Neurocontroller analysis via evolutionary network minimization

TitleNeurocontroller analysis via evolutionary network minimization
Publication TypeJournal Article
Year of Publication2006
AuthorsGanon Z, Keinan A, Ruppin E
JournalArtif. Life
Volume12
Pagination435–448
ISSN1064-5462
KeywordsAlgorithms, Behavior, Biological Evolution, Memory, Models, Neural Networks (Computer), Theoretical
Abstract

This study presents a new evolutionary network minimization ({ENM)} algorithm. Neurocontroller minimization is beneficial for finding small parsimonious networks that permit a better understanding of their workings. The {ENM} algorithm is specifically geared to an evolutionary agents setup, as it does not require any explicit supervised training error, and is very easily incorporated in current evolutionary algorithms. {ENM} is based on a standard genetic algorithm with an additional step during reproduction in which synaptic connections are irreversibly eliminated. It receives as input a successfully evolved neurocontroller and aims to output a pruned neurocontroller, while maintaining the original fitness level. The small neurocontrollers produced by {ENM} provide upper bounds on the neurocontroller size needed to perform a given task successfully, and can provide for more effcient hardware implementations.

URLhttp://keinanlab.cb.bscb.cornell.edu/sites/default/files/papers/ganon_etal_2006_neurocontrolleranalysis_artificiallife.pdf
DOI10.1162/artl.2006.12.3.435