2021-02-26T03:56:58Z
http://oa.upm.es/cgi/oai2
oai:oa.upm.es:40608
2016-06-15T09:09:17Z
7374617475733D707562
7375626A656374733D6D6174656D617469636173
7375626A656374733D696E666F726D6174696361
747970653D61727469636C65
Decision boundary for discrete Bayesian network classifiers
Varando, Gherardo
Bielza Lozoya, Maria Concepcion
Larrañaga Múgica, Pedro
Mathematics
Computer Science
Bayesian network classifiers are a powerful machine learning tool. In order to evaluate the expressive power of these models, we compute families of polynomials that sign-represent decision functions induced by Bayesian network classifiers. We prove that those families are linear combinations of products of Lagrange basis polynomials. In absence of V -structures in the predictor sub-graph, we are also able to prove that this family of polynomials does indeed characterize the specific classifier considered. We then use this representation to bound the number of decision functions representable by Bayesian network classifiers with a given structure.
E.T.S. de Ingenieros Informáticos (UPM)
(c) Editor/Autor
2015-12
info:eu-repo/semantics/article
Article
Journal of Machine Learning Research, ISSN 1533-7928, 2015-12, No. 16
PeerReviewed
application/pdf
eng
http://jmlr.org/papers/v16/varando15a.html
info:eu-repo/semantics/openAccess
http://oa.upm.es/40608/