{"list":"other","total":77,"rows":[{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1806.07366","title":"Neural Ordinary Differential Equations","created":"2018-06-19","cited_by_count":3779},{"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":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1511.07289","title":"Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)","created":"2015-11-23","cited_by_count":1070},{"id":"1502.05767","title":"Automatic differentiation in machine learning: a survey","created":"2015-02-20","cited_by_count":855},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"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":"1606.06160","title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients","created":"2016-06-20","cited_by_count":569},{"id":"1505.00853","title":"Empirical Evaluation of Rectified Activations in Convolutional Network","created":"2015-05-05","cited_by_count":519},{"id":"1805.06085","title":"PACT: Parameterized Clipping Activation for Quantized Neural Networks","created":"2018-05-16","cited_by_count":467},{"id":"1511.06464","title":"Unitary Evolution Recurrent Neural Networks","created":"2015-11-20","cited_by_count":294},{"id":"1702.03044","title":"Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights","created":"2017-02-10","cited_by_count":217},{"id":"2006.00719","title":"ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning","created":"2020-06-01","cited_by_count":202},{"id":"1302.4389","title":"Maxout Networks","created":"2013-02-18","cited_by_count":187},{"id":"1612.08544","title":"Theory-guided Data Science: A New Paradigm for Scientific Discovery from Data","created":"2016-12-27","cited_by_count":171},{"id":"1908.08681","title":"Mish: A Self Regularized Non-Monotonic Activation Function","created":"2019-08-23","cited_by_count":141},{"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":"1702.00953","title":"Deep Learning with Low Precision by Half-wave Gaussian Quantization","created":"2017-02-03","cited_by_count":117},{"id":"2104.10013","title":"Parallel Physics-Informed Neural Networks via Domain Decomposition","created":"2021-04-20","cited_by_count":112},{"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":"1808.08952","title":"Deep Learning of Vortex Induced Vibrations","created":"2018-08-26","cited_by_count":76},{"id":"2202.11821","title":"Physics-informed neural networks for inverse problems in supersonic flows","created":"2022-02-23","cited_by_count":76},{"id":"1704.07483","title":"Continuously Differentiable Exponential Linear Units","created":"2017-04-24","cited_by_count":73},{"id":"1412.6830","title":"Learning Activation Functions to Improve Deep Neural Networks","created":"2014-12-21","cited_by_count":63},{"id":"1505.03654","title":"Neural Network with Unbounded Activation Functions is Universal Approximator","created":"2015-05-14","cited_by_count":63},{"id":"2203.09346","title":"Error estimates for physics informed neural networks approximating the Navier-Stokes equations","created":"2022-03-17","cited_by_count":63},{"id":"2109.09444","title":"When Do Extended Physics-Informed Neural Networks (XPINNs) Improve Generalization?","created":"2021-09-20","cited_by_count":58},{"id":"1603.00391","title":"Noisy Activation Functions","created":"2016-03-01","cited_by_count":53},{"id":"1709.01134","title":"WRPN: Wide Reduced-Precision Networks","created":"2017-09-04","cited_by_count":51},{"id":"2105.09513","title":"Deep Kronecker neural networks: A general framework for neural networks with adaptive activation functions","created":"2021-05-20","cited_by_count":49},{"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":"1707.00070","title":"Better than Real: Complex-valued Neural Nets for MRI Fingerprinting","created":"2017-07-01","cited_by_count":30},{"id":"1512.07030","title":"Deep Learning with S-shaped Rectified Linear Activation Units","created":"2015-12-22","cited_by_count":26},{"id":"1602.09046","title":"On Complex Valued Convolutional Neural Networks","created":"2016-02-29","cited_by_count":26},{"id":"2006.03179","title":"Discovering Parametric Activation Functions","created":"2020-06-05","cited_by_count":22},{"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":"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":"1807.06714","title":"Defend Deep Neural Networks Against Adversarial Examples via Fixed and Dynamic Quantized Activation Functions","created":"2018-07-18","cited_by_count":17},{"id":"1808.00783","title":"The Quest for the Golden Activation Function","created":"2018-08-02","cited_by_count":14},{"id":"1806.10064","title":"Adaptive Blending Units: Trainable Activation Functions for Deep Neural Networks","created":"2018-06-26","cited_by_count":13},{"id":"2108.12943","title":"Growing Cosine Unit: A Novel Oscillatory Activation Function That Can Speedup Training and Reduce Parameters in Convolutional Neural Networks","created":"2021-08-30","cited_by_count":13},{"id":"1604.04112","title":"Deep Residual Networks with Exponential Linear Unit","created":"2016-04-14","cited_by_count":12},{"id":"1905.10761","title":"ProbAct: A Probabilistic Activation Function for Deep Neural Networks","created":"2019-05-26","cited_by_count":12},{"id":"1902.03306","title":"A simple and efficient architecture for trainable activation functions","created":"2019-02-08","cited_by_count":10},{"id":"1607.02241","title":"Overcoming Challenges in Fixed Point Training of Deep Convolutional Networks","created":"2016-07-08","cited_by_count":9},{"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":"1901.05894","title":"LiSHT: Non-Parametric Linearly Scaled Hyperbolic Tangent Activation Function for Neural Networks","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":"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":"2207.04889","title":"Linear Leaky-Integrate-and-Fire Neuron Model Based Spiking Neural Networks and Its Mapping Relationship to Deep Neural Networks","created":"2022-05-31","cited_by_count":8},{"id":"1405.2262","title":"Training Deep Fourier Neural Networks To Fit Time-Series Data","created":"2014-05-09","cited_by_count":7},{"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":"2206.12089","title":"Evolution of Activation Functions for Deep Learning-Based Image Classification","created":"2022-06-24","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":"1312.6116","title":"Improving Deep Neural Networks with Probabilistic Maxout Units","created":"2013-12-20","cited_by_count":4},{"id":"1603.05145","title":"Suppressing the Unusual: towards Robust CNNs using Symmetric Activation Functions","created":"2016-03-16","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":"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":"1711.11059","title":"Gaussian Process Neurons Learn Stochastic Activation Functions","created":"2017-11-29","cited_by_count":3},{"id":"2011.03842","title":"Universal Activation Function For Machine Learning","created":"2020-11-07","cited_by_count":3},{"id":"1706.03609","title":"Noisy Softplus: an activation function that enables SNNs to be trained as ANNs","created":"2017-03-31","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":"1605.05216","title":"Combinatorially Generated Piecewise Activation Functions","created":"2016-05-17","cited_by_count":1},{"id":"1811.04303","title":"PolyNeuron: Automatic Neuron Discovery via Learned Polyharmonic Spline Activations","created":"2018-11-10","cited_by_count":1}],"next_cursor":null}