Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Paper summary A *Batch Normalization* applied immediately after fully connected layers and adjusts the values of the feedforward output so that they are centered to a zero mean and have unit variance. It has been used by famous Convolutional Neural Networks such as GoogLeNet \cite{journals/corr/SzegedyLJSRAEVR14} and ResNet \cite{journals/corr/HeZRS15}
arxiv.org
arxiv-sanity.com
scholar.google.com
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe and Christian Szegedy
arXiv e-Print archive - 2015 via Local arXiv
Keywords: cs.LG

more

[link]
Summary by Léo Paillier 1 year ago
Loading...
Your comment:


ShortScience.org allows researchers to publish paper summaries that are voted on and ranked!
About

Sponsored by: and