Regularization of mixture density networks

Lars U. Hjorth, Ian T. Nabney

Research output: Chapter in Book/Report/Conference proceedingChapter in a book

Abstract

Mixture Density Networks (MDNs) are a well-established method for modelling complex multi-valued functions where regression methods (such as MLPs) fail. In this paper we develop a Bayesian regularization method for MDNs by an extension of the evidence procedure. The method is tested on two data sets and compared with early stopping.
Original languageEnglish
Title of host publicationIEE Conference Publication
Place of PublicationUnited Kingdom
PublisherInstitution of Engineering and Technology (IET)
Pages521-526
Number of pages6
Volume2
Edition470
ISBN (Print)0852967217
Publication statusPublished - 1999

Cite this