AI 安全与对齐 · 全部实体（第 17 / 100 页）

本页收录第 1601–1700 条，共 10000 条 · 返回 AI 安全与对齐 首页

• Graph Neural Networks in Brain Connectivity Studies: Methods, Challenges, and Future Directions
  Brain connectivity analysis plays a crucial role in unraveling the complex network dynamics of the human brain, providing insights into cognitive functions, behaviors, and neurological disorders. Traditional graph-theoretical methods, while foundational, often…
  openalex Hamed Mohammadi, Waldemar Karwowski 2024-12-27 置信度 0.72 InterpretabilityNeuroimagingComputer scienceModalitiesPower graph analysis
• On the Analyses of Medical Images Using Traditional Machine Learning Techniques and Convolutional Neural Networks
  Convolutional neural network (CNN) has shown dissuasive accomplishment on different areas especially Object Detection, Segmentation, Reconstruction (2D and 3D), Information Retrieval, Medical Image Registration, Multi-lingual translation, Local language Proces…
  openalex Saeed Iqbal, Adnan N. Qureshi, Jianqiang Li, Tariq Mahmood 2023-04-04 置信度 0.72 Computer scienceConvolutional neural networkDeep learningArtificial intelligenceSegmentation
• Shapley additive explanations for NO2 forecasting
  openalex María Vega García, Jose L Aznarte 2019-12-21 置信度 0.72 InterpretabilityComputer scienceMachine learningArtificial intelligenceArtificial neural network
• A Transformer based neural network for emotion recognition and visualizations of crucial EEG channels
  openalex Jiayi Guo, Qing Cai, Jian-Peng An, Pei‐Yin Chen 等 2022-06-17 置信度 0.72 Computer scienceElectroencephalographyInterpretabilityArtificial intelligencePattern recognition (psychology)
• Similarity-navigated graph neural networks for node classification
  Graph Neural Networks are effective in learning representations of graph-structured data. Some recent works are devoted to addressing heterophily, which exists ubiquitously in real-world networks, breaking the homophily assumption that nodes belonging to the s…
  openalex Minhao Zou, Zhongxue Gan, Ruizhi Cao, Chun Guan 等 2023-03-11 置信度 0.72 Computer scienceAdjacency matrixGraphHomophilySimilarity (geometry)
• Deep Convolutional Neural Network for Flood Extent Mapping Using Unmanned Aerial Vehicles Data
  Flooding is one of the leading threats of natural disasters to human life and property, especially in densely populated urban areas. Rapid and precise extraction of the flooded areas is key to supporting emergency-response planning and providing damage assessm…
  openalex Asmamaw Gebrehiwot, Leila Hashemi-Beni, Gary L. Thompson, Parisa Kordjamshidi 等 2019-03-27 置信度 0.72 Computer scienceArtificial intelligenceConvolutional neural networkSupport vector machineAerial imagery
• Fully Character-Level Neural Machine Translation without Explicit Segmentation
  Most existing machine translation systems operate at the level of words, relying on explicit segmentation to extract tokens. We introduce a neural machine translation (NMT) model that maps a source character sequence to a target character sequence without any …
  openalex Jason D. Lee, Kyunghyun Cho, Thomas Hofmann 2017-12-01 置信度 0.72 Computer scienceMachine translationCharacter (mathematics)PoolingEncoder
• A review on neural network models of schizophrenia and autism spectrum disorder
  This survey presents the most relevant neural network models of autism spectrum disorder and schizophrenia, from the first connectionist models to recent deep neural network architectures. We analyzed and compared the most representative symptoms with its neur…
  openalex Pablo Lanillos, Daniel Oliva, Anja Philippsen, Yuichi Yamashita 等 2019-11-13 置信度 0.72 AutismSchizophrenia (object-oriented programming)Artificial neural networkConnectionismAutism spectrum disorder
• Two-way interaction of input variables in the sensitivity analysis of neural network models
  openalex Muriel Gevrey, Ioannis Dimopoulos, Sovan Lek 2006-01-19 置信度 0.72 Standard deviationArtificial neural networkSensitivity (control systems)Multivariate statisticsVariable (mathematics)
• Human brain networks function in connectome-specific harmonic waves
  A key characteristic of human brain activity is coherent, spatially distributed oscillations forming behaviour-dependent brain networks. However, a fundamental principle underlying these networks remains unknown. Here we report that functional networks of the …
  openalex Selen Atasoy, I. C. Donnelly, Joel Pearson 2016-01-21 置信度 0.72 ConnectomeNeuroscienceHuman brainHuman Connectome ProjectComputer science
• A gentle introduction to artificial neural networks
  Artificial neural network (ANN) is a flexible and powerful machine learning technique. However, it is under utilized in clinical medicine because of its technical challenges. The article introduces some basic ideas behind ANN and shows how to build ANN using R…
  openalex Zhongheng Zhang 2016-10-01 置信度 0.72 Artificial neural networkComputer scienceSimple (philosophy)Activation functionFunction (biology)
• Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data
  One of the defining properties of deep learning is that models are chosen to have many more parameters than available training data. In light of this capacity for overfitting, it is remarkable that simple algorithms like SGD reliably return solutions with low …
  openalex Gintare Karolina Dziugaite, Daniel M. Roy 2017-03-31 置信度 0.72 OverfittingGeneralizationComputer scienceArtificial neural networkMaxima and minima
• The Neural Correlates of Conscious Vision
  Conflicting accounts of the neurobiology of consciousness have emerged from previous imaging studies. Some studies suggest that visual consciousness relates to a distributed network of frontal and partietal regions while others point to localized activity with…
  openalex Delphine Pins 2003-04-04 置信度 0.72 ConsciousnessNeural correlates of consciousnessPsychologyPerceptionFunctional magnetic resonance imaging
• Multistep Neural Networks for Data-driven Discovery of Nonlinear Dynamical Systems
  The process of transforming observed data into predictive mathematical models of the physical world has always been paramount in science and engineering. Although data is currently being collected at an ever-increasing pace, devising meaningful models out of s…
  openalex Maziar Raissi, Paris Perdikaris, George Em Karniadakis 2018-01-04 置信度 0.72 Computer scienceNonlinear systemArtificial neural networkBenchmark (surveying)Dynamical systems theory
• One neuron is more informative than a deep neural network for aftershock pattern forecasting
  29 August 2018: "Artificial intelligence nails predictions of earthquake aftershocks". This Nature News headline is based on the results of DeVries et al. (2018) who forecasted the spatial distribution of aftershocks using Deep Learning (DL) and static stress …
  openalex Mignan, Arnaud, Marco Broccardo 2019-01-01 置信度 0.72 Receiver operating characteristicArtificial intelligenceArtificial neural networkLogistic regressionMathematics
• A Model of Interval Timing by Neural Integration
  We show that simple assumptions about neural processing lead to a model of interval timing as a temporal integration process, in which a noisy firing-rate representation of time rises linearly on average toward a response threshold over the course of an interv…
  openalex Patrick Simen, Fuat Balcı, Laura deSouza, J. D. Cohen 等 2011-06-22 置信度 0.72 Interval (graph theory)SkewnessComputer sciencePoisson distributionArtificial intelligence
• DEEP CONVOLUTIONAL NEURAL NETWORK FOR AUTOMATIC DETECTION OF DAMAGED PHOTOVOLTAIC CELLS
  Abstract. The number of distributed Photovoltaic (PV) plants that produce electricity has been significantly increased, and issue of monitoring and maintaining a PV plant has become of great importance and involves many challenges as efficiency, reliability, s…
  openalex Roberto Pierdicca, Eva Savina Malinverni, F. Piccinini, Marina Paolanti 等 2018-05-30 置信度 0.72 Photovoltaic systemReliability (semiconductor)Convolutional neural networkComputer scienceDrone
• Neural network potentials for chemistry: concepts, applications and prospects
  Artificial Neural Networks (NN) are already heavily involved in methods and applications for frequent tasks in the field of computational chemistry such as representation of potential energy surfaces (PES) and spectroscopic predictions. This perspective provid…
  openalex Silvan Käser, Luis Itza Vazquez-Salazar, Markus Meuwly, Kai Töpfer 2022-12-21 置信度 0.72 Computer scienceArtificial neural networkRepresentation (politics)Field (mathematics)Reliability (semiconductor)
• Interpretability Analysis of Data Augmented Convolutional Neural Network in Mineral Prospectivity Mapping Using Black-Box Visualization Tools
  openalex Yue Liu, Tao Sun, Kaixing Wu, Wenyuan Xiang 等 2025-01-31 置信度 0.72 Prospectivity mappingInterpretabilityBlack boxVisualizationConvolutional neural network
• Modelling population dynamics of aquatic insects with artificial neural networks
  openalex Michael Obach, Rüdiger Wagner, Heinrich Werner, Hans‐Heinrich Schmidt 2001-12-01 置信度 0.72 Abundance (ecology)PopulationArtificial neural networkSelf-organizing mapMultilayer perceptron
• Char-Net: A Character-Aware Neural Network for Distorted Scene Text Recognition
  In this paper, we present a Character-Aware Neural Network (Char-Net) for recognizing distorted scene text. Our Char-Net is composed of a word-level encoder, a character-level encoder, and a LSTM-based decoder. Unlike previous work which employed a global spat…
  openalex Wei Liu, Chaofeng Chen, Kwan-Yee Wong 2018-04-27 置信度 0.72 Computer scienceCharacter (mathematics)EncoderArtificial intelligenceTransformer
• Artificial neural networks in pathology and medical laboratories
  openalex Richard Dybowski, Vanya Gant 1995-11-01 置信度 0.72 Computer scienceTurnaround timeHousekeepingAutomationMicroprocessor
• GPX-ADMM-Net: Interpretable Deep Neural Network for Image Compressive Sensing
  The building of effective neural network architectures for solving image compressive sensing (CS) problems is a challenge. Hence, it is helpful to consult the structural insight provided by traditional optimization algorithms, the results of which are interpre…
  openalex Shih-Wei Hu, Gang-Xuan Lin, Chun-Shien Lu 2021-01-01 置信度 0.72 InpaintingComputer scienceImage (mathematics)Artificial neural networkArtificial intelligence
• Prediction of IDH genotype in gliomas with dynamic susceptibility contrast perfusion MR imaging using an explainable recurrent neural network
  BACKGROUND: The aim of this study was to predict isocitrate dehydrogenase (IDH) genotypes of gliomas using an interpretable deep learning application for dynamic susceptibility contrast (DSC) perfusion MRI. METHODS: Four hundred sixty-three patients with gliom…
  openalex Kyu Sung Choi, Seung Hong Choi, Bumseok Jeong 2019-05-23 置信度 0.72 Contrast (vision)GenotypeMedicineBiologyComputer science
• ATSE: a peptide toxicity predictor by exploiting structural and evolutionary information based on graph neural network and attention mechanism
  MOTIVATION: Peptides have recently emerged as promising therapeutic agents against various diseases. For both research and safety regulation purposes, it is of high importance to develop computational methods to accurately predict the potential toxicity of pep…
  openalex Lesong Wei, Lesong Wei, Xiucai Ye, Yuyang Xue 等 2021-01-29 置信度 0.72 Mechanism (biology)Computer scienceGraphToxicityComputational biology
• Theory-based residual neural networks: A synergy of discrete choice models and deep neural networks
  openalex Shenhao Wang, Baichuan Mo, Jinhua Zhao 2021-03-19 置信度 0.72 Computer scienceOverfittingResidualArtificial intelligenceResidual neural network
• A convolutional neural network highlights mutations relevant to antimicrobial resistance in Mycobacterium tuberculosis
  Long diagnostic wait times hinder international efforts to address antibiotic resistance in M. tuberculosis. Pathogen whole genome sequencing, coupled with statistical and machine learning models, offers a promising solution. However, generalizability and clin…
  openalex Anna G. Green, Chang Ho Yoon, Michael L. Chen, Yasha Ektefaie 等 2022-07-02 置信度 0.72 InterpretabilityConvolutional neural networkMycobacterium tuberculosisArtificial intelligenceGeneralizability theory
• scBERT as a large-scale pretrained deep language model for cell type annotation of single-cell RNA-seq data
  openalex Fan Yang, Wenchuan Wang, Fang Wang, Yuan Fang 等 2022-09-26 置信度 0.72 AnnotationComputer scienceInterpretabilityRobustness (evolution)Artificial intelligence
• Neural-Tube Defects and Antiretroviral Treatment Regimens in Botswana
  BACKGROUND: A preliminary safety signal for neural-tube defects was previously reported in association with dolutegravir exposure from the time of conception, which has affected choices of antiretroviral treatment (ART) for human immunodeficiency virus (HIV)-i…
  openalex Rebecca Zash, Lewis B. Holmes, Modiegi Diseko, Denise L. Jacobson 等 2019-07-22 置信度 0.72 Neural tubeAntiretroviral treatmentAntiretroviral therapyTube (container)Human immunodeficiency virus (HIV)
• PadChest: A large chest x-ray image dataset with multi-label annotated reports
  openalex Aurelia Bustos, Antonio Pertusa, José María Salinas, María de la Iglesia-Vayá 2020-08-20 置信度 0.72 Artificial intelligenceComputer scienceImage (mathematics)Pattern recognition (psychology)Multi-label classification
• Interpreting Wide-Band Neural Activity Using Convolutional Neural Networks
  A bstract Rapid progress in technologies such as calcium imaging and electrophysiology has seen a dramatic increase in the size and extent of neural recordings. Even so, interpretation of this data often depends on manual operations and requires considerable k…
  openalex Markus Frey, Sander Tanni, Catherine Perrodin, Alice O’Leary 等 2019-12-11 置信度 0.72 Computer scienceArtificial neural networkRepresentation (politics)Encoding (memory)Convolutional neural network
• A machine learning approach for predicting hidden links in supply chain with graph neural networks
  Supply chain business interruption has been identified as a key risk factor in recent years, with high-impact disruptions due to disease outbreaks, logistic issues such as the recent Suez Canal blockage showing examples of how disruptions could propagate acros…
  openalex Edward Elson Kosasih, Alexandra Brintrup 2021-07-31 置信度 0.72 Computer scienceSupply chainArtificial neural networkContingencyArtificial intelligence
• Is neuron coverage a meaningful measure for testing deep neural networks?
  Recent effort to test deep learning systems has produced an intuitive and compelling test criterion called neuron coverage (NC), which resembles the notion of traditional code coverage. NC measures the proportion of neurons activated in a neural network and it…
  openalex Fabrice Harel-Canada, Lingxiao Wang, Muhammad Ali Gulzar, Quanquan Gu 等 2020-11-08 置信度 0.72 Computer scienceNaturalnessTest suiteAdversarial systemArtificial neural network
• Hyperspectral Image Classification Using Convolutional Neural Networks and Multiple Feature Learning
  Convolutional neural networks (CNNs) have been extended to hyperspectral imagery (HSI) classification due to its better feature representation and high performance, whereas multiple feature learning has shown its effectiveness in computer vision areas. This pa…
  openalex Qishuo Gao, Samsung Lim, Xiuping Jia 2018-02-15 置信度 0.72 Hyperspectral imagingComputer scienceArtificial intelligencePattern recognition (psychology)Feature (linguistics)
• Identifying Emotions on the Basis of Neural Activation
  We attempt to determine the discriminability and organization of neural activation corresponding to the experience of specific emotions. Method actors were asked to self-induce nine emotional states (anger, disgust, envy, fear, happiness, lust, pride, sadness,…
  openalex Karim Kassam, Amanda Markey, Vladimir L. Cherkassky, George Loewenstein 等 2013-06-19 置信度 0.72 DisgustSadnessPsychologyValence (chemistry)Anger
• Diagnosis of heart disease using genetic algorithm based trained recurrent fuzzy neural networks
  The World Health Organization (WHO) estimated one third of all global deaths reason as cardiovascular diseases in 2015. Some computational techniques were proposed for investigation of heart diseases. This study proposes a genetic algorithm (GA) based trained …
  openalex Kaan Uyar, Ahmet İlhan 2017-01-01 置信度 0.72 Computer scienceArtificial neural networkArtificial intelligenceFuzzy logicMean squared error
• Improving hydrologic models for predictions and process understanding using neural ODEs
  Abstract. Deep learning methods have frequently outperformed conceptual hydrologic models in rainfall-runoff modelling. Attempts of investigating such deep learning models internally are being made, but the traceability of model states and processes and their …
  openalex Marvin Höge, Andreas Scheidegger, Marco Baity‐Jesi, Carlo Albert 等 2022-10-11 置信度 0.72 InterpretabilityOdeArtificial neural networkComputer scienceDeep learning
• Electricity Theft Detection in Smart Grids Based on Deep Neural Network
  Electricity theft is a global problem that negatively affects both utility companies and electricity users. It destabilizes the economic development of utility companies, causes electric hazards and impacts the high cost of energy for users. The development of…
  openalex Leloko J. Lepolesa, Shamin Achari, Ling Cheng 2022-01-01 置信度 0.72 Computer scienceElectricityArtificial intelligenceBenchmark (surveying)Data mining
• Deep learning analysis of fMRI data for predicting Alzheimer’s Disease: A focus on convolutional neural networks and model interpretability
  The early detection of Alzheimer's Disease (AD) is thought to be important for effective intervention and management. Here, we explore deep learning methods for the early detection of AD. We consider both genetic risk factors and functional magnetic resonance …
  openalex Xiao Zhou, Sanchita Kedia, Ran Meng, Mark Gerstein 2024-12-04 置信度 0.72 InterpretabilityConvolutional neural networkNeuroimagingDeep learningFunctional magnetic resonance imaging
• Generative Moment Matching Networks
  We consider the problem of learning deep generative models from data. We formulate a method that generates an independent sample via a single feedforward pass through a multilayer perceptron, as in the recently proposed generative adversarial networks (Goodfel…
  openalex Yujia Li, Kevin Swersky, Rich Zemel 2015-02-10 置信度 0.72 MNIST databaseComputer scienceGenerative grammarArtificial intelligenceMatching (statistics)
• Providing Interpretability of Document Classification by Deep Neural Network with Self-attention
  Deep learning has been widely used in natural language processing (NLP) such as document classification. For example, self-attention has achieved significant improvement in NLP. However, it has been pointed out that although deep learning accurately classifies…
  openalex Atsuki Tamekuri, Kôsuke Nakamura, Yoshihaya Takahashi, Saneyasu Yamaguchi 2022-01-01 置信度 0.72 InterpretabilityComputer scienceArtificial intelligenceDocument classificationWord (group theory)
• Combining a neural network with case-based reasoning in a diagnostic system
  openalex Eliseo Berní Reategui, J. A. Campbell, Beatriz F. Leão 1997-01-01 置信度 0.72 Artificial neural networkComputer scienceCase-based reasoningArtificial intelligenceSearch engine indexing
• Two-stage biologically interpretable neural-network models for liver cancer prognosis prediction using histopathology and transcriptomic data
  ABSTRACT Purpose Pathological images are easily accessible data with the potential as prognostic biomarkers. Moreover, integration of heterogeneous data types from multi-modality, such as pathological image and gene expression data, is invaluable to help predi…
  openalex Zhucheng Zhan, Zheng Jing, Bing He, Noshad Hosseini 等 2020-01-28 置信度 0.72 Proportional hazards modelStage (stratigraphy)PathologicalArtificial intelligenceComputer science
• Cola-GNN: Cross-location Attention based Graph Neural Networks for Long-term ILI Prediction
  Forecasting influenza-like illness (ILI) is of prime importance to epidemiologists and health-care providers. Early prediction of epidemic outbreaks plays a pivotal role in disease intervention and control. Most existing work has either limited long-term predi…
  openalex Songgaojun Deng, Shusen Wang, Huzefa Rangwala, Lijing Wang 等 2020-10-19 置信度 0.72 Computer scienceCola (plant)GraphTerm (time)Machine learning
• TME-NET: an interpretable deep neural network for predicting pan-cancer immune checkpoint inhibitor responses
  Immunotherapy with immune checkpoint inhibitors (ICIs) is increasingly used to treat various tumor types. Determining patient responses to ICIs presents a significant clinical challenge. Although components of the tumor microenvironment (TME) are used to predi…
  openalex Xiaobao Ding, Lin Zhang, Ming Fan, Lihua Li 2024-07-25 置信度 0.72 Tumor microenvironmentImmunotherapyImmune systemCD8Biology
• Supervised Versus Unsupervised Binary-Learning by Feedforward Neural Networks
  openalex Nathalie Japkowicz 2001-01-01 置信度 0.72 GeneralizationArtificial intelligenceConnectionismComputer scienceBinary classification
• Towards Interpretable Semantic Segmentation via Gradient-Weighted Class Activation Mapping (Student Abstract)
  Convolutional neural networks have become state-of-the-art in a wide range of image recognition tasks. The interpretation of their predictions, however, is an active area of research. Whereas various interpretation methods have been suggested for image classif…
  openalex Kira Vinogradova, Alexandr Dibrov, Gene Myers 2020-04-03 置信度 0.72 SegmentationArtificial intelligenceInterpretation (philosophy)Computer sciencePattern recognition (psychology)
• Explaining Convolutional Neural Networks using Softmax Gradient Layer-wise Relevance Propagation
  Convolutional Neural Networks (CNN) have become state-of-the-art in the field of image classification. However, not everything is understood about their inner representations. This paper tackles the interpretability and explainability of the predictions of CNN…
  openalex Brian Kenji Iwana, Ryohei Kuroki, Seiichi Uchida 2019-10-01 置信度 0.72 Softmax functionInterpretabilityComputer scienceConvolutional neural networkArtificial intelligence
• GemNet: Universal Directional Graph Neural Networks for Molecules
  Effectively predicting molecular interactions has the potential to accelerate molecular dynamics by multiple orders of magnitude and thus revolutionize chemical simulations. Graph neural networks (GNNs) have recently shown great successes for this task, overta…
  openalex Johannes Gasteiger, Florian Becker, Stephan Günnemann 2021-06-02 置信度 0.72 Computer scienceLeverage (statistics)Theoretical computer scienceInvariant (physics)Equivariant map
• Deep learning in hydrology and water resources disciplines: concepts, methods, applications, and research directions
  openalex Kumar Puran Tripathy, Ashok K. Mishra 2023-11-15 置信度 0.72 Deep learningInterpretabilityComputer scienceArtificial intelligenceMachine learning
• Deep convolutional neural network VGG-16 model for differential diagnosing of papillary thyroid carcinomas in cytological images: a pilot study
  : In summary, after training with a large dataset, the DCNN VGG-16 model showed great potential in facilitating PTC diagnosis from cytological images. The contours, perimeter, area and mean of pixel intensity of PTC in fragmented images were more than the beni…
  openalex Qing Guan, Yunjun Wang, Bo Ping, Duanshu Li 等 2019-01-01 置信度 0.72 PerimeterConvolutional neural networkMedicineThyroid carcinomaPixel
• Multifaceted Feature Visualization: Uncovering the Different Types of\n Features Learned By Each Neuron in Deep Neural Networks
  We can better understand deep neural networks by identifying which features\neach of their neurons have learned to detect. To do so, researchers have\ncreated Deep Visualization techniques including activation maximization, which\nsynthetically generates input…
  openalex Anh Nguyen, Jason Yosinski, Jeff Clune 2016-02-11 置信度 0.72 InterpretabilityComputer scienceVisualizationNeuronArtificial intelligence
• A convolutional neural network for the screening and staging of diabetic retinopathy
  Diabetic retinopathy (DR) is a serious retinal disease and is considered as a leading cause of blindness in the world. Ophthalmologists use optical coherence tomography (OCT) and fundus photography for the purpose of assessing the retinal thickness, and struct…
  openalex Mohamed Shaban, Zeliha Ogur, Ali Mahmoud, Andrew E. Switala 等 2020-06-22 置信度 0.72 Diabetic retinopathyConvolutional neural networkMedicineArtificial intelligenceFundus (uterus)
• Explainable AI Methods - A Brief Overview
  Abstract Explainable Artificial Intelligence (xAI) is an established field with a vibrant community that has developed a variety of very successful approaches to explain and interpret predictions of complex machine learning models such as deep neural networks.…
  openalex Andreas Holzinger, Anna Saranti, Christoph Molnar, Przemysław Biecek 等 2022-01-01 置信度 0.72 Computer scienceVariety (cybernetics)Field (mathematics)Artificial intelligenceArtificial neural network
• Predicting mental conditions based on “history of present illness” in psychiatric notes with deep neural networks
  openalex Tung Tran, Ramakanth Kavuluru 2017-06-10 置信度 0.72 Task (project management)Computer scienceSet (abstract data type)NarrativeMental illness
• The Effect of the Normalization Method Used in Different Sample Sizes on the Success of Artificial Neural Network Model
  In this study, it was aimed to compare different normalization methods employed in model developing process via artificial neural networks with different sample sizes. As part of comparison of normalization methods, input variables were set as: work discipline…
  openalex Gökhan Aksu, Cem Oktay Güzeller, Mehmet Taha ESER 2019-03-28 置信度 0.72 Normalization (sociology)OverfittingArtificial neural networkArtificial intelligenceDatabase normalization
• Leveraging Machine Learning and Molecular Neural Networks to Interpret and Explain AI-Driven Prediction of Drug Efficacy
  Drug discovery along with efficacy prediction through artificial intelligence (AI) requires researchers to build explainable models which offer interpretability. The introduced framework uses machine learning (ML) with molecular neural networks (MNNs) to reinf…
  openalex T. Venkata Naga Jayudu, Koushik Reddy Chaganti, Kottil Rammohan, N. Srihari Rao 等 2025-06-04 置信度 0.72 Computer scienceArtificial neural networkArtificial intelligenceMachine learning
• Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures
  Model-based methods and deep neural networks have both been tremendously successful paradigms in machine learning. In model-based methods, problem domain knowledge can be built into the constraints of the model, typically at the expense of difficulties during …
  openalex John R. Hershey, Jonathan Le Roux, Felix Weninger 2014-09-09 置信度 0.72 InferenceComputer scienceArtificial intelligenceDeep learningArtificial neural network
• Interpretable Retinal Disease Classification from OCT Images Using Deep Neural Network and Explainable AI
  Deep Learning Models (DNN) are being used extensively for medical image classification such as MRI, OCT, x-ray in recent years. The proposed model revolves around the analysis of macular Optical Coherence Tomography (OCT) images to distinguish three eye-relate…
  openalex Md Tanzim Reza, Farzad Ahmed, Shihab Sharar, Annajiat Alim Rasel 2021-09-14 置信度 0.72 Computer scienceArtificial intelligenceDrusenOptical coherence tomographyResidual neural network
• Learning How to Propagate Messages in Graph Neural Networks
  This paper studies the problem of learning message propagation strategies for graph neural networks (GNNs). One of the challenges for graph neural networks is that of defining the propagation strategy. For instance, the choices of propagation steps are often s…
  openalex Teng Xiao, Zhengyu Chen, Donglin Wang, Suhang Wang 2021-08-12 置信度 0.72 Computer scienceGraphMaximizationArtificial intelligenceMachine learning
• In vivo imaging of phosphocreatine with artificial neural networks
  Abstract Phosphocreatine (PCr) plays a vital role in neuron and myocyte energy homeostasis. Currently, there are no routine diagnostic tests to noninvasively map PCr distribution with clinically relevant spatial resolution and scan time. Here, we demonstrate t…
  openalex Lin Chen, Michael Schär, Kannie W. Y. Chan, Jianpan Huang 等 2020-02-26 置信度 0.72 PhosphocreatineMagnetic resonance imagingNuclear magnetic resonanceSkeletal muscleBiomedical engineering
• Contextualized Non-Local Neural Networks for Sequence Learning
  Recently, a large number of neural mechanisms and models have been proposed for sequence learning, of which selfattention, as exemplified by the Transformer model, and graph neural networks (GNNs) have attracted much attention. In this paper, we propose an app…
  openalex Pengfei Liu, Shuaichen Chang, Xuanjing Huang, Jian Tang 等 2019-07-17 置信度 0.72 InterpretabilityComputer scienceArtificial intelligenceLeverage (statistics)Artificial neural network
• Interpretable COVID-19 Classification Leveraging Ensemble Neural Network and XAI
  openalex Shakib Mahmud Dipto, Irfana Afifa, Mostofa Kamal Sagor, Md Tanzim Reza 等 2021-01-01 置信度 0.72 Death tollComputer scienceCoronavirus disease 2019 (COVID-19)Artificial intelligenceInfection rate
• Google matrix analysis of directed networks
  In past ten years, modern societies developed enormous communication and social networks. Their classification and information retrieval processing become a formidable task for the society. Due to the rapid growth of World Wide Web, social and communication ne…
  arxiv Leonardo Ermann, Klaus M. Frahm, Dima L. Shepelyansky 2014-09-01T14:14:11Z 置信度 0.78 physics.soc-phcond-mat.stat-mechcs.SInlin.CD
• InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques
  Mechanistic interpretability methods aim to identify the algorithm a neural network implements, but it is difficult to validate such methods when the true algorithm is unknown. This work presents InterpBench, a collection of semi-synthetic yet realistic transf…
  arxiv Rohan Gupta, Iván Arcuschin, Thomas Kwa, Adrià Garriga-Alonso 2024-07-19T17:46:51Z 置信度 0.78 cs.LG
• Lightweight Neural Networks
  Most of the weights in a Lightweight Neural Network have a value of zero, while the remaining ones are either +1 or -1. These universal approximators require approximately 1.1 bits/weight of storage, posses a quick forward pass and achieve classification accur…
  arxiv Altaf H. Khan 2017-12-15T14:56:05Z 置信度 0.78 cs.LGcs.AIcs.CVcs.NE
• SONIC: A Sparse Neural Network Inference Accelerator with Silicon Photonics for Energy-Efficient Deep Learning
  Sparse neural networks can greatly facilitate the deployment of neural networks on resource-constrained platforms as they offer compact model sizes while retaining inference accuracy. Because of the sparsity in parameter matrices, sparse neural networks can, i…
  arxiv Febin Sunny, Mahdi Nikdast, Sudeep Pasricha 2021-09-09T17:57:09Z 置信度 0.78 cs.LGcs.ARcs.NE
• Gate-level boolean evolutionary geometric attention neural networks
  This paper presents a gate-level Boolean evolutionary geometric attention neural network that models images as Boolean fields governed by logic gates. Each pixel is a Boolean variable (0 or 1) embedded on a two-dimensional geometric manifold (for example, a di…
  arxiv Xianshuai Shi, Jianfeng Zhu, Leibo Liu 2025-11-11T11:53:36Z 置信度 0.78 cs.NEcs.AIcs.LG
• Feeder Load Balancing using Neural Network
  The distribution system problems, such as planning, loss minimization, and energy restoration, usually involve the phase balancing or network reconfiguration procedures. The determination of an optimal phase balance is, in general, a combinatorial optimization…
  arxiv A. Ukil, W. Siti, J. Jordaan 2015-03-20T06:48:14Z 置信度 0.78 cs.NE
• Development of input connections in neural cultures
  We introduce a novel approach for the quantitative assessment of the connectivity in neuronal cultures, based on the statistical mechanics of percolation on a graph. This allows us to follow the development of the culture and see the emergence of connectivity …
  arxiv Jordi Soriano, Maria Rodrriguez Martinez, Tsvi Tlusty, Elisha Moses 2010-07-31T07:28:39Z 置信度 0.78 cond-mat.dis-nnq-bio.NC
• Implicit recurrent networks: A novel approach to stationary input processing with recurrent neural networks in deep learning
  The brain cortex, which processes visual, auditory and sensory data in the brain, is known to have many recurrent connections within its layers and from higher to lower layers. But, in the case of machine learning with neural networks, it is generally assumed …
  arxiv Sebastian Sanokowski 2020-10-20T18:55:32Z 置信度 0.78 cs.LGcs.NE
• Under the Hood of Neural Networks: Characterizing Learned Representations by Functional Neuron Populations and Network Ablations
  The need for more transparency of the decision-making processes in artificial neural networks steadily increases driven by their applications in safety critical and ethically challenging domains such as autonomous driving or medical diagnostics. We address tod…
  arxiv Richard Meyes, Constantin Waubert de Puiseau, Andres Posada-Moreno, Tobias Meisen 2020-04-02T20:45:01Z 置信度 0.78 cs.NEcs.LGq-bio.NC
• Statistical Guarantees for Regularized Neural Networks
  Neural networks have become standard tools in the analysis of data, but they lack comprehensive mathematical theories. For example, there are very few statistical guarantees for learning neural networks from data, especially for classes of estimators that are …
  arxiv Mahsa Taheri, Fang Xie, Johannes Lederer 2020-05-30T15:28:47Z 置信度 0.78 cs.LGcs.NEmath.STstat.MEstat.ML
• Attacking Graph Neural Networks with Bit Flips: Weisfeiler and Lehman Go Indifferent
  Prior attacks on graph neural networks have mostly focused on graph poisoning and evasion, neglecting the network's weights and biases. Traditional weight-based fault injection attacks, such as bit flip attacks used for convolutional neural networks, do not co…
  arxiv Lorenz Kummer, Samir Moustafa, Nils N. Kriege, Wilfried N. Gansterer 2023-11-02T12:59:32Z 置信度 0.78 cs.LGcs.AIcs.CRcs.NE
• A continuum among logarithmic, linear, and exponential functions, and its potential to improve generalization in neural networks
  We present the soft exponential activation function for artificial neural networks that continuously interpolates between logarithmic, linear, and exponential functions. This activation function is simple, differentiable, and parameterized so that it can be tr…
  arxiv Luke B. Godfrey, Michael S. Gashler 2016-02-03T14:46:35Z 置信度 0.78 cs.NE
• Spatial and temporal correlations in neural networks with structured connectivity
  Correlated fluctuations in the activity of neural populations reflect the network's dynamics and connectivity. The temporal and spatial dimensions of neural correlations are interdependent. However, prior theoretical work mainly analyzed correlations in either…
  arxiv Yan-Liang Shi, Roxana Zeraati, Anna Levina, Tatiana A. Engel 2022-07-16T12:47:32Z 置信度 0.78 q-bio.NCcond-mat.dis-nncond-mat.stat-mech
• Sequence Training and Adaptation of Highway Deep Neural Networks
  Highway deep neural network (HDNN) is a type of depth-gated feedforward neural network, which has shown to be easier to train with more hidden layers and also generalise better compared to conventional plain deep neural networks (DNNs). Previously, we investig…
  arxiv Liang Lu 2016-07-07T11:24:51Z 置信度 0.78 cs.CLcs.LGcs.NE
• Spiking Neural Network for Intra-cortical Brain Signal Decoding
  Decoding brain signals accurately and efficiently is crucial for intra-cortical brain-computer interfaces. Traditional decoding approaches based on neural activity vector features suffer from low accuracy, whereas deep learning based approaches have high compu…
  arxiv Song Yang, Haotian Fu, Herui Zhang, Peng Zhang 等 2025-04-12T13:41:59Z 置信度 0.78 cs.HCcs.LGcs.NE
• Towards spiking analog hardware implementation of a trajectory interpolation mechanism for smooth closed-loop control of a spiking robot arm
  Neuromorphic engineering aims to incorporate the computational principles found in animal brains, into modern technological systems. Following this approach, in this work we propose a closed-loop neuromorphic control system for an event-based robotic arm. The …
  arxiv Daniel Casanueva-Morato, Chenxi Wu, Giacomo Indiveri, Juan P. Dominguez-Morales 等 2025-01-23T14:11:32Z 置信度 0.78 cs.NEcs.RO
• Neural Networks, Hypersurfaces, and Radon Transforms
  Connections between integration along hypersufaces, Radon transforms, and neural networks are exploited to highlight an integral geometric mathematical interpretation of neural networks. By analyzing the properties of neural networks as operators on probabilit…
  arxiv Soheil Kolouri, Xuwang Yin, Gustavo K. Rohde 2019-07-04T05:01:14Z 置信度 0.78 stat.MLcs.LG
• Data-aware customization of activation functions reduces neural network error
  Activation functions play critical roles in neural networks, yet current off-the-shelf neural networks pay little attention to the specific choice of activation functions used. Here we show that data-aware customization of activation functions can result in st…
  arxiv Fuchang Gao, Boyu Zhang 2023-01-16T23:38:37Z 置信度 0.78 cs.LGcs.NEstat.ML
• The Comparison of Methods Artificial Neural Network with Linear Regression Using Specific Variables for Prediction Stock Price in Tehran Stock Exchange
  In this paper, researchers estimated the stock price of activated companies in Tehran (Iran) stock exchange. It is used Linear Regression and Artificial Neural Network methods and compared these two methods. In Artificial Neural Network, of General Regression …
  arxiv Reza Gharoie Ahangar, Mahmood Yahyazadehfar, Hassan Pournaghshband 2010-03-07T12:05:22Z 置信度 0.78 cs.NE
• On Complex Valued Convolutional Neural Networks
  Convolutional neural networks (CNNs) are the cutting edge model for supervised machine learning in computer vision. In recent years CNNs have outperformed traditional approaches in many computer vision tasks such as object detection, image classification and f…
  arxiv Nitzan Guberman 2016-02-29T17:13:47Z 置信度 0.78 cs.NE
• On Feature Selection Using Anisotropic General Regression Neural Network
  The presence of irrelevant features in the input dataset tends to reduce the interpretability and predictive quality of machine learning models. Therefore, the development of feature selection methods to recognize irrelevant features is a crucial topic in mach…
  arxiv Federico Amato, Fabian Guignard, Philippe Jacquet, Mikhail Kanevski 2020-10-12T14:35:40Z 置信度 0.78 stat.MLcs.AIcs.LG
• Crafting Adversarial Input Sequences for Recurrent Neural Networks
  Machine learning models are frequently used to solve complex security problems, as well as to make decisions in sensitive situations like guiding autonomous vehicles or predicting financial market behaviors. Previous efforts have shown that numerous machine le…
  arxiv Nicolas Papernot, Patrick McDaniel, Ananthram Swami, Richard Harang 2016-04-28T00:35:32Z 置信度 0.78 cs.CRcs.LGcs.NE
• Evolving Neural Networks in Reinforcement Learning by means of UMDAc
  Neural networks are gaining popularity in the reinforcement learning field due to the vast number of successfully solved complex benchmark problems. In fact, artificial intelligence algorithms are, in some cases, able to overcome human professionals. Usually, …
  arxiv Mikel Malagon, Josu Ceberio 2019-04-24T17:12:42Z 置信度 0.78 cs.NEcs.LG
• Automatic Optimisation of Normalised Neural Networks
  We propose automatic optimisation methods considering the geometry of matrix manifold for the normalised parameters of neural networks. Layerwise weight normalisation with respect to Frobenius norm is utilised to bound the Lipschitz constant and to enhance gra…
  arxiv Namhoon Cho, Hyo-Sang Shin 2023-12-17T10:13:42Z 置信度 0.78 cs.LGcs.NEeess.SYmath.OC
• Generating Sequences With Recurrent Neural Networks
  This paper shows how Long Short-term Memory recurrent neural networks can be used to generate complex sequences with long-range structure, simply by predicting one data point at a time. The approach is demonstrated for text (where the data are discrete) and on…
  arxiv Alex Graves 2013-08-04T21:04:36Z 置信度 0.78 cs.NEcs.CL
• DeepFire2: A Convolutional Spiking Neural Network Accelerator on FPGAs
  Brain-inspired spiking neural networks (SNNs) replace the multiply-accumulate operations of traditional neural networks by integrate-and-fire neurons, with the goal of achieving greater energy efficiency. Specialized hardware implementations of those neurons c…
  arxiv Myat Thu Linn Aung, Daniel Gerlinghoff, Chuping Qu, Liwei Yang 等 2023-05-09T05:46:07Z 置信度 0.78 cs.NEcs.AIcs.AR
• Beltrami Flow and Neural Diffusion on Graphs
  We propose a novel class of graph neural networks based on the discretised Beltrami flow, a non-Euclidean diffusion PDE. In our model, node features are supplemented with positional encodings derived from the graph topology and jointly evolved by the Beltrami …
  arxiv Benjamin Paul Chamberlain, James Rowbottom, Davide Eynard, Francesco Di Giovanni 等 2021-10-18T16:23:38Z 置信度 0.78 cs.LGcs.AIstat.ML
• Neural Module Networks
  Visual question answering is fundamentally compositional in nature---a question like "where is the dog?" shares substructure with questions like "what color is the dog?" and "where is the cat?" This paper seeks to simultaneously exploit the representational ca…
  arxiv Jacob Andreas, Marcus Rohrbach, Trevor Darrell, Dan Klein 2015-11-09T18:48:39Z 置信度 0.78 cs.CVcs.CLcs.LGcs.NE
• Evolutionary Architecture Search for Graph Neural Networks
  Automated machine learning (AutoML) has seen a resurgence in interest with the boom of deep learning over the past decade. In particular, Neural Architecture Search (NAS) has seen significant attention throughout the AutoML research community, and has pushed f…
  arxiv Min Shi, David A. Wilson, Xingquan Zhu, Yu Huang 等 2020-09-21T22:11:53Z 置信度 0.78 cs.NE
• Integration of Neural Network-Based Symbolic Regression in Deep Learning for Scientific Discovery
  Symbolic regression is a powerful technique that can discover analytical equations that describe data, which can lead to explainable models and generalizability outside of the training data set. In contrast, neural networks have achieved amazing levels of accu…
  arxiv Samuel Kim, Peter Y. Lu, Srijon Mukherjee, Michael Gilbert 等 2019-12-10T17:07:52Z 置信度 0.78 cs.LGcs.NEphysics.data-anstat.ML
• The Power of Depth for Feedforward Neural Networks
  We show that there is a simple (approximately radial) function on $\reals^d$, expressible by a small 3-layer feedforward neural networks, which cannot be approximated by any 2-layer network, to more than a certain constant accuracy, unless its width is exponen…
  arxiv Ronen Eldan, Ohad Shamir 2015-12-12T21:41:24Z 置信度 0.78 cs.LGcs.NEstat.ML
• Efficient Scale Estimation Methods using Lightweight Deep Convolutional Neural Networks for Visual Tracking
  In recent years, visual tracking methods that are based on discriminative correlation filters (DCF) have been very promising. However, most of these methods suffer from a lack of robust scale estimation skills. Although a wide range of recent DCF-based methods…
  arxiv Seyed Mojtaba Marvasti-Zadeh, Hossein Ghanei-Yakhdan, Shohreh Kasaei 2020-04-06T18:49:37Z 置信度 0.78 cs.CVcs.LGeess.IV
• Feature interpretability in BCIs: exploring the role of network lateralization
  Brain-computer interfaces (BCIs) enable users to interact with the external world using brain activity. Despite their potential in neuroscience and industry, BCI performance remains inconsistent in noninvasive applications, often prioritizing algorithms that a…
  arxiv Juliana Gonzalez-Astudillo, Fabrizio De Vico Fallani 2024-07-16T11:27:39Z 置信度 0.78 q-bio.NC
• Rounding Methods for Neural Networks with Low Resolution Synaptic Weights
  Neural network algorithms simulated on standard computing platforms typically make use of high resolution weights, with floating-point notation. However, for dedicated hardware implementations of such algorithms, fixed-point synaptic weights with low resolutio…
  arxiv Lorenz K. Muller, Giacomo Indiveri 2015-04-22T12:47:32Z 置信度 0.78 cs.NE
• GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network
  The feature correlation layer serves as a key neural network module in numerous computer vision problems that involve dense correspondences between image pairs. It predicts a correspondence volume by evaluating dense scalar products between feature vectors ext…
  arxiv Prune Truong, Martin Danelljan, Luc Van Gool, Radu Timofte 2020-09-16T17:33:01Z 置信度 0.78 cs.CV
• Interpretable Convolutional Neural Networks via Feedforward Design
  The model parameters of convolutional neural networks (CNNs) are determined by backpropagation (BP). In this work, we propose an interpretable feedforward (FF) design without any BP as a reference. The FF design adopts a data-centric approach. It derives netwo…
  arxiv C. -C. Jay Kuo, Min Zhang, Siyang Li, Jiali Duan 等 2018-10-05T16:44:49Z 置信度 0.78 cs.CV
• Adaptive Intrusion Detection System Leveraging Dynamic Neural Models with Adversarial Learning for 5G/6G Networks
  Intrusion Detection Systems (IDS) are critical components in safeguarding 5G/6G networks from both internal and external cyber threats. While traditional IDS approaches rely heavily on signature-based methods, they struggle to detect novel and evolving attacks…
  arxiv Neha, Tarunpreet Bhatia 2025-12-11T13:40:37Z 置信度 0.78 cs.CRcs.LG