Efficient Evolution of Asymetric Recurrent Neural Networks Using a PDGP-inspired Two-dimensional Representation

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

@InProceedings{pujol:1998:eearNN,
  author =       "Joao Carlos Figueira Pujol and Riccardo Poli",
  title =        "Efficient Evolution of Asymetric Recurrent Neural
                 Networks Using a PDGP-inspired Two-dimensional
                 Representation",
  booktitle =    "Proceedings of the First European Workshop on Genetic
                 Programming",
  year =         "1998",
  editor =       "Wolfgang Banzhaf and Riccardo Poli and 
                 Marc Schoenauer and Terence C. Fogarty",
  volume =       "1391",
  series =       "LNCS",
  pages =        "130--141",
  address =      "Paris",
  publisher_address = "Berlin",
  month =        "14-15 " # apr,
  publisher =    "Springer-Verlag",
  keywords =     "genetic algorithms, genetic programming",
  ISBN =         "3-540-64360-5",
  URL =          "http://cswww.essex.ac.uk/staff/poli/papers/Pujol-EUROGP1998.pdf",
  URL =          "http://citeseer.ist.psu.edu/305558.html",
  DOI =          "doi:10.1007/BFb0055933",
  abstract =     "Recurrent neural networks are particularly useful for
                 processing time sequences and simulating dynamical
                 systems. However, methods for building recurrent
                 architectures have been hindered by the fact that
                 available training algorithms are considerably more
                 complex than those for feedforward networks. In this
                 paper, we present a new method to build recurrent
                 neural networks based on evolutionary computation,
                 which combines a linear chromosome with a
                 two-dimensional representation inspired by Parallel
                 Distributed Genetic Programming (a form of genetic
                 programming for the evolution of graph-like programs)
                 to evolve the architecture and the weights
                 simultaneously. Our method can evolve general
                 asymmetric recurrent architectures as well as
                 specialized recurrent architectures. This paper
                 describes the method and reports on results of its
                 application.",
  notes =        "EuroGP'98. Artificial Ant John Muir Trail",
  affiliation =  "The University of Birmingham School of Computer
                 Science B15 2TT Birmingham UK B15 2TT Birmingham UK",
}

Genetic Programming entries for Joao Carlos Figueira Pujol Riccardo Poli

Citations