Salah Rifai

• Université de Montréal

Classifying scenes (e.g. into “street”, “home” or “leisure”) is an important but complicated task nowadays, because images come with variability, ambiguity, and a wide range of illumination or scale conditions. Standard approaches build an intermediate representation of the global image and learn classifiers on it. Recently, it has been proposed to...

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 emotion classification algorithm should be both robust to (1) remaining variations due to the pose of the face in the image after centering and alignment, (2)...

It has previously been hypothesized, and supported with some experimental evidence, that deeper representations, when well trained, tend to do a better job at disentangling the underlying factors of variation. We study the following related conjecture: better representations, in the sense of better disentangling, can be exploited to produce faster-...

Recent work suggests that some auto-encoder variants do a good job of capturing the local manifold structure of the unknown data generating density. This paper contributes to the mathematical understanding of this phenomenon and helps define better justified sampling algorithms for deep learning based on auto-encoder variants. We consider an MCMC w...

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 the transformation from input to representation. The corresponding singular values specify how much local variation is plausible in directions associated wi...

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 the norm of the Jacobian (analytically) and the Hessian (stochastically) of the encoder’s output with respect to its input, at the training points. While the...

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 achieve results that equal or surpass those attained by other regularized auto-encoders as well as denoising auto-encoders on a range of datasets. This penalty te...

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 or heavily contaminated with noise. The regularization of a parametric model can be achieved in different manners some of which are early stopping (Morgan and B...

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 achieve results that equal or surpass those attained by other regularized autoencoders as well as denoising auto-encoders on a range of datasets. This penalty ter...

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 composing multiple levels of representation. The hypothesis evaluated here is that intermediate levels of representation, because they can be shared across tasks and e...

We combine three important ideas present in previous work for building classi-fiers: the semi-supervised hypothesis (the input distribution contains information about the classifier), the unsupervised manifold hypothesis (data density concen-trates near low-dimensional manifolds), and the manifold hypothesis for classifi-cation (different classes c...

Learning good representations from a large set of unlabeled data is a particularly chal-lenging task. Recent work (see Bengio (2009) for a review) shows that training deep architectures is a good way to extract such representations, by extracting and disentan-gling gradually higher-level factors of variation characterizing the input distribution. I...

Recent theoretical and empirical work in statistical machine learning has demonstrated the importance of learning algorithms for deep architectures, i.e., function classes obtained by composing multiple non-linear transformations. Self-taught learning (exploiting unlabeled examples or examples from other distributions) has already been applied to d...