BriefGPT.xyz
Jul, 2020
神经网络的全球概览
The Global Landscape of Neural Networks: An Overview
HTML
PDF
Ruoyu Sun, Dawei Li, Shiyu Liang, Tian Ding, R Srikant
TL;DR
本文回顾了关于神经网络全局和局部损失函数的广泛研究，重点探讨了在某些假设下宽神经网络可能存在亚优局部最小值的性质以及一些修改方法，并讨论了实际神经网络的可视化和经验探索，最后简要讨论了一些收敛结果及其与全局和局部损失函数相关的关系。
Abstract
One of the major concerns for neural network training is that the non-convexity of the associated loss functions may cause bad landscape. The recent success of
neural networks
suggests that their
loss landscape
i
→