Evolutionary network minimization: Adaptive implicit pruning of successful agents

Zohar Ganon, Alon Keinan, Eytan Ruppin

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations


Neurocontroller minimization is beneficial for constructing small parsimonious networks that permit a better understanding of their workings. This paper presents a novel, Evolutionary Network Minimization (ENM) algorithm which is applied to fully recurrent neurocontrollers. ENM is a simple, standard genetic algorithm with an additional step in which small weights are irreversibly eliminated. ENM has a unique combination of features which distinguish it from previous evolutionary minimization algorithms: 1. An explicit penalty term is not added to the fitness function. 2. Minimization begins after functional neurocontrollers have been successfully evolved. 3. Successful minimization relies solely on the workings of a drift that removes unimportant weights and, importantly, on continuing adaptive modifications of the magnitudes of the remaining weights. Our results testify that ENM is successful in extensively minimizing recurrent evolved neurocontrollers while keeping their fitness intact and maintaining their principal functional characteristics.

Original languageEnglish
Title of host publicationAdvances in Artificial Life
EditorsWolfgang Banzhaf, Jens Ziegler, Thomas Christaller, Peter Dittrich, Jan T. Kim
PublisherSpringer Verlag
Number of pages9
ISBN (Print)3540200576, 9783540200574
StatePublished - 2003
Event7th European Conference on Artificial Life, ECAL 2003 - Dortmund, Germany
Duration: 14 Sep 200317 Sep 2003

Publication series

NameLecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
ISSN (Print)0302-9743


Conference7th European Conference on Artificial Life, ECAL 2003


Dive into the research topics of 'Evolutionary network minimization: Adaptive implicit pruning of successful agents'. Together they form a unique fingerprint.

Cite this