Using Bayesian neural networks to classify segmented images

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.