File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: A note on variational Bayesian factor analysis

TitleA note on variational Bayesian factor analysis
Authors
Issue Date2009
PublisherPergamon. The Journal's web site is located at http://www.elsevier.com/locate/neunet
Citation
Neural Networks, 2009, v. 22 n. 7, p. 988-997 How to Cite?
AbstractExisting works on variational bayesian (VB) treatment for factor analysis (FA) model such as [Ghahramani, Z., & Beal, M. (2000). Variational inference for Bayesian mixture of factor analysers. In Advances in neural information proceeding systems. Cambridge, MA: MIT Press; Nielsen, F. B. (2004). Variational approach to factor analysis and related models. Master's thesis, The Institute of Informatics and Mathematical Modelling, Technical University of Denmark.] are found theoretically and empirically to suffer two problems: 1{circled} penalize the model more heavily than BIC and 2{circled} perform unsatisfactorily in low noise cases as redundant factors can not be effectively suppressed. A novel VB treatment is proposed in this paper to resolve the two problems and a simulation study is conducted to testify its improved performance over existing treatments. © 2008 Elsevier Ltd. All rights reserved.
Persistent Identifierhttp://hdl.handle.net/10722/172463
ISSN
2015 Impact Factor: 3.216
2015 SCImago Journal Rankings: 1.629
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorZhao, Jhen_US
dc.contributor.authorYu, PLHen_US
dc.date.accessioned2012-10-30T06:22:39Z-
dc.date.available2012-10-30T06:22:39Z-
dc.date.issued2009en_US
dc.identifier.citationNeural Networks, 2009, v. 22 n. 7, p. 988-997en_US
dc.identifier.issn0893-6080en_US
dc.identifier.urihttp://hdl.handle.net/10722/172463-
dc.description.abstractExisting works on variational bayesian (VB) treatment for factor analysis (FA) model such as [Ghahramani, Z., & Beal, M. (2000). Variational inference for Bayesian mixture of factor analysers. In Advances in neural information proceeding systems. Cambridge, MA: MIT Press; Nielsen, F. B. (2004). Variational approach to factor analysis and related models. Master's thesis, The Institute of Informatics and Mathematical Modelling, Technical University of Denmark.] are found theoretically and empirically to suffer two problems: 1{circled} penalize the model more heavily than BIC and 2{circled} perform unsatisfactorily in low noise cases as redundant factors can not be effectively suppressed. A novel VB treatment is proposed in this paper to resolve the two problems and a simulation study is conducted to testify its improved performance over existing treatments. © 2008 Elsevier Ltd. All rights reserved.en_US
dc.languageengen_US
dc.publisherPergamon. The Journal's web site is located at http://www.elsevier.com/locate/neuneten_US
dc.relation.ispartofNeural Networksen_US
dc.subject.meshAlgorithmsen_US
dc.subject.meshBayes Theoremen_US
dc.subject.meshComputer Simulationen_US
dc.subject.meshHumansen_US
dc.subject.meshNeural Networks (Computer)en_US
dc.subject.meshPattern Recognition, Automateden_US
dc.titleA note on variational Bayesian factor analysisen_US
dc.typeArticleen_US
dc.identifier.emailYu, PLH: plhyu@hkucc.hku.hken_US
dc.identifier.authorityYu, PLH=rp00835en_US
dc.description.naturelink_to_subscribed_fulltexten_US
dc.identifier.doi10.1016/j.neunet.2008.11.002en_US
dc.identifier.pmid19135337-
dc.identifier.scopuseid_2-s2.0-69449103358en_US
dc.identifier.hkuros170575-
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-69449103358&selection=ref&src=s&origin=recordpageen_US
dc.identifier.volume22en_US
dc.identifier.issue7en_US
dc.identifier.spage988en_US
dc.identifier.epage997en_US
dc.identifier.eissn1879-2782-
dc.identifier.isiWOS:000270524500015-
dc.publisher.placeUnited Kingdomen_US
dc.identifier.scopusauthoridZhao, Jh=7410313775en_US
dc.identifier.scopusauthoridYu, PLH=7403599794en_US

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats