{"list":"other","total":56,"rows":[{"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":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1902.09229","title":"A Theoretical Analysis of Contrastive Unsupervised Representation Learning","created":"2019-02-25","cited_by_count":530},{"id":"1409.5185","title":"Deeply-Supervised Nets","created":"2014-09-18","cited_by_count":367},{"id":"1905.11881","title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","created":"2019-05-28","cited_by_count":341},{"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":"1412.7525","title":"Difference Target Propagation","created":"2014-12-23","cited_by_count":148},{"id":"1608.05343","title":"Decoupled Neural Interfaces using Synthetic Gradients","created":"2016-08-18","cited_by_count":137},{"id":"1901.06656","title":"Training Neural Networks with Local Error Signals","created":"2019-01-20","cited_by_count":136},{"id":"1812.11446","title":"Greedy Layerwise Learning Can Scale to ImageNet","created":"2018-12-29","cited_by_count":115},{"id":"1807.04587","title":"Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures","created":"2018-07-12","cited_by_count":101},{"id":"1905.11786","title":"Putting An End to End-to-End: Gradient-Isolated Learning of Representations","created":"2019-05-28","cited_by_count":86},{"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":"1901.08164","title":"Decoupled Greedy Learning of CNNs","created":"2019-01-23","cited_by_count":78},{"id":"1908.01580","title":"The HSIC Bottleneck: Deep Learning without Back-Propagation","created":"2019-08-05","cited_by_count":77},{"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":"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":"1806.10181","title":"Unsupervised Learning by Competing Hidden Units","created":"2018-06-26","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":"1711.06756","title":"Deep supervised learning using local errors","created":"2017-11-17","cited_by_count":41},{"id":"1803.00225","title":"Global Convergence of Block Coordinate Descent in Deep Learning","created":"2018-03-01","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":"1703.00522","title":"Understanding Synthetic Gradients and Decoupled Neural Interfaces","created":"2017-03-01","cited_by_count":35},{"id":"1706.04964","title":"Learning Deep ResNet Blocks Sequentially using Boosting Theory","created":"2017-06-15","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":"1906.00889","title":"Learning to solve the credit assignment problem","created":"2019-06-03","cited_by_count":27},{"id":"1711.07354","title":"Convergent Block Coordinate Descent for Training Tikhonov Regularized Deep Neural Networks","created":"2017-11-20","cited_by_count":26},{"id":"1910.01526","title":"Gated Linear Networks","created":"2019-09-30","cited_by_count":26},{"id":"2006.07123","title":"Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks","created":"2020-06-12","cited_by_count":25},{"id":"1806.09077","title":"Beyond Backprop: Online Alternating Minimization with Auxiliary Variables","created":"2018-06-24","cited_by_count":23},{"id":"1906.04554","title":"Principled Training of Neural Networks with Direct Feedback Alignment","created":"2019-06-11","cited_by_count":23},{"id":"1904.11717","title":"Classification from Pairwise Similarities/Dissimilarities and Unlabeled Data via Empirical Risk Minimization","created":"2019-04-26","cited_by_count":21},{"id":"1703.07914","title":"Why do similarity matching objectives lead to Hebbian/anti-Hebbian networks?","created":"2017-03-23","cited_by_count":20},{"id":"1803.09522","title":"A Provably Correct Algorithm for Deep Learning that Actually Works","created":"2018-03-26","cited_by_count":20},{"id":"1805.01532","title":"Lifted Neural Networks","created":"2018-05-03","cited_by_count":20},{"id":"1811.08039","title":"Fenchel Lifted Networks: A Lagrange Relaxation of Neural Network Training","created":"2018-11-20","cited_by_count":19},{"id":"2003.01513","title":"Two Routes to Scalable Credit Assignment without Weight Symmetry","created":"2020-02-28","cited_by_count":19},{"id":"2010.04116","title":"Interlocking Backpropagation: Improving depthwise model-parallelism","created":"2020-10-08","cited_by_count":17},{"id":"1803.09082","title":"A Proximal Block Coordinate Descent Algorithm for Deep Neural Network Training","created":"2018-03-24","cited_by_count":15},{"id":"2007.15139","title":"Deriving Differential Target Propagation from Iterating Approximate Inverses","created":"2020-07-29","cited_by_count":15},{"id":"1811.01501","title":"Lifted Proximal Operator Machines","created":"2018-11-05","cited_by_count":14},{"id":"1411.6191","title":"Kickback cuts Backprop's red-tape: Biologically plausible credit assignment in neural networks","created":"2014-11-23","cited_by_count":11},{"id":"2007.05112","title":"Biological credit assignment through dynamic inversion of feedforward networks","created":"2020-07-10","cited_by_count":11},{"id":"1910.01689","title":"Spike-based causal inference for weight alignment","created":"2019-10-03","cited_by_count":10},{"id":"1910.04958","title":"Structured and Deep Similarity Matching via Structured and Deep Hebbian Networks","created":"2019-10-11","cited_by_count":9},{"id":"2005.05541","title":"Modularizing Deep Learning via Pairwise Learning With Kernels","created":"2020-05-12","cited_by_count":7},{"id":"2002.07720","title":"Local Propagation in Constraint-based Neural Network","created":"2020-02-18","cited_by_count":5},{"id":"1802.03774","title":"On Kernel Method-Based Connectionist Models and Supervised Deep Learning Without Backpropagation","created":"2018-02-11","cited_by_count":4},{"id":"1605.09114","title":"ParMAC: distributed optimisation of nested functions, with application to learning binary autoencoders","created":"2016-05-30","cited_by_count":2}],"next_cursor":null}