mk:ea99

Summary

Scout Algorithms and Genetic Algorithms: A Comparative Study. Fabio Abbattista, Valeria Carofiglio and Mario Köppen. In Proceedings Evolution Artificielle 1999, November 1999, Dunkerque, France, 1999.

Abstract

This paper gives a comparative study of the recently proposed Scout algorithm and the standard genetic algorithm (SGA). Although these evolutionary algorithms are differently configurated and use different evolutionary operators, essential similarities of both algorithms can be pointed out. These similarities can be found at three levels, theoretically and empirically: it is discussed that the Scout algorithm fulfills Holland's paradigm of admissible detector configuration; from the definition of the Scout algorithm and its variants, the Schemata theorem for Scout algorithms is justified; and experimental evidence is given, that Scout algorithm's performance reflects SGA's performance for SGA hard problems (Tanese functions) and SGA deceptive problems (Royal Road Functions). Thus, Scout algorithms and SGA are both unique instances of a broader, yet unknown class of evolutionary algorithms. The most important advantage of Scout algorithms is the fashioning of their update rules. This update rule has no counterpart in the SGA.

Bibtex entry

@INPROCEEDINGS { mk:ea99,
    ABSTRACT = { This paper gives a comparative study of the recently proposed Scout algorithm and the standard genetic algorithm (SGA). Although these evolutionary algorithms are differently configurated and use different evolutionary operators, essential similarities of both algorithms can be pointed out. These similarities can be found at three levels, theoretically and empirically: it is discussed that the Scout algorithm fulfills Holland's paradigm of admissible detector configuration; from the definition of the Scout algorithm and its variants, the Schemata theorem for Scout algorithms is justified; and experimental evidence is given, that Scout algorithm's performance reflects SGA's performance for SGA hard problems (Tanese functions) and SGA deceptive problems (Royal Road Functions). Thus, Scout algorithms and SGA are both unique instances of a broader, yet unknown class of evolutionary algorithms. The most important advantage of Scout algorithms is the fashioning of their update rules. This update rule has no counterpart in the SGA. },
    AUTHOR = { Fabio Abbattista and Valeria Carofiglio and Mario Köppen },
    BOOKTITLE = { Proceedings Evolution Artificielle 1999, November 1999, Dunkerque, France },
    MODIFIED = { 2008-02-28 16:26:16 +0900 },
    HASABSTRACT = { Yes },
    PDF = { ea99.pdf },
    TITLE = { Scout Algorithms and Genetic Algorithms: A Comparative Study },
    YEAR = { 1999 },
}

On small computer displays, you can hide this right bar by using the 'Hide' button above.

News

Next conferences COMPSAC 2014 (Vasteras, Sweden, July 2014), INCoS-2014 (Salerno, Italy, September 2014).

New edited book "Soft Computing in Industrial Applications", V. Snasel, P. Kroemer, M. Koeppen, G. Schaefer, Springer AISC 223, July 2013.