Simultaneous Evolution of Programs and their Control Structures

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

@InCollection{spector:1996:aigp2,
  author =       "Lee Spector",
  title =        "Simultaneous Evolution of Programs and their Control
                 Structures",
  booktitle =    "Advances in Genetic Programming 2",
  publisher =    "MIT Press",
  year =         "1996",
  editor =       "Peter J. Angeline and K. E. {Kinnear, Jr.}",
  pages =        "137--154",
  chapter =      "7",
  address =      "Cambridge, MA, USA",
  keywords =     "genetic algorithms, genetic programming",
  ISBN =         "0-262-01158-1",
  URL =          "http://helios.hampshire.edu/lspector/pubs/AiGP2-post-final-e.pdf",
  URL =          "http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6277496",
  size =         "18 pages",
  abstract =     "This chapter shows how a genetic programming system
                 can be used to simultaneously evolve programs and their
                 control structures. Koza has previously shown that the
                 performance of a genetic programming system can
                 sometimes be improved by allowing for the simultaneous
                 evolution of a main program and a collection of
                 automatically defined functions (ADFs). This chapter
                 shows how related techniques can be used to
                 simultaneously evolve a main program and a collection
                 of automatically defined macros (ADMs). Examples are
                 provided to show how the use of ADMs can lead to the
                 production of useful new control structures during
                 evolution, and data is presented to show that ADMs
                 sometimes provide a greater benefit than do ADFs. The
                 chapter includes a discussion of characteristics of
                 problems that may benefit most from the use of ADMs or
                 from architectures that include both ADFs and ADMs. It
                 is suggested that ADMs are likely to be useful for
                 evolving intelligent action systems for complex
                 environments, and data is presented to show that this
                 is the case for one such application. The chapter
                 concludes with a discussion of several directions for
                 further research.",
}

Genetic Programming entries for Lee Spector

Citations