v1v2v3v4v5v6 (latest)

On the Expressive Power of Deep Neural Networks

16 June 2016

Jascha Narain Sohl-Dickstein

ArXiv (abs)PDF HTML

Papers citing "On the Expressive Power of Deep Neural Networks"

50 / 267 papers shown

Title
Empirical Bounds on Linear Regions of Deep Rectifier Networks Thiago Serra Srikumar Ramalingam 83 42 0 08 Oct 2018
Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning Charles H. Martin Michael W. Mahoney AI4CE 137 201 0 02 Oct 2018
Deep Neural Networks for Estimation and Inference M. Farrell Tengyuan Liang S. Misra BDL 186 256 0 26 Sep 2018
The jamming transition as a paradigm to understand the loss landscape of deep neural networks Mario Geiger S. Spigler Stéphane dÁscoli Levent Sagun Marco Baity-Jesi Giulio Biroli Matthieu Wyart 86 143 0 25 Sep 2018
Towards Understanding Regularization in Batch Normalization Ping Luo Xinjiang Wang Wenqi Shao Zhanglin Peng MLT AI4CE 89 180 0 04 Sep 2018
Deep Learning of Vortex Induced Vibrations M. Raissi Zhicheng Wang M. Triantafyllou George Karniadakis AI4CE 81 378 0 26 Aug 2018
Learning ReLU Networks on Linearly Separable Data: Algorithm, Optimality, and Generalization G. Wang G. Giannakis Jie Chen MLT 83 132 0 14 Aug 2018
Hidden Fluid Mechanics: A Navier-Stokes Informed Deep Learning Framework for Assimilating Flow Visualization Data M. Raissi A. Yazdani George Karniadakis AI4CE PINN 102 161 0 13 Aug 2018
Bounds on the Approximation Power of Feedforward Neural Networks M. Mehrabi A. Tchamkerten Mansoor I. Yousefi 69 12 0 29 Jun 2018
Adversarial Reprogramming of Neural Networks Gamaleldin F. Elsayed Ian Goodfellow Jascha Narain Sohl-Dickstein OOD AAML 55 183 0 28 Jun 2018
On the Spectral Bias of Neural Networks Nasim Rahaman A. Baratin Devansh Arpit Felix Dräxler Min Lin Fred Hamprecht Yoshua Bengio Aaron Courville 172 1,463 0 22 Jun 2018
Learning One-hidden-layer ReLU Networks via Gradient Descent Xiao Zhang Yaodong Yu Lingxiao Wang Quanquan Gu MLT 129 135 0 20 Jun 2018
How Could Polyhedral Theory Harness Deep Learning? Thiago Serra Christian Tjandraatmadja Srikumar Ramalingam AI4CE 32 0 0 17 Jun 2018
A Framework for the construction of upper bounds on the number of affine linear regions of ReLU feed-forward neural networks Peter Hinz Sara van de Geer 67 23 0 05 Jun 2018
Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach Ryo Karakida S. Akaho S. Amari FedML 199 146 0 04 Jun 2018
The Nonlinearity Coefficient - Predicting Generalization in Deep Neural Networks George Philipp J. Carbonell 66 14 0 01 Jun 2018
Entropy and mutual information in models of deep neural networks Marylou Gabrié Andre Manoel Clément Luneau Jean Barbier N. Macris Florent Krzakala Lenka Zdeborová 85 179 0 24 May 2018
Mean Field Theory of Activation Functions in Deep Neural Networks M. Milletarí Thiparat Chotibut P. E. Trevisanutto 30 4 0 22 May 2018
A Tropical Approach to Neural Networks with Piecewise Linear Activations Vasileios Charisopoulos Petros Maragos 78 40 0 22 May 2018
Tropical Geometry of Deep Neural Networks Liwen Zhang Gregory Naitzat Lek-Heng Lim 95 140 0 18 May 2018
End-to-end Learning of a Convolutional Neural Network via Deep Tensor Decomposition Samet Oymak Mahdi Soltanolkotabi 87 12 0 16 May 2018
Improving GAN Training via Binarized Representation Entropy (BRE) Regularization Yanshuai Cao G. Ding Kry Yik-Chau Lui Ruitong Huang GAN 65 19 0 09 May 2018
What do Deep Networks Like to See? Sebastián M. Palacio Joachim Folz Jörn Hees Federico Raue Damian Borth Andreas Dengel SSL 51 30 0 22 Mar 2018
Learning the Localization Function: Machine Learning Approach to Fingerprinting Localization Linchen Xiao Arash Behboodi R. Mathar 29 12 0 21 Mar 2018
On the importance of single directions for generalization Ari S. Morcos David Barrett Neil C. Rabinowitz M. Botvinick 101 332 0 19 Mar 2018
Generalization and Expressivity for Deep Nets Shao-Bo Lin 77 45 0 10 Mar 2018
How to Start Training: The Effect of Initialization and Architecture Boris Hanin David Rolnick 113 257 0 05 Mar 2018
Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions Quynh N. Nguyen Mahesh Chandra Mukkamala Matthias Hein MLT 109 56 0 28 Feb 2018
Sensitivity and Generalization in Neural Networks: an Empirical Study Roman Novak Yasaman Bahri Daniel A. Abolafia Jeffrey Pennington Jascha Narain Sohl-Dickstein AAML 99 442 0 23 Feb 2018
On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization Sanjeev Arora Nadav Cohen Elad Hazan 132 488 0 19 Feb 2018
On Characterizing the Capacity of Neural Networks using Algebraic Topology William H. Guss Ruslan Salakhutdinov 86 90 0 13 Feb 2018
Intriguing Properties of Randomly Weighted Networks: Generalizing While Learning Next to Nothing Amir Rosenfeld John K. Tsotsos MLT 75 52 0 02 Feb 2018
Deep Learning Works in Practice. But Does it Work in Theory? L. Hoang R. Guerraoui PINN 53 3 0 31 Jan 2018
Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification Yinhao Zhu N. Zabaras UQCV BDL 115 649 0 21 Jan 2018
Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations M. Raissi PINN AI4CE 132 759 0 20 Jan 2018
Which Neural Net Architectures Give Rise To Exploding and Vanishing Gradients? Boris Hanin 110 256 0 11 Jan 2018
The exploding gradient problem demystified - definition, prevalence, impact, origin, tradeoffs, and solutions George Philipp Basel Alomair J. Carbonell ODL 92 46 0 15 Dec 2017
A trans-disciplinary review of deep learning research for water resources scientists Chaopeng Shen AI4CE 226 702 0 06 Dec 2017
Adversarial Feature Augmentation for Unsupervised Domain Adaptation Riccardo Volpi Pietro Morerio Silvio Savarese Vittorio Murino GAN OOD 115 234 0 23 Nov 2017
Bounding and Counting Linear Regions of Deep Neural Networks Thiago Serra Christian Tjandraatmadja Srikumar Ramalingam MLT 114 251 0 06 Nov 2017
An efficient quantum algorithm for generative machine learning Xun Gao Zhengyu Zhang L. Duan 90 25 0 06 Nov 2017
Expressive power of recurrent neural networks Valentin Khrulkov Alexander Novikov Ivan Oseledets 116 114 0 02 Nov 2017
Approximating Continuous Functions by ReLU Nets of Minimal Width Boris Hanin Mark Sellke 120 239 0 31 Oct 2017
Optimization Landscape and Expressivity of Deep CNNs Quynh N. Nguyen Matthias Hein 101 29 0 30 Oct 2017
A Correspondence Between Random Neural Networks and Statistical Field Theory S. Schoenholz Jeffrey Pennington Jascha Narain Sohl-Dickstein 94 20 0 18 Oct 2017
Searching for Activation Functions Prajit Ramachandran Barret Zoph Quoc V. Le 97 612 0 16 Oct 2017
Training Feedforward Neural Networks with Standard Logistic Activations is Feasible Emanuele Sansone F. D. De Natale 29 4 0 03 Oct 2017
When is a Convolutional Filter Easy To Learn? S. Du Jason D. Lee Yuandong Tian MLT 67 130 0 18 Sep 2017
Learning Deep Neural Network Representations for Koopman Operators of Nonlinear Dynamical Systems Enoch Yeung Soumya Kundu Nathan Oken Hodas AI4CE 85 387 0 22 Aug 2017
Deep Learning the Ising Model Near Criticality A. Morningstar R. Melko AI4CE 66 86 0 15 Aug 2017