reset_population_mu_sigma

darch


This function resets the mu and sigmas of hidden layers in a darch instance
 to 0 and 1


An implementation of deep neural network with rectifier linear units trained
with stochastic gradient descent method and batch normalization. A combination of these methods have
achieved state-of-the-art performance in ImageNet classification by overcoming the gradient saturation
problem experienced by many deep architecture neural network models in the past. In addition,
batch normalization and dropout are implemented as a means of regularization. The deeplearning package is
inspired by the darch package and uses its class DArch.

reset_population_mu_sigma: Resets the mu and sigmas of a darch instance to 0 and 1

Description

Usage

Arguments