General Method Of Multivariate Non-Linear Regression Based On Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.4221

  author =       "Jorge Eduardo {Ortiz Trivino} and 
                 Mauro {Florez Calderon}",
  title =        "General Method Of Multivariate Non-Linear Regression
                 Based On Genetic Programming",
  journal =      "International Journal of Basic and Applied Sciences",
  year =         "2012",
  volume =       "12",
  number =       "3",
  month =        "10 " # jun,
  ISSN =         "2077-1223",
  keywords =     "genetic algorithms, genetic programming",
  annote =       "The Pennsylvania State University CiteSeerX Archives",
  bibsource =    "OAI-PMH server at",
  language =     "en",
  oai =          "oai:CiteSeerX.psu:",
  rights =       "Metadata may be used without restrictions as long as
                 the oai identifier remains attached to it.",
  URL =          "",
  URL =          "",
  size =         "12 pages",
  abstract =     "In this paper we show the method phi to estimate the
                 structure and parameters of a non-linear function of
                 real value phi from a data set {(x1, x2,..., xj,...,
                 xn,; y1)}i=m i=n taken from that function. The
                 technique phi is based in the Holland's genetic
                 algorithm, this employ the genetic operations of
                 selection, crossover and mutation. But unlike this, the
                 individuals are dynamic structures called trees,
                 allowing its size can grow without restrictions and
                 these ones can become a better representation of the
                 desired response. The experimentation shows that the
                 method is efficient for both linear and nonlinear
                 functions as well as for multivaried cases",

Genetic Programming entries for Jorge Eduardo Ortiz Trivino Mauro Florez Calderon