Parallel evolutionary algorithms on graphics processing unit   [PEA] [EA] [GPU]

by

Wong, M.-L., Wong, T.-T. and Fok, K.-L.

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 2005 IEEE Congress on Evolutionary Computation (Conference proceedings), 2005, p. 2286-2293
Keywords:genetic algorithms, GPU
Abstract:
Evolutionary algorithms (EAs) [EA] are effective and robust methods for solving many practical problems such as feature selection, electrical circuit synthesis, [FS] [CS] and data mining. [DM] However, they may execute for a long time for some difficult problems, because several fitness evaluations must be performed. A promising approach to overcome this limitation is to parallelise these algorithms. In this paper, we propose to implement a parallel EA on consumer-level graphics cards. [GC] We perform experiments to compare our parallel EA with an ordinary EA and demonstrate that the former is much more effective than the latter. Since consumer-level graphics cards [GC] are available in ubiquitous personal computers and these computers are easy to use and manage, more people are able to use our parallel algorithm [PA] to solve their problems encountered in real-world applications [RA]
URL(s):Other format

Review item:

Mark as doublet (will be reviewed)

Print entry



BibTex:
@InProceedings{Man-Leung:Pea:cec2005,
  author =       "Man-Leung Wong and Tien-Tsin Wong and Ka-Ling Fok",
  title =        "Parallel evolutionary algorithms on graphics
                 processing unit",
  booktitle =    "Proceedings of the 2005 IEEE Congress on Evolutionary
                 Computation",
  year =         "2005",
  editor =       "David Corne and Zbigniew Michalewicz and Bob McKay and
                 Gusz Eiben and David Fogel and Carlos Fonseca and
                 Garrison Greenwood and Gunther Raidl and Kay Chen Tan
                 and Ali Zalzala",
  pages =        "2286--2293",
  address =      "Edinburgh, Scotland, UK",
  month =        "2-5 " # sep,
  publisher =    "IEEE Press",
  volume =       "3",
  keywords =     "genetic algorithms, GPU",
  ISBN =         "0-7803-9363-5",
  URL =          "http://ieeexplore.ieee.org/servlet/opac?punumber=10417&isvol=3",
  URL =          "http://ieeexplore.ieee.org/servlet/opac?punumber=10417",
  doi =          "doi:10.1109/CEC.2005.1554979",
  size =         "8 pages",
  abstract =     "Evolutionary algorithms (EAs) are effective and robust
                 methods for solving many practical problems such as
                 feature selection, electrical circuit synthesis, and
                 data mining. However, they may execute for a long time
                 for some difficult problems, because several fitness
                 evaluations must be performed. A promising approach to
                 overcome this limitation is to parallelise these
                 algorithms. In this paper, we propose to implement a
                 parallel EA on consumer-level graphics cards. We
                 perform experiments to compare our parallel EA with an
                 ordinary EA and demonstrate that the former is much
                 more effective than the latter. Since consumer-level
                 graphics cards are available in ubiquitous personal
                 computers and these computers are easy to use and
                 manage, more people are able to use our parallel
                 algorithm to solve their problems encountered in
                 real-world applications",
}