{"list":"other","total":79,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"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":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"1511.07289","title":"Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)","created":"2015-11-23","cited_by_count":1070},{"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":"1303.5778","title":"Speech Recognition with Deep Recurrent Neural Networks","created":"2013-03-22","cited_by_count":669},{"id":"1706.02515","title":"Self-Normalizing Neural Networks","created":"2017-06-08","cited_by_count":598},{"id":"1610.01145","title":"Error bounds for approximations with deep ReLU networks","created":"2016-10-03","cited_by_count":574},{"id":"1505.00853","title":"Empirical Evaluation of Rectified Activations in Convolutional Network","created":"2015-05-05","cited_by_count":519},{"id":"1812.05720","title":"Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem","created":"2018-12-13","cited_by_count":323},{"id":"1611.01491","title":"Understanding Deep Neural Networks with Rectified Linear Units","created":"2016-11-04","cited_by_count":257},{"id":"2002.10118","title":"Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks","created":"2020-02-24","cited_by_count":231},{"id":"1302.4389","title":"Maxout Networks","created":"2013-02-18","cited_by_count":187},{"id":"1908.08681","title":"Mish: A Self Regularized Non-Monotonic Activation Function","created":"2019-08-23","cited_by_count":141},{"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":"2005.00817","title":"A survey on modern trainable activation functions","created":"2020-05-02","cited_by_count":89},{"id":"1603.05201","title":"Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units","created":"2016-03-16","cited_by_count":86},{"id":"2004.01902","title":"Rational neural networks","created":"2020-04-04","cited_by_count":75},{"id":"1704.07483","title":"Continuously Differentiable Exponential Linear Units","created":"2017-04-24","cited_by_count":73},{"id":"2012.00641","title":"A Decade Survey of Content Based Image Retrieval using Deep Learning","created":"2020-11-23","cited_by_count":72},{"id":"1907.06732","title":"Pad\\'e Activation Units: End-to-end Learning of Flexible Activation Functions in Deep Networks","created":"2019-07-15","cited_by_count":67},{"id":"1412.6830","title":"Learning Activation Functions to Improve Deep Neural Networks","created":"2014-12-21","cited_by_count":63},{"id":"2003.10027","title":"Dynamic ReLU","created":"2020-03-22","cited_by_count":55},{"id":"1603.00391","title":"Noisy Activation Functions","created":"2016-03-01","cited_by_count":53},{"id":"1706.03301","title":"Neural networks and rational functions","created":"2017-06-11","cited_by_count":40},{"id":"1906.09529","title":"Learning Activation Functions: A new paradigm for understanding Neural Networks","created":"2019-06-23","cited_by_count":34},{"id":"1605.09332","title":"Parametric Exponential Linear Unit for Deep Convolutional Neural Networks","created":"2016-05-30","cited_by_count":32},{"id":"1911.01462","title":"Time/Accuracy Tradeoffs for Learning a ReLU with respect to Gaussian Marginals","created":"2019-11-04","cited_by_count":32},{"id":"1909.11015","title":"diffGrad: An Optimization Method for Convolutional Neural Networks","created":"2019-09-12","cited_by_count":29},{"id":"1512.07030","title":"Deep Learning with S-shaped Rectified Linear Activation Units","created":"2015-12-22","cited_by_count":26},{"id":"2010.09458","title":"Review and Comparison of Commonly Used Activation Functions for Deep Neural Networks","created":"2020-10-15","cited_by_count":21},{"id":"1801.09403","title":"Learning Combinations of Activation Functions","created":"2018-01-29","cited_by_count":20},{"id":"1802.08026","title":"Complex-valued Neural Networks with Non-parametric Activation Functions","created":"2018-02-22","cited_by_count":19},{"id":"1804.02763","title":"Comparison of non-linear activation functions for deep neural networks on MNIST classification task","created":"2018-04-08","cited_by_count":19},{"id":"1902.02771","title":"Impact of Fully Connected Layers on Performance of Convolutional Neural Networks for Image Classification","created":"2019-01-21","cited_by_count":19},{"id":"1804.02253","title":"A comparison of deep networks with ReLU activation function and linear spline-type methods","created":"2018-04-06","cited_by_count":18},{"id":"1808.00783","title":"The Quest for the Golden Activation Function","created":"2018-08-02","cited_by_count":14},{"id":"1605.05509","title":"Learning activation functions from data using cubic spline interpolation","created":"2016-05-18","cited_by_count":13},{"id":"1806.10064","title":"Adaptive Blending Units: Trainable Activation Functions for Deep Neural Networks","created":"2018-06-26","cited_by_count":13},{"id":"1905.10761","title":"ProbAct: A Probabilistic Activation Function for Deep Neural Networks","created":"2019-05-26","cited_by_count":12},{"id":"1909.05136","title":"PowerNet: Efficient Representations of Polynomials and Smooth Functions by Deep Neural Networks with Rectified Power Units","created":"2019-09-09","cited_by_count":12},{"id":"1602.05980","title":"Revise Saturated Activation Functions","created":"2016-02-18","cited_by_count":11},{"id":"1809.09534","title":"PLU: The Piecewise Linear Unit Activation Function","created":"2018-09-03","cited_by_count":11},{"id":"2002.07082","title":"PCSGAN: Perceptual Cyclic-Synthesized Generative Adversarial Networks for Thermal and NIR to Visible Image Transformation","created":"2020-02-13","cited_by_count":11},{"id":"1812.02566","title":"Singular Values for ReLU Layers","created":"2018-12-06","cited_by_count":10},{"id":"1902.03306","title":"A simple and efficient architecture for trainable activation functions","created":"2019-02-08","cited_by_count":10},{"id":"1901.02671","title":"Is it Time to Swish? Comparing Deep Learning Activation Functions Across NLP tasks","created":"2019-01-09","cited_by_count":9},{"id":"1901.05903","title":"A Performance Comparison of Loss Functions for Deep Face Recognition","created":"2019-01-01","cited_by_count":9},{"id":"1905.02473","title":"Ensemble of Convolutional Neural Networks Trained with Different Activation Functions","created":"2019-05-07","cited_by_count":9},{"id":"1901.03611","title":"The Benefits of Over-parameterization at Initialization in Deep ReLU Networks","created":"2019-01-11","cited_by_count":8},{"id":"1908.03682","title":"Natural-Logarithm-Rectified Activation Function in Convolutional Neural Networks","created":"2019-08-10","cited_by_count":8},{"id":"2003.00547","title":"Soft-Root-Sign Activation Function","created":"2020-03-01","cited_by_count":8},{"id":"1606.00305","title":"Improving Deep Neural Network with Multiple Parametric Exponential Linear Units","created":"2016-06-01","cited_by_count":6},{"id":"1801.07145","title":"E-swish: Adjusting Activations to Different Network Depths","created":"2018-01-22","cited_by_count":6},{"id":"1804.02051","title":"Average Biased ReLU Based CNN Descriptor for Improved Face Retrieval","created":"2018-04-02","cited_by_count":6},{"id":"1702.07790","title":"Activation Ensembles for Deep Neural Networks","created":"2017-02-24","cited_by_count":5},{"id":"1911.03925","title":"Symmetrical Gaussian Error Linear Units (SGELUs)","created":"2019-11-10","cited_by_count":5},{"id":"1604.00676","title":"Multi-Bias Non-linear Activation in Deep Neural Networks","created":"2016-04-03","cited_by_count":4},{"id":"1910.12259","title":"L*ReLU: Piece-wise Linear Activation Functions for Deep Fine-grained Visual Categorization","created":"2019-10-27","cited_by_count":4},{"id":"2011.05627","title":"Skin disease diagnosis with deep learning: a review","created":"2020-11-11","cited_by_count":4},{"id":"1602.01321","title":"A continuum among logarithmic, linear, and exponential functions, and its potential to improve generalization in neural networks","created":"2016-02-03","cited_by_count":3},{"id":"1707.08214","title":"Dual Rectified Linear Units (DReLUs): A Replacement for Tanh Activation Functions in Quasi-Recurrent Neural Networks","created":"2017-07-25","cited_by_count":3},{"id":"1710.11272","title":"Empirical analysis of non-linear activation functions for Deep Neural Networks in classification tasks","created":"2017-10-30","cited_by_count":3},{"id":"1812.06247","title":"Flatten-T Swish: a thresholded ReLU-Swish-like activation function for deep learning","created":"2018-12-15","cited_by_count":3},{"id":"1901.09849","title":"Activation Adaptation in Neural Networks","created":"2019-01-28","cited_by_count":3},{"id":"1710.01013","title":"Training Feedforward Neural Networks with Standard Logistic Activations is Feasible","created":"2017-10-03","cited_by_count":2},{"id":"1901.10232","title":"Multikernel activation functions: formulation and a case study","created":"2019-01-29","cited_by_count":2},{"id":"1709.06123","title":"A Probabilistic Framework for Nonlinearities in Stochastic Neural Networks","created":"2017-09-18","cited_by_count":1},{"id":"1805.08878","title":"ARiA: Utilizing Richard's Curve for Controlling the Non-monotonicity of the Activation Function in Deep Neural Nets","created":"2018-05-22","cited_by_count":1},{"id":"1901.05995","title":"Activation Functions for Generalized Learning Vector Quantization - A Performance Comparison","created":"2019-01-17","cited_by_count":1},{"id":"1902.02085","title":"Widely Linear Kernels for Complex-Valued Kernel Activation Functions","created":"2019-02-06","cited_by_count":1},{"id":"1912.12187","title":"Learning Neural Activations","created":"2019-12-27","cited_by_count":1}],"next_cursor":null}