Transcription of Batch Normalization: Accelerating Deep Network Training …
{{id}} {{{paragraph}}}
[ ] 2 Mar 2015 Batch normalization : Accelerating deep Network Training byReducing Internal Covariate ShiftSergey IoffeGoogle SzegedyGoogle deep Neural Networks is complicated by the factthat the distribution of each layer s inputs changes duringtraining, as the parameters of the previous layers slows down the Training by requiring lower learningrates and careful parameter initialization, and makes it no-toriously hard to train models with saturating nonlineari-ties. We refer to this phenomenon asinternal covariateshift, and address the problem by normalizing layer in-puts. Our method draws its strength from making normal-ization a part of the model architecture and performing thenormalizationfor each Training mini- Batch .
vector, and Xbe the set of these inputs over the training data set. The normalization can then be written as a trans-formation bx = Norm(x,X) which depends not only on the given training example x
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document:
{{id}} {{{paragraph}}}