Pre-integration lateral inhibition enhances unsupervised learning

Research output: Contribution to journalArticlepeer-review

45 Citations (Scopus)
201 Downloads (Pure)

Abstract

A large and influential class of neural network architectures uses postintegration lateral inhibition as a mechanism for competition. We argue that these algorithms are computationally deficient in that they fail to generate, or learn, appropriate perceptual representations under certain circumstances. An alternative neural network architecture is presented here in which nodes compete for the right to receive inputs rather than for the right to generate outputs. This form of competition, implemented through preintegration lateral inhibition, does provide appropriate coding properties and can be used to learn such representations efficiently. Furthermore, this architecture is consistent with both neuroanatomical and neurophysiological data. We thus argue that preintegration lateral inhibition has computational advantages over conventional neural network architectures while remaining equally biologically plausible.
Original languageEnglish
Article numberN/A
Pages (from-to)2157 - 2179
Number of pages23
JournalNeural Computation
Volume14
Issue number9
DOIs
Publication statusPublished - Sept 2002

Fingerprint

Dive into the research topics of 'Pre-integration lateral inhibition enhances unsupervised learning'. Together they form a unique fingerprint.

Cite this