title: Pattern-Generator-Driven Development in Self-Organizing Models
creator: Bednar, James A.
creator: Miikkulainen, Risto
subject: Computational Neuroscience
subject: Artificial Intelligence
subject: Complexity Theory
subject: Machine Learning
subject: Neural Nets
subject: Developmental Psychology
subject: Neural Modelling
subject: Neural Modelling
description: Self-organizing models develop realistic cortical structures when given approximations of the visual environment as input. Recently it has been proposed that internally generated input patterns, such as those found in the developing retina and in PGO waves during REM sleep, may have the same effect. Internal pattern generators would constitute an efficient way to specify, develop, and maintain functionally appropriate perceptual organization. They may help express complex structures from minimal genetic information, and retain this genetic structure within a highly plastic system. Simulations with the RF-LISSOM orientation map model indicate that such preorganization is possible, providing a computational framework for examining how genetic influences interact with visual experience.
publisher: Plenum, New York
contributor: Bower, James M.
date: 1998
type: Conference Paper
type: NonPeerReviewed
format: application/pdf
identifier: http://cogprints.org/140/3/bednar.cns97.pdf
identifier:   Bednar, James A. and Miikkulainen, Risto  (1998) Pattern-Generator-Driven Development in Self-Organizing Models.  [Conference Paper]     
relation: http://cogprints.org/140/