Learn R Programming

deeplearning (version 0.1.0)

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

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