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
Proceedings Article
Perceptual Generative Autoencoders
TL;DR: In this article, a perceptual generative autoencoder (PGA) is proposed to map both the generated and target distributions to a latent space using the encoder of a standard autoencoders, and train the generator or decoder to match the target distribution in the latent space.
Posted Content
Variational Causal Networks: Approximate Bayesian Inference over Causal Structures.
Yashas Annadani,Jonas Rothfuss,Alexandre Lacoste,Nino Scherrer,Anirudh Goyal,Yoshua Bengio,Stefan Bauer +6 more
TL;DR: In this article, a parametric variational family modelled by an autoregressive distribution over the space of discrete DAGs is proposed to learn the causal structure that underlies data.
Proceedings Article
Factorizing Declarative and Procedural Knowledge in Structured, Dynamical Environments
Anirudh Goyal,Alex Lamb,Phanideep Gampa,Philippe Beaudoin,Charles Blundell,Sergey Levine,Yoshua Bengio,Michael C. Mozer +7 more
TL;DR: In this article, the authors propose an architecture that factorizes declarative and procedural knowledge and imposes modularity within each form of knowledge by using attention to determine which object files to update, the selection of schemata, and the propagation of information between object files.
Distributed Representation Prediction for Generalization to New Words
Hugo Larochelle,Yoshua Bengio +1 more
TL;DR: This work considers the distributed representations of symbols of words as predictions from low-level or domain-knowledge features of words, which demonstrates the success of this approach in learning meaningful representations and in providing improved accuracy, especially for new words.
Posted Content
An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming
TL;DR: In this article, an end-to-end solution for molecular conformation prediction called ConfVAE based on the conditional variational autoencoder framework is proposed, where the molecular graph is first encoded in a latent space, and then the 3D structures are generated by solving a principled bilevel optimization program.