Guillaume Lajoie

Biographie

Guillaume Lajoie est professeur agrégé au Département de mathématiques et de statistiques (DMS) de l'Université de Montréal et membre académique principal de Mila – Institut québécois d’intelligence artificielle. Il est titulaire d'une chaire CIFAR (CCAI Canada) ainsi que d'une chaire de recherche du Canada (CRC) en calcul et interfaçage neuronaux.

Auparavant, Guillaume Lajoie a été chercheur postdoctoral à l'Institut de dynamique et d'auto-organisation Max-Planck et à l'Institut de neuro-ingénierie de l'Université de Washington. Il a obtenu son doctorat à l'Université de Washington (Seattle), au Département de mathématiques appliquées.

Ses recherches sont positionnées à l'intersection de l'IA et des neurosciences où il développe des outils pour mieux comprendre les mécanismes d'intelligence communs aux systèmes biologiques et artificiels. Les contributions de son groupe de recherche vont des progrès des paradigmes d'apprentissage à plusieurs échelles pour les grands systèmes artificiels aux applications en neurotechnologie. Dr. Lajoie participe activement aux efforts de développement responsables de l'IA, cherchant à identifier les lignes directrices et les meilleures pratiques pour l'utilisation de l'IA dans la recherche et au-delà.

Ses récentes recherches se concentrent sur le développement de biais inductifs architecturaux pour la propagation de l'information dans les réseaux récurrents, ainsi que le développement d'algorithmes et de modèles pour l'optimisation de l'interface bidirectionnelle cerveau-machine.

Étudiants actuels

Stefan Bauer

Visiteur de recherche indépendant

Superviseur⋅e principal⋅e :

Yoshua Bengio

Sangnie Bhardwaj

Doctorat - UdeM

Co-superviseur⋅e :

Hugo Larochelle

Colin Bredenberg

Postdoctorat - UdeM

Co-superviseur⋅e :

Leo Choiniere

Doctorat - UdeM

Olivier Codol

Postdoctorat - UdeM

Co-superviseur⋅e :

Matt Perich

Eric Elmoznino

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Leo Gagnon

Doctorat - UdeM

Rose Guay Hottin

Maîtrise recherche - Polytechnique

Superviseur⋅e principal⋅e :

Marco Bonizzato

Juan Guerra

Maîtrise recherche - Polytechnique

Superviseur⋅e principal⋅e :

Marco Bonizzato

Site web

Nanda Harishankar Krishna

Doctorat - UdeM

Collaborateur·rice de recherche - Western Washington University (faculty; assistant prof))

Superviseur⋅e principal⋅e :

Maîtrise recherche - UdeM

Co-superviseur⋅e :

Collaborateur·rice de recherche - UdeM

Ximeng Mao

Doctorat - UdeM

Co-superviseur⋅e :

Joelle Pineau

Abdel Mfougouon Njupoun

Doctorat - UdeM

Co-superviseur⋅e :

Doctorat - UdeM

Co-superviseur⋅e :

Amine Natik

Doctorat - UdeM

Co-superviseur⋅e :

Guy Wolf

François Paugam

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Lune Bellec

Que nous apprennent les distributions des coefficients synaptiques au sujet de l’apprentissage dans le cerveau ?

Alexandre Payeur

Collaborateur·rice de recherche - UdeM

Roman Pogodin

Postdoctorat - McGill

Superviseur⋅e principal⋅e :

Avery Ryoo

Maîtrise recherche - UdeM

Superviseur⋅e principal⋅e :

Doctorat - UdeM

Co-superviseur⋅e :

Doctorat - McGill

Stagiaire de recherche - Western Washington University

Co-superviseur⋅e :

Doctorat - UdeM

Billets de blogue

13 juin 2024

par

Roman Pogodin

Jonathan Cornford

Arna Ghosh

Gauthier Gidel

Guillaume Lajoie

Blake Richards

Lire l'article

Publications

Brain-like learning with exponentiated gradients

Jonathan Cornford

Roman Pogodin

Arna Ghosh

Kaiwen Sheng

Brendan A. Bicknell

Olivier Codol

Beverley A. Clark

2024-10-26

bioRxiv (prépublication)

Multi-agent cooperation through learning-aware policy gradients

Alexander Meulemans

Seijin Kobayashi

Johannes von Oswald

Nino Scherrer

Eric Elmoznino

Blaise Agüera y Arcas

João Sacramento

Self-interested individuals often fail to cooperate, posing a fundamental challenge for multi-agent learning. How can we achieve cooperation… (voir plus) among self-interested, independent learning agents? Promising recent work has shown that in certain tasks cooperation can be established between learning-aware agents who model the learning dynamics of each other. Here, we present the first unbiased, higher-derivative-free policy gradient algorithm for learning-aware reinforcement learning, which takes into account that other agents are themselves learning through trial and error based on multiple noisy trials. We then leverage efficient sequence models to condition behavior on long observation histories that contain traces of the learning dynamics of other agents. Training long-context policies with our algorithm leads to cooperative behavior and high returns on standard social dilemmas, including a challenging environment where temporally-extended action coordination is required. Finally, we derive from the iterated prisoner's dilemma a novel explanation for how and when cooperation arises among self-interested learning-aware agents.

2024-10-24

ArXiv (prépublication)

A Complexity-Based Theory of Compositionality

Eric Elmoznino

Thomas Jiralerspong

Yoshua Bengio

2024-10-18

ArXiv (prépublication)

Learning Stochastic Rainbow Networks

Vivian White

Muawiz Sajjad Chaudhary

Guy Wolf

Kameron Decker Harris

Random feature models are a popular approach for studying network learning that can capture important behaviors while remaining simpler than… (voir plus) traditional training. Guth et al. [2024] introduced “rainbow” networks which model the distribution of trained weights as correlated random features conditioned on previous layer activity. Sampling new weights from distributions fit to learned networks led to similar performance in entirely untrained networks, and the observed weight covariance were found to be low rank. This provided evidence that random feature models could be extended to some networks away from initialization, but White et al. [2024] failed to replicate their results in the deeper ResNet18 architecture. Here we ask whether the rainbow formulation can succeed in deeper networks by directly training a stochastic ensemble of random features, which we call stochastic rainbow networks. At every gradient descent iteration, new weights are sampled for all intermediate layers and features aligned layer-wise. We find: (1) this approach scales to deeper models, which outperform shallow networks at large widths; (2) ensembling multiple samples from the stochastic model is better than retraining the classifier head; and (3) low-rank parameterization of the learnable weight covariances can approach the accuracy of full-rank networks. This offers more evidence for rainbow and other structured random feature networks as reduced models of deep learning.

2024-10-10

NeurIPS.cc/2024/Workshop/SciForDL (poster)

openreview.net

The oneirogen hypothesis: modeling the hallucinatory effects of classical psychedelics in terms of replay-dependent plasticity mechanisms

Colin Bredenberg

Fabrice Normandin

2024-09-30

bioRxiv (prépublication)

Accelerating Training with Neuron Interaction and Nowcasting Networks

Boris Knyazev

Abhinav Moudgil

Eugene Belilovsky

Simon Lacoste-Julien

Neural network training can be accelerated when a learnable update rule is used in lieu of classic adaptive optimizers (e.g. Adam). However,… (voir plus) learnable update rules can be costly and unstable to train and use. A simpler recently proposed approach to accelerate training is to use Adam for most of the optimization steps and periodically, only every few steps, nowcast (predict future) parameters. We improve this approach by Neuron interaction and Nowcasting (NiNo) networks. NiNo leverages neuron connectivity and graph neural networks to more accurately nowcast parameters by learning in a supervised way from a set of training trajectories over multiple tasks. We show that in some networks, such as Transformers, neuron connectivity is non-trivial. By accurately modeling neuron connectivity, we allow NiNo to accelerate Adam training by up to 50\% in vision and language tasks.

2024-09-06

ArXiv (prépublication)

When can transformers compositionally generalize in-context?

Seijin Kobayashi

Simon Schug

Yassir Akram

Florian Redhardt

Johannes von Oswald

Razvan Pascanu

João Sacramento

Many tasks can be composed from a few independent components. This gives rise to a combinatorial explosion of possible tasks, only some of w… (voir plus)hich might be encountered during training. Under what circumstances can transformers compositionally generalize from a subset of tasks to all possible combinations of tasks that share similar components? Here we study a modular multitask setting that allows us to precisely control compositional structure in the data generation process. We present evidence that transformers learning in-context struggle to generalize compositionally on this task despite being in principle expressive enough to do so. Compositional generalization becomes possible only when introducing a bottleneck that enforces an explicit separation between task inference and task execution.

2024-07-17

ArXiv (prépublication)

Expressivity of Neural Networks with Random Weights and Learned Biases

Ezekiel Williams

Avery Hee-Woon Ryoo

Thomas Jiralerspong

Alexandre Payeur

Matt Perich

Luca Mazzucato

2024-07-01

ArXiv (prépublication)

Using neural biomarkers to personalize dosing of vagus nerve stimulation

Antonin Berthon

Lorenz Wernisch

Myrta Stoukidi

Michael Thornton

Olivier Tessier-Lariviere

Pascal Fortier-Poisson

Jorin Mamen

Max Pinkney

Susannah Lee

Elvijs Sarkans

Luca Annecchino

Ben Appleton

Philip Garsed

Bret Patterson

Samuel Gonshaw

Matjaž Jakopec

Sudhakaran Shunmugam

Tristan Edwards

Aleksi Tukiainen

Joel Jennings … (voir 3 de plus)

Emil Hewage

Oliver Armitage

2024-06-17

Bioelectronic Medicine (publié)

Expressivity of Neural Networks with Fixed Weights and Learned Biases

Ezekiel Williams

Avery Hee-Woon Ryoo

Thomas Jiralerspong

Alexandre Payeur

Matt Perich

Luca Mazzucato

2024-06-16

ICML.cc/2024/Workshop/HiLD (poster)

openreview.net

Does learning the right latent variables necessarily improve in-context learning?

Sarthak Mittal

Eric Elmoznino

L'eo Gagnon

Sangnie Bhardwaj

Dhanya Sridhar

Large autoregressive models like Transformers can solve tasks through in-context learning (ICL) without learning new weights, suggesting ave… (voir plus)nues for efficiently solving new tasks. For many tasks, e.g., linear regression, the data factorizes: examples are independent given a task latent that generates the data, e.g., linear coefficients. While an optimal predictor leverages this factorization by inferring task latents, it is unclear if Transformers implicitly do so or if they instead exploit heuristics and statistical shortcuts enabled by attention layers. Both scenarios have inspired active ongoing work. In this paper, we systematically investigate the effect of explicitly inferring task latents. We minimally modify the Transformer architecture with a bottleneck designed to prevent shortcuts in favor of more structured solutions, and then compare performance against standard Transformers across various ICL tasks. Contrary to intuition and some recent works, we find little discernible difference between the two; biasing towards task-relevant latent variables does not lead to better out-of-distribution performance, in general. Curiously, we find that while the bottleneck effectively learns to extract latent task variables from context, downstream processing struggles to utilize them for robust prediction. Our study highlights the intrinsic limitations of Transformers in achieving structured ICL solutions that generalize, and shows that while inferring the right latents aids interpretability, it is not sufficient to alleviate this problem.

2024-05-29

ArXiv (prépublication)

Assistive sensory-motor perturbations influence learned neural representations

Pavithra Rajeswaran

Alexandre Payeur

Amy L. Orsborn

Task errors are used to learn and refine motor skills. We investigated how task assistance influences learned neural representations using B… (voir plus)rain-Computer Interfaces (BCIs), which map neural activity into movement via a decoder. We analyzed motor cortex activity as monkeys practiced BCI with a decoder that adapted to improve or maintain performance over days. Population dimensionality remained constant or increased with learning, counter to trends with non-adaptive BCIs. Yet, over time, task information was contained in a smaller subset of neurons or population modes. Moreover, task information was ultimately stored in neural modes that occupied a small fraction of the population variance. An artificial neural network model suggests the adaptive decoders contribute to forming these compact neural representations. Our findings show that assistive decoders manipulate error information used for long-term learning computations, like credit assignment, which informs our understanding of motor learning and has implications for designing real-world BCIs.

2024-03-20

bioRxiv (prépublication)