Information Geometry of Orthogonal Initializations and Training

9 October 2018

Papers citing "Information Geometry of Orthogonal Initializations and Training"

3 / 3 papers shown

Title
Asymptotic Freeness of Layerwise Jacobians Caused by Invariance of Multilayer Perceptron: The Haar Orthogonal Case B. Collins Tomohiro Hayase 22 7 0 24 Mar 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 220 348 0 14 Jun 2018
Optimization on Submanifolds of Convolution Kernels in CNNs Mete Ozay Takayuki Okatani 43 46 0 22 Oct 2016