Random Sampling Technique for Overfitting Control in Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.3963

@InProceedings{goncalves:2012:EuroGP,
  author =       "Ivo Goncalves and Sara Silva and Joana B. Melo and 
                 Joao M. B. Carreiras",
  title =        "Random Sampling Technique for Overfitting Control in
                 Genetic Programming",
  booktitle =    "Proceedings of the 15th European Conference on Genetic
                 Programming, EuroGP 2012",
  year =         "2012",
  month =        "11-13 " # apr,
  editor =       "Alberto Moraglio and Sara Silva and 
                 Krzysztof Krawiec and Penousal Machado and Carlos Cotta",
  series =       "LNCS",
  volume =       "7244",
  publisher =    "Springer Verlag",
  address =      "Malaga, Spain",
  pages =        "218--229",
  organisation = "EvoStar",
  isbn13 =       "978-3-642-29138-8",
  DOI =          "doi:10.1007/978-3-642-29139-5_19",
  size =         "12 pages",
  keywords =     "genetic algorithms, genetic programming, Over fitting,
                 Generalisation",
  abstract =     "One of the areas of Genetic Programming (GP) that, in
                 comparison to other Machine Learning methods, has seen
                 fewer research efforts is that of generalization.
                 Generalisation is the ability of a solution to perform
                 well on unseen cases. It is one of the most important
                 goals of any Machine Learning method, although in GP
                 only recently has this issue started to receive more
                 attention. In this work we perform a comparative
                 analysis of a particularly interesting configuration of
                 the Random Sampling Technique (RST) against the
                 Standard GP approach. Experiments are conducted on
                 three multidimensional symbolic regression real world
                 datasets, the first two on the pharmacokinetics domain
                 and the third one on the forestry domain. The results
                 show that the RST decreases over fitting on all
                 datasets. This technique also improves testing fitness
                 on two of the three datasets. Furthermore, it does so
                 while producing considerably smaller and less complex
                 solutions. We discuss the possible reasons for the good
                 performance of the RST, as well as its possible
                 limitations.",
  notes =        "Part of \cite{Moraglio:2012:GP} EuroGP'2012 held in
                 conjunction with EvoCOP2012 EvoBIO2012, EvoMusArt2012
                 and EvoApplications2012",
}

Genetic Programming entries for Ivo Goncalves Sara Silva Joana B Melo Joao M B Carreiras

Citations