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 ArticleDOI
Quadratic Features and Deep Architectures for Chunking
TL;DR: Quadratic filters, a simplification of a theoretical model of V1 complex cells, reliably increase accuracy and logistic regression with quadratic filters outperforms a standard single hidden layer neural network.
Proceedings Article
Learning tags that vary within a song
TL;DR: It is found that the agreement between different people’s tags decreases as the distance between the parts of a song that they heard increases, and a conditional restricted Boltzmann machine is described to model this relationship.
Posted Content
Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models
TL;DR: This paper proposes a novel framework --- deep verifier networks (DVN) to verify the inputs and outputs of deep discriminative models with deep generative models based on conditional variational auto-encoders with disentanglement constraints.
Proceedings Article
InfoBot: Transfer and Exploration via the Information Bottleneck
Anirudh Goyal,Riashat Islam,DJ Strouse,Zafarali Ahmed,Hugo Larochelle,Matthew Botvinick,Yoshua Bengio,Sergey Levine +7 more
TL;DR: The authors propose to learn about decision states from prior experience by training a goal-conditioned policy with an information bottleneck, which can identify decision states by examining where the model actually leverages the goal state.
Proceedings ArticleDOI
Interpolated Adversarial Training: Achieving Robust Neural Networks Without Sacrificing Too Much Accuracy
TL;DR: Interpolated adversarial training as discussed by the authors employs interpolation based training methods in the framework of adversarial learning to improve the adversarial robustness of deep learning models, but it does not improve generalization performance on unperturbed data.