IFT6135 Representation Learning winter 2020, (Deep Learning)):
This is a course on representation learning in general and deep learning in particular. Deep learning has recently been responsible for a large number of impressive empirical gains across a wide array of applications including most dramatically in object recognition and detection in images and speech recognition.
In this course we will explore both the fundamentals and recent advances in the area of deep learning. Our focus will be on neural network-type models including convolutional neural networks and recurrent neural networks such as LSTMs. We will also review recent work on attention mechanism and efforts to incorporate memory structures into neural network models. We will also consider some of the modern neural network-base generative models such as Generative Adversarial Networks and Variational Autoencoders.
IFT6266 Representation Learning (winter 2015, winter 2017 (Deep Learning)):
This course explores both the fundamentals and recent advances in the area of deep learning. Our focus will be on neural network-type models including convolutional neural networks and recurrent neural networks such as the LSTM. We will also consider some probabilistic graphical models, including undirected models such as the Boltzmann machines and directed models that have recently shown promise.
IFT6085: Sujets en IA (winter2014, autumn2014 — available to enrolled students):
The actual topic is: Introduction to Probabilistic Graphical Models
(en francais: Introduction des modèles graphiques probabilistes)
This course is designed to be an introductory course on probabilistic graphical models. We will explore how to represent complex systems as probabilistic graphical models, how to perform inference in these models (both exact and approximate inference) as well as how to learn the model parameters from data. We will also include an emphasis on the models and methods that are currently popular within the deep learning literature, in particular undirected graphical models.
Course website is on studium (not visible to students not enrolled).
Probability Theory Review; Maximum Likelihood Estimation; Bayesian Estimation; Bayesian Network Representation; Undirected Graphical Models; Local Probability Models; Temporal Models; Gaussian Network Models; Variable Elimination; Clique Trees; Deterministic Approximate Inference Methods (such as Variational Methods); Particle-Based Approximate Inference Methods; MAP Inference; Inference in Hybrid and Temporal Models; Parameter Estimation in Directed and Undirected Graphical Models; and Learning with Partially Observed Data (i.e. Expectation Maximization).
IFT1015: Introduction to Programming: (course website open only to enrolled students)