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 ArticleDOI
Model evaluation for extreme risks
Toby Shevlane,Sebastian Farquhar,Ben Garfinkel,Mary Phuong,Jess Whittlestone,Jade Leung,Daniel Kokotajlo,Nahema Marchal,Markus Anderljung,Noam Kolt,Divya Siddarth,Shahar Avin,William T. Hawkins,Been Kim,Iason Gabriel,Jack Clark,Yoshua Bengio,Paul F. Christiano,Allan Dafoe +18 more
TL;DR: In this paper , the authors explain why model evaluation is critical for addressing extreme risks and why developers must be able to identify dangerous capabilities (through"dangerous capability evaluations") and the propensity of models to apply their capabilities for harm (through "alignment evaluations").
Proceedings ArticleDOI
On random weights for texture generation in one layer CNNS
TL;DR: It is theoretically show that one layer convolutional architectures (without a non-linearity) paired with the an energy function used in previous literature, can in fact preserve and modulate frequency coefficients in a manner so that random weights and pretrained weights will generate the same type of images.
Proceedings Article
Learning the Arrow of Time for Problems in Reinforcement Learning
TL;DR: This work illustrates how a learned arrow of time can capture salient information about the environment, which in turn can be used to measure reachability, detect side-effects and to obtain an intrinsic reward signal.
Découpage thématique des conversations : un outil d'aide à l'extraction
TL;DR: In this article, the authors decrivons the complexite du traitement automatique des conversations and present le decoupage thematique comme un outil d'aide a l'extraction.
Journal ArticleDOI
Detonation Classification from Acoustic Signature with the Restricted Boltzmann Machine
Yoshua Bengio,Nicolas Chapados,Olivier Delalleau,Hugo Larochelle,Xavier Saint-Mleux,Christian Hudon,Jérôme Louradour +6 more
TL;DR: In this paper, the authors compared the performance of the discriminative restricted Boltzmann machine (DRBM) and the classical Support Vector Machine (SVM) on a challenging classification task consisting in identifying weapon classes from audio signals.