Multinational Evolutionary Algorithms   [EA]

by

Ursem, R., K.

Literature search on Evolutionary ComputationBBase ©1999-2013, Rasmus K. Ursem
     Home · Search · Adv. search · Authors · Login · Add entries   Webmaster
Note to authors: Please submit your bibliography and contact information - online papers are more frequently cited.

Info: Proceedings of the Congress of Evolutionary Computation (CEC-99) (Conference proceedings), 1999, p. 1633-1640
Keywords:search space division, multimodal, adaptive, optimization, selforganization, subpopulation, island model, finding local, global optimas
Abstract:
Since practical problems often are very complex with a large number of objectives it can be difficult or impossible to create an objective function expressing all the criterias of good solutions. Sometimes a simpler function can be used where local optimas could be both valid and interesting. Because evolutionary algorithms [EA] are population-based they have the best potential for finding more of the best solutions among the possible solutions. However, standard EAs often converge to one solution and leave therefore only this single option for a final human selection. So far at least two methods, sharing and tagging, have been proposed to solve the problem. This paper presents a new method for finding more quality solutions, not only global optimas [GO] but local as well. The method tries to adapt its search strategy to the problem by taking the topology of the fitness landscape [FL] into account. The idea is to use the topology of the fitness landscape to group [FL] the individuals into sub-populations each covering a part of the fitness landscape. [FL]
Notes:
CEC-99 - A joint meeting of the IEEE, Evolutionary Programming Society, Galesia, and the IEE.
URL(s):Postscript
(G)zipped postscript
PDF

Review item:

Mark as doublet (will be reviewed)

Print entry




BibTex:
@inproceedings (ursem:1999:MEA,
  author =	{Rasmus K. Ursem},
  title =	{Multinational Evolutionary Algorithms},
  booktitle =	{Proceedings of the Congress of Evolutionary Computation (CEC-99)},
  year =	{1999},
  editor = 	{Peter J. Angeline and Zbyszek Michalewicz and Marc Schoenauer and Xin Yao and Ali Zalzala},
  volume =	{3},
  pages = 	{1633--1640},
  address = 	{Mayflower Hotel, Washington D.C., USA},
  publisher_address = 	{445 Hoes Lane, P.O. Box 1331, Piscataway, NJ  08855-1331, USA},
  month = 	{6-9 July},
  organisation ={Congress on Evolutionary Computation, IEEE / Neural Networks Council, Evolutionary Programming Society, Galesia, IEE},
  publisher = 	{IEEE Press},
  note =	{},
  keywords =    {search space division, multimodal, adaptive, optimization, selforganization, subpopulation, island model, finding local and global optimas},
  ISBN =        {0-7803-5536-9 (softbound)},
  ISBN =        {0-7803-5537-7 (Microfiche)},
  url =         {http://www.evalife.dk/publications/multinational_CEC1999.ps.gz},
  size = 	{},
  abstract =	{Since practical problems often are very complex with a large number of objectives it can be difficult or impossible to create an objective function expressing all the criterias of good solutions. Sometimes a simpler function can be used where local optimas could be both valid and interesting. 
Because evolutionary algorithms are population-based they have the best potential for finding more of the best solutions among the possible solutions. However, standard EAs often converge to one solution and leave therefore only this single option for a final human selection. So far at least two methods, sharing and tagging, have been proposed to solve the problem.
This paper presents a new method for finding more quality solutions, not only global optimas but local as well. The method tries to adapt its search strategy to the problem by taking the topology of the fitness landscape into account. The idea is to use the topology of the fitness landscape to group the individuals into sub-populations each covering a part of the fitness landscape.},
  notes =	{CEC-99 - A joint meeting of the IEEE, Evolutionary Programming Society, Galesia, and the IEE.},
)