Using Bayesian neural networks to classify segmented images

F. Vivarelli, C.K.I. Williams

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present results that compare the performance of neural networks trained with two Bayesian methods, (i) the evidence framework of D.J.C. MacKay (1992) and (ii) a Markov chain Monte Carlo method due to R.M. Neal (1996) on a task of classifying segmented outdoor images. We also investigate the use of the automatic relevance determination method for input feature selection
Original languageEnglish
Title of host publicationArtificial Neural Networks, Fifth International Conference on (Conf. Publ. No. 440)
PublisherIET
Pages268-273
Number of pages6
ISBN (Print)0-85296-690-3
DOIs
Publication statusPublished - 1 Jul 1997

Keywords

  • neural nets
  • Bayesian neural networks
  • Markov chain Monte Carlo method
  • automatic relevance determination method
  • evidence framework
  • input feature selection
  • performance
  • segmented images classification

Fingerprint

Dive into the research topics of 'Using Bayesian neural networks to classify segmented images'. Together they form a unique fingerprint.

Cite this