Selection Bias and Generalisation Error in Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.4549

  author =       "Jeannie Fitzgerald and Conor Ryan",
  title =        "Selection Bias and Generalisation Error in Genetic
  booktitle =    "Sixth International Conference on Computational
                 Intelligence, Communication Systems and Networks,
  year =         "2014",
  editor =       "David Al-Dabass and Vullnet Ameti and 
                 Fauzi Skenderi and Festim Halili",
  pages =        "59--64",
  address =      "Tetovo, Macedonia",
  month =        "27-29 " # may,
  keywords =     "genetic algorithms, genetic programming,
                 generalisation, Tournament Size, Elitism, Replacement
  isbn13 =       "978-1-4799-5076-8",
  URL =          "",
  URL =          "",
  URL =          "",
  size =         "6 pages",
  abstract =     "There have been many studies undertaken to determine
                 the efficacy of parameters and algorithmic components
                 of Genetic Programming, but historically,
                 generalisation considerations have not been of central
                 importance in such investigations. Recent contributions
                 have stressed the importance of generalization to the
                 future development of the field. In this paper we
                 investigate aspects of selection bias as a component of
                 generalisation error, where selection bias refers to
                 the method used by the learning system to select one
                 hypothesis over another. Sources of potential bias
                 include the replacement strategy chosen and the means
                 of applying selection pressure. We investigate the
                 effects on generalisation of two replacement
                 strategies, together with tournament selection with a
                 range of tournament sizes. Our results suggest that
                 larger tournaments are more prone to overfitting than
                 smaller ones, and that a small tournament combined with
                 a generational replacement strategy produces relatively
                 small solutions and is least likely to over-fit.",
  notes =        "Not in the IEEE digital


Genetic Programming entries for Jeannie Fitzgerald Conor Ryan