Title :
Inference and learning in fuzzy bayesian networks
Author :
Baldwin, Jim F. ; Tomaso, Enza Di
Author_Institution :
Dept. of Eng. Math., Bristol Univ., UK
Abstract :
This paper deals with the development of a theory on bayesian networks. It proposes a modified algorithm for solving knowledge querying and information updating, when dealing with continuous variables and with probabilistic and uncertain instantiations. Fuzzy sets are used to rewrite the information contained in a database in order to reduce the complexity of the automatic learning of a bayesian net from data.
Keywords :
belief networks; data mining; fuzzy set theory; inference mechanisms; query processing; automatic learning; fuzzy Bayesian networks; fuzzy sets; graphical models; inference; information updating; joint probability distribution; knowledge querying; knowledge representation; modified algorithm; probabilistic instantiations; uncertain instantiations; Bayesian methods; Databases; Distributed computing; Fuzzy neural networks; Fuzzy sets; Inference algorithms; Intelligent networks; Knowledge representation; Mathematics; Uncertainty;
Conference_Titel :
Fuzzy Systems, 2003. FUZZ '03. The 12th IEEE International Conference on
Print_ISBN :
0-7803-7810-5
DOI :
10.1109/FUZZ.2003.1209437
