Depth-Width Trade-offs for ReLU Networks via Sharkovsky's Theorem

9 December 2019

Papers citing "Depth-Width Trade-offs for ReLU Networks via Sharkovsky's Theorem"

7 / 7 papers shown

Title
The Disharmony between BN and ReLU Causes Gradient Explosion, but is Offset by the Correlation between Activations Inyoung Paik Jaesik Choi 21 0 0 23 Apr 2023
Transformer Vs. MLP-Mixer: Exponential Expressive Gap For NLP Problems D. Navon A. Bronstein MoE 38 0 0 17 Aug 2022
Expressivity of Neural Networks via Chaotic Itineraries beyond Sharkovsky's Theorem Clayton Sanford Vaggos Chatziafratis 16 1 0 19 Oct 2021
Depth separation beyond radial functions Luca Venturi Samy Jelassi Tristan Ozuch Joan Bruna 19 15 0 02 Feb 2021
The Connection Between Approximation, Depth Separation and Learnability in Neural Networks Eran Malach Gilad Yehudai Shai Shalev-Shwartz Ohad Shamir 21 20 0 31 Jan 2021
On the Number of Linear Functions Composing Deep Neural Network: Towards a Refined Definition of Neural Networks Complexity Yuuki Takai Akiyoshi Sannai Matthieu Cordonnier 80 4 0 23 Oct 2020
Benefits of depth in neural networks Matus Telgarsky 153 603 0 14 Feb 2016