CGP visits the Santa Fe trail: effects of heuristics on GP

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

  author =       "Cezary Z. Janikow and Christopher J. Mann",
  title =        "CGP visits the Santa Fe trail: effects of heuristics
                 on GP",
  booktitle =    "{GECCO 2005}: Proceedings of the 2005 conference on
                 Genetic and evolutionary computation",
  year =         "2005",
  editor =       "Hans-Georg Beyer and Una-May O'Reilly and 
                 Dirk V. Arnold and Wolfgang Banzhaf and Christian Blum and 
                 Eric W. Bonabeau and Erick Cantu-Paz and 
                 Dipankar Dasgupta and Kalyanmoy Deb and James A. Foster and 
                 Edwin D. {de Jong} and Hod Lipson and Xavier Llora and 
                 Spiros Mancoridis and Martin Pelikan and Guenther R. Raidl and 
                 Terence Soule and Andy M. Tyrrell and 
                 Jean-Paul Watson and Eckart Zitzler",
  volume =       "2",
  ISBN =         "1-59593-010-8",
  pages =        "1697--1704",
  address =      "Washington DC, USA",
  URL =          "",
  DOI =          "doi:10.1145/1068009.1068293",
  publisher =    "ACM Press",
  publisher_address = "New York, NY, 10286-1405, USA",
  month =        "25-29 " # jun,
  organisation = "ACM SIGEVO (formerly ISGEC)",
  keywords =     "genetic algorithms, genetic programming, evolutionary
                 computation, design, experimentation, heuristics",
  abstract =     "GP uses trees to represent chromosomes. The user
                 defines the representation space by defining the set of
                 functions and terminals to label the nodes in the
                 trees, and GP searches the space. Previous research and
                 experimentation show that the choice of the
                 function/terminal set, choice of the initial
                 population, and some other explicit and implicit
                 {"}design{"} factors have great influence on both the
                 quality and the speed of the evolution. Such heuristics
                 are valuable simply because they improve GP's
                 performance, or because they enforce some desired
                 properties on the solutions. In this paper, we evaluate
                 the effect of heuristics on GP solving the Santa Fe
                 trail. We concentrate on improving the solution
                 quality, but we also look at efficiency. Various
                 heuristics are tried and mixed by hand, while evaluated
                 with the help of the CGP system. Results show that some
                 heuristics result in very substantial performance
                 improvements, that complex heuristics are usually not
                 decomposable, and that the heuristics generalize to
                 apply to other similar problems, but the applicability
                 reduces with the complexity of the heuristics and the
                 dissimilarity of the new problem to the old one. We
                 also compare such user-mixed heuristics with those
                 generated by the ACGP system which automatically
                 extracts heuristics improving GP performance.",
  notes =        "GECCO-2005 A joint meeting of the fourteenth
                 international conference on genetic algorithms
                 (ICGA-2005) and the tenth annual genetic programming
                 conference (GP-2005).

                 ACM Order Number 910052",

Genetic Programming entries for Cezary Z Janikow Christopher J Mann