Blog

Learn About Our Meetup

4500+ Members

Category: Vector Institute

Bengio, Hinton et LeCun acceptent le prix A.M. Turing 2018 de l’ACM à San Francisco

Les lauréats du prix A.M. Turing 2018 de l’ACM, Geoffrey Hinton, Yoshua Bengio et Yann LeCun, ont reçu le prix A.M. Turing de l’ACM au banquet de remise des prix 2019 de l’ACM, à San Francisco, au mois de juin.

 

À la conférence FCRC de l’ACM à Phœnix, Hinton et LeCun ont prononcé leur conférence Turing : « La révolution de l’apprentissage profond » et « La révolution de l’apprentissage numérique : La suite ». | Vidéo

 

Les trois lauréats ont fait la couverture du numéro de juin 2019 de la revue Communications of the ACM | Lisez ici

 

Cette année, la Banque d’Angleterre a rendu hommage à Alan Turing pour ses travaux d’avant-garde sur les ordinateurs, ainsi que pour ses contributions lors de la Deuxième Guerre mondiale, y compris la « bombe de Turing », l’un des outils principaux utilisés pour décrypter les messages codés à l’aide d’Enigma; son portrait figurera sur les billets de 50 £. Pendant le mois de la fierté gaie cette année, le New York Times a aussi rendu hommage à Alan Turing pour ses idées qui ont contribué à la victoire pendant la Deuxième Guerre mondiale, et les épreuves qu’il a traversées relativement à sa sexualité : Overlooked No More: Alan Turing, Condemned Code Breaker and Computer Visionary

Cet article a été publié dans le Bulletin IACan. Abonnez-vous à la publication électronique bimestrielle pour rester au fait des plus récentes nouvelles en IA au Canada.

Vector Researchers Prepare for 33rd Annual Conference on Neural Information Processing Systems (NeurIPS)

Vector researchers are preparing for the world’s premier machine learning conference, the 33rd annual conference on Neural Information Processing Systems (NeurIPS). A multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers, NeurIPS 2019 runs December 8-14 at the Vancouver Convention Center, Vancouver, BC.

This year, Vector researchers had an impressive 23 papers accepted to the conference. Additionally, they are organizing four workshops.

At the 2018 NeurIPS conference, Vector Faculty Members and students collaborated to win two of four Best Paper awards and a Best Student Paper Award for their research. Read more about Vector’s accomplishments at last year’s conference here.

 

Accepted Papers by Vector researchers:

Efficient Graph Generation with Graph Recurrent Attention Networks
Renjie Liao (University of Toronto) · Yujia Li (DeepMind) · Yang Song (Stanford University) · Shenlong Wang (University of Toronto) · Will Hamilton (McGill) · David Duvenaud (University of Toronto) · Raquel Urtasun (Uber ATG) · Richard Zemel (Vector Institute/University of Toronto)

 

Incremental Few-Shot Learning with Attention Attractor Networks
Mengye Ren (University of Toronto / Uber ATG) · Renjie Liao (University of Toronto) · Ethan Fetaya (University of Toronto) · Richard Zemel (Vector Institute/University of Toronto)

 

SMILe: Scalable Meta Inverse Reinforcement Learning through Context-Conditional Policies
Seyed Kamyar Seyed Ghasemipour (University of Toronto, Vector Institute) · Shixiang (Shane) Gu (Google Brain) · Richard Zemel (Vector Institute/University of Toronto)

 

Lookahead Optimizer: k steps forward, 1 step back
Michael Zhang (University of Toronto) · James Lucas (University of Toronto) · Jimmy Ba (University of Toronto / Vector Institute) · Geoffrey Hinton (Google)

Graph Normalizing Flows
Jenny Liu (Vector Institute, University of Toronto) · Aviral Kumar (UC Berkeley) · Jimmy Ba (University of Toronto / Vector Institute) · Jamie Kiros (Google Inc.) · Kevin Swersky (Google)

 

Latent Ordinary Differential Equations for Irregularly-Sampled Time Series
Yulia Rubanova (University of Toronto) · Tian Qi Chen (U of Toronto) · David Duvenaud (University of Toronto)

 

Residual Flows for Invertible Generative Modeling
Tian Qi Chen (U of Toronto) · Jens Behrmann (University of Bremen) · David Duvenaud (University of Toronto) · Joern-Henrik Jacobsen (Vector Institute)

 

Neural Networks with Cheap Differential Operators
Tian Qi Chen (U of Toronto) · David Duvenaud (University of Toronto)

 

Stochastic Runge-Kutta Accelerates Langevin Monte Carlo and Beyond
Xuechen Li (Google) · Yi Wu (University of Toronto & Vector Institute) · Lester Mackey (Microsoft Research) · Murat Erdogdu (University of Toronto)

Value Function in Frequency Domain and Characteristic Value Iteration
Amir-massoud Farahmand (Vector Institute)

 

Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer
Wenzheng Chen (University of Toronto) · Huan Ling (University of Toronto, NVIDIA) · Jun Gao (University of Toronto) · Edward Smith (McGill University) · Jaakko Lehtinen (NVIDIA Research; Aalto University) · Alec Jacobson (University of Toronto) · Sanja Fidler (University of Toronto)

 

Fast Convergence of Natural Gradient Descent for Over-Parameterized Neural Networks
Guodong Zhang (University of Toronto) · James Martens (DeepMind) · Roger Grosse (University of Toronto)

 

Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model
Guodong Zhang (University of Toronto) · Lala Li (Google) · Zachary Nado (Google Inc.) · James Martens (DeepMind) · Sushant Sachdeva (University of Toronto) · George Dahl (Google Brain) · Chris Shallue (Google Brain) · Roger Grosse (University of Toronto)

 

Understanding Posterior Collapse in Variational Autoencoders
James Lucas (University of Toronto) · George Tucker (Google Brain) · Roger Grosse (University of Toronto) · Mohammad Norouzi (Google Brain)

 

Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks
Qiyang Li (University of Toronto) · Saminul Haque (University of Toronto) · Cem Anil (University of Toronto; Vector Institute) · James Lucas (University of Toronto) · Roger Grosse (University of Toronto) · Joern-Henrik Jacobsen (Vector Institute)

 

MixMatch: A Holistic Approach to Semi-Supervised Learning
David Berthelot (Google Brain) · Nicholas Carlini (Google) · Ian Goodfellow (Google Brain) · Nicolas Papernot (University of Toronto) · Avital Oliver (Google Brain) · Colin A Raffel (Google Brain)

 

Fast PAC-Bayes via Shifted Rademacher Complexity
Jun Yang (University of Toronto) · Shengyang Sun (University of Toronto) · Daniel Roy (Univ of Toronto & Vector)

 

Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates
Gintare Karolina Dziugaite (Element AI) · Mahdi Haghifam (University of Toronto) · Jeffrey Negrea (University of Toronto) · Ashish Khisti (University of Toronto) · Daniel Roy (Univ of Toronto & Vector)

 

Understanding attention in graph neural networks
Boris Knyazev (University of Guelph) · Graham W Taylor (University of Guelph) · Mohamed R. Amer (Robust.AI)

 

The Cells Out of Sample (COOS) dataset and benchmarks for measuring out-of-sample generalization of image classifiers
Alex Lu (University of Toronto) · Amy Lu (University of Toronto/Vector Institute) · Wiebke Schormann (Sunnybrook Research Institute) · David Andrews (Sunnybrook Research Institute) · Alan Moses (University of Toronto)

 

Learning Reward Machines for Partially Observable Reinforcement Learning
Rodrigo Toro Icarte (University of Toronto and Vector Institute) · Ethan Waldie (University of Toronto) · Toryn Klassen (University of Toronto) · Rick Valenzano (Element AI) · Margarita Castro (University of Toronto) · Sheila McIlraith (University of Toronto)

 

When does label smoothing help?
Rafael Müller (Google Brain) · Simon Kornblith (Google Brain) · Geoffrey E Hinton (Google & University of Toronto)

 

Stacked Capsule Autoencoders
Adam Kosiorek (University of Oxford) · Sara Sabour (Google) · Yee Whye Teh (University of Oxford, DeepMind) · Geoffrey E Hinton (Google & University of Toronto)

 

Vector Institute researchers are hosting four workshops:

 

Machine Learning and the Physical Science: Organized by Juan Felipe Carrasquilla, (Canada CIFAR AI Chair, Vector Institute, Faculty Member, Vector Institute and Assistant Professor (Adjunct), Department of Physics and Astronomy, University of Waterloo) and collaborators, this workshop focuses on applying machine learning to outstanding physics problems. | Learn more 

 

Fair ML in Healthcare: Organized by Shalmali Joshi, Post-doctoral Fellow, and Shems Saleh at the Vector Institute, and collaborators this, the goal of this workshop is to investigate issues around fairness in machine learning-based health care. | Learn more

 

Program Transformations for ML: Organized by David Duvenaud (Assistant Professor at the University of Toronto, Co-founder, Invenia, Canada Research Chair in Generative Models and Faculty Member, Vector Institute) and his collaborators.  This workshop aims at viewing program transformations in ML in a unified light, making these capabilities more accessible, and building entirely new ones | Learn more

 

Machine Learning with Guarantees: Organized by Daniel Roy (Assistant Professor at the University of Toronto, Faculty Member, Vector Institute and Canada CIFAR Artificial Intelligence Chair) and his collaborators, this workshop will bring together researchers to discuss the problem of obtaining performance guarantees and algorithms to optimize them.  | Learn more

Learn more:

  • Check out a full list of Vector research publications here.

Vector’s Chief Scientific Advisor, Dr. Geoffrey Hinton, wins the Honda Prize 2019

Today, the Vector Institute congratulates our very own Chief Scientific Advisor, Dr. Geoffrey Hinton, for winning the Honda Prize 2019 for his pioneering research in the field of deep learning in artificial intelligence (AI) and his contribution to practical application of the technology. Dr. Hinton is also VP and Engineering Fellow, Google, Professor Emeritus, University of Toronto and Advisor, Learning in Machine & Brain program, Canadian Institute for Advanced Research (CIFAR).

Established in 1980, the annual Honda Prize recognizes the work of individuals or groups generating new knowledge to drive the next generation, from the standpoint of eco-technology. AI is expected to play an important role not only in the advancement of science and technology but also in resolving many different global issues that humankind must address in the areas of energy and climate change.

The award caps off a year in which Dr. Hinton’s achievements, as well as the legacy of Canada’s pioneering role in AI, have yielded increasing accolades. In December, the Governor General of Canada appointed Dr. Hinton as a Companion of the Order of Canada. He was granted the 2019 Toronto Region Builder Award at a ceremony attended by Prime Minister Justin Trudeau in February and in March, the Association for Computing Machinery awarded this year’s A.M. Turing Award, to Dr. Hinton and his colleagues Yoshua Bengio, scientific director of Vector’s sibling organization Mila, and Yann LeCunn, Professor at New York University and Chief AI Scientist at Facebook.

Read more about the Honda Prize and Dr. Hinton’s work here.

Tick Identification to Combat Lyme Disease

Photo credit: Jim Gathany

By Ian Gormely

Toronto – Today, the Vector Institute, an independent, not-for-profit research institute focused on leading-edge machine learning, announced the third of its series of Pathfinder Projects to implement artificial intelligence (AI) in the health sector.

The third Pathfinder Project, performed in partnership with Public Health Ontario (PHO), will classify tick species using computer vision. Blacklegged ticks are the only ticks in Ontario known to carry B. burgdorferi, the bacteria that causes Lyme disease. Not all blacklegged ticks carry B. burgdorferi, but a bite from one is of more concern than a bite from a dog tick or another tick species that doesn’t carry the bacteria. For this project, Vector’s technical AI staff scientist Dr. Elham Dolatabadi, Dr. Vanessa Allen, Chief of Microbiology, PHO and Dr. Samir Patel, clinical microbiologist at PHO, will develop a method to automatically identify tick species using computer vision.

The first deliverable will be an AI algorithm that professionals at PHO will use to identify whether or not a tick is a blacklegged tick. The long-term goal is to create an app that anyone can use to simply take a photo of a tick. Once the app identifies the species, it will provide advice.

“The app we want to build would empower the public,” says Dr. Patel. PHO receives around 10,000 ticks each year for identification. Currently, the PHO laboratory has to identify each individual tick that is submitted. “Manually identifying and reporting each tick back to the submitter can take up to three weeks,” he says. The process can be automated using machine learning approaches so it is faster at PHO in the short term. “Once the app is developed the process will be even faster because the app can tell you right away whether or not it is a blacklegged tick and infer the risk of contracting Lyme disease.” The rapid identification of the blacklegged ticks will allow individuals to determine whether or not they should seek medical attention within the recommended 72 hours of tick removal.

Pathfinder Projects are small-scale efforts designed to produce results in 12 to 18 months that guide future research and technology adoption. With technical and resource support from the Vector Institute, the projects each bring together a multidisciplinary research team to tackle an important health care problem or opportunity using machine learning and AI more broadly. Each project was chosen for its potential to help identify a “path” through which world-class machine learning research can be translated into widespread benefits for patients.

About the Vector Institute

The Vector Institute is an independent, not-for-profit corporation dedicated to advancing artificial intelligence, excelling in machine and deep learning. The Vector Institute’s vision is to drive excellence and leadership in Canada’s knowledge, creation, and use of AI to foster economic growth and improve the lives of Canadians.

The Vector Institute is funded by the Province of Ontario, the Government of Canada through the Pan-Canadian AI Strategy administered by CIFAR, and industry sponsors from across the Canadian economy.

Tick Identification

Ticks, and the threat of Lyme disease, have become a regular feature of venturing outdoors in the summer months. For many Canadians, a thorough check for the tiny insects, which feed on our blood, is par for the course when returning from a hike or camping trip. Yet, only certain tick species actually carry the bacteria that causes Lyme disease. The challenge for most Ontarians is correctly identifying the type of tick that has decided to make you its lunch.

“Half of the ticks in Ontario are dog ticks,” explains Dr. Samir Patel, clinical microbiologist with Public Health Ontario (PHO). “They don’t carry the bacteria that causes Lyme disease.” However, blacklegged ticks are capable of carrying and transmitting that bacteria, with the risk of infection higher in certain parts of the province than others. Anyone who finds one on their body should consult a doctor.

PHO receives over 10,000 tick submissions every year — ticks sent to their laboratory site in Sault Ste. Marie — from Ontarians looking for guidance around a potential tick bite. Currently the laboratory has to manually identify each bug, a process that can take up to three weeks.

To ensure rapid and streamlined medical assessment of high risk tick bites, as well as reduce individuals’ anxiety about the potential Lyme disease after a tick bite, PHO is developing a mobile app to rapidly and accurately identify tick species and provide next-steps medical guidance. “There’s currently a gap in care,” admits Dr. Vanessa Allen, Chief of Medical Microbiology at PHO, “and this is one way to close that gap and improve the care and the delivery of services for Lyme disease in Ontario and beyond.”

Along with Dr. Allen and Vector’s technical AI staff scientist, Dr. Elham Dolatabadi, Dr. Patel is currently developing a computer vision model to differentiate between the two common tick species normally found in Ontario. “In the short-term we look forward to using computer vision for blacklegged tick identification at PHO.” he says. “Once the app is developed, it will empower the public. If you find a tick on your body, the app will be able to tell you right away whether it is a blacklegged tick or not.”

Tick populations have been increasing in recent years, as has awareness around tick bites and the threat of Lyme disease, says Dr. Allen. But both she and Dr. Patel caution that a tick bite, even from a blacklegged tick, doesn’t automatically mean that a person will contract Lyme disease and where appropriate, a single dose of prophylaxis should mitigate the chances of infection.

PHO plans to have the app available to the public by the end of next year. They also hope to use data from the user-submitted photos to help track tick populations in the province and better understand where ticks are moving, which can help inform future strategies, says Dr. Allen. “It’s not a magic bullet, but it’s a tool to speed up the process of both patient care and our understanding of Lyme disease.”

Next Meetup

 

Days
:
Hours
:
Minutes
:
Seconds

 

Plug yourself into AI and don't miss a beat

 


Toronto AI is a social and collaborative hub to unite AI innovators of Toronto and surrounding areas. We explore AI technologies in digital art and music, healthcare, marketing, fintech, vr, robotics and more. Toronto AI was founded by Dave MacDonald and Patrick O'Mara.