Portrait de Guillaume Lajoie

Guillaume Lajoie

Membre académique principal
Chaire en IA Canada-CIFAR
Professeur agrégé, Université de Montréal
Chercheur invité, Google
Sujets de recherche
Apprentissage de représentations
Apprentissage profond
Cognition
IA en santé
IA pour la science
Neurosciences computationnelles
Optimisation
Raisonnement
Réseaux de neurones récurrents
Systèmes dynamiques

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

Collaborateur·rice alumni - Polytechnique
Doctorat - UdeM
Co-superviseur⋅e :
Visiteur de recherche indépendant - UdeM
Co-superviseur⋅e :
Doctorat - UdeM
Superviseur⋅e principal⋅e :
Postdoctorat - McGill
Superviseur⋅e principal⋅e :
Visiteur de recherche indépendant - McGill
Doctorat - McGill
Superviseur⋅e principal⋅e :
Collaborateur·rice de recherche - UdeM
Co-superviseur⋅e :
Doctorat - McGill
Superviseur⋅e principal⋅e :
Stagiaire de recherche - Concordia
Co-superviseur⋅e :
Visiteur de recherche indépendant - UdeM
Maîtrise recherche - UdeM
Maîtrise recherche - UdeM
Superviseur⋅e principal⋅e :
Doctorat - UdeM
Superviseur⋅e principal⋅e :
Doctorat - UdeM
Co-superviseur⋅e :
Postdoctorat - UdeM

Publications

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.
Learning to evoke complex motor outputs with spatiotemporal neurostimulation using a hierarchical and adaptive optimization algorithm.
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.
Gradient Starvation: A Learning Proclivity in Neural Networks
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.
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.
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.
Learning Brain Dynamics With Coupled Low-Dimensional Nonlinear Oscillators and Deep Recurrent Networks.
Aleksandr Y. Aravkin
Peng Zheng
James R. Kozloski
Pablo Polosecki
David D. Cox
Silvina Ponce Dawson
Guillermo A. Cecchi
Many natural systems, especially biological ones, exhibit complex multivariate nonlinear dynamical behaviors that can be hard to capture by … (voir plus)linear autoregressive models. On the other hand, generic nonlinear models such as deep recurrent neural networks often require large amounts of training data, not always available in domains such as brain imaging; also, they often lack interpretability. Domain knowledge about the types of dynamics typically observed in such systems, such as a certain type of dynamical systems models, could complement purely data-driven techniques by providing a good prior. In this work, we consider a class of ordinary differential equation (ODE) models known as van der Pol (VDP) oscil lators and evaluate their ability to capture a low-dimensional representation of neural activity measured by different brain imaging modalities, such as calcium imaging (CaI) and fMRI, in different living organisms: larval zebrafish, rat, and human. We develop a novel and efficient approach to the nontrivial problem of parameters estimation for a network of coupled dynamical systems from multivariate data and demonstrate that the resulting VDP models are both accurate and interpretable, as VDP's coupling matrix reveals anatomically meaningful excitatory and inhibitory interactions across different brain subsystems. VDP outperforms linear autoregressive models (VAR) in terms of both the data fit accuracy and the quality of insight provided by the coupling matrices and often tends to generalize better to unseen data when predicting future brain activity, being comparable to and sometimes better than the recurrent neural networks (LSTMs). Finally, we demonstrate that our (generative) VDP model can also serve as a data-augmentation tool leading to marked improvements in predictive accuracy of recurrent neural networks. Thus, our work contributes to both basic and applied dimensions of neuroimaging: gaining scientific insights and improving brain-based predictive models, an area of potentially high practical importance in clinical diagnosis and neurotechnology.
PNS-GAN: Conditional Generation of Peripheral Nerve Signals in the Wavelet Domain via Adversarial Networks
Luke Y. Prince
Pascal Fortier-Poisson
Lorenz Wernisch
Oliver Armitage
Emil Hewage
Blake Aaron Richards
Simulated datasets of neural recordings are a crucial tool in neural engineering for testing the ability of decoding algorithms to recover k… (voir plus)nown ground-truth. In this work, we introduce PNS-GAN, a generative adversarial network capable of producing realistic nerve recordings conditioned on physiological biomarkers. PNS-GAN operates in the wavelet domain to preserve both the timing and frequency of neural events with high resolution. PNS-GAN generates sequences of scaleograms from noise using a recurrent neural network and 2D transposed convolution layers. PNS-GAN discriminates over stacks of scaleograms with a network of 3D convolution layers. We find that our generated signal reproduces a number of characteristics of the real signal, including similarity in a canonical time-series feature-space, and contains physiologically related neural events including respiration modulation and similar distributions of afferent and efferent signalling.
Implicit Regularization via Neural Feature Alignment
We approach the problem of implicit regularization in deep learning from a geometrical viewpoint. We highlight a regularization effect induc… (voir plus)ed by a dynamical alignment of the neural tangent features introduced by Jacot et al, along a small number of task-relevant directions. This can be interpreted as a combined mechanism of feature selection and compression. By extrapolating a new analysis of Rademacher complexity bounds for linear models, we motivate and study a heuristic complexity measure that captures this phenomenon, in terms of sequences of tangent kernel classes along optimization paths.
Untangling tradeoffs between recurrence and self-attention in neural networks
Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules
Robust perception relies on both bottom-up and top-down signals. Bottom-up signals consist of what's directly observed through sensation. To… (voir plus)p-down signals consist of beliefs and expectations based on past experience and short-term memory, such as how the phrase `peanut butter and~...' will be completed. The optimal combination of bottom-up and top-down information remains an open question, but the manner of combination must be dynamic and both context and task dependent. To effectively utilize the wealth of potential top-down information available, and to prevent the cacophony of intermixed signals in a bidirectional architecture, mechanisms are needed to restrict information flow. We explore deep recurrent neural net architectures in which bottom-up and top-down signals are dynamically combined using attention. Modularity of the architecture further restricts the sharing and communication of information. Together, attention and modularity direct information flow, which leads to reliable performance improvements in perceptual and language tasks, and in particular improves robustness to distractions and noisy data. We demonstrate on a variety of benchmarks in language modeling, sequential image classification, video prediction and reinforcement learning that the \emph{bidirectional} information flow can improve results over strong baselines.
Advantages of biologically-inspired adaptive neural activation in RNNs during learning
Dynamic adaptation in single-neuron response plays a fundamental role in neural coding in biological neural networks. Yet, most neural activ… (voir plus)ation functions used in artificial networks are fixed and mostly considered as an inconsequential architecture choice. In this paper, we investigate nonlinear activation function adaptation over the large time scale of learning, and outline its impact on sequential processing in recurrent neural networks. We introduce a novel parametric family of nonlinear activation functions, inspired by input-frequency response curves of biological neurons, which allows interpolation between well-known activation functions such as ReLU and sigmoid. Using simple numerical experiments and tools from dynamical systems and information theory, we study the role of neural activation features in learning dynamics. We find that activation adaptation provides distinct task-specific solutions and in some cases, improves both learning speed and performance. Importantly, we find that optimal activation features emerging from our parametric family are considerably different from typical functions used in the literature, suggesting that exploiting the gap between these usual configurations can help learning. Finally, we outline situations where neural activation adaptation alone may help mitigate changes in input statistics in a given task, suggesting mechanisms for transfer learning optimization.
Learning Long-term Dependencies Using Cognitive Inductive Biases in Self-attention RNNs
Attention and self-attention mechanisms, inspired by cognitive processes, are now central to state-of-the-art deep learning on sequential ta… (voir plus)sks. However, most recent progress hinges on heuristic approaches that rely on considerable memory and computational resources that scale poorly. In this work, we propose a relevancy screening mechanism, inspired by the cognitive process of memory consolidation, that allows for a scalable use of sparse self-attention with recurrence. We use simple numerical experiments to demonstrate that this mechanism helps enable recurrent systems on generalization and transfer learning tasks. Based on our results, we propose a concrete direction of research to improve scalability and generalization of attentive recurrent networks.