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
Exponentially Improving the Complexity of Simulating the Weisfeiler-Lehman Test with Graph Neural Networks Anders Aamand Justin Y. Chen Piotr Indyk Shyam Narayanan R. Rubinfeld Nicholas Schiefer Sandeep Silwal Tal Wagner 83 21 0 06 Nov 2022
Isometric Representations in Neural Networks Improve Robustness Kosio Beshkov Jonas Verhellen M. Lepperød AAML OOD 61 1 0 02 Nov 2022
A Dimension-Augmented Physics-Informed Neural Network (DaPINN) with High Level Accuracy and Efficiency Weilong Guan Kai-Ping Yang Yinsheng Chen Zhong Guan PINN AI4CE 67 13 0 19 Oct 2022
Improved Bounds on Neural Complexity for Representing Piecewise Linear Functions Kuan-Lin Chen H. Garudadri Bhaskar D. Rao 69 20 0 13 Oct 2022
Curved Representation Space of Vision Transformers Juyeop Kim Junha Park Songkuk Kim Jongseok Lee ViT 81 7 0 11 Oct 2022
Meta-Principled Family of Hyperparameter Scaling Strategies Sho Yaida 111 16 0 10 Oct 2022
LieGG: Studying Learned Lie Group Generators A. Moskalev A. Sepliarskaia Ivan Sosnovik A. Smeulders 97 27 0 09 Oct 2022
Joint Protection Scheme for Deep Neural Network Hardware Accelerators and Models Jingbo Zhou Xinmiao Zhang AAML 36 6 0 06 Oct 2022
Dynamical Isometry for Residual Networks Advait Gadhikar R. Burkholz ODL AI4CE 81 2 0 05 Oct 2022
Batch Normalization Explained Randall Balestriero Richard G. Baraniuk AAML 92 17 0 29 Sep 2022
PINCH: An Adversarial Extraction Attack Framework for Deep Learning Models William Hackett Stefan Trawicki Zhengxin Yu N. Suri Peter Garraghan MIACV AAML 45 3 0 13 Sep 2022
Progressive Voronoi Diagram Subdivision: Towards A Holistic Geometric Framework for Exemplar-free Class-Incremental Learning Chunwei Ma Zhanghexuan Ji Ziyun Huang Yan Shen Mingchen Gao Jinhui Xu 94 1 0 28 Jul 2022
The Neural Race Reduction: Dynamics of Abstraction in Gated Networks Andrew M. Saxe Shagun Sodhani Sam Lewallen AI4CE 97 37 0 21 Jul 2022
Piecewise Linear Neural Networks and Deep Learning Qinghua Tao Li Li Xiaolin Huang Xiangming Xi Shuning Wang Johan A. K. Suykens 43 30 0 18 Jun 2022
On the Number of Regions of Piecewise Linear Neural Networks Alexis Goujon Arian Etemadi M. Unser 116 15 0 17 Jun 2022
Gradient-Based Adversarial and Out-of-Distribution Detection Jinsol Lee Mohit Prabhushankar Ghassan AlRegib UQCV 167 14 0 16 Jun 2022
Not All Lotteries Are Made Equal Surya Kant Sahu Sai Mitheran Somya Suhans Mahapatra 19 1 0 16 Jun 2022
Decomposed Linear Dynamical Systems (dLDS) for learning the latent components of neural dynamics Noga Mudrik Yenho Chen Eva Yezerets Christopher Rozell Adam S. Charles 99 16 0 07 Jun 2022
Lower and Upper Bounds for Numbers of Linear Regions of Graph Convolutional Networks Hao Chen Yu Wang Huan Xiong GNN 63 6 0 01 Jun 2022
Functional Network: A Novel Framework for Interpretability of Deep Neural Networks Ben Zhang Zhetong Dong Junsong Zhang Hongwei Lin 60 9 0 24 May 2022
$Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete$ Training Fully Connected Neural Networks is $\exists\mathbb{R}$ -Complete Daniel Bertschinger Christoph Hertrich Paul Jungeblut Tillmann Miltzow Simon Weber OffRL 125 30 0 04 Apr 2022
The Mathematics of Artificial Intelligence Gitta Kutyniok 53 0 0 16 Mar 2022
UncertaINR: Uncertainty Quantification of End-to-End Implicit Neural Representations for Computed Tomography Francisca Vasconcelos Bobby He Nalini Singh Yee Whye Teh BDL OOD UQCV 72 13 0 22 Feb 2022
Learning to be a Statistician: Learned Estimator for Number of Distinct Values Renzhi Wu Bolin Ding Xu Chu Zhewei Wei Xiening Dai Tao Guan Jingren Zhou 63 13 0 06 Feb 2022
Few-shot Learning as Cluster-induced Voronoi Diagrams: A Geometric Approach Chunwei Ma Ziyun Huang Mingchen Gao Jinhui Xu 61 5 0 05 Feb 2022
MarkovGNN: Graph Neural Networks on Markov Diffusion Md. Khaledur Rahman Abhigya Agrawal A. Azad GNN BDL 66 2 0 05 Feb 2022
Spherical Poisson Point Process Intensity Function Modeling and Estimation with Measure Transport T. L. J. Ng A. Zammit‐Mangion 65 3 0 24 Jan 2022
Neural Architecture Search for Spiking Neural Networks Youngeun Kim Yuhang Li Hyoungseob Park Yeshwanth Venkatesha Priyadarshini Panda 113 92 0 23 Jan 2022
SkipNode: On Alleviating Performance Degradation for Deep Graph Convolutional Networks Weigang Lu Yibing Zhan Binbin Lin Ziyu Guan Liu Liu Baosheng Yu Wei Zhao Yaming Yang Dacheng Tao GNN 70 15 0 22 Dec 2021
Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts Daniel Khashabi Xinxi Lyu Sewon Min Lianhui Qin Kyle Richardson ... Hannaneh Hajishirzi Tushar Khot Ashish Sabharwal Sameer Singh Yejin Choi 109 75 0 15 Dec 2021
Training BatchNorm Only in Neural Architecture Search and Beyond Yichen Zhu Jie Du Yuqin Zhu Yi Wang Zhicai Ou Feifei Feng Jian Tang 84 1 0 01 Dec 2021
On the Effectiveness of Neural Ensembles for Image Classification with Small Datasets Lorenzo Brigato Luca Iocchi UQCV 56 0 0 29 Nov 2021
Gradient representations in ReLU networks as similarity functions Dániel Rácz Balint Daroczy FAtt 57 1 0 26 Oct 2021
Efficient and Robust Mixed-Integer Optimization Methods for Training Binarized Deep Neural Networks Jannis Kurtz B. Bah MQ 38 4 0 21 Oct 2021
Expressivity of Neural Networks via Chaotic Itineraries beyond Sharkovsky's Theorem Clayton Sanford Vaggos Chatziafratis 29 1 0 19 Oct 2021
Distinguishing rule- and exemplar-based generalization in learning systems Ishita Dasgupta Erin Grant Thomas Griffiths 88 16 0 08 Oct 2021
On the Impact of Stable Ranks in Deep Nets B. Georgiev L. Franken Mayukh Mukherjee Georgios Arvanitidis 62 3 0 05 Oct 2021
NASI: Label- and Data-agnostic Neural Architecture Search at Initialization Yao Shu Shaofeng Cai Zhongxiang Dai Beng Chin Ooi K. H. Low 98 44 0 02 Sep 2021
Finding Representative Interpretations on Convolutional Neural Networks P. C. Lam Lingyang Chu Maxim Torgonskiy J. Pei Yong Zhang Lanjun Wang FAtt SSL HAI 70 6 0 13 Aug 2021
Neural Network Approximation of Refinable Functions Ingrid Daubechies Ronald A. DeVore Nadav Dym Shira Faigenbaum-Golovin S. Kovalsky Kung-Chin Lin Josiah Park G. Petrova B. Sober 65 14 0 28 Jul 2021
An Embedding of ReLU Networks and an Analysis of their Identifiability Pierre Stock Rémi Gribonval 147 18 0 20 Jul 2021
Neural Network Layer Algebra: A Framework to Measure Capacity and Compression in Deep Learning Alberto Badías A. Banerjee 69 3 0 02 Jul 2021
On the Expected Complexity of Maxout Networks Hanna Tseran Guido Montúfar 67 12 0 01 Jul 2021
Multifidelity Modeling for Physics-Informed Neural Networks (PINNs) Michael Penwarden Shandian Zhe A. Narayan Robert M. Kirby 99 46 0 25 Jun 2021
Causal Navigation by Continuous-time Neural Networks Charles J. Vorbach Ramin Hasani Alexander Amini Mathias Lechner Daniela Rus 102 47 0 15 Jun 2021
The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective Geoff Pleiss John P. Cunningham 70 27 0 11 Jun 2021
On the Robustness of Average Losses for Partial-Label Learning Jiaqi Lv Biao Liu Lei Feng Ning Xu Miao Xu Bo An Gang Niu Xin Geng Masashi Sugiyama 92 35 0 11 Jun 2021
What training reveals about neural network complexity Andreas Loukas Marinos Poiitis Stefanie Jegelka 67 11 0 08 Jun 2021
Reverse Engineering the Neural Tangent Kernel James B. Simon Sajant Anand M. DeWeese 104 9 0 06 Jun 2021
Feature Flow Regularization: Improving Structured Sparsity in Deep Neural Networks Yue Wu Yuan Lan Luchan Zhang Yang Xiang 51 6 0 05 Jun 2021