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 review recent work on Attention mechanism and efforts to incorporant memory structures into neural network models. We will also consider some probabilistic graphical models, including undirected models such as the Boltzmann machines and especially directed models that have recently shown promise.
The course will use the textbook: Deep Learning by Ian Goodfellow, Yoshua Bengio and Aaron Courville (available for order at amazon or online for free here).
Instruction style: The lecture time will mostly be devoted to traditional lectures, but we will spend approximately 10-20% 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 this course website.
Evaluation: The course will include a set of 3-5 assignments. Each assignment will consist of two components: (i) a set of theoretical questions, and (ii) practical component with a significant programming component. In addition to these assignments there will be a course project and a final exam. The practical components of assignments as well as the course project can be done in groups of 2 or 3 students. The theoretical component of the assignments is to be done individually.
The final grade will be composed as follows (modified based on majority vote in class):
- Assignments: 60%
- Course Project: 25%
- Final Exam: 15%
Département d’informatique et recherche opérationnelle (DIRO)
Université de Montréal
- Instructor: Prof. Aaron Courville
- Teaching assistants:
- Chin-Wei Huang (chin-wei.huang at umontreal.ca ),
- Sai Rajeshwar (rajsai24 at gmail.com)
- Shawn Tan (tanjings at iro.umontreal.ca)
-
Francis Dutil (frdutil at gmail.com)
Class schedule
- Mondays: 9:30 – 11:30 AM (G-415, pavillon Roger-Gaudry)
- Wednesdays: 12:30 – 2:30 PM (G-1015 Pav. Roger-Gaudry)
Office Hours (with the Prof)
- Mondays: 11:30 AM– 12:30 PM (G-415, pavillon Roger-Gaudry)
Important Dates:
- Final Exam: 04/16/2018 at 9h30 (location: G-415 Pav. Roger-Gaudry)
- Final Project Due: 05/7/2018 (Firm)
IFT6135 - Representation Learning 