Increasing Depth Leads to U-Shaped Test Risk in Over-parameterized Convolutional Networks

19 October 2020

Papers citing "Increasing Depth Leads to U-Shaped Test Risk in Over-parameterized Convolutional Networks"

5 / 5 papers shown

Title
Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks Eshaan Nichani Alexandru Damian Jason D. Lee MLT 38 13 0 11 May 2023
Room dimensions and absorption inference from room transfer function via machine learning Yuanxin Xia C. Jeong 13 2 0 25 Apr 2023
Towards Learning Convolutions from Scratch Behnam Neyshabur SSL 220 71 0 27 Jul 2020
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 222 348 0 14 Jun 2018
Benefits of depth in neural networks Matus Telgarsky 142 602 0 14 Feb 2016