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
Focused Hierarchical RNNs for Conditional Sequence Processing
Nan Rosemary Ke,Konrad Zolna,Alessandro Sordoni,Zhouhan Lin,Adam Trischler,Yoshua Bengio,Joelle Pineau,Laurent Charlin,Chris Pal +8 more
TL;DR: This article propose a discrete gating mechanism for RNN encoders to attend to key parts of the input as needed, which is similar to our approach in the context embedding and current hidden state.
Posted Content
Perceptual Generative Autoencoders
TL;DR: This work proposes to map both the generated and target distributions to a latent space using the encoder of a standard autoencoder, and train the generator (or decoder) to match the target distribution in the latent space with theoretically justified data and latent reconstruction losses.
Posted Content
Learning invariant features through local space contraction
TL;DR: A novel approach for training deterministic auto-encoders is presented that by adding a well chosen penalty term to the classical reconstruction cost function, it is shown that this penalty term results in a localized space contraction which in turn yields robust features on the activation layer.
Posted Content
Predicting Solution Summaries to Integer Linear Programs under Imperfect Information with Machine Learning.
Eric Larsen,Sébastien Lachapelle,Yoshua Bengio,Emma Frejinger,Simon Lacoste-Julien,Andrea Lodi +5 more
TL;DR: This work proposes a methodology to quickly predict solution summaries to discrete stochastic optimization problems to solve intermodal containers on double-stack trains through supervised learning and a large number of deterministic problems that have been solved independently and offline.