Evidence propagation on influence diagrams and value of evidence
In this paper, we introduce evidence propagation operations on influence diagrams and a concept of value of evidence, which measures the value of experimentation. Evidence propagation operations are critical for the computation of the value of evidence, general update and inference operations in normative expert systems which are based on the influence diagram (Bayesian Network) paradigm. The value of evidence allows us to compute directly a value of perfect information and a value of control which are used in decision analysis (the science of decision making under uncertainty).
Unable to display preview. Download preview PDF.
- 1.Ezawa, K. J., “Efficient Evaluation of Influence Diagrams,” Ph. D. Thesis, Dept. of Engineering-Economic Systems, Stanford University, Palo Alto, CA, 1986Google Scholar
- 2.Ezawa, K. J., and Scherer, J. B., “Technology Planning For Advanced Telecommunication Services: A Computer-Aided Approach,” Telematics and Informatics, pp. 101–112, 1992.Google Scholar
- 3.Lauritzen, S. L., and Spiegelhalter, D. J., “Local Computations with Probabilities on Graphical Structures and their Application to Expert Systems,” J. R. Statist. Soc., B 50, No.2 pp 157–224, 1988.Google Scholar
- 4.Matheson, James E., “Using Influence Diagrams to Value of Information and Control,” Influence Diagrams, Belief Nets and Decision Analysis, John Wiley & Sons, 1990.Google Scholar
- 5.Pearl, Judea, “Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference,” Morgan Kaufmann, 1988.Google Scholar
- 6.Shachter, R. D., “Evidence Absorption and Propagation through Evidence Reversals,” Uncertainty in Artificial Intelligence, Vol. 5, pp. 173–190, North-Holland, 1990.Google Scholar
- 7.Shachter, R. D., “Evaluating Influence Diagrams,” Operations Research, Vol. 34, No. 6, 1986.Google Scholar