… & 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. …

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 …

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 …

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.“…

Multilayer neural networks trained with the back-propagation algorithm constitute the best
example of a successful gradient based learning technique. Given an appropriate network …

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 …

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, …

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 …

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 …

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 …