Generalization Performance of Radial Basis Function Networks

Yunwen Lei, Lixin Ding, Wensheng Zhang

Research output: Contribution to journalJournal articlepeer-review

31 Citations (Scopus)

Abstract

This paper studies the generalization performance of radial basis function (RBF) networks using local Rademacher complexities. We propose a general result on controlling local Rademacher complexities with the L1 -metric capacity. We then apply this result to estimate the RBF networks' complexities, based on which a novel estimation error bound is obtained. An effective approximation error bound is also derived by carefully investigating the Hölder continuity of the lp loss function's derivative. Furthermore, it is demonstrated that the RBF network minimizing an appropriately constructed structural risk admits a significantly better learning rate when compared with the existing results. An empirical study is also performed to justify the application of our structural risk in model selection.

Original languageEnglish
Pages (from-to)551-564
Number of pages14
JournalIEEE Transactions on Neural Networks and Learning Systems
Volume26
Issue number3
Early online date19 May 2014
DOIs
Publication statusPublished - Mar 2015

Scopus Subject Areas

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

User-Defined Keywords

  • Learning theory
  • local Rademacher complexity
  • radial basis function (RBF) networks
  • structural risk minimization (SRM).

Fingerprint

Dive into the research topics of 'Generalization Performance of Radial Basis Function Networks'. Together they form a unique fingerprint.

Cite this