#### Filter Results:

- Full text PDF available (14)

#### Publication Year

2012

2016

- This year (0)
- Last 5 years (13)
- Last 10 years (14)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Data Set Used

Learn More

- Ian J. Goodfellow, Jean Pouget-Abadie, +5 authors Yoshua Bengio
- NIPS
- 2014

We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize theâ€¦ (More)

- Volodymyr Mnih, AdriÃ PuigdomÃ¨nech Badia, +5 authors Koray Kavukcuoglu
- ICML
- 2016

We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers. We present asynchronous variants of four standard reinforcement learning algorithms and show that parallel actor-learners have a stabilizing effect on training allowing allâ€¦ (More)

We consider the problem of designing models to leverage a recently introduced approximate model averaging technique called dropout. We define a simple new model called maxout (so named because its output is the max of a set of inputs, and because it is a natural companion to dropout) designed to both facilitate optimization by dropout and improve theâ€¦ (More)

- Rami Al-Rfou', Guillaume Alain, +109 authors Ying Zhang
- ArXiv
- 2016

Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements. Theano is being activelyâ€¦ (More)

- Mehdi Mirza, Simon Osindero
- ArXiv
- 2014

Generative Adversarial Nets [8] were recently introduced as a novel way to train generative models. In this work we introduce the conditional version of generative adversarial nets, which can be constructed by simply feeding the data, y, we wish to condition on to both the generator and discriminator. We show that this model can generate MNIST digitsâ€¦ (More)

- Ian J. Goodfellow, Jean Pouget-Abadie, +5 authors Yoshua Bengio
- ArXiv
- 2014

We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize theâ€¦ (More)

- Ian J. Goodfellow, Dumitru Erhan, +25 authors Yoshua Bengio
- ICONIP
- 2013

The ICML 2013 Workshop on Challenges in Representation Learning(1) focused on three challenges: the black box learning challenge, the facial expression recognition challenge, and the multimodal learning challenge. We describe the datasets created for these challenges and summarize the results of the competitions. We provide suggestions for organizers ofâ€¦ (More)

- Ian J. Goodfellow, David Warde-Farley, +6 authors Yoshua Bengio
- ArXiv
- 2013

Pylearn2 is a machine learning research library. This does not just mean that it is a collection of machine learning algorithms that share a common API; it means that it has been designed for flexibility and extensibility in order to facilitate research projects that involve new or unusual use cases. In this paper we give a brief history of the library, anâ€¦ (More)

We introduce the multi-prediction deep Boltzmann machine (MP-DBM). The MPDBM can be seen as a single probabilistic model trained to maximize a variational approximation to the generalized pseudolikelihood, or as a family of recurrent nets that share parameters and approximately solve different inference problems. Prior methods of training DBMs either do notâ€¦ (More)

- Samira Ebrahimi Kahou, Christopher Joseph Pal, +24 authors Zhenzhou Wu
- ICMI
- 2013

In this paper we present the techniques used for the University of Montréal's team submissions to the 2013 Emotion Recognition in the Wild Challenge. The challenge is to classify the emotions expressed by the primary human subject in short video clips extracted from feature length movies. This involves the analysis of video clips of acted scenesâ€¦ (More)