Random orthogonal additive filters: a solution to the vanishing/exploding gradient of deep neural networks

3 October 2022

Papers citing "Random orthogonal additive filters: a solution to the vanishing/exploding gradient of deep neural networks"

1 / 1 papers shown

Title
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 220 348 0 14 Jun 2018