Matrix-vector algorithms of local posteriori inference in algebraic Bayesian networks on ideal of disjuncts

An alternative mathematical model of knowledge pattern is described in the article. The calculation of transition matrix from the probability estimates of ideal of disjuncts to probability estimates of ideal of conjuncts and quanta propositions are proposed. The matrix-vector notation of posteriori...

Full description

Saved in:
Bibliographic Details
Published in2016 XIX IEEE International Conference on Soft Computing and Measurements (SCM) pp. 31 - 34
Main Authors Zolotin, Andrey A., Malchevskaia, Ekaterina A.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.05.2016
Subjects
Algebraic Bayesian networks
alternative models of knowledge patterns
Bayes methods
Computer science
Inference algorithms
Linear programming
Mathematical model
matrix-vector equations
Probabilistic logic
probabilistic-logic inference
Online AccessGet full text
DOI10.1109/SCM.2016.7519674

Cover

More Information
Summary:An alternative mathematical model of knowledge pattern is described in the article. The calculation of transition matrix from the probability estimates of ideal of disjuncts to probability estimates of ideal of conjuncts and quanta propositions are proposed. The matrix-vector notation of posteriori inference equations for knowledge patterns over ideal of disjuncts is given. Obtained results are applied to the posteriori inference equations for knowledge patterns with uncertain probability estimates.
DOI:10.1109/SCM.2016.7519674