Montreal AI Symposium 2019

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. Information about the last year event can be found here.


Tweets by SymposiumAi



The Symposium will be held on September 6th, 2019, and is hosted at the University of Montreal. The event is free of charge for participants with mandatory registration. It is easily accessible from the public transit system (Station Université-de-Montréal / Éd.-Montpetit, blue line).

The day program (8am-5pm) will be held in the room K-500 of the Roger-Gaudry Building at the 2900 Boulevard Edouard-Montpetit, Montréal, QC H3T 1J4 (see the red star on the map below).

The poster session + reception (5-8pm) is held in the Hall L-400 of the same building.


Daycare will be offered for free during the symposium. However, registration will be mandatory.

Code of Conduct

This symposium aims at facilitating discussions and the exchange of ideas. We ask all participants to be respectful of others and to be aware of their own behaviour. Registration for the symposium will require signing the code of conduct available here.

Accepted Papers

List of accepted papers IDS can be found here.

Detailed list of oral and poster presentations available here.

Where will the posters be presented?
Main Hall – Posters 1 – 70
Hall of Medicine – Posters 71 – 80
M-425 – Posters 81 – 100


8.00 – 9.00Registration & Breakfast (provided)
9.00 – 9.10Opening Remarks
9.10 – 9.50Keynote – Shiri Azenkot – AI-Powered Access: Intelligent Interactive Systems to Support People with Visual Impairments
9.50 – 10.10Tackling Societal Problems of Climate Change with Machine Learning, Tegan Maharaj (MILA, Polytechnic Montreal); Sasha Luccioni (Mila); Kris Sankaran (Montreal Institute for Learning Algorithms)
10.10 – 10.30Temporal Knowledge Graph CompletionRishab Goel (Borealis AI); Seyed Mehran Kazemi (Borealis AI); Marcus Brubaker (Borealis AI); Pascal Poupart (Borealis AI)
10.30 – 11.00Coffee break
11.00 – 11.20Verifying Individual Fairness in Neural Networks, Golnoosh Farnadi (Polytechnique Montreal); Behrouz Babaki (Polytechnique Montreal); Michel Gendreau (Polytechnique Montreal)
11.20 – 11.40Gradient-Based Neural DAG Learning, Sebastien Lachapelle (Mila, Université de Montréal); Philippe Brouillard (Mila); Tristan Deleu (Mila, Université de Montréal); Simon Lacoste-Julien (Mila, Université de Montréal)
11.40 – 12.00Deep learning techniques applied to thermal inspection of the underground distribution cables, Arnaud Zinflou (Hydro-Québec); Michel Trepanier (Hydro-Québec); Olfa Ben Sik Ali (Hydro-Québec); Luc Cauchon (Hydro-Québec); François Miralles (Hydro-Québec); Marc-Andre Magnan (Hydro-Québec); Jonathan Racine (Hydro-Québec)

12.00 – 13.30Lunch (provided)
13.30 – 14.10Keynote – Suchi Saria – Safety Challenges with Deep Learning and Novel Approaches for Failure Proofing
14.10 – 14.30Kotlin∇: A Shape Safe eDSL for Differentiable Functional ProgrammingBreandan M Considine (Mila); Liam Paull (Université de Montréal); Michalis Famelis (Université de Montréal)
14.30 – 14.50Recurrent Language Modeling with Multiplicative RNNs, Diego Maupomé (UQÀM); Marie-Jean Meurs (UQAM)
14.50 – 15.20Coffee Break
15.20 – 15.40Cardiac MRI Segmentation with Strong Anatomical Guarantees, Nathan Painchaud (Université de Sherbrooke); Youssef Skandrani (Universite de Bourgogne Franche-Comté); Thierry Judge (Université de Sherbrooke); Olivier Bernard (Creatis); Alain Lalande (Universite de Bourgogne Franche-Comté); Pierre-Marc Jodoin (Universite de Sherbrooke)

15.40 – 16.00Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning, Mahmoud Assran (McGill University / Facebook AI Research); Joshua Romoff (McGill University); Nicolas Ballas (Facebook FAIR); Joelle Pineau (Facebook); Mike Rabbat (Facebook FAIR)
16.00 – 16.20Reducing Noise in GAN Training with Variance Reduced ExtragradientTatjana Chavdarova (Mila); Gauthier Gidel (Mila, Université de Montréal, Element AI); Francois Fleuret (Idiap Research Institute); Simon Lacoste-Julien (Mila, Université de Montréal)
16:20 – 17.00Panel – Artificial Intelligence at the Interface with Other Disciplines
17.00 – 20.00Poster Session + Happy Hour with Sponsors


Suchi Saria is the John C. Malone Assistant Professor at Johns Hopkins University where she directs the Machine Learning and Healthcare Lab. Her work with the lab enables new classes of diagnostic and treatment planning tools for healthcare—tools that use statistical machine learning techniques to tease out subtle information from “messy” observational datasets, and provide reliable inferences for individualizing care decisions.

Saria’s methodological work spans Bayesian and probabilistic approaches for addressing challenges associated with inference and prediction in complex, real-world temporal systems, with a focus in reliable ML, methods for counterfactual reasoning, and Bayesian nonparametrics for tackling sample heterogeneity and time-series data. 

Her work has received recognition in numerous forms including best paper awards at machine learning, informatics, and medical venues, a Rambus Fellowship (2004-2010), an NSF Computing Innovation Fellowship (2011), selection by IEEE Intelligent Systems to Artificial Intelligence’s “10 to Watch” (2015), the DARPA Young Faculty Award (2016), MIT Technology Review’s ‘35 Innovators under 35’ (2017), the Sloan Research Fellowship in CS (2018), the World Economic Forum Young Global Leader (2018), and the National Academies of Medicine (NAM) Emerging Leader in Health and Medicine (2018). In 2017, her work was among four research contributions presented by Dr. France Córdova, Director of the National Science Foundation to Congress’ Commerce, Justice Science Appropriations Committee. Saria received her PhD from Stanford University working with Prof. Daphne Koller.

Keynote title: Safety Challenges with Deep Learning and Novel Approaches for Failure Proofing.

Shiri Azenkot is an Assistant Professor of Information Science at Cornell Tech, the new Cornell University campus in New York City. Her research lies in the intersection of technology, disability, and interaction. She likes building things and discussing their sociocultural implications. In particular, Shiri’s research focuses on designing intelligent interactive systems for people with visual impairments. She has published at top-tier human-computer interaction and accessibility venues such as ACM CHI, ACM ASSETS, and ACM UIST, receiving multiple best paper awards and nominations. Shiri is also the founder of the XR Access Initiative (, a broad academic-industry partnership to make augmented and virtual reality accessible from the ground up. She received her PhD in computer science from the University of Washington and her BA, also in computer science, from Pomona College. 

Keynote title: AI-Powered Access: Intelligent Interactive Systems to Support People with Visual Impairments

Abstract: As artificial intelligence advances, it presents opportunities to address human needs in new ways. I aim to leverage advances in AI to solve problems of equity for people with diverse abilities. The US Census Bureau estimates that about 20 percent of Americans have a disability, meaning that they face significant barriers in their daily lives because their needs and abilities differ from what is typically considered “mainstream.” In my research, I conduct studies to understand these specific barriers and design intelligent interactive systems that help people overcome them. In my talk, I will describe several recent projects involving people with visual impairments, both blind and low vision. The projects aim to help people with visual impairments learn STEM concepts, navigate, and engage with others on social networking sites. I will conclude with open questions for the community on how to ensure that advances in AI empower (instead of further marginalize) all people, regardless of (dis)ability.


Title: Artificial Intelligence at the Interface with Other Disciplines

Abstract: Artificial intelligence has begun to impact research and development in a variety of disciplines–including the social sciences and humanities–and domains–including health care and education.  While AI has contributed to a variety of areas, there are opportunities to broaden the impact to new disciplines or to incorporate insights from other disciplines.  The focus of this panel is to more deeply understand how AI influences the disciplines it interacts with and how researchers can learn from and work with stakeholders those outside of the AI community.  This panel will be a conversation between individuals from diverse disciplines.


  • Suchi Saria (Johns Hopkins University)
  • Pablo Samuel Castro (Google)
  • Fenwick McKelvey (Concordia University)
  • Doina Precup (McGill University/DeepMind)


To prevent the event from being full immediately, an unlimited number of pre-registrations will be open from August 12th to August 21st. Applicants can pre-register by following this link.

By August 23rd, participants will be chosen at random among those who pre-registered, based on the capacity of the venue. For every accepted paper, one of its authors will have a guaranteed participation. The random draw will not be uniform as the organizers will try to get as representative an attendance as possible. To that end, we encourage you to fill in the demographics questionnaire which, with your approval, will be used for the random draw.*

Once the participations have been chosen, each participant will need to confirm their attendance. If they do not, the registration will be relinquished. Participants who cannot attend can also choose to voluntarily relinquish their registration until 2 days prior to the event. Participants who are registered but do not come to the symposium might be barred from next year’s event. This is to ensure as many people as possible will attend this event.

*We are concerned about barriers faced by people with particular identity profiles which may limit their participation in the field. As an early step of any coordinated effort to reduce these barriers and hopefully increase the participation of underrepresented groups, we wanted to characterize our community according to various dimensions of identity. It is important for us to do this in a way that allows people to voluntarily and accurately self-identify but is also standardized and easy to analyze in an anonymized way. These data can be used to better understand the specific needs of our community members, track our efforts to increase diversity over time, compare the makeup of different communities/conferences and establish base-rates for certain identities. For MAIS 2019, following the successful experience of MAIS 2018, we use the voluntarily self-identified demographic information to have a fair representation of participants.

Call for Contributions

We invite you to submit a contribution to the third Montreal AI symposium. We encourage the 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 but are not limited to:

  • Fundamental research in deep learning, reinforcement learning, kernel machines, Bayesian modelling, ensemble methods, optimization for machine learning;
  • Implementation issues, parallelization, software platforms, hardware;
  • Fairness, Accountablity, Transparency and Ethics in AI.
  • Intersection of AI and Art.
  • Applications, including vision, audio, speech, natural language processing, robotics, healthcare, bioinformatics.

Instructions for abstract submission

Submissions will be handled electronically via the symposium’s CMT website: You will be asked to create a CMT account if you do not already have one. All abstracts must be written in English.

To create a new submission, click on ‘Create new submission’. You will be asked to select your subject area and indicate your conflicts of interest as well as your preference for presentation format (short talk or poster).  Abstracts should be at most two pages in 10pt font, not including references. Note that there is no specific format for submissions and any standard format is accepatable (e.g: ICML, ICLR, NeurIPS, ACM MM).

Reviews are double-blind: submissions revealing the authors’ identities will be automatically rejected. When citing your previous work, refrain from using ‘we’ or ‘our’. We accept previously published material (including pre-prints) but we ask you not to cite this material to maintain anonymity during the reviewing period. We also ask you to omit acknowledgments in your submission.

Extended Submission deadline: July 5 2019, 17:00 EST.

Submission deadline: June 28 2019, 17:00 EST.

Notification of acceptance: August 9 2019.

Call for Sponsors

The organization of this event is entirely supported by sponsors, as registration is free of charge for attendees.

If you are interested in learning about our sponsorship offers for the Montreal AI Symposium, please contact the Symposium organizers.

Land acknowledgement

We would like to acknowledge that the University of Montreal is located on unceded Indigenous lands.
The Kanien’kehá:ka Nation is recognized as the custodians of the lands and waters on which we gather for this event.
Tiohtiá:ke/Montreal is historically known as a gathering place for many First Nations.
Today, it is home to a diverse population of Indigenous and other peoples.
We respect the continued connections with the past, present and future in our ongoing relationships with Indigenous and other peoples within the Montreal community.

Organizing Committee

Senior Program Chair:

  • Negar Rostamzadeh, Element AI

Program Chairs:

  • Laurent Charlin, MILA, Université de Montréal/ HEC
  • Adriana Romero, Facebook AI Research/ McGill
  • Fernando Diaz, Microsoft Research

Local Chair:

  • Émélie Brunet, MILA, Université de Montréal

Diversity and Inclusion Chairs:

  • Laurent Dinh, Google Brain
  • Hana Nagel, Element AI

Contact the

Contact the diversity and inclusion





%d bloggers like this: