On computational procedures for probabilistic compositional models

0410938 20240103182250.220060210235959.9 On computational procedures for probabilistic compositional models Osaka Osaka University 2002 8 s. Proceedings of the 5th Czech-Japan Seminar on Data Analysis and Decision Making under Uncertainty3-10WatadaJ. multidimensional model Bayesian network operators of composition cav_un_auth*0101118 Jiroušek Radim UTIA-B Department of Decision Making Theory Ústav teorie informace a automatizace AV ČR, v. v. i. 12A LN00B107 GA MŠk cav_un_auth*0001461 CEZ:AV0Z1075907 The goal of the paper is to present theoretical issues supporting design of algorithms for efficient computations with compositional models; previous results are summarized that make computation of marginal distributions possible and new properties necessary for computation of conditional probability distributions are introduced. cav_un_auth*0212968 Czech-Japan Seminar on Data Analysis and Decision Making under Uncertainty /5./ Mt. Koyasan JP 14.09.2002-16.09.2002 BA MTR http://hdl.handle.net/11104/0131025 UTIA-B 20020152 2002 2002 Osaka Osaka University Proceedings of the 5th Czech-Japan Seminar on Data Analysis and Decision Making under Uncertainty 3 10 Watada J. 340