Institute of Information Theory and Automation

You are here

Bibliography

Conference Paper (international conference)

Characterization of essential graphs by means of an operation of legal component merging

Studený Milan

: Proceedings of the First European Workshop on Probabilistic Graphical Models, p. 161-168 , Eds: Gamez J. A., Salmeron A.

: University of Castilla, (Cuenca 2002)

: European Workshop on Probabilistic Graphical Models /1./ PGM'02, (Cuenca, ES, 06.11.2002-08.11.2002)

: CEZ:AV0Z1075907

: GA201/01/1482, GA ČR, IAA1075104, GA AV ČR

: essential graphs, chain graphs without flags, legal merging

(eng): The essential graph is known as a representative of an equivalence class of Bayesian networks. In the contribution an alternative characterization of essential graphs is presented. The characterization is based on a special operation with chain graphs without flags which is called the legal component merging. The operation leads to an algorithm for finding the essential graph on basis of any graph in the equivalence class of chain graphs without flags, in particular on basis of any Bayesian network.

: 12A

: BA

2019-01-07 08:39