Learning Bayesian Networks: A Unification for Discrete and Gaussian Domains

Abstract

We examine Bayesian methods for learning Bayesian networks from a combination of prior knowledge and statistical data. In particular, we unify the approaches we presented at last year's conference for discrete and Gaussian domains. We derive a general Bayesian scoring metric, appropriate for both domains. We then use this metric in combination with well-known statistical facts about the Dirichlet and normal--Wishart distributions to derive our metrics for discrete and Gaussian domains.

Cite

Text

Heckerman and Geiger. "Learning Bayesian Networks: A Unification for Discrete and Gaussian Domains." Conference on Uncertainty in Artificial Intelligence, 1995.

Markdown

[Heckerman and Geiger. "Learning Bayesian Networks: A Unification for Discrete and Gaussian Domains." Conference on Uncertainty in Artificial Intelligence, 1995.](https://mlanthology.org/uai/1995/heckerman1995uai-learning/)

BibTeX

@inproceedings{heckerman1995uai-learning,
  title     = {{Learning Bayesian Networks: A Unification for Discrete and Gaussian Domains}},
  author    = {Heckerman, David and Geiger, Dan},
  booktitle = {Conference on Uncertainty in Artificial Intelligence},
  year      = {1995},
  pages     = {274-284},
  url       = {https://mlanthology.org/uai/1995/heckerman1995uai-learning/}
}