On the applicability of maximum entropy to inexact reasoning. (English) Zbl 0665.68079

It is shown that under a certain interpretaion of belief maximum entropy arises naturally in inexact reasoning. Practical and theoretical consequences of this method are then discussed.


68T35 Theory of languages and software systems (knowledge-based systems, expert systems, etc.) for artificial intelligence
94A17 Measures of information, entropy
Full Text: DOI


[1] Paris, J., and Rutherford, J., Parut: an expert system for resolving difficult differential diagnoses, Preprint.; Paris, J., and Rutherford, J., Parut: an expert system for resolving difficult differential diagnoses, Preprint.
[2] Nilsson, N. J., Probabilistic logic, AI, 28, 71-87 (1986) · Zbl 0589.03007
[3] Hájek, P.; Valdes, J., Algebraic foundations of uncertainty processing in rule based consulting systems, Sistemy Obratki Znanij i Izobraženij, 93-98 (1986)
[4] Perez, A.; Jiroušek, R., Construction of an intensional expert system (INES), (van Bemmel, J.; Grémy, E.; Zvárova, J., Medical Decision Making-Diagnostic Strategies in Expert Systems (1985), North Holland: North Holland Amsterdam)
[5] Goldstein, M., Systematic analysis of limited belief specification, duplicated notes (1986), University of Hull: University of Hull England
[6] Pearl, J., On evidential reasoning in a hierarchy of hypotheses, AI, 28, 9-15 (1986)
[7] Lauritzen, S. L.; Spiegelhalter, D. J., Fast manipulation of probabilities with local representations, (Proceedings from the AI Workshop on Inductive Reasoning (1987), Riso National Laboratory: Riso National Laboratory Roskilde, Denmark) · Zbl 0684.68106
[8] Pearl, J., Distributed revision of composite beliefs, AI, 33, 173-215 (1987) · Zbl 0633.68094
[9] Bundy, A., Incidence calculus: a mechanism for probabilistic reasoning, (Proceedings of the Workshop on Uncertainty in Artificial Intelligence (1985), UCLA: UCLA Los Angeles), 177-184 · Zbl 0615.68067
[10] Perez, A., The maximum entropy principle and the barycenter approach in knowledge integration, (Proceedings of the 3rd Joint Soviet-Swedish International Workshop on Information Theory (May 1987), Sochi: Sochi USSR), to appear
[11] Shore, J. E.; Johnson, R. W., Axiomatic derivation of the principle of maximum entropy and minimum cross entropy, IEEE Trans. Inf. Theory, IT-26, 1, 26-37 (1980) · Zbl 0429.94011
[12] Jaynes, E. T., Information theory and statistical mechanics, Phys. Rev., 106, 620-630 (1957) · Zbl 0084.43701
[13] Hájek, P., Combining functions for certainty degrees in consulting systems, Int. J. Man-Mach. Stud., 22, 59-76 (1985) · Zbl 0567.68055
[14] Cheeseman, P., A method of computing generalized Bayesian probability values for expert systems, (Kaufmann, W., Proceedings of the International Joint Conference on Artificial Intelligence. Proceedings of the International Joint Conference on Artificial Intelligence, Los Altos, Calif. (1983)), 198-202
[15] Griffeath, D. S., Computer solution of the discrete maximum entropy problem, Technometrics, 14, 4, 891-897 (1972)
[16] Perez, A., The barycenter concept of a set of probability measures as a tool in statistical decision, (Proceedings of the IV Vilnius Conference on Probability Theory and Mathematical Statistics. Proceedings of the IV Vilnius Conference on Probability Theory and Mathematical Statistics, Vilnius (1985)), 437-450 · Zbl 0649.62001
[17] Pearl, J., Fusion, propagation, and structuring in belief networks, AI, 29, 241-288 (1986) · Zbl 0624.68081
[18] Spiegelhalter, D. J., Probabilistic reasoning in predictive expert systems, (Kanal, L.; Lemmer, J., Uncertainty in Artificial Intelligence (1986), North-Holland: North-Holland Amsterdam), 47-68
[19] Kahneman, D.; Tversky, A., Judgement under uncertainty: heuristics and biases, (Kahneman, D.; Slovic, P.; Tversky, A., Judgement under Uncertainty: Heuristics and Biases (1982), Cambridge University Press)
[20] McLewin, W., Linear Programming and Applications (1982), Input-Output Pub. Co: Input-Output Pub. Co London
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.