Genetic L-System Programming

by

Jacob, C.

Literature search on Evolutionary ComputationBBase ©1999-2013, Rasmus K. Ursem
     Home · Search · Adv. search · Authors · Login · Add entries   Webmaster
Note to authors: Please submit your bibliography and contact information - online papers are more frequently cited.

Info: Parallel Problem Solving from Nature III (Conference proceedings), 1994, p. 334-343
Keywords:genetic algorithms, genetic programming
Abstract:
GLP combines simulated evolution [SE] and simulated structure formation (based on Lindenmayer systems) [LS]
Notes:
PPSN3 L-systems difficult for human programmers to use, presents simple example where L-system is evolved using a GP. Initial population created from pool of pre-defined patterns (subtrees, building blocks?) rather than GP functions or terminals. Such patterns and genetic operators have a rank (like a fitness) which is used to bias the choice of pattern. A pattern is a gramtical rule and specifies (a number of possible) types for each of its arguments. Genetic operators include copying templates (sub trees?) into the pattern pool (or genetic library).
URL(s):(G)zipped postscript

Review item:

Mark as doublet (will be reviewed)

Print entry




BibTex:
@InProceedings{jacob:1994:glp,
  author =       "Christian Jacob",
  title =        "Genetic {L}-System Programming",
  booktitle =    "Parallel Problem Solving from Nature III",
  year =         "1994",
  editor =       "Yuval Davidor and Hans-Paul Schwefel and Reinhard
                 M{\"a}nner",
  pages =        "334--343",
  address =      "Jerusalem",
  publisher_address = "Berlin, Germany",
  month =        "9-14 " # oct,
  publisher =    "Springer-Verlag",
  keywords =     "genetic algorithms, genetic programming",
  URL =          "http://www2.informatik.uni-erlangen.de/IMMD-II/Persons/jacob/Publications/GeneticLSystemProgramming.ps.gz",
  abstract =     "GLP combines simulated evolution and simulated
                 structure formation (based on Lindenmayer systems)",
  notes =        "PPSN3 L-systems difficult for human programmers to
                 use, presents simple example where L-system is evolved
                 using a GP.

                 Initial population created from pool of pre-defined
                 patterns (subtrees, building blocks?) rather than GP
                 functions or terminals. Such patterns and genetic
                 operators have a rank (like a fitness) which is used to
                 bias the choice of pattern. A pattern is a gramtical
                 rule and specifies (a number of possible) types for
                 each of its arguments.

                 Genetic operators include copying templates (sub
                 trees?) into the pattern pool (or genetic library).",
}