connected networks with small initialization and gradient-based training methods exhibit a phenomenon known as condensation during training. This phenomenon refers to the input weights of hidden neurons condensing into is…
  arxiv Zhangchen Zhou, Hanxu Zhou, Yuqing Li, Zhi-Qin John Xu 2023-05-17T05:00:47Z 置信度 0.78 cs.LGcs.NE
• Neuromorphic Acceleration for Approximate Bayesian Inference on Neural Networks via Permanent Dropout
  As neural networks have begun performing increasingly critical tasks for society, ranging from driving cars to identifying candidates for drug development, the value of their ability to perform uncertainty quantification (UQ) in their predictions has risen com…
  arxiv Nathan Wycoff, Prasanna Balaprakash, Fangfang Xia 2019-04-29T18:43:07Z 置信度 0.78 stat.MLcs.LGcs.NE
• Audio Spectrogram Representations for Processing with Convolutional Neural Networks
  One of the decisions that arise when designing a neural network for any application is how the data should be represented in order to be presented to, and possibly generated by, a neural network. For audio, the choice is less obvious than it seems to be for vi…
  arxiv L. Wyse 2017-06-29T03:04:06Z 置信度 0.78 cs.SDcs.LGcs.MMcs.NE
• Memory and Information Processing in Recurrent Neural Networks
  Recurrent neural networks (RNN) are simple dynamical systems whose computational power has been attributed to their short-term memory. Short-term memory of RNNs has been previously studied analytically only for the case of orthogonal networks, and only under a…
  arxiv Alireza Goudarzi, Sarah Marzen, Peter Banda, Guy Feldman 等 2016-04-23T17:36:12Z 置信度 0.78 cs.NE
• Breaking the Conventional Forward-Backward Tie in Neural Networks: Activation Functions
  Gradient-based neural network training traditionally enforces symmetry between forward and backward propagation, requiring activation functions to be differentiable (or sub-differentiable) and strictly monotonic in certain regions to prevent flat gradient area…
  arxiv Luigi Troiano, Francesco Gissi, Vincenzo Benedetto, Genny Tortora 2025-09-08T21:30:00Z 置信度 0.78 cs.NEcs.AIcs.LG
• Associative Memory Model with Neural Networks: Memorizing multiple images with one neuron
  This paper presents a neural network model (associative memory model) for memory and recall of images. In this model, only a single neuron can memorize multi-images and when that neuron is activated, it is possible to recall all the memorized images at the sam…
  arxiv Hiroshi Inazawa 2025-10-08T00:44:46Z 置信度 0.78 cs.NE
• Graph Neural Networks for Image Classification and Reinforcement Learning using Graph representations
  In this paper, we will evaluate the performance of graph neural networks in two distinct domains: computer vision and reinforcement learning. In the computer vision section, we seek to learn whether a novel non-redundant representation for images as graphs can…
  arxiv Naman Goyal, David Steiner 2022-03-07T15:16:31Z 置信度 0.78 cs.LGcs.CV
• Activations Through Extensions: A Framework To Boost Performance Of Neural Networks
  Activation functions are non-linearities in neural networks that allow them to learn complex mapping between inputs and outputs. Typical choices for activation functions are ReLU, Tanh, Sigmoid etc., where the choice generally depends on the application domain…
  arxiv Chandramouli Kamanchi, Sumanta Mukherjee, Kameshwaran Sampath, Pankaj Dayama 等 2024-08-07T07:36:49Z 置信度 0.78 cs.LGcs.AIcs.NEmath.NA
• glitterin: Towards Replacing the Role of Lorenz-Mie Theory in Astronomy Using Neural Networks Trained on Light Scattering of Irregularly Shaped Grains
  Light scattering by dust particles is often modeled assuming the dust is spherical for numerical simplicity and speed. However, real dust particles have highly irregular morphologies that significantly affect their scattering properties. We have developed glit…
  arxiv Zhe-Yu Daniel Lin, Alycia J. Weinberger, Evgenij Zubko, Jessica A. Arnold 等 2025-11-12T19:15:00Z 置信度 0.78 astro-ph.EP
• Survey on Deep Neural Networks in Speech and Vision Systems
  This survey presents a review of state-of-the-art deep neural network architectures, algorithms, and systems in vision and speech applications. Recent advances in deep artificial neural network algorithms and architectures have spurred rapid innovation and dev…
  arxiv Mahbubul Alam, Manar D. Samad, Lasitha Vidyaratne, Alexander Glandon 等 2019-08-16T16:40:49Z 置信度 0.78 cs.CVcs.LGcs.NEcs.SDeess.AS
• Improving GPS/INS Integration through Neural Networks
  The Global Positioning Systems (GPS) and Inertial Navigation System (INS) technology have attracted a considerable importance recently because of its large number of solutions serving both military as well as civilian applications. This paper aims to develop a…
  arxiv M. Nguyen-H, C. Zhou 2010-05-27T16:46:13Z 置信度 0.78 cs.NE
• Tustin neural networks: a class of recurrent nets for adaptive MPC of mechanical systems
  The use of recurrent neural networks to represent the dynamics of unstable systems is difficult due to the need to properly initialize their internal states, which in most of the cases do not have any physical meaning, consequent to the non-smoothness of the o…
  arxiv Simone Pozzoli, Marco Gallieri, Riccardo Scattolini 2019-11-04T16:21:27Z 置信度 0.78 cs.NEeess.SY
• Recognition of convolutional neural network based on CUDA Technology
  For the problem whether Graphic Processing Unit(GPU),the stream processor with high performance of floating-point computing is applicable to neural networks, this paper proposes the parallel recognition algorithm of Convolutional Neural Networks(CNNs).It adopt…
  arxiv Yi-bin Huang, Kang Li, Ge Wang, Min Cao 等 2015-05-30T05:38:00Z 置信度 0.78 cs.DCcs.NE
• Dreaming neural networks: rigorous results
  Recently a daily routine for associative neural networks has been proposed: the network Hebbian-learns during the awake state (thus behaving as a standard Hopfield model), then, during its sleep state, optimizing information storage, it consolidates pure patte…
  arxiv Elena Agliari, Francesco Alemanno, Adriano Barra, Alberto Fachechi 2018-12-21T12:29:48Z 置信度 0.78 cond-mat.dis-nncs.AIstat.ML
• Consensus Function from an $L_p^q-$norm Regularization Term for its Use as Adaptive Activation Functions in Neural Networks
  The design of a neural network is usually carried out by defining the number of layers, the number of neurons per layer, their connections or synapses, and the activation function that they will execute. The training process tries to optimize the weights assig…
  arxiv Juan Heredia-Juesas, José Á. Martínez-Lorenzo 2022-06-30T04:48:14Z 置信度 0.78 cs.NE
• Improved neural network for checking the stability of multidimensional systems
  In this paper, the author's previous work is extended and a new neural network is utilized to solve the stability problem of multidimensional systems. In the original authors work the problem is transformed into an optimization problem. Using the DeCarlo-Strin…
  crossref Nikos E. Mastorakis, Valeri M. Mladenov, M. N. S. Swamy 2010-12-09T10:34:50Z 置信度 0.70
• Figure 10: (A) Neural network training phase (B) Validation epochs.
  crossref 2026-01-27T08:54:27Z 置信度 0.70
• Figure 2: Framework of the proposed dual branch neural network.
  crossref 2022-11-14T03:16:13Z 置信度 0.70
• Front Matter
  crossref 2011-10-06T10:14:16Z 置信度 0.70
• Low-rank network models of neural computations
  Réseaux de neurones de bas rang et calculs neuronaux À tout instant, des myriades de neurones coopèrent au sein d’un système nerveux, produisant des motifs d’activité collectifs qui forment un substrat biologique pour la perception, la cognition, et le comport…
  crossref Adrian Valente 2026-04-07T08:08:14Z 置信度 0.70
• Learned D-AMP: Principled Neural Network based Compressive Image\n Recovery
  Compressive image recovery is a challenging problem that requires fast and\naccurate algorithms. Recently, neural networks have been applied to this\nproblem with promising results. By exploiting massively parallel GPU processing\narchitectures and oodles of t…
  openalex Christopher A. Metzler, Alireza Mousavi, Richard G. Baraniuk 2017-04-21 置信度 0.72 Computer scienceCompressed sensingHeuristicArtificial neural networkNoise reduction
• Brain age prediction using interpretable multi-feature-based convolutional neural network in mild traumatic brain injury
  BACKGROUND: Convolutional neural network (CNN) can capture the structural features changes of brain aging based on MRI, thus predict brain age in healthy individuals accurately. However, most studies use single feature to predict brain age in healthy individua…
  openalex Xiang Zhang, Yizhen Pan, Tingting Wu, Wenpu Zhao 等 2024-07-22 置信度 0.72 Traumatic brain injuryConvolutional neural networkFeature (linguistics)Pattern recognition (psychology)Artificial intelligence
• DNA methylation-based forensic age prediction using artificial neural networks and next generation sequencing
  The ability to estimate the age of the donor from recovered biological material at a crime scene can be of substantial value in forensic investigations. Aging can be complex and is associated with various molecular modifications in cells that accumulate over a…
  openalex Athina Vidaki, David Ballard, Anastasia Aliferi, Thomas H. Miller 等 2017-02-28 置信度 0.72 DNA methylationCpG siteMethylationRegressionEpigenetics
• Attribution-based interpretable classification neural network with global and local perspectives
  Neural networks are challenging to apply in domains requiring high reliability due to their black-box nature, and researchers are increasingly focusing on interpreting neural networks. While pursuing neural network performance, most methods often sacrifice int…
  openalex Zihao Shi, Zuqiang Meng, Hu Tuo, Chao-Hong Tan 2025-07-09 置信度 0.72 Computer scienceAttributionArtificial neural networkArtificial intelligenceMachine learning
• Entropy-Based Logic Explanations of Neural Networks
  Explainable artificial intelligence has rapidly emerged since lawmakers have started requiring interpretable models for safety-critical domains. Concept-based neural networks have arisen as explainable-by-design methods as they leverage human-understandable sy…
  openalex Pietro Barbiero, Gabriele Ciravegna, Francesco Giannini, Píetro Lió 等 2022-06-28 置信度 0.72 Computer scienceArtificial intelligenceArtificial neural networkLeverage (statistics)Machine learning
• Protein secondary structure and homology by neural networks The α‐helices in rhodopsin
  Neural networks provide a basis for semiempirical studies of pattern matching between the primary and secondary structures of proteins. Networks of the perceptron class have been trained to classify the amino-acid residues into two categories for each of three…
  openalex Henrik Bohr, J. Bohr, Søren Brunak, R. M. J. Cotterill 等 1988-12-05 置信度 0.72 RhodopsinProtein secondary structureHomology (biology)Protein primary structureAlpha helix
• Semantic Role Labeling with Neural Network Factors
  We present a new method for semantic role labeling in which arguments and semantic roles are jointly embedded in a shared vector space for a given predicate. These embeddings belong to a neural network, whose output represents the potential functions of a grap…
  openalex Nicholas FitzGerald, Oscar Täckström, Kuzman Ganchev, Dipanjan Das 2015-01-01 置信度 0.72 FrameNetComputer scienceSemantic role labelingArtificial intelligencePredicate (mathematical logic)
• A Face Emotion Recognition Method Using Convolutional Neural Network and Image Edge Computing
  To avoid the complex process of explicit feature extraction in traditional facial expression recognition, a face expression recognition method based on a convolutional neural network (CNN) and an image edge detection is proposed. Firstly, the facial expression…
  openalex Hongli Zhang, Alireza Jolfaei, Mamoun Alazab 2019-01-01 置信度 0.72 Artificial intelligenceSoftmax functionPattern recognition (psychology)Convolutional neural networkComputer science
• Convergent activation dynamics in continuous time networks
  openalex Morris W. Hirsch 1989-01-01 置信度 0.72 Differentiable functionConvergence (economics)MathematicsNet (polyhedron)Chaotic
• Interpretable neural networks for predicting algal blooms in turbid nearshore waters: A case study of Macao's Chl-a dynamics
  openalex Zhengming Yi, Yahong Dong 2025-10-15 置信度 0.72 Environmental scienceAlgal bloomArtificial neural networkPhytoplanktonWater quality
• Directed migration of neural stem cells to sites of CNS injury by the stromal cell-derived factor 1α/CXC chemokine receptor 4 pathway
  Migration toward pathology is the first critical step in stem cell engagement during regeneration. Neural stem cells (NSCs) migrate through the parenchyma along nonstereotypical routes in a precise directed manner across great distances to injury sites in the …
  openalex Jaime Imitola, Khadir Raddassi, Kook In Park, Franz-Josef Müeller 等 2004-12-17 置信度 0.72 Homing (biology)Neural stem cellBiologyStromal cellCell biology
• Discrete Mutation Hopfield Neural Network in Propositional Satisfiability
  The dynamic behaviours of an artificial neural network (ANN) system are strongly dependent on its network structure. Thus, the output of ANNs has long suffered from a lack of interpretability and variation. This has severely limited the practical usability of …
  openalex Mohd Shareduwan Mohd Kasihmuddin, Mohd. Asyraf Mansor, Md Faisal Md Basir, Saratha Sathasivam 2019-11-19 置信度 0.72 Artificial neural networkOverfittingComputer scienceInterpretabilityHopfield network
• Explainable 1-D convolutional neural network for damage detection using Lamb wave
  openalex P. C. Pandey, Akshay Rai, Mira Mitra 2021-07-22 置信度 0.72 Convolutional neural networkLamb wavesExperimental dataFinite element methodComputer science
• WeedMap: A Large-Scale Semantic Weed Mapping Framework Using Aerial Multispectral Imaging and Deep Neural Network for Precision Farming
  The ability to automatically monitor agricultural fields is an important capability in precision farming, enabling steps towards more sustainable agriculture. Precise, high-resolution monitoring is a key prerequisite for targeted intervention and the selective…
  openalex Inkyu Sa, Marija Popović, Raghav Khanna, Zetao Chen 等 2018-09-07 置信度 0.72 Multispectral imageComputer sciencePrecision agricultureGround sample distanceRemote sensing
• Artificial neural network analysis (ANNA) of prostatic transrectal ultrasound
  BACKGROUND: Our purpose was to determine the diagnostic potential of a new, computerized method of interpreting transrectal ultrasound (TRUS) information by artificial neural network analysis (ANNA). This method was developed to resolve the current dilemma of …
  openalex Tillmann Loch, Ivo Leuschner, Carl Genberg, K. Weichert-Jacobsen 等 1999-05-15 置信度 0.72 MedicineUltrasoundProstatectomyHistopathologyProstate cancer
• Sanity Checks for Saliency Maps
  Saliency methods have emerged as a popular tool to highlight features in an input deemed relevant for the prediction of a learned model. Several saliency methods have been proposed, often guided by visual appeal on image data. In this work, we propose an actio…
  openalex Julius Adebayo, Justin Gilmer, Michael Muelly, Ian Goodfellow 等 2018-10-08 置信度 0.72 Computer scienceDebuggingArtificial intelligenceMachine learningConvolutional neural network
• A Network-based End-to-End Trainable Task-oriented Dialogue System
  Tsung-Hsien Wen, David Vandyke, Nikola Mrkšić, Milica Gašić, Lina M. Rojas-Barahona, Pei-Hao Su, Stefan Ultes, Steve Young. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers. 2017…
  openalex Tsung-Hsien Wen, David Vandyke, Nikola Mrkšić, Milica Gašić 等 2017-01-01 置信度 0.72 Task (project management)Computer scienceEnd-to-end principleAssociation (psychology)Volume (thermodynamics)
• Supramolecular Peptide Hydrogel-Based Soft Neural Interface Augments Brain Signals through a Three-Dimensional Electrical Network
  Recording neural activity from the living brain is of great interest in neuroscience for interpreting cognitive processing or neurological disorders. Despite recent advances in neural technologies, development of a soft neural interface that integrates with ne…
  openalex Jiyoung Nam, Hyun‐Kyoung Lim, Nam Hyeong Kim, Jong Kwan Park 等 2020-01-02 置信度 0.72 Supramolecular chemistryPeptideMaterials scienceInterface (matter)Self-healing hydrogels
• DeNTNet: Deep Neural Transfer Network for the detection of periodontal bone loss using panoramic dental radiographs
  In this study, a deep learning-based method for developing an automated diagnostic support system that detects periodontal bone loss in the panoramic dental radiographs is proposed. The presented method called DeNTNet not only detects lesions but also provides…
  openalex Jae‐Young Kim, Hong-Seok Lee, In‐Seok Song, Kyu-Hwan Jung 2019-11-26 置信度 0.72 RadiographyConvolutional neural networkTransfer of learningMedicineDentistry
• Coupled neural systems underlie the production and comprehension of naturalistic narrative speech
  Neuroimaging studies of language have typically focused on either production or comprehension of single speech utterances such as syllables, words, or sentences. In this study we used a new approach to functional MRI acquisition and analysis to characterize th…
  openalex Lauren J. Silbert, Christopher J. Honey, Erez Simony, David Poeppel 等 2014-09-29 置信度 0.72 ComprehensionNarrativeSpeech productionCognitive psychologyPsychology
• Neural basis of eye gaze processing deficits in autism
  Impairments in using eye gaze to establish joint attention and to comprehend the mental states and intentions of other people are striking features of autism. Here, using event-related functional MRI (fMRI), we show that in autism, brain regions involved in ga…
  openalex Kevin A. Pelphrey, J. P. Morris, Gregory McCarthy 2005-03-09 置信度 0.72 AutismGazePsychologyEye movementNeuroscience
• Interpreting Deep Neural Networks Beyond Attribution Methods: Quantifying Global Importance of Genomic Features
  Abstract Despite deep neural networks (DNNs) having found great success at improving performance on various prediction tasks in computational genomics, it remains difficult to understand why they make any given prediction. In genomics, the main approaches to i…
  openalex Peter K. Koo, Matt Ploenzke 2020-02-20 置信度 0.72 InterpretabilityComputer scienceArtificial intelligenceCausality (physics)Attribution
• Auto-GNN: Neural architecture search of graph neural networks
  Graph neural networks (GNNs) have been widely used in various graph analysis tasks. As the graph characteristics vary significantly in real-world systems, given a specific scenario, the architecture parameters need to be tuned carefully to identify a suitable …
  openalex Kaixiong Zhou, Xiao Huang, Qingquan Song, Rui Chen 等 2022-11-17 置信度 0.72 Computer scienceArchitectureBenchmark (surveying)GraphArtificial intelligence
• NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation
  With the progress of 3D human pose and shape estimation, state-of-the-art methods can either be robust to occlusions or obtain pixel-aligned accuracy in non-occlusion cases. However, they cannot obtain robustness and mesh-image alignment at the same time. In t…
  openalex Jiefeng Li, Siyuan Bian, Qi Liu, Jiasheng Tang 等 2023-06-01 置信度 0.72 Robustness (evolution)Computer sciencePoseArtificial intelligenceKinematics
• Geometric deep learning and equivariant neural networks
  Abstract We survey the mathematical foundations of geometric deep learning, focusing on group equivariant and gauge equivariant neural networks. We develop gauge equivariant convolutional neural networks on arbitrary manifolds $$\mathcal {M}$$ M using principa…
  openalex Jan E. Gerken, Jimmy Aronsson, Oscar Carlsson, Hampus Linander 等 2023-06-04 置信度 0.72 Equivariant mapArtificial intelligenceAlgorithmConvolutional neural networkComputer science
• Interpretable Prediction of Protein-Ligand Interaction by Convolutional Neural Network
  Evaluation of protein-ligand interaction is a crucial step in the process of drug discovery. Recently, several methods based on deep learning have gained impressive binary classification performance on protein-ligand binding prediction. However, lack of three-…
  openalex Fan Hu, Jiaxin Jiang, Peng Yin 2019-11-01 置信度 0.72 Computer scienceArtificial intelligenceRobustness (evolution)Protein ligandBinary classification
• Individual differences among deep neural network models
  Deep neural networks (DNNs) excel at visual recognition tasks and are increasingly used as a modeling framework for neural computations in the primate brain. Just like individual brains, each DNN has a unique connectivity and representational profile. Here, we…
  openalex Johannes Mehrer, Courtney J. Spoerer, Nikolaus Kriegeskorte, Tim C. Kietzmann 2020-11-12 置信度 0.72 Computer scienceInitializationArtificial neural networkArtificial intelligenceDeep neural networks
• DisenHAN: Disentangled Heterogeneous Graph Attention Network for Recommendation
  Heterogeneous information network has been widely used to alleviate sparsity and cold start problems in recommender systems since it can model rich context information in user-item interactions. Graph neural network is able to encode this rich context informat…
  openalex Yifan Wang, Suyao Tang, Yuntong Lei, Weiping Song 等 2020-10-19 置信度 0.72 Computer scienceInterpretabilityEmbeddingRecommender systemHeterogeneous network
• Credit scoring models for the microfinance industry using neural networks: Evidence from Peru
  openalex Antonio Blanco‐Oliver, Rafael Pino‐Mejías, Juan Lara‐Rubio, Salvador Rayo 2012-08-01 置信度 0.72 MicrofinanceArtificial neural networkComputer scienceArtificial intelligenceMachine learning
• Learnable Subdivision Graph Neural Network for Functional Brain Network Analysis and Interpretable Cognitive Disorder Diagnosis
  openalex Dongdong Chen, Mengjun Liu, Zhenrong Shen, Xiangyu Zhao 等 2023-01-01 置信度 0.72 InterpretabilityComputer scienceCognitionENCODEArtificial intelligence
• Artificial Intelligence in the Age of Neural Networks and Brain Computing
  openalex R. Kozma, C. Alippi, Y. Choe, F. C. Morabito, Kozma, R., Alippi, C., Choe, Y. 等 2018-11-02 置信度 0.72 Artificial neural networkComputer scienceArtificial intelligenceCognitive sciencePsychology
• A multiple objective optimization based GA for designing interpretable and comprehensible neural network trees
  Neural network tree (NNTree) is a hybrid model for machine learning. The overall structure is a decision tree (DT), and each non-terminal node is an expert neural network (ENN). Generally speaking, NNTrees can achieve better performance than conventional DTs w…
  openalex Chun Lu, Qiangfu Zhao, Wenjiang Pei, Zhenya He 2003-01-01 置信度 0.72 Computer scienceArtificial neural networkArtificial intelligenceTree (set theory)Machine learning
• Cyclone track forecasting based on satellite images using artificial neural networks
  openalex Rita Kovordányi, Chandan Roy 2009-04-16 置信度 0.72 Artificial neural networkMeteorologyTropical cyclone forecast modelWeather forecastingTrack (disk drive)
• A deep neural network trained to interpret results from electrocardiograms: better than physicians?
  Heart function depends on precisely orchestrated cell membrane depolarisations of billions of heart muscle cells that elicit voltage differences on the body surface—recordable by an electrocardiogram (ECG).
  openalex Daniel Sinnecker 2020-06-04 置信度 0.72 Artificial neural networkArtificial intelligenceComputer scienceMedicine
• Identifying meaningful drug response biomarkers from public pharmacogenomic datasets with biologically informed interpretable neural networks
  openalex Maoxin Ran, Shaolin Zhang, Kin Yip Tam 2025-09-02 置信度 0.72 PharmacogenomicsDrug responseComputer scienceArtificial neural networkArtificial intelligence
• WINNet: Wavelet-Inspired Invertible Network for Image Denoising
  Image denoising aims to restore a clean image from an observed noisy one. Model-based image denoising approaches can achieve good generalization ability over different noise levels and are with high interpretability. Learning-based approaches are able to achie…
  openalex Junjie Huang, Pier Luigi Dragotti 2022-01-01 置信度 0.72 Artificial intelligenceInterpretabilityNoise reductionPattern recognition (psychology)Deblurring