Beyond Signal Propagation: Is Feature Diversity Necessary in Deep Neural Network Initialization?

2 July 2020

Papers citing "Beyond Signal Propagation: Is Feature Diversity Necessary in Deep Neural Network Initialization?"

5 / 5 papers shown

Title
Leveraging Sub-Optimal Data for Human-in-the-Loop Reinforcement Learning Calarina Muslimani M. E. Taylor OffRL 43 2 0 30 Apr 2024
Dynamical Isometry for Residual Networks Advait Gadhikar R. Burkholz ODL AI4CE 40 2 0 05 Oct 2022
Marginalizable Density Models D. Gilboa Ari Pakman Thibault Vatter BDL 32 5 0 08 Jun 2021
The Future is Log-Gaussian: ResNets and Their Infinite-Depth-and-Width Limit at Initialization Mufan Bill Li Mihai Nica Daniel M. Roy 30 33 0 07 Jun 2021
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks Lechao Xiao Yasaman Bahri Jascha Narain Sohl-Dickstein S. Schoenholz Jeffrey Pennington 227 348 0 14 Jun 2018