Overfitting Avoidance in Genetic Programming of Polynomials

Created by W.Langdon from gp-bibliography.bib Revision:1.3872

  author =       "Nikolay Nikolaev and Lilian M. {de Menezes} and 
                 Hitoshi Iba",
  title =        "Overfitting Avoidance in Genetic Programming of
  booktitle =    "Proceedings of the 2002 Congress on Evolutionary
                 Computation CEC2002",
  editor =       "David B. Fogel and Mohamed A. El-Sharkawi and 
                 Xin Yao and Garry Greenwood and Hitoshi Iba and Paul Marrow and 
                 Mark Shackleton",
  pages =        "1209--1214",
  year =         "2002",
  publisher =    "IEEE Press",
  publisher_address = "445 Hoes Lane, P.O. Box 1331, Piscataway, NJ
                 08855-1331, USA",
  organisation = "IEEE Neural Network Council (NNC), Institution of
                 Electrical Engineers (IEE), Evolutionary Programming
                 Society (EPS)",
  ISBN =         "0-7803-7278-6",
  month =        "12-17 " # may,
  notes =        "CEC 2002 - A joint meeting of the IEEE, the
                 Evolutionary Programming Society, and the IEE. Held in
                 connection with the World Congress on Computational
                 Intelligence (WCCI 2002)",
  keywords =     "genetic algorithms, genetic programming, stroganoff,
                 Stroganoff system, complexity tuning, fitness function,
                 genetic programming, local ridge regression, model
                 specification flexibility, overfitting avoidance,
                 polynomial block reformulation, polynomials, predictive
                 models, regularised weight subset selection, search
                 navigation, statistical bias, statistical variance,
                 time series forecasting, forecasting theory,
                 mathematics computing, polynomials, programming,
                 statistical analysis, time series",
  DOI =          "doi:10.1109/CEC.2002.1004415",
  abstract =     "This paper proposes several techniques for avoiding
                 over fitting in the genetic programming (GP) of
                 polynomials. The model specification flexibility is
                 increased by: (1) a polynomial block reformulation,
                 which reduces the statistical bias, and, (2) complexity
                 tuning using local ridge regression and regularised
                 weight subset selection, which reduce the statistical
                 variance. Another contribution is the designed fitness
                 function for search navigation towards highly
                 predictive models. Experimental results on time-series
                 forecasting show that these techniques help GP to find
                 accurate, less complex and better forecasting
                 polynomials than traditional Koza-style GP (J.R. Koza,
                 1992) and the previous Stroganoff system (H. Iba et
                 al., 1994, 2001)",

Genetic Programming entries for Nikolay Nikolaev Lilian M de Menezes Hitoshi Iba