Guillaume Lajoie

matteo.alleman@mila.quebec

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.

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.

Étudiants actuels

Matteo Alleman

Postdoctorat - UdeM

Rohan Banerjee

Collaborateur·rice alumni - Polytechnique

rohan.banerjee@mila.quebec

Doctorat - UdeM

Co-superviseur⋅e :

Hugo Larochelle

sangnie.bhardwaj@mila.quebec

Colin Bredenberg

Visiteur de recherche indépendant - UdeM

Co-superviseur⋅e :

colin.bredenberg@mila.quebec

Leo Choiniere

Doctorat - UdeM

leo.choiniere@mila.quebec

Claudia Clopath

Visiteur de recherche indépendant - University College London

claudia.clopath@mila.quebec

Eric Elmoznino

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Yoshua Bengio

eric.elmoznino@mila.quebec

Leo Gagnon

Doctorat - UdeM

leo.gagnon@mila.quebec

Tom George

Postdoctorat - McGill

Superviseur⋅e principal⋅e :

tomgeorge1@btinternet.com

Juan Guerra

Doctorat - Polytechnique

juan.guerra@mila.quebec

thomas.jiralerspong@mila.quebec

Nanda Harishankar Krishna

Doctorat - UdeM

Anna Jahn

Visiteur de recherche indépendant - McGill

anna.jahn1@mila.quebec

Chen Jiang

Doctorat - McGill

Superviseur⋅e principal⋅e :

Paul Masset

chen.jiang@mila.quebec

Thomas Jiralerspong

Doctorat - UdeM

Co-superviseur⋅e :

Yoshua Bengio

Maîtrise recherche - UdeM

Co-superviseur⋅e :

Dhanya Sridhar

tejaskasetty@gmail.com

Doctorat - McGill

Superviseur⋅e principal⋅e :

pingsheng.li@mila.quebec

mathys.loiselle@mila.quebec

Mathys Loiselle

Stagiaire de recherche - Concordia

Co-superviseur⋅e :

Matt Perich

Ximeng Mao

Doctorat - UdeM

Co-superviseur⋅e :

Joelle Pineau

ximeng.mao@mila.quebec

Abdel Mfougouon Njupoun

Doctorat - UdeM

Co-superviseur⋅e :

alexandre.payeur@mila.quebec

abdelnjupoun@gmail.com

Doctorat - UdeM

Co-superviseur⋅e :

Visiteur de recherche indépendant - UdeM

Julia Price

Maîtrise recherche - UdeM

julia.price@mila.quebec

Mauricio Rivera

Maîtrise recherche - UdeM

Superviseur⋅e principal⋅e :

Marco Bonizzato

mauriv2010@gmail.com

hee-woon.ryoo@mila.quebec

Avery Ryoo

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Matt Perich

Doctorat - UdeM

Co-superviseur⋅e :

Lune Bellec

sainathp@mila.quebec

ezekiel.williams@mila.quebec

Ryan Vogt

Postdoctorat - UdeM

ryan.vogt@mila.quebec

Ezekiel Williams

Doctorat - UdeM

Visiteur de recherche indépendant - University of Western Ontario

jinkang.xiang@mila.quebec

Billets de blogue

Représentation graphique d'un nerf vague

21 mai 2025

Apprentissage automatique pour la segmentation des différentes activations des fibres nerveuses à partir des signaux neuronaux du cerveau vers le corps

par

Param Raval

Olivier Tessier-Larivière

Pascal Fortier-Poisson

Blake Richards

Guillaume Lajoie

Lire l'article

13 juin 2024

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

par

Roman Pogodin

Jonathan Cornford

Arna Ghosh

Gauthier Gidel

Guillaume Lajoie

Blake Richards

Lire l'article

Publications

How Gradient Estimator Variance and Bias Could Impact Learning in Neural Circuits

Arna Ghosh

Yuhan Helena Liu

Konrad Kording

Blake A. Richards

2023-04-30

International Conference on Learning Representations (Accept: poster)

Reliability of CKA as a Similarity Measure in Deep Learning

MohammadReza Davari

Comparing learned neural representations in neural networks is a challenging but important problem, which has been approached in different w… (voir plus)ays. The Centered Kernel Alignment (CKA) similarity metric, particularly its linear variant, has recently become a popular approach and has been widely used to compare representations of a network's different layers, of architecturally similar networks trained differently, or of models with different architectures trained on the same data. A wide variety of conclusions about similarity and dissimilarity of these various representations have been made using CKA. In this work we present analysis that formally characterizes CKA sensitivity to a large class of simple transformations, which can naturally occur in the context of modern machine learning. This provides a concrete explanation of CKA sensitivity to outliers, which has been observed in past works, and to transformations that preserve the linear separability of the data, an important generalization attribute. We empirically investigate several weaknesses of the CKA similarity metric, demonstrating situations in which it gives unexpected or counter-intuitive results. Finally we study approaches for modifying representations to maintain functional behaviour while changing the CKA value. Our results illustrate that, in many cases, the CKA value can be easily manipulated without substantial changes to the functional behaviour of the models, and call for caution when leveraging activation alignment metrics.

2023-04-30

International Conference on Learning Representations (Accept: poster)

Use of Invasive Brain-Computer Interfaces in Pediatric Neurosurgery: Technical and Ethical Considerations

David Bergeron

Christian Iorio-Morin

Marco Bonizzato

Nathalie Orr Gaucher

Éric Racine

Alexander G. Weil

2023-04-27

Journal of Child Neurology (publié)

Autonomous optimization of neuroprosthetic stimulation parameters that drive the motor cortex and spinal cord outputs in rats and monkeys

Marco Bonizzato

Rose Guay Hottin

Sandrine L. Côté

Elena Massai

Leo Choiniere

Uzay Macar

Samuel Laferrière

Parikshat Sirpal

Stephan Quessy

Marina Martinez

Numa Dancause

Neural stimulation can alleviate paralysis and sensory deficits. Novel high-density neural interfaces can enable refined and multipronged ne… (voir plus)urostimulation interventions. To achieve this, it is essential to develop algorithmic frameworks capable of handling optimization in large parameter spaces. Here, we leveraged an algorithmic class, Gaussian-process (GP)-based Bayesian optimization (BO), to solve this problem. We show that GP-BO efficiently explores the neurostimulation space, outperforming other search strategies after testing only a fraction of the possible combinations. Through a series of real-time multi-dimensional neurostimulation experiments, we demonstrate optimization across diverse biological targets (brain, spinal cord), animal models (rats, non-human primates), in healthy subjects, and in neuroprosthetic intervention after injury, for both immediate and continual learning over multiple sessions. GP-BO can embed and improve “prior” expert/clinical knowledge to dramatically enhance its performance. These results advocate for broader establishment of learning agents as structural elements of neuroprosthetic design, enabling personalization and maximization of therapeutic effectiveness.

2023-03-31

Cell Reports Medicine (publié)

Neural manifolds and learning regimes in neural-interface tasks

Alexandre Payeur

Amy L. Orsborn

Neural activity tends to reside on manifolds whose dimension is lower than the dimension of the whole neural state space. Experiments using … (voir plus)brain-computer interfaces (BCIs) with microelectrode arrays implanted in the motor cortex of nonhuman primates have provided ways to test whether neural manifolds influence learning-related neural computations. Starting from a learned BCI-controlled motor task, these experiments explored the effect of changing the BCI decoder to implement perturbations that were either “aligned” or not with the pre-existing neural manifold. In a series of studies, researchers found that within-manifold perturbations (WMPs) evoked fast reassociations of existing neural patterns for rapid adaptation, while outside-manifold perturbations (OMPs) triggered a slower adaptation process that led to the emergence of new neural patterns. Together, these findings have been interpreted as suggesting that these different rates of adaptation might be associated with distinct learning mechanisms. Here, we investigated whether gradient-descent learning could alone explain these differences. Using an idealized model that captures the fixed-point dynamics of recurrent neural networks, we uncovered gradient-based learning dynamics consistent with experimental findings. Crucially, this experimental match arose only when the network was initialized in a lazier learning regime, a concept inherited from deep learning theory. A lazy learning regime—in contrast with a rich regime—implies small changes on synaptic strengths throughout learning. For OMPs, these small changes were less effective at increasing performance and could lead to unstable adaptation with a heightened sensitivity to learning rates. For WMPs, they helped reproduce the reassociation mechanism on short adaptation time scales, especially with large input variances. Since gradient descent has many biologically plausible variants, our findings establish lazy gradient-based learning as a plausible mechanism for adaptation under network-level constraints and unify several experimental results from the literature.

2023-03-11

bioRxiv (prépublication)

Transfer Entropy Bottleneck: Learning Sequence to Sequence Information Transfer

Damjan Kalajdzievski

Ximeng Mao

Pascal Fortier-Poisson

Blake A. Richards

When presented with a data stream of two statistically dependent variables, predicting the future of one of the variables (the target stream… (voir plus)) can benefit from information about both its history and the history of the other variable (the source stream). For example, fluctuations in temperature at a weather station can be predicted using both temperatures and barometric readings. However, a challenge when modelling such data is that it is easy for a neural network to rely on the greatest joint correlations within the target stream, which may ignore a crucial but small information transfer from the source to the target stream. As well, there are often situations where the target stream may have previously been modelled independently and it would be useful to use that model to inform a new joint model. Here, we develop an information bottleneck approach for conditional learning on two dependent streams of data. Our method, which we call Transfer Entropy Bottleneck (TEB), allows one to learn a model that bottlenecks the directed information transferred from the source variable to the target variable, while quantifying this information transfer within the model. As such, TEB provides a useful new information bottleneck approach for modelling two statistically dependent streams of data in order to make predictions about one of them.

2023-03-07

Transactions on Machine Learning Research (accepté)

Steerable Equivariant Representation Learning

Sangnie Bhardwaj

Willie McClinton

Tongzhou Wang

Chen Sun

Phillip Isola

Dilip Krishnan

Pre-trained deep image representations are useful for post-training tasks such as classification through transfer learning, image retrieval,… (voir plus) and object detection. Data augmentations are a crucial aspect of pre-training robust representations in both supervised and self-supervised settings. Data augmentations explicitly or implicitly promote invariance in the embedding space to the input image transformations. This invariance reduces generalization to those downstream tasks which rely on sensitivity to these particular data augmentations. In this paper, we propose a method of learning representations that are instead equivariant to data augmentations. We achieve this equivariance through the use of steerable representations. Our representations can be manipulated directly in embedding space via learned linear maps. We demonstrate that our resulting steerable and equivariant representations lead to better performance on transfer learning and robustness: e.g. we improve linear probe top-1 accuracy by between 1% to 3% for transfer; and ImageNet-C accuracy by upto 3.4%. We further show that the steerability of our representations provides significant speedup (nearly 50x) for test-time augmentations; by applying a large number of augmentations for out-of-distribution detection, we significantly improve OOD AUC on the ImageNet-C dataset over an invariant representation.

2023-02-21

ArXiv (prépublication)

« Que notre cerveau soit constitué de neurones n’est pas un accident »

Roman Ikonicoff

2023-01-01

Pour la Science (inconnu)

Multi-view manifold learning of human brain-state trajectories.

Erica L. Busch

Jessie Huang

Andrew Benz

Tom Wallenstein

Guy Wolf

Smita Krishnaswamy

Nicholas B. Turk-Browne

The complexity of the human brain gives the illusion that brain activity is intrinsically high-dimensional. Nonlinear dimensionality-reducti… (voir plus)on methods such as uniform manifold approximation and t-distributed stochastic neighbor embedding have been used for high-throughput biomedical data. However, they have not been used extensively for brain activity data such as those from functional magnetic resonance imaging (fMRI), primarily due to their inability to maintain dynamic structure. Here we introduce a nonlinear manifold learning method for time-series data—including those from fMRI—called temporal potential of heat-diffusion for affinity-based transition embedding (T-PHATE). In addition to recovering a low-dimensional intrinsic manifold geometry from time-series data, T-PHATE exploits the data’s autocorrelative structure to faithfully denoise and unveil dynamic trajectories. We empirically validate T-PHATE on three fMRI datasets, showing that it greatly improves data visualization, classification, and segmentation of the data relative to several other state-of-the-art dimensionality-reduction benchmarks. These improvements suggest many potential applications of T-PHATE to other high-dimensional datasets of temporally diffuse processes.

2022-12-31

Nature Computational Science (publié)

NEURAL MANIFOLDS AND GRADIENT-BASED ADAPTATION IN NEURAL-INTERFACE TASKS

Alexandre Payeur

Amy L. Orsborn

. Neural activity tends to reside on manifolds whose dimension is much lower than the dimension of the whole neural state space. Experiments… (voir plus) using brain-computer interfaces with microelectrode arrays implanted in the motor cortex of nonhuman primates tested the hypothesis that external perturbations should produce different adaptation strategies depending on how “aligned” the perturbation is with respect to a pre-existing intrinsic manifold. On the one hand, perturbations within the manifold (WM) evoked fast reassociations of existing patterns for rapid adaptation. On the other hand, perturbations outside the manifold (OM) triggered the slow emergence of new neural patterns underlying a much slower—and, without adequate training protocols, inconsistent or virtually impossible—adaptation. This suggests that the time scale and the overall difficulty of the brain to adapt depend fundamentally on the structure of neural activity. Here, we used a simplified static Gaussian model to show that gradient-descent learning could explain the differences between adaptation to WM and OM perturbations. For small learning rates, we found that the adaptation speeds were different but the model eventually adapted to both perturbations. Moreover, sufficiently large learning rates could entirely prohibit adaptation to OM perturbations while preserving adaptation to WM perturbations, in agreement with experiments. Adopting an incremental training protocol, as has been done in experiments, permitted a swift recovery of a full adaptation in the cases where OM perturbations were previously impossible to relearn. Finally, we also found that gradient descent was compatible with the reassociation mechanism on short adaptation time scales. Since gradient descent has many biologically plausible variants, our findings thus establish gradient-based learning as a plausible mechanism for adaptation under network-level constraints, with a central role for the learning rate.

2022-12-31

(publié)

www.semanticscholar.org

Lazy vs hasty: linearization in deep networks impacts learning schedule based on example difficulty

Thomas George

Aristide Baratin

Among attempts at giving a theoretical account of the success of deep neural networks, a recent line of work has identified a so-called `laz… (voir plus)y' training regime in which the network can be well approximated by its linearization around initialization. Here we investigate the comparative effect of the lazy (linear) and feature learning (non-linear) regimes on subgroups of examples based on their difficulty. Specifically, we show that easier examples are given more weight in feature learning mode, resulting in faster training compared to more difficult ones. In other words, the non-linear dynamics tends to sequentialize the learning of examples of increasing difficulty. We illustrate this phenomenon across different ways to quantify example difficulty, including c-score, label noise, and in the presence of easy-to-learn spurious correlations. Our results reveal a new understanding of how deep networks prioritize resources across example difficulty.

2022-12-19

TMLR (accepté)

Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules

Yuhan Helena Liu

Arna Ghosh

Blake A. Richards

Eric Shea-Brown

To unveil how the brain learns, ongoing work seeks biologically-plausible approximations of gradient descent algorithms for training recurre… (voir plus)nt neural networks (RNNs). Yet, beyond task accuracy, it is unclear if such learning rules converge to solutions that exhibit different levels of generalization than their nonbiologically-plausible counterparts. Leveraging results from deep learning theory based on loss landscape curvature, we ask: how do biologically-plausible gradient approximations affect generalization? We first demonstrate that state-of-the-art biologically-plausible learning rules for training RNNs exhibit worse and more variable generalization performance compared to their machine learning counterparts that follow the true gradient more closely. Next, we verify that such generalization performance is correlated significantly with loss landscape curvature, and we show that biologically-plausible learning rules tend to approach high-curvature regions in synaptic weight space. Using tools from dynamical systems, we derive theoretical arguments and present a theorem explaining this phenomenon. This predicts our numerical results, and explains why biologically-plausible rules lead to worse and more variable generalization properties. Finally, we suggest potential remedies that could be used by the brain to mitigate this effect. To our knowledge, our analysis is the first to identify the reason for this generalization gap between artificial and biologically-plausible learning rules, which can help guide future investigations into how the brain learns solutions that generalize.

2022-11-28

Conference on Neural Information Processing Systems (Accept)