A Unified and Constructive Framework for the Universality of Neural Networks

30 December 2021

Papers citing "A Unified and Constructive Framework for the Universality of Neural Networks"

10 / 10 papers shown

Title
The Barron Space and the Flow-induced Function Spaces for Neural Network Models E. Weinan Chao Ma Lei Wu 71 110 0 18 Jun 2019
The Deep Ritz method: A deep learning-based numerical algorithm for solving variational problems E. Weinan Ting Yu 115 1,380 0 30 Sep 2017
Self-Normalizing Neural Networks Günter Klambauer Thomas Unterthiner Andreas Mayr Sepp Hochreiter 404 2,507 0 08 Jun 2017
Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning Stefan Elfwing E. Uchibe Kenji Doya 120 1,717 0 10 Feb 2017
Error bounds for approximations with deep ReLU networks Dmitry Yarotsky 181 1,226 0 03 Oct 2016
$Approximation by Combinations of ReLU and Squared ReLU Ridge Functions with $ \ell^1 $ and $ \ell^0 $ Controls$ Approximation by Combinations of ReLU and Squared ReLU Ridge Functions with $\ell^1$ and $\ell^0$ Controls Jason M. Klusowski Andrew R. Barron 241 143 0 26 Jul 2016
Gaussian Error Linear Units (GELUs) Dan Hendrycks Kevin Gimpel 165 4,994 0 27 Jun 2016
A single hidden layer feedforward network with only one neuron in the hidden layer can approximate any univariate function Namig J. Guliyev V. Ismailov 29 79 0 31 Dec 2015
Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) Djork-Arné Clevert Thomas Unterthiner Sepp Hochreiter 283 5,518 0 23 Nov 2015
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification Kaiming He Xinming Zhang Shaoqing Ren Jian Sun VLM 286 18,587 0 06 Feb 2015