Loading…
Asymptotic analysis of Bayesian generalization error with Newton diagram
Statistical learning machines that have singularities in the parameter space, such as hidden Markov models, Bayesian networks, and neural networks, are widely used in the field of information engineering. Singularities in the parameter space determine the accuracy of estimation in the Bayesian scena...
Saved in:
Published in: | Neural networks 2010, Vol.23 (1), p.35-43 |
---|---|
Main Authors: | , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-c435t-ad60649be8d005237452869988b20874141ff065bc9ee11b48de539b622870793 |
---|---|
cites | cdi_FETCH-LOGICAL-c435t-ad60649be8d005237452869988b20874141ff065bc9ee11b48de539b622870793 |
container_end_page | 43 |
container_issue | 1 |
container_start_page | 35 |
container_title | Neural networks |
container_volume | 23 |
creator | Yamazaki, Keisuke Aoyagi, Miki Watanabe, Sumio |
description | Statistical learning machines that have singularities in the parameter space, such as hidden Markov models, Bayesian networks, and neural networks, are widely used in the field of information engineering. Singularities in the parameter space determine the accuracy of estimation in the Bayesian scenario. The Newton diagram in algebraic geometry is recognized as an effective method by which to investigate a singularity. The present paper proposes a new technique to plug the diagram in the Bayesian analysis. The proposed technique allows the generalization error to be clarified and provides a foundation for an efficient model selection. We apply the proposed technique to mixtures of binomial distributions. |
doi_str_mv | 10.1016/j.neunet.2009.07.029 |
format | article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_734163598</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0893608009002007</els_id><sourcerecordid>734163598</sourcerecordid><originalsourceid>FETCH-LOGICAL-c435t-ad60649be8d005237452869988b20874141ff065bc9ee11b48de539b622870793</originalsourceid><addsrcrecordid>eNp9kctr3DAQh0VoSTaP_yAUX0pPdkcP63EppCGPQmgvzVnI8jjVYstbSduw_evrZZf21tPA8P1mhm8IuabQUKDy47qJuI1YGgZgGlANMHNCVlQrUzOl2RuyAm14LUHDGTnPeQ0AUgt-Ss6okYYxUCvyeJN306bMJfjKRTfucsjVPFSf3Q5zcLF6wYjJjeG3K2GOFaY0p-o1lB_VV3wtS6cP7iW56ZK8HdyY8epYL8jz_d3328f66dvDl9ubp9oL3pba9RKkMB3qHqBlXImWaWmM1h0DrQQVdBhAtp03iJR2QvfYctNJxrQCZfgF-XCYu0nzzy3mYqeQPY6jizhvs1VcUMlboxdSHEif5pwTDnaTwuTSzlKwe4V2bQ8K7V6hBWUXhUvs3XHBtpuw_xc6OluA90fAZe_GIbnoQ_7LMcb3P2AL9-nA4aLjV8Bksw8YPfYhoS-2n8P_L_kDTz2QWg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>734163598</pqid></control><display><type>article</type><title>Asymptotic analysis of Bayesian generalization error with Newton diagram</title><source>ScienceDirect Journals</source><creator>Yamazaki, Keisuke ; Aoyagi, Miki ; Watanabe, Sumio</creator><creatorcontrib>Yamazaki, Keisuke ; Aoyagi, Miki ; Watanabe, Sumio</creatorcontrib><description>Statistical learning machines that have singularities in the parameter space, such as hidden Markov models, Bayesian networks, and neural networks, are widely used in the field of information engineering. Singularities in the parameter space determine the accuracy of estimation in the Bayesian scenario. The Newton diagram in algebraic geometry is recognized as an effective method by which to investigate a singularity. The present paper proposes a new technique to plug the diagram in the Bayesian analysis. The proposed technique allows the generalization error to be clarified and provides a foundation for an efficient model selection. We apply the proposed technique to mixtures of binomial distributions.</description><identifier>ISSN: 0893-6080</identifier><identifier>EISSN: 1879-2782</identifier><identifier>DOI: 10.1016/j.neunet.2009.07.029</identifier><identifier>PMID: 19692207</identifier><language>eng</language><publisher>Kidlington: Elsevier Ltd</publisher><subject>Algorithms ; Applied sciences ; Artificial Intelligence ; Automatic Data Processing ; Bayes generalization error ; Bayes Theorem ; Computer science; control theory; systems ; Computer Simulation ; Connectionism. Neural networks ; Exact sciences and technology ; Generalization (Psychology) ; Humans ; Information Storage and Retrieval ; Newton diagram ; Statistical singular models</subject><ispartof>Neural networks, 2010, Vol.23 (1), p.35-43</ispartof><rights>2009 Elsevier Ltd</rights><rights>2015 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c435t-ad60649be8d005237452869988b20874141ff065bc9ee11b48de539b622870793</citedby><cites>FETCH-LOGICAL-c435t-ad60649be8d005237452869988b20874141ff065bc9ee11b48de539b622870793</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>315,786,790,4043,27956,27957,27958</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=22318792$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/19692207$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Yamazaki, Keisuke</creatorcontrib><creatorcontrib>Aoyagi, Miki</creatorcontrib><creatorcontrib>Watanabe, Sumio</creatorcontrib><title>Asymptotic analysis of Bayesian generalization error with Newton diagram</title><title>Neural networks</title><addtitle>Neural Netw</addtitle><description>Statistical learning machines that have singularities in the parameter space, such as hidden Markov models, Bayesian networks, and neural networks, are widely used in the field of information engineering. Singularities in the parameter space determine the accuracy of estimation in the Bayesian scenario. The Newton diagram in algebraic geometry is recognized as an effective method by which to investigate a singularity. The present paper proposes a new technique to plug the diagram in the Bayesian analysis. The proposed technique allows the generalization error to be clarified and provides a foundation for an efficient model selection. We apply the proposed technique to mixtures of binomial distributions.</description><subject>Algorithms</subject><subject>Applied sciences</subject><subject>Artificial Intelligence</subject><subject>Automatic Data Processing</subject><subject>Bayes generalization error</subject><subject>Bayes Theorem</subject><subject>Computer science; control theory; systems</subject><subject>Computer Simulation</subject><subject>Connectionism. Neural networks</subject><subject>Exact sciences and technology</subject><subject>Generalization (Psychology)</subject><subject>Humans</subject><subject>Information Storage and Retrieval</subject><subject>Newton diagram</subject><subject>Statistical singular models</subject><issn>0893-6080</issn><issn>1879-2782</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2010</creationdate><recordtype>article</recordtype><recordid>eNp9kctr3DAQh0VoSTaP_yAUX0pPdkcP63EppCGPQmgvzVnI8jjVYstbSduw_evrZZf21tPA8P1mhm8IuabQUKDy47qJuI1YGgZgGlANMHNCVlQrUzOl2RuyAm14LUHDGTnPeQ0AUgt-Ss6okYYxUCvyeJN306bMJfjKRTfucsjVPFSf3Q5zcLF6wYjJjeG3K2GOFaY0p-o1lB_VV3wtS6cP7iW56ZK8HdyY8epYL8jz_d3328f66dvDl9ubp9oL3pba9RKkMB3qHqBlXImWaWmM1h0DrQQVdBhAtp03iJR2QvfYctNJxrQCZfgF-XCYu0nzzy3mYqeQPY6jizhvs1VcUMlboxdSHEif5pwTDnaTwuTSzlKwe4V2bQ8K7V6hBWUXhUvs3XHBtpuw_xc6OluA90fAZe_GIbnoQ_7LMcb3P2AL9-nA4aLjV8Bksw8YPfYhoS-2n8P_L_kDTz2QWg</recordid><startdate>2010</startdate><enddate>2010</enddate><creator>Yamazaki, Keisuke</creator><creator>Aoyagi, Miki</creator><creator>Watanabe, Sumio</creator><general>Elsevier Ltd</general><general>Elsevier</general><scope>IQODW</scope><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope></search><sort><creationdate>2010</creationdate><title>Asymptotic analysis of Bayesian generalization error with Newton diagram</title><author>Yamazaki, Keisuke ; Aoyagi, Miki ; Watanabe, Sumio</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c435t-ad60649be8d005237452869988b20874141ff065bc9ee11b48de539b622870793</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2010</creationdate><topic>Algorithms</topic><topic>Applied sciences</topic><topic>Artificial Intelligence</topic><topic>Automatic Data Processing</topic><topic>Bayes generalization error</topic><topic>Bayes Theorem</topic><topic>Computer science; control theory; systems</topic><topic>Computer Simulation</topic><topic>Connectionism. Neural networks</topic><topic>Exact sciences and technology</topic><topic>Generalization (Psychology)</topic><topic>Humans</topic><topic>Information Storage and Retrieval</topic><topic>Newton diagram</topic><topic>Statistical singular models</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yamazaki, Keisuke</creatorcontrib><creatorcontrib>Aoyagi, Miki</creatorcontrib><creatorcontrib>Watanabe, Sumio</creatorcontrib><collection>Pascal-Francis</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>Neural networks</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yamazaki, Keisuke</au><au>Aoyagi, Miki</au><au>Watanabe, Sumio</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Asymptotic analysis of Bayesian generalization error with Newton diagram</atitle><jtitle>Neural networks</jtitle><addtitle>Neural Netw</addtitle><date>2010</date><risdate>2010</risdate><volume>23</volume><issue>1</issue><spage>35</spage><epage>43</epage><pages>35-43</pages><issn>0893-6080</issn><eissn>1879-2782</eissn><notes>ObjectType-Article-1</notes><notes>SourceType-Scholarly Journals-1</notes><notes>ObjectType-Feature-2</notes><notes>content type line 23</notes><abstract>Statistical learning machines that have singularities in the parameter space, such as hidden Markov models, Bayesian networks, and neural networks, are widely used in the field of information engineering. Singularities in the parameter space determine the accuracy of estimation in the Bayesian scenario. The Newton diagram in algebraic geometry is recognized as an effective method by which to investigate a singularity. The present paper proposes a new technique to plug the diagram in the Bayesian analysis. The proposed technique allows the generalization error to be clarified and provides a foundation for an efficient model selection. We apply the proposed technique to mixtures of binomial distributions.</abstract><cop>Kidlington</cop><pub>Elsevier Ltd</pub><pmid>19692207</pmid><doi>10.1016/j.neunet.2009.07.029</doi><tpages>9</tpages></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0893-6080 |
ispartof | Neural networks, 2010, Vol.23 (1), p.35-43 |
issn | 0893-6080 1879-2782 |
language | eng |
recordid | cdi_proquest_miscellaneous_734163598 |
source | ScienceDirect Journals |
subjects | Algorithms Applied sciences Artificial Intelligence Automatic Data Processing Bayes generalization error Bayes Theorem Computer science control theory systems Computer Simulation Connectionism. Neural networks Exact sciences and technology Generalization (Psychology) Humans Information Storage and Retrieval Newton diagram Statistical singular models |
title | Asymptotic analysis of Bayesian generalization error with Newton diagram |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-21T20%3A24%3A07IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Asymptotic%20analysis%20of%20Bayesian%20generalization%20error%20with%20Newton%20diagram&rft.jtitle=Neural%20networks&rft.au=Yamazaki,%20Keisuke&rft.date=2010&rft.volume=23&rft.issue=1&rft.spage=35&rft.epage=43&rft.pages=35-43&rft.issn=0893-6080&rft.eissn=1879-2782&rft_id=info:doi/10.1016/j.neunet.2009.07.029&rft_dat=%3Cproquest_cross%3E734163598%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c435t-ad60649be8d005237452869988b20874141ff065bc9ee11b48de539b622870793%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=734163598&rft_id=info:pmid/19692207&rfr_iscdi=true |