HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Alert me to new issues of the journal Download to citation manager Google Scholar Articles by Rozell, C. J. Articles by Olshausen, B. A. PubMed Articles by Rozell, C. J. Articles by Olshausen, B. A.

Sparse Coding via Thresholding and Local Competition in Neural Circuits

crozell{at}gatech.edu Department of Electrical and Computer Engineering, Rice University, Houston, TX 77251-1892, U.S.A.

Don H. Johnson

dhj{at}rice.edu Department of Electrical and Computer Engineering, Rice University, Houston, TX 77251-1892, U.S.A.

Richard G. Baraniuk

richb{at}rice.edu Department of Electrical and Computer Engineering, Rice University, Houston, TX 77251-1892, U.S.A.

Bruno A. Olshausen

baolshausen{at}berkeley.edu Helen Wills Neuroscience Institute and School of Optometry, University of California, Berkeley, Berkeley, CA 94720-3192, U.S.A.

While evidence indicates that neural systems may be employing sparse approximations to represent sensed stimuli, the mechanisms underlying this ability are not understood. We describe a locally competitive algorithm (LCA) that solves a collection of sparse coding principles minimizing a weighted combination of mean-squared error and a coefficient cost function. LCAs are designed to be implemented in a dynamical system composed of many neuron-like elements operating in parallel. These algorithms use thresholding functions to induce local (usually one-way) inhibitory competitions between nodes to produce sparse representations. LCAs produce coefficients with sparsity levels comparable to the most popular centralized sparse coding algorithms while being readily suited for neural implementation. Additionally, LCA coefficients for video sequences demonstrate inertial properties that are both qualitatively and quantitatively more regular (i.e., smoother and more predictable) than the coefficients produced by greedy algorithms.