Bayesian information criteria and smoothing parameter selection in radial basis function networks

Sadanori Konishi, Tomohiro Ando, Seiya Imoto

Research output: Contribution to journalArticle

72 Citations (Scopus)

Abstract

By extending Schwarz's (1978) basic idea we derive a Bayesian information criterion which enables us to evaluate models estimated by the maximum penalised likelihood method or the method of regularisation. The proposed criterion is applied to the choice of smoothing parameters and the number of basis functions in radial basis function network models. Monte Carlo experiments were conducted to examine the performance of the nonlinear modelling strategy of estimating the weight parameters by regularisation and then determining the adjusted parameters by the Bayesian information criterion. The simulation results show that our modelling procedure performs well in various situations.

Original languageEnglish
Pages (from-to)27-43
Number of pages17
JournalBiometrika
Volume91
Issue number1
DOIs
Publication statusPublished - 2004 Dec 1

Keywords

  • Bayes approach
  • Maximum penalised likelihood
  • Model selection
  • Neural network
  • Nonlinear regression

ASJC Scopus subject areas

  • Statistics and Probability
  • Mathematics(all)
  • Agricultural and Biological Sciences (miscellaneous)
  • Agricultural and Biological Sciences(all)
  • Statistics, Probability and Uncertainty
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Bayesian information criteria and smoothing parameter selection in radial basis function networks'. Together they form a unique fingerprint.

  • Cite this