{"list":"other","total":78,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"1511.07289","title":"Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)","created":"2015-11-23","cited_by_count":1070},{"id":"1412.6806","title":"Striving for Simplicity: The All Convolutional Net","created":"2014-12-21","cited_by_count":990},{"id":"1702.03118","title":"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning","created":"2017-02-10","cited_by_count":950},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"1704.05796","title":"Network Dissection: Quantifying Interpretability of Deep Visual Representations","created":"2017-04-19","cited_by_count":708},{"id":"1704.03296","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","created":"2017-04-11","cited_by_count":612},{"id":"1703.03864","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","created":"2017-03-10","cited_by_count":574},{"id":"1710.05006","title":"Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)","created":"2017-10-13","cited_by_count":549},{"id":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"2102.06171","title":"High-Performance Large-Scale Image Recognition Without Normalization","created":"2021-02-11","cited_by_count":360},{"id":"2007.05785","title":"Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks","created":"2020-07-11","cited_by_count":345},{"id":"2212.13345","title":"The Forward-Forward Algorithm: Some Preliminary Investigations","created":"2022-12-27","cited_by_count":266},{"id":"1602.05179","title":"Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation","created":"2016-02-16","cited_by_count":259},{"id":"2109.12894","title":"Training Spiking Neural Networks Using Lessons From Deep Learning","created":"2021-09-27","cited_by_count":259},{"id":"1512.02479","title":"Explaining NonLinear Classification Decisions with Deep Taylor Decomposition","created":"2015-12-08","cited_by_count":250},{"id":"1609.01596","title":"Direct Feedback Alignment Provides Learning in Deep Neural Networks","created":"2016-09-06","cited_by_count":240},{"id":"1908.02288","title":"BCN20000: Dermoscopic Lesions in the Wild","created":"2019-08-06","cited_by_count":225},{"id":"1708.07120","title":"Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates","created":"2017-08-23","cited_by_count":199},{"id":"2211.10154","title":"CRAFT: Concept Recursive Activation FacTorization for Explainability","created":"2022-11-17","cited_by_count":178},{"id":"1702.04595","title":"Visualizing Deep Neural Network Decisions: Prediction Difference Analysis","created":"2017-02-15","cited_by_count":166},{"id":"1712.06567","title":"Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning","created":"2017-12-18","cited_by_count":150},{"id":"1412.7525","title":"Difference Target Propagation","created":"2014-12-23","cited_by_count":148},{"id":"2206.03208","title":"From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation","created":"2022-06-07","cited_by_count":141},{"id":"1706.05350","title":"L2 Regularization versus Batch and Weight Normalization","created":"2017-06-16","cited_by_count":124},{"id":"2006.15417","title":"Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation Vectors","created":"2020-06-27","cited_by_count":120},{"id":"1812.10025","title":"Attention Branch Network: Learning of Attention Mechanism for Visual Explanation","created":"2018-12-25","cited_by_count":109},{"id":"1807.04587","title":"Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures","created":"2018-07-12","cited_by_count":101},{"id":"1912.08881","title":"Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning","created":"2019-12-18","cited_by_count":89},{"id":"1904.02323","title":"Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizations","created":"2019-04-04","cited_by_count":72},{"id":"1910.09840","title":"Towards Best Practice in Explaining Neural Network Decisions with LRP","created":"2019-10-22","cited_by_count":70},{"id":"2006.03824","title":"Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing its Gradient Estimator Bias","created":"2020-06-06","cited_by_count":64},{"id":"1605.02026","title":"Training Neural Networks Without Gradients: A Scalable ADMM Approach","created":"2016-05-06","cited_by_count":61},{"id":"2209.11883","title":"Hebbian Deep Learning Without Feedback","created":"2022-09-23","cited_by_count":61},{"id":"2007.08790","title":"Explanation-Guided Training for Cross-Domain Few-Shot Classification","created":"2020-07-17","cited_by_count":58},{"id":"2106.13200","title":"Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy","created":"2021-06-24","cited_by_count":55},{"id":"2301.11911","title":"Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees","created":"2023-01-27","cited_by_count":50},{"id":"1803.00225","title":"Global Convergence of Block Coordinate Descent in Deep Learning","created":"2018-03-01","cited_by_count":38},{"id":"2201.13415","title":"Towards Scaling Difference Target Propagation by Learning Backprop Targets","created":"2022-01-31","cited_by_count":34},{"id":"1905.13633","title":"Updates of Equilibrium Prop Match Gradients of Backprop Through Time in an RNN with Static Input","created":"2019-05-31","cited_by_count":33},{"id":"2010.07859","title":"EqSpike: Spike-driven Equilibrium Propagation for Neuromorphic Implementations","created":"2020-10-15","cited_by_count":31},{"id":"2112.11407","title":"Toward Explainable AI for Regression Models","created":"2021-12-21","cited_by_count":31},{"id":"2305.18321","title":"Training an Ising Machine with Equilibrium Propagation","created":"2023-05-22","cited_by_count":29},{"id":"2306.06805","title":"Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization","created":"2023-06-11","cited_by_count":27},{"id":"1905.13611","title":"ADMM for Efficient Deep Learning with Global Convergence","created":"2019-05-31","cited_by_count":20},{"id":"1705.09132","title":"First-spike based visual categorization using reward-modulated STDP","created":"2017-05-25","cited_by_count":19},{"id":"2107.01729","title":"Hebbian learning with gradients: Hebbian convolutional neural networks with modern deep learning frameworks","created":"2021-07-04","cited_by_count":19},{"id":"2002.10438","title":"xAI-GAN: Enhancing Generative Adversarial Networks via Explainable AI Systems","created":"2020-02-24","cited_by_count":18},{"id":"2008.09072","title":"Utilizing Explainable AI for Quantization and Pruning of Deep Neural Networks","created":"2020-08-20","cited_by_count":17},{"id":"2109.04236","title":"ECQ$^{\\text{x}}$: Explainability-Driven Quantization for Low-Bit and Sparse DNNs","created":"2021-09-09","cited_by_count":15},{"id":"2003.13268","title":"Architecture Disentanglement for Deep Neural Networks","created":"2020-03-30","cited_by_count":10},{"id":"1509.05936","title":"STDP as presynaptic activity times rate of change of postsynaptic activity","created":"2015-09-19","cited_by_count":9},{"id":"1806.07406","title":"Contrastive Hebbian Learning with Random Feedback Weights","created":"2018-06-19","cited_by_count":8},{"id":"2008.09388","title":"CDE-GAN: Cooperative Dual Evolution Based Generative Adversarial Network","created":"2020-08-21","cited_by_count":8},{"id":"1805.09092","title":"Excitation Dropout: Encouraging Plasticity in Deep Neural Networks","created":"2018-05-23","cited_by_count":7},{"id":"2205.01929","title":"Explain to Not Forget: Defending Against Catastrophic Forgetting with XAI","created":"2022-05-04","cited_by_count":7},{"id":"2202.06621","title":"Measurably Stronger Explanation Reliability via Model Canonization","created":"2022-02-14","cited_by_count":6},{"id":"1811.04187","title":"Accelerated Gradient-free Neural Network Training by Multi-convex Alternating Optimization","created":"2018-11-10","cited_by_count":5},{"id":"2005.05955","title":"RSO: A Gradient Free Sampling Based Approach For Training Deep Neural Networks","created":"2020-05-12","cited_by_count":5},{"id":"1505.04150","title":"Reinforcement Learning applied to Single Neuron","created":"2015-05-15","cited_by_count":2},{"id":"2008.07513","title":"Notes on Worst-case Inefficiency of Gradient Descent Even in R^2","created":"2020-08-17","cited_by_count":1}],"next_cursor":null}