Abstract:
Maintaining semantics for uncertainty is critical during knowledge acquisition. We examine Bayesian Knowledge-Bases (BKBs) which are a generalization of Bayesian networks. BKBs provide a highly flexible and intuitive representation following a basic "if-then" structure in conjunction with probability theory. We present theoretical results concerning BKBs and how BKBs naturally and implicitly preserve semantics as new knowledge is added. In particular, equivalence of rule weights and conditional probabilities is achieved through stability of inferencing in BKBs.
Published Date: May 2002
Registration: ISBN 978-1-57735-141-2
Copyright: Published by The AAAI Press, Menlo Park, California