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

Visiteur de recherche indépendant - N/A

philippe.beaudoin@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

Compositional Attention: Disentangling Search and Retrieval

Sarthak Mittal

Sharath Chandra Raparthy

Irina Rish

Yoshua Bengio

Multi-head, key-value attention is the backbone of the widely successful Transformer model and its variants. This attention mechanism uses m… (voir plus)ultiple parallel key-value attention blocks (called heads), each performing two fundamental computations: (1) search - selection of a relevant entity from a set via query-key interactions, and (2) retrieval - extraction of relevant features from the selected entity via a value matrix. Importantly, standard attention heads learn a rigid mapping between search and retrieval. In this work, we first highlight how this static nature of the pairing can potentially: (a) lead to learning of redundant parameters in certain tasks, and (b) hinder generalization. To alleviate this problem, we propose a novel attention mechanism, called Compositional Attention, that replaces the standard head structure. The proposed mechanism disentangles search and retrieval and composes them in a dynamic, flexible and context-dependent manner through an additional soft competition stage between the query-key combination and value pairing. Through a series of numerical experiments, we show that it outperforms standard multi-head attention on a variety of tasks, including some out-of-distribution settings. Through our qualitative analysis, we demonstrate that Compositional Attention leads to dynamic specialization based on the type of retrieval needed. Our proposed mechanism generalizes multi-head attention, allows independent scaling of search and retrieval, and can easily be implemented in lieu of standard attention heads in any network architecture.

2022-04-24

International Conference on Learning Representations (Accept (Spotlight))

Continuous-Time Meta-Learning with Forward Mode Differentiation

Drawing inspiration from gradient-based meta-learning methods with infinitely small gradient steps, we introduce Continuous-Time Meta-Learni… (voir plus)ng (COMLN), a meta-learning algorithm where adaptation follows the dynamics of a gradient vector field. Specifically, representations of the inputs are meta-learned such that a task-specific linear classifier is obtained as a solution of an ordinary differential equation (ODE). Treating the learning process as an ODE offers the notable advantage that the length of the trajectory is now continuous, as opposed to a fixed and discrete number of gradient steps. As a consequence, we can optimize the amount of adaptation necessary to solve a new task using stochastic gradient descent, in addition to learning the initial conditions as is standard practice in gradient-based meta-learning. Importantly, in order to compute the exact meta-gradients required for the outer-loop updates, we devise an efficient algorithm based on forward mode differentiation, whose memory requirements do not scale with the length of the learning trajectory, thus allowing longer adaptation in constant memory. We provide analytical guarantees for the stability of COMLN, we show empirically its efficiency in terms of runtime and memory usage, and we illustrate its effectiveness on a range of few-shot image classification problems.

2022-04-24

ICLR (Accept (Spotlight))

From Points to Functions: Infinite-dimensional Representations in Diffusion Models

Sarthak Mittal

Stefan Bauer

Arash Mehrjou

Diffusion-based generative models learn to iteratively transfer unstructured noise to a complex target distribution as opposed to Generative… (voir plus) Adversarial Networks (GANs) or the decoder of Variational Autoencoders (VAEs) which produce samples from the target distribution in a single step. Thus, in diffusion models every sample is naturally connected to a random trajectory which is a solution to a learned stochastic differential equation (SDE). Generative models are only concerned with the final state of this trajectory that delivers samples from the desired distribution. Abstreiter et. al showed that these stochastic trajectories can be seen as continuous filters that wash out information along the way. Consequently, it is reasonable to ask if there is an intermediate time step at which the preserved information is optimal for a given downstream task. In this work, we show that a combination of information content from different time steps gives a strictly better representation for the downstream task. We introduce an attention and recurrence based modules that ``learn to mix'' information content of various time-steps such that the resultant representation leads to superior performance in downstream tasks.

2022-03-27

ICLR.cc/2022/Workshop/DGM4HSD (poster)

Inductive Biases for Relational Tasks

Blake Aaron Richards

Current deep learning approaches have shown good in-distribution performance but struggle in out-of-distribution settings. This is especiall… (voir plus)y true in the case of tasks involving abstract relations like recognizing rules in sequences, as required in many intelligence tests. In contrast, our brains are remarkably flexible at such tasks, an attribute that is likely linked to anatomical constraints on computations. Inspired by this, recent work has explored how enforcing that relational representations remain distinct from sensory representations can help artificial systems. Building on this work, we further explore and formalize the advantages afforded by ``partitioned'' representations of relations and sensory details. We investigate inductive biases that ensure abstract relations are learned and represented distinctly from sensory data across several neural network architectures and show that they outperform existing architectures on out-of-distribution generalization for various relational tasks. These results show that partitioning relational representations from other information streams may be a simple way to augment existing network architectures' robustness when performing relational computations.

2022-03-24

ICLR.cc/2022/Workshop/OSC (poster)

On Lyapunov Exponents for RNNs: Understanding Information Propagation Using Dynamical Systems Tools

Ryan Vogt

Maximilian Puelma Touzel

Eli Shlizerman

Recurrent neural networks (RNNs) have been successfully applied to a variety of problems involving sequential data, but their optimization i… (voir plus)s sensitive to parameter initialization, architecture, and optimizer hyperparameters. Considering RNNs as dynamical systems, a natural way to capture stability, i.e., the growth and decay over long iterates, are the Lyapunov Exponents (LEs), which form the Lyapunov spectrum. The LEs have a bearing on stability of RNN training dynamics because forward propagation of information is related to the backward propagation of error gradients. LEs measure the asymptotic rates of expansion and contraction of nonlinear system trajectories, and generalize stability analysis to the time-varying attractors structuring the non-autonomous dynamics of data-driven RNNs. As a tool to understand and exploit stability of training dynamics, the Lyapunov spectrum fills an existing gap between prescriptive mathematical approaches of limited scope and computationally-expensive empirical approaches. To leverage this tool, we implement an efficient way to compute LEs for RNNs during training, discuss the aspects specific to standard RNN architectures driven by typical sequential datasets, and show that the Lyapunov spectrum can serve as a robust readout of training stability across hyperparameters. With this exposition-oriented contribution, we hope to draw attention to this understudied, but theoretically grounded tool for understanding training stability in RNNs.

2022-03-01

Frontiers in Applied Mathematics and Statistics (publié)

arxiv.org

Author Correction: Gradient-based learning drives robust representations in recurrent neural networks by balancing compression and expansion

Matthew Farrell

Stefano Recanatesi

Timothy Moore

Eric Shea-Brown

2021-12-31

Nature Machine Intelligence (publié)

Exploring the Geometry and Topology of Neural Network Loss Landscapes

Bastian Rieck

Recent work has established clear links between the generalization performance of trained neural networks and the geometry of their loss lan… (voir plus)dscape near the local minima to which they converge. This suggests that qualitative and quantitative examination of the loss landscape geometry could yield insights about neural network generalization performance during training. To this end, researchers have proposed visualizing the loss landscape through the use of simple dimensionality reduction techniques. However, such visualization methods have been limited by their linear nature and only capture features in one or two dimensions, thus restricting sampling of the loss landscape to lines or planes. Here, we expand and improve upon these in three ways. First, we present a novel "jump and retrain" procedure for sampling relevant portions of the loss landscape. We show that the resulting sampled data holds more meaningful information about the network's ability to generalize. Next, we show that non-linear dimensionality reduction of the jump and retrain trajectories via PHATE, a trajectory and manifold-preserving method, allows us to visualize differences between networks that are generalizing well vs poorly. Finally, we combine PHATE trajectories with a computational homology characterization to quantify trajectory differences.

2021-12-31

International Symposium on Intelligent Data Analysis (publié)

arxiv.org

Goal-driven optimization of single-neuron properties in artiﬁcial networks reveals regularization role of neural diversity and adaptation in the brain

Neurons in the brain have rich and adaptive input-output properties. Features such as diverse f-I curves and spike frequency adaptation are … (voir plus)known to place single neurons in optimal coding regimes when facing changing stimuli. Yet, it is still unclear how brain circuits exploit single neuron ﬂexibility, and how network-level requirements may have shaped such cellular function. To answer this question, a multi-scaled approach is needed where the computations of single neurons and of neural circuits must be considered as a complete system. In this work, we use artiﬁcial neural networks to systematically investigate single neuron input-output adaptive mechanisms, optimized in an end-to-end fashion. Throughout the optimization process, each neuron has the liberty to modify its nonlinear activation function, parametrized to mimic f-I curves of biological neurons, and to learn adaptation strategies to modify activation functions in real-time during a task. We ﬁnd that such networks show much-improved robustness to noise and changes in input statistics. Importantly, we ﬁnd that this procedure recovers precise coding strategies found in biological neurons, such as gain scaling and fractional order differentiation/integration. Using tools from dynamical systems theory, we analyze the role of these emergent single neuron properties and argue that neural diversity and adaptation plays an active regularization role that enables neural circuits to optimally propagate information across time.

2021-12-31

(publié)

www.semanticscholar.org

Learning to evoke complex motor outputs with spatiotemporal neurostimulation using a hierarchical and adaptive optimization algorithm.

Samuel Laferrière

Marco Bonizzato

Numa Dancause

The development of neurostimulation techniques to evoke motor patterns is an active area of research. It serves as a crucial experimental to… (voir plus)ol to probe computation in neural circuits, and it has applications in neuroprostheses used to aid recovery of function after stroke or injury. There are two important challenges when designing algorithms to unveil and control neurostimulation-to-motor mappings, thereby linking spatiotemporal patterns of neural stimulation to muscle activation: (1) the exploration of motor maps needs to be fast and efficient (exhaustive search is to be avoided for clinical and experimental reasons) (2) online learning needs to be flexible enough to track ongoing changes in these maps. We propose a stimulation search algorithm to address these issues, and demonstrate its efficacy with experiments in non-human primate models. Our solution is a novel iterative process using Bayesian Optimization via Gaussian Processes on increasingly complex signal spaces. We show that our algorithm can successfully and rapidly learn mappings between complex stimulation patterns and evoked muscle activation patterns, where standard approaches fail. Importantly, we uncover nonlinear circuit-level computations in M1 that would not have been possible to identify using conventional mapping techniques.

2021-12-31

Conference on Cognitive Computational Neuroscience (publié)

Gradient Starvation: A Learning Proclivity in Neural Networks

Sékou-Oumar Kaba

We identify and formalize a fundamental gradient descent phenomenon resulting in a learning proclivity in over-parameterized neural networks… (voir plus). Gradient Starvation arises when cross-entropy loss is minimized by capturing only a subset of features relevant for the task, despite the presence of other predictive features that fail to be discovered. This work provides a theoretical explanation for the emergence of such feature imbalance in neural networks. Using tools from Dynamical Systems theory, we identify simple properties of learning dynamics during gradient descent that lead to this imbalance, and prove that such a situation can be expected given certain statistical structure in training data. Based on our proposed formalism, we develop guarantees for a novel regularization method aimed at decoupling feature learning dynamics, improving accuracy and robustness in cases hindered by gradient starvation. We illustrate our findings with simple and real-world out-of-distribution (OOD) generalization experiments.

2021-12-06

NEURIPS (Accept (Poster))

Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning

Nan Rosemary Ke

Danilo Rezende

Michael Mozer

Christopher Pal

Inducing causal relationships from observations is a classic problem in machine learning. Most work in causality starts from the premise tha… (voir plus)t the causal variables themselves are observed. However, for AI agents such as robots trying to make sense of their environment, the only observables are low-level variables like pixels in images. To generalize well, an agent must induce high-level variables, particularly those which are causal or are affected by causal variables. A central goal for AI and causality is thus the joint discovery of abstract representations and causal structure. However, we note that existing environments for studying causal induction are poorly suited for this objective because they have complicated task-specific causal graphs which are impossible to manipulate parametrically (e.g., number of nodes, sparsity, causal chain length, etc.). In this work, our goal is to facilitate research in learning representations of high-level variables as well as causal structures among them. In order to systematically probe the ability of methods to identify these variables and structures, we design a suite of benchmarking RL environments. We evaluate various representation learning algorithms from the literature and find that explicitly incorporating structure and modularity in models can help causal induction in model-based reinforcement learning.

2021-10-10

Datasets and Benchmarks Track @ Neural Information Processing Systems (accepté)

Learning function from structure in neuromorphic networks

Laura E. Suárez

Blake A. Richards

Bratislav Misic

The connection patterns of neural circuits in the brain form a complex network. Collective signaling within the network manifests as pattern… (voir plus)ed neural activity, and is thought to support human cognition and adaptive behavior. Recent technological advances permit macro-scale reconstructions of biological brain networks. These maps, termed connectomes, display multiple non-random architectural features, including heavy-tailed degree distributions, segregated communities and a densely interconnected core. Yet, how computation and functional specialization emerge from network architecture remains unknown. Here we reconstruct human brain connectomes using in vivo diffusion-weighted imaging, and use reservoir computing to implement these connectomes as artificial neural networks. We then train these neuromorphic networks to learn a cognitive task. We show that biologically realistic neural architectures perform optimally when they display critical dynamics. We find that performance is driven by network topology, and that the modular organization of large-scale functional systems is computationally relevant. Throughout, we observe a prominent interaction between network structure and dynamics, such that the same underlying architecture can support a wide range of learning capacities across dynamical regimes. This work opens new opportunities to discover how the network organization of the brain optimizes cognitive capacity, conceptually bridging neuroscience and artificial intelligence.

2021-08-08

Nature Machine Intelligence (inconnu)