A Linear Regression Approach to Numerical Simplification in Tree-Based Genetic Programming

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

@TechReport{Johnston:tr09-7,
  author =       "Mark Johnston and Thomas Liddle and Mengjie Zhang",
  title =        "A Linear Regression Approach to Numerical
                 Simplification in Tree-Based Genetic Programming",
  institution =  "School of Mathematics Statistics and Operations
                 Research, Victoria University of Wellington",
  year =         "2009",
  type =         "Research report",
  number =       "09-7",
  address =      "New Zealand",
  month =        "14 " # dec,
  keywords =     "genetic algorithms, genetic programming",
  URL =          "http://msor.victoria.ac.nz/twiki/pub/Main/ResearchReportSeries/msor09-07.pdf",
  abstract =     "We propose a novel approach to simplification in
                 tree-based Genetic Programming to combat program bloat,
                 based upon numerical relaxations of algebraic rules.We
                 also separate proposal of simplifications (using linear
                 regression, removing redundant children, and replacing
                 small ranges with a constant) from an acceptance
                 criterion that checks the effect of proposed
                 simplifications on the evaluation of training examples,
                 looking several levels up the tree.We test our
                 simplification method on three classification datasets
                 and conclude that the success of linear regression is
                 data set dependent, that looking further up the tree
                 can catch unwanted bad case simplifications, and that
                 CPU time can be significantly reduced while maintaining
                 classification accuracy on unseen examples.",
  notes =        "Wine, Wisconsin, Coins",
  size =         "38 pages",
}

Genetic Programming entries for Mark Johnston Thomas Liddle Mengjie Zhang

Citations