License
When quoting this document, please refer to the following
URN: urn:nbn:de:0030-drops-28146
URL: http://drops.dagstuhl.de/opus/volltexte/2010/2814/
Go to the corresponding Portal


Langdon, William

2-bit Flip Mutation Elementary Fitness Landscapes

pdf-format:
Document 1.pdf (266 KB)


Abstract

Genetic Programming parity is not elementary. GP parity cannot be represented as the sum of a small number of elementary landscapes. Statistics, including fitness distance correlation, of Parity's fitness landscape are calculated. Using Walsh analysis the eigen values and eigenvectors of the Laplacian of the two bit flip fitness landscape are given and a ruggedness measure for elementary landscapes is proposed. An elementary needle in a haystack (NIH) landscape is given.

BibTeX - Entry

@InProceedings{langdon:DSP:2010:2814,
  author =	{William Langdon},
  title =	{2-bit Flip Mutation Elementary Fitness Landscapes},
  booktitle =	{Theory of Evolutionary Algorithms},
  year =	{2010},
  editor =	{Anne Auger and Jonathan L. Shapiro and L. Darrell Whitley and Carsten Witt},
  number =	{10361},
  series =	{Dagstuhl Seminar Proceedings},
  ISSN =	{1862-4405},
  publisher =	{Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik, Germany},
  address =	{Dagstuhl, Germany},
  URL =		{http://drops.dagstuhl.de/opus/volltexte/2010/2814},
  annote =	{Keywords: Genetic Algorithms, Genetic Programming, search, optimisation, graph theory, Laplacian, Hamming cube}
}

Keywords: Genetic Algorithms, Genetic Programming, search, optimisation, graph theory, Laplacian, Hamming cube
Seminar: 10361 - Theory of Evolutionary Algorithms
Issue Date: 2010
Date of publication: 24.11.2010


DROPS-Home | Fulltext Search | Imprint Published by LZI