Co-evolving Intertwined Spirals

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

  author =       "Hugues Juille and Jordan B Pollack",
  title =        "Co-evolving Intertwined Spirals",
  booktitle =    "Evolutionary Programming V: Proceedings of the Fifth
                 Annual Conference on Evolutionary Programming",
  year =         "1996",
  editor =       "Lawrence J. Fogel and Peter J. Angeline and 
                 Thomas Baeck",
  pages =        "461--467",
  address =      "San Diego",
  publisher_address = "Cambridge, MA, USA",
  month =        feb # " 29-" # mar # " 3",
  publisher =    "MIT Press",
  keywords =     "genetic algorithms, genetic programming, Spirals,
  ISBN =         "0-262-06190-2",
  URL =          "",
  URL =          "",
  URL =          "",
  URL =          "",
  URL =          "",
  abstract =     "We recently solved the two spirals problem, a
                 difficult neural network benchmark classification
                 problem, using the genetic programming primitives set
                 up by [ \cite{koza:book} ]. Instead of using absolute
                 fitness, we use a relative fitness based on a
                 competition for coverage of the data set. This is a
                 form of co-evolutionary search because the fitness
                 function changes with the population. Because niches
                 are opened by proportionate reproduction, rather than
                 crowded out, and because of the crossover operator, we
                 find solutions which have a nice modular structure. Our
                 experiments used our Massively Parallel Genetic
                 Programming (MPGP) system running on a SIMD machine of
                 4096 processors, the Maspar MP-2.",
  notes =        "EP-96


                 Massively Parallel Genetic Programming MPGP on SIMD
                 machine of 4096 processors, the Maspar MP-2",

Genetic Programming entries for Hugues Juille Jordan B Pollack