Using multiple populations of memetic algorithms for fuzzy rule-base optimization

Zsolt Dányádi, Krisztián Balázs, L. Kóczy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Evolutionary algorithms are an important branch of soft computing, being able to provide approximate solutions to problems in a reasonable amount of time. The underlying principle can be realized in an almost unlimited number of ways. This paper presents four main variants of evolutionary algorithms, and a method of running them in a topology consisting of multiple populations. The resources given to each population and migration are altered dynamically throughout the test, based on the effectiveness they show. Along with evolutionary methods, the solutions are also adjusted by gradient-based numerical optimization, in our case the Levenberg-Marquardt algorithm. These steps are added to the evolutionary processes as an extension, resulting in what are called memetic algorithms. The specific application for these methods here is optimizing fuzzy rule-bases, thereby making inference systems better at emulating a desired behavior, such as modeling a certain objective function.

Original languageEnglish
Title of host publication11th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2010 - Proceedings
Pages113-118
Number of pages6
DOIs
Publication statusPublished - 2010
Event11th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2010 - Budapest, Hungary
Duration: Nov 18 2010Nov 20 2010

Other

Other11th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2010
CountryHungary
CityBudapest
Period11/18/1011/20/10

Fingerprint

Fuzzy rules
Evolutionary algorithms
Soft computing
Topology

ASJC Scopus subject areas

  • Artificial Intelligence
  • Information Systems

Cite this

Dányádi, Z., Balázs, K., & Kóczy, L. (2010). Using multiple populations of memetic algorithms for fuzzy rule-base optimization. In 11th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2010 - Proceedings (pp. 113-118). [5672264] https://doi.org/10.1109/CINTI.2010.5672264

Using multiple populations of memetic algorithms for fuzzy rule-base optimization. / Dányádi, Zsolt; Balázs, Krisztián; Kóczy, L.

11th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2010 - Proceedings. 2010. p. 113-118 5672264.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Dányádi, Z, Balázs, K & Kóczy, L 2010, Using multiple populations of memetic algorithms for fuzzy rule-base optimization. in 11th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2010 - Proceedings., 5672264, pp. 113-118, 11th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2010, Budapest, Hungary, 11/18/10. https://doi.org/10.1109/CINTI.2010.5672264
Dányádi Z, Balázs K, Kóczy L. Using multiple populations of memetic algorithms for fuzzy rule-base optimization. In 11th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2010 - Proceedings. 2010. p. 113-118. 5672264 https://doi.org/10.1109/CINTI.2010.5672264
Dányádi, Zsolt ; Balázs, Krisztián ; Kóczy, L. / Using multiple populations of memetic algorithms for fuzzy rule-base optimization. 11th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2010 - Proceedings. 2010. pp. 113-118
@inproceedings{5d77332f7813434680ba6608c1698eb0,
title = "Using multiple populations of memetic algorithms for fuzzy rule-base optimization",
abstract = "Evolutionary algorithms are an important branch of soft computing, being able to provide approximate solutions to problems in a reasonable amount of time. The underlying principle can be realized in an almost unlimited number of ways. This paper presents four main variants of evolutionary algorithms, and a method of running them in a topology consisting of multiple populations. The resources given to each population and migration are altered dynamically throughout the test, based on the effectiveness they show. Along with evolutionary methods, the solutions are also adjusted by gradient-based numerical optimization, in our case the Levenberg-Marquardt algorithm. These steps are added to the evolutionary processes as an extension, resulting in what are called memetic algorithms. The specific application for these methods here is optimizing fuzzy rule-bases, thereby making inference systems better at emulating a desired behavior, such as modeling a certain objective function.",
author = "Zsolt D{\'a}ny{\'a}di and Kriszti{\'a}n Bal{\'a}zs and L. K{\'o}czy",
year = "2010",
doi = "10.1109/CINTI.2010.5672264",
language = "English",
isbn = "9781424492800",
pages = "113--118",
booktitle = "11th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2010 - Proceedings",

}

TY - GEN

T1 - Using multiple populations of memetic algorithms for fuzzy rule-base optimization

AU - Dányádi, Zsolt

AU - Balázs, Krisztián

AU - Kóczy, L.

PY - 2010

Y1 - 2010

N2 - Evolutionary algorithms are an important branch of soft computing, being able to provide approximate solutions to problems in a reasonable amount of time. The underlying principle can be realized in an almost unlimited number of ways. This paper presents four main variants of evolutionary algorithms, and a method of running them in a topology consisting of multiple populations. The resources given to each population and migration are altered dynamically throughout the test, based on the effectiveness they show. Along with evolutionary methods, the solutions are also adjusted by gradient-based numerical optimization, in our case the Levenberg-Marquardt algorithm. These steps are added to the evolutionary processes as an extension, resulting in what are called memetic algorithms. The specific application for these methods here is optimizing fuzzy rule-bases, thereby making inference systems better at emulating a desired behavior, such as modeling a certain objective function.

AB - Evolutionary algorithms are an important branch of soft computing, being able to provide approximate solutions to problems in a reasonable amount of time. The underlying principle can be realized in an almost unlimited number of ways. This paper presents four main variants of evolutionary algorithms, and a method of running them in a topology consisting of multiple populations. The resources given to each population and migration are altered dynamically throughout the test, based on the effectiveness they show. Along with evolutionary methods, the solutions are also adjusted by gradient-based numerical optimization, in our case the Levenberg-Marquardt algorithm. These steps are added to the evolutionary processes as an extension, resulting in what are called memetic algorithms. The specific application for these methods here is optimizing fuzzy rule-bases, thereby making inference systems better at emulating a desired behavior, such as modeling a certain objective function.

UR - http://www.scopus.com/inward/record.url?scp=78651475812&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78651475812&partnerID=8YFLogxK

U2 - 10.1109/CINTI.2010.5672264

DO - 10.1109/CINTI.2010.5672264

M3 - Conference contribution

AN - SCOPUS:78651475812

SN - 9781424492800

SP - 113

EP - 118

BT - 11th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2010 - Proceedings

ER -