暂无分享,去创建一个
[1] Guido Montúfar,et al. Universal Approximation Depth and Errors of Narrow Belief Networks with Discrete Units , 2013, Neural Computation.
[2] Jesse Johnson,et al. Deep, Skinny Neural Networks are not Universal Approximators , 2018, ICLR.
[3] Kristian Kersting,et al. Padé Activation Units: End-to-end Learning of Flexible Activation Functions in Deep Networks , 2019, ICLR.
[4] Brendan McCane,et al. Deep, super-narrow neural network is a universal classifier , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).
[5] Tuo Zhao,et al. Efficient Approximation of Deep ReLU Networks for Functions on Low Dimensional Manifolds , 2019, NeurIPS.
[6] Joan Bruna,et al. Gradient Dynamics of Shallow Univariate ReLU Networks , 2019, NeurIPS.
[7] David Duvenaud,et al. Residual Flows for Invertible Generative Modeling , 2019, NeurIPS.
[8] Jian Sun,et al. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).
[9] Suvrit Sra,et al. Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity , 2018, NeurIPS.
[10] Raman Arora,et al. Understanding Deep Neural Networks with Rectified Linear Units , 2016, Electron. Colloquium Comput. Complex..
[11] Stefanie Jegelka,et al. ResNet with one-neuron hidden layers is a Universal Approximator , 2018, NeurIPS.
[12] George Cybenko,et al. Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..
[13] Philipp Petersen,et al. Optimal approximation of piecewise smooth functions using deep ReLU neural networks , 2017, Neural Networks.
[14] Matthias Hein,et al. Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions , 2018, ICML.
[15] Sepp Hochreiter,et al. Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.
[16] Mark Sellke,et al. Approximating Continuous Functions by ReLU Nets of Minimal Width , 2017, ArXiv.
[17] Alex Townsend,et al. Rational neural networks , 2020, NeurIPS.
[18] Tianqi Chen,et al. Empirical Evaluation of Rectified Activations in Convolutional Network , 2015, ArXiv.
[19] Liwei Wang,et al. The Expressive Power of Neural Networks: A View from the Width , 2017, NIPS.
[20] Quoc V. Le,et al. Swish: a Self-Gated Activation Function , 2017, 1710.05941.
[21] Nicolas Le Roux,et al. Deep Belief Networks Are Compact Universal Approximators , 2010, Neural Computation.
[22] Andrew L. Maas. Rectifier Nonlinearities Improve Neural Network Acoustic Models , 2013 .
[23] Udo Schröder,et al. On decision regions of narrow deep neural networks , 2018, ArXiv.
[24] Kurt Hornik,et al. Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.
[25] Quoc V. Le,et al. Searching for Activation Functions , 2018, arXiv.
[26] G. Petrova,et al. Nonlinear Approximation and (Deep) ReLU\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mathrm {ReLU}$$\end{document} , 2019, Constructive Approximation.
[27] Gitta Kutyniok,et al. Error bounds for approximations with deep ReLU neural networks in $W^{s, p}$ norms , 2019, Analysis and Applications.
[28] Sepp Hochreiter,et al. Self-Normalizing Neural Networks , 2017, NIPS.
[29] Geoffrey E. Hinton,et al. Deep, Narrow Sigmoid Belief Networks Are Universal Approximators , 2008, Neural Computation.
[30] Philipp Grohs,et al. How degenerate is the parametrization of neural networks with the ReLU activation function? , 2019, NeurIPS.
[31] A. Krizhevsky. Convolutional Deep Belief Networks on CIFAR-10 , 2010 .
[32] Raúl Rojas. Networks of width one are universal classifiers , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..
[33] Allan Pinkus,et al. Approximation theory of the MLP model in neural networks , 1999, Acta Numerica.