activation function

Adaptive Estimators Show Information Compression in Deep Neural Networks ICLR 2019 A Representer Theorem for Deep Neural Networks JMLR 2019 Deep, Skinny Neural Networks are not Universal Approximators ICLR 2019 Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup NeurIPS 2019 Fast Image Restoration With Multi-Bin Trainable Linear Units ICCV 2019 From Hard to Soft: Understanding Deep Network Nonlinearities via Vector Quantization and Statistical Inference ICLR 2019 Learning in the Machine: Random Backpropagation and the Deep Learning Channel (Extended Abstract) IJCAI 2019 Lifted Proximal Operator Machines AAAI 2019 On the Impact of the Activation function on Deep Neural Networks Training ICML 2019 Small nonlinearities in activation functions create bad local minima in neural networks ICLR 2019 Tight Sample Complexity of Learning One-hidden-layer Convolutional Neural Networks NeurIPS 2019 Towards Non-Saturating Recurrent Units for Modelling Long-Term Dependencies AAAI 2019 Breaking the Activation Function Bottleneck through Adaptive Parameterization NeurIPS 2018 Efficient Neural Network Robustness Certification with General Activation Functions NeurIPS 2018 Gaussian Process Neural Networks for Speech Recognition Interspeech 2018 Is it Time to Swish? Comparing Deep Learning Activation Functions Across NLP tasks EMNLP 2018 Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions ICML 2018 xUnit: Learning a Spatial Activation Function for Efficient Image Restoration CVPR 2018 A Probabilistic Framework for Nonlinearities in Stochastic Neural Networks NeurIPS 2017 Deep Activation Mixture Model for Speech Recognition Interspeech 2017 Diverse Neuron Type Selection for Convolutional Neural Networks IJCAI 2017 Improving Speech Recognition by Revising Gated Recurrent Units Interspeech 2017 Nonlinear random matrix theory for deep learning NeurIPS 2017 On the Complexity of Learning Neural Networks NeurIPS 2017 Self-Normalizing Neural Networks NeurIPS 2017