CVPR 2019

Accepted Papers

DeepFlux for Skeletons in the Wild
By Yukang Wang, Yongchao Xu, Stavros Tsogkas, Xiang Bai, Sven Dickinson, Kaleem Siddiqi


Scene Categorization from Contours: Medial Axis Based Salience Measures
By Morteza Rezanejad, Gabriel Downs, John Wilder, Dirk B. Walther, Allan Jepson, Sven Dickinson, Kaleem Siddiqi


ICLR 2019

Accepted Papers

Explaining Image Classifiers by Counterfactual Generation
By Chun-Hao Chang, Elliot Creager, Anna Goldenberg, David Duvenaud


Visual Reasoning by Progressive Module Networks
By Seung Wook Kim, Makarand Tapaswi, Sanja Fidler


Three Mechanisms of Weight Decay Regularization
By Guodong Zhang, Chaoqi Wang, Bowen Xu, Roger Grosse


LanczosNet: Multi-Scale Deep Graph Convolutional Networks
By Renjie Liao, Zhizhen Zhao, Raquel Urtasun, Richard Zemel


Excessive Invariance Causes Adversarial Vulnerability
By Joern-Henrik Jacobsen, Jens Behrmann, Richard Zemel, Matthias Bethge


Neural Graph Evolution: Automatic Robot Design
By Tingwu Wang, Yuhao Zhou, Sanja Fidler, Jimmy Ba


DOM-Q-NET: Grounded RL on Structured Language
By Sheng Jia, Jamie Ryan Kiros, Jimmy Ba


TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre Transfer
By Sicong Huang, Qiyang Li, Cem Anil, Xuchan Bao, Sageev Oore, Roger B. Grosse


Dimensionality Reduction for Representing the Knowledge of Probabilistic Models
By Marc T Law, Jake Snell, Amir-massoud Farahmand, Raquel Urtasun, Richard S Zemel


Aggregated Momentum: Stability Through Passive Damping
By James Lucas, Shengyang Sun, Richard Zemel, Roger Grosse


Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions
By Matthew Mackay, Paul Vicol, Jonathan Lorraine, David Duvenaud, Roger Grosse


Graph HyperNetworks for Neural Architecture Search
By Chris Zhang, Mengye Ren, Raquel Urtasun


Functional Variational Bayesian Neural Networks
By Shenyang Sun, Guodong Zhang, Jiaxin Xi, Roger Grosse.

Accepted Oral

FFJORD: Free-Form Continuous Dynamics for Scalable Reversible Generative Models
By Will Grathwohl, Ricky T. Q. Chen, Jesse Bettencourt, Ilya Sutskever, David Duvenaud

NIPS 2018

Accepted Papers

Neural Guided Constraint Logic Programming for Program Synthesis
By Lisa Zhang · Gregory Rosenblatt · Ethan Fetaya · Renjie Liao · William Byrd · Matthew Might · Raquel Urtasun · Richard Zemel


Learning Latent Subspaces in Variational Autoencoders
By Jack Klys · Jake Snell · Richard Zemel


Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer
By David Madras · Toni Pitassi · Richard Zemel


Reversible Recurrent Neural Networks
By Matthew MacKay · Paul Vicol · Jimmy Ba · Roger Grosse


On the Convergence and Robustness of Training GANs with Regularized Optimal Transport
By Maziar Sanjabi · Jimmy Ba · Meisam Razaviyayn · Jason Lee


Neural Ordinary Differential Equations
By Tian Qi Chen · Yulia Rubanova · Jesse Bettencourt · David Duvenaud


Isolating Sources of Disentanglement in Variational Autoencoders
By Tian Qi Chen · Xuechen Li · Roger Grosse · David Duvenaud


Iterative Value-Aware Model Learning
By Amir-massoud Farahmand


A Neural Compositional Paradigm for Image Captioning
By Bo Dai · Sanja Fidler · Dahua Lin


Online Structure Learning for Feed-Forward and Recurrent Sum-Product Networks
By Abdullah Rashwan · Agastya Kalra · Pascal Poupart · Prashant Doshi · Georgios Trimponias · Wei-Shou Hsu


Monte-Carlo Tree Search for Constrained POMDPs
By Jongmin Lee · Geon-hyeong Kim · Pascal Poupart · Kee-Eung Kim


Unsupervised Video Object Segmentation for Deep Reinforcement Learning
By Vikash Goel · Jameson Weng · Pascal Poupart


Deep Homogeneous Mixture Models: Representation, Separation, and Approximation
By Priyank Jaini · Pascal Poupart · Yaoliang Yu


Data-dependent PAC-Bayes priors via differential privacy
By Gintare Karolina Dziugaite · Daniel Roy


Nearly tight sample complexity bounds for learning mixtures of Gaussians via sample compression schemes
By Hassan Ashtiani, Shai Ben-David, Nick Harvey, Chris Liaw, Abbas Mehrabian, Yaniv Plan


Non-convex Optimization with Discretized Diffusions
By Murat A Erdogdu, Lester Mackey, Ohad Shamir


Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures
By Sergey Bartunov, Adam Santoro, Blake Richards, Luke Marris, Geoffrey E Hinton, Timothy Lillicrap


Occam’s razor is insufficient to infer the preferences of irrational agents
By Stuart Armstrong, Sören Mindermann


Machine Learning for Health (ML4H): Moving beyond supervised learning in healthcare
Andrew Beam · Tristan Naumann · Marzyeh Ghassemi · Matthew McDermott · Madalina Fiterau · Irene Y Chen · Brett Beaulieu-Jones · Michael Hughes · Farah Shamout · Corey Chivers · Jaz Kandola · Alexandre Yahi · Samuel G Finlayson · Bruno Jedynak · Peter Schulam · Natalia Antropova · Jason Fries · Adrian Dalca

ICML 2018

Accepted Papers and Oral

Neural Relational Inference for Interacting Systems
By Thomas Kipf · Ethan Fetaya · Kuan-Chieh Wang · Max Welling · Richard Zemel


Distilling the Posterior in Bayesian Neural Networks
By Kuan-Chieh Wang · Paul Vicol · James Lucas · Li Gu · Roger Grosse · Richard Zemel


Reviving and Improving Recurrent Back-Propagation
By Renjie Liao · Yuwen Xiong · Ethan Fetaya · Lisa Zhang · KiJung Yoon · Zachary S Pitkow · Raquel Urtasun · Richard Zemel


Learning Adversarially Fair and Transferable Representations
By David Madras · Elliot Creager · Toniann Pitassi · Richard Zemel


Inference Suboptimality in Variational Autoencoders
By Chris Cremer · Xuechen Li · David Duvenaud


Noisy Natural Gradient as Variational Inference
By Guodong Zhang · Shengyang Sun · David Duvenaud · Roger Grosse


Reinforcement Learning with Function-Valued Action Spaces for Partial Differential Equation Control
By Yangchen Pan · Amir-massoud Farahmand · Martha White · Saleh Nabi · Piyush Grover · Daniel Nikovski


Differentiable Compositional Kernel Learning for Gaussian Processes
By Shengyang Sun · Guodong Zhang · Chaoqi Wang · Wenyuan Zeng · Jiaman Li · Roger Grosse


Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors
By Gintare Karolina Dziugaite · Daniel Roy


Learning to Reweight Examples for Robust Deep Learning
By Mengye Ren · Wenyuan Zeng · Bin Yang · Raquel Urtasun


Nature: International Journal of Science

Published Letter

Observation of topological phenomena in a programmable lattice of 1,800 qubits

By Andrew D. King, Juan Carrasquilla, Jack Raymond, Isil Ozfidan, Evgeny Andriyash, Andrew Berkley, Mauricio Reis,  Trevor Lanting, Richard Harris, Fabio Altomare, Kelly Boothby, Paul I. Bunyk, Colin Enderud, Alexandre Fréchette,  Emile Hoskinson, Nicolas Ladizinsky, Travis Oh, Gabriel Poulin-Lamarre, Christopher Rich, Yuki Sato,  Anatoly Yu. Smirnov, Loren J. Swenson, Mark H. Volkmann1, Jed Whittaker1, Jason Yao1, Eric Ladizinsky, Mark W. Johnson, Jeremy Hilton & Mohammad H. Amin

Published Article

Machine learning for MEG during speech tasks

By Demetres Kostas, Elizabeth W. Pang & Frank Rudzicz

CVPR 2018


Now You Shake Me: Towards Automatic 4D Cinema
By Yuhao Zhou, Makarand Tapaswi and Sanja Fidler
Spotlight 3330


MovieGraphs: Towards Understanding Human-Centric Situations from Videos
By Paul Vicol, Makarand Tapaswi, Lluís Castrejón and Sanja Fidler
Spotlight 3308

Accepted Posters

Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++
By David Acuna, Huan Ling, Amlan Kar and Sanja Fidler
Poster 3409


Learning to Act Properly: Predicting and Explaining Affordances from Images
By Ching-Yao Chuang, Jiaman Li, Antonio Torralba and Sanja Fidler
Poster 631


SurfConv: Bridging 3D and 2D Convolution for RGBD Images
By Hang Chu, Wei-Chiu Ma, Kaustav Kundu, Raquel Urtasun and Sanja Fidler
Poster 711


A Face to Face Neural Conversation Model
By Hang Chu and Sanja Fidler
Poster 710


Now You Shake Me: Towards Automatic 4D Cinema
By Yuhao Zhou, Makarand Tapaswi and Sanja Fidler
Poster 3330


VirtualHome: Simulating Household Activities via Programs
By Xavier Puig, Kevin Ra, Marko Boben, Jiaman Li, Tingwu Wang, Sanja Fidler and Antonio Torralba
Poster 3399


MovieGraphs: Towards Understanding Human-Centric Situations from Videos
By Paul Vicol, Makarand Tapaswi, Lluís Castrejón and Sanja Fidler
Poster 3308


Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points
By Fabien Baradel, Christian Wolf, Julien Mille, and Graham Taylor
Poster 182


VirtualHome: Simulating Household Activities via Programs
By Xavier Puig, Kevin Ra, Marko Boben, Jiaman Li, Tingwu Wang, Sanja Fidler and Antonio Torralba
Oral 3399

ICLR 2018

Accepted Papers

Kronecker-factored Curvature Approximations for Recurrent Neural Networks

By James Martens, Jimmy Ba, Matt Johnson


Quantitatively Evaluating GANs With Divergences Proposed for Training

By Daniel Jiwoong Im, Alllan He Ma, Graham W. Taylor, Kristin Branson


Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches

By Yeming Wen, Paul Vicol, Jimmy Ba, Dustin Tran, Roger Grosse


Attacking Binarized Neural Networks

By Angus Galloway, Graham W. Taylor, Medhat Moussa


Meta-Learning for Semi-Supervised Few-Shot Classification

By Mengye Ren, Sachin Ravi, Eleni Triantafillou, Jake Snell, Kevin Swersky, Josh B. Tenenbaum, Hugo Larochelle, Richard S. Zemel


Backpropagation through the Void: Optimizing control variates for black-box gradient estimation

By Will Grathwohl, Dami Choi, Yuhuai Wu, Geoff Roeder, David Duvenaud


Understanding Short-Horizon Bias in Stochastic Meta-Optimization

By Yuhuai Wu, Mengye Ren, Renjie Liao, Roger Grosse


NerveNet: Learning Structured Policy with Graph Neural Networks

By Tingwu Wang, Renjie Liao, Jimmy Ba, Sanja Fidler

Workshop Papers

Predict Responsibly: Increasing Fairness by Learning to Defer

By David Madras, Toniann Pitassi, Richard Zemel


Isolating Sources of Disentanglement in Variational Autoencoders

By Tian Qi Chen, Xuechen Li, Roger Grosse, David Duvenaud


Graph Partition Neural Networks for Semi-Supervised Classification

By Renjie Liao, Marc Brockschmidt, Daniel Tarlow, Alexander Gaunt, Raquel Urtasun, Richard S. Zemel


Gradient-based Optimization of Neural Network Architecture

By Will Grathwohl, Elliot Creager, Seyed Ghasemipour, Richard Zemel


Reconstructing evolutionary trajectories of mutations in cancer

By Yulia Rubanova, Ruian Shi, Roujia Li, Jeff Wintersinger, Amit Deshwar, Nil Sahin, Quaid Morris


Inference in probabilistic graphical models by Graph Neural Networks

By KiJung Yoon, Renjie Liao, Yuwen Xiong, Lisa Zhang, Ethan Fetaya, Raquel Urtasun, Richard Zemel, Xaq Pitkow


Leveraging Constraint Logic Programming for Neural Guided Program Synthesis

By Lisa Zhang, Gregory Rosenblatt, Ethan Fetaya, Renjie Liao, William Byrd, Raquel Urtasun, Richard Zemel


Deep Learning and Reinforcement Learning Summer School 2018

2018- Deep Learning Summer School

Katherine A. Heller, Department of Statistical Science, Duke University
Title: Introduction to Machine Learning

Hugo Larochelle, Google
Title: Neural Networks I

David Duvenaud, Department of Computer Science, University of Toronto
Title: Autodiff

Hugo Larochelle, Google
Title: Neural Networks II

Jonathon Shlens, Google
Title: Introduction to Convolutional Neural Networks (CNNs)

Sanja Fidler, Department of Computer Science, University of Toronto
Title: Advanced Deep Vision

Balázs Kégl, Laboratoire de l Accélérateur Linéaire, University of Paris-Sud 11
Title: RAMP (Practical session)

David Duvenaud, Department of Computer Science, University of Toronto
Title: Generative Models I

Been Kim, Google
Title: Interpretability

Sanjeev Arora, Department of Computer Science, Princeton University
Title: Theory

Jimmy Ba, Department of Computer Science, University of Toronto
Title: Optimization I

Jorge Nocedal, Robert R. McCormick School of Engineering and Applied Science, Northwestern University
Title: Optimization II

Yoshua Bengio, Department of Computer Science and Operations Research, University of Montreal
Title: Recurrent Neural Networks (RNNs)

Graham Neubig,  Language Technologies Institute, Carnegie Mellon University
Title: Language Understanding

Jamie Kiros, Department of Computer Science, University of Toronto
Title: Multimodal Learning

Blake Aaron Richards, Centre for the Neurobiology of Stress (CNS), University of Toronto Scarborough
Title: Computational Neuroscience

Andrew Gordon Wilson, Department of Computer Science, Cornell University
Title: Bayesian Neural Nets

Sageev Oore, Vector Institute
Title: Deep Learning and Music

2018- Reinforcement Learning Summer School

Richard S. Sutton, Department of Computing Science, University of Alberta
Title: Introduction to RL and TD

Sergey Levine, Department of Electrical Engineering and Computer Sciences, UC Berkeley
Title: Policy Search

Amir-massoud Farahmand, Vector Institute
Title: Batch RL and ADP

Martha White, Department of Computing Science, University of Alberta
Title: Off-Policy Learning

Tor Lattimore, DeepMind Technologies Limited
Title: Bandits and Explore/Exploit in RL

Doina Precup, School of Computer Science, McGill University
Title: Temporal Abstraction

Emma Brunskill, Computer Science Department, Carnegie Mellon University
Title: Multi-task and Transfer in RL

Marc G. Bellemare, Google
Title: Deep RL

Hal Daumé III, Department of Computer Science, University of Maryland
Title: Imitation Learning

Mohammad Ghavamzadeh, INRIA Lille – Nord Europe
Title: Safety in RL

Michael Bowling, Department of Computing Science, University of Alberta
Title: Multi-agent RL


Presented at The Fields Institute

Vector Logo


Presented at Fields Institute

Barak Pearlmutter, Hamilton Institute, Maynooth
Near-Criticality and Pathology in the Central Nervous System

Suchi Saria, Johns Hopkins University
Individualizing Healthcare with Machine Learning (Video)

Peter Grünwald, Leiden University
Learning the learning rate: how to repair Bayes when the model is wrong (Video)

Emma Brunskill, Stanford University
Reinforcement Learning When Experience is Expensive (Video)

Josh Tenenbaum, Massachusetts Institute of Technology
Building machines that learn and think like humans (Video)

Chris Maddison, University of Oxford
Relaxed Gradient Estimators (Video)

Yair Weiss, Hebrew University
Learning the Statistics of Full Images (Video)

Christopher Manning, Stanford University
Towards a better model for neural network reasoning (Video)

Vlad Mnih, DeepMind
Efficient Multi-Task Deep Reinforcement Learning (Video)

Stephen Friend, Sage Bionetworks
Exploring fundamental unknowns that prevent us from using our devices to navigate between disease and health (Video)

Ilya Sutskever, OpenAI
Meta Learning and Self Play (Video)

Yee Whye Teh, University of Oxford
DisTraL: Distill and Transfer for Deep Multitask Reinforcement Learning (Video)

Guang Wei Yu (Layer 6), Mohammad Islam (Wattpad), Putra anggala (Shopify), and Javier Moreno (Rubikloud)
Recommendation Systems (Video)

Jennifer Listgarten, Microsoft Research
From Genetics to CRISPR Gene Editing with Machine Learning (Video)

Chris Williams, Univeristy of Edinburgh
Artificial Intelligence for Data Analytics (Video)

Jon Shlens, Google Brain
Learning representations of the visual world

Geoffrey Hinton, University of Toronto
What is wrong with convolutional neural nets? (Video)


Presented at Fields Institute

David Sontag, Massachusetts Institute of Technology
How is Machine Learning Going to Change Health Care? (Video)

Alex Graves, DeepMind
Frontiers in Recurrent Neural Network Research

Max Welling, University of Amsterdam
Generalizing convolutions for Deep Learning (Video)

Ernest Earon, Precision Hawk
Airborne Intelligence: Why birds are so good at what they do (Video)

James Bergstra, Kindred
From Teleoperation to AGI (Video)

Ryan Geriepy, ClearPath Robotics
3 Steps To Applying Machine Learning To Fleets Of Self-Driving Vehicles (Video)

Shane Gu, Cambridge University
Sample-Efficient Deep Reinforcement Learning for Robotics (Video)

David Blei, Columbia University
Probabilistic Topic Models and User Behavior (Video)

Fernanda Viegas, Martin Wattenberg and Daniel Smilkov, Google
Visualization for machine learning–and human learning, too (Video)

Roger Melko, University of Waterloo
Machine Learning Quantum Physics (Video)

Pieter Abbeel, University of California, Berkeley
Deep Reinforcement Learning for Robotics (Video)

Roger Grosse, University of Toronto
Optimizing neural networks using structured probabilistic models (Video)

Graham Taylor, University of Guelph
Dataset Augmentation in Feature Space (Video)

Rob Fergus, New York University / Facebook
Memory and Communication in Neural Networks (Video)

Hugo Larochelle, Google Brain

Autoregressive Generative Models with Deep Learning (Video)


Michael Schull, Institute for Clinical Evaluative Sciences
ICES: Linking data and discovery, and building a health data science agenda (Video)

Alexandre Le Bouthillier, Imagia
Imagia: Artificial Intelligence for medical image analysis (Video)

Brendan Frey, Deep Genomics
Deep Genomics: Changing the course of genomic medicine (Video)

Joshua Landy, Figure 1
Figure 1: The computer will see you now (Video)

Ofer Shai, Meta Inc.
Meta: Unlocking the world’s scientific and technical insights (Video)

Roger Grosse, David Duvenaud and Sanja Fidler,, University of Toronto
Meet the New Faculty: Roger Grosse, David Duvenaud & Sanja Fidler (Video)

Andrew McCallum, University of Massachusetts
Universal Schema for Representation and Reasoning from Natural Language (Video)

Richard Sutton, University of Alberta
The Future of Artificial Intelligence Belongs to Search and Learning (Video)

Geoffrey Hinton, University of Toronto
Using Fast Weights to Store Temporary Memories (Video)

Amir Ban, Tel-Aviv University
When Should an Expert Make a Prediction? (Video)



Yaoliang Yu, University of Toronto
Deep Homogeneous Mixture Models: Representation, Separation and Approximation (Video)
Vector Institute

Sheila McIlraith, University of Toronto
High-level Reward Function Specification in Reinforcement Learning (Video)
Vector Institute

Babak Taati, University of Toronto
Vector Institute

Yuri Boykov, University of Toronto
Image Segmentation without Full Supervision (Video)
Vector Institute


Gillian Hadfield, University of Toronto
AI Alignment and Human Normativity (Video)
Vector Institute

Scott Sanner, University of Toronto
Autoencoders for Collaborative Filtering (Video)
Vector Institute

Peter Wittek, University of Toronto
Machine Learning on Near-Term Quantum Computers (Video)
Vector Institute

Jesse Hoey, University of Waterloo
Affective Dynamics and Control in Group Processes (Video)
Vector Institute

Andreas Moshovos, University of Toronto
Value-Based Deep Learning Hardware Acceleration (Video)
Vector Institute

Micheal Brudno, University of Toronto
Improving Doctor-Patient Interaction with AI-Enabled Medical Note Taking (Video)
Vector Institute



Bartha Knoppers, McGill University
Data Sharing and the Human Right to Benefit From Science and its Applications (Video)
Vector Institute

Yin Aphinyanaphongs, NYU Langone Health
Clinical Predictive Analytics at NYU Langone Health (Video)
Vector Institute


Samantha Kleinberg, Stevens Institute of Technology
Large-scale causal inference in bio-medicine (Video)
Vector Institute

Responsible AI


Presented at Centre of Ethics, University of Toronto

Richard Zemel, University of Toronto
Ensuring Fair and Responsible Automated Decisions (Video)
Centre of Ethics, University of Toronto

Frank Rudzicz, University of Toronto, University Health Network, Winterlight Labs
The Future of Automated Healthcare (Video)
Centre of Ethics, University of Toronto


Taking Responsibility for Responsible AI

On August 26, Join the Vector Institute and the Schwartz Reisman Institute for Technology and Society hosted Chris Meserole of the Brookings Institution to explore opportunities to collaborate on advancing the Vector Institute’s vision to use AI to foster economic growth and improve the lives of Canadians.

Canada was the first country to announce a national AI strategy in 2017. The world quickly followed suit. The same year, China announced its intent to become the world’s AI leader by 2030 and shortly after, the United States launched the American AI Initiative.

Recognizing the transformative potential of AI, organizations are evolving to handle complex interdisciplinary questions. MIT launched the Schwarzman College and Stanford established the Institute for Human-Centered Artificial Intelligence (HAI). Companies are hiring ethicists, developing ethical AI principles, and investing in related initiatives.

Right here in Toronto, the largest ever donation to the University of Toronto will establish the Schwartz Reisman Institute for Technology and Society to harness strengths across disciplines. And governments are exploring digital governance principles.

Canada’s concentration of world-class machine learning scientists presents a major opportunity to turn knowledge into economic competitiveness. What will the roles of governments and businesses be in maximizing Canada’s economic opportunity while protecting Canadians’ rights and values? Will we be leaders or laggards?


Taking Responsibility for Responsible AI

Gillian Hadfield: Faculty Affiliate, Vector Institute; Inaugural Director, Schwartz Reisman Institute for Technology and Society and Schwartz Reisman Chair in Technology and Society; Professor of Law and Strategic Management at the University of Toronto Rotman School of Management

Topic: Overview: Schwartz-Reisman Institute for Technology and Society


Graham Taylor: Canada CIFAR AI Chair and Faculty Member, Vector Institute; Academic Director, University of Guelph Centre for Advancing Responsible and Ethical Artificial Intelligence (CARE-AI); Associate Professor and Canada Research Chair in Machine Learning, School of Engineering, University of Guelph; Visiting Faculty, Google Brain Montreal (until 2019-05); Academic Director, NextAI

Topic: Overview: University of Guelph Centre for Advancing Responsible and Ethical Artificial Intelligence (CARE-AI)


David Madras: PhD Student in the Machine Learning Group at the University of Toronto and the Vector Institute

Topic: Machine learning in decision-making systems


Aleksandar Nikolov: Professor, Department of Computer Science, University of Toronto; Canada Research Chair in Algorithms and Private Data Analysis

Topic: Differential Privacy: Rigorously Private Data Analysis


Sheila McIlraith: Faculty Affiliate, Vector Institute; Professor, Department of Computer Science, University of Toronto

Topic: AI Safety


Melissa McCradden: Postdoctoral Fellow in Ethics of AI in Healthcare, Department of Bioethics and Genetics & Genome Biology at The Hospital for Sick Children and Vector Institute

Research interests: Translation of AI tools into clinical care, neuroethics, paediatric bioethics, and sport ethics


Shalmali Joshi: Postdoctoral Fellow, Vector Institute

Topic: Towards safe deployment of (clinical) machine learning models


Frank Rudzicz: Canada CIFAR AI Chair and Faculty Member, Vector Institute; Director of AI, Surgical Safety Technologies Incorporated; Scientist, International Centre for Surgical Safety, Li Ka Shing Knowledge Institute, St Michael’s Hospital; Associate Professor, Department of Computer Science, University of Toronto

Topic: AI safety, explainable AI in the operating room, standards for evaluating ML models


Charles Morgan: President, International Technology Law Association (ITechLaw); Partner, McCarthy Tétrault

Topic: ITech Law’s recently published “Responsible AI: A Global Policy Framework”


Chris Meserole: Fellow in Foreign Policy at the Brookings Institution and Deputy Director of the Brookings Artificial Intelligence and Emerging Technology Initiative

Advancing AI: A Framework and Agenda for Cross-Disciplinary Research

Abstract: Technical breakthroughs in deep learning architectures, such as capsule networks and transformers, continue to drive forward the state-of-the-art in AI performance. Likewise, research on the ethical, legal, and social implications (ELSI) of AI has also advanced rapidly in recent years, most notably the work on ethical principles. Yet most AI scholarship remains relatively siloed, despite the urgent need for work informed by both technical and non-technical fields. This talk aims to sketch a brief framework and agenda for cross-disciplinary research on AI.


Scroll to Top