Multistep sequential exploration of growing Bayesian classification models
If the collection of training data is costly, one can gain by actively selecting particular informative data points in a sequential way. In a Bayesian decision theoretic framework we develop a query selection criterion for classification models which explicitly takes into account the utility of deci...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 571 vol.3 |
|---|---|
| container_issue | |
| container_start_page | 566 |
| container_title | |
| container_volume | 3 |
| creator | Paass, C. Kindermann, J. |
| description | If the collection of training data is costly, one can gain by actively selecting particular informative data points in a sequential way. In a Bayesian decision theoretic framework we develop a query selection criterion for classification models which explicitly takes into account the utility of decisions. We determine the overall utility and its derivative with respect to changes of the queries. An optimal query now may be obtained by stochastic hill climbing. Simultaneously, the model structure can be adapted by reversible jump Markov chain Monte Carlo. |
| doi_str_mv | 10.1109/IJCNN.2000.861371 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_861371</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>861371</ieee_id><sourcerecordid>861371</sourcerecordid><originalsourceid>FETCH-LOGICAL-i172t-2ed35c36371b96952ca521e864054373241c138d94d8599453ff52c47ded50173</originalsourceid><addsrcrecordid>eNotkMlOwzAURS0GiarkA2CVH0jw8-wlRAytStnAujLxS2XkJiFOBf17IoXVXdxBR5eQG6AlALV3q3W13ZaMUloaBVzDGVmAlKbglrJzklltqFZWUgVWX0wetabQUqsrkqX0NfWAcqkYLMj69RjHkEbs84TfR2zH4GKOv33sBjeGrs27Jt8P3U9o9_mDO2EKrs3r6FIKTajnyKHzGNM1uWxcTJj965J8PD2-Vy_F5u15Vd1vigCajQVDz2XN1YT9aSdIVjvJAI0SVAquORNQAzfeCm-ktULypplCQnv0koLmS3I77wZE3PVDOLjhtJuP4H9ic09L</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Multistep sequential exploration of growing Bayesian classification models</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Paass, C. ; Kindermann, J.</creator><creatorcontrib>Paass, C. ; Kindermann, J.</creatorcontrib><description>If the collection of training data is costly, one can gain by actively selecting particular informative data points in a sequential way. In a Bayesian decision theoretic framework we develop a query selection criterion for classification models which explicitly takes into account the utility of decisions. We determine the overall utility and its derivative with respect to changes of the queries. An optimal query now may be obtained by stochastic hill climbing. Simultaneously, the model structure can be adapted by reversible jump Markov chain Monte Carlo.</description><identifier>ISSN: 1098-7576</identifier><identifier>ISBN: 9780769506197</identifier><identifier>ISBN: 0769506194</identifier><identifier>EISSN: 1558-3902</identifier><identifier>DOI: 10.1109/IJCNN.2000.861371</identifier><language>eng</language><publisher>IEEE</publisher><subject>Bayesian methods ; Design for experiments ; Laboratories ; Monte Carlo methods ; Neural networks ; Sampling methods ; Simulated annealing ; Stochastic processes ; Training data ; Utility theory</subject><ispartof>Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium, 2000, Vol.3, p.566-571 vol.3</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/861371$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,777,781,786,787,2052,4036,4037,27906,54901</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/861371$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Paass, C.</creatorcontrib><creatorcontrib>Kindermann, J.</creatorcontrib><title>Multistep sequential exploration of growing Bayesian classification models</title><title>Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium</title><addtitle>IJCNN</addtitle><description>If the collection of training data is costly, one can gain by actively selecting particular informative data points in a sequential way. In a Bayesian decision theoretic framework we develop a query selection criterion for classification models which explicitly takes into account the utility of decisions. We determine the overall utility and its derivative with respect to changes of the queries. An optimal query now may be obtained by stochastic hill climbing. Simultaneously, the model structure can be adapted by reversible jump Markov chain Monte Carlo.</description><subject>Bayesian methods</subject><subject>Design for experiments</subject><subject>Laboratories</subject><subject>Monte Carlo methods</subject><subject>Neural networks</subject><subject>Sampling methods</subject><subject>Simulated annealing</subject><subject>Stochastic processes</subject><subject>Training data</subject><subject>Utility theory</subject><issn>1098-7576</issn><issn>1558-3902</issn><isbn>9780769506197</isbn><isbn>0769506194</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2000</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotkMlOwzAURS0GiarkA2CVH0jw8-wlRAytStnAujLxS2XkJiFOBf17IoXVXdxBR5eQG6AlALV3q3W13ZaMUloaBVzDGVmAlKbglrJzklltqFZWUgVWX0wetabQUqsrkqX0NfWAcqkYLMj69RjHkEbs84TfR2zH4GKOv33sBjeGrs27Jt8P3U9o9_mDO2EKrs3r6FIKTajnyKHzGNM1uWxcTJj965J8PD2-Vy_F5u15Vd1vigCajQVDz2XN1YT9aSdIVjvJAI0SVAquORNQAzfeCm-ktULypplCQnv0koLmS3I77wZE3PVDOLjhtJuP4H9ic09L</recordid><startdate>2000</startdate><enddate>2000</enddate><creator>Paass, C.</creator><creator>Kindermann, J.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>2000</creationdate><title>Multistep sequential exploration of growing Bayesian classification models</title><author>Paass, C. ; Kindermann, J.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i172t-2ed35c36371b96952ca521e864054373241c138d94d8599453ff52c47ded50173</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2000</creationdate><topic>Bayesian methods</topic><topic>Design for experiments</topic><topic>Laboratories</topic><topic>Monte Carlo methods</topic><topic>Neural networks</topic><topic>Sampling methods</topic><topic>Simulated annealing</topic><topic>Stochastic processes</topic><topic>Training data</topic><topic>Utility theory</topic><toplevel>online_resources</toplevel><creatorcontrib>Paass, C.</creatorcontrib><creatorcontrib>Kindermann, J.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Paass, C.</au><au>Kindermann, J.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Multistep sequential exploration of growing Bayesian classification models</atitle><btitle>Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium</btitle><stitle>IJCNN</stitle><date>2000</date><risdate>2000</risdate><volume>3</volume><spage>566</spage><epage>571 vol.3</epage><pages>566-571 vol.3</pages><issn>1098-7576</issn><eissn>1558-3902</eissn><isbn>9780769506197</isbn><isbn>0769506194</isbn><abstract>If the collection of training data is costly, one can gain by actively selecting particular informative data points in a sequential way. In a Bayesian decision theoretic framework we develop a query selection criterion for classification models which explicitly takes into account the utility of decisions. We determine the overall utility and its derivative with respect to changes of the queries. An optimal query now may be obtained by stochastic hill climbing. Simultaneously, the model structure can be adapted by reversible jump Markov chain Monte Carlo.</abstract><pub>IEEE</pub><doi>10.1109/IJCNN.2000.861371</doi></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1098-7576 |
| ispartof | Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium, 2000, Vol.3, p.566-571 vol.3 |
| issn | 1098-7576 1558-3902 |
| language | eng |
| recordid | cdi_ieee_primary_861371 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Bayesian methods Design for experiments Laboratories Monte Carlo methods Neural networks Sampling methods Simulated annealing Stochastic processes Training data Utility theory |
| title | Multistep sequential exploration of growing Bayesian classification models |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-20T00%3A32%3A11IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Multistep%20sequential%20exploration%20of%20growing%20Bayesian%20classification%20models&rft.btitle=Proceedings%20of%20the%20IEEE-INNS-ENNS%20International%20Joint%20Conference%20on%20Neural%20Networks.%20IJCNN%202000.%20Neural%20Computing:%20New%20Challenges%20and%20Perspectives%20for%20the%20New%20Millennium&rft.au=Paass,%20C.&rft.date=2000&rft.volume=3&rft.spage=566&rft.epage=571%20vol.3&rft.pages=566-571%20vol.3&rft.issn=1098-7576&rft.eissn=1558-3902&rft.isbn=9780769506197&rft.isbn_list=0769506194&rft_id=info:doi/10.1109/IJCNN.2000.861371&rft_dat=%3Cieee_6IE%3E861371%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=861371&rfr_iscdi=true |