4.4 How Batch Normalization works

Here's the original paper

Batch Normalization: Accelerating Deep Network Training byReducing Internal Covariate Shift

by Sergey Ioffe and Christian Szegedy

https://arxiv.org/pdf/1502.03167v3.pdf

The Wikipedia page is helpful too

https://en.wikipedia.org/wiki/Batch_normalization


Discussion

0 comments