Title :
A new method for estimating Markov random fields
Author :
Almeida, Murilo ; Gidas, Basilis
Author_Institution :
Div. of Appl. Math., Brown Univ., Providence, RI, USA
Abstract :
A method is introduced for estimating the parameters of Markov random fields from complete or incomplete data. The method is computationally more efficient than its best competitor, the method of maximum pseudo-likelihood. For incomplete data, the method leads to an algorithm which is similar to, but simpler than, the EM algorithm
Keywords :
Markov processes; data analysis; parameter estimation; Markov random fields; incomplete data; parameter estimation; random field estimation; variational method; Computer network reliability; Computer networks; Computer vision; Degradation; Markov random fields; Mathematics; Neural networks; Parameter estimation; Speech recognition; Virtual manufacturing;
Conference_Titel :
TENCON '89. Fourth IEEE Region 10 International Conference
Conference_Location :
Bombay
DOI :
10.1109/TENCON.1989.176881
