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
Deep Generative Stochastic Networks Trainable by Backprop
TL;DR: Generative stochastic networks (GSN) as discussed by the authors learn the transition operator of a Markov chain whose stationary distribution estimates the data distribution, which is an alternative to maximum likelihood.
Proceedings Article
Sharp minima can generalize for deep nets
TL;DR: The authors argue that most notions of flatness are problematic for deep models and can not be directly applied to explain generalization, and exploit the particular geometry of parameter space induced by the inherent symmetries that these architectures exhibit to build equivalent models corresponding to arbitrarily sharper minima.
Proceedings Article
MetaGAN: an adversarial approach to few-shot learning
TL;DR: This paper proposes a conceptually simple and general framework called MetaGAN for few-shot learning problems, and shows that with this MetaGAN framework, it can extend supervised few- shot learning models to naturally cope with unlabeled data.
Proceedings Article
What Regularized Auto-Encoders Learn from the Data Generating Distribution
Guillaume Alain,Yoshua Bengio +1 more
TL;DR: It is shown that the auto-encoder captures the score (derivative of the log-density with respect to the input) and contradicts previous interpretations of reconstruction error as an energy function.
Posted Content
SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
Soroush Mehri,Kundan Kumar,Ishaan Gulrajani,Rithesh Kumar,Shubham Jain,Jose Sotelo,Aaron Courville,Yoshua Bengio +7 more
TL;DR: In this article, the authors proposed a novel model for unconditional audio generation based on generating one audio sample at a time, which profits from combining memoryless modules, namely autoregressive multilayer perceptrons, and stateful recurrent neural networks in a hierarchical structure.