As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
Inspired by the problem of fault isolation we consider Bayesian inference from training data and background knowledge. We discuss how the background knowledge can be translated to equality constraints and show how it is introduced in the computations. The main advantage of combining data and background knowledge is achieved when the amount of data is limited.