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
Posted Content
Ensemble of Generative and Discriminative Techniques for Sentiment Analysis of Movie Reviews
TL;DR: The authors compare several machine learning approaches to sentiment analysis, and combine them to achieve the best possible results on a large dataset of IMDB movie reviews, and show how to use for this task the standard generative language model.
Journal ArticleDOI
Feature-wise transformations
Vincent Dumoulin,Ethan Perez,Nathan Schucher,Florian Strub,Harm de Vries,Aaron Courville,Yoshua Bengio +6 more
TL;DR: In this paper, the authors present a set of real-world problems that require integrating multiple sources of information, such as vision, language, audio, etc., in order to understand a scene in a movie or answer a question about an image.
Proceedings Article
Artificial neural networks applied to taxi destination prediction
TL;DR: This work describes its first-place solution to the ECML/PKDD discovery challenge on taxi destination prediction by using an almost fully automated approach based on neural networks and ranking first out of 381 teams.
Proceedings ArticleDOI
Global training of document processing systems using graph transformer networks
TL;DR: A new machine learning paradigm called Graph Transformer Networks is proposed that extends the applicability of gradient-based learning algorithms to systems composed of modules that take graphs as inputs and produce graphs as output.
Posted Content
HeMIS: Hetero-Modal Image Segmentation
TL;DR: In this article, the authors introduce a deep learning image segmentation framework that is extremely robust to missing imaging modalities, which learns, for each modality, an embedding of the input image into a single latent vector space for which arithmetic operations (such as taking the mean) are well defined.