{"list":"other","total":111,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"2008.02217","title":"Hopfield Networks is All You Need","created":"2020-07-16","cited_by_count":475},{"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":"1609.01596","title":"Direct Feedback Alignment Provides Learning in Deep Neural Networks","created":"2016-09-06","cited_by_count":240},{"id":"1701.01724","title":"DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker","created":"2017-01-06","cited_by_count":233},{"id":"1801.00631","title":"Deep Learning: A Critical Appraisal","created":"2018-01-02","cited_by_count":217},{"id":"1605.08104","title":"Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning","created":"2016-05-25","cited_by_count":204},{"id":"1412.7525","title":"Difference Target Propagation","created":"2014-12-23","cited_by_count":148},{"id":"2009.11162","title":"Implicit Gradient Regularization","created":"2020-09-23","cited_by_count":146},{"id":"2206.15378","title":"Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning","created":"2022-06-30","cited_by_count":131},{"id":"2008.06996","title":"Large Associative Memory Problem in Neurobiology and Machine Learning","created":"2020-08-16","cited_by_count":112},{"id":"1810.11393","title":"Dendritic cortical microcircuits approximate the backpropagation algorithm","created":"2018-10-26","cited_by_count":97},{"id":"2006.04182","title":"Predictive Coding Approximates Backprop along Arbitrary Computation Graphs","created":"2020-06-07","cited_by_count":90},{"id":"1407.7906","title":"How Auto-Encoders Could Provide Credit Assignment in Deep Networks via Target Propagation","created":"2014-07-29","cited_by_count":79},{"id":"2107.12979","title":"Predictive Coding: a Theoretical and Experimental Review","created":"2021-07-27","cited_by_count":77},{"id":"1704.08863","title":"On weight initialization in deep neural networks","created":"2017-04-28","cited_by_count":67},{"id":"1502.04156","title":"Towards Biologically Plausible Deep Learning","created":"2015-02-14","cited_by_count":66},{"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":"2006.01981","title":"Training End-to-End Analog Neural Networks with Equilibrium Propagation","created":"2020-06-02","cited_by_count":63},{"id":"2201.11665","title":"Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass","created":"2022-01-27","cited_by_count":63},{"id":"1510.05067","title":"How Important is Weight Symmetry in Backpropagation?","created":"2015-10-17","cited_by_count":58},{"id":"2006.14331","title":"A Theoretical Framework for Target Propagation","created":"2020-06-25","cited_by_count":57},{"id":"2006.12878","title":"Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures","created":"2020-06-23","cited_by_count":56},{"id":"2202.04557","title":"Universal Hopfield Networks: A General Framework for Single-Shot Associative Memory Models","created":"2022-02-09","cited_by_count":55},{"id":"2112.01871","title":"Active Inference in Robotics and Artificial Agents: Survey and Challenges","created":"2021-12-03","cited_by_count":52},{"id":"2202.09467","title":"Predictive Coding: Towards a Future of Deep Learning beyond Backpropagation?","created":"2022-02-18","cited_by_count":45},{"id":"2012.03405","title":"The Neural Coding Framework for Learning Generative Models","created":"2020-12-07","cited_by_count":44},{"id":"2109.08063","title":"Associative Memories via Predictive Coding","created":"2021-09-16","cited_by_count":44},{"id":"1805.11703","title":"Biologically Motivated Algorithms for Propagating Local Target Representations","created":"2018-05-26","cited_by_count":43},{"id":"2209.00530","title":"Holomorphic Equilibrium Propagation Computes Exact Gradients Through Finite Size Oscillations","created":"2022-09-01","cited_by_count":42},{"id":"1807.04489","title":"Fast yet Simple Natural-Gradient Descent for Variational Inference in Complex Models","created":"2018-07-12","cited_by_count":38},{"id":"1811.03567","title":"Biologically-plausible learning algorithms can scale to large datasets","created":"2018-11-08","cited_by_count":37},{"id":"2301.05832","title":"World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges","created":"2023-01-14","cited_by_count":36},{"id":"2301.01452","title":"The Predictive Forward-Forward Algorithm","created":"2023-01-04","cited_by_count":35},{"id":"2201.13415","title":"Towards Scaling Difference Target Propagation by Learning Backprop Targets","created":"2022-01-31","cited_by_count":34},{"id":"2201.13180","title":"Learning on Arbitrary Graph Topologies via Predictive Coding","created":"2022-01-31","cited_by_count":33},{"id":"1711.08416","title":"Equivalence of Equilibrium Propagation and Recurrent Backpropagation","created":"2017-11-22","cited_by_count":32},{"id":"1810.07411","title":"Continual Learning of Recurrent Neural Networks by Locally Aligning Distributed Representations","created":"2018-10-17","cited_by_count":32},{"id":"1812.06488","title":"Feedback alignment in deep convolutional networks","created":"2018-12-12","cited_by_count":31},{"id":"2001.03241","title":"Network Geometry","created":"2020-01-09","cited_by_count":31},{"id":"2010.07859","title":"EqSpike: Spike-driven Equilibrium Propagation for Neuromorphic Implementations","created":"2020-10-15","cited_by_count":31},{"id":"2204.02169","title":"Hybrid Predictive Coding: Inferring, Fast and Slow","created":"2022-04-05","cited_by_count":26},{"id":"2205.03076","title":"Beyond backpropagation: bilevel optimization through implicit differentiation and equilibrium propagation","created":"2022-05-06","cited_by_count":26},{"id":"2206.02629","title":"Backpropagation at the Infinitesimal Inference Limit of Energy-Based Models: Unifying Predictive Coding, Equilibrium Propagation, and Contrastive Hebbian Learning","created":"2022-05-31","cited_by_count":26},{"id":"1805.07526","title":"Deep Predictive Coding Network with Local Recurrent Processing for Object Recognition","created":"2018-05-19","cited_by_count":25},{"id":"2204.01723","title":"Signal Propagation: A Framework for Learning and Inference In a Forward Pass","created":"2022-04-04","cited_by_count":24},{"id":"1808.04873","title":"Generalization of Equilibrium Propagation to Vector Field Dynamics","created":"2018-08-14","cited_by_count":23},{"id":"2103.04689","title":"Reverse Differentiation via Predictive Coding","created":"2021-03-08","cited_by_count":23},{"id":"2212.01354","title":"Designing Ecosystems of Intelligence from First Principles","created":"2022-12-02","cited_by_count":23},{"id":"2011.07464","title":"Predictive Coding, Variational Autoencoders, and Biological Connections","created":"2020-11-15","cited_by_count":21},{"id":"2106.13082","title":"On the relationship between predictive coding and backpropagation","created":"2021-06-20","cited_by_count":20},{"id":"2106.02749","title":"Predify: Augmenting deep neural networks with brain-inspired predictive coding dynamics","created":"2021-06-04","cited_by_count":19},{"id":"1908.08655","title":"Spiking Neural Predictive Coding for Continual Learning from Data Streams","created":"2019-08-23","cited_by_count":17},{"id":"2111.06862","title":"Silicon Photonic Architecture for Training Deep Neural Networks with Direct Feedback Alignment","created":"2021-11-12","cited_by_count":17},{"id":"2206.00164","title":"A Theoretical Framework for Inference Learning","created":"2022-06-01","cited_by_count":17},{"id":"2207.12316","title":"A Theoretical Framework for Inference and Learning in Predictive Coding Networks","created":"2022-07-21","cited_by_count":17},{"id":"1905.10696","title":"Lifelong Neural Predictive Coding: Learning Cumulatively Online without Forgetting","created":"2019-05-25","cited_by_count":15},{"id":"2002.06015","title":"Scalable and Practical Natural Gradient for Large-Scale Deep Learning","created":"2020-02-13","cited_by_count":15},{"id":"2205.09930","title":"BayesPCN: A Continually Learnable Predictive Coding Associative Memory","created":"2022-05-20","cited_by_count":14},{"id":"1301.3541","title":"Deep Predictive Coding Networks","created":"2013-01-16","cited_by_count":13},{"id":"1805.03104","title":"Adaptive robot body learning and estimation through predictive coding","created":"2018-05-08","cited_by_count":13},{"id":"2103.08953","title":"Training Dynamical Binary Neural Networks with Equilibrium Propagation","created":"2021-03-16","cited_by_count":13},{"id":"2305.13562","title":"Understanding and Improving Optimization in Predictive Coding Networks","created":"2023-05-23","cited_by_count":13},{"id":"1711.11542","title":"Learning to Adapt by Minimizing Discrepancy","created":"2017-11-30","cited_by_count":12},{"id":"2107.07046","title":"Backprop-Free Reinforcement Learning with Active Neural Generative Coding","created":"2021-07-10","cited_by_count":12},{"id":"2205.05303","title":"Dendritic predictive coding: A theory of cortical computation with spiking neurons","created":"2022-05-11","cited_by_count":12},{"id":"2210.08122","title":"Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again","created":"2022-10-14","cited_by_count":11},{"id":"1804.11313","title":"How Robust are Deep Neural Networks?","created":"2018-04-30","cited_by_count":10},{"id":"2005.02181","title":"A neural network walks into a lab: towards using deep nets as models for human behavior","created":"2020-05-02","cited_by_count":10},{"id":"2012.06373","title":"Hardware Beyond Backpropagation: a Photonic Co-Processor for Direct Feedback Alignment","created":"2020-12-11","cited_by_count":10},{"id":"2210.13461","title":"Active Predictive Coding: A Unified Neural Framework for Learning Hierarchical World Models for Perception and Planning","created":"2022-10-23","cited_by_count":10},{"id":"2211.12047","title":"Convolutional Neural Generative Coding: Scaling Predictive Coding to Natural Images","created":"2022-11-22","cited_by_count":10},{"id":"2106.13300","title":"Continual Competitive Memory: A Neural System for Online Task-Free Lifelong Learning","created":"2021-06-24","cited_by_count":8},{"id":"2304.02658","title":"Predictive Coding as a Neuromorphic Alternative to Backpropagation: A Critical Evaluation","created":"2023-04-05","cited_by_count":8},{"id":"2201.08813","title":"Active Predictive Coding Networks: A Neural Solution to the Problem of Learning Reference Frames and Part-Whole Hierarchies","created":"2022-01-14","cited_by_count":6},{"id":"2209.09174","title":"Active Predicting Coding: Brain-Inspired Reinforcement Learning for Sparse Reward Robotic Control Problems","created":"2022-09-19","cited_by_count":6},{"id":"2212.10352","title":"Fixed-Weight Difference Target Propagation","created":"2022-12-19","cited_by_count":6},{"id":"2306.15479","title":"Predictive Coding beyond Correlations","created":"2023-06-27","cited_by_count":6},{"id":"1702.04770","title":"Training Language Models Using Target-Propagation","created":"2017-02-15","cited_by_count":5},{"id":"2104.15137","title":"Tightening the Biological Constraints on Gradient-Based Predictive Coding","created":"2021-04-30","cited_by_count":5},{"id":"2109.04602","title":"Augmenting BERT-style Models with Predictive Coding to Improve Discourse-level Representations","created":"2021-09-10","cited_by_count":5},{"id":"2208.07114","title":"Preventing Deterioration of Classification Accuracy in Predictive Coding Networks","created":"2022-08-15","cited_by_count":5},{"id":"2212.04656","title":"Robust Graph Representation Learning via Predictive Coding","created":"2022-12-09","cited_by_count":5}],"next_cursor":"100"}