Learning Link-Probabilities in Causal Trees
arXiv:1304.3103
Abstract
A learning algorithm is presented which given the structure of a causal tree, will estimate its link probabilities by sequential measurements on the leaves only. Internal nodes of the tree represent conceptual (hidden) variables inaccessible to observation. The method described is incremental, local, efficient, and remains robust to measurement imprecisions.
Appears in Proceedings of the Second Conference on Uncertainty in Artificial Intelligence (UAI1986)