Evolution of learning rules for supervised tasks II: hard learning problems

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

  author =       "Ibrahim Kuscu",
  title =        "Evolution of learning rules for supervised tasks II:
                 hard learning problems",
  institution =  "School of Cognitive and Computing Sciences, University
                 of Sussex",
  year =         "1995",
  type =         "Cognitive Science Research Paper",
  number =       "395",
  address =      "Falmer, Brighton, Sussex, UK",
  month =        "10 " # nov,
  keywords =     "genetic algorithms, genetic programming",
  URL =          "ftp://ftp.cogs.susx.ac.uk/pub/reports/csrp/csrp395.ps.Z",
  abstract =     "Recent experiments with a genetic-based encoding
                 schema are presented as a potentially powerful tool to
                 discover learning rules by means of evolution. The
                 representation used is similar to the one used in
                 Genetic Programming (GP) but it employs only a fixed
                 set of functions to solve a variety of problems. In
                 this paper three Monks' and parity problems are tested.
                 The results indicate the usefulness of the encoding
                 schema in discovering learning rules for hard learning
                 problems. The problems and future research directions
                 are discussed within the context of GP practices.",
  size =         "18 pages",

Genetic Programming entries for Ibrahim Kuscu