An Introduction to Belief Networks

Belief networks, also called Bayesian networks or probabilistic causal networks, were developed in the late 1970’s to model the distributed processing in reading comprehension. Since then they have attracted much attention and have become popular within the AI probability and uncertainty community. As a natural and efficient model for human’s inferential reasoning, belief networks have emerged as the general knowledge representation scheme under uncertainty [14][15][16][17]. In this report, we first introduce belief networks in the light of knowledge representation under uncertainty, then in the following sections we give the descriptions of the semantics, inference mechanisms and some issues related to learning belief networks, respectively. This report is not intended to be a tutorial for beginners. Rather it aims to point out some important aspects of belief networks and summarize some important algorithms. For those who are interested in a tutorial, we refer to [4]. This work was supported by the Center for Satellite and Hybrid Communication Networks, under NASA cooperative agreement NCC3-528.