finetune_SGD_bn

darch

trainData

targetData

learn_rate_weight

learn_rate_bias

learn_rate_gamma

the error function to minimize during training

errorFunc

logical value, T to train the neural net with batch normalization

with_BN


This function finetunes a DArch network using SGD approach


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.

finetune_SGD_bn: Updates a deep neural network's parameters using stochastic gradient descent method and batch normalization

Description

Usage

Arguments

Value