Neurocontroller analysis via evolutionary network minimization

Zohar Ganon, Alon Keinan, Eytan Ruppin*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

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.

Original languageEnglish
Pages (from-to)435-448
Number of pages14
JournalArtificial Life
Volume12
Issue number3
DOIs
StatePublished - 2006

Keywords

  • Evolutionary agents
  • Evolutionary algorithms
  • Network minimization
  • Neurocontroller analysis
  • Synaptic pruning

Fingerprint

Dive into the research topics of 'Neurocontroller analysis via evolutionary network minimization'. Together they form a unique fingerprint.

Cite this