Maximum Entropy Beyond Selecting Probability Distributions
Traditionally, the Maximum Entropy technique is used to select a probability distribution in situations when several different probability distributions are consistent with our knowledge. In this paper, we show that this technique can be extended beyond selecting probability distributions, to explain facts, numerical values, and even types of functional dependence.
This work was supported in part by the National Science Foundation grant HRD-1242122 (Cyber-ShARE Center of Excellence).
- 1.Garibaldi, J.: Type-2 Beyond the Centroid. In: Proceedings of the IEEE International Confreence on Fuzzy Systems FUZZ-IEEE 2017, Naples, Italy, 8–12 July 2017Google Scholar
- 2.Hobbs, J.R.: Half orders of magnitude. In: Obrst, L., Mani, I. (eds.) Proceeding of the Workshop on Semantic Approximation, Granularity, and Vagueness, A Workshop of the Seventh International Conference on Principles of Knowledge Representation and Reasoning KR 2000, Breckenridge, Colorado, pp. 28–38, 11 April 2000Google Scholar