Web site for the graduate class on Representation Learning Algorithms IFT6266 H14.
Instructor: Professor Yoshua Bengio
Teaching assistant: PhD candidate David Warde-Farley
Université de Montréal, département d’informatique et recherche opérationnelle
Course plan (pdf, in French)
Class hours and locations:
Mondays 2:30-4:30pm, Z-210
Thursdays 9:30-11:30am, 1409 PAA
Representation Learning - ift6266h14 
In Larochelle’s lecture 9.6, I am having trouble understanding the numbers from the first convolution layer.
The input image is 83×83 and, using 9×9 convolutions (64 kernels) he gets a layer of 64 feature maps of 75×75.
I am sure this is a simple question, but I still have trouble understanding how to derive these. Could we maybe go over this quickly?
This link will bring up the Figure: https://www.youtube.com/watch?v=cDdpwAIsuD8&list=PL6Xpj9I5qXYEcOhn7TqghAJ6NAPrNmUBH#t=45