{"list":"other","total":56,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"1807.03039","title":"Glow: Generative Flow with Invertible 1x1 Convolutions","created":"2018-07-09","cited_by_count":1545},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"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":"1312.6120","title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","created":"2013-12-20","cited_by_count":763},{"id":"1706.02515","title":"Self-Normalizing Neural Networks","created":"2017-06-08","cited_by_count":598},{"id":"1511.00363","title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","created":"2015-11-02","cited_by_count":592},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"1602.07868","title":"Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks","created":"2016-02-25","cited_by_count":543},{"id":"1711.00489","title":"Don't Decay the Learning Rate, Increase the Batch Size","created":"2017-11-01","cited_by_count":320},{"id":"1711.04623","title":"Three Factors Influencing Minima in SGD","created":"2017-11-13","cited_by_count":273},{"id":"2003.04887","title":"ReZero is All You Need: Fast Convergence at Large Depth","created":"2020-03-10","cited_by_count":264},{"id":"1610.08914","title":"Ex Machina: Personal Attacks Seen at Scale","created":"2016-10-27","cited_by_count":210},{"id":"1901.09321","title":"Fixup Initialization: Residual Learning Without Normalization","created":"2019-01-27","cited_by_count":198},{"id":"1806.05393","title":"Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks","created":"2018-06-14","cited_by_count":176},{"id":"1703.00512","title":"PMLB: A Large Benchmark Suite for Machine Learning Evaluation and Comparison","created":"2017-03-01","cited_by_count":140},{"id":"1711.04735","title":"Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice","created":"2017-11-13","cited_by_count":132},{"id":"1811.03378","title":"Activation Functions: Comparison of trends in Practice and Research for Deep Learning","created":"2018-11-08","cited_by_count":130},{"id":"1511.06422","title":"All you need is a good init","created":"2015-11-19","cited_by_count":124},{"id":"1803.01719","title":"How to Start Training: The Effect of Initialization and Architecture","created":"2018-03-05","cited_by_count":109},{"id":"1703.00548","title":"Evolving Deep Neural Networks","created":"2017-03-01","cited_by_count":95},{"id":"1801.03744","title":"Which Neural Net Architectures Give Rise To Exploding and Vanishing Gradients?","created":"2018-01-11","cited_by_count":94},{"id":"2005.00817","title":"A survey on modern trainable activation functions","created":"2020-05-02","cited_by_count":89},{"id":"2006.14536","title":"Smooth Adversarial Training","created":"2020-06-25","cited_by_count":89},{"id":"2101.08692","title":"Characterizing signal propagation to close the performance gap in unnormalized ResNets","created":"2021-01-21","cited_by_count":88},{"id":"2001.05992","title":"Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear Networks","created":"2020-01-16","cited_by_count":73},{"id":"1905.01392","title":"A Survey on Neural Architecture Search","created":"2019-05-04","cited_by_count":71},{"id":"1905.13214","title":"On Network Design Spaces for Visual Recognition","created":"2019-05-30","cited_by_count":68},{"id":"1806.05394","title":"Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks","created":"2018-06-14","cited_by_count":45},{"id":"2004.02967","title":"Evolving Normalization-Activation Layers","created":"2020-04-06","cited_by_count":45},{"id":"2102.08098","title":"GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training","created":"2021-02-16","cited_by_count":44},{"id":"1906.02341","title":"How to Initialize your Network? Robust Initialization for WeightNorm & ResNets","created":"2019-06-05","cited_by_count":36},{"id":"1511.06856","title":"Data-dependent Initializations of Convolutional Neural Networks","created":"2015-11-21","cited_by_count":29},{"id":"2006.03179","title":"Discovering Parametric Activation Functions","created":"2020-06-05","cited_by_count":22},{"id":"1902.06827","title":"Evolutionary Neural AutoML for Deep Learning","created":"2019-02-18","cited_by_count":20},{"id":"2002.07224","title":"Evolutionary Optimization of Deep Learning Activation Functions","created":"2020-02-17","cited_by_count":18},{"id":"1808.00783","title":"The Quest for the Golden Activation Function","created":"2018-08-02","cited_by_count":14},{"id":"1709.02956","title":"Deep Residual Networks and Weight Initialization","created":"2017-09-09","cited_by_count":12}],"next_cursor":null}