Minimum Error Tree Decomposition
This addresses the issue of imprecise correlation data in belief network construction, which is an incremental extension of existing methods.
The paper tackles the problem of constructing tree-structured belief networks with hidden variables when correlation data contains errors, using a greedy search algorithm to locally minimize an error function, resulting in a method that can handle imprecise measurements.
This paper describes a generalization of previous methods for constructing tree-structured belief network with hidden variables. The major new feature of the described method is the ability to produce a tree decomposition even when there are errors in the correlation data among the input variables. This is an important extension of existing methods since the correlational coefficients usually cannot be measured with precision. The technique involves using a greedy search algorithm that locally minimizes an error function.