Y
Yoshua Bengio
Researcher at Université de Montréal
Publications - 1146
Citations - 534376
Yoshua Bengio is an academic researcher from Université de Montréal. The author has contributed to research in topics: Artificial neural network & Deep learning. The author has an hindex of 202, co-authored 1033 publications receiving 420313 citations. Previous affiliations of Yoshua Bengio include McGill University & Centre de Recherches Mathématiques.
Papers
More filters
Journal ArticleDOI
PhAST: Physics-Aware, Scalable, and Task-specific GNNs for Accelerated Catalyst Design
Alexandre Duval,Victor Schmidt,Santiago Miret,Yoshua Bengio,Alejandro Hernández-García,David Rolnick +5 more
TL;DR: PhAST as mentioned in this paper proposes task-specific improvements applicable to most architectures, enhancing both computational efficiency and accuracy for the Open Catalyst Project OC20 dataset, including improvements in graph creation step, atom representation, energy prediction head, and force prediction head.
Proceedings ArticleDOI
IAPR keynote lecture IV: Deep learning
TL;DR: This talk will summarize the advances that have made these breakthroughs possible, and end with questions about some major challenges still ahead of researchers in order to continue the climb towards AI-level competence.
Journal ArticleDOI
Consistent Training via Energy-Based GFlowNets for Modeling Discrete Joint Distributions
TL;DR: In this paper , a joint energy-based generative flow network (JEBGFN) is proposed to solve the problem of incompatibility between the inductive optimization biases in training the generator and the generator.
Posted Content
Comment améliorer la capacité de généralisation des algorithmes d'apprentissage pour la prise de décisions financières
Nicolas Chapados,Yoshua Bengio +1 more
TL;DR: In this paper, the authors present and propose several methods to improve the capacity of generalization of the learning algorithms in a context of financial decision-making, which aim at controlling the capacity to limit the problem of the over-training.
Posted Content
A Large-Scale, Open-Domain, Mixed-Interface Dialogue-Based ITS for STEM
Iulian Vlad Serban,Varun Gupta,Ekaterina Kochmar,Dung Do Vu,Robert Belfer,Joelle Pineau,Aaron Courville,Laurent Charlin,Yoshua Bengio +8 more
TL;DR: Korbit as discussed by the authors is a large-scale, open-domain, mixed-interface, dialogue-based intelligent tutoring system that uses machine learning, natural language processing and reinforcement learning to provide interactive, personalized learning online.