backpropagate_delta_bn: Calculates the delta functions using backpropagation

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

Description

function that calculates the delta function of a darch object with batch normalization

Usage

backpropagate_delta_bn(darch, trainData, targetData,
  errorFunc = meanSquareErr, with_BN = TRUE)

Arguments

darch	a darch instance
trainData	training input
targetData	training target
errorFunc	error function to minimize during training. Right now mean squared erros and cross entropy errors are supported.
with_BN	traing with batch normalization on or off

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.