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 Article
Transformers with Competitive Ensembles of Independent Mechanisms
TL;DR: Transformer with Independent Mechanisms (TIM) as discussed by the authors proposes Transformers with independent mechanisms, a new Transformer layer which divides the hidden representation and parameters into multiple mechanisms, which only exchange information through attention.
Journal ArticleDOI
GFlowNet-EM for learning compositional latent variable models
TL;DR: GFlowNet-EM as mentioned in this paper uses GFlowNets to sample from the posterior over latents, taking advantage of their strengths as amortized variational inference algorithms for complex distributions over discrete structures.
Posted Content
Variance Regularizing Adversarial Learning
TL;DR: This work proposes an additional method to train GANs by explicitly modeling the discriminator's output as a bi-modal Gaussian distribution over the real/fake indicator variables and observes that this new method, when trained together with a strong discriminator, provides meaningful, non-vanishing gradients.
Journal Article
RECOVER: sequential model optimization platform for combination drug repurposing identifies novel synergistic compounds in vitro
Paul Bertin,Jarrid Rector-Brooks,Deepak Sharma,Thomas Gaudelet,Andrew Anighoro,Torsten Gross,Francisco Martínez-Peña,Eileen L. Tang,S. SurajM,Cristian Regep,Jeremy B. R. Hayter,Maksym Korablyov,Nicholas Valiante,Almer M. van der Sloot,Mike Tyers,Charles Roberts,Michael J. Brownstein,Luke L. Lairson,Jake P. Taylor-King,Yoshua Bengio +19 more
TL;DR: A sequential model optimization search utilising a deep learning model is employed to quickly discover synergistic drug combinations active against a cancer cell line, requiring substantially less screening than an exhaustive evaluation.