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
Small-GAN: Speeding up GAN Training using Core-Sets
TL;DR: In this article, the authors proposed to use a cached dataset of Inception activations of each training image, and then use Coreset-selection on those projected activations at training time.
Posted Content
Statistical Learning Algorithms Applied to Automobile Insurance Ratemaking
TL;DR: This paper presents a meta-analyses of six models used for Bayesian inference of Neural Networks’ Representation of Nonlinear Interactions and concludes that three of them, the Constant Model and the Linear Model, are good candidates forBayesian inference.
Proceedings Article
Brain Inspired Reinforcement Learning
TL;DR: New reinforcement learning algorithms inspired by neurological evidence that provides potential new approaches to the feature construction problem are developed and evaluated.
Proceedings ArticleDOI
MaD TwinNet: Masker-Denoiser Architecture with Twin Networks for Monaural Sound Source Separation
Konstantinos Drossos,Stylianos Ioannis Mimilakis,Dmitriy Serdyuk,Gerald Schuller,Tuomas Virtanen,Yoshua Bengio +5 more
TL;DR: In this article, a novel recurrent neural approach that learns long-term temporal patterns and structures of a musical piece was proposed. But the performance of the proposed method was not as good as previous state-of-the-art methods, such as the Masker-Denoiser (MaD) architecture.