Inproceedings1460: Unterschied zwischen den Versionen
K (Added from ontology) |
Uri (Diskussion | Beiträge) |
||
Zeile 25: | Zeile 25: | ||
|ISBN=978-1-59593-697-4 | |ISBN=978-1-59593-697-4 | ||
|VG Wort-Seiten=27 | |VG Wort-Seiten=27 | ||
− | + | |Forschungsgruppe=Effiziente Algorithmen | |
− | |||
− | |Forschungsgruppe= | ||
}} | }} | ||
{{Forschungsgebiet Auswahl | {{Forschungsgebiet Auswahl | ||
|Forschungsgebiet=Evolutionäre Algorithmen | |Forschungsgebiet=Evolutionäre Algorithmen | ||
}} | }} |
Aktuelle Version vom 24. September 2009, 21:41 Uhr
Addressing sampling errors and diversity loss in UMDA
Addressing sampling errors and diversity loss in UMDA
Published: 2007
Herausgeber: D. Thierens et al.
Buchtitel: Proceedings of the 2007 Genetic and Evolutionary Computation Conference
Seiten: 508-515
Verlag: ACM
Referierte Veröffentlichung
BibTeX
Kurzfassung
Estimation of distribution algorithms replace the typical crossover and mutation operators by constructing a probabilistic model and generating offspring according to this model. In previous studies, it has been shown that this generally leads to diversity loss due to sampling errors. In this paper, for the case of the simple Univariate Marginal Distribution Algorithm (UMDA), we propose and test several methods for counteracting diversity loss. The diversity loss can come in two phases: sampling from the probability model (offspring generation) and selection. We show that it is possible to completely remove the sampling error during offspring generation.
Furthermore, we examine several plausible model construction variants which counteract diversity loss during selection and demonstrate that these update rules work better than the standard update on a variety of simple test problems.
ISBN: 978-1-59593-697-4
VG Wort-Seiten: 27