Dual Network Representation Applied to the Evolution of Neural Controllers

Created by W.Langdon from gp-bibliography.bib Revision:1.4202

  author =       "Joao Carlos Figueira Pujol and Riccardo Poli",
  title =        "Dual Network Representation Applied to the Evolution
                 of Neural Controllers",
  booktitle =    "Evolutionary Programming VII: Proceedings of the
                 Seventh Annual Conference on Evolutionary Programming",
  year =         "1998",
  editor =       "V. William Porto and N. Saravanan and D. Waagen and 
                 A. E. Eiben",
  volume =       "1447",
  series =       "LNCS",
  pages =        "637--646",
  address =      "Mission Valley Marriott, San Diego, California, USA",
  publisher_address = "Berlin",
  month =        "25-27 " # mar,
  publisher =    "Springer-Verlag",
  keywords =     "genetic algorithms, genetic programming, PDGP",
  ISBN =         "3-540-64891-7",
  URL =          "http://cswww.essex.ac.uk/staff/poli/papers/Pujol-EP1998.pdf",
  URL =          "http://citeseer.ist.psu.edu/pujol98dual.html",
  DOI =          "doi:10.1007/BFb0040753",
  size =         "10 pages",
  abstract =     "This paper presents a to the evolution of neural
                 networks. A linear chromosome combined with a grid
                 based representation of the network and a new crossover
                 operator allow the evolution of the architecture and
                 the weights simultaneously. There is no need for a
                 separate weight optimisation procedure and networks
                 with more than one type of activation function can be
                 evolved. This paper describes the representation, the
                 crossover operator, and reports on results of the
                 application of the method to evolve a neural controller
                 for the pole balancing problem.",
  notes =        "EP-98.


Genetic Programming entries for Joao Carlos Figueira Pujol Riccardo Poli