Portrait de Blake Richards

Blake Richards

Membre académique principal
blake.richards@mila.quebec
Chaire en IA Canada-CIFAR
McGill University, École d'informatique et Département de neurologie et de neurochirurgie
Google
Sujets de recherche
Apprentissage de représentations
Apprentissage par renforcement
Modèles génératifs
Neurosciences computationnelles
Site web
Google Scholar
X

Biographie

Blake Richards est directeur de recherche au sein de l'équipe Paradigms of Intelligence chez Google et professeur agrégé à l'École d'informatique et au Département de neurologie et de neurochirurgie de l'Université McGill. Il est également et membre académique principal à Mila - Institut québécois d'intelligence artificielle.

Ses recherches se situent à l'intersection des neurosciences et de l'intelligence artificielle. Son laboratoire étudie les principes universels de l'intelligence qui s'appliquent aux agents naturels et artificiels.

Il a reçu plusieurs distinctions pour ses travaux, notamment une bourse Arthur-B.-McDonald du Conseil de recherches en sciences naturelles et en génie du Canada (CRSNG) en 2022, le Prix du jeune chercheur de l'Association canadienne des neurosciences en 2019 et une chaire en IA Canada-CIFAR en 2018. M. Richards a en outre été titulaire d'une bourse postdoctorale Banting à l'hôpital SickKids de 2011 à 2013. Il a obtenu un doctorat en neurosciences de l'Université d'Oxford en 2010 et une licence en sciences cognitives et en IA de l'Université de Toronto en 2004.

Étudiants actuels

Aliya Affdal
Collaborateur·rice de recherche - UdeM
aliya.affdal@mila.quebec
Benjamin Alsbury-Nealy
Doctorat - McGill
benjamin@silicolabs.ca
Site web
Github
Google Scholar
Antoine Boudreau LeBlanc
Postdoctorat - McGill
antoine.boudreau-leblanc@mila.quebec
Site web
Google Scholar
Colin Bredenberg
Postdoctorat - UdeM
Superviseur⋅e principal⋅e :
Guillaume Lajoie
colin.bredenberg@mila.quebec
Nour Chahine
Doctorat - McGill
nour.chahine@mila.quebec
Github
Raymond Chua
Doctorat - McGill
Superviseur⋅e principal⋅e :
Doina Precup
chuaraym@mila.quebec
Site web
Google Scholar
Erica Cianfarano
Doctorat - McGill
erica.cianfarano@mila.quebec
Jonathan Cornford
Collaborateur·rice de recherche - McGill
cornforj@mila.quebec
Sabrina Du
Baccalauréat - McGill
sabrina.du@mila.quebec
Github
Alex Efremov
Doctorat - McGill
aleksei.efremov@mail.mcgill.ca
Github
Google Scholar
Tom George
Postdoctorat - McGill
Co-superviseur⋅e :
Guillaume Lajoie
tomgeorge1@btinternet.com
Site web
Github
Google Scholar
Oumayma Gharbi
Visiteur de recherche indépendant - UdeM
oumayma.gharbi@mila.quebec
Arna Ghosh
Collaborateur·rice de recherche - McGill
ghosharn@mila.quebec
Site web
Github
Google Scholar
Adel Halawa
Doctorat - McGill
adel.halawa@mila.quebec
Roy Henha Eyono
Doctorat - McGill
roy.eyono@mila.quebec
Github
Google Scholar
Sonia Joseph
Doctorat - McGill
sonia.joseph@mila.quebec
Site web
Github
Daniel Levenstein
Collaborateur·rice alumni - McGill
daniel.levenstein@mila.quebec
Github
Google Scholar
Pingsheng Li
Doctorat - McGill
Co-superviseur⋅e :
Guillaume Lajoie
pingsheng.li@mila.quebec
Github
Matthew Loukine
Doctorat - McGill
matthew.loukine@mail.mcgill.ca
Dane Malenfant
Maîtrise recherche - McGill
dane.malenfant@mila.quebec
Site web
Github
Google Scholar
Abdel Mfougouon Njupoun
Doctorat - UdeM
Superviseur⋅e principal⋅e :
Guillaume Lajoie
abdelnjupoun@gmail.com
Site web
Github
Google Scholar
Le Thuy Duong Nguyen
Maîtrise recherche - McGill
Superviseur⋅e principal⋅e :
Matt Perich
le-thuy-duong.nguyen@mila.quebec
Site web
Ghazaleh Ranjbaran
Visiteur de recherche indépendant - Université de Montréal
qazaleh.ranjbaran@gmail.com
Site web
Github
Alexis Roger
Doctorat - McGill
Co-superviseur⋅e :
Irina Rish
alexis.roger@mila.quebec
Github
Ali Saheb Pasand
Doctorat - McGill
Co-superviseur⋅e :
Pablo Samuel Castro
ali.sahebpasand@mila.quebec
Mandana Samiei
Doctorat - McGill
Superviseur⋅e principal⋅e :
Doina Precup
samiemandana@gmail.com
Site web
Github
Google Scholar
Aidan Sirbu
Maîtrise recherche - McGill
aidan.sirbu@mila.quebec
Site web
Github
Google Scholar
Hiro Tanabe
Visiteur de recherche indépendant - NA
hiroyuki.tanabe@mila.quebec
Josh Tindall
Collaborateur·rice alumni - McGill
joshua.tindall@mila.quebec
Mashbayar Tugsbayar
Doctorat - McGill
Github
Charlotte Volk
Doctorat - McGill
Co-superviseur⋅e :
Shahab Bakhtiari
charlotte.volk@mila.quebec
Github
Maren Wehrheim
Visiteur de recherche indépendant - York University
maren.wehrheim@mila.quebec
Github
Google Scholar
Amirhossein Zamani
Doctorat - Concordia
Superviseur⋅e principal⋅e :
Eugene Belilovsky
amirhossein.zamani@mila.quebec
Site web
Github
Google Scholar

Publications

Learning to Live with Dale's Principle: ANNs with Separate Excitatory and Inhibitory Units
Jonathan Cornford
Damjan Kalajdzievski
Marco Leite
Amélie Lamarquette
Dimitri M. Kullmann
Blake Richards
A bstract The units in artificial neural networks (ANNs) can be thought of as abstraction… (voir plus)s of biological neurons, and ANNs are increasingly used in neuroscience research. However, there are many important differences between ANN units and real neurons. One of the most notable is the absence of Dale’s principle, which ensures that biological neurons are either exclusively excitatory or inhibitory. Dale’s principle is typically left out of ANNs because its inclusion impairs learning. This is problematic, because one of the great advantages of ANNs for neuroscience research is their ability to learn complicated, realistic tasks. Here, by taking inspiration from feedforward inhibitory interneurons in the brain we show that we can develop ANNs with separate populations of excitatory and inhibitory units that learn just as well as standard ANNs. We call these networks Dale’s ANNs (DANNs). We present two insights that enable DANNs to learn well: (1) DANNs are related to normalization schemes, and can be initialized such that the inhibition centres and standardizes the excitatory activity, (2) updates to inhibitory neuron parameters should be scaled using corrections based on the Fisher Information matrix. These results demonstrate how ANNs that respect Dale’s principle can be built without sacrificing learning performance, which is important for future work using ANNs as models of the brain. The results may also have interesting implications for how inhibitory plasticity in the real brain operates.
2021-01-11
ICLR.cc/2021/Conference (poster)
doi.org
openreview.net
Adversarial Feature Desensitization
Pouya Bashivan
Reza Bayat
Adam Ibrahim
Kartik Ahuja
Mojtaba Faramarzi
Touraj Laleh
Blake Richards
Irina Rish
Neural networks are known to be vulnerable to adversarial attacks -- slight but carefully constructed perturbations of the inputs which can … (voir plus)drastically impair the network's performance. Many defense methods have been proposed for improving robustness of deep networks by training them on adversarially perturbed inputs. However, these models often remain vulnerable to new types of attacks not seen during training, and even to slightly stronger versions of previously seen attacks. In this work, we propose a novel approach to adversarial robustness, which builds upon the insights from the domain adaptation field. Our method, called Adversarial Feature Desensitization (AFD), aims at learning features that are invariant towards adversarial perturbations of the inputs. This is achieved through a game where we learn features that are both predictive and robust (insensitive to adversarial attacks), i.e. cannot be used to discriminate between natural and adversarial data. Empirical results on several benchmarks demonstrate the effectiveness of the proposed approach against a wide range of attack types and attack strengths. Our code is available at https://github.com/BashivanLab/afd.
2020-12-31
Advances in Neural Information Processing Systems 34 (NeurIPS 2021) (publié)
doi.org
openreview.net
Different scaling of linear models and deep learning in UKBiobank brain images versus machine-learning datasets
Marc-Andre Schulz
B. T. Thomas Yeo
Joshua T. Vogelstein
Janaina Mourao-Miranada
Jakob N. Kather
Konrad Kording
Blake Richards
Danilo Bzdok
Recently, deep learning has unlocked unprecedented success in various domains, especially using images, text, and speech. However, deep lear… (voir plus)ning is only beneficial if the data have nonlinear relationships and if they are exploitable at available sample sizes. We systematically profiled the performance of deep, kernel, and linear models as a function of sample size on UKBiobank brain images against established machine learning references. On MNIST and Zalando Fashion, prediction accuracy consistently improves when escalating from linear models to shallow-nonlinear models, and further improves with deep-nonlinear models. In contrast, using structural or functional brain scans, simple linear models perform on par with more complex, highly parameterized models in age/sex prediction across increasing sample sizes. In sum, linear models keep improving as the sample size approaches ~10,000 subjects. Yet, nonlinearities for predicting common phenotypes from typical brain scans remain largely inaccessible to the examined kernel and deep learning methods.
2020-08-24
Nature Communications (publié)
doi.org