Problem Difficulty and Code Growth in Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.4221

  author =       "Steven Gustafson and Aniko Ekart and Edmund Burke and 
                 Graham Kendall",
  title =        "Problem Difficulty and Code Growth in Genetic
  journal =      "Genetic Programming and Evolvable Machines",
  year =         "2004",
  volume =       "5",
  number =       "3",
  pages =        "271--290",
  month =        sep,
  keywords =     "genetic algorithms, genetic programming, population
                 diversity, code growth, problem difficulty",
  ISSN =         "1389-2576",
  URL =          "",
  DOI =          "doi:10.1023/B:GENP.0000030194.98244.e3",
  size =         "20 pages",
  abstract =     "the relationship between code growth and problem
                 difficulty in genetic programming. The symbolic
                 regression problem domain is used to investigate this
                 relationship using two different types of increased
                 instance difficulty. Results are supported by a
                 simplified model of genetic programming and show that
                 increased difficulty induces higher selection pressure
                 and less genetic diversity, which both contribute
                 toward an increased rate of code growth.",
  notes =        "Article ID: 5272970",

Genetic Programming entries for Steven M Gustafson Aniko Ekart Edmund Burke Graham Kendall