Description: A simple convolutional neural network with linear neurons.
Structure: input->convolution->max pooling->convolution->max pooling->fully connected.
Compile the max pooling function in C++ first by typing mex MaxPooling.cpp .
The data can be downloaded in http://ai.stanford.edu/~amaas/data/data.zip
The data loading functions can be downloaded in http://ufldl.stanford.edu/wiki/index.php/Using_the_MNIST_Dataset
About 98 classification accuracy for 50 epochs of all training data.
To Search:
File list (Check if you may need any files):
cnn_linear_max-master
.....................\cnnTest.m
.....................\cnnTrain.m
.....................\Debug
.....................\.....\MaxPooling.pch
.....................\.....\vc60.idb
.....................\.....\vc60.pdb
.....................\MaxPooling.cpp
.....................\MaxPooling.dsp
.....................\MaxPooling.dsw
.....................\MaxPooling.ncb
.....................\MaxPooling.opt
.....................\MaxPooling.plg
.....................\README.md
.....................\upsampleMax.m
Download