User profiles for Yoshua Bengio
Yoshua BengioProfessor of computer science, University of Montreal, Mila, IVADO, CIFAR Verified email at umontreal.ca Cited by 785400 |
Deep learning
… & Bengio, Y. On the number of linear regions of deep neural networks. In Proc. … &
Bengio, Y. Neural machine translation by jointly learning to align and translate. In Proc. …
Bengio, Y. Neural machine translation by jointly learning to align and translate. In Proc. …
Learning deep architectures for AI
Y Bengio - Foundations and trends® in Machine Learning, 2009 - nowpublishers.com
Theoretical results suggest that in order to learn the kind of complicated functions that can
represent high-level abstractions (eg, in vision, language, and other AI-level tasks), one may …
represent high-level abstractions (eg, in vision, language, and other AI-level tasks), one may …
Representation learning: A review and new perspectives
The success of machine learning algorithms generally depends on data representation, and
we hypothesize that this is because different representations can entangle and hide more or …
we hypothesize that this is because different representations can entangle and hide more or …
[BOOK][B] Deep learning
An introduction to a broad range of topics in deep learning, covering mathematical and
conceptual background, deep learning techniques used in industry, and research perspectives.“…
conceptual background, deep learning techniques used in industry, and research perspectives.“…
Gradient-based learning applied to document recognition
Multilayer neural networks trained with the back-propagation algorithm constitute the best
example of a successful gradient based learning technique. Given an appropriate network …
example of a successful gradient based learning technique. Given an appropriate network …
Understanding the difficulty of training deep feedforward neural networks
X Glorot, Y Bengio - Proceedings of the thirteenth …, 2010 - proceedings.mlr.press
Whereas before 2006 it appears that deep multi-layer neural networks were not successfully
trained, since then several algorithms have been shown to successfully train them, with …
trained, since then several algorithms have been shown to successfully train them, with …
Scaling learning algorithms toward AI
One long-term goal of machine learning research is to produce methods that are applicable
to highly complex tasks, such as perception (vision, audition), reasoning, intelligent control, …
to highly complex tasks, such as perception (vision, audition), reasoning, intelligent control, …
Estimating or propagating gradients through stochastic neurons for conditional computation
Stochastic neurons and hard non-linearities can be useful for a number of reasons in deep
learning models, but in many cases they pose a challenging problem: how to estimate the …
learning models, but in many cases they pose a challenging problem: how to estimate the …
Deep generative stochastic networks trainable by backprop
We introduce a novel training principle for probabilistic models that is an alternative to maximum
likelihood. The proposed Generative Stochastic Networks (GSN) framework is based on …
likelihood. The proposed Generative Stochastic Networks (GSN) framework is based on …
Generative adversarial nets
We propose a new framework for estimating generative models via adversarial nets, in
which we simultaneously train two models: a generative model G that captures the data …
which we simultaneously train two models: a generative model G that captures the data …