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 ContentDOI
Learning from unexpected events in the neocortical microcircuit
Colleen J Gillon,Jason E. Pina,Jérôme Lecoq,Ruweida Ahmed,Yazan N. Billeh,Shiella Caldejon,Peter A. Groblewski,Timothy M. Henley,India Kato,Eric Lee,Jennifer Luviano,Kyla Mace,Chelsea Nayan,Thuyanh V. Nguyen,Kat North,Jed Perkins,Sam Seid,Matthew T. Valley,Ali Williford,Yoshua Bengio,Yoshua Bengio,Timothy P. Lillicrap,Blake A. Richards,Joel Zylberberg +23 more
TL;DR: In this article, the authors show that unexpected event signals predict subsequent changes in responses to expected and unexpected stimuli in individual neurons and distal apical dendrites that are tracked over a period of days.
Posted Content
Batch Normalized Recurrent Neural Networks
TL;DR: This paper showed that batch normalization can lead to faster convergence of the training criterion but doesn't seem to improve the generalization performance on both language modelling and speech recognition tasks. But they also showed that applying batch normalisation to the hidden-to-hidden transitions of RNNs doesn't help the training procedure.
Posted Content
Drawing and Recognizing Chinese Characters with Recurrent Neural Network
TL;DR: Wang et al. as mentioned in this paper proposed a framework by using the recurrent neural network (RNN) as both a discriminative model for recognizing Chinese characters and a generator model for drawing (generating) Chinese characters.
Posted Content
How to Initialize your Network? Robust Initialization for WeightNorm & ResNets
TL;DR: This work proposes a novel parameter initialization strategy that avoids explosion/vanishment of information across layers for weight normalized networks with and without residual connections and shows that the proposed initialization outperforms existing initialization methods in terms of generalization performance, robustness to hyper-parameter values and variance between seeds.
Journal ArticleDOI
Learning GFlowNets from partial episodes for improved convergence and stability
Kanika Madan,Jarrid Rector-Brooks,Maksym Korablyov,Emmanuel Bengio,Moksh Jain,Andrei Cristian Nica,Tom Bosc,Yoshua Bengio,Kolya Malkin +8 more
TL;DR: Sub-trajectory balance as mentioned in this paper is a GFlowNet training objective that can learn from partial action subsequences of varying lengths, which accelerates sampler convergence in previously studied and new environments and enables training GFlowNets in environments with longer action sequences and sparser reward landscapes than what was possible before.