Tikhonov Regularization as a Complexity Measure in Multiobjective Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.4192

  author =       "Ji Ni and Peter Rockett",
  title =        "Tikhonov Regularization as a Complexity Measure in
                 Multiobjective Genetic Programming",
  journal =      "IEEE Transactions on Evolutionary Computation",
  year =         "2015",
  volume =       "19",
  number =       "2",
  pages =        "157--166",
  month =        apr,
  keywords =     "genetic algorithms, genetic programming, Tikhonov
                 regularisation, Complexity measure, Pareto dominance",
  ISSN =         "1089-778X",
  URL =          "http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6746085",
  DOI =          "doi:10.1109/TEVC.2014.2306994",
  size =         "10 pages",
  abstract =     "We propose using Tikhonov regularisation in
                 conjunction with node count as a general complexity
                 measure in multiobjective genetic programming. We
                 demonstrate that employing this general complexity
                 yields mean squared test error measures over a range of
                 regression problems which are typically superior to
                 those from conventional node count (but never
                 statistically worse). We also analyse the reason why
                 our new method outperforms the conventional complexity
                 measure and conclude that it forms a decision mechanism
                 which balances both syntactic and semantic
  notes =        "also known as \cite{6746085}",

Genetic Programming entries for Ji Ni Peter I Rockett