DMCA
Linkage Learning via Probabilistic Modeling in the ECGA (1999)
| Citations: | 232 - 4 self |
BibTeX
@TECHREPORT{Harik99linkagelearning,
author = {Georges Harik and Georges Harik},
title = {Linkage Learning via Probabilistic Modeling in the ECGA},
institution = {},
year = {1999}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
The goal of linkage learning, or building block identification, is the creation of a more effective genetic algorithm (GA). This paper explores the relationship between the linkage-learning problem and that of learning probability distributions over multi-variate spaces. Herein, it is argued that these problems are equivalent. Using a simple but effective approach to learning distributions, and by implication linkage, this paper reveals the existence of GA-like algorithms that are potentially orders of magnitude faster and more accurate than the simple GA. I. Introduction Linkage learning in genetic algorithms (GAs) is the identification of building blocks to be conserved under crossover. Theoretical studies have shown that if an effective linkage-learning GA were developed, it would hold significant advantages over the simple GA (2). Therefore, the task of developing such an algorithm has drawn significant attention. Past approaches to developing such an algorithm have focused on ev...
Keyphrases
probabilistic modeling simple ga theoretical study introduction linkage learning past approach linkage-learning problem multi-variate space genetic algorithm effective approach probability distribution building block identification ga-like algorithm significant attention implication linkage effective linkage-learning ga significant advantage building block effective genetic algorithm linkage learning
