The Use of an Analytic Quotient Operator in Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.4208

  author =       "Ji Ni and Russ H. Drieberg and Peter I. Rockett",
  title =        "The Use of an Analytic Quotient Operator in Genetic
  journal =      "IEEE Transactions on Evolutionary Computation",
  year =         "2013",
  volume =       "17",
  number =       "1",
  pages =        "146--152",
  month =        feb,
  keywords =     "genetic algorithms, genetic programming, analytic
                 quotient, protected division, variance stabilisation",
  ISSN =         "1089-778X",
  DOI =          "doi:10.1109/TEVC.2012.2195319",
  size =         "7 pages",
  abstract =     "We propose replacing the division operator used in
                 genetic programming with an analytic quotient
                 operator.We demonstrate that this analytic quotient
                 operator systematically yields lower mean squared
                 errors over a range of regression tasks, due
                 principally to removing the discontinuities or
                 singularities that can often result from using either
                 protected or unprotected division. Further, the
                 analytic quotient operator is differentiable. We also
                 show that the new analytic quotient operator stabilises
                 the variance of the intermediate quantities in the
  notes =        "Discussion of NaN inf (IEEE754, 1985). Cites
                 \cite{keijzer03}. Analytic Quotient AQ(x,y) =
                 x/sqrt(1+y*y). Normal (single objective SOGP). MOGP
                 used to limit bloat (cf \cite{langdon:book}). PCGP
                 doi:10.1162/106365602760234117 Tested on six regression
                 problems (do any of them have negative values?) 'using
                 the AQ operator always yielded the smallest mean test
                 errors' (sec 3). 'AQ yields the smallest standard
                 deviation' (except one case, sec 3). 'correlation
                 between low training error and low test error' (sec 4).
                 Fig 3 uses log scales. Bloat shown in Table 12.

                 Also known as \cite{6186815}",

Genetic Programming entries for Ji Ni Russ H Drieberg Peter I Rockett