batch_normalization_differential

delta_y

sigma_2

x_hat

transformed input after batch normalization

gamma

beta

the contant added to the variance for numeric stability

epsilon

logical value, set to TRUE to turn on batch normalization

with_BN


Calculates the differentials in batch normalization


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.

batch_normalization_differential: Function that calcualtes the differentials in the batch normalization mode

Description

Usage

Arguments

References

See Also