Training genetic programming classifiers by vicinal-risk minimization

Created by W.Langdon from gp-bibliography.bib Revision:1.7615

@Article{Ni:2014:GPEM,

• author = "Ji Ni and Peter Rockett",
• title = "Training genetic programming classifiers by vicinal-risk minimization",
• journal = "Genetic Programming and Evolvable Machines",
• year = "2015",
• volume = "16",
• number = "1",
• pages = "3--25",
• month = mar,
• keywords = "genetic algorithms, genetic programming, Classification, Vicinal-risk minimisation",
• ISSN = "1389-2576",
• DOI = "doi:10.1007/s10710-014-9222-4",
• size = "23 pages",
• abstract = "We propose and motivate the use of vicinity-risk minimisation (VRM) for training genetic programming classifiers. We demonstrate that VRM has a number of attractive properties and demonstrate that it has a better correlation with generalisation error compared to empirical risk minimisation (ERM) so is more likely to lead to better generalisation performance, in general. From the results of statistical tests over a range of real and synthetic datasets, we further demonstrate that VRM yields consistently superior generalisation errors compared to conventional ERM.",
• notes = "Department of Electronic and Electrical Engineering, University of Sheffield, Mappin Street, Sheffield, S1 3JD, UK",

}

Genetic Programming entries for Ji Ni Peter I Rockett

Citations