Model selection with cross-validations and bootstraps - Application to time series prediction with RBFN models

Lendasse, Amaury;Wertz, Vincent;Verleysen, Michel
(2003) Joint International Conference on Artificial Neural Networks (ICANN)/International on Neural Information Processing (ICANN 2003) — Location: ISTANBUL (Turkey) (26.June.2003)

Files

C19-Modelselectionwithcross-validationsandbootstrapsApplicationtotimeseriespredictionwithRBFNmodels.pdf
  • Restricted Access
  • Adobe PDF
  • 206.69 KB
Request a copy

Details

Authors
  • Lendasse, AmauryUCLouvain
    Author
  • Wertz, VincentUCLouvain
    Author
  • Verleysen, MichelUCLouvain
    Author
Abstract
This paper compares several model selection methods, based on experimental estimates of their generalization errors. Experiments in the context of nonlinear time series prediction by Radial-Basis Function Networks show the superiority of the bootstrap methodology over classical cross-validations and leave-one-out.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Lendasse, A., Wertz, V., & Verleysen, M. (2003). Model selection with cross-validations and bootstraps - Application to time series prediction with RBFN models. Lecture Notes in Computer Science, 2714, 573-580. https://hdl.handle.net/2078.5/253947 (Original work published 2003)