Recently, there has been considerable interest in employing unsupervised learning methods as feature extractors for supervised learning tasks such as classification. The literature shows that methods based on this approach have proved to be competitive with established state-of-the-art machine learning strategies. One important recent advance was the discovery by (Hinton, Osindero, & Teh, 2006)...

This short paper describes a simple coding technique, Sparse Sequential Dirichlet Coding, for multi-alphabet memoryless sources. It is appropriate in situations where only a small, unknown subset of the possible alphabet symbols can be expected to occur in any particular data sequence. We provide a competitive analysis which shows that the performance of Sparse Sequential Dirichlet Coding will ...

A combination of the sparse coding and transfer learning techniques was shown to be accurate and robust in classification tasks where training and testing objects have a shared feature space but are sampled from different underlying distributions, i.e., belong to different domains. The key assumption in such case is that in spite of the domain disparity, samples from different domains share som...

3

In recent years, the application of sparse coding techniques has led to frameworks that match or set the state-of-the-art in object recognition tasks. Despite such success, applying sparse coding to vision tasks presents unique challenges and many papers addressing these concerns appear in top conferences annually. This paper acts as an introduction to the subject of sparse coding, identifies t...

Sparse coding as applied to natural image patches learns Gabor-like components that resemble those found in the lower areas of the visual cortex. This biological motivation for sparse coding would also suggest that the learned receptive field elements be organized spatially by their response properties. However, the factorized prior in the original sparse coding model does not enforce this. We ...

Sparse coding is a proven principle for learning compact representations of images. However, sparse coding by itself often leads to very redundant dictionaries. With images, this often takes the form of similar edge detectors which are replicated many times at various positions, scales and orientations. An immediate consequence of this observation is that the estimation of the dictionary compon...

Inspired by the great success of sparse coding for vector valued data, our goal is to represent symmetric positive definite (SPD) data matrices as sparse linear combinations of atoms from a dictionary, where each atom itself is an SPD matrix. Since SPD matrices follow a non-Euclidean (in fact a Riemannian) geometry, existing sparse coding techniques for Euclidean data cannot be directly extende...

In compressed sensing, we wish to reconstruct a sparse signal x from observed data y. In sparse coding, on the other hand, we wish to find a representation of an observed signal y as a sparse linear combination, with coefficients x, of elements from an overcomplete dictionary. While many algorithms are competitive at both problems when x is very sparse, it can be challenging to recover x when i...