Publication Details

Estimation Distribution Algorithm for mixed continuous-discrete optimization problems

OČENÁŠEK Jiří and SCHWARZ Josef. Estimation Distribution Algorithm for mixed continuous-discrete optimization problems. In: Proceedings of the 2nd Euro-International Symposium on Computational Intelligence. Kosice: IOS Press, 2002, pp. 227-232. ISBN 1-58603-256-9.
Czech title
Algoritmus založený na pravděpodobnostních modelech pro smíšené spojitě-diskrétní optimalizační problémy
Type
conference paper
Language
english
Authors
Keywords

Estimation Distribution Algorithm, Bayesian Optimization Algorithm, Bayesian network, Gaussian network,  classification and regression tree model (CART).

Abstract

In recent few years expressive progress in the theory and practice of Estimation of Distribution Algorithms (EDAs) [1] has appeared, where the classical genetic recombination operators are replaced by probability estimation and stochastic sampling techniques. In this paper we identify some disadvantages of present probabilistic models used in EDAs and propose more general and efficient model for continuous optimization problems based on the decision trees. The new variant of EDA is capable to solve mixed continuous-discrete optimization problems.

Published
2002
Pages
227-232
Proceedings
Proceedings of the 2nd Euro-International Symposium on Computational Intelligence
Conference
2nd Euro-International Symposium on Computational Intelligence, Kosice, CZ
ISBN
1-58603-256-9
Publisher
IOS Press
Place
Kosice, SK
BibTeX
@INPROCEEDINGS{FITPUB6938,
   author = "Ji\v{r}\'{i} O\v{c}en\'{a}\v{s}ek and Josef Schwarz",
   title = "Estimation Distribution Algorithm for mixed continuous-discrete optimization problems",
   pages = "227--232",
   booktitle = "Proceedings of the 2nd Euro-International Symposium on Computational Intelligence",
   year = 2002,
   location = "Kosice, SK",
   publisher = "IOS Press",
   ISBN = "1-58603-256-9",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/6938"
}
Back to top