Comparative investigation of various evolutionary and memetic algorithms

Krisztián Balázs, János Botzheim, L. Kóczy

Research output: Chapter in Book/Report/Conference proceedingChapter

17 Citations (Scopus)

Abstract

Optimization methods known from the literature include gradient techniques and evolutionary algorithms. The main idea of gradient methods is to calculate the gradient of the objective function at the actual point and then to step towards better values according to this value. Evolutionary algorithms imitate a simplified abstract model of evolution observed in nature. Memetic algorithms traditionally combine evolutionary and gradient techniques to exploit the advantages of both methods. Our current research aims to discover the properties, especially the efficiency (i.e. the speed of convergence) of particular evolutionary and memetic algorithms. For this purpose the techniques are compared on several numerical optimization benchmark functions and on machine learning problems.

Original languageEnglish
Title of host publicationStudies in Computational Intelligence
Pages129-140
Number of pages12
Volume313
DOIs
Publication statusPublished - 2010

Publication series

NameStudies in Computational Intelligence
Volume313
ISSN (Print)1860949X

Fingerprint

Evolutionary algorithms
Gradient methods
Learning systems

Keywords

  • evolutionary algorithms
  • fuzzy rule-based learning
  • memetic algorithms

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Balázs, K., Botzheim, J., & Kóczy, L. (2010). Comparative investigation of various evolutionary and memetic algorithms. In Studies in Computational Intelligence (Vol. 313, pp. 129-140). (Studies in Computational Intelligence; Vol. 313). https://doi.org/10.1007/978-3-642-15220-7_11

Comparative investigation of various evolutionary and memetic algorithms. / Balázs, Krisztián; Botzheim, János; Kóczy, L.

Studies in Computational Intelligence. Vol. 313 2010. p. 129-140 (Studies in Computational Intelligence; Vol. 313).

Research output: Chapter in Book/Report/Conference proceedingChapter

Balázs, K, Botzheim, J & Kóczy, L 2010, Comparative investigation of various evolutionary and memetic algorithms. in Studies in Computational Intelligence. vol. 313, Studies in Computational Intelligence, vol. 313, pp. 129-140. https://doi.org/10.1007/978-3-642-15220-7_11
Balázs K, Botzheim J, Kóczy L. Comparative investigation of various evolutionary and memetic algorithms. In Studies in Computational Intelligence. Vol. 313. 2010. p. 129-140. (Studies in Computational Intelligence). https://doi.org/10.1007/978-3-642-15220-7_11
Balázs, Krisztián ; Botzheim, János ; Kóczy, L. / Comparative investigation of various evolutionary and memetic algorithms. Studies in Computational Intelligence. Vol. 313 2010. pp. 129-140 (Studies in Computational Intelligence).
@inbook{8ff172da551340e2ad551d7abeb95988,
title = "Comparative investigation of various evolutionary and memetic algorithms",
abstract = "Optimization methods known from the literature include gradient techniques and evolutionary algorithms. The main idea of gradient methods is to calculate the gradient of the objective function at the actual point and then to step towards better values according to this value. Evolutionary algorithms imitate a simplified abstract model of evolution observed in nature. Memetic algorithms traditionally combine evolutionary and gradient techniques to exploit the advantages of both methods. Our current research aims to discover the properties, especially the efficiency (i.e. the speed of convergence) of particular evolutionary and memetic algorithms. For this purpose the techniques are compared on several numerical optimization benchmark functions and on machine learning problems.",
keywords = "evolutionary algorithms, fuzzy rule-based learning, memetic algorithms",
author = "Kriszti{\'a}n Bal{\'a}zs and J{\'a}nos Botzheim and L. K{\'o}czy",
year = "2010",
doi = "10.1007/978-3-642-15220-7_11",
language = "English",
isbn = "9783642152191",
volume = "313",
series = "Studies in Computational Intelligence",
pages = "129--140",
booktitle = "Studies in Computational Intelligence",

}

TY - CHAP

T1 - Comparative investigation of various evolutionary and memetic algorithms

AU - Balázs, Krisztián

AU - Botzheim, János

AU - Kóczy, L.

PY - 2010

Y1 - 2010

N2 - Optimization methods known from the literature include gradient techniques and evolutionary algorithms. The main idea of gradient methods is to calculate the gradient of the objective function at the actual point and then to step towards better values according to this value. Evolutionary algorithms imitate a simplified abstract model of evolution observed in nature. Memetic algorithms traditionally combine evolutionary and gradient techniques to exploit the advantages of both methods. Our current research aims to discover the properties, especially the efficiency (i.e. the speed of convergence) of particular evolutionary and memetic algorithms. For this purpose the techniques are compared on several numerical optimization benchmark functions and on machine learning problems.

AB - Optimization methods known from the literature include gradient techniques and evolutionary algorithms. The main idea of gradient methods is to calculate the gradient of the objective function at the actual point and then to step towards better values according to this value. Evolutionary algorithms imitate a simplified abstract model of evolution observed in nature. Memetic algorithms traditionally combine evolutionary and gradient techniques to exploit the advantages of both methods. Our current research aims to discover the properties, especially the efficiency (i.e. the speed of convergence) of particular evolutionary and memetic algorithms. For this purpose the techniques are compared on several numerical optimization benchmark functions and on machine learning problems.

KW - evolutionary algorithms

KW - fuzzy rule-based learning

KW - memetic algorithms

UR - http://www.scopus.com/inward/record.url?scp=78049262630&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78049262630&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-15220-7_11

DO - 10.1007/978-3-642-15220-7_11

M3 - Chapter

AN - SCOPUS:78049262630

SN - 9783642152191

VL - 313

T3 - Studies in Computational Intelligence

SP - 129

EP - 140

BT - Studies in Computational Intelligence

ER -