BriefGPT.xyz
Aug, 2020
无批归一化训练深度神经网络
Training Deep Neural Networks Without Batch Normalization
HTML
PDF
Divya Gaur, Joachim Folz, Andreas Dengel
TL;DR
本篇论文详细研究了批量归一化在训练神经网络中的作用,以及其与其他优化方法的比较,主要目的是通过改进训练过程判断是否有可能在不使用批量归一化情况下有效地训练网络。
Abstract
Training
neural networks
is an
optimization
problem, and finding a decent set of parameters through gradient descent can be a difficult task. A host of techniques has been developed to aid this process before and
→