Pattern Recognition Distance between Experts’ Statements
Institute of Information Theories and Applications FOI ITHEA
The paper discusses a logical expert statements represented as the formulas with probabilities of the
first order language consistent with some theory T. Theoretical-models methods for setting metrics on such
statements are offered. Properties of metrics are investigated. The research allows solve problems of the best
reconciliation of expert statements, constructions of decision functions in pattern recognition, creations the bases
of knowledge and development of expert systems.
* This work was financially supported by the Russian Foundation for Basic Research, project no. 04-01-00858a.