A study on Koza's performance measures

Created by W.Langdon from gp-bibliography.bib Revision:1.4549

  author =       "David F. Barrero and Bonifacio Castano and 
                 Maria D. R-Moreno and David Camacho",
  title =        "A study on Koza's performance measures",
  journal =      "Genetic Programming and Evolvable Machines",
  year =         "2015",
  volume =       "16",
  number =       "3",
  pages =        "327--349",
  month =        sep,
  keywords =     "genetic algorithms, genetic programming, Computational
                 effort, Performance measures, Experimental methods,
                 Measurement error",
  ISSN =         "1389-2576",
  DOI =          "doi:10.1007/s10710-014-9238-9",
  size =         "23 pages",
  abstract =     "John R. Koza defined several metrics to measure the
                 performance of an Evolutionary Algorithm that have been
                 widely used by the Genetic Programming community.
                 Despite the importance of these metrics, and the doubts
                 that they have generated in many authors, their
                 reliability has attracted little research attention,
                 and is still not well understood. The lack of knowledge
                 about these metrics has likely contributed to the
                 decline in their usage in the last years. This paper is
                 an attempt to increase the knowledge about these
                 measures, exploring in which circumstances they are
                 more reliable, providing some clues to improve how they
                 are used, and eventually making their use more
                 justifiable. Specifically, we investigate the amount of
                 uncertainty associated with the measures, taking an
                 analytical and empirical approach and reaching
                 theoretical boundaries to the error. Additionally, a
                 new method to calculate Koza's performance measures is
                 presented. It is shown that these metrics, under common
                 experimental configurations, have an unacceptable
                 error, which can be arbitrary large in certain

Genetic Programming entries for David F Barrero Bonifacio Castano Ma Dolores Rodriguez Moreno David Camacho