A Canonical Genetic Algorithm Based Approach to Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.4340

  author =       "F. Oppacher and M. Wineberg",
  title =        "A Canonical Genetic Algorithm Based Approach to
                 Genetic Programming",
  booktitle =    "Artificial Neural Nets and Genetic Algorithms:
                 Proceedings of the International Conference,
  year =         "1997",
  editor =       "George D. Smith and Nigel C. Steele and 
                 Rudolf F. Albrecht",
  pages =        "401--404",
  address =      "University of East Anglia, Norwich, UK",
  publisher =    "Springer-Verlag",
  note =         "published in 1998",
  keywords =     "genetic algorithms, genetic programming",
  ISBN =         "3-211-83087-1",
  DOI =          "doi:10.1007/978-3-7091-6492-1_88",
  abstract =     "This paper studies genetic programming (GP) and its
                 relation to the genetic algorithm (GA). Since the
                 programs used as chromosomes by GP are non-homologous,
                 GP uses a different crossover operator than GA. Thus,
                 by modifying the GA, GP loses the theoretical
                 foundations which have been developed for GA. This
                 paper describes an algorithm (called EPI for
                 evolutionary program induction) that stays within the
                 canonical GA paradigm yet breeds programs in a similar
                 manner to GP. EPI has been tested on three problems
                 whose behaviour under GP is known; EPI performed
                 identically to GP over this test suite. The success of
                 the implementation shows that the special crossover
                 used in GP is not necessary to solve program induction
                 using a GA.",
  notes =        "http://www.sys.uea.ac.uk/Research/ResGroups/MAG/ICANNGA97/papers_frame.html",

Genetic Programming entries for Franz Oppacher Mark Wineberg