Deep ReLU Networks Preserve Expected Length

21 February 2021

Papers citing "Deep ReLU Networks Preserve Expected Length"

12 / 12 papers shown

Title
On Space Folds of ReLU Neural Networks Michal Lewandowski Hamid Eghbalzadeh Bernhard Heinzl Raphael Pisoni Bernhard A.Moser MLT 81 1 0 17 Feb 2025
SmoothHess: ReLU Network Feature Interactions via Stein's Lemma Max Torop A. Masoomi Davin Hill Kivanc Kose Stratis Ioannidis Jennifer Dy 25 4 0 01 Nov 2023
Expected Gradients of Maxout Networks and Consequences to Parameter Initialization Hanna Tseran Guido Montúfar ODL 24 0 0 17 Jan 2023
Maximal Initial Learning Rates in Deep ReLU Networks Gaurav M. Iyer Boris Hanin David Rolnick 29 9 0 14 Dec 2022
Curved Representation Space of Vision Transformers Juyeop Kim Junha Park Songkuk Kim Jongseok Lee ViT 35 6 0 11 Oct 2022
On Scrambling Phenomena for Randomly Initialized Recurrent Networks Vaggos Chatziafratis Ioannis Panageas Clayton Sanford S. Stavroulakis 24 2 0 11 Oct 2022
On the Number of Regions of Piecewise Linear Neural Networks Alexis Goujon Arian Etemadi M. Unser 44 13 0 17 Jun 2022
Lower and Upper Bounds for Numbers of Linear Regions of Graph Convolutional Networks Hao Chen Yu Wang Huan Xiong GNN 16 6 0 01 Jun 2022
Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis Wuyang Chen Wei Huang Xinyu Gong Boris Hanin Zhangyang Wang 30 7 0 11 May 2022
Gradient representations in ReLU networks as similarity functions Dániel Rácz Bálint Daróczy FAtt 19 1 0 26 Oct 2021
On the Expected Complexity of Maxout Networks Hanna Tseran Guido Montúfar 19 11 0 01 Jul 2021
Benefits of depth in neural networks Matus Telgarsky 148 602 0 14 Feb 2016