Inductive Bias and Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.3973

@InProceedings{whigham:1995:ingp,
  author =       "P. A. Whigham",
  title =        "Inductive Bias and Genetic Programming",
  booktitle =    "First International Conference on Genetic Algorithms
                 in Engineering Systems: Innovations and Applications,
                 GALESIA",
  year =         "1995",
  editor =       "A. M. S. Zalzala",
  volume =       "414",
  pages =        "461--466",
  address =      "Sheffield, UK",
  publisher_address = "London, UK",
  month =        "12-14 " # sep,
  publisher =    "IEE",
  keywords =     "genetic algorithms, genetic programming, context free
                 grammar",
  ISBN =         "0-85296-650-4",
  URL =          "http://divcom.otago.ac.nz/sirc/Peterw/Publications/galesia.zip",
  URL =          "http://citeseer.ist.psu.edu/whigham95inductive.html",
  URL =          "http://ieeexplore.ieee.org/iel3/3532/10616/00501939.pdf?tp=&arnumber=501939&isnumber=10616",
  abstract =     "Many engineering problems may be described as a search
                 for one near optimal description amongst many
                 possibilities, given certain constraints. Search
                 techniques such as genetic programming, seem
                 appropriate to represent many problems. The paper
                 describes a grammatically based learning technique
                 based upon the genetic programming paradigm, that
                 allows declarative biasing and modifies the bias as the
                 evolution proceeds. The use of bias allows complex
                 problems to be represented and searched efficiently",
  notes =        "12--14 September 1995, Halifax Hall, University of
                 Sheffield, UK see also
                 http://www.iee.org.uk/LSboard/Conf/program/galprog.htm

                 Using 6-multiplexor problem shows using a syntax (of
                 the correct sort, specified using a context free
                 grammar) to constrain the form of the program trees
                 helps GP solve the problem. More restrictions, easier
                 it is.

                 Then presents a method based on the syntax of the
                 fitest member of the population to modify the grammar
                 whilst the GP runs. Shows improvement on 6-multiplexor.
                 Still greater improvements obtained by introducing a
                 fitness for rules within the grammar. This weakly
                 biases the grammar, ie all legal program are still
                 legal, but now some are more likley to be produced than
                 they where before the fitness of the grammar rules
                 where changed.

                 10\% of population each generation regenerated using
                 his {"}replacement{"} operator.",
}

Genetic Programming entries for Peter Alexander Whigham

Citations