Neutrality and Self-Adaptation. Igel, C. & Toussaint, M. Natural Computing, 2(2):117–132, 2003.
Neutrality and Self-Adaptation [link]Paper  doi  abstract   bibtex   
Neutral genotype-phenotype mappings can be observed in natural evolution and are often used in evolutionary computation. In this article, important aspects of such encodings are analysed. First, it is shown that in the absence of external control neutrality allows a variation of the search distribution independent of phenotypic changes. In particular, neutrality is necessary for self-adaptation, which is used in a variety of algorithms from all main paradigms of evolutionary computation to increase efficiency. Second, the average number of fitness evaluations needed to find a desirable (e.g., optimally adapted) genotype depending on the number of desirable genotypes and the cardinality of the genotype space is derived. It turns out that this number increases only marginally when neutrality is added to an encoding presuming that the fraction of desirable genotypes stays constant and that the number of these genotypes is not too small.
@Article{Igel:2003:NC,
  author =       "Christian Igel and Marc Toussaint",
  title =        "Neutrality and Self-Adaptation",
  journal =      "Natural Computing",
  year =         "2003",
  volume =       "2",
  number =       "2",
  URL =          "http://ipsapp009.kluweronline.com/content/getfile/5030/5/1/abstract.htm",
  doi =          "doi:10.1023/A:1024906105255",
  pages =        "117--132",
  keywords =     "evolutionary computation, genotype-phenotype mapping,
                 neutrality, No-Free-Lunch theorem, redundancy,
                 self-adaptation, genetic programming",
  abstract =     "Neutral genotype-phenotype mappings can be observed in
                 natural evolution and are often used in evolutionary
                 computation. In this article, important aspects of such
                 encodings are analysed. First, it is shown that in the
                 absence of external control neutrality allows a
                 variation of the search distribution independent of
                 phenotypic changes. In particular, neutrality is
                 necessary for self-adaptation, which is used in a
                 variety of algorithms from all main paradigms of
                 evolutionary computation to increase efficiency.
                 Second, the average number of fitness evaluations
                 needed to find a desirable (e.g., optimally adapted)
                 genotype depending on the number of desirable genotypes
                 and the cardinality of the genotype space is derived.
                 It turns out that this number increases only marginally
                 when neutrality is added to an encoding presuming that
                 the fraction of desirable genotypes stays constant and
                 that the number of these genotypes is not too small.",
  notes =        "Article ID: 5126729",
}

Downloads: 0