A framework for measuring the generalization ability of Geometric Semantic Genetic Programming (GSGP) for Black-Box Boolean Functions Learning

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

@InProceedings{Mambrini:2014:SMGP,
  author =       "Andrea Mambrini and Yang Yu2 and Xin Yao",
  title =        "A framework for measuring the generalization ability
                 of Geometric Semantic Genetic Programming (GSGP) for
                 Black-Box Boolean Functions Learning",
  booktitle =    "Semantic Methods in Genetic Programming",
  year =         "2014",
  editor =       "Colin Johnson and Krzysztof Krawiec and 
                 Alberto Moraglio and Michael O'Neill",
  address =      "Ljubljana, Slovenia",
  month =        "13 " # sep,
  note =         "Workshop at Parallel Problem Solving from Nature 2014
                 conference",
  keywords =     "genetic algorithms, genetic programming",
  URL =          "http://www.cs.put.poznan.pl/kkrawiec/smgp2014/uploads/Site/Mambrini.pdf",
  size =         "2 pages",
  abstract =     "Moraglio et al. proposed GSGP operators for learning
                 Boolean functions [1]. The work provides upper bounds
                 of the expected time for the algorithm to t the
                 training set but it doesn't give any guarantees on how
                 the learnt functions will evolve on unseen input. In
                 this work we provide a framework to analyse GSGP as
                 learning tool. This can be used to obtain lower bounds
                 on the generalisation error of the Boolean functions
                 evolved by the algorithm.",
  notes =        "SMGP 2014",
}

Genetic Programming entries for Andrea Mambrini Yang Yu2 Xin Yao

Citations