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 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.
Instruction style: We will spend approximately 25-50% of the class time working through questions. Students are responsible for keeping up-to-date with the course material outside of class time, mainly by reading the textbook. The material to be reviewed for each class will be made available on the course website.
Département d’informatique et recherche opérationnelle (DIRO)
Université de Montréal
- Mondays: 2:30 – 4:30 PM (Z-220 Pav. Claire-McNicoll)
- Thursdays: 9:30 – 11:30 AM (1360 Pav. André-Aisenstadt)
Office Hours (with the Prof)
- Fridays: 11:00 AM– 12:00 PM (3253 Pav. André-Aisenstadt)
- The final exam will take place in class on the final lecture: April 13th, 2017 in 1360 Pav. André-Aisenstadt.
- The exam will be 3 hours long: 9h00-12h00 (confirmed).
- Your questions/answers are due April 20th, 2017.
- The class project is due April 30th, 2017. By this date your blog should be complete, presenting your problem statement, your approach (in detail) and your results.
Previous Exams (Note: course material has changed since 2015)