Author: PIERRE_HAO
Data: 2015/05/01
An improved version for Deep Learning Toolbox CNN
-
Add ReLu function
-
Add Max pooling function
-
Add function to read MNIST which we can get from Yann LeCun Home Page
-
Pad size 2828 to 3232 with value 0
-
Other minor changes which are not important
-
Add softmax
-
Add stepsize for changing learning rate
@MASTERSTHESIS{IMM2012-06284,
author = "R. B. Palm",
title = "Prediction as a candidate for learning deep hierarchical models of data",
year = "2012",
}