Inference via Fuzzy Belief Networks.
Carl G. Looney, Lily Rui Liang · 2002
The power of belief networks lies in its connective edges where the influencesare bidirectional.WhileBayesian methods capture bidirectional influences, we propose a simpler and faster method of inferencing from nodal observations that uses bidirectional fuzzy influences that are propagated via fuzzy set membership functions. We need neither the conditional probability tables nor constraining mathematical structure that make inferencing NP-hard.