Learning Link-Probabilities in Causal Trees
Artificial Intelligence
2013-04-12 v1
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.
Cite
@article{arxiv.1304.3103,
title = {Learning Link-Probabilities in Causal Trees},
author = {Igor Roizer and Judea Pearl},
journal= {arXiv preprint arXiv:1304.3103},
year = {2013}
}
Comments
Appears in Proceedings of the Second Conference on Uncertainty in Artificial Intelligence (UAI1986)