BriefGPT.xyz
Dec, 2022
稀疏深度学习的统计保证
Statistical guarantees for sparse deep learning
HTML
PDF
Johannes Lederer
TL;DR
发展用于稀疏深度学习的统计保证来进一步增加我们对神经网络潜力和局限性的理解,这一理论考虑了不同类型的稀疏性,如连通性,结点性等,并覆盖了先前理论忽略的重要方面,如多重输出和正则化。
Abstract
neural networks
are becoming increasingly popular in applications, but our mathematical understanding of their potential and limitations is still limited. In this paper, we further this understanding by developing
stati
→