Comparing Bayesian Neural Network Algorithms for Classifying Segmented Outdoor Images

Francesco Vivarelli, Christopher K. I. Williams

Research output: Contribution to journalArticlepeer-review

Abstract

In this paper we investigate the Bayesian training of neural networks for region labelling of segmented outdoor scenes; the data are drawn from the Sowerby Image Database of British Aerospace. Neural networks are trained with two Bayesian methods, (i) the evidence framework of MacKay (1992a,b) and (ii) a Markov Chain Monte Carlo method due to Neal (1996). The performance of the two methods is compared to evaluating the empirical learning curves of neural networks trained with the two methods. We also investigate the use of the Automatic Relevance Determination method for input feature selection.
Original languageEnglish
Pages (from-to)427-437
Number of pages11
JournalNeural Networks
Volume14
Issue number4-5
DOIs
Publication statusPublished - 1 May 2001

Keywords

  • Bayesian training of neural networks, Markov Chain Monte Carlo, automatic relevance determination, empirical learning curves, evidence framework

Fingerprint

Dive into the research topics of 'Comparing Bayesian Neural Network Algorithms for Classifying Segmented Outdoor Images'. Together they form a unique fingerprint.

Cite this