Table Of Contents

Previous topic

Modèles probabilistes pour les architectures profondes

Next topic

Very Brief Introduction to Machine Learning for AI

This Page

IFT6266: Course Outline

The following table contains a summary of each class of the course (click on the date for more details for each entry):

Date Subject To read
April 2nd Exam  
March 29th Review session  
March 26th Convolutional networks

Neocognitron article.

LeNet article.

Convolutional networks tutorial.

March 22nd

Gradient propagation

DAE vs AE

final part of Yoshua Bengio’s presentation.

Denoising autoencoders vs. ordinary autoencoders.

March 19th Challenges for deep networks The challenges of training deep neural networks.
March 15th Pre-training

Yoshua Bengio’s presentation.

Dumitru Erhan presentation.

March 12th Contracting AE and MTC Articles on Contracting Auto-Encoders and on Manifold Tangent Classifier
March 1st Contracting AE, Article on Contracting Auto-Encoders
February 27th DBMs The Boltzmann Machine.
February 20th+23rd DBNs Stacked RBMs and DBNs.
February 13rd+16th RBMs Restricted Boltzmann Machines.
February 6th+9th Probabilistic models Probabilistic models Probabilistic models for deep architectures.
February 2nd

Probabilistic models

Launching jobs

Introduction to Probabilistic models for deep architectures.

Jobman.

January 30th Probabilistic models Introduction to Probabilistic models for deep architectures.
January 26th Auto-encoders, DAE Section 4.6 de Learning Deep Architectures for AI. Denoising Auto-Encoders
January 23rd

python, numpy, Theano

Logistical regression

Documentation on python, numpy, et Theano. Logistic regression tutorial. Notes on training MLPs.
January 19th Neural networks Efficient Backprop. Introduction to the Deep Learning Tutorials. The Getting Started tutorial.
January 16th Computing gradients Notes on computing gradients.
January 12th Introduction to deep networks Introduction to deep networks, Sec. 1 of Learning Deep Architectures for AI. Notes on gradient based learning.
January 9th Introduction to deep networks Introduction to deep networks, Sec. 1 of Learning Deep Architectures for AI.
January 5th

Introtuction to this class

Introduction to Machine Learning

course outline .

slides . Introduction to Machine Learning, Sec. 1 and 2 of Scaling Learning Algorithms towards AI.

April 2nd

  • Open book theoretical exam

March 29th

  • Review session before the exam

March 26th

March 22nd

March 15th

March 1st

February 27th

February 20th+23rd

February 13rd+16th

February 2nd

January 30th

January 26th

January 5th