Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift on ShortScience.org

jmlr.org
scholar.google.com

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, Sergey and Szegedy, Christian
International Conference on Machine Learning - 2015 via Local Bibsonomy
Keywords: dblp

Summaries/Notes 8

[link] Summary by Joseph Paul Cohen 8 years ago

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}

Your comment:

Write your summary here (You can use $\LaTeX$ and markdown syntax):

Anon Private