Deep-neural-network

I try to use Hessian-free optimization to train the deep neural network. The training is based on the MNIST data set.

Name		Name	Last commit message	Last commit date
Latest commit History 3 Commits
FDiagCheck.m		FDiagCheck.m
README.md		README.md
computeFDiag.m		computeFDiag.m
computeGV.m		computeGV.m
computeGV_1.m		computeGV_1.m
computeGV_2.m		computeGV_2.m
computeHV.m		computeHV.m
dnnCostFunction.m		dnnCostFunction.m
dnnCostOnly.m		dnnCostOnly.m
dnnGradOnly.m		dnnGradOnly.m
dnnHessianFreeOpt.m		dnnHessianFreeOpt.m
dnnParamToStack.m		dnnParamToStack.m
dnnParamToVec.m		dnnParamToVec.m
dnnPredict.m		dnnPredict.m
dnnRandInitializeWeights.m		dnnRandInitializeWeights.m
gaussCheck.m		gaussCheck.m
gradientCheck.m		gradientCheck.m
gradient_check.m		gradient_check.m
hessianCheck.m		hessianCheck.m
hessianFree.m		hessianFree.m
minFunHessianFree.m		minFunHessianFree.m
minFuncMinibatch.m		minFuncMinibatch.m
params.mat		params.mat
plot_data.m		plot_data.m
sigmoid.m		sigmoid.m
train_dnn.m		train_dnn.m
train_hessian.m		train_hessian.m
training_data.mat		training_data.mat

Provide feedback