Effects of Occam's Razor in Evolving Sigma-Pi Neural Networks

Created by W.Langdon from gp-bibliography.bib Revision:1.3872

@InProceedings{Zhang-94-PPSN,
  author =       "Byoung-Tak Zhang",
  title =        "Effects of {O}ccam's Razor in Evolving Sigma-Pi Neural
                 Networks",
  booktitle =    "Lecture Notes in Computer Science 866: Parallel
                 Problem Solving from Nature III",
  address =      "Jerusalem",
  publisher_address = "Berlin, Germany",
  publisher =    "Springer-Verlag",
  editor =       "Y. Davidor and H.-P. Schwefel and R. M{\"a}nner",
  year =         "1994",
  pages =        "462--471",
  keywords =     "genetic algorithms, genetic programming",
  URL =          "http://www.ais.fraunhofer.de/~muehlen/publications/gmd_as_ga-94_07.ps",
  URL =          "http://citeseer.ist.psu.edu/zhang94effect.html",
  abstract =     "Several evolutionary algorithms make use of
                 hierarchical representations of variable size rather
                 than linear strings of fixed length. Variable
                 complexity of the structures provides an additional
                 representational power which may widen the application
                 domain of evolutionary algorithms. The price for this
                 is, however, that the search space is open-ended and
                 solutions may grow to arbitrarily large size. In this
                 paper we study the effects of structural complexity of
                 the solutions on their generalization performance by
                 analyzing the fitness landscape of sigma-pi neural
                 networks. The analysis suggests that smaller networks
                 achieve, on average, better generalization accuracy
                 than larger ones, thus confirming the usefulness of
                 Occam's razor. A simple method for implementing the
                 Occam's razor principle is described and shown to be
                 effective in improving the generalization accuracy
                 without limiting their learning capacity.",
}

Genetic Programming entries for Byoung-Tak Zhang

Citations