The Benefits of Over-parameterization at Initialization in Deep ReLU Networks

11 January 2019

Papers citing "The Benefits of Over-parameterization at Initialization in Deep ReLU Networks"

6 / 6 papers shown

Title
Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation Can Yaras Peng Wang Laura Balzano Qing Qu AI4CE 37 13 0 06 Jun 2024
Randomly Initialized One-Layer Neural Networks Make Data Linearly Separable Promit Ghosal Srinath Mahankali Yihang Sun MLT 29 4 0 24 May 2022
Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark S. Dubey S. Singh B. B. Chaudhuri 41 643 0 29 Sep 2021
BR-NS: an Archive-less Approach to Novelty Search Achkan Salehi Alexandre Coninx Stéphane Doncieux 28 6 0 08 Apr 2021
A Comprehensive and Modularized Statistical Framework for Gradient Norm Equality in Deep Neural Networks Zhaodong Chen Lei Deng Bangyan Wang Guoqi Li Yuan Xie 35 28 0 01 Jan 2020
Deep Learning for CSI Feedback Based on Superimposed Coding Chaojin Qing Bin Cai Qingyao Yang Jiafan Wang Chuan Huang 16 42 0 27 Jul 2019