Regularisation of mixture density networks

Lars U. Hjorth, Ian T. Nabney

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

6 Citations (Scopus)
11 Downloads (Pure)

Abstract

Mixture Density Networks are a principled method to model conditional probability density functions which are non-Gaussian. This is achieved by modelling the conditional distribution for each pattern with a Gaussian Mixture Model for which the parameters are generated by a neural network. This thesis presents a novel method to introduce regularisation in this context for the special case where the mean and variance of the spherical Gaussian Kernels in the mixtures are fixed to predetermined values. Guidelines for how these parameters can be initialised are given, and it is shown how to apply the evidence framework to mixture density networks to achieve regularisation. This also provides an objective stopping criteria that can replace the `early stopping' methods that have previously been used. If the neural network used is an RBF network with fixed centres this opens up new opportunities for improved initialisation of the network weights, which are exploited to start training relatively close to the optimum. The new method is demonstrated on two data sets. The first is a simple synthetic data set while the second is a real life data set, namely satellite scatterometer data used to infer the wind speed and wind direction near the ocean surface. For both data sets the regularisation method performs well in comparison with earlier published results. Ideas on how the constraint on the kernels may be relaxed to allow fully adaptable kernels are presented.
Original languageEnglish
Title of host publicationNinth International Conference on Artificial Neural Networks, 1999
Place of PublicationUnited Kingdom
PublisherInstitution of Engineering and Technology (IET)
Pages521-526
Number of pages6
Volume2
ISBN (Print)0-85296-721-7
DOIs
Publication statusPublished - 1999

Publication series

NameIET conference publications
PublisherIET

Bibliographical note

This paper is a postprint of a paper submitted to and accepted for publication in IET conference publications and is subject to Institution of Engineering and Technology Copyright. The copy of record is available at IET Digital Library.

Keywords

  • NCRG, neural nets, Bayesian regularisation, maximum likelihood estimation, mixture density networks, multivalued functions, neural networks, probability

Fingerprint Dive into the research topics of 'Regularisation of mixture density networks'. Together they form a unique fingerprint.

Cite this