batch_normalization_differential: Function that calcualtes the differentials in the batch...

In deeplearning: An Implementation of Deep Neural Network for Regression and Classification

Description

Calculates the differentials in batch normalization

Usage

batch_normalization_differential(delta_y, mu, sigma_2, x, x_hat, y, gamma, beta,
  epsilon = exp(-12), with_BN = T)

Arguments

delta_y	derivative wrt y
mu	mean of the input
sigma_2	variance of the input
x	input
x_hat	normalized input
y	transformed input after batch normalization
gamma	gamma coefficient
beta	beta coefficient
epsilon	the contant added to the variance for numeric stability
with_BN	logical value, set to TRUE to turn on batch normalization

References

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift Sergey Ioffe, Christian Szegedy

See Also

http://jmlr.org/proceedings/papers/v37/ioffe15.pdf Pg 4

deeplearning documentation built on Jan. 15, 2017, 9:52 a.m.