Please use this identifier to cite or link to this item:
http://hdl.handle.net/2445/8523
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yang, Ying | cat |
dc.contributor.author | Webb, Geoffrey I. | cat |
dc.contributor.author | Cerquides Bueno, Jesús | cat |
dc.contributor.author | Korb, Kevin B. | cat |
dc.contributor.author | Boughton, Janice | cat |
dc.contributor.author | Ting, Kai Ming | cat |
dc.date.accessioned | 2009-06-05T07:34:17Z | - |
dc.date.available | 2009-06-05T07:34:17Z | - |
dc.date.issued | 2007 | cat |
dc.identifier.issn | 1041-4347 | cat |
dc.identifier.uri | http://hdl.handle.net/2445/8523 | - |
dc.description.abstract | We conduct a large-scale comparative study on linearly combining superparent-one-dependence estimators (SPODEs), a popular family of seminaive Bayesian classifiers. Altogether, 16 model selection and weighing schemes, 58 benchmark data sets, and various statistical tests are employed. This paper's main contributions are threefold. First, it formally presents each scheme's definition, rationale, and time complexity and hence can serve as a comprehensive reference for researchers interested in ensemble learning. Second, it offers bias-variance analysis for each scheme's classification error performance. Third, it identifies effective schemes that meet various needs in practice. This leads to accurate and fast classification algorithms which have an immediate and significant impact on real-world applications. Another important feature of our study is using a variety of statistical tests to evaluate multiple learning methods across multiple data sets. | eng |
dc.format.extent | 14 p. | cat |
dc.format.mimetype | application/pdf | eng |
dc.language.iso | eng | eng |
dc.publisher | IEEE | cat |
dc.relation.isformatof | Reproducció del document publicat a http://dx.doi.org/10.1109/TKDE.2007.190650 | cat |
dc.relation.ispartof | IEEE Transactions on Knowledge and Data Engineering, 2007, vol. 19, núm. 12, p. 1652-1665. | eng |
dc.relation.uri | http://dx.doi.org/10.1109/TKDE.2007.190650 | - |
dc.rights | (c) IEEE, 2007 | cat |
dc.source | Articles publicats en revistes (Matemàtiques i Informàtica) | - |
dc.subject.classification | Estadística bayesiana | cat |
dc.subject.classification | Complexitat computacional | cat |
dc.subject.classification | Teoria de l'estimació | cat |
dc.subject.classification | Aprenentatge automàtic | cat |
dc.subject.classification | Reconeixement de formes (Informàtica) | cat |
dc.subject.other | Bayes methods | eng |
dc.subject.other | Computational complexity | eng |
dc.subject.other | Estimation theory | eng |
dc.subject.other | Learning (artificial intelligence) | eng |
dc.subject.other | Pattern classification | eng |
dc.subject.other | Statistical testing | eng |
dc.title | To select or to weigh: a comparative study of linear combination schemes for superparent-one-dependence estimators | eng |
dc.type | info:eu-repo/semantics/article | eng |
dc.type | info:eu-repo/semantics/publishedVersion | - |
dc.identifier.idgrec | 556420 | eng |
dc.rights.accessRights | info:eu-repo/semantics/openAccess | - |
Appears in Collections: | Articles publicats en revistes (Matemàtiques i Informàtica) |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
556420.pdf | 3.42 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.