Evolving Neural Networks for Decomposable Problems using Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.4192

  author =       "Bret Talko and Linda Stern and Les Kitchen",
  title =        "Evolving Neural Networks for Decomposable Problems
                 using Genetic Programming",
  booktitle =    "PRICAI 2000 Topics in Artificial Intelligence: 6th
                 Pacific Rim International Conference on Artificial
  pages =        "446--456",
  year =         "2000",
  editor =       "Riichiro Mizoguchi and John K. Slaney",
  series =       "Lecture Notes in Artifical Intelligence",
  volume =       "1886",
  address =      "Melbourne Convention Centre, Austrlia",
  month =        "28 " # aug # "-1 " # sep,
  publisher =    "Springer",
  keywords =     "genetic algorithms, genetic programming",
  ISBN =         "3-540-67925-1",
  bibsource =    "DBLP, http://dblp.uni-trier.de",
  DOI =          "doi:10.1007/3-540-44533-1_46",
  abstract =     "Many traditional methods for training neural networks
                 using genetic algorithms and genetic programming do not
                 have any special provisions for taking advantage of
                 decomposable problems which can be solved by combining
                 solutions to each subproblem. This paper describes a
                 new approach to neural network construction using
                 genetic programming which is designed to rapidly
                 construct networks composed of similar subnetworks. A
                 system has been developed to produce trained weightless
                 neural networks by using construction rules to build
                 the networks. The network construction rules are
                 evolved by the genetic programming system. The system
                 has been applied to decomposable Boolean problems and
                 the results were compared with a modified version of
                 the system in which networks cannot be constructed
                 modularly. The modular version of the system obtains
                 significantly better results than the non-modular
                 version of the program.",
  notes =        "PRICAI 2000 http://www3.cm.deakin.edu.au/pricai/",

Genetic Programming entries for Bret Talko Linda Stern Les Kitchen