Portrait of Blake Richards

Blake Richards

Core Academic Member
blake.richards@mila.quebec
Canada CIFAR AI Chair
Associate Professor, McGill University, School of Computer Science and Department of Neurology and Neurosurgery
Google
Research Topics
Computational Neuroscience
Generative Models
Reinforcement Learning
Representation Learning
Website
Google Scholar
X

Biography

Blake Richards is Research Scientist Manager with the Paradigms of Intelligence team at Google, and an Associate Professor in the School of Computer Science and Department of Neurology and Neurosurgery at McGill University. He is also a Core Faculty Member at Mila.

Richards’ research lies at the intersection of neuroscience and AI. His laboratory investigates universal principles of intelligence that apply to both natural and artificial agents.

He has received several awards for his work, including the NSERC Arthur B. McDonald Fellowship in 2022, the Canadian Association for Neuroscience Young Investigator Award in 2019, and a Canada CIFAR AI Chair in 2018. Richards was a Banting Postdoctoral Fellow at SickKids Hospital from 2011 to 2013.

He obtained his PhD in neuroscience from the University of Oxford in 2010, and his BSc in cognitive science and AI from the University of Toronto in 2004.

Current Students

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