Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions

28 February 2018

Quynh N. Nguyen

Mahesh Chandra Mukkamala

Matthias Hein

MLT

ArXiv PDF HTML

Papers citing "Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions"

28 / 28 papers shown

Title
When Deep Learning Meets Polyhedral Theory: A Survey Joey Huchette Gonzalo Muñoz Thiago Serra Calvin Tsay AI4CE 129 37 0 29 Apr 2023
A Tropical Approach to Neural Networks with Piecewise Linear Activations Vasileios Charisopoulos Petros Maragos 55 40 0 22 May 2018
Bounding and Counting Linear Regions of Deep Neural Networks Thiago Serra Christian Tjandraatmadja Srikumar Ramalingam MLT 59 249 0 06 Nov 2017
Approximating Continuous Functions by ReLU Nets of Minimal Width Boris Hanin Mark Sellke 103 234 0 31 Oct 2017
Optimization Landscape and Expressivity of Deep CNNs Quynh N. Nguyen Matthias Hein 61 29 0 30 Oct 2017
The Expressive Power of Neural Networks: A View from the Width Zhou Lu Hongming Pu Feicheng Wang Zhiqiang Hu Liwei Wang 96 892 0 08 Sep 2017
Classification regions of deep neural networks Alhussein Fawzi Seyed-Mohsen Moosavi-Dezfooli P. Frossard Stefano Soatto 57 51 0 26 May 2017
The loss surface of deep and wide neural networks Quynh N. Nguyen Matthias Hein ODL 131 284 0 26 Apr 2017
Understanding Deep Neural Networks with Rectified Linear Units R. Arora A. Basu Poorya Mianjy Anirbit Mukherjee PINN 143 640 0 04 Nov 2016
Adversarial Machine Learning at Scale Alexey Kurakin Ian Goodfellow Samy Bengio AAML 461 3,138 0 04 Nov 2016
Why and When Can Deep -- but Not Shallow -- Networks Avoid the Curse of Dimensionality: a Review T. Poggio H. Mhaskar Lorenzo Rosasco Brando Miranda Q. Liao 97 578 0 02 Nov 2016
Depth-Width Tradeoffs in Approximating Natural Functions with Neural Networks Itay Safran Ohad Shamir 80 174 0 31 Oct 2016
Why Deep Neural Networks for Function Approximation? Shiyu Liang R. Srikant 107 385 0 13 Oct 2016
Error bounds for approximations with deep ReLU networks Dmitry Yarotsky 175 1,226 0 03 Oct 2016
Deep vs. shallow networks : An approximation theory perspective H. Mhaskar T. Poggio 147 342 0 10 Aug 2016
Adversarial examples in the physical world Alexey Kurakin Ian Goodfellow Samy Bengio SILM AAML 517 5,893 0 08 Jul 2016
On the Expressive Power of Deep Neural Networks M. Raghu Ben Poole Jon M. Kleinberg Surya Ganguli Jascha Narain Sohl-Dickstein 61 786 0 16 Jun 2016
Convolutional Rectifier Networks as Generalized Tensor Decompositions Nadav Cohen Amnon Shashua 60 153 0 01 Mar 2016
Benefits of depth in neural networks Matus Telgarsky 330 608 0 14 Feb 2016
The Power of Depth for Feedforward Neural Networks Ronen Eldan Ohad Shamir 195 732 0 12 Dec 2015
Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) Djork-Arné Clevert Thomas Unterthiner Sepp Hochreiter 275 5,518 0 23 Nov 2015
Representation Benefits of Deep Feedforward Networks Matus Telgarsky 76 242 0 27 Sep 2015
On the Expressive Power of Deep Learning: A Tensor Analysis Nadav Cohen Or Sharir Amnon Shashua 79 470 0 16 Sep 2015
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification Kaiming He Xinming Zhang Shaoqing Ren Jian Sun VLM 280 18,587 0 06 Feb 2015
Caffe: Convolutional Architecture for Fast Feature Embedding Yangqing Jia Evan Shelhamer Jeff Donahue Sergey Karayev Jonathan Long Ross B. Girshick S. Guadarrama Trevor Darrell VLM BDL 3DV 251 14,704 0 20 Jun 2014
On the Number of Linear Regions of Deep Neural Networks Guido Montúfar Razvan Pascanu Kyunghyun Cho Yoshua Bengio 88 1,254 0 08 Feb 2014
On the number of response regions of deep feed forward networks with piece-wise linear activations Razvan Pascanu Guido Montúfar Yoshua Bengio FAtt 111 257 0 20 Dec 2013
Sum-Product Networks: A New Deep Architecture Hoifung Poon Pedro M. Domingos TPM 74 758 0 14 Feb 2012