Belief Revision and Information Fusion in a Probabilistic Environment

This paper presents new methods for probabilistic belief revision and information fusion. By making use of the principles of optimum entropy (ME-principles), we define a generalized revision operator which aims at simulating the human learning of lessons, and we introduce a fusion operator which handles probabilistic information faithfully. In general, this fusion operator computes kind of mean probabilistic values from pieces of information provided by different sources.