backpropagate_delta_bn: Calculates the delta functions using backpropagation
In rz1988/deeplearning: An Implementation of Deep Neural Network for Regression and Classification

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

1 2	backpropagate_delta_bn(darch, trainData, targetData, errorFunc = meanSquareErr, with_BN = TRUE)

`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

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

rz1988/deeplearning documentation built on May 28, 2019, 10:46 a.m.

rz1988/deeplearning index

README.md

Note that we can't provide technical support on individual packages. You should contact the package authors for that.

Description