Montreal AI Symposium

The Montreal AI Symposium aims at gathering experts and professionals interested in fundamental advances and applications of artificial intelligence, with an emphasis on machine learning, deep learning and related approaches.
The Symposium welcomes both academic and industrial participants; it seeks to build strong connections between researchers within the Greater Montreal area.

We will feature a day-long event, filled with keynote addresses, contributed talks and posters, and time for networking and socializing.

The Symposium will be held on September 26th, 2017, and is hosted by École Polytechnique de Montréal. The event is free of charge for participants with mandatory registration (available in early September). It is easily accessible from the public transit system (“Université de Montréal” metro station – Blue line).

Live streaming [updated 2017-09-25]: Thanks to Polytechnique’s generous technical support, we are able to live-stream this event on social media. Follow these links:

Getting There

The event is held in the main building of École Polytechnique (noted “1” in the map below), in the Bernard-Lamarre auditorium on the 6th floor. Registration to the symposium will be done in front of the auditorium. There will be signs to guide you to the venue.

Schedule: September 26th, 2017

8.00 – 9.00


9.00 – 9.10

Opening Remarks

9.10 – 9.50

Keynote — Artificial Intelligence Goes All-In: Computers Playing Poker
Michael Bowling, University of Alberta and DeepMind

9.50 – 10.10

Contributed talk — A Distributional Perspective on Reinforcement Learning
Marc G. Bellemare, Google Brain

10.10 – 10.30

Contributed talk — Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
Ryan Lowe, McGill University, OpenAI; Yi Wu, UC Berkeley; Aviv Tamar, UC Berkeley; Jean Harb, McGill University, OpenAI; Pieter Abbeel, UC Berkeley, Openai; Igor Mordatch, OpenAI

10.30 – 11.00

Coffee break

11.00 – 11.20

Contributed talk — Team Sports Modelling
Norm Ferns, SPORTLOGiQ; Mehrsan Javan, SPORTLOGiQ

11.20 – 11.40

Contributed talk — FigureQA: An annotated figure dataset for visual reasoning
Samira Ebrahimi Kahou, Microsoft; Adam Atkinson, Microsoft; Vincent Michalski, University of Montreal; Akos Kadar, Microsoft; Adam Trischler, Microsoft; Yoshua Bengio, University of Montreal

11.40 – 12.00

Contributed talk — FiLM: Visual Reasoning with a General Conditioning Layer
Ethan Perez, MILA and Rice University; Harm de Vries, MILA; Florian Strub, Université Lille; Vincent Dumoulin, MILA; Aaron Courville, MILA and CIFAR

12.00 – 13.30


13.30 – 14.10

Keynote — Deep Learning for Self-Driving Cars
Raquel Urtasun, University of Toronto and Uber

14.10 – 14.30

Contributed Talk — Deep 6-DOF Tracking
Mathieu Garon, Université Laval; Jean-François Lalonde, Université Laval

14.30 – 14.50

Contributed Talk — Deep Learning for Character Animation
Daniel Holden, Ubisoft Montreal

14.50 – 15.20

Coffee Break

15.20 – 15.40

Contributed Talk — Assisting combinatorial chemistry in the search of highly bioactive peptides
Prudencio Tossou, Université Laval; Mario Marchand, Université Laval; François Laviolette, Université Laval

15.40 – 16.00

Contributed Talk — Saving Newborn Lives at Birth through Machine Learning
Charles Onu, Ubenwa Intelligence Solutions Inc; Doina Precup, McGill University

16.00 – 16.20

Contributed Talk — Meticulous Transparency — A Necessary Practice for Ethical AI
Abhishek Gupta ; Dr. David Benrimoh

16:20 – 17.00

Community Town Hall

17.00 – 20.00

Poster Session + Happy Hour with Sponsors

List of accepted posters

Keynote Speakers

Michael Bowling is a Professor of Computing Science at the University of Alberta. He is also one of the senior scientists at DeepMind Alberta. His research focuses on artificial intelligence, machine learning, and game theory; and he is particularly fascinated by the problem of how computers can learn to play games through experience. Michael led the team that developed Polaris, the first computer program to defeat top professional players in heads-up limit poker; Cepheus, the first computer program to solve a human-scale poker game; and DeepStack, the first computer program to beat professional players at heads-up no-limit poker. He also started the Arcade Learning Environment, a reinforcement learning testbed now used around the world. And if you ask him, he will tell you more than you wanted to know about AI for the olympic sport of curling. Raquel Urtasun is the Head of Uber ATG Toronto. She is also an Associate Professor in the Department of Computer Science at the University of Toronto, a Canada Research Chair in Machine Learning and Computer Vision and a co-founder of the Vector Institute for AI. Prior to this, she was an Assistant Professor at TTI Chicago. She was also a visiting professor at ETH Zurich during the spring semester of 2010. She received her Ph.D. degree from Ecole Polytechnique Federal de Lausanne (EPFL) in 2006 and did her postdoc at MIT and UC Berkeley. She is a world leading expert in machine perception for self-driving cars. Her research interests include machine learning, computer vision, robotics and remote sensing. Her lab was selected as an NVIDIA NVAIL lab. She is a recipient of an NSERC EWR Steacie Award, an NVIDIA Pioneers of AI Award, a Ministry of Education and Innovation Early Researcher Award, three Google Faculty Research Awards, an Amazon Faculty Research Award, a Connaught New Researcher Award and two Best Paper Runner up Prizes awarded at the Conference on Computer Vision and Pattern Recognition (CVPR) in 2013 and 2017 respectively.


The event is free of charge for participants. However, all attendees must register to attend the symposium. Moreover, we will send you a confirmation email two weeks prior to the symposium, to which you must respond in order to maintain your registration.

Update (2017-09-06): due to overwhelming demand, we have reached our maximum number of 300 participants and we must close registration for the time being. We may re-open the registration one week prior to the event if more spots becomes available.

Call for Contributions

We invite you to submit a contribution to the first Montreal AI symposium. We encourage submission of abstracts from both academic and industrial researchers, which can describe a technical or practical contribution, an open problem, an application or a position statement. Previously published material is acceptable. Do not include any confidential material.

Topics of interest include:

  • Fundamental research in deep learning, reinforcement learning, kernel machines, Bayesian modeling, ensemble methods, optimization for machine learning;
  • Implementation issues, parallelization, software platforms, hardware;
  • Applications, including vision, audio, speech, natural language processing, robotics, healthcare, bioinformatics.

Indicate your preference (short talk or poster) when submitting your abstract. Abstracts should be at most 5000 characters.

Submission deadline: August 18th, 2017.
(The call for contributions is now closed.)

Call for Sponsors

The organization of this event is entirely supported by sponsors, as registration is free of charge for attendees. Sponsors at the silver level or higher are offered space in the common area to showcase their activities and for recruitment purposes. We welcome additional sponsors at the bronze level:

$5K – Platinum (special mention at opening, mention on website, 1 table and 1 poster panel)

$2.5K – Gold (mention on website, 1 table and 1 poster panel)

$1K – Silver (mention on website, 1 table)

$250 – Bronze (mention on website)

If you are interested in sponsoring the Montreal AI Symposium, please contact the Symposium organizers.






Organizing Committee

Senior Program Chair: Hugo Larochelle, Google

Program Chairs:

  • Joëlle Pineau, McGill University
  • Adam Trischler, Microsoft
  • Nicolas Chapados, Element AI & Imagia

Local Chair: Guillaume Chicoisne, IVADO

Contact the