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
GradMask: Reduce Overfitting by Regularizing Saliency.
TL;DR: A regularization method is proposed, GradMask, which penalizes saliency maps inferred from the classifier gradients when they are not consistent with the lesion segmentation, which prevents non-tumor related features to contribute to the classification of unhealthy samples.
Proceedings Article
FigureQA: An annotated figure dataset for visual reasoning
Samira Ebrahimi Kahou,Adam Atkinson,Vincent Michalski,Ákos Kádár,Adam Trischler,Yoshua Bengio +5 more
TL;DR: FigureQA as discussed by the authors is a visual reasoning corpus of over one million question-answer pairs grounded in over 100,000 images, including line plots, dot-line plots, vertical and horizontal bar graphs, and pie charts.
Posted Content
Joint Training Deep Boltzmann Machines for Classification
TL;DR: In this article, a multi-inference trick is used to train all layers of the DBM simultaneously, using a novel training procedure called multi-prediction training, which can be interpreted as a single generative model trained to maximize a variational approximation to the generalized pseudolikelihood, or as a family of recurrent networks that share parameters and may be approximately averaged together.
Journal ArticleDOI
On the Morality of Artificial Intelligence [Commentary]
Alexandra Luccioni,Yoshua Bengio +1 more
TL;DR: Ethical principles and guidelines that surround machine learning and artificial intelligence are examined in a bid to clarify the role of language in the development of artificial intelligence.
Posted Content
S2RMs: Spatially Structured Recurrent Modules.
Nasim Rahaman,Anirudh Goyal,Muhammad Waleed Gondal,Manuel Wüthrich,Stefan Bauer,Yash Sharma,Yoshua Bengio,Bernhard Schölkopf +7 more
TL;DR: This work abstracts the modeled dynamical system as a collection of autonomous but sparsely interacting sub-systems, which results in a class of models that are well suited for modeling the dynamics of systems that only offer local views into their state, along with corresponding spatial locations of those views.