#### Filter Results:

- Full text PDF available (15)

#### Publication Year

1967

2013

- This year (0)
- Last 5 years (3)
- Last 10 years (15)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Data Set Used

Learn More

- Salah Rifai, Pascal Vincent, Xavier Muller, Xavier Glorot, Yoshua Bengio
- ICML
- 2011

We present in this paper a novel approach for training deterministic auto-encoders. We show that by adding a well chosen penalty term to the classical reconstruction cost function, we can achieveâ€¦ (More)

- Yoshua Bengio, GrÃ©goire Mesnil, Yann Dauphin, Salah Rifai
- ICML
- 2013

It has been hypothesized, and supported with experimental evidence, that deeper representations, when well trained, tend to do a better job at disentangling the underlying factors of variation. Weâ€¦ (More)

- Salah Rifai, Yann Dauphin, Pascal Vincent, Yoshua Bengio, Xavier Muller
- NIPS
- 2011

We combine three important ideas present in previous work for building classifiers: the semi-supervised hypothesis (the input distribution contains information about the classifier), the unsupervisedâ€¦ (More)

- Salah Rifai, GrÃ©goire Mesnil, +4 authors Xavier Glorot
- ECML/PKDD
- 2011

We propose a novel regularizer when training an auto-encoder for unsupervised feature extraction. We explicitly encourage the latent representation to contract the input space by regularizing theâ€¦ (More)

We propose a semi-supervised approach to solve the task of emotion recognition in 2D face images using recent ideas in deep learning for handling the factors of variation present in data. An emotionâ€¦ (More)

- Yoshua Bengio, FrÃ©dÃ©ric Bastien, +14 authors Guillaume Sicard
- AISTATS
- 2011

Recent theoretical and empirical work in statistical machine learning has demonstrated the potential of learning algorithms for deep architectures, i.e., function classes obtained by composingâ€¦ (More)

- GrÃ©goire Mesnil, Yann Dauphin, +10 authors James Bergstra
- ICML Unsupervised and Transfer Learning
- 2012

Learning good representations from a large set of unlabeled data is a particularly challenging task. Recent work (see Bengio (2009) for a review) shows that training deep architectures is a good wayâ€¦ (More)

- Guillaume Alain, Yoshua Bengio, Salah Rifai
- ArXiv
- 2012

What do auto-encoders learn about the underlying data generating distribution? Recent work suggests that some auto-encoder variants do a good job of capturing the local manifold structure of theâ€¦ (More)

- Salah Rifai, Yann Dauphin, Pascal Vincent, Yoshua Bengio
- ICML
- 2012

The contractive auto-encoder learns a representation of the input data that captures the local manifold structure around each data point, through the leading singular vectors of the Jacobian of theâ€¦ (More)

- Salah Rifai, Xavier Glorot, Yoshua Bengio, Pascal Vincent
- ArXiv
- 2011

Regularization is a well studied problem in the context of neural networks. It is usually used to improve the generalization performance when the number of input samples is relatively small orâ€¦ (More)