Some Notes on Possibilistic Learning
We outline a possibilistic learning method for structure identification from a database of samples. In comparison to the construction of Bayesian belief networks, the proposed framework has some advantages, namely the explicit consideration of imprecise data, and the realization of a controlled form of information compression in order to increase the efficiency of the learning strategy as well as approximate reasoning using local propagation techniques.
Our learning method has been applied to reconstruct a non-singly connected network of 22 nodes and 22 arcs without the need of any a priori supplied node ordering.
KeywordsBelief Function Possibility Distribution Frame Condition Possibility Theory Approximate Reasoning
Unable to display preview. Download preview PDF.
- Kampé de Fériet, J.: Interpretation of Membership Functions of Fuzzy Sets in Terms of Plausibility and Belief, in: Fuzzy Information and Decision Processes (Ed. M.M. Gupta, E. Sanchez ), North-Holland, 1982, 13–98.Google Scholar
- Gebhardt, J. and R. Kruse: A Comparative Discussion of Combination Rules in Numerical Settings, CEC-ESPRIT III BRA 6156 DRUMS II, Annual Report, 1993.Google Scholar
- Shafer, G.: A Mathematical Theory of Evidence, Princeton University Press, Princeton 1976.Google Scholar
- Gebhardt, J. and R. Kruse: A New Approach to Semantic Aspects of Possihilistic Reasoning, in: Symbolic and Quantitative Approaches to Reasoning and Uncertainty (Ed. M. Clarke, R. Kruse, and S. Moral), Lecture Notes in Computer Science, 747 (1993), Springer, Berlin, 151–160.Google Scholar
- Gebhardt, J. and R. Kruse: On an Information Compression View of Possibility Theory, in: Proc. 3rd IEEE Int. Conf. on Fuzzy Systems, Orlando 1994.Google Scholar
- Pearl, J. and N. Wermuth: When Can Association Graphs Admit a Causal Interpretation (First Report), in: Preliminary Papers of the 4th Int. Workshop on Artificial Intelligence and Statistics, Ft. Lauderdale, FL January 3–6 1993, 141–1 51.Google Scholar
- Verma, T. and J. Pearl: An Algorithm for Deciding if a Set of Observed Independencies Has a Causal Explanation, in: Proceedings 8th Conf. on Uncertainty in AI, 1992, 323–330.Google Scholar
- Lauritzen, S.L., B. Thiesson, and D. Spiegelhalter: Diagnostic Systems Created by Model Selection Methods — A Case Study, in: Preliminary Papers of the 4th Int. Workshop on Artificial Intelligence and Statistics, Ft. Lauderdale, FL January 3–6 1993, 141–151.Google Scholar
- Singh, M. and M. Valtorta: An Algorithm for the Construction of Bayesian Network Structures from Data, in: Proc. 9th. Conf. on Uncertainty in Artificial Intelligence, Washington 1993, 259–265.Google Scholar
- Hartley, R.V.L., Transmission of Information: The Bell Systems Technical J., 7 1928, 535–563.Google Scholar
- Pearl, J.: Probabilistic Reasoning in Intelligent Systems — Networks of Plausible Inference, Morgan Kaufman, San Mateo 1988.Google Scholar
- Andersen, S.K., K.G. Olesen, F.V. Jensen, and F. Jensen: HUGIN — A Shell for Building Bayesian Belief Universes for Expert Systems, in: Proc. 11th Int. Joint Conf. on AI, 1989, 1080–1085.Google Scholar
- Rasmussen, L.K.: Blood Group Determination of Danish Jersey Cattle in the F-blood Group System, Dina Research Report 8, Dina Foulum, 8830 Tjele, Denmark, November 1992.Google Scholar
- Kruse, R., J. Gebhardt, and F. Klawonn: Foundations of Fuzzy Systems, Wiley, Chichester 1994.Google Scholar