Modeling large cortical networks with growing self-organizing maps

James A. Bednar, Amol Kelkar, Risto Miikkulainen

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

Self-organizing computational models with specific intracortical connections can explain many features of visual cortex. However, due to their computation and memory requirements, it is difficult to use such detailed models to study large-scale object segmentation and recognition. This paper describes GLISSOM, a method for scaling a small RF-LISSOM model network into a larger one during self-organization, dramatically reducing time and memory needs while obtaining equivalent results. With GLISSOM it should be possible to simulate all of human V1 at the single-column level using existing supercomputers. The scaling equations GLISSOM uses also allow comparison of biological maps and parameters between individuals and species with different brain region sizes.
Original languageEnglish
Pages (from-to)315-321
Number of pages6
JournalNeurocomputing
DOIs
Publication statusPublished - 1 Jun 2002

Keywords / Materials (for Non-textual outputs)

  • Self-organization
  • Cortical modeling
  • Vision
  • Orientation maps
  • Growing networks

Fingerprint

Dive into the research topics of 'Modeling large cortical networks with growing self-organizing maps'. Together they form a unique fingerprint.

Cite this