Mixtures of Truncated Basis Functions
In this paper we propose a framework, called mixtures of truncated basis functions (MoTBFs), for representing general hybrid Bayesian networks. The proposed framework generalizes both the mixture of truncated exponentials (MTEs) framework and the mixture of polynomials (MoPs) framework. Similar to M...
| Main Authors: | , , , |
|---|---|
| Format: | info:eu-repo/semantics/article |
| Language: | English |
| Published: |
2017
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10835/4886 |
| _version_ | 1789406540006948864 |
|---|---|
| author | Langseth, Helge Nielsen, Thomas D. Rumí, Rafael Salmerón Cerdán, Antonio |
| author_facet | Langseth, Helge Nielsen, Thomas D. Rumí, Rafael Salmerón Cerdán, Antonio |
| author_sort | Langseth, Helge |
| collection | DSpace |
| description | In this paper we propose a framework, called mixtures of truncated basis functions (MoTBFs), for representing general hybrid Bayesian networks. The proposed framework generalizes both the mixture of truncated exponentials (MTEs) framework and the mixture of polynomials (MoPs) framework. Similar to MTEs and MoPs, MoTBFs are defined so that the potentials are closed under combination and marginalization, which ensures that inference in MoTBF networks can be performed efficiently using the Shafer-Shenoy architecture.
Based on a generalized Fourier series approximation, we devise a method for efficiently pproximating an arbitrary density function using the MoTBF framework. The translation method is more flexible than existing MTE or MoP-based methods, and it supports an online/anytime tradeoff between the accuracy and the complexity of the approximation. Experimental results show that the approximations obtained are either comparable or significantly better than the approximations obtained using existing methods. |
| format | info:eu-repo/semantics/article |
| id | oai:repositorio.ual.es:10835-4886 |
| institution | Universidad de Cuenca |
| language | English |
| publishDate | 2017 |
| record_format | dspace |
| spelling | oai:repositorio.ual.es:10835-48862023-04-12T19:38:14Z Mixtures of Truncated Basis Functions Langseth, Helge Nielsen, Thomas D. Rumí, Rafael Salmerón Cerdán, Antonio Hybrid Bayesian networks Approximations Mixtures of truncated basis functions Mixtures of truncated exponentials Inference In this paper we propose a framework, called mixtures of truncated basis functions (MoTBFs), for representing general hybrid Bayesian networks. The proposed framework generalizes both the mixture of truncated exponentials (MTEs) framework and the mixture of polynomials (MoPs) framework. Similar to MTEs and MoPs, MoTBFs are defined so that the potentials are closed under combination and marginalization, which ensures that inference in MoTBF networks can be performed efficiently using the Shafer-Shenoy architecture. Based on a generalized Fourier series approximation, we devise a method for efficiently pproximating an arbitrary density function using the MoTBF framework. The translation method is more flexible than existing MTE or MoP-based methods, and it supports an online/anytime tradeoff between the accuracy and the complexity of the approximation. Experimental results show that the approximations obtained are either comparable or significantly better than the approximations obtained using existing methods. 2017-07-05T08:37:35Z 2017-07-05T08:37:35Z 2012 info:eu-repo/semantics/article http://hdl.handle.net/10835/4886 DOI: 10.1016/j.ijar.2011.10.004 en Attribution-NonCommercial-NoDerivatives 4.0 Internacional http://creativecommons.org/licenses/by-nc-nd/4.0/ info:eu-repo/semantics/openAccess |
| spellingShingle | Hybrid Bayesian networks Approximations Mixtures of truncated basis functions Mixtures of truncated exponentials Inference Langseth, Helge Nielsen, Thomas D. Rumí, Rafael Salmerón Cerdán, Antonio Mixtures of Truncated Basis Functions |
| title | Mixtures of Truncated Basis Functions |
| title_full | Mixtures of Truncated Basis Functions |
| title_fullStr | Mixtures of Truncated Basis Functions |
| title_full_unstemmed | Mixtures of Truncated Basis Functions |
| title_short | Mixtures of Truncated Basis Functions |
| title_sort | mixtures of truncated basis functions |
| topic | Hybrid Bayesian networks Approximations Mixtures of truncated basis functions Mixtures of truncated exponentials Inference |
| url | http://hdl.handle.net/10835/4886 |
| work_keys_str_mv | AT langsethhelge mixturesoftruncatedbasisfunctions AT nielsenthomasd mixturesoftruncatedbasisfunctions AT rumirafael mixturesoftruncatedbasisfunctions AT salmeroncerdanantonio mixturesoftruncatedbasisfunctions |