{"id":{"repo_id":"odu","oai_identifier":"oai:digitalcommons.odu.edu:computerscience_etds-1168"},"canonical_url":"https://search.ndltd.org/etd/odu/oai:digitalcommons.odu.edu:computerscience_etds-1168","repository":{"repo_id":"odu","name":"Old Dominion University","base_url":"https://digitalcommons.odu.edu/do/oai/"},"display":{"title":"Multiple Learner Systems Using Resampling Methods","abstract":"The N-Learners Problem deals with combining a number of learners such that the resultant system is \"better\", under some criterion, than the best of the individual learners. We consider a system of probably approximately correct concept learners. Depending on the available information, there are several methods to make the composite system better than the best of the individual learners. If a sample and an oracle that generates data points (but, not their classification) is available, then we show that we can achieve arbitrary levels of the normalized confidence of the composite system if (a) a robust learning algorithm is available, and (b) the hypothesis space of the fuser is \"sufficiently rich\". Our method consists of generating a suitable number of pseudo examples, and then performing another step of learning using the sample and the pseudo examples. This method, by restriction, can be used to boost the performance of a single PAC learner. Pseudo examples are generated by producing data points using the oracle and classifying them using the composite system.","abstract_html":"The N-Learners Problem deals with combining a number of learners such that the resultant system is &quot;better&quot;, under some criterion, than the best of the individual learners. We consider a system of probably approximately correct concept learners. Depending on the available information, there are several methods to make the composite system better than the best of the individual learners. If a sample and an oracle that generates data points (but, not their classification) is available, then we show that we can achieve arbitrary levels of the normalized confidence of the composite system if (a) a robust learning algorithm is available, and (b) the hypothesis space of the fuser is &quot;sufficiently rich&quot;. Our method consists of generating a suitable number of pseudo examples, and then performing another step of learning using the sample and the pseudo examples. This method, by restriction, can be used to boost the performance of a single PAC learner. Pseudo examples are generated by producing data points using the oracle and classifying them using the composite system.","abstract_has_math":false,"creators":["Xie, Binyun"],"institution":null,"degree_name":"Master of Science (MS)","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Nageswara S. V. Rao","Ravi Mukkamala","Larry Wilson"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:29:47Z","subjects":["Learning","Mathematical models","Machine learning","Numerical Analysis and Scientific Computing","Theory and Algorithms"],"languages":[],"rights":["<p>In Copyright. URI: <a href=\"http://rightsstatements.org/vocab/InC/1.0/\">http://rightsstatements.org/vocab/InC/1.0/</a> This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).</p>"],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.odu.edu/computerscience_etds/165","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.odu.edu/computerscience_etds/165","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.odu.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.odu.edu%3Acomputerscience_etds-1168","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Nageswara S. V. Rao","Ravi Mukkamala","Larry Wilson"]},{"key":"dc:creator","label":"Author","values":["Xie, Binyun"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2023-10-26T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["1992-08-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Learning","Mathematical models","Machine learning","Numerical Analysis and Scientific Computing","Theory and Algorithms"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["<p>In Copyright. URI: <a href=\"http://rightsstatements.org/vocab/InC/1.0/\">http://rightsstatements.org/vocab/InC/1.0/</a> This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).</p>"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.odu.edu/computerscience_etds/165"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The N-Learners Problem deals with combining a number of learners such that the resultant system is \"better\", under some criterion, than the best of the individual learners. We consider a system of probably approximately correct concept learners. Depending on the available information, there are several methods to make the composite system better than the best of the individual learners. If a sample and an oracle that generates data points (but, not their classification) is available, then we show that we can achieve arbitrary levels of the normalized confidence of the composite system if (a) a robust learning algorithm is available, and (b) the hypothesis space of the fuser is \"sufficiently rich\". Our method consists of generating a suitable number of pseudo examples, and then performing another step of learning using the sample and the pseudo examples. This method, by restriction, can be used to boost the performance of a single PAC learner. Pseudo examples are generated by producing data points using the oracle and classifying them using the composite system."]},{"key":"dc:title","label":"Title","values":["Multiple Learner Systems Using Resampling Methods"]}]}],"canonical_facts":{"dc:contributor":["Nageswara S. V. Rao","Ravi Mukkamala","Larry Wilson"],"dc:creator":["Xie, Binyun"],"dc:date.available":["2023-10-26T07:00:00Z"],"dc:date.created":["1992-08-01T07:00:00Z"],"dc:description.abstract":["The N-Learners Problem deals with combining a number of learners such that the resultant system is \"better\", under some criterion, than the best of the individual learners. We consider a system of probably approximately correct concept learners. Depending on the available information, there are several methods to make the composite system better than the best of the individual learners. If a sample and an oracle that generates data points (but, not their classification) is available, then we show that we can achieve arbitrary levels of the normalized confidence of the composite system if (a) a robust learning algorithm is available, and (b) the hypothesis space of the fuser is \"sufficiently rich\". Our method consists of generating a suitable number of pseudo examples, and then performing another step of learning using the sample and the pseudo examples. This method, by restriction, can be used to boost the performance of a single PAC learner. Pseudo examples are generated by producing data points using the oracle and classifying them using the composite system."],"dc:identifier":["https://digitalcommons.odu.edu/computerscience_etds/165"],"dc:rights":["<p>In Copyright. URI: <a href=\"http://rightsstatements.org/vocab/InC/1.0/\">http://rightsstatements.org/vocab/InC/1.0/</a> This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).</p>"],"dc:subject":["Learning","Mathematical models","Machine learning","Numerical Analysis and Scientific Computing","Theory and Algorithms"],"dc:title":["Multiple Learner Systems Using Resampling Methods"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T08:29:47Z"}