Search

Learning in
Machines & Brains

Learning Machines and Brains

About this program

How do we understand intelligence and build intelligent machines?

The program in Learning in Machines & Brains (formerly known as Neural Computation & Adaptive Perception) is revolutionizing the field of artificial intelligence, and creating computers that think more like us – that can recognize faces, understand what is happening in a picture or video, and comprehend the actual meaning of language. The result will be computers that are not only powerful but intelligent, and that will be able to do everything from conduct a casual conversation to extract meaning from massive databases of information.

Program at a glance

Founded in
2004
Members
38
Renewal Dates
2008, 2014
Supporters
  •   Céline and Jacques Lamarre
  •   Facebook
  •   Google Inc.
Partners
  •   Brain Canada Foundation through the Canada Brain Research Fund
  •   Inria

Disciplines
Computer science, including artificial intelligence & machine learning; neuroscience; bioinformatics & computational biology

Program details

The CIFAR program has shaken up the field of artificial intelligence by pioneering a technique called “deep learning,” which is now routinely used by Internet giants like Google and Facebook. A decade ago, CIFAR took a risk on researchers who wanted to revive interest in neural networks, a computer technique inspired by the human brain. CIFAR brought together computer scientists, biologists, neuroscientists, psychologists and others, and the result was rich collaborations that have propelled artificial intelligence research forward.


optimal stimuli

How Google sees you and your cat. These “optimal stimuli” for both human and cat faces resulted from training a deep learning network on more than 10 million pictures

Increased processing power and the availability of big data sets are making computers more powerful and useful. Yet computers still face challenges as they try to deal with humans and with the real world, including everyday tasks like understanding written and spoken speech and recognizing faces and objects, or even more interestingly, answering questions about all kinds of documents, communicating with humans, or using reasoning to solve problems.

Neural Network

A deep learning network takes in raw information, such as values for individual pixels, in the top input layer, and processes it through one or more hidden layers, with each layer adding a further level of abstraction.

Computers that are better at understanding and learning from the real world could revolutionize medicine, industry, transportation, and our day-to-day lives. Already, CIFAR researchers have used deep learning to identify previously unknown genetic contributors to conditions such as autism. Soon, computers could learn to drive cars and trucks safely and reliably, or detect the first hint of a major epidemic from public health records and Facebook posts. Computers could also become better at interacting with people. Talking to a computer could become as easy as talking to another person.

The fundamental objective of the program is to understand the principles behind natural and artificial intelligence, and to uncover mechanisms by which learning can cause intelligence to emerge.

SELECTED PAPERS

Hinton, G. E., Osindero, S. and Teh, Y. (2006). “A fast learning algorithm for deep belief nets.” Neural Computation, 18, pp 1527-1554. PDF

Y. Bengio and P. Lamblin and D. Popovici and H. Larochelle, “Greedy Layer-Wise Training of Deep Networks,” Neural Information Processing Systems Proceedings (2006). PDF

Salakhutdinov, R. and Hinton, G., “Learning a Nonlinear Embedding by Preserving Class Neighbourhood Structure,” Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics, 412-419 (2007). PDF

Graves, A., Mohamed, A., Hinton, G. E., “Speech Recognition with Deep Recurrent Neural Networks,” 39th International Conference on Acoustics, Speech and Signal Processing, Vancouver (2013). PDF

Yann LeCun, Yoshua Bengio and Geoffrey Hinton. (2015). “Deep Learning.” Nature, 521, pp 436–444. Abstract

Contact the program’s senior director, Kate Geddie

Program fellows & advisors

Program Directors

LMB_YoshuaBengio
Yoshua Bengio
Program Co-Director

Yoshua Bengio’s current interests include fundamental questions on deep learning, the geometry of generalization in high-dimensional spaces, biologically inspired learning algorithms, and challenging applications of statistical machine learning in artificial intelligence tasks.

LMB_YannLaCun
Yann LeCun
Program Co-Director

Yann LeCun’s research interests include computational and biological models of learning and perception

LMB_HugoLarochelle
Hugo Larochelle
Associate Program Director

Hugo Larochelle is a computer scientist whose research focuses on machine learning, i.e., on the development of algorithms capable of extracting concepts and abstractions from data.

Fellows

LMB_AapoHyvarinen

Aapo Johannes Hyvärinen

  • Associate Fellow
  • Learning in Machines & Brains
  • University College London
  • Finland
Bio Outline

Aaron Courville

  • Fellow
  • Learning in Machines & Brains
  • Université de Montréal
  • Canada
LMB_AndrewNg

Andrew Ng

  • Associate Fellow
  • Learning in Machines & Brains
  • Stanford University
  • United States
LMB_AntonioTorralba

Antonio Torralba

  • Associate Fellow
  • Learning in Machines & Brains
  • Massachusetts Institute of Technology
  • United States
LMB_BlakeRichards

Blake Richards

  • Fellow
  • Learning in Machines & Brains
  • University of Toronto
  • Canada
Brendan Frey

Brendan J. Frey

  • Senior Fellow
  • Learning in Machines & Brains
  • University of Toronto
  • Canada
LMB_BrunoOlshausen

Bruno Olshausen

  • Senior Fellow
  • Learning in Machines & Brains
  • University of California Berkeley
  • United States
LMB_ChristopherWilliams

Christopher K. I. Williams

  • Associate Fellow
  • Learning in Machines & Brains
  • University of Edinburgh
  • United Kingdom
LMB_ChristopherManning

Christopher Manning

  • Associate Fellow
  • Learning in Machines & Brains
  • Stanford University
  • United States
LMB_DavidFleet

David J. Fleet

  • Senior Fellow
  • Learning in Machines & Brains
  • University of Toronto
  • Canada
Bio Outline

Doina Precup

  • Senior Fellow
  • Learning in Machines & Brains
  • McGill University
  • Canada
LMB_EeroSimoncelli

Eero Simoncelli

  • Associate Fellow
  • Learning in Machines & Brains
  • New York University
  • United States
LMB_FrancisBach

Francis Bach

  • Senior Fellow
  • Learning in Machines & Brains
  • École normale supérieure Paris
  • Inria
  • France
LMB_LeeHonglak

Honglak Lee

  • Associate Fellow
  • Learning in Machines & Brains
  • University of Michigan
  • United States
photo of Ila R. Fiete

Ila R. Fiete

  • Senior Fellow
  • Learning in Machines & Brains
  • University of Texas at Austin
  • United States
LMB_IlyaSutskever

Ilya Sutskever

  • Associate Fellow
  • Learning in Machines & Brains
  • OpenAI
  • United States
LMB_JamesDicarlo

James DiCarlo

  • Associate Fellow
  • Learning in Machines & Brains
  • Massachusetts Institute of Technology
  • United States
LMB_JoellePineau

Joelle Pineau

  • Senior Fellow
  • Learning in Machines & Brains
  • McGill University
  • Canada
LMB_JosefSivic

Josef Sivic

  • Senior Fellow
  • Learning in Machines & Brains
  • École normale supérieure
  • Inria
  • France
LMB_KonradKording

Konrad Kording

  • Associate Fellow
  • Learning in Machines & Brains
  • University of Pennsylvania
  • United States
Marc G. Bellemare

Marc G. Bellemare

  • Fellow
  • Learning in Machines & Brains
  • McGill University
  • Google Brain
  • Canada
LMB_MarkSchmidt

Mark Schmidt

  • Associate Fellow
  • Learning in Machines & Brains
  • University of British Columbia
  • Canada
LMB_MaxWelling

Max Welling

  • Senior Fellow
  • Learning in Machines & Brains
  • University of Amsterdam
  • The Netherlands
LMB_NandoDeFreitas

Nando de Freitas

  • Senior Fellow
  • Learning in Machines & Brains
  • University of Oxford
  • United Kingdom
Bio Outline

Pascal Vincent

  • Associate Fellow
  • Learning in Machines & Brains
  • Université de Montréal
  • Canada
LMB_RichardSutton

Richard Sutton

  • Senior Fellow
  • Learning in Machines & Brains
  • University of Alberta
  • Canada
LMB_RichardZemel

Richard Zemel

  • Senior Fellow
  • Learning in Machines & Brains
  • University of Toronto
  • Canada
Bio Outline

Rob Fergus

  • Senior Fellow
  • Learning in Machines & Brains
  • New York University
  • United States
LMB_RolandMemisevic

Roland Memisevic

  • Fellow
  • Learning in Machines & Brains
  • Université de Montréal
  • Canada
Bio Outline

Ruslan Salakhutdinov

  • Fellow
  • Learning in Machines & Brains
  • Carnegie Mellon University
  • United States
LMB_Simon

Simon Lacoste-Julien

  • Fellow
  • Learning in Machines & Brains
  • Université de Montréal
  • Canada
LMB_SuryaGanguli

Surya Ganguli

  • Associate Fellow
  • Learning in Machines & Brains
  • Stanford University
  • United States
LMB_YairWeiss

Yair Weiss

  • Senior Fellow
  • Learning in Machines & Brains
  • The Hebrew University of Jerusalem
  • Israel
LMB_ZaidHarchaoui

Zaid Harchaoui

  • Associate Fellow
  • Learning in Machines & Brains
  • University of Washington
  • France

Advisors

LMB_BernhardScholkopf

Bernhard Schölkopf

  • Advisory Committee Chair
  • Learning in Machines & Brains
  • Max Planck Institute for Intelligent Systems
  • Germany
LMB_GeoffHinton

Geoffrey Hinton

  • Advisor
  • Learning in Machines & Brains
  • University of Toronto
  • Google
  • Canada
LMB_LeonBottou

Léon Bottou

  • Advisor
  • Learning in Machines & Brains
  • Facebook AI Research
  • France
LMB_PieterAbbeel

Pieter Abbeel

  • Advisor
  • Learning in Machines & Brains
  • University of California Berkeley
  • United States
Bio Outline

Pietro Perona

  • Advisor
  • Learning in Machines & Brains
  • California Institute of Technology
  • United States
LMB_SebastianSeung

Sebastian Seung

  • Advisor
  • Learning in Machines & Brains
  • Princeton University
  • United States
Bio Outline

Terrence J. Sejnowski

  • Advisor
  • Learning in Machines & Brains
  • Salk Institute for Biological Studies
  • United States

CIFAR Azrieli Global Scholars

LMB_JoelZylberberg

Joel Zylberberg

  • CIFAR Azrieli Global Scholar 2016
  • Learning in Machines & Brains
  • University of Colorado Denver
  • United States
LMB_GrahamTaylor

Graham Taylor

  • CIFAR Azrieli Global Scholar 2016
  • Learning in Machines & Brains
  • University of Guelph
  • Vector Institute
  • Canada
LMB_KyunghyunCho

Kyunghyun Cho

  • CIFAR Azrieli Global Scholar 2017
  • Learning in Machines & Brains
  • New York University
  • United States