Automatic Design of Modular Neural Networks Using Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.4420

  author =       "Naser NourAshrafoddin and Ali R. Vahdat and 
                 Mohammad Mehdi Ebadzadeh",
  title =        "Automatic Design of Modular Neural Networks Using
                 Genetic Programming",
  booktitle =    "Proceedings of the 17th International Conference on
                 Artificial Neural Networks, ICANN 2007, Part {I}",
  year =         "2007",
  editor =       "Joaquim Marques de S{\'a} and 
                 Lu{\'i}s A. Alexandre and Wlodzislaw Duch and Danilo P. Mandic",
  volume =       "4668",
  series =       "Lecture Notes in Computer Science",
  pages =        "788--798",
  address =      "Porto, Portugal",
  month =        sep # " 9-13",
  publisher =    "Springer",
  keywords =     "genetic algorithms, genetic programming, Modular
                 neural networks, evolutionary computing, automatic
  isbn13 =       "978-3-540-74689-8",
  DOI =          "doi:10.1007/978-3-540-74690-4_80",
  size =         "11 pages",
  abstract =     "Traditional trial-and-error approach to design neural
                 networks is time consuming and does not guarantee
                 yielding the best neural network feasible for a
                 specific application. Therefore automatic approaches
                 have gained more importance and popularity. In
                 addition, traditional (non-modular) neural networks can
                 not solve complex problems since these problems
                 introduce wide range of overlap which, in turn, causes
                 a wide range of deviations from efficient learning in
                 different regions of the input space, whereas a modular
                 neural network attempts to reduce the effect of these
                 problems via a divide and conquer approach. In this
                 paper we are going to introduce a different approach to
                 autonomous design of modular neural networks. Here we
                 use genetic programming for automatic modular neural
                 networks design; their architectures, transfer
                 functions and connection weights. Our approach offers
                 important advantages over existing methods for
                 automated neural network design. First it prefers
                 smaller modules to bigger modules, second it allows
                 neurons even in the same layer to use different
                 transfer functions, and third it is not necessary to
                 convert each individual into a neural network to obtain
                 the fitness value during the evolution process. Several
                 tests were performed with problems based on some of the
                 most popular test databases. Results show that using
                 genetic programming for automatic design of neural
                 networks is an efficient method and is comparable with
                 the already existing techniques",
  bibdate =      "2007-09-17",
  bibsource =    "DBLP,

Genetic Programming entries for Naser NourAshrafoddin Ali Vahdat Mohammad Mehdi Ebadzadeh