Accueil

Inspirer le développement de l'intelligence artificielle au bénéfice de tous·tes

Un professeur s'entretient avec ses étudiants dans un café/lounge.

Situé au cœur de l’écosystème québécois en intelligence artificielle (IA), Mila rassemble une communauté de plus de 1200 personnes spécialisées en apprentissage automatique et dédiées à l’excellence scientifique et l’innovation.

À propos

À la une

Nouvelles

26 Sep 2024
Yoshua Bengio de Mila, Alondra Nelson ainsi que plusieurs autres experts en IA, formulent la Déclaration de Manhattan
Des participants à une réunion des Nations unies en septembre 2024
Lire la nouvelle
24 Sep 2024
Trinary signe un partenariat avec Mila pour faire progresser l'intelligence artificielle dans les PME
Mila and Trinary logo
Lire la nouvelle
20 Sep 2024
Lumière sur nos alumnis : Julien Horwood
picture of Julien Horwood
Lire la nouvelle
Voir plus de nouvelles

Corps professoral

Fondé en 1993 par le professeur Yoshua Bengio, Mila regroupe aujourd'hui plus de 140 professeur·e·s affilié·e·s à l'Université de Montréal, l'Université McGill, Polytechnique Montréal et HEC Montréal. L'institut accueille également des professeur·e·s de l'Université Laval, de l'Université de Sherbrooke, de l'École de technologie supérieure (ÉTS) et de l'Université Concordia.

Consultez l'annuaire en ligne

Photo de Yoshua Bengio

Publications récentes

INTREPPPID - An Orthologue-Informed Quintuplet Network for Cross-Species Prediction of Protein-Protein Interaction
Joseph Szymborski
Amin Emad
An overwhelming majority of protein-protein interaction (PPI) studies are conducted in a select few model organisms largely due to constrain… (voir plus)ts in time and cost of the associated “wet lab” experiments. In silico PPI inference methods are ideal tools to overcome these limitations, but often struggle with cross-species predictions. We present INTREPPPID, a method which incorporates orthology data using a new “quintuplet” neural network, which is constructed with five parallel encoders with shared parameters. INTREPPPID incorporates both a PPI classification task and an orthologous locality task. The latter learns embeddings of orthologues that have small Euclidean distances between them and large distances between embeddings of all other proteins. INTREPPPID outperforms all other leading PPI inference methods tested on both the intra-species and cross-species tasks using strict evaluation datasets. We show that INTREPPPID’s orthologous locality loss increases performance because of the biological relevance of the orthologue data, and not due to some other specious aspect of the architecture. Finally, we introduce PPI.bio and PPI Origami, a web server interface for INTREPPPID and a software tool for creating strict evaluation datasets, respectively. Together, these two initiatives aim to make both the use and development of PPI inference tools more accessible to the community. GRAPHICAL ABSTRACT
2024-08-22
Briefings in Bioinformatics (publié)
doi.org
One hundred years of EEG for brain and behaviour research
Faisal Mushtaq
Dominik Welke
Anne Gallagher
Yuri G. Pavlov
Layla Kouara
Jorge Bosch-Bayard
Jasper JF van den Bosch
Mahnaz Arvaneh
Amy R. Bland
Maximilien Chaumon
Cornelius Borck
Xun He
Steven J. Luck
Maro G. Machizawa
Cyril Pernet
Aina Puce
Sidney J. Segalowitz
Christine Rogers
Muhammad Awais
Claudio Babiloni … (voir 75 de plus)
Neil W. Bailey
Sylvain Baillet
Robert C. A. Bendall
Daniel Brady
Maria L. Bringas-Vega
Niko A. Busch
Ana Calzada-Reyes
Armand Chatard
Peter E. Clayson
Michael X. Cohen
Jonathan Cole
Martin Constant
Alexandra Corneyllie
Damien Coyle
Damian Cruse
Ioannis Delis
Arnaud Delorme
Damien Fair
Tiago H. Falk
Matthias Gamer
Giorgio Ganis
Kilian Gloy
Samantha Gregory
Cameron D. Hassall
Katherine E. Hiley
Richard B. Ivry
Karim Jerbi
Michael Jenkins
Jakob Kaiser
Andreas Keil
Robert T. Knight
Silvia Kochen
Boris Kotchoubey
Olave E. Krigolson
Nicolas Langer
Heinrich R. Liesefeld
Sarah Lippé
Raquel E. London
Annmarie MacNamara
Scott Makeig
Welber Marinovic
Eduardo Martínez-Montes
Aleya A. Marzuki
Ryan K. Mathew
Christoph Michel
José d. R. Millán
Mark Mon-Williams
Lilia Morales-Chacón
Richard Naar
Gustav Nilsonne
Guiomar Niso
Erika Nyhus
Robert Oostenveld
Katharina Paul
Walter Paulus
Daniela M. Pfabigan
Gilles Pourtois
Stefan Rampp
Manuel Rausch
Kay Robbins
Paolo M. Rossini
Manuela Ruzzoli
Barbara Schmidt
Magdalena Senderecka
Narayanan Srinivasan
Yannik Stegmann
Paul M. Thompson
Mitchell Valdes-Sosa
Melle J. W. van der Molen
Domenica Veniero
Edelyn Verona
Bradley Voytek
Dezhong Yao
Alan C. Evans
Pedro Valdes-Sosa
2024-08-22
Nature Human Behaviour (publié)
doi.org
Zero-Shot Object-Centric Representation Learning
Aniket Rajiv Didolkar
Andrii Zadaianchuk
Anirudh Goyal
Michael Curtis Mozer
Yoshua Bengio
Georg Martius
Maximilian Seitzer
The goal of object-centric representation learning is to decompose visual scenes into a structured representation that isolates the entities… (voir plus). Recent successes have shown that object-centric representation learning can be scaled to real-world scenes by utilizing pre-trained self-supervised features. However, so far, object-centric methods have mostly been applied in-distribution, with models trained and evaluated on the same dataset. This is in contrast to the wider trend in machine learning towards general-purpose models directly applicable to unseen data and tasks. Thus, in this work, we study current object-centric methods through the lens of zero-shot generalization by introducing a benchmark comprising eight different synthetic and real-world datasets. We analyze the factors influencing zero-shot performance and find that training on diverse real-world images improves transferability to unseen scenarios. Furthermore, inspired by the success of task-specific fine-tuning in foundation models, we introduce a novel fine-tuning strategy to adapt pre-trained vision encoders for the task of object discovery. We find that the proposed approach results in state-of-the-art performance for unsupervised object discovery, exhibiting strong zero-shot transfer to unseen datasets.
2024-08-17
ArXiv (prépublication)
arxiv.org
arxiv.org
Context-Aware Assistant Selection for Improved Inference Acceleration with Large Language Models
Jerry Huang
Prasanna Parthasarathi
Mehdi Rezagholizadeh
Sarath Chandar Anbil Parthipan
2024-08-16
ArXiv (prépublication)
arxiv.org
arxiv.org
Voir plus de publications

IA pour l'humanité

Le développement socialement responsable et bénéfique de l'IA est une dimension fondamentale de la mission de Mila. En tant que chef de file, nous souhaitons contribuer au dialogue social et au développement d'applications qui seront bénéfiques pour la société.

En savoir plus

Une personne regarde un ciel étoilé.