Depth Degeneracy in Neural Networks: Vanishing Angles in Fully Connected ReLU Networks on Initialization

20 February 2023

Papers citing "Depth Degeneracy in Neural Networks: Vanishing Angles in Fully Connected ReLU Networks on Initialization"

3 / 3 papers shown

Title
Why neural networks find simple solutions: the many regularizers of geometric complexity Benoit Dherin Michael Munn M. Rosca David Barrett 57 31 0 27 Sep 2022
Rapid training of deep neural networks without skip connections or normalization layers using Deep Kernel Shaping James Martens Andy Ballard Guillaume Desjardins G. Swirszcz Valentin Dalibard Jascha Narain Sohl-Dickstein S. Schoenholz 88 43 0 05 Oct 2021
Deep Networks and the Multiple Manifold Problem Sam Buchanan D. Gilboa John N. Wright 166 39 0 25 Aug 2020