Improving the Generalization Properties of Radial Basis Function Neural Networks

Christopher M. Bishop

Research output: Contribution to journalArticlepeer-review

Abstract

An important feature of radial basis function neural networks is the existence of a fast, linear learning algorithm in a network capable of representing complex non-linear mappings. Satisfactory generalization in these networks requires that the network mapping be sufficiently smooth. We show that a modification to the error functional allows smoothing to be introduced explicitly without significantly affecting the speed of training. A simple example is used to demonstrate the resulting improvement in the generalization properties of the network.

Original languageEnglish
Pages (from-to)579–588
Number of pages10
JournalNeural Computation
Volume3
Issue number4
DOIs
Publication statusPublished - 1 Jan 1991

Fingerprint

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

Cite this