BriefGPT.xyz
Jul, 2023
深度神经网络的稀疏感知泛化理论
Sparsity aware generalization theory for deep neural networks
HTML
PDF
Ramchandran Muthukumar, Jeremias Sulam
TL;DR
本文研究了深度神经网络的泛化能力和节点稀疏性之间的关系，通过开发一个基于减小的有效模型大小的框架来证明了稀疏和泛化之间的基本权衡关系，并提出了一种新的方法来分析这个问题。
Abstract
deep artificial neural networks
achieve surprising
generalization
abilities that remain poorly understood. In this paper, we present a new approach to analyzing
→