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
ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation
Francesco Visin,Marco Ciccone,Adriana Romero,Kyle Kastner,Kyunghyun Cho,Yoshua Bengio,Matteo Matteucci,Aaron Courville +7 more
TL;DR: A structured prediction architecture, which exploits the local generic features extracted by Convolutional Neural Networks and the capacity of Recurrent Neural Networks to retrieve distant dependencies, based on the recently introduced ReNet model for image classification is proposed.
Posted Content
Low precision arithmetic for deep learning
TL;DR: It is found that very low precision computation is sufficient not just for running trained networks but also for training them.
Journal ArticleDOI
LeRec: a NN/HMM hybrid for on-line handwriting recognition
TL;DR: A new approach for on-line recognition of handwritten words written in unconstrained mixed style by fitting a model of the word structure using the EM algorithm to minimize word-level errors.
Posted Content
Inductive Biases for Deep Learning of Higher-Level Cognition
Anirudh Goyal,Yoshua Bengio +1 more
TL;DR: This work considers a larger list of inductive biases that humans and animals exploit, focusing on those which concern mostly higher-level and sequential conscious processing, and suggests they could potentially help build AI systems benefiting from humans' abilities in terms of flexible out-of-distribution and systematic generalization.
Proceedings Article
Quick Training of Probabilistic Neural Nets by Importance Sampling
TL;DR: Inspired by the contrastive divergence model, sampling-based methods which require network passes only for the observed “positive example” and a few sampled negative example words are proposed and evaluated.