Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 1498))
Included in the following conference series:
-
184 Accesses
-
14 Citations
Abstract
Traditionally, selection in Evolutionary Algorithms operates global on the entire population. In nature we rarely find global mating pools and thus we introduce a more-or-less geographical isolation in which individuals may interact only with individuals in the immediate locality, the local overlapping neighborhoods.
This paper studies two classes of diffusion models for Evolution Strategies (ES) where the decision for survival as well as the parent choice is performed locally only. The classes differ in that we either allow both parents to be chosen randomly from the neighborhood or one parent is chosen to be the centre individual and the other one is chosen randomly from the neighborhood. We introduce a notation for the diffusion model ES, give a theoretical analysis and present results of a numerical study.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Unable to display preview. Download preview PDF.
Explore related subjects
Discover the latest articles, books and news in related subjects, suggested using machine learning.References
I. Rechenberg, Evolutionsstrategie — Optimierung technischer Systeme nach Prinzipien der biologischen Information, Frommann Verlag, Stuttgart (1973) in german
H.-P. Schwefel, Numerical Optimization of Computer Models, John Wiley & Sons (1981), english translation of the original edition by Birkhäuser, Basel (1977)
J. Holland, Adaptation in Natural and Artificial Systems, University of Michigan Press, Ann Arbor (1975)
B. Manderick, P. Spiessens, Fine-grained Parallel Genetic Algorithm, in Proc. of the 3rd Int. Conf. on Genetic Algorithms, Morgan Kaufmann (1989) 428–433
R. Collins, D. Jefferson, Selection in Massively Parallel Genetic Algorithms, in Proc. 4th Int. Conf. on Genetic Algorithms, Morgan Kaufmann (1991) 249–256
M. Gorges-Schleuter, ASPARAGOS An Asynchronous Parallel Genetic Optimization Strategy, in Proc. of the 3rd ICGA, Morgan Kaufmann (1989) 422–427
M. Gorges-Schleuter, Explicit Parallelism of GAs through Population Structures, Proc. of PPSN I, LNCS 496, Springer Verlag (1991) 150–159
M. Gorges-Schleuter, Genetic Algorithms and Population Structures, Doctoral dissertation, University of Dortmund (1991). Extended abstract in V. Plantamura et al (Eds.), Frontier Decision Support Concepts, Wiley, New York (1994) 261–319
J. Sprave, Linear neighborhood Evolution Strategy, Conf. on Evolutionary Programming (1994); Software Package LICE-1.02, both via http://ls11-www.informatik.uni-dortmund.de/people/joe
H.-P. Schwefel, G. Rudolph, Contemporary Evolution Strategies, Third Int. Conf. on Artificial Life, LNCS 929, Springer Verlag, Berlin (1995) 893–907
D. Goldberg, K. Deb, A comparative analysis of selection schemes used in genetic algorithms, in Foundations of Genetic Algorithms, Morgan Kaufmann (1991) 69–93
M. Gorges-Schleuter, On Global and Local Selection in Evolution Strategies, submitted to FOGA 5, Leiden (1998)
Th. Bäck, Evolutionary Algorithms in Theory and Practice, Oxford University Press, New York (1995)
Th. Bäck, GENEsYs 1.0, ftp://lumpi.informatik.uni-dortmund.de/pub/GA
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gorges-Schleuter, M. (1998). A comparative study of global and local selection in evolution strategies. In: Eiben, A.E., Bäck, T., Schoenauer, M., Schwefel, HP. (eds) Parallel Problem Solving from Nature — PPSN V. PPSN 1998. Lecture Notes in Computer Science, vol 1498. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0056879
Download citation
DOI: https://doi.org/10.1007/BFb0056879
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65078-2
Online ISBN: 978-3-540-49672-4
eBook Packages: Springer Book Archive
Share this paper
Anyone you share the following link with will be able to read this content:
Sorry, a shareable link is not currently available for this article.
Provided by the Springer Nature SharedIt content-sharing initiative
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.