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 …

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 …

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 …

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 …

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 …

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 …

Recent theoretical and empirical work in statistical machine learning has demonstrated the
potential of learning algorithms for deep architectures, ie, function classes obtained by …

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 …

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 …

Classifying scenes (eg into “street”, “home” or “leisure”) is an important but complicated task
nowadays, because images come with variability, ambiguity, and a wide range of …