Portrait de Blake Richards

Blake Richards

Membre académique principal
Chaire en IA Canada-CIFAR
Professeur adjoint, 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

Biographie

Blake Richards est professeur agrégé à l'École d'informatique et au Département de neurologie et de neurochirurgie de l'Université McGill et membre du corps professoral de 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

Stagiaire de recherche - UdeM
Visiteur de recherche indépendant - Seoul National University
Postdoctorat - UdeM
Superviseur⋅e principal⋅e :
Doctorat - McGill
Co-superviseur⋅e :
Doctorat - McGill
Superviseur⋅e principal⋅e :
Doctorat - McGill
Postdoctorat - McGill
Visiteur de recherche indépendant - Seoul National University
Stagiaire de recherche - McGill
Collaborateur·rice alumni
Doctorat - McGill
Visiteur de recherche indépendant - ETH Zurich
Collaborateur·rice de recherche - Georgia Tech
Postdoctorat - McGill
Maîtrise recherche - McGill
Doctorat - UdeM
Superviseur⋅e principal⋅e :
Baccalauréat - McGill
Maîtrise recherche - McGill
Visiteur de recherche indépendant
Postdoctorat - McGill
Co-superviseur⋅e :
Doctorat - McGill
Co-superviseur⋅e :
Doctorat - McGill
Co-superviseur⋅e :
Doctorat - McGill
Superviseur⋅e principal⋅e :
Maîtrise recherche - McGill
Co-superviseur⋅e :
Maîtrise recherche - McGill
Doctorat - McGill
Maîtrise recherche - McGill
Co-superviseur⋅e :
Visiteur de recherche indépendant - Seoul National University
Visiteur de recherche indépendant - York University
Doctorat - McGill
Doctorat - Concordia
Superviseur⋅e principal⋅e :

Publications

Burst-dependent synaptic plasticity can coordinate learning in hierarchical circuits
Alexandre Payeur
Jordan Guerguiev
Friedemann Zenke
Richard Naud
Optogenetic activation of parvalbumin and somatostatin interneurons selectively restores theta-nested gamma oscillations and oscillation-induced spike timing-dependent long-term potentiation impaired by amyloid β oligomers
Kyerl Park
Jaedong Lee
Hyun Jae Jang
Michael M Kohl
Jeehyun Kwag
Spike-based causal inference for weight alignment
Jordan Guerguiev
Konrad Paul Kording
In artificial neural networks trained with gradient descent, the weights used for processing stimuli are also used during backward passes to… (voir plus) calculate gradients. For the real brain to approximate gradients, gradient information would have to be propagated separately, such that one set of synaptic weights is used for processing and another set is used for backward passes. This produces the so-called "weight transport problem" for biological models of learning, where the backward weights used to calculate gradients need to mirror the forward weights used to process stimuli. This weight transport problem has been considered so hard that popular proposals for biological learning assume that the backward weights are simply random, as in the feedback alignment algorithm. However, such random weights do not appear to work well for large networks. Here we show how the discontinuity introduced in a spiking system can lead to a solution to this problem. The resulting algorithm is a special case of an estimator used for causal inference in econometrics, regression discontinuity design. We show empirically that this algorithm rapidly makes the backward weights approximate the forward weights. As the backward weights become correct, this improves learning performance over feedback alignment on tasks such as Fashion-MNIST, SVHN, CIFAR-10 and VOC. Our results demonstrate that a simple learning rule in a spiking network can allow neurons to produce the right backward connections and thus solve the weight transport problem.
Forgetting at biologically realistic levels of neurogenesis in a large-scale hippocampal model
Lina M. Tran
Sheena A. Josselyn
Paul W. Frankland
A deep learning framework for neuroscience
Timothy P. Lillicrap
Philippe Beaudoin
Rafal Bogacz
Amelia Christensen
Claudia Clopath
Rui Ponte Costa
Archy de Berker
Surya Ganguli
Colleen J Gillon
Danijar Hafner
Adam Kepecs
Nikolaus Kriegeskorte
Peter Latham
Grace W. Lindsay
Kenneth D. Miller
Richard Naud
Christopher C. Pack
Panayiota Poirazi … (voir 12 de plus)
Pieter Roelfsema
João Sacramento
Andrew Saxe
Benjamin Scellier
Anna C. Schapiro
Walter Senn
Greg Wayne
Daniel Yamins
Friedemann Zenke
Joel Zylberberg
Denis Therien
Konrad Paul Kording
Dissociating memory accessibility and precision in forgetting
S. Berens
A. Horner
Dendritic solutions to the credit assignment problem
Timothy P. Lillicrap
Irrelevance by inhibition: Learning, computation, and implications for schizophrenia
Nathan Insel
Jordan Guerguiev
Symptoms of schizophrenia may arise from a failure of cortical circuits to filter-out irrelevant inputs. Schizophrenia has also been linked … (voir plus)to disruptions in cortical inhibitory interneurons, consistent with the possibility that in the normally functioning brain, these cells are in some part responsible for determining which sensory inputs are relevant versus irrelevant. Here, we develop a neural network model that demonstrates how the cortex may learn to ignore irrelevant inputs through plasticity processes affecting inhibition. The model is based on the proposal that the amount of excitatory output from a cortical circuit encodes the expected magnitude of reward or punishment (“relevance”), which can be trained using a temporal difference learning mechanism acting on feedforward inputs to inhibitory interneurons. In the model, irrelevant and blocked stimuli drive lower levels of excitatory activity compared with novel and relevant stimuli, and this difference in activity levels is lost following disruptions to inhibitory units. When excitatory units are connected to a competitive-learning output layer with a threshold, the relevance code can be shown to “gate” both learning and behavioral responses to irrelevant stimuli. Accordingly, the combined network is capable of recapitulating published experimental data linking inhibition in frontal cortex with fear learning and expression. Finally, the model demonstrates how relevance learning can take place in parallel with other types of learning, through plasticity rules involving inhibitory and excitatory components, respectively. Altogether, this work offers a theory of how the cortex learns to selectively inhibit inputs, providing insight into how relevance-assignment problems may emerge in schizophrenia.
Relevance learning via inhibitory plasticity and its implications for schizophrenia
Nathan Insel
Jordan Guerguiev
Symptoms of schizophrenia may arise from a failure of cortical circuits to filter-out irrelevant inputs. Schizophrenia has also been linked … (voir plus)to disruptions to cortical inhibitory interneurons, consistent with the possibility that in the normally functioning brain, these cells are in some part responsible for determining which inputs are relevant and which irrelevant. Here, we develop an abstract but biologically plausible neural network model that demonstrates how the cortex may learn to ignore irrelevant inputs through plasticity processes affecting inhibition. The model is based on the proposal that the amount of excitatory output from a cortical circuit encodes expected magnitude of reward or punishment (”relevance”), which can be trained using a temporal difference learning mechanism acting on feed-forward inputs to inhibitory interneurons. The model exhibits learned irrelevance and blocking, which become impaired following disruptions to inhibitory units. When excitatory units are connected to a competitive-learning output layer, the relevance code is capable of modulating learning and activity. Accordingly, the combined network is capable of recapitulating published experimental data linking inhibition in frontal cortex with fear learning and expression. Finally, the model demonstrates how relevance learning can take place in parallel with other types of learning, through plasticity rules involving inhibitory and excitatory components respectively. Altogether, this work offers a theory of how the cortex learns to selectively inhibit inputs, providing insight into how relevance-assignment problems may emerge in schizophrenia.
Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures
Sergey Bartunov
Adam Santoro
Luke Marris
Geoffrey Hinton
Timothy P. Lillicrap
The backpropagation of error algorithm (BP) is impossible to implement in a real brain. The recent success of deep networks in machine learn… (voir plus)ing and AI, however, has inspired proposals for understanding how the brain might learn across multiple layers, and hence how it might approximate BP. As of yet, none of these proposals have been rigorously evaluated on tasks where BP-guided deep learning has proved critical, or in architectures more structured than simple fully-connected networks. Here we present results on scaling up biologically motivated models of deep learning on datasets which need deep networks with appropriate architectures to achieve good performance. We present results on the MNIST, CIFAR-10, and ImageNet datasets and explore variants of target-propagation (TP) and feedback alignment (FA) algorithms, and explore performance in both fully- and locally-connected architectures. We also introduce weight-transport-free variants of difference target propagation (DTP) modified to remove backpropagation from the penultimate layer. Many of these algorithms perform well for MNIST, but for CIFAR and ImageNet we find that TP and FA variants perform significantly worse than BP, especially for networks composed of locally connected units, opening questions about whether new architectures and algorithms are required to scale these approaches. Our results and implementation details help establish baselines for biologically motivated deep learning schemes going forward.