Sparse coding via thresholding and local competition in neural circuits

Christopher J. Rozell, Don H. Johnson, Richard G. Baraniuk, Bruno A. Olshausen

Research output: Contribution to journalArticlepeer-review

268 Scopus citations


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.

Original languageEnglish (US)
Pages (from-to)2526-2563
Number of pages38
JournalNeural Computation
Issue number10
StatePublished - Oct 1 2008

ASJC Scopus subject areas

  • Arts and Humanities (miscellaneous)
  • Cognitive Neuroscience


Dive into the research topics of 'Sparse coding via thresholding and local competition in neural circuits'. Together they form a unique fingerprint.

Cite this