caa a22 4500 475800966 CHVBK 20180406123737.0 cr unu---uuuuu 170329e20001001xx s 000 0 eng 10.1023/A:1009617914949 doi (NATIONALLICENCE)springer-10.1023/A:1009617914949 Improving the Mean-Field Approximation in Belief Networks Using Bahadur's Reparameterisation of the Multivariate Binary Distribution [Elektronische Daten] [K. Humphreys, D. Titterington] We develop a new extension to the Mean-Field approximation for inference in graphical models which has advantages over other approximation schemes which have been proposed. The method is economical in its use of variational parameters and the approximating conditional distribution can be specified with direct reference to the dependence structure of the variables in the graphical model. We apply the method to sigmoid belief networks. Kluwer Academic Publishers, 2000 Bahadur nationallicence belief network nationallicence EM algorithm nationallicence Mean-Field nationallicence variational approximation nationallicence Humphreys K. Department of Statistics, University of Glasgow, Glasgow, U.K. aut Titterington D. Department of Statistics, University of Glasgow, Glasgow, U.K. aut Neural Processing Letters Kluwer Academic Publishers 12/2(2000-10-01), 183-197 1370-4621 12:2<183 2000 12 11063 https://doi.org/10.1023/A:1009617914949 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1023/A:1009617914949 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Humphreys K. Department of Statistics, University of Glasgow, Glasgow, U.K aut NATIONALLICENCE 700 1- Titterington D. Department of Statistics, University of Glasgow, Glasgow, U.K aut NATIONALLICENCE 773 0- Neural Processing Letters Kluwer Academic Publishers 12/2(2000-10-01), 183-197 1370-4621 12:2<183 2000 12 11063 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer