The convergence analysis and specification of the Population-Based Incremental Learning algorithm

In this paper, we investigate the global convergence properties in probability of the Population-Based Incremental Learning (PBIL) algorithm when the initial configuration p ( 0 ) is fixed and the learning rate α is close to zero. The convergence in probability of PBIL is confirmed by the experiment...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Neurocomputing (Amsterdam) Jg. 74; H. 11; S. 1868 - 1873
Hauptverfasser: Li, Helong, Kwong, Sam, Hong, Yi
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 01.05.2011
Schlagworte:
Convergence
Global optimum
Population-Based Incremental Learning (PBIL)
Global optimum
Population-Based Incremental Learning (PBIL)
Convergence
ISSN:0925-2312, 1872-8286
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this paper, we investigate the global convergence properties in probability of the Population-Based Incremental Learning (PBIL) algorithm when the initial configuration p ( 0 ) is fixed and the learning rate α is close to zero. The convergence in probability of PBIL is confirmed by the experimental results. This paper presents a meaningful discussion on how to establish a unified convergence theory of PBIL that is not affected by the population and the selected individuals.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2010.06.032