Выходит 12 номеров в год
ISSN Печать: 1064-2315
ISSN Онлайн: 2163-9337
Indexed in
Complexity of Bayesian Procedure of Inductive Inference. Discrete Case
Краткое описание
Behavior of inductive procedures depending on content of learning sampling is studied. We demonstrate, that if the learning sampling contains no information about some class of objects or statistical information about a priori probabilities of classes, then any procedure works badly and its error is strictly positive. An estimate of error of Bayesian recognition procedure depending on size of learning sampling and other parameters is derived. Suboptimality of Bayesian approach is proved, complexity of class of problems is assessed.
-
Sergienko I. V., Gupal A. M., Vagis A. A., Bayesian approach, theory of empirical risk minimization. Comparative analysis, Cybernetics and Systems Analysis, 44, 6, 2008. Crossref
-
Sergienko I. V., Gupal A. M., Optimal pattern recognition procedures and their application, Cybernetics and Systems Analysis, 43, 6, 2007. Crossref
-
Biletskyy B., Distributed Bayesian Machine Learning Procedures, Cybernetics and Systems Analysis, 55, 3, 2019. Crossref