Learning dynamic Bayesian network models via cross-validation
2005 (English)In: Pattern Recognition Letters, ISSN 0167-8655, Vol. 26, no 14, 2295-2308 p.Article in journal (Refereed) Published
We study cross-validation as a scoring criterion for learning dynamic Bayesian network models that generalize well. We argue that cross-validation is more suitable than the Bayesian scoring criterion for one of the most common interpretations of generalization. We confirm this by carrying out an experimental comparison of cross-validation and the Bayesian scoring criterion, as implemented by the Bayesian Dirichlet metric and the Bayesian information criterion. The results show that cross-validation leads to models that generalize better for a wide range of sample sizes. © 2005 Elsevier B.V. All rights reserved.
Place, publisher, year, edition, pages
2005. Vol. 26, no 14, 2295-2308 p.
Cross-validation, Dynamic Bayesian network models, Learning.
Engineering and Technology
IdentifiersURN: urn:nbn:se:liu:diva-50403DOI: 10.1016/j.patrec.2005.04.005OAI: oai:DiVA.org:liu-50403DiVA: diva2:271299