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
Using Simulated Data to Generate Images of Climate Change
Gautier Cosne,Adrien Juraver,Mélisande Teng,Victor Schmidt,Vahe Vardanyan,Alexandra Luccioni,Yoshua Bengio +6 more
TL;DR: The potential of using images from a simulated 3D environment to improve a domain adaptation task carried out by the MUNIT architecture is explored, aiming to use the resulting images to raise awareness of the potential future impacts of climate change.
Posted Content
A Robust Adaptive Stochastic Gradient Method for Deep Learning
TL;DR: An adaptive learning rate algorithm, which utilizes stochastic curvature information of the loss function for automatically tuning the learning rates and a new variance reduction technique to speed up the convergence.
Journal ArticleDOI
On the Generalization and Adaption Performance of Causal Models
TL;DR: This work systematically study the generalization and adaption performance of such modular neural causal models by comparing it to monolithic models and structured models where the set of predictors is not constrained to causal parents.
A simple and general method for semi-supervised learning
TL;DR: This work evaluates Brown clusters, Collobert and Weston (2008) embeddings, and HLBL (Mnih & Hinton, 2009) embeds of words on both NER and chunking, and finds that each of the three word representations improves the accuracy of these baselines.
Posted Content
Dynamic Layer Normalization for Adaptive Neural Acoustic Modeling in Speech Recognition
TL;DR: In this article, a new layer normalization technique called Dynamic Layer Normalization (DLN) is introduced for adaptive neural acoustic modeling in speech recognition, which dynamically generates the scaling and shifting parameters in layer normalisation.