Learning generalisation and localisation: Competition for stimulus type and receptive field

Michael William Oram, Peter Foldiak

Research output: Contribution to journalArticlepeer-review

11 Citations (Scopus)

Abstract

The evidence from neurophysiological recordings from the primate visual system suggests that sensory patterns are processed using units arranged in a hierarchical multi-layered network. Responses of these units show progressively increasing receptive field size combined with selectivity for increasing stimulus complexity at successively higher levels. It is argued that the rate of the increase in receptive field size is less than the maximum possible given the initial spread of neuronal projections that occurs during development. We show here that a competitive learning mechanism using a 'trace-Hebbian' learning rule [14] with a larger number of competing output units learns not only positional invariance for a given input feature but can also establish restricted receptive field sizes (i.e. less than the maximum size given the initial connections). Importantly the same stimulus selectivity was maintained throughout the receptive field. It is shown that this is accompanied by a relative increase in the spatial evenness of the representation of each detector type across position within the input array. The network properties were found to be robust and stable over a wide range of learning parameters. We suggest that such a competitive mechanism may help account for the reported properties of cells in the ventral stream of the primate visual system.

Original languageEnglish
Pages (from-to)297-321
Number of pages25
JournalNeurocomputing
Volume11
Issue number2-4
DOIs
Publication statusPublished - 1 Jun 1996

Keywords

  • vision
  • competitive learning
  • invariance
  • INFERIOR TEMPORAL CORTEX
  • CAT VISUAL-CORTEX
  • SHORT-TERM-MEMORY
  • CORTICAL MAP
  • INFEROTEMPORAL CORTEX
  • NEURONAL CORRELATE
  • SINGLE NEURONS
  • NERVE INJURY
  • MONKEYS
  • MODEL

Fingerprint

Dive into the research topics of 'Learning generalisation and localisation: Competition for stimulus type and receptive field'. Together they form a unique fingerprint.

Cite this