Genetic Programming: Parametric Analysis of Structure Altering Mutation Techniques

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

  author =       "Alan Piszcz and Terence Soule",
  title =        "Genetic Programming: Parametric Analysis of Structure
                 Altering Mutation Techniques",
  booktitle =    "Genetic and Evolutionary Computation Conference
                 {(GECCO2005)} workshop program",
  year =         "2005",
  month =        "25-29 " # jun,
  editor =       "Franz Rothlauf and Misty Blowers and 
                 J{\"u}rgen Branke and Stefano Cagnoni and Ivan I. Garibay and 
                 Ozlem Garibay and J{\"o}rn Grahl and Gregory Hornby and 
                 Edwin D. {de Jong} and Tim Kovacs and Sanjeev Kumar and 
                 Claudio F. Lima and Xavier Llor{\`a} and 
                 Fernando Lobo and Laurence D. Merkle and Julian Miller and 
                 Jason H. Moore and Michael O'Neill and Martin Pelikan and 
                 Terry P. Riopka and Marylyn D. Ritchie and Kumara Sastry and 
                 Stephen L. Smith and Hal Stringer and 
                 Keiki Takadama and Marc Toussaint and Stephen C. Upton and 
                 Alden H. Wright",
  publisher =    "ACM Press",
  address =      "Washington, D.C., USA",
  keywords =     "genetic algorithms, genetic programming",
  pages =        "220--227",
  URL =          "",
  abstract =     "We suggest that the relationship between parameter
                 settings, ie parameters controlling mutation, and
                 performance is non-linear in genetic programs. Genetic
                 programming environments have few means for a priori
                 determination of appropriate parameters values.The
                 hypothesised nonlinear behaviour of genetic programming
                 creates difficulty in selecting parameter values for
                 many problems. we study three structure altering
                 mutation techniques using parametric analysis on a
                 problem with scalable complexity. We nd through
                 parameter analysis that two of the three mutation types
                 tested exhibit nonlinear behaviour. Higher mutation
                 rates cause a larger degree of nonlinear behaviour as
                 measured by tness and computational effort.
                 Characterisation of the mutation techniques using
                 parametric analysis confirms the nonlinear behavior. In
                 addition, we propose an extension to the existing
                 parameter setting taxonomy to include commonly used
                 structure altering mutation attributes. Finally we show
                 that the proportion of mutations applied to internal
                 nodes, instead of leaf nodes, has a significant effect
                 on performance.",
  notes =        "Distributed on CD-ROM at GECCO-2005. ACM

Genetic Programming entries for Alan Piszcz Terence Soule