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
Three Factors Influencing Minima in SGD
Stanisław Jastrzębski,Zachary Kenton,Devansh Arpit,Nicolas Ballas,Asja Fischer,Yoshua Bengio,Amos Storkey +6 more
TL;DR: Through this analysis, it is found that three factors – learning rate, batch size and the variance of the loss gradients – control the trade-off between the depth and width of the minima found by SGD, with wider minima favoured by a higher ratio of learning rate to batch size.
Posted Content
Deep Complex Networks
Chiheb Trabelsi,Olexa Bilaniuk,Ying Zhang,Dmitriy Serdyuk,Sandeep Subramanian,João Felipe Santos,Soroush Mehri,Negar Rostamzadeh,Yoshua Bengio,Chris Pal +9 more
TL;DR: This work relies on complex convolutions and present algorithms for complex batch-normalization, complex weight initialization strategies for complex-valued neural nets and uses them in experiments with end-to-end training schemes and demonstrates that such complex- valued models are competitive with their real-valued counterparts.
Proceedings ArticleDOI
Advances in optimizing recurrent networks
TL;DR: In this paper, the authors evaluate the use of clipping gradients, spanning longer time ranges with leaky integration, advanced momentum techniques, using more powerful output probability models, and encouraging sparser gradients to help symmetry breaking and credit assignment.
Proceedings Article
Hierarchical Recurrent Neural Networks for Long-Term Dependencies
Salah El Hihi,Yoshua Bengio +1 more
TL;DR: This paper proposes to use a more general type of a-priori knowledge, namely that the temporal dependencies are structured hierarchically, which implies that long-term dependencies are represented by variables with a long time scale.
Journal ArticleDOI
EmoNets: Multimodal deep learning approaches for emotion recognition in video
Samira Ebrahimi Kahou,Xavier Bouthillier,Pascal Lamblin,Caglar Gulcehre,Vincent Michalski,Kishore Konda,Sébastien Jean,Pierre Froumenty,Yann N. Dauphin,Nicolas Boulanger-Lewandowski,Raul Chandias Ferrari,Mehdi Mirza,David Warde-Farley,Aaron Courville,Pascal Vincent,Roland Memisevic,Chris Pal,Yoshua Bengio +17 more
TL;DR: In this article, the authors presented an approach to learn several specialist models using deep learning techniques, each focusing on one modality, including CNN, deep belief net, K-means based bag-of-mouths, and relational autoencoder.