Portrait de Guillaume Dumas

Guillaume Dumas

Membre académique associé
Professeur agrégé, Université de Montréal, Département de psychiatrie et d’addictologie
Professeur adjoint, McGill University, Département de psychiatrie
Sujets de recherche
Apprentissage automatique médical
Apprentissage par renforcement
Apprentissage profond
Biologie computationnelle
Neurosciences computationnelles
Systèmes dynamiques
Théorie de l'apprentissage automatique

Biographie

Guillaume Dumas est professeur agrégé de psychiatrie computationnelle à la Faculté de médecine de l'Université de Montréal et chercheur principal du laboratoire de psychiatrie de précision et de physiologie sociale du Centre de recherche du CHU Sainte-Justine. Il est titulaire de la chaire IVADO IA en santé mentale et chercheur-boursier junior 1 du Fonds de recherche du Québec - Santé (FRQS) dans le domaine de l’ IA en santé et de la santé numérique. En 2023, il a été retenu dans le cadre du Programme des chercheurs mondiaux CIFAR-Azrieli pour le programme de recherche Cerveau, esprit et conscience. Il a également été nommé parmi les Futurs leaders canadiens de la recherche sur le cerveau par la Fondation Brain Canada.

Il a auparavant été chercheur permanent en neurosciences et en biologie computationnelle à l'Institut Pasteur (Paris, France), ainsi que chercheur postdoctoral au Center for Complex Systems and Brain Sciences à l’Université Florida Atlantic (FAU), aux États-Unis. Il est titulaire d'un diplôme d'ingénieur en ingénierie avancée et informatique (École centrale Paris), de deux masters (physique théorique, Université Paris-Saclay; sciences cognitives, ENS/EHESS/Paris 5) et d'un doctorat en neurosciences cognitives (Sorbonne Université).

Ses recherches visent à combiner l’intelligence artificielle, les neurosciences cognitives et la médecine numérique à travers un programme interdisciplinaire suivant deux axes principaux :

- L’intelligence artificielle en santé mentale, par la création de nouveaux algorithmes pour étudier le développement de l'architecture cognitive humaine et pour fournir une médecine personnalisée en neuropsychiatrie grâce à des données allant du génome à celles des téléphones intelligents;

- Les neurosciences sociales en intelligence artificielle, par la traduction de la recherche fondamentale sur le cerveau et le formalisme des systèmes dynamiques en des modèles hybrides neurocomputationnels et d’apprentissage automatique (NeuroML) et de nouvelles architectures présentant des capacités d'apprentissage social (NeuroIA Sociale et IHM).

Étudiants actuels

Maîtrise recherche - UdeM
Doctorat - UdeM
Maîtrise recherche - UdeM
Superviseur⋅e principal⋅e :
Postdoctorat - UdeM
Co-superviseur⋅e :
Doctorat - UdeM
Superviseur⋅e principal⋅e :

Publications

Grokking Beyond the Euclidean Norm of Model Parameters
Tikeng Notsawo Pascal Junior
Grokking refers to a delayed generalization following overfitting when optimizing artificial neural networks with gradient-based methods. I… (voir plus)n this work, we demonstrate that grokking can be induced by regularization, either explicit or implicit. More precisely, we show that when there exists a model with a property
Towards Multi-Brain Decoding in Autism: A Self-Supervised Learning Approach
Ghazaleh Ranjabaran
Quentin Moreau
Adrien Dubois
This study introduces a self-supervised learning (SSL) approach to hyperscanning electroencephalography (EEG) data, targeting the identifica… (voir plus)tion of autism spectrum condition (ASC) during social interactions. Hyperscanning enables simultaneous recording of neural activity across interacting individuals, offering a novel path for studying brain-to-brain synchrony in ASC. Leveraging a large-scale, single-brain EEG dataset for SSL pretraining, we developed a multi-brain classification model fine-tuned with hyperscanning data from dyadic interactions involving ASC and neurotypical participants. The SSL model demonstrated superior performance (78.13% accuracy) compared to supervised baselines and logistic regression using spectral EEG biomarkers. These results underscore the efficacy of SSL in addressing the challenges of limited labeled data, enhancing EEG-based diagnostic tools for ASC, and advancing research in social neuroscience.
La communication financière à l’épreuve de la crise COVID : une gestion des impressions ?
Corinne Bessieux-Ollier
Grégoire Davrinche
Nous étudions l’impact de la crise du COVID-19 sur la gestion des impressions pratiquée par les entreprises françaises cotées. Cette c… (voir plus)rise ayant eu un impact fort sur l’activité des entreprises, nous observons si les dirigeants modifient la manière de présenter l’information liée aux résultats non-GAAP, à travers l’utilisation de stratégies d’obscurcissement. Les données sur la gestion des impressions ont été collectées manuellement dans les communiqués de résultats annuels des entreprises du SBF 120 sur la période 2018-2020. Nous constatons une diminution générale du niveau de gestion des impressions en période de crise, notamment pour les entreprises des secteurs ayant été les plus impactés par la crise COVID. Cette diminution est toutefois moins prononcée pour les entreprises ayant sous-performé par rapport à leur secteur d’activité et pour les entreprises dont la performance a le plus diminué (indépendamment du secteur auquel elles appartiennent). Nos résultats suggèrent que les entreprises dont la baisse de performance pourrait être attribuée à des causes internes (résultats très défavorables, résultats en deçà du secteur d’activité) demeurent soucieuses de l’image qu’elles renvoient et maintiennent leur niveau de gestion des impressions malgré la crise.
Mirror effect of genomic deletions and duplications on cognitive ability across the human cerebral cortex
Kuldeep Kumar
Sayeh Kazem
Guillaume Huguet
Thomas Renne
Worrawat Engchuan
Martineau Jean-Louis
Jakub Kopal
Zohra Saci
Omar Shanta
Bhooma Thiruvahindrapuram
Jeffrey R. MacDonald
Josephine Mollon
Laura Schultz
Emma E M Knowles
David Porteous
Gail Davies
Paul Redmond
Sarah E. Harris
Simon R. Cox
Gunter Schumann … (voir 9 de plus)
Zdenka Pausova
Celia M. T. Greenwood
Tomas Paus
Stephen W Scherer
Laura Almasy
Jonathan Sebat
David C. Glahn
Sébastien Jacquemont
Regulation of gene expression shapes the interaction between brain networks which in-turn supports psychological processes such as cognitive… (voir plus) ability. How changes in level of gene expression across the cerebral cortex influence cognitive ability remains unknown. Here, we tackle this by leveraging genomic deletions and duplications - copy number variants (CNVs) that fully encompass one or more genes expressed in the human cortex - which lead to large effects on gene-expression levels. We assigned genes to 180 regions of the human cerebral cortex based on their preferential expression across the cortex computed using data from the Allen Human Brain Atlas. We aggregated CNVs in cortical regions, and ran a burden association analysis to compute the mean effect size of genes on general cognitive ability for each of the 180 regions. When affected by CNVs, most of the regional gene-sets were associated with lower cognitive ability. The spatial patterns of effect sizes across the cortex were correlated negatively between deletions and duplications. The largest effect sizes for deletions and duplications were observed for gene-sets with high expression in sensorimotor and association regions, respectively. These two opposing patterns of effect sizes were not influenced by intolerance to loss of function, demonstrating orthogonality to dosage-sensitivity scores. The same mirror patterns were also observed after stratifying genes based on cell types and developmental epochs markers. These results suggest that the effect size of gene dosage on cognitive ability follows a cortical gradient. The same brain region and corresponding gene-set may show different effects on cognition depending on whether variants increase or decrease transcription. The latter has major implications for the association of brain networks with phenotypes
Mirror effect of genomic deletions and duplications on cognitive ability across the human cerebral cortex
Kuldeep Kumar
Sayeh Kazem
Guillaume Huguet
Thomas Renne
Worrawat Engchuan
Martineau Jean-Louis
Jakub Kopal
Zohra Saci
Omar Shanta
Bhooma Thiruvahindrapuram
Jeffrey R. MacDonald
Josephine Mollon
Laura Schultz
Emma E M Knowles
David Porteous
Gail Davies
Paul Redmond
Sarah E. Harris
Simon R. Cox
Gunter Schumann … (voir 9 de plus)
Zdenka Pausova
Celia M. T. Greenwood
Tomas Paus
Stephen W Scherer
Laura Almasy
Jonathan Sebat
David C. Glahn
Sébastien Jacquemont
Regulation of gene expression shapes the interaction between brain networks which in-turn supports psychological processes such as cognitive… (voir plus) ability. How changes in level of gene expression across the cerebral cortex influence cognitive ability remains unknown. Here, we tackle this by leveraging genomic deletions and duplications - copy number variants (CNVs) that fully encompass one or more genes expressed in the human cortex - which lead to large effects on gene-expression levels. We assigned genes to 180 regions of the human cerebral cortex based on their preferential expression across the cortex computed using data from the Allen Human Brain Atlas. We aggregated CNVs in cortical regions, and ran a burden association analysis to compute the mean effect size of genes on general cognitive ability for each of the 180 regions. When affected by CNVs, most of the regional gene-sets were associated with lower cognitive ability. The spatial patterns of effect sizes across the cortex were correlated negatively between deletions and duplications. The largest effect sizes for deletions and duplications were observed for gene-sets with high expression in sensorimotor and association regions, respectively. These two opposing patterns of effect sizes were not influenced by intolerance to loss of function, demonstrating orthogonality to dosage-sensitivity scores. The same mirror patterns were also observed after stratifying genes based on cell types and developmental epochs markers. These results suggest that the effect size of gene dosage on cognitive ability follows a cortical gradient. The same brain region and corresponding gene-set may show different effects on cognition depending on whether variants increase or decrease transcription. The latter has major implications for the association of brain networks with phenotypes
Decomposing the Brain in Autism: Linking Behavioral Domains to Neuroanatomical Variation and Genomic Underpinnings.
Hanna Seelemeyer
Caroline Gurr
Johanna Leyhausen
Lisa M. Berg
Charlotte M. Pretzsch
Tim Schäfer
Bassem Hermila
Christine M. Freitag
Eva Loth
Beth Oakley
Luke Mason
Jan K. Buitelaar
Christian Beckmann
Dorothea L. Floris
Tony Charman
Tobias Banaschewski
Thomas Bourgeron
Jumana Ahmad
Sara Ambrosino
Bonnie Auyeung … (voir 56 de plus)
Simon Baron-Cohen
Sarah Baumeister
Sven Bölte
Carsten Bours
Michael Brammer
Daniel Brandeis
Claudia Brogna
Yvette de Bruijn
Bhismadev Chakrabarti
Ineke Cornelissen
Daisy Crawley
Flavio Dell’Acqua
Sarah Durston
Christine Ecker
Jessica Faulkner
Vincent Frouin
Pilar Garcés
David Goyard
Lindsay Ham
Hannah Hayward
Joerg F. Hipp
Rosemary Holt
Mark Johnson
Emily J. H. Jones
Prantik Kundu
Meng-Chuan Lai
Xavier Liogier D’ardhuy
Michael V. Lombardo
David J. Lythgoe
René Mandl
Andre Marquand
Maarten Mennes
Andreas Meyer-Lindenberg
Carolin Moessnang
Nico Bast
Laurence O’Dwyer
Marianne Oldehinkel
Bob Oranje
Gahan Pandina
Antonio Persico
Barbara Ruggeri
Amber N. V. Ruigrok
Jessica Sabet
Roberto Sacco
Antonia San José Cáceres
Emily Simonoff
Will Spooren
Julian Tillmann
Roberto Toro
Heike Tost
Jack Waldman
Steve C.R. Williams
Caroline Wooldridge
Marcel P. Zwiers
Declan Murphy
Decomposing the Brain in Autism: Linking Behavioral Domains to Neuroanatomical Variation and Genomic Underpinnings.
Hanna Seelemeyer
Caroline Gurr
Johanna Leyhausen
Lisa M. Berg
Charlotte M. Pretzsch
Tim Schäfer
Bassem Hermila
Christine M. Freitag
Dorothea L. Floris
Emily Jones
Jumana Ahmad
Sara Ambrosino
Bonnie Auyeung
Tobias Banaschewski
Simon Baron-Cohen
Sarah Baumeister
Christian Beckmann
Sven Bölte
Thomas Bourgeron
Carsten Bours … (voir 58 de plus)
Michael Brammer
Daniel Brandeis
Claudia Brogna
Yvette de Bruijn
Jan K. Buitelaar
Bhismadev Chakrabarti
Tony Charman
Ineke Cornelissen
Daisy Crawley
Flavio Dell’Acqua
Sarah Durston
Jessica Faulkner
Vincent Frouin
Pilar Garcés
David Goyard
Lindsay Ham
Hannah Hayward
Joerg F. Hipp
Rosemary Holt
Mark Johnson
Emily J. H. Jones
Prantik Kundu
Meng-Chuan Lai
Xavier Liogier D’ardhuy
Michael V. Lombardo
Eva Loth
David J. Lythgoe
René Mandl
Andre Marquand
Luke Mason
Maarten Mennes
Andreas Meyer-Lindenberg
Carolin Moessnang
Nico Bast
Declan G.M. Murphy
Beth Oakley
Laurence O’Dwyer
Marianne Oldehinkel
Bob Oranje
Gahan Pandina
Antonio Persico
Barbara Ruggeri
Amber N. V. Ruigrok
Jessica Sabet
Roberto Sacco
Antonia San José Cáceres
Emily Simonoff
Will Spooren
Julian Tillmann
Roberto Toro
Heike Tost
Jack Waldman
Steve C. R. Williams
Caroline Wooldridge
Marcel P. Zwiers
Declan Murphy
Christine Ecker
Decomposing the Brain in Autism: Linking Behavioral Domains to Neuroanatomical Variation and Genomic Underpinnings.
Hanna Seelemeyer
Caroline Gurr
Johanna Leyhausen
Lisa M. Berg
Charlotte M. Pretzsch
Tim Schäfer
Bassem Hermila
Christine M. Freitag
Eva Loth
Beth Oakley
Luke Mason
Jan K. Buitelaar
Christian Beckmann
Dorothea L. Floris
Tony Charman
Tobias Banaschewski
Thomas Bourgeron
Jumana Ahmad
Sara Ambrosino
Bonnie Auyeung … (voir 56 de plus)
Simon Baron-Cohen
Sarah Baumeister
Sven Bölte
Carsten Bours
Michael Brammer
Daniel Brandeis
Claudia Brogna
Yvette de Bruijn
Bhismadev Chakrabarti
Ineke Cornelissen
Daisy Crawley
Flavio Dell’Acqua
Sarah Durston
Christine Ecker
Jessica Faulkner
Vincent Frouin
Pilar Garcés
David Goyard
Lindsay Ham
Hannah Hayward
Joerg F. Hipp
Rosemary Holt
Mark Johnson
Emily J. H. Jones
Prantik Kundu
Meng-Chuan Lai
Xavier Liogier D’ardhuy
Michael V. Lombardo
David J. Lythgoe
René Mandl
Andre Marquand
Maarten Mennes
Andreas Meyer-Lindenberg
Carolin Moessnang
Nico Bast
Laurence O’Dwyer
Marianne Oldehinkel
Bob Oranje
Gahan Pandina
Antonio Persico
Barbara Ruggeri
Amber N. V. Ruigrok
Jessica Sabet
Roberto Sacco
Antonia San José Cáceres
Emily Simonoff
Will Spooren
Julian Tillmann
Roberto Toro
Heike Tost
Jack Waldman
Steve C. R. Williams
Caroline Wooldridge
Marcel P. Zwiers
Declan Murphy
Introducing Brain Foundation Models
Mohammad Javad Darvishi Bayazi
Hena Ghonia
Roland Riachi
Bruno Aristimunha
Arian Khorasani
Md Rifat Arefin
Sylvain Chevallier
Amin Darabi
Brain function represents one of the most complex systems driving our world. Decoding its signals poses significant challenges, particularly… (voir plus) due to the limited availability of data and the high cost of recordings. The existence of large hospital datasets and laboratory collections partially mitigates this issue. However, the lack of standardized recording protocols, varying numbers of channels, diverse setups, scenarios, and recording devices further complicate the task. This work addresses these challenges by introducing the Brain Foundation Model (BFM), a suite of open-source models trained on brain signals. These models serve as foundational tools for various types of time-series neuroimaging tasks. This work presents the first model of the BFM series, which is trained on electroencephalogram signal data. Our results demonstrate that BFM-EEG can generate signals more accurately than other models. Upon acceptance, we will release the model weights and pipeline.
LLMs and Personalities: Inconsistencies Across Scales
Tosato Tommaso
Mahmood Hegazy
David Lemay
Mohammed Abukalam
This study investigates the application of human psychometric assessments to large language models (LLMs) to examine their consistency and m… (voir plus)alleability in exhibiting personality traits. We administered the Big Five Inventory (BFI) and the Eysenck Personality Questionnaire-Revised (EPQ-R) to various LLMs across different model sizes and persona prompts. Our results reveal substantial variability in responses due to question order shuffling, challenging the notion of a stable LLM "personality." Larger models demonstrated more consistent responses, while persona prompts significantly influenced trait scores. Notably, the assistant persona led to more predictable scaling, with larger models exhibiting more socially desirable and less variable traits. In contrast, non-conventional personas displayed unpredictable behaviors, sometimes extending personality trait scores beyond the typical human range. These findings have important implications for understanding LLM behavior under different conditions and reflect on the consequences of scaling.
LLMs and Personalities: Inconsistencies Across Scales
Tosato Tommaso
Mahmood Hegazy
David Lemay
Mohammed Abukalam
This study investigates the application of human psychometric assessments to large language models (LLMs) to examine their consistency and m… (voir plus)alleability in exhibiting personality traits. We administered the Big Five Inventory (BFI) and the Eysenck Personality Questionnaire-Revised (EPQ-R) to various LLMs across different model sizes and persona prompts. Our results reveal substantial variability in responses due to question order shuffling, challenging the notion of a stable LLM "personality." Larger models demonstrated more consistent responses, while persona prompts significantly influenced trait scores. Notably, the assistant persona led to more predictable scaling, with larger models exhibiting more socially desirable and less variable traits. In contrast, non-conventional personas displayed unpredictable behaviors, sometimes extending personality trait scores beyond the typical human range. These findings have important implications for understanding LLM behavior under different conditions and reflect on the consequences of scaling.
Scalable Approaches for a Theory of Many Minds
Maximilian Puelma Touzel
Amin Memarian
Matthew D Riemer
Andrei Mircea
Andrew Robert Williams
Elin Ahlstrand
Lucas Lehnert
Rupali Bhati
A major challenge as we move towards building agents for real-world problems, which could involve a massive number of human and/or machine a… (voir plus)gents, is that we must learn to reason about the behavior of these many other agents. In this paper, we consider the problem of scaling a predictive Theory of Mind (ToM) model to a very large number of interacting agents with a fixed computational budget. Motivated by the limited diversity of agent types, existing approaches to scalable TOM learn versatile single-agent representations for quickly adapting to new agents encountered sequentially. We consider the more general setting that many agents are observed in parallel and formulate the corresponding Theory of Many Minds (ToMM) problem of estimating the joint policy. We frame the scaling behavior of solutions in terms of parameter sharing schemes and in particular propose two parameter-free architectural features that endow models with the ability to exploit action correlations: encoding a multi-agent context, and decoding through an abstracted joint action space. The increased predictive capabilities that have come with foundation models have made it easier to imagine the possibility of using these models to make simulations that imitate the behavior of many agents within complex real-world systems. Being able to perform these simulations in a general-purpose way would not only help make more capable agents, it also would be a very useful capability for applications in social science, political science, and economics.