Controlling Covariate Shift using Equilibrium Normalization of Weights

12/11/2018

∙

by   Aaron Defazio, et al.

∙

1

∙

share

We introduce a new normalization technique that exhibits the fast convergence properties of batch normalization using a transformation of layer weights instead of layer outputs. The proposed technique keeps the contribution of positive and negative weights to the layer output in equilibrium. We validate our method on a set of standard benchmarks including CIFAR-10/100, SVHN and ILSVRC 2012 ImageNet.