Full text
|
PDF
- Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (401kB) | Preview |
Decision boundary for discrete Bayesian network classifiers
Citation
Varando, Gherardo and Bielza Lozoya, Maria Concepcion and Larrañaga Múgica, Pedro (2015). Decision boundary for discrete Bayesian network classifiers. "Journal of Machine Learning Research" (n. 16); pp. 2725-2749. ISSN 1533-7928.
Description
| Title: | Decision boundary for discrete Bayesian network classifiers |
|---|---|
| Author/s: |
|
| Item Type: | Article |
| Título de Revista/Publicación: | Journal of Machine Learning Research |
| Date: | December 2015 |
| ISSN: | 1533-7928 |
| Subjects: | |
| Freetext Keywords: | Bayesian networks, supervised classification, decision boundary, polynomial threshold function, Lagrange basis |
| Faculty: | E.T.S. de Ingenieros Informáticos (UPM) |
| Department: | Inteligencia Artificial |
| Creative Commons Licenses: | None |
Available versions for this object
This is the latest version for this electronic publication.
-
Decision boundary for discrete Bayesian network classifiers. (deposited 16 May 2014 06:55)
-
Decision boundary for discrete Bayesian network classifiers. (deposited 30 Sep 2014 14:59)
- Decision boundary for discrete Bayesian network classifiers. (deposited 25 May 2016 06:57) [Currently Displayed]
-
Decision boundary for discrete Bayesian network classifiers. (deposited 30 Sep 2014 14:59)
Abstract
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.
More information
| Item ID: | 40608 |
|---|---|
| DC Identifier: | http://oa.upm.es/40608/ |
| OAI Identifier: | oai:oa.upm.es:40608 |
| Official URL: | http://jmlr.org/papers/v16/varando15a.html |
| Deposited by: | Archivo Digital UPM |
| Deposited on: | 25 May 2016 06:57 |
| Last Modified: | 15 Jun 2016 09:09 |
