TBU Publications
Repository of TBU Publications

A review of methods for encoding neural network topologies in evolutionary computation

DSpace Repository

Show simple item record

dc.title A review of methods for encoding neural network topologies in evolutionary computation en
dc.contributor.author Fekiač, Jozef
dc.contributor.author Zelinka, Ivan
dc.contributor.author Burguillo, Juan Carlos
dc.relation.ispartof Proceedings - 25th European Conference on Modelling and Simulation, ECMS 2011
dc.identifier.isbn 978-0-9564944-2-9
dc.date.issued 2011
dc.citation.spage 410
dc.citation.epage 416
dc.event.title 25th European Conference on Modelling and Simulation, ECMS 2011
dc.event.location Krakow
utb.event.state-en Poland
utb.event.state-cs Polsko
dc.event.sdate 2011-06-07
dc.event.edate 2011-06-10
dc.type conferenceObject
dc.language.iso en
dc.identifier.doi 10.7148/2011-0410-0416
dc.relation.uri http://www.scs-europe.net/dlib/2011/2011-0410.htm
dc.relation.uri http://www.scs-europe.net/conf/ecms2011/ecms2011%20accepted%20papers/is_ECMS_0081.pdf
dc.subject Artificial neural network en
dc.subject Automata network en
dc.subject Evolutionary computation en
dc.subject Genetic algorithm en
dc.subject Genetic programming en
dc.subject Graph grammar en
dc.subject Network encoding en
dc.description.abstract This paper describes various methods used to encode artificial neural networks to chromosomes to be used in evolutionary computation. The target of this review is to cover the main techniques of network encoding and make it easier to choose one when implementing a custom evolutionary algorithm for finding the network topology. Most of the encoding methods are mentioned in the context of neural networks; however all of them could be generalized to automata networks or even oriented graphs. We present direct and indirect encoding methods, and given examples of their genotypes. We also describe the possibilities of applying genetic operators of mutation and crossover to genotypes encoded by these methods. Also, the dependencies of using special evolutionary algorithms with some of the encodings were considered. © ECMS. en
utb.faculty Faculty of Applied Informatics
dc.identifier.uri http://hdl.handle.net/10563/1004833
utb.identifier.obdid 43867531
utb.identifier.scopus 2-s2.0-84857697001
utb.identifier.wok 000392767500062
utb.source d-scopus
dc.date.accessioned 2015-06-04T12:55:42Z
dc.date.available 2015-06-04T12:55:42Z
dc.description.sponsorship Internal Grant Agency of Tomas Bata University [IGA/28/FAI/10/D]; European Regional Development Fund under the Project CEBIA-Tech [CZ.1.05/2.1.00/03.0089]
utb.contributor.internalauthor Fekiač, Jozef
Find Full text

Files in this item

Show simple item record