search

rasmusbergpalm / DeepLearnToolbox

Matlab/Octave toolbox for deep learning. Includes Deep Belief Nets, Stacked Autoencoders, Convolutional Neural Nets, Convolutional Autoencoders and vanilla Neural Nets. Each method has examples to get you started.
BSD 2-Clause "Simplified" License
3.8k stars 2.28k forks source link

CNN backpropagation #97

Closed mnaetr closed 10 years ago

mnaetr commented 10 years ago

Hi. I'm using your CNN code. I understood how the backpropagation algorithm work for traditional NN, but I have some problem with the CNN. In particular I don't understand how the errors are back propagated from a convolutional to a subsampling layer and viceversa. Can you suggest me some papers or theoretical lectures that explain it with details? Thank you

rasmusbergpalm commented 10 years ago

See http://cogprints.org/5869/1/cnn_tutorial.pdf which is the one i followed when implementing it.