The goal of predictive sparse coding is to learn a representation of examples as sparse linear combinations of elements from a dictionary, such that a learned hypothesis linear in the new representation performs well on a predictive task. Predictive sparse coding has demonstrated impressive performance on a variety of supervised tasks, but its generalization properties have not been studied. We...

Sparse coding aims to model data vectors as sparse linear combinations of basis elements, but a majority related studies are restricted continuous without spatial or temporal structure. A new model-based (MSC) method is proposed provide an effective and flexible framework for learning features from different types: continuous, discrete, categorical, modeling types correlations: temporal. The sp...

Sparse coding has been proposed as a guiding principle in neural representations of sensory input, particularly in the visual system. Because sparse codes are defined as representations with low activity ratios—i.e., at any given time a small proportion of neurons are active—they are sometimes proposed as a means to help conserve metabolic costs. Although we accept that such metabolic costs pla...