Comparing Bayesian neural network algorithms for classifying segmented outdoor images

In this paper we investigate the Bayesian training of neural networks for r egion labelling of segmented outdoor scenes; the data are drawn from the So werby 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 o f the two methods is compared to evaluating the empirical learning curves o f neural networks trained with the two methods. We also investigate the use of the Automatic Relevance Determination method for input feature selectio n. (C) 2001 Elsevier Science Ltd. All rights reserved.